CottonLeafVision: An Explainable and Robust Deep Learning Framework for Cotton Leaf Disease Classification
2026-06-12 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial Intelligence
AI summaryⓘ
The authors created a computer program called CottonLeafVision to help identify diseases on cotton leaves, which is important for farmers and the economy. They tested different advanced image recognition models and found that DenseNet201 worked best, correctly identifying diseases 98% of the time. To make the program more reliable and easier to understand, they used special techniques like Grad-CAM and tried to make it resistant to errors caused by noise. They also built a prototype to apply their model in real farming situations. Overall, their work shows how deep learning can help manage cotton leaf diseases effectively.
cotton leaf diseasedeep convolutional neural networksDenseNet201image classificationGrad-CAMocclusion sensitivityadversarial trainingpretrained modelsprototype development
Authors
Rafi Ahamed, Md. Abir Rahman, Tasnia Tarannum Roza, Munaia Jannat Easha, Md. Asif Khan, Sudeepta Mandal
Abstract
Globally, cotton is a highly economically beneficial crop, as the textile industry heavily depends on it. So, the precise identification and detection of cotton leaf disease is crucial for economic stability. The development goal of "CottonLeafVision" is to accurately classify and detect cotton leaf disease. With this goal, we have evaluated multiple pretrained Deep Convolutional Neural Networks, including DenseNet201, InceptionV3, and VGG19 on a publicly available cotton leaf disease image dataset. This image dataset includes seven classes, six disease classes, and one healthy class, collected under various field conditions reflecting real-world challenges. Among these pretrained models, with DenseNet201, we have achieved the highest classification accuracy of 98%. To enhance the model reliability and interpretability, we have implemented different techniques and methods such as Gradient-weighted Class Activation Mapping (Grad-CAM), occlusion sensitivity analysis and adversarial training to increase the noise resistance of the model. Finally, we have developed a prototype in order to utilize the model's capabilities on real life agriculture. This paper shows the deep learning model's capabilities to classify the disease in real-life cotton disease management situations.