Rice Leaf Disease Detection using Image Recognition and Convolutional Neural Networks

Devendra Bangde1
Prof. Kanifnath S Satav2
Student, MBA Department Professor, MBA Department
Dhole Patil College of Engineering, PuneDholePatil College of Engineering, Pune

Abstract:Rice is a fundamental food crop sustaining more than 50% of the global population. However, its production is significantly affected by various leaf diseases such as bacterial blight, brown spot, and leaf smut. Early and accurate detection of these diseases is essential tominimize yield loss and ensure food security. Traditional disease identification methods rely heavily on manual inspection by agricultural experts, which is time consuming, subjective, and not scalable. This research proposes a deep learning-based automated system for rice leaf disease detection using imagerecognition techniques. Multiple Convolutional Neural  Network (CNN) architectures, including MobileNetV2,VGG16, ResNet50, EfficientNetB0, and a custom CNN, were implemented and evaluated on a labeled dataset of rice leaf images. The models were assessed using performance metrics such as accuracy, precision, recall, and F1-score.Experimental results indicate that MobileNetV2 achieved the highest performance with an accuracy of 83.33% and F1-score of 0.8372, demonstrating its effectiveness in real-time applications due to its lightweight architecture. The study highlights the importance of transfer learning and optimized architectures for agricultural disease detection systems.Keywords: Deep Learning, Rice Leaf Disease, CNN,Transfer Learning, Image Classification, Precision Agriculture