A twin CNN-based framework for optimized rice leaf disease classification with feature fusion

This paper presents a novel Twin Convolutional Neural Network (CNN)-based framework for classifying rice leaf diseases. The framework integrates an optimized feature fusion algorithm using pre-trained CNN models to improve disease detection accuracy. Rice leaf images are processed to classify plants as either healthy or diseased with greater accuracy compared to conventional methods. Experiments conducted on publicly available datasets demonstrate that the proposed Twin CNN architecture, combined with a robust feature fusion mechanism, outperforms existing methods in terms of accuracy and computational efficiency. The proposed framework shows promising results for real-world applications in precision agriculture.