Hyperspectral Imaging (HSI) Has Emerged As A Powerful Remote Sensing Technique Due To Its Ability To Capture Detailed Spectral Information Across Hundreds Of Narrow And Contiguous Wavelength Bands. This Rich Spectral Resolution Enables Precise Identification And Discrimination Of Surface Materials, Which Is Critical In Applications Such As Agriculture, Mineral Exploration, Environmental Monitoring, And Defense. Traditional Classification Methods Often Face Challenges In Handling The High Dimensionality And Spectral Similarity Inherent In Hyperspectral Data. To Address This, Maximum Abundance Classification (MAC) Is Employed As An Effective Technique For Hyperspectral Image Analysis. MAC Is Based On Spectral Unmixing, Where Each Pixel Is Represented As A Mixture Of Multiple Endmembers, And Classification Is Performed By Assigning A Pixel To The Class Corresponding To The Endmember With The Highest Abundance Fraction. This Method Not Only Improves Classification Accuracy But Also Provides Insights Into The Sub-pixel Composition Of Heterogeneous Regions. The Proposed Work Focuses On Implementing MAC For Hyperspectral Image Datasets, Highlighting Its Effectiveness In Resolving Mixed Pixels And Enhancing Material Discrimination Compared To Conventional Pixel-based Classifiers. The Results Demonstrate That Maximum Abundance Classification Offers A Robust Approach For Extracting Meaningful Information From Hyperspectral Images, Making It Highly Suitable For Real-world Remote Sensing Applications.
Apple Production Plays A Vital Role In Global Horticulture, But Its Yield And Quality Are Often Threatened By Various Leaf Diseases Such As Apple Scab, Powdery Mildew, And Rust. Early And Accurate Detection Of These Diseases Is Crucial For Effective Management And Prevention. Traditional Manual Inspection Methods Are Time-consuming, Labor-intensive, And Prone To Human Error, While Conventional Machine Learning Techniques Often Lack Robustness And Generalization Ability In Complex Field Environments. To Address These Challenges, This Study Proposes An Apple Leaf Disease Detection Algorithm Based On An Improved YOLOv8 Model. The Enhanced Framework Integrates Optimized Feature Extraction Modules, Multi-scale Attention Mechanisms, And Lightweight Convolutional Operations To Improve Detection Accuracy While Reducing Computational Complexity. The Proposed Model Is Trained And Validated On A Large Dataset Of Apple Leaf Images Under Varying Conditions Of Illumination, Occlusion, And Background Interference. Experimental Results Demonstrate That The Improved YOLOv8 Achieves Higher Precision, Recall, And Mean Average Precision (mAP) Compared To The Baseline YOLOv8 And Other State-of-the-art Object Detection Models. This Approach Provides An Efficient And Reliable Solution For Real-time Apple Leaf Disease Detection, Offering Significant Potential For Precision Agriculture And Intelligent Crop Management Systems.
Age And Gender Prediction Using Facial Images Has Gained Significant Attention In Recent Years Due To Its Wide Range Of Applications In Fields Such As Human–computer Interaction, Security, Personalized Marketing, And Social Media Analytics. Traditional Computer Vision Techniques Often Struggle To Achieve High Accuracy Because Of Variations In Pose, Illumination, Facial Expressions, And Occlusions. To Overcome These Challenges, This Study Employs Deep Learning Models That Automatically Learn Discriminative Features From Raw Images Without Requiring Handcrafted Descriptors. Convolutional Neural Networks (CNNs) And Advanced Architectures Such As Residual Networks (ResNet) And Vision Transformers (ViT) Are Utilized For Robust Feature Extraction And Classification. The Models Are Trained And Validated On Benchmark Facial Image Datasets, Enabling The System To Predict Both Age Groups And Gender With High Precision. Experimental Results Demonstrate That Deep Learning–based Approaches Outperform Conventional Methods In Terms Of Accuracy, Generalization, And Scalability. The Proposed Framework Can Be Integrated Into Real-world Applications, Offering Reliable And Efficient Solutions For Automated Demographic Analysis.
White Blood Cells (WBCs) Play A Vital Role In The Immune System, And Abnormalities In Their Morphology And Distribution Are Key Indicators Of Blood Disorders Such As Leukemia. Early And Accurate Detection Of Leukemic Cells Is Critical For Effective Treatment And Improved Patient Outcomes. Traditional Manual Examination Of Blood Smears Under A Microscope Is Time-consuming, Prone To Human Error, And Requires Significant Expertise. To Address These Limitations, This Study Proposes An Automated System For Classifying Leukemic Blood Images Using Deep Learning And Image Processing Techniques. The Approach Involves Preprocessing Of Microscopic Blood Images To Enhance Quality, Followed By Segmentation Methods To Isolate WBCs From The Background. Feature Extraction Is Then Performed To Capture Both Morphological And Texture Characteristics. A Convolutional Neural Network (CNN) Model Is Employed To Automatically Learn Discriminative Features And Classify WBCs Into Normal Or Leukemic Categories. The Proposed Method Aims To Achieve High Accuracy, Robustness, And Efficiency In Leukemic Cell Detection, Thereby Supporting Hematologists In Clinical Diagnosis. This Research Highlights The Potential Of Integrating Deep Learning With Image Processing To Develop Computer-aided Diagnostic Tools For Leukemia Screening.
Rice Is One Of The Most Important Staple Crops Worldwide, And Its Productivity Is Often Threatened By Various Leaf Diseases Such As Bacterial Blight, Blast, And Brown Spot. Early And Accurate Identification Of These Diseases Is Crucial For Effective Crop Management And Yield Improvement. Traditional Disease Detection Methods, Which Rely On Manual Field Inspection, Are Time-consuming, Labor-intensive, And Prone To Human Error. To Overcome These Limitations, This Study Proposes An Automated Rice Leaf Disease Prediction System Based On MobileNetV2, A Lightweight Deep Learning Model Optimized For Mobile And Embedded Devices. The Model Leverages Transfer Learning To Extract Discriminative Features From Rice Leaf Images And Classify Them Into Healthy Or Diseased Categories. MobileNetV2’s Efficient Architecture Significantly Reduces Computational Cost While Maintaining High Classification Accuracy, Making It Suitable For Real-time Deployment In Agricultural Environments. Experimental Results Demonstrate That The Proposed System Achieves Robust Performance With High Accuracy, Precision, And Recall, Thereby Offering A Reliable And Scalable Solution For Smart Farming. This Work Highlights The Potential Of Integrating Deep Learning With Mobile Technologies To Support Farmers In Disease Monitoring And Decision-making, Ultimately Contributing To Sustainable Agriculture.
Jute Is An Economically Significant Natural Fiber Crop Widely Cultivated In Many Parts Of The World, Particularly In South Asia. However, Its Productivity And Fiber Quality Are Often Threatened By Various Foliar Diseases, Including Stem Rot, Anthracnose, And Leaf Blight, Which Can Cause Severe Yield Losses If Not Detected At An Early Stage. Traditional Methods Of Disease Identification, Which Rely On Manual Field Inspection, Are Labor-intensive, Time-consuming, And Prone To Human Error. To Address These Challenges, This Study Proposes A Deep Learning–based Automated System For Jute Leaf Disease Detection Using The ResNet50 Architecture. ResNet50, A Powerful Convolutional Neural Network (CNN), Is Employed To Extract High-level Discriminative Features From Leaf Images, Enabling Robust Classification Of Healthy And Diseased Leaves. The Model Is Trained And Validated On A Dataset Of Jute Leaf Images, Incorporating Preprocessing And Data Augmentation Techniques To Improve Generalization. Experimental Results Demonstrate That The Proposed Approach Achieves High Accuracy, Precision, And Recall, Making It Suitable For Real-time Deployment In Precision Agriculture. By Enabling Early Detection And Accurate Classification Of Jute Leaf Diseases, This System Can Assist Farmers In Taking Timely Remedial Actions, Thereby Enhancing Crop Yield, Reducing Economic Losses, And Promoting Sustainable Agricultural Practices.
The Accurate Classification Of Pharmaceutical Drugs And Vitamins Plays A Vital Role In Ensuring Patient Safety, Preventing Medication Errors, And Supporting Effective Healthcare Delivery. Traditional Methods Of Drug Identification Often Rely On Manual Inspection Of Physical Features Such As Shape, Size, And Imprint, Which Are Time-consuming, Prone To Human Error, And Impractical For Large-scale Applications. To Overcome These Limitations, This Study Proposes A Deep Learning–based Automated Classification System That Leverages Convolutional Neural Networks (CNNs) Combined With Transfer Learning Techniques. Pretrained CNN Architectures Such As ResNet, VGG, And Inception Are Utilized To Extract Discriminative Visual Features From Drug And Vitamin Images, Significantly Reducing Training Complexity While Improving Classification Accuracy. The Proposed System Is Trained On A Curated Dataset Of Pharmaceutical Drug And Vitamin Images, With Preprocessing And Augmentation Techniques Applied To Enhance Generalization Across Varying Lighting And Imaging Conditions. Experimental Results Demonstrate That The Transfer Learning–based CNN Models Outperform Traditional Machine Learning Methods By Achieving High Accuracy, Precision, And Recall. The System Has Strong Potential For Real-world Applications In Healthcare And Pharmacy Sectors, Such As Mobile-based Drug Recognition Tools, Automated Pill Dispensers, And Intelligent Healthcare Management Systems. By Ensuring Reliable Classification And Reducing The Chances Of Medication Errors, The Proposed Approach Contributes To Safer, More Efficient, And Technology-driven Healthcare Practices.
