A novel attention based vision transformer optimized with hybrid optimization algorithm for turmeric leaf disease detection

Turmeric leaf disease detection is essential to maintain the crop health and optimize the yield. Through early identification disease can be controlled and its relevant economic losses can be avoided. However, the existing methods for leaf disease detection exhibit limitations in extracting complex leaf features which leads to lower classification accuracy. Also, the existing models often struggle to process the fine details in turmeric leaves which further reduces the reliability in real-world applications. The objective of this research is overcome these limitations through a novel leaf disease detection model which incorporates Vision Transformer (ViT) with hybrid Falcon-Bowerbird Optimization (FBO). The proposed approach aimed to attain improved feature extraction abilities which enhances the overall performance of turmeric leaf diseases detection process. In the first step turmeric images are preprocessed histogram equalization to highlight the complex features like leaf texture and color intensity then the image is divided into non-overlapping patches. The Vision Transformer process each patch as a token through a self-attention mechanism so that the most relevant patches can be processed to extract the essential features. The Hybrid Falcon-Bowerbird Optimization further enhance the convergence speed and fine-tune the hyperparameters to attain improved detection performances. Using turmeric leaf disease dataset, the performance of the proposed model is evaluated through metrics like precision, recall, F1-score and accuracy. With an accuracy of 97.03%, the proposed model outperforms AlexNet which achieved 95.5%, and optimized MobileNetv3 which achieved 96.8%. The proposed hybrid optimized ViT model attained superior performance in turmeric leaf disease detection in terms of accuracy compared to existing techniques.