Revolutionizing Crop Disease Management Fine-Tuned Integrated Convolutional Attention Capsule Autoencoder for Automated Paddy Leaf Disease Identification

Abstract

Crop diseases are a major threat to food security and agricultural productivity. Early and accurate detection of crop diseases is essential for effective disease management and prevention. However, conventional methods of crop disease identification are time-consuming, labor-intensive, and require expert knowledge. Therefore, there is a need for developing automated and reliable methods of crop disease identification using advanced technologies such as artificial intelligence (AI). In this paper, we propose a novel AI-based method for automated paddy leaf disease identification using fine-tuned integrated convolutional attention capsule autoencoder (FICACA). FICACA is a deep learning model that combines the advantages of convolutional neural networks (CNNs), attention mechanisms, capsule networks, and autoencoders to extract and encode discriminative features from paddy leaf images. FICACA can identify 10 common paddy leaf diseases with high accuracy and efficiency. We evaluate the performance of FICACA on a large-scale dataset of paddy leaf images collected from different regions and seasons. We compare FICACA with several state-of-the-art methods and demonstrate its superiority in terms of accuracy, robustness, and generalization. We also conduct ablation studies to analyze the contribution of each component of FICACA. Our results show that FICACA can revolutionize crop disease management by providing a fast and accurate solution for paddy leaf disease identification.