Nutrient Deficiency Detection In Paddy Crop Using Leaf Images

Abstract

The Early Detection Of Nutrient Deficiencies In Paddy Crops Is Essential For Improving Crop Yield And Ensuring Sustainable Agricultural Practices. Traditional Methods Rely On Manual Observation And Expert Knowledge, Which Can Be Time-consuming, Costly, And Prone To Errors. This Paper Presents A Deep Learning Based Approach To Detect Nitrogen (N), Phosphorus (P), And Potassium (K) Deficiencies Using Paddy Leaf Images. The Proposed System Utilizes A MobileNetV2 Transfer Learning Model For Accurate Image Classification. Image Pre-processing Techniques Such As Resizing, Normalisation, And Data Augmentation Are Applied To Enhance Model Performance. The System Is Implemented As A Web-based Application Using HTML, CSS, JavaScript, And Python Flask, Allowing Users To Upload Leaf Images And Receive Real-time Predictions Along With Confidence Scores. Additionally, The System Provides Fertilizer Recommendations And Generates PDF Reports For Future Reference. The Model Achieves High Classification Accuracy, Demonstrating Its Effectiveness In Identifying Nutrient Deficiencies And Supporting Precision Agriculture.

Keywords