Potato Is One Of The Most Widely Cultivated Food Crops Worldwide, Yet Its Productivity Is Severely Threatened By Leaf Diseases Such As Early Blight, Late Blight, And Leaf Spot. Early And Accurate Detection Of These Diseases Is Crucial For Minimizing Yield Loss And Supporting Sustainable Agricultural Practices. Traditional Disease Diagnosis Methods Rely Heavily On Manual Field Inspection, Which Is Time-consuming, Labor-intensive, And Prone To Human Error. Recent Advances In Deep Learning Have Demonstrated Significant Potential In Automating Plant Disease Detection By Extracting Discriminative Features Directly From Image Data. This Study Presents A Comparative Analysis Of Multiple Deep Learning Architectures, Including Convolutional Neural Networks (cnns), Vgg16, Resnet50, And Mobilenetv2, For Potato Leaf Disease Detection. The Models Were Trained And Evaluated On Publicly Available Datasets, And Their Performance Was Compared In Terms Of Accuracy, Precision, Recall, F1-score, And Computational Efficiency. Experimental Results Highlight That Transfer Learning–based Models Outperform Traditional Cnns By Achieving Higher Accuracy And Faster Convergence. Among The Evaluated Models, Resnet50 And Mobilenetv2 Demonstrated Superior Performance, Balancing Both Accuracy And Lightweight Computation, Making Them Suitable For Real-time Field Deployment. The Findings Of This Study Emphasize The Importance Of Model Selection In Building Robust Disease Detection Systems And Provide Valuable Insights For Developing Practical, Ai-driven Tools To Assist Farmers And Agronomists In Precision Agriculture.
Forest Fires Are One Of The Most Destructive Natural Disasters, Causing Significant Ecological Damage, Economic Loss, And Threats To Human Life. Early Detection And Accurate Classification Of Forest Fire Incidents Are Crucial For Effective Fire Management And Mitigation Strategies. Traditional Fire Monitoring Systems, Which Rely On Manual Observation And Sensor-based Techniques, Are Often Time-consuming, Expensive, And Limited In Scalability. Recent Advancements In Machine Learning (ML) And Deep Learning (DL) Have Opened New Opportunities For Automated Forest Fire Detection Using Image Classification Techniques. In This Study, We Propose A Comparative Framework For Classifying Forest Fire Images Using Both Traditional Machine Learning Algorithms And Deep Learning Architectures Such As Convolutional Neural Networks (CNNs). Machine Learning Models Are Employed With Handcrafted Features, While Deep Learning Approaches Automatically Extract Discriminative Spatial Features From Raw Images. The Performance Of Different Models Is Evaluated Using Accuracy, Precision, Recall, And F1-score Metrics On Benchmark Datasets. Experimental Results Demonstrate That Deep Learning Methods Significantly Outperform Traditional Machine Learning Techniques In Terms Of Classification Accuracy And Robustness, Particularly Under Complex Environmental Conditions. The Findings Highlight The Potential Of Deep Learning–based Image Classification Systems As Effective Tools For Real-time Forest Fire Detection, Supporting Rapid Response And Disaster Management Efforts.
Chili (Capsicum Spp.) Is One Of The Most Widely Cultivated Spice Crops, Playing A Vital Role In Global Agriculture And The Food Industry. However, Its Productivity Is Significantly Threatened By Various Leaf Diseases Such As Leaf Spot, Mosaic, And Curl, Which Lead To Reduced Yield And Economic Losses. Early And Accurate Identification Of These Diseases Is Essential For Effective Crop Management And Disease Control. Traditional Diagnostic Methods, Which Rely On Manual Field Inspection, Are Often Time-consuming, Labor-intensive, And Prone To Human Error. To Overcome These Limitations, This Study Proposes An Automated Chili Leaf Classification System Using Deep Learning Techniques. Convolutional Neural Networks (CNNs) And Transfer Learning Models Are Employed To Automatically Extract Discriminative Features From Chili Leaf Images, Enabling Precise Classification Of Healthy And Diseased Samples. The Proposed Approach Demonstrates High Accuracy And Robustness Compared To Conventional Machine Learning Methods, Making It A Scalable And Efficient Solution For Real-time Disease Monitoring. The Findings Of This Study Highlight The Potential Of Deep Learning–based Classification Systems To Support Farmers And Agricultural Stakeholders In Improving Chili Crop Productivity Through Timely Disease Detection And Management.
Coffee Is One Of The Most Important Commercial Crops Worldwide, Contributing Significantly To The Global Economy And Agricultural Livelihoods. However, Its Productivity Is Severely Threatened By Various Leaf Diseases Such As Coffee Leaf Rust, Cercospora Leaf Spot, And Coffee Berry Disease, Which Lead To Substantial Yield Losses And Reduced Bean Quality. Early And Accurate Detection Of These Diseases Is Crucial For Effective Crop Management And Sustainable Coffee Production. Traditional Disease Diagnosis Methods Rely On Manual Inspection, Which Is Labor-intensive, Time-consuming, And Often Prone To Human Error. To Address These Challenges, This Study Proposes An Automated Coffee Leaf Disease Detection System Using Deep Learning Algorithms. Convolutional Neural Networks (CNNs) And Transfer Learning Models Such As VGG16, ResNet50, And MobileNetV2 Are Employed To Extract Discriminative Features From Leaf Images And Classify Them Into Healthy And Diseased Categories. The Proposed Approach Enhances Accuracy, Reduces Dependency On Expert Knowledge, And Enables Real-time Disease Monitoring. Experimental Results Demonstrate That Deep Learning–based Models Outperform Conventional Methods, Achieving High Precision, Recall, And Overall Classification Accuracy. This Study Highlights The Potential Of AI-driven Solutions In Supporting Precision Agriculture And Ensuring The Sustainable Cultivation Of Coffee.
Nail Diseases, Including Fungal Infections, Psoriasis, And Onycholysis, Are Common Health Concerns That Affect Both Aesthetics And Overall Well-being. Traditional Diagnostic Methods Rely Heavily On Visual Inspection And Clinical Expertise, Which Are Often Subjective, Time-consuming, And Prone To Human Error. With The Rapid Advancements In Artificial Intelligence, Deep Learning Has Emerged As A Powerful Tool For Automated Medical Image Analysis. This Study Proposes SMART Diagnosis, A Deep Learning–based System Designed To Accurately Identify And Classify Various Nail Diseases From Digital Images. By Leveraging Convolutional Neural Networks (CNNs) And Transfer Learning Techniques, The System Can Extract Discriminative Features From Nail Images, Enabling Precise Disease Classification. The Proposed Model Aims To Assist Dermatologists In Early And Reliable Diagnosis, Reduce Diagnostic Errors, And Provide Scalable Solutions For Telemedicine Applications. Experimental Results Demonstrate High Accuracy And Robustness, Highlighting The Potential Of SMART Diagnosis To Transform Nail Disease Identification Into A Faster, More Accurate, And Accessible Process, Ultimately Improving Patient Care And Health Outcomes.
Livestock Health Plays A Critical Role In Ensuring Sustainable Dairy And Meat Production, Yet Early Detection Of Sickness In Cows Remains A Major Challenge For Farmers. Traditional Methods Of Disease Monitoring Rely On Manual Observation Of Behavioral And Physical Changes, Which Are Often Subjective, Time-consuming, And Prone To Human Error. With Advancements In Artificial Intelligence, Machine Learning (ML) And Deep Learning (DL) Techniques Provide Promising Solutions For Automated Health Monitoring. This Study Proposes An Intelligent System For The Early Detection Of Sickness In Cows By Analyzing Behavioral Patterns, Physiological Parameters, And Visual Features Extracted From Images And Sensor Data. Various ML Algorithms, Including Support Vector Machines (SVM) And Random Forest, Are Compared With State-of-the-art DL Models Such As Convolutional Neural Networks (CNNs) And Long Short-Term Memory (LSTM) Networks For Time-series Data. The Results Demonstrate That Deep Learning Models Achieve Superior Accuracy In Identifying Subtle Patterns Of Illness, Enabling Timely Intervention And Reducing Economic Losses. The Proposed Approach Highlights The Potential Of AI-driven Livestock Monitoring Systems To Support Farmers In Enhancing Animal Welfare, Optimizing Productivity, And Ensuring Food Security.
Osteoarthritis (OA) Is One Of The Most Common Degenerative Joint Diseases, Primarily Affecting The Knee Joint And Leading To Pain, Stiffness, And Reduced Mobility. Early And Accurate Prediction Of OA Progression Is Crucial For Timely Intervention, Improved Patient Outcomes, And Reduced Healthcare Costs. Traditional Diagnostic Methods, Such As Clinical Examination And Radiographic Analysis, Are Often Subjective, Time-consuming, And Limited In Their Ability To Detect Subtle Pathological Changes. With Recent Advancements In Artificial Intelligence, Deep Learning (DL) Techniques Have Emerged As Powerful Tools For Automated Medical Image Analysis. This Study Proposes A Deep Learning–based Framework For The Prediction Of Osteoarthritis In Knee Joints Using Radiographic And MRI Data. Convolutional Neural Networks (CNNs) Are Employed To Automatically Extract Discriminative Features From Knee Images, Enabling Precise Detection And Grading Of OA Severity. The System Is Designed To Assist Clinicians By Providing Objective, Reliable, And Rapid Predictions, Thereby Reducing Diagnostic Errors And Supporting Personalized Treatment Planning. The Proposed Approach Demonstrates The Potential Of Deep Learning In Advancing Computer-aided Diagnosis And Improving The Early Prediction And Management Of Knee Osteoarthritis.
Kidney Anomalies, Including Cysts, Tumors, And Structural Abnormalities, Are Among The Leading Causes Of Renal Dysfunction And Can Progress To Severe Chronic Kidney Disease If Not Diagnosed Early. Traditional Diagnostic Methods, Such As Ultrasound And CT Scan Interpretation, Rely Heavily On Radiologists’ Expertise, Making Them Time-consuming, Subjective, And Prone To Human Error. With Recent Advancements In Artificial Intelligence, Deep Learning (DL) Has Emerged As A Powerful Tool For Automated Medical Image Analysis, Offering High Accuracy In Detecting Subtle Pathological Changes. This Study Proposes An Intelligent Framework For Automated Kidney Anomaly Detection Using Deep Learning Models Integrated With Explainable AI (XAI) Techniques. The DL Models Are Trained On Medical Imaging Datasets To Identify And Classify Kidney Anomalies With Improved Precision, While XAI Methods, Such As Grad-CAM And SHAP, Provide Visual And Interpretable Explanations Of Model Decisions. This Combination Not Only Enhances The Transparency And Reliability Of AI-driven Diagnostics But Also Assists Clinicians In Making Informed Decisions. The Proposed System Demonstrates Significant Potential In Early Detection, Reduced Diagnostic Workload, And Improved Patient Outcomes, Paving The Way For Trustworthy And Clinically Applicable AI Solutions In Nephrology.
