Published Paper Details:

Cotton is a critical cash crop, and its yield is significantly affected by various leaf diseases. Early and accurate recognition of these diseases is essential for mitigating damage and ensuring sustainable agricultural productivity. In this paper, we propose a hybrid CNN-LSTM (Convolutional Neural Network - Long Short-Term Memory) model for automated cotton leaf disease recognition. The model leverages the feature extraction capability of CNN to capture spatial patterns from input images, followed by the LSTM to process sequential features and detect temporal dependencies in the disease progression. An attention mechanism is integrated to focus on critical disease-specific features, further enhancing recognition accuracy. The model is trained and tested on a subset of the Plant Village dataset, comprising images of healthy and diseased cotton leaves, including common diseases like bacterial blight, fungal infections, and leaf curl virus. Data augmentation techniques are applied to enhance the robustness of the model, making it suitable for real-world field conditions. The proposed model achieves high accuracy, precision, and recall, outperforming conventional CNN-based approaches. This work demonstrates the potential of hybrid deep learning models in precision agriculture, offering an efficient and scalable solution for early disease detection and crop management.