Deep Neural Network Classifier for Detecting Cotton Plant Diseases Using Antlion Optimization

Abstract

Image processing techniques are used to autonomously identify agricultural plant diseases can significantly reduce reliance on farmers for safeguarding crop yields. The classification of cotton leaf diseases presents a formidable challenge. This study introduces a novel approach for classifying Cotton Leaf Diseases, employing an Antlion Optimization (ALO)-enhanced Deep Neural Network (DNN) classifier. The dataset comprises 10,000 images, a combination of directly captured farm field images and downloaded samples, encompassing normal leaves, bacterial blight, Anthracnose, Cercospora leaf spot, and Alternaria diseases. Preprocessing incorporates Wiener filtering to eliminate image noise, while Fuzzy Rough C-Means (FRCM) clustering is employed for diseased and normal portion segmentation. The ALO-augmented DNN achieves an impressive 93.37% accuracy in classifying cotton leaf diseases.