Monkeypox, An Emerging Zoonotic Viral Disease, Has Recently Re-emerged As A Global Health Concern Due To Its Rapid Transmission And Clinical Similarity To Other Skin-related Infections. Early And Accurate Diagnosis Is Essential For Effective Containment And Treatment, Yet Traditional Diagnostic Methods Such As Polymerase Chain Reaction (PCR) Testing And Clinical Evaluation Are Time-consuming, Costly, And Require Expert Resources That Are Often Unavailable In Low-resource Settings. With The Advancement Of Artificial Intelligence, Deep Learning (DL) Has Shown Remarkable Potential In The Automated Diagnosis Of Infectious Diseases From Medical Images, Particularly Skin Lesion Analysis. This Survey Provides A Comprehensive Overview Of Recent Research Efforts In Applying Deep Learning Techniques For Monkeypox Detection And Classification. It Discusses Commonly Used Datasets, Image Preprocessing Methods, Deep Neural Network Architectures, Evaluation Metrics, And Comparative Performance Outcomes. Furthermore, The Paper Highlights Existing Challenges, Including Limited Datasets, Class Imbalance, And The Need For Explainable AI In Clinical Settings. Finally, Potential Future Directions Such As Transfer Learning, Federated Learning, And Multimodal Approaches Are Outlined To Enhance Diagnostic Accuracy And Real-world Applicability. This Survey Aims To Serve As A Reference For Researchers And Healthcare Professionals Seeking To Leverage Deep Learning In Improving The Timely And Reliable Diagnosis Of Monkeypox.
Human–wildlife Conflict Is A Growing Concern, Particularly In Regions Where Wild Animals Intrude Into Agricultural Fields, Residential Areas, Or Roadways, Leading To Significant Crop Losses, Property Damage, And Threats To Human Safety. Traditional Animal Monitoring Methods, Such As Manual Patrolling And Camera Trapping, Are Time-consuming, Labor-intensive, And Often Fail To Provide Real-time Alerts. With Advancements In Computer Vision And Deep Learning, Object Detection Models Have Shown Great Potential In Addressing These Challenges. This Study Proposes An Advanced Wild Animal Detection And Alert System Using The YOLOv5 Model, A State-of-the-art Deep Learning Framework Known For Its High Accuracy And Fast Detection Speed. The System Is Designed To Identify And Classify Various Wild Animal Species From Live Video Streams Or Camera Trap Images In Real Time. Once Detection Occurs, An Automatic Alert Mechanism Is Triggered Through IoT-based Communication Channels (e.g., SMS, Alarms, Or Mobile Notifications) To Warn Farmers, Forest Officials, Or Nearby Residents. The Integration Of YOLOv5 With IoT Technologies Ensures Timely Response, Reduces Human–animal Conflict, And Enhances Both Community Safety And Wildlife Conservation Efforts. Experimental Evaluations Demonstrate That The Proposed System Achieves High Precision And Recall Rates While Maintaining Low Latency, Making It Suitable For Deployment In Real-world Environments.
With The Rapid Advancement Of Digital Editing Tools, Image Manipulation Has Become Increasingly Sophisticated And Widespread, Raising Serious Concerns In Areas Such As Journalism, Law Enforcement, Medical Imaging, And Social Media. Traditional Image Forgery Detection Techniques, Such As Error Level Analysis And Metadata Inspection, Often Fail To Detect Subtle Manipulations Or Perform Poorly On Large-scale Datasets. Deep Learning Has Recently Emerged As A Powerful Solution, Offering Automated Feature Extraction And High Accuracy In Identifying Complex Patterns Of Tampering. This Study Explores The Application Of Deep Learning Models—such As Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs), And Hybrid Architectures—for Detecting Common Forgery Types Including Copy-move, Splicing, And Deepfake Images. The Proposed Framework Leverages Spatial And Frequency Domain Analysis, Combined With Transfer Learning, To Enhance Detection Robustness Across Diverse Datasets. Experimental Evaluations Demonstrate That Deep Learning–based Methods Outperform Conventional Approaches In Terms Of Precision, Recall, And Generalization To Unseen Manipulations. The Findings Highlight The Potential Of Deep Learning Models As Reliable And Scalable Tools For Real-world Image Forgery Detection, Paving The Way For Stronger Digital Content Authentication Systems.
With The Rapid Growth Of E-commerce And The Fashion Retail Industry, Automated Product Classification And Personalized Recommendations Have Become Essential For Improving User Experience And Increasing Sales. Bags, Being A Diverse Product Category With Variations In Design, Size, Material, And Style, Pose Significant Challenges For Accurate Classification And Effective Product Suggestions. Traditional Machine Learning Approaches Often Rely On Handcrafted Features, Which Are Limited In Capturing Complex Visual Patterns. To Address This, This Study Proposes A Chatbot System For Bag Classification And Product Suggestion Using EfficientNet, A State-of-the-art Deep Learning Architecture Known For Its High Accuracy And Computational Efficiency. The Proposed Model Leverages EfficientNet For Robust Feature Extraction And Fine-grained Classification Of Different Bag Categories, While The Chatbot Interface Enables Interactive Communication With Users To Provide Real-time Product Recommendations Based On Preferences And Browsing Behavior. This Integration Of Deep Learning With Conversational AI Not Only Enhances Classification Accuracy But Also Improves Customer Engagement And Decision-making In Online Shopping.
Skin Cancer Is One Of The Most Prevalent Forms Of Cancer Worldwide, And Its Early Detection Is Crucial For Effective Treatment And Improved Survival Rates. Traditional Diagnostic Methods Rely Heavily On Clinical Expertise And Invasive Biopsy Procedures, Which Are Often Time-consuming, Costly, And Subject To Human Error. With Advancements In Artificial Intelligence, Image Processing Combined With Machine Learning Has Emerged As A Powerful Tool For Automated Skin Cancer Classification. This Study Focuses On Developing A System That Leverages Image Preprocessing Techniques—such As Noise Removal, Contrast Enhancement, And Segmentation—to Accurately Extract Relevant Features From Dermoscopic Images. Machine Learning Algorithms Are Then Applied To Classify Skin Lesions Into Benign Or Malignant Categories. The Proposed Approach Aims To Improve Diagnostic Accuracy, Reduce Dependency On Manual Interpretation, And Provide A Cost-effective, Non-invasive Solution For Early Skin Cancer Detection. By Integrating Image Processing And Intelligent Classification Models, This Work Contributes To The Advancement Of Computer-aided Diagnosis In Dermatology And Supports Timely Clinical Decision-making.
Plant Diseases Significantly Affect Agricultural Productivity, Leading To Severe Economic Losses And Threats To Food Security Worldwide. Traditional Disease Identification Methods Rely Heavily On Expert Knowledge And Manual Inspection, Which Are Time-consuming, Error-prone, And Impractical For Large-scale Monitoring. With The Advancement Of Artificial Intelligence, Deep Learning Has Emerged As A Powerful Tool For Automated Plant Disease Recognition Through Image Analysis. This Study Focuses On Developing An Intelligent System For Plant Leaf Disease Recognition Using Deep Learning Algorithms, Particularly Convolutional Neural Networks (CNNs). The Proposed Model Leverages Image Preprocessing, Feature Extraction, And Classification Techniques To Accurately Identify And Categorize Different Types Of Leaf Diseases. By Training On Large-scale Plant Image Datasets, The System Demonstrates High Accuracy In Distinguishing Between Healthy And Diseased Leaves, Even In Complex Environments. Such An Approach Not Only Reduces Dependency On Manual Expertise But Also Enables Real-time And Cost-effective Disease Detection, Empowering Farmers With Early Diagnosis And Effective Crop Management Strategies. The Results Highlight The Potential Of Deep Learning-based Solutions In Precision Agriculture And Sustainable Farming Practices.
The Rapid Advancement Of Artificial Intelligence And Generative Models Has Led To The Rise Of Deepfakes—synthetically Altered Or Fabricated Audio, Video, And Images That Are Increasingly Indistinguishable From Authentic Content. While Deepfake Technology Has Promising Applications In Entertainment, Education, And Creative Industries, It Also Poses Severe Threats To Privacy, Security, Politics, And Digital Trust When Misused For Disinformation, Identity Theft, Or Fraud. Traditional Detection Methods, Such As Manual Inspection And Handcrafted Feature-based Techniques, Are Insufficient Against The Sophisticated Manipulations Generated By Modern Deep Learning Architectures Like Generative Adversarial Networks (GANs) And Autoencoders. To Address These Challenges, Deep Learning-based Detection Techniques Have Emerged As A Powerful Solution Due To Their Ability To Automatically Learn Discriminative Features From Large-scale Datasets. Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), And Transformer-based Architectures Have Been Widely Employed To Capture Spatial, Temporal, And Frequency Inconsistencies Present In Forged Media. Additionally, Hybrid Models That Integrate Multimodal Analysis—combining Visual, Audio, And Physiological Cues—have Shown Significant Improvements In Detection Accuracy. This Study Explores Recent Advancements In Deepfake Detection Using Deep Learning, Highlighting Key Methodologies, Benchmark Datasets, Performance Metrics, And Ongoing Challenges Such As Generalizability, Adversarial Attacks, And Real-time Implementation. The Findings Emphasize The Critical Role Of Robust And Adaptive Detection Systems In Safeguarding Digital Media Integrity And Mitigating The Societal Risks Associated With Deepfakes.
The Increasing Demand For Health Awareness And Personalized Dietary Management Has Driven The Need For Automated Food Recognition And Nutritional Analysis Systems. Traditional Methods Of Food Logging, Such As Manual Entry Or Barcode Scanning, Are Often Inconvenient, Time-consuming, And Prone To User Error. Recent Advancements In Deep Learning, Particularly Convolutional Neural Networks (CNNs), Have Demonstrated Remarkable Success In Image Classification Tasks, Providing A Foundation For Intelligent Food Recognition. This Study Proposes An Automatic Food Image Classification System That Leverages Deep Learning Techniques To Accurately Identify Food Categories From Images And Estimate Their Corresponding Nutritional Values, Such As Calories, Protein, Carbohydrates, And Fat Content. The Framework Involves Preprocessing Of Food Images, Feature Extraction Through CNN-based Models, And Classification Into Predefined Food Categories. A Nutritional Database Is Integrated To Map Recognized Food Items To Their Nutritional Information, Enabling Precise Prediction Of Dietary Intake. Experimental Evaluations On Benchmark Food Image Datasets Demonstrate The Effectiveness Of The Proposed Approach In Achieving High Classification Accuracy And Reliable Nutrient Estimation. This System Has Significant Applications In Healthcare, Fitness Tracking, And Personalized Diet Management, Ultimately Contributing To Improved Lifestyle And Well-being.
Dog Breed Classification Is A Challenging Computer Vision Task Due To High Intra-class Variation, Inter-class Similarity, And The Large Number Of Breeds With Subtle Visual Differences. Traditional Methods Relying On Handcrafted Features And Shallow Classifiers Often Fail To Achieve Satisfactory Performance In Real-world Scenarios. Recent Advancements In Deep Learning, Particularly Convolutional Neural Networks (CNNs), Have Demonstrated Remarkable Success In Image Recognition Tasks By Automatically Learning Discriminative Features From Data. This Study Proposes A Breakthrough Conventional-based Approach For Dog Breed Classification That Integrates CNNs With Transfer Learning Techniques. Pre-trained Deep Learning Models Such As VGG16, ResNet, And Inception Are Fine-tuned On A Curated Dog Breed Dataset To Leverage Their Feature Extraction Capabilities While Reducing Computational Cost And Training Time. The Proposed Method Enhances Classification Accuracy, Robustness, And Generalization Compared To Training Models From Scratch. Experimental Results Highlight The Effectiveness Of Transfer Learning In Achieving Superior Performance Across Multiple Dog Breeds, Offering A Scalable And Efficient Solution For Applications In Veterinary Research, Animal Identification, And Intelligent Pet-care Systems.
Handwritten Text Recognition Remains A Challenging Problem In The Field Of Computer Vision And Pattern Recognition Due To The High Variability In Individual Writing Styles, Distortions, Overlapping Characters, And Background Noise. Traditional Recognition Systems Based On Handcrafted Features And Rule-based Methods Often Fail To Achieve High Accuracy And Generalization In Real-world Scenarios. Recent Advancements In Deep Learning Have Introduced Powerful Hybrid Models That Combine Convolutional Neural Networks (CNNs) And Recurrent Neural Networks (RNNs), Forming Convolutional Recurrent Neural Networks (CRNNs). CNNs Are Effective In Extracting Robust Spatial Features From Handwritten Images, While RNNs—particularly Long Short-Term Memory (LSTM) Or Gated Recurrent Units (GRUs)—capture The Sequential Dependencies Inherent In Handwriting. This Study Focuses On Developing A CRNN-based Framework For End-to-end Handwritten Text Recognition, Eliminating The Need For Manual Feature Engineering. The Model Is Trained On Large-scale Handwritten Datasets And Evaluated Using Sequence-to-sequence Mapping With Connectionist Temporal Classification (CTC) Loss To Align Input Images With Output Text. Experimental Results Demonstrate That The Proposed CRNN Architecture Achieves High Recognition Accuracy And Robustness Against Diverse Handwriting Variations, Making It A Promising Solution For Applications Such As Digitizing Historical Documents, Automated Form Processing, And Intelligent Handwriting-based Interfaces.
Fish Detection And Tracking In Aquaculture Environments Is A Crucial Task For Monitoring Fish Behavior, Estimating Population Density, And Optimizing Farm Management Practices. Traditional Manual Observation Methods Are Labor-intensive, Prone To Error, And Lack Scalability In Large-scale Fish Farms. Recent Advancements In Computer Vision And Deep Learning Provide Automated Solutions For Real-time Monitoring. This Study Proposes An Efficient Fish Detection And Tracking Framework That Integrates The YOLO (You Only Look Once) Object Detection Algorithm With Euclidean Distance-based Tracking. YOLO Is Employed To Accurately Detect Fish In Underwater Video Streams, Leveraging Its High-speed Inference And Robustness Against Complex Backgrounds, Water Turbidity, And Varying Illumination. Subsequently, A Euclidean Distance Tracker Associates Detections Across Consecutive Frames, Enabling Reliable Multi-fish Tracking Without The Computational Complexity Of Deep Tracking Models. The Proposed System Ensures Real-time Performance With High Detection Accuracy And Low Identity-switch Rates, Making It Suitable For Practical Deployment In Aquaculture Farms. The Approach Can Support Applications Such As Fish Counting, Growth Monitoring, And Behavioral Analysis, Contributing To Sustainable And Intelligent Aquaculture Management.
Cotton Is One Of The Most Important Commercial Crops Worldwide, And Its Productivity Is Severely Affected By Various Leaf Diseases Such As Bacterial Blight, Grey Mildew, Fusarium Wilt, And Alternaria Leaf Spot. Early And Accurate Detection Of These Diseases Is Essential For Minimizing Yield Losses And Ensuring Sustainable Crop Management. Traditional Diagnostic Methods Relying On Manual Observation Are Often Time-consuming, Subjective, And Prone To Human Error, Making Them Unsuitable For Large-scale Monitoring. In Recent Years, Advancements In Computer Vision And Machine Learning Have Enabled The Development Of Automated Systems For Disease Detection And Classification. This Survey Provides A Comprehensive Overview Of Existing Techniques For Cotton Leaf Disease Identification, Ranging From Traditional Image Processing Methods To Deep Learning-based Approaches. Various Algorithms Such As Convolutional Neural Networks (CNNs), Support Vector Machines (SVM), Random Forests, And Transfer Learning Models Are Discussed In Terms Of Their Accuracy, Robustness, And Computational Efficiency. Furthermore, The Survey Highlights Publicly Available Datasets, Key Performance Metrics, Challenges Such As Variations In Illumination And Background Noise, And Potential Solutions Through Hybrid And Ensemble Models. Finally, It Outlines Future Research Directions, Emphasizing The Need For Lightweight, Real-time, And Scalable Solutions Deployable In Smart Farming Applications.
Handwritten Signature Verification Is One Of The Most Widely Used Biometric Authentication Methods Due To Its Simplicity, Uniqueness, And Acceptance In Legal And Financial Transactions. However, Traditional Manual Verification Methods Are Prone To Human Error, Time-consuming, And Susceptible To Forgery. With The Rapid Advancement Of Computer Vision And Pattern Recognition, Automated Signature Verification Has Become A Promising Solution For Enhancing Security And Reliability. This Study Presents A Handwritten Signature Verification System Utilizing OpenCV Techniques For Image Preprocessing, Feature Extraction, And Classification. The System Employs Image Enhancement Methods Such As Grayscale Conversion, Thresholding, Edge Detection, And Contour Analysis To Extract Discriminative Features From Signatures. These Features Are Then Compared Using Similarity Measures Or Machine Learning Models To Distinguish Between Genuine And Forged Signatures. The Proposed Approach Demonstrates The Effectiveness Of OpenCV-based Techniques In Achieving Accurate, Efficient, And Scalable Signature Verification, Offering Potential Applications In Banking, Legal Documentation, And Secure Identity Management.
The Choice Of A Suitable Hairstyle Plays A Significant Role In Enhancing Personal Appearance And Confidence. However, Selecting The Most Appropriate Hairstyle Often Depends On Factors Such As Face Shape, Facial Features, And Individual Preferences, Making It A Challenging And Subjective Process. Traditional Methods Of Hairstyle Selection Rely On Manual Consultation With Experts, Which Can Be Time-consuming, Inconsistent, And Costly. To Address This Challenge, This Study Presents The Design And Implementation Of A Hair Recommendation System Based On Face Recognition. The System Employs Computer Vision Techniques For Face Detection And Feature Extraction, Classifying Face Shapes Such As Oval, Round, Square, And Heart-shaped. Using These Classifications, A Recommendation Engine Suggests Suitable Hairstyles Tailored To The User’s Facial Attributes. The Proposed Framework Integrates Image Preprocessing, Facial Landmark Detection, Feature Analysis, And Machine Learning Models To Provide Personalized Hairstyle Suggestions In Real Time. Experimental Results Demonstrate That The System Offers Accurate Face Shape Classification And Effective Hairstyle Recommendations, Thereby Enhancing User Satisfaction. This Approach Highlights The Potential Of Artificial Intelligence And Face Recognition Technologies In Personal Grooming, Fashion, And Virtual Try-on Applications.
Wild Animal Detection And Segmentation Play A Vital Role In Wildlife Monitoring, Biodiversity Conservation, And Prevention Of Human–animal Conflicts. Traditional Methods Such As Manual Observation And Camera Traps Are Often Time-consuming, Labor-intensive, And Prone To Inaccuracies In Large-scale Or Dense Environments. With Recent Advancements In Deep Learning, Automated Detection Systems Have Become Increasingly Effective For Real-time Monitoring Of Wildlife. This Study Proposes An Efficient Framework For Wild Animal Detection And Segmentation Using The YOLOv7 (You Only Look Once Version 7) Object Detection Algorithm. YOLOv7 Is Utilized For Its Superior Speed And Accuracy In Identifying Multiple Animal Species Within Complex Natural Backgrounds. Furthermore, Segmentation Is Integrated To Provide Precise Boundary Information, Enabling Detailed Analysis Of Animal Size, Movement Patterns, And Habitat Utilization. The Proposed System Can Assist Researchers, Forest Authorities, And Conservationists In Automating Wildlife Surveillance, Reducing Manual Effort, And Enhancing Decision-making For Ecological Management.
Rice Is One Of The Most Important Staple Crops Worldwide, And Its Productivity Is Significantly Affected By Various Leaf Diseases Such As Bacterial Blight, Brown Spot, And Leaf Smut. Early And Accurate Detection Of These Diseases Is Crucial For Effective Crop Management And Yield Improvement. Traditional Manual Identification Methods Are Time-consuming, Subjective, And Prone To Error, Making Them Unsuitable For Large-scale Monitoring. Recent Advances In Deep Learning Have Provided Efficient Solutions For Automated Plant Disease Recognition. This Study Focuses On The Classification Of Rice Leaf Diseases Using Convolutional Neural Networks (CNNs) And Transfer Learning Approaches. A CNN Model Is Developed For Feature Extraction And Classification, While Pre-trained Models Such As VGG16, ResNet50, And InceptionV3 Are Fine-tuned To Improve Accuracy And Reduce Training Time. Experimental Results Demonstrate That Transfer Learning-based Models Outperform Standard CNNs By Achieving Higher Classification Accuracy, Robustness, And Generalization. The Proposed Framework Provides An Efficient And Scalable Solution For Real-time Rice Disease Detection, Thereby Supporting Precision Agriculture And Sustainable Farming Practices.
Potato Is One Of The Most Widely Cultivated And Consumed Crops Worldwide, But Its Productivity Is Severely Threatened By Various Leaf Diseases Such As Early Blight, Late Blight, And Bacterial Infections. Timely And Accurate Detection Of These Diseases Is Essential To Reduce Yield Losses And Ensure Sustainable Agricultural Practices. Traditional Manual Identification Methods Are Often Labor-intensive, Time-consuming, And Prone To Human Error, Making Them Unsuitable For Large-scale Monitoring. Recent Advancements In Computer Vision And Deep Learning Provide Promising Solutions For Automated Plant Disease Recognition. This Study Focuses On Potato Disease Detection Using Convolutional Neural Networks (CNNs) Integrated With Image Processing Techniques. The Proposed Approach Involves Preprocessing Potato Leaf Images, Feature Extraction, And Classification Of Healthy And Diseased Leaves. CNNs Are Employed Due To Their Superior Capability In Learning Hierarchical Features Directly From Image Data Without The Need For Handcrafted Features. Experimental Results Demonstrate High Accuracy And Robustness Of The Model In Detecting And Classifying Potato Leaf Diseases. The Findings Highlight The Potential Of CNN-based Frameworks As An Effective Decision-support Tool For Precision Agriculture, Enabling Farmers To Take Timely Preventive Measures And Improve Crop Yield.
Fruits Are An Essential Component Of Global Agriculture And Food Supply, Yet Accurate Identification Of Fruit Species Remains A Significant Challenge Due To Variations In Size, Shape, Color, Texture, And Environmental Conditions During Image Acquisition. Traditional Manual Classification Methods Are Time-consuming, Error-prone, And Impractical For Large-scale Applications. Recent Advancements In Computer Vision And Deep Learning Have Opened New Opportunities For Automated And Highly Accurate Fruit Species Detection. This Study Proposes An Improved Fruit Species Detection System Using Image Processing Techniques Combined With Deep Learning Models Such As Convolutional Neural Networks (CNNs). The System Utilizes Preprocessing Methods Including Noise Reduction, Image Enhancement, And Segmentation To Extract Discriminative Features. These Features Are Then Fed Into Deep Learning Architectures To Achieve Robust Classification Across Diverse Fruit Categories. Experimental Results Demonstrate That The Proposed Approach Significantly Enhances Detection Accuracy And Efficiency Compared To Conventional Machine Learning Techniques. The System Has Potential Applications In Smart Agriculture, Food Quality Control, Automated Harvesting, And Supply Chain Management, Thereby Contributing To Increased Productivity And Reduced Labor Dependency.
Handwritten Digit Recognition Is One Of The Most Widely Studied Problems In The Field Of Computer Vision And Pattern Recognition, With Applications Ranging From Automated Postal Sorting And Bank Check Processing To Digital Form Analysis And Authentication Systems. Traditional Manual Recognition Methods Are Time-consuming, Error-prone, And Unsuitable For Large-scale Applications. With Recent Advancements In Deep Learning, Significant Progress Has Been Made In Achieving High Accuracy For Digit Classification Tasks. This Study Presents A Handwritten Digit Recognition System That Integrates Deep Learning Networks With OpenCV For Efficient Image Preprocessing, Feature Extraction, And Classification. The Proposed System Employs Techniques Such As Noise Reduction, Thresholding, And Contour Detection To Enhance Image Quality Before Feeding It Into A Deep Neural Network For Accurate Classification. The Model Is Trained And Evaluated Using Benchmark Datasets Such As MNIST To Demonstrate Its Effectiveness. Experimental Results Indicate That The Integration Of OpenCV With Deep Learning Significantly Improves Recognition Accuracy And Computational Efficiency, Making The System Robust And Applicable For Real-world Scenarios.
Mango Is One Of The Most Economically Significant Fruit Crops Cultivated Worldwide, But Its Yield And Quality Are Severely Affected By Various Leaf Diseases Such As Anthracnose, Powdery Mildew, And Bacterial Canker. Accurate And Timely Detection Of These Diseases Is Crucial For Effective Crop Management, Prevention Of Yield Loss, And Ensuring Sustainable Agricultural Practices. Traditional Disease Identification Methods Relying On Visual Inspection Are Labor-intensive, Time-consuming, And Prone To Human Error. In Recent Years, Numerous Computational Techniques, Ranging From Conventional Image Processing And Machine Learning To Advanced Deep Learning Models, Have Been Developed To Improve The Efficiency And Accuracy Of Mango Leaf Disease Detection. This Study Presents A Systematic Analysis Of Existing Techniques Used For Mango Leaf Disease Detection, Highlighting Their Methodologies, Strengths, Limitations, And Application Scope. The Comparative Review Emphasizes The Transition From Handcrafted Feature-based Approaches To Data-driven Deep Learning Architectures, Which Have Demonstrated Superior Performance In Terms Of Robustness And Scalability. Furthermore, The Analysis Discusses Challenges Such As Variability In Imaging Conditions, Dataset Limitations, And Computational Complexity, While Also Outlining Future Research Directions For Developing More Generalized, Real-time, And Farmer-friendly Detection Systems.
Potholes Are A Major Cause Of Road Accidents, Vehicle Damage, And Traffic Disruptions, Making Their Timely Detection And Repair A Critical Aspect Of Modern Transportation Management. Traditional Manual Inspection Methods Are Labor-intensive, Time-consuming, And Prone To Human Error, Highlighting The Need For Automated, Reliable, And Scalable Solutions. Recent Advancements In Computer Vision And Deep Learning Have Opened New Opportunities For Accurate Pothole Detection And Measurement. This Study Proposes A Modern Pothole Detection And Dimension Estimation System That Integrates The YOLO (You Only Look Once) Deep Learning Model With Advanced Image Processing Techniques. The YOLO Architecture Is Employed For Real-time Pothole Localization And Classification, While Image Processing Methods Are Utilized To Estimate The Dimensions Of Detected Potholes, Such As Width, Depth, And Surface Area. The Proposed System Ensures High Accuracy, Robustness Under Varying Lighting And Environmental Conditions, And The Ability To Process Large-scale Road Datasets Efficiently. Experimental Results Demonstrate That This Hybrid Approach Outperforms Traditional Methods, Offering A Practical And Cost-effective Solution For Smart City Infrastructure, Automated Road Condition Monitoring, And Predictive Maintenance Systems.
Medicinal Plants Play A Vital Role In Traditional Healthcare Systems And Modern Pharmacology, Yet Their Accurate Identification In The Wild Remains A Challenging Task Due To Variations In Plant Morphology, Environmental Conditions, And Similarities Between Species. Traditional Identification Methods Rely On Expert Knowledge And Manual Inspection, Which Are Often Time-consuming, Subjective, And Impractical For Large-scale Applications. Recent Advancements In Computer Vision And Deep Learning Provide New Opportunities For Automated And Reliable Plant Recognition. This Study Presents A Medicinal Plant Identification System Based On Convolutional Neural Networks (CNNs), Designed To Classify And Recognize Plant Species Directly From Leaf And Plant Images Captured In Natural Environments. The Proposed System Leverages Image Preprocessing, Feature Extraction, And Classification Through CNN Models To Achieve High Accuracy Under Varying Lighting And Background Conditions. Such An Approach Not Only Facilitates Faster And More Accurate Plant Recognition But Also Contributes To The Preservation Of Traditional Knowledge, Supports Biodiversity Research, And Enhances Applications In Healthcare And Drug Discovery.
Leather Is One Of The Most Widely Used Natural Materials In Industries Such As Fashion, Furniture, And Automotive Manufacturing. However, The Presence Of Defects Such As Scratches, Cuts, Insect Bites, Wrinkles, And Stains Significantly Reduces Its Commercial Value And Usability. Traditional Defect Inspection Relies Heavily On Human Expertise, Which Is Time-consuming, Subjective, And Prone To Error, Especially When Applied To Large-scale Production. To Overcome These Limitations, Automated Leather Defect Detection And Classification Systems Have Gained Increasing Attention. This Study Presents A Deep Learning–based Framework For Accurate Detection, Classification, And Segmentation Of Leather Defects. Convolutional Neural Networks (CNNs) And Advanced Architectures Such As U-Net And YOLO Are Employed To Localize And Categorize Defects At Pixel And Region Levels. The Proposed System Ensures Both High Accuracy In Defect Classification And Precise Segmentation For Defect Localization, Enabling Manufacturers To Automate Quality Control Processes Effectively. Experimental Results Demonstrate The System’s Robustness In Handling Diverse Defect Types Under Varying Illumination And Texture Conditions.
Machine And Deep Learning Applications Play A Dominant Role In The Current Scenario In The Agriculture Sector. To Date, The Classification Of Fruits Using Image Features Has Attained The Researcher’s Attraction Very Much From The Last Few Years. Fruit Recognition And Classification Is An Ill-posed Problem Due To The Heterogeneous Nature Of Fruits. In The Proposed Work, Convolution Neural Network (CNN), Recurrent Neural Network (RNN), And Long-short Term Memory (LSTM) Deep Learning Methods Are Used To Extract The Optimal Image Features, And To Select Features After Extraction, And Finally, Use Extracted Image Features To Classify The Fruits. To Evaluate The Performance Of The Proposed Approach, The Support Vector Machine (SVM) Unsupervised Learning Method, Artificial Neuro-fuzzy Inference System (ANFIS), And Feed-forward Neural Network (FFNN) Classification Results Are Compared, And Observed That The Proposed Fruit Classification Approach Results Are Quite Efficient And Promising.
Machine Learning Is An Important Decision Support Tool For Crop Yield Prediction, Including Supporting Decisions On What Crops To Grow And What To Do During The Growing Season Of The Crops. Several Machine Learning Algorithms Have Been Applied To Support Crop Yield Prediction Research. In This Study, We Performed A Systematic Literature Review (SLR) To Extract And Synthesize The Algorithms And Features That Have Been Used In Crop Yield Prediction Studies. Based On Our Search Criteria, We Retrieved 567 Relevant Studies From Six Electronic Databases, Of Which We Have Selected 50 Studies For Further Analysis Using Inclusion And Exclusion Criteria. We Investigated These Selected Studies Carefully, Analyzed The Methods And Features Used, And Provided Suggestions For Further Research. According To Our Analysis, The Most Used Features Are Temperature, Rainfall, And Soil Type, And The Most Applied Algorithm Is Artificial Neural Networks In These Models. After This Observation Based On The Analysis Of Machine Learning-based 50 Papers, We Performed An Additional Search In Electronic Databases To Identify Deep Learning-based Studies, Reached 30 Deep Learning-based Papers, And Extracted The Applied Deep Learning Algorithms. According To This Additional Analysis, Convolutional Neural Networks (CNN) Is The Most Widely Used Deep Learning Algorithm In These Studies, And The Other Widely Used Deep Learning Algorithms Are Long-Short Term Memory (LSTM) And Deep Neural Networks (DNN).
This Paper Presents A Unique Method To Classify Food Items And Estimate The Calorie Content Based On Photos By Combining Convolutional Neural Networks (CNNs) With Image Processing Techniques. To Improve The Quality Of The Dataset, We First Curate A Wide Range Of Food Photographs From Different Presentation Styles And Cuisines. We Do This By Applying Pre-processing Techniques Including Image Segmentation And Feature Extraction. Next, Using The CNN's Capacity To Extract Hierarchical Features From Raw Pixel Data, A Custom Deep CNN Architecture Is Trained On This Dataset To Efficiently Classify Diverse Food Items And Achieve High Accuracy In Differentiating Between Different Dishes. Furthermore, We Tackle The Problem Of Calorie Prediction By Employing Regression Models That Include Features Extracted From The CNN, Which Allows One To Forecast The Calorie Content Of A Food Item Based On Its Visual Attributes. Our Technique Intends To Enable Users To Make More Educated Nutritional Decisions And Better Control Their Caloric Intake By Fusing Image Categorization With Calorie Prediction. The Suggested Approach Shows Encouraging Results In Terms Of Food Item Classification Accuracy And Precision In Calorie Estimate. It’s Possible Uses Include Promoting Better Eating Practices And Assisting Individuals, Dietitians, And The Food Industry With Their Dietary Monitoring. In Addition, Our Technology Gives Customers Access To Weekly Calorie Intake Information, Which Can Help Them Avoid Obesity-related Illnesses Like Diabetes.
Object Detection Is One Of The Key Areas For All The Researchers In The Field Of Computer Science. The Research Is To Find The Types Of Objects In The Image And Provide Their Temporal And Spatial Characteristics. In The Recent Times There Have Been A Lot Of Improvements In The Field Of Satellite Image Detection With Varying Data Sets Being Available And Has Left High Impact On The Performance Of Such Analysis. A Number Of Algorithms Have Evolved Over A Period Of Time In Object Detection And Analysis Namely Different Versions Of YOLO, CNN, DETR Etc. There Is A Need To Deploy A Study Which Enables The Performance Comparison Of Different Versions Of These Algorithms On Specific Data Set To Understand Their Efficacy. The Study In The Paper Contributes To Understanding, Evaluating And Analyzing The Performance Characteristics Of YOLO V7 Algorithm With Varying Parameters.
Agriculture Is The Backbone Of Indian Economy And Livelihood To Many People. The Use Of Computer Science In The Field Of Agriculture Will Potentially Solve Many Problems Faced By Farmers. Farmers Often Choose Crops For Their Field Based On Their Own Experience And Instinct. This Sometimes Leads To Loss And Less Yield. If The Selection Of Crops Is Done With Productivity Data Of The Entire Region, It May Lead To Better Results.However All The Crops Cannot Be Cultivated In A Particular Soil. So The Soil Must Be Analysed And Crops Must Be Suggested Based On The Type Of Soil. Many Soil Classification Techniques Involve Testing In Laboratories Whichmight Not Be Affordable And Available To All The Farmers. This Work Suggests An Idea That Is Useful And Easily Accessible To All The Farmers In India Without Any Need Of Hardware. A List Of Crops With Their Success Rate Will Be Suggested To The Farmer When The Region Of Agriculture And Soil Image (used For Agriculture) Are Given As Inputs. This List Of Crops Are Both Profitable And Produce More Yield In That Region. The Results Obtained Are Promising. An Accuracy Of 94% Is Achieved In The Soil Classification Module.The Success Rate For The Crops Obtained Are Realistic With The Agricultural Practices In The Region. The Web Application Developed Is Extremely User Friendly And Easy To Use By The Farmers.
Chatbot For Bag Classification And Product Suggestion Is An Emerging Technology That Can Revolutionize The E-commerce Industry. The Chatbot Interacts With The User In A Conversational Manner And Uses Natural Language Processing And Machine Learning Algorithms To Classify Bags Based On Various Attributes Such As Color, Size, Material, And Style. The Chatbot Can Also Suggest Products Based On The User's Preferences, Purchase History, And Browsing Behavior. The Chatbot Can Enhance The User's Shopping Experience By Providing Personalized Product Recommendations, Reducing The Time And Effort Required To Search For Products, And Improving Customer Engagement And Satisfaction. The Chatbot Can Also Help E-commerce Businesses Streamline Their Inventory Management By Providing Insights Into User Preferences And Behaviour.
One Of The Most Rapidly Spreading Cancers Among Various Other Types Of Cancers Known To Humans Is Skin Cancer. Melanoma Is The Worst And The Most Dangerous Type Of Skin Cancer That Appears Usually On The Skin Surface And Then Extends Deeper Into The Layers Of Skin. However, If Diagnosed At An Early Stage; The Survival Rate Of Melanoma Patients Is 96% With Simple And Economical Treatments. The Conventional Method Of Diagnosing Melanoma Involves Expert Dermatologists, Equipment, And Biopsies. To Avoid The Expensive Diagnosis, And To Assist Dermatologists, The Field Of Machine Learning Has Proven To Provide State Of The Art Solutions For Skin Cancer Detection At An Earlier Stage With High Accuracy. In This Paper, A Method For Skin Lesion Classification And Segmentation As Benign Or Malignant Is Proposed Using Image Processing And Machine Learning. A Novel Method Of Contrast Stretching Of Dermoscopic Images Based On The Methods Of Mean Values And Standard Deviation Of Pixels Is Proposed. Then The OTSU Thresholding Algorithm Is Applied For Image Segmentation. After The Segmentation, Features Including Gray Level Co-occurrence Matrix (GLCM) Features For Texture Identification, The Histogram Of Oriented Gradients (HOG) Object, And Color Identification Features Are Extracted From The Segmented Images. Principal Component Analysis (PCA) Reduction Of HOG Features Is Performed For Dimensionality Reduction. Synthetic Minority Oversampling Technique (SMOTE) Sampling Is Performed To Deal With The Class Imbalance Problem. The Feature Vector Is Then Standardized And Scaled.
Machine Learning Is A Branch Of Artificial Intelligence. In Recent Years, With The Advantages Of Automatic Learning And Feature Extraction, It Has Been Widely Concerned By Academic And Industrial Circles. It Has Been Widely Used In Image And Video Processing, Voice Processing, And Natural Language Processing. At The Same Time, It Has Also Become A Research Hotspot In The field Of Agricultural Plant Protection, Such As Plant Disease Recognition And Pest Range Assessment, Etc. The Application Of Machine Learningin Plant Disease Recognition Can Avoid The Disadvantages Caused By Artificial Selection Of Disease Spot Features, Make Plant Disease Feature Extraction More Objective,and Improve There Search Efficiency And Technology Transformationspeed. This Review Provides There Search Progress Of Machine Learning Technology In The field Of Crop Leaf Disease Identification In Recent Years. In This Paper, We Present The Current Trends And Challenges For The Detection Of Plant Leaf Disease Using Machine Learning And Advanced Imaging Techniques. We Hope That This Work Will Be A Valuable Resource For Researchers Who Study The Detection Of Plant Diseases And Insect Pests. At The Same Time, We Also Discussed Some Of The Current Challenges And Problems That Need To Be Resolved.
Deep Learning Is An Effective And Useful Technique That Has Been Widely Applied In A Variety Of Fields, Including Computer Vision, Machine Vision, And Natural Language Processing. Deepfakes Uses Deep Learning Technology To Manipulate Images And Videos Of A Person That Humans Cannot Differentiate Them From The Real One. In Recent Years, Many Studies Have Been Conducted To Understand How Deepfakes Work And Many Approaches Based On Deep Learning Have Been Introduced To Detect Deepfakes Videos Or Images. In This Paper, We Conduct A Comprehensive Review Of Deepfakes Creation And Detection Technologies Using Deep Learning Approaches. In Addition, We Give A Thorough Analysis Of Various Technologies And Their Application In Deepfakes Detection. Our Study Will Be Beneficial For Researchers In This Field As It Will Cover The Recent State-of-art Methods That Discover Deepfakes Videos Or Images In Social Contents. In Addition, It Will Help Comparison With The Existing Works Because Of The Detailed Description Of The Latest Methods And Dataset Used In This Domain.
Classification Is Now Simpler Thanks To Deep Learning, Bigger Datasets, And More Powerful Computing Power. Convolutional Neural Networks Have Emerged As The Most Popular And Widely Used Method For Categorising Images In Recent Years. Several Transfer Learning Techniques Are Employed In This Article To Categorise Photos From A Dataset Of Indian Food. Everyone Needs To Keep Track Of Their Eating Habits Because Food Is Essential To Life Because It Provides Us With A Range Of Nutrients. Food Classification Is Therefore Essential For A Better Way Of Life. In This Project, Pre-trained Models Are Used Instead Of Conventional Methods For Building A Model From Scratch, Which Reduces Processing Costs And Time While Simultaneously Generating Better Outcomes.
In The Present World, We Have Wide Varieties Of Species And Organisms. This Brings Into Light, The Criticality Of Classification Of Various Tangible Objects. Also, Keeping In Mind, The On-going Research On Genetics And Evolution By Various Scientists Across The World, Discerning The Resemblance Among Different Classes Also Becomes Very Crucial. This Paper Is Based On A Project Which Builds A CNN (Convolutional Neural Network) To Classify Different Dog Breeds. If The Image Of A Dog Is Found, This Algorithm Would Find The Estimate Of The Breed. The Resembling Dog Breed Is Identified If The Image Of A Human Is Supplied. We Have Built A Pipeline To Process Real World Images.
Underwater Fish Detection Plays A Crucial Role In Various Domains, Such As Marine Biology, Environmental Monitoring, And Fisheries Management. Traditional Methods For Fish Detection In Underwater Environments Often Suffer From Limitations In Accuracy And Efficiency. In Recent Years, Deep Learning-based Object Detection Models Have Shown Remarkable Success In Various Computer Vision Tasks. This Study Presents An Underwater Fish Detection System Utilizing The YOLOv8 Architecture, A State-of-the-art Deep Learning Framework
Deep Learning Is A Branch Of Artificial Intelligence. In Recent Years, With The Advantages Of Automatic Learning And Feature Extraction, It Has Been Widely Concerned By Academic And Industrial Circles. It Has Been Widely Used In Image And Video Processing, Voice Processing, And Natural Language Processing. At The Same Time, It Has Also Become A Research Hotspot In The field Of Agricultural Plant Protection, Such As Plant Disease Recognition And Pest Range Assessment, Etc. The Application Of Deep Learning In Plant Disease Recognition Can Avoid The Disadvantages Caused By Artificial Selection Of Disease Spot Features, Make Plant Disease Feature Extraction More Objective, And Improve Their Search Efficiency And Technology Transformation Speed. This Review Provides The Research Progress Of Deep Learning Technology In The field Of Crop Leaf Disease Identification In Recent Years. In This Paper, We Present The Current Trends And Challenges For The Detection Of Plant Leaf Disease Using Deep Learning And Advanced Imaging Techniques. We Hope That This Work Will Be A Valuable Resource For Researchers Who Study The Detection Of Plant Diseases And Insect Pests. At The Same Time, We Also Discussed Some Of The Current Challenges And Problems That Need To Be Resolved.
Hairstyling Is An Art Of Fashion Transformed Since Ancient Era, With The Influences From Many Diverse Factors. It Has Been A Primary Aspect Of Human Lifestyle And Society In Various Different Ways With The Growth Of Research Fields Like Modeling Human, Visual Searching, Visual Matching, Facial Verification For Security Measures And Etc. Perfect Hairstyle Improves Specially A Woman’s Self-confidence. This Paper Presents A Hairstyle Recommendation System Based On Face Shapes And Suitable Hairstyle With Expert’s Knowledge For The Face Shape Derived From Face Shape Classification Algorithm. Different Noise Types And Lighten, Which Have Given Less Accuracy Of Features Landmark Detection. The Images Whose Values Are Confined To Some Specific Range Of Values Only. For Brighter Image Will Have All Pixels Confined High Values. But A Good Image Will Have Pixels From All Regions Of The Image. Therefore, We Applied Histogram Equalization Improves The Contrast Of The Image. The Median Filter Is Used To Remove The Different Types Of Noises.
Underwater Fish Detection Plays A Crucial Role In Various Domains, Such As Marine Biology, Environmental Monitoring, And Fisheries Management. Traditional Methods For Fish Detection In Underwater Environments Often Suffer From Limitations In Accuracy And Efficiency. In Recent Years, Deep Learning-based Object Detection Models Have Shown Remarkable Success In Various Computer Vision Tasks. This Study Presents An Underwater Fish Detection System Utilizing The YOLO Architecture, A State-of-the-art Deep Learning Framework.
One Of The Most Difficult Issues Is Conflict Between Humans And Animals. The Main Reason For Animal Detection, Particularly Wild Animal Infiltration Into Human Habitation, Has Been The Expansion Of Human Settlement Into Forest Areas. The Conflict Between Humans And Animals Is Largely A Result Of The Loss Of Habitat, Food, And Other Necessities For The Animal Kingdom. Many Catastrophic Events In The Future Can Be Prevented By The Early Recognition Of These Conflicts. The Scope Of Earlier Automated Image Detection Processes Aids In Finding A Remedy For These Occurrences. The Detection Can Utilise An Algorithm For Earlier Detection Because The Manual, Traditional Method Is More Difficult. Different Deep Learning Algorithms Help To Identify Invaders Sooner To Prevent Confrontation.
Rice Is One Of The World's Most Important Staple Crops, And The Health Of Rice Plants Is Crucial For Global Food Security. Detecting And Classifying Diseases In Rice Leaves Is Essential To Ensure A Healthy Crop Yield. In This Project, We Propose A System For The Classification Of Rice Leaf Diseases Using Convolutional Neural Networks (CNN) And Transfer Learning. We Aim To Leverage The Power Of Deep Learning And Pre-trained Models To Accurately Identify And Categorize Various Rice Leaf Diseases, Providing Farmers And Agronomists With An Efficient Tool For Early Disease Detection. This Paper Discusses The Existing System's Limitations And Presents The Advantages Of Our Proposed Approach.
Potato Is One Of The Prominent Food Crops All Over The World. In Some Places Potato Cultivation Has Been Getting Remarkable Popularity Over The Last Decades. Many Diseases Affect The Proper Growth Of Potato Plants. Noticeable Diseases Are Seen In The Leaf Region Of This Plant. Two Common And Popular Leaf Diseases Of The Potato Plants Are Early Blight (EB) And Late Blight (LB). However, If These Diseases Were Identified At An Early Stage It Would Be Very Helpful For Better Production Of This Crop. To Solve This Problem By Detecting And Analyzing These Diseases Image Processing Is The Best Option. This Paper Proposes An Image Processing And Deep Learning-based Automatic System That Will Identify And Classify Potato Leaf Diseases. In This Paper, Image Segmentation Is Done Over 152 Images Of Healthy And Diseased Potato Leaf, Which Is Taken From Publicly Available Plant Village Database And Seven Classifier Algorithms Are Used For Recognition And Classification Of Diseased And Healthy Leaves. Among Them, The Convolutional Neural Network Gives An Accuracy Of 97%. In This Manner, Our Proposed Approach Leads To A Path Of Automatic Plant Leaf Disease Detection.
Developing An Android Application For Character Recognition To Read The Text From An Image Is A Big Area Of Research. Nowadays, There Is A Trend Of Storing Information From The Handwritten Documents For Future Use. A Simple Way To Store The Information Is Image Capturing Of The Handwritten Document And Save It In Image Format. The Method To Transform Handwritten Data Into Electronic Format Is ‘Optical Character Recognition’. It Involves Several Steps Including Pre-processing, Segmentation, Feature Extraction And Post-processing. Many Researchers Have Been Used OCR For Recognizing Character. This System Uses The Android Phone To Capture The Image Of The Document And Further Steps Are Done By OCR. The Main Challenge Is To Recognize The Characters From Different Styles Of Handwriting. Thus, A System Is Designed That Recognizes The Handwritten Data To Obtain An Editable Text. The Output Of This System Depends Upon The Data That Has To Be Written By The Writer. Our System Offers 90% Accuracy For Handwritten Documents And Gives The Easiest Way To Edit Or Share The Recognized Data.
The World Is Advancing Towards An Autonomous Environment At A Great Pace And It Has Become A Need Of An Hour, Especially During The Current Pandemic Situation. The Pandemic Has Hindered The Functioning Of Many Sectors, One Of Them Being Road Development And Maintenance. Creating A Safe Working Environment For Workers Is A Major Concern Of Road Maintenance During Such Difficult Times. This Can Be Achieved To Some Extent With The Help Of An Autonomous System That Will Aim At Reducing Human Dependency. In This Paper, One Of Such Systems, A Pothole Detection And Dimension Estimation, Is Proposed. The Proposed System Uses A Deep Learning Based Algorithm YOLO (You Only Look Once) For Pothole Detection. Further, An Image Processing Based Triangular Similarity Measure Is Used For Pothole Dimension Estimation. The Proposed System Provides Reasonably Accurate Results Of Both Pothole Detection And Dimension Estimation. The Proposed System Also Helps In Reducing The Time Required For Road Maintenance. The System Uses A Custom Made Dataset Consisting Of Images Of Water-logged And Dry Potholes Of Various Shapes And Sizes.
In This Paper, Our Main Aim Is To Create A Medicinal Plant Identification System Using Deep Learning Concept. This System Will Classify The Medicinal Plant Species With High Accuracy. Identification And Classification Of Medicinal Plants Are Essential For Better Treatment. In This System We Are Going To Use Five Different Indian Medicinal Plant Species Namely Alstonia, Chinar, And Jamun (Naval)l. We Utilize Dataset Contains 58,280 Images, Includes Approximately 10,000 Images For Each Species. We Use Leaf Texture, Shape, And Color, Physiological Or Morphological As The Features Set Of The Data. The Data Are Collected By Us. We Use CNN Architecture To Train Our Data And Develop The System With High Accuracy. Several Model Architectures Were Trained, With The Best Performance Reaching A 95.67% Success Rate In Identifying The Corresponding Medicinal Plant. The Significantly High Success Rate Makes The Model A Very Useful Advisory Or Early Warning Tool.
The Leather Industry Plays A Crucial Role In Fashion, Manufacturing, And Luxury Goods, Where The Quality Of Leather Products Is Of Paramount Importance. Ensuring The Absence Of Defects In Leather Is A Fundamental Aspect Of Maintaining Product Quality. In This Context, We Present A Cutting-edge Approach To Leather Defect Detection Using Deep Learning Techniques. Our Research Leverages The Power Of Deep Neural Networks, Specifically Convolutional Neural Networks (CNNs), To Develop A Robust And Efficient System For Identifying And Classifying Defects In Leather Hides. We Employ State-of-the-art Image Analysis Methods To Process High-resolution Images Of Leather Surfaces, Enabling The Automated Detection Of Various Types Of Defects, Including Scars, Blemishes, Wrinkles, And Discolorations. This Paper Outlines The Design, Training, And Evaluation Of The Deep Learning Model, Highlighting Its Ability To Accurately And Rapidly Detect Defects With High Precision And Recall. The Proposed System Holds The Potential To Revolutionize Quality Control Processes Within The Leather Industry, Improving Product Quality, Reducing Waste, And Enhancing Overall Efficiency. As The Demand For High-quality Leather Products Continues To Grow, Our Work Demonstrates The Potential Of Deep Learning To Advance Quality Control And Defect Detection In This Industry, Ultimately Contributing To The Production Of Flawless Leather Goods.
The World Is Advancing Towards An Autonomous Environment At A Great Pace And It Has Become A Need Of An Hour, Especially During The Current Pandemic Situation. The Pandemic Has Hindered The Functioning Of Many Sectors, One Of Them Being Road Development And Maintenance. Creating A Safe Working Environment For Workers Is A Major Concern Of Road Maintenance During Such Difficult Times. This Can Be Achieved To Some Extent With The Help Of An Autonomous System That Will Aim At Reducing Human Dependency. In This Paper, One Of Such Systems, A Pothole Detection And Dimension Estimation, Is Proposed. The Proposed System Uses A Deep Learning Based Algorithm YOLO (You Only Look Once) For Pothole Detection. Further, An Image Processing Based Triangular Similarity Measure Is Used For Pothole Dimension Estimation. The Proposed System Provides Reasonably Accurate Results Of Both Pothole Detection And Dimension Estimation. The Proposed System Also Helps In Reducing The Time Required For Road Maintenance. The System Uses A Custom Made Dataset Consisting Of Images Of Water-logged And Dry Potholes Of Various Shapes And Sizes.
Images Captured In Low-light Conditions Are Often Disturbed By Low-light, Blur And Noise. Most Of The Conventional Image Enhancement Methods Are Less Robust Without Considering The Effectiveness Of The Blur And Noise. To Enhance Image Equality Under The Complex Environment, We Propose A Novel Image Enhancement Method Based On Joint Generative Adversarial Network (GAN) And Image Quality Assessment (IQA) Techniques. GAN Can Be Well Used For Image Enhancement In Low-light Case, But It Is Not Robust In Blur And Noise Case. IQA Method Uses CNN To Evaluate Each Enhanced Image Quality Based On Some Scores That Correlates Well With The Human Perception. The Scores Can Guide The GAN Learning For Further Enhancing The Image Quality. Instead Of L2-term Loss Function, We Define A Multi-term Loss Function For Its Minimization To Create A Good Image Estimate. Experimental Results Demonstrate The Proposed Method Is More Effective Than Current State-of-art Methods In Terms Of The Quantitative And Qualitative Evaluation.
Detection Of Diseases In Plants Is A Significant Task That Has To Be Done In Agriculture. This Is Something On Which The Economy Profoundly Depends. Infection Discovery In Plants Is A Significant Job In The Agribusiness Field, As Having Diseases In Plants Is Very Common. To Recognize The Diseases In Leaves, A Continuous Observation Of The Plants Is Required. This Observation Or Continuous Monitoring Of The Plants Takes A Lot Of Human Effort And It Is Time-consuming Too. To Make It Simply Some Sort Of Programmed Strategy Is Required To Observe The Plants. Program Based Identification Of Diseases In Plants Makes Easier To Detect The Damaged Leaves And Reduces Human Efforts And Time-saving. The Proposed Algorithm Distinguishing Sickness In Plants And Classify Them More Accurately As Compared To Existing Techniques.
Dogs Are One Of The Most Common Domestic Animals. Due To A Large Number Of Dogs, There Are Several Issues Such As Population Control, Decrease Outbreak Such As Rabies, Vaccination Control, And Legal Ownership. At Present, There Are Over 180 Dog Breeds. Each Dog Breed Has Specific Characteristics And Health Conditions. In Order To Provide Appropriate Treatments And Training, It Is Essential To Identify Individuals And Their Breeds. The Paper Presents The Classification Methods For Dog Breed Classification Using Two Image Processing Approaches 1) Conventional Based Approaches By Local Binary Pattern (LBP) And Histogram Of Oriented Gradient (HOG) 2) The Deep Learning Based Approach By Using Convolutional Neural Networks (CNN) With Transfer Learning. The Result Shows That Our Retrained CNN Model Performs Better In Classifying A Dog Breeds. It Achieves 96.75% Accuracy Compared With 79.25% Using The HOG Descriptor.
Detection Of Diseases In Plants Is A Significant Task That Has To Be Done In Agriculture. This Is Something On Which The Economy Profoundly Depends. Infection Discovery In Plants Is A Significant Job In The Agribusiness Field, As Having Diseases In Plants Is Very Common. To Recognize The Diseases In Leaves, A Continuous Observation Of The Plants Is Required. This Observation Or Continuous Monitoring Of The Plants Takes A Lot Of Human Effort And It Is Time-consuming Too. To Make It Simply Some Sort Of Programmed Strategy Is Required To Observe The Plants. Program Based Identification Of Diseases In Plants Makes Easier To Detect The Damaged Leaves And Reduces Human Efforts And Time-saving. The Proposed Algorithm Distinguishing Sickness In Plants And Classify Them More Accurately As Compared To Existing Techniques.
Historical Photographs Record The True Face Of A Moment In The Development Of Human History; They Have Authenticity, Vividness, And Unique Values. However, Due To Various Factors, Aging And Damage Will Occur. With The Development Of Computer Technology, The Restoration Technology Is More Used In Photo Restoration And Virtual Restoration Of Cultural Relics. This Paper First Analyzes The Principle Of Repairing Photo Archives Based On Computer Technology, And Then Uses The Combination Of Statistics And Computer Image Processing Technology To Detect And Repair The Scratches In Historical Photographs. And The Paper Establishes A Model Repair Framework, Which Provides A New Idea For The Repair Of Such Historical Photos. The Experimental Results Show That The Method Has A Significant Repair Effect.
One Of The Most Rapidly Spreading Cancers Among Various Other Types Of Cancers Known To Humans Is Skin Cancer. Melanoma Is The Worst And The Most Dangerous Type Of Skin Cancer That Appears Usually On The Skin Surface And Then Extends Deeper Into The Layers Of Skin. However, If Diagnosed At An Early Stage; The Survival Rate Of Melanoma Patients Is 96% With Simple And Economical Treatments. The Conventional Method Of Diagnosing Melanoma Involves Expert Dermatologists, Equipment, And Biopsies. To Avoid The Expensive Diagnosis, And To Assist Dermatologists, The Field Of Machine Learning Has Proven To Provide State Of The Art Solutions For Skin Cancer Detection At An Earlier Stage With High Accuracy. In This Paper, A Method For Skin Lesion Classification And Segmentation As Benign Or Malignant Is Proposed Using Image Processing And Machine Learning. A Novel Method Of Contrast Stretching Of Dermoscopic Images Based On The Methods Of Mean Values And Standard Deviation Of Pixels Is Proposed. Then The OTSU Thresholding Algorithm Is Applied For Image Segmentation.
Over The Last Decades, The Incidence Of Skin Cancer, Melanoma And Non-melanoma, Has Increased At A Continuous Rate. In Particular For Melanoma, The Deadliest Type Of Skin Cancer, Early Detection Is Important To Increase Patient Prognosis. Recently, Deep Neural Networks (DNNs) Have Become Viable To Deal With Skin Cancer Detection. In This Work, We Present A Smartphone-based Application To Assist On Skin Cancer Detection. This Application Is Based On A Convolutional Neural Network (CNN) Trained On Clinical Images And Patients Demographics, Both Collected From Smartphones. Also, As Skin Cancer Datasets Are Imbalanced, We Present An Approach, Based On The Mutation Operator Of Differential Evolution (DE) Algorithm, To Balance Data.In This Sense, Beyond Provides A flexible Tool To Assist Doctors On Skin Cancer Screening Phase, The Method Obtains Promising Results With A Balanced Accuracy Of 85% And A Recall Of 96%. Index Terms Skin Cancer Detection, Smartphone Application, Deep Learning, Convolutional Neural Network.
We do code in matlab for all domains, Image Processing, Simulink Design and Power Electronics.
Our Complete portfolio describes how stuff we are watch our demo @ Youtube Link.
2025 © All Rights Reserved. Site Map