Cotton and Soybean Plant Leaf Dataset Generation for Multiclass Disease Classification

Cotton and soybeans are important crops for the country's economic growth. Due to the rapid spread of disease, plants are susceptible to bacterial and viral diseases. Early identification and classification using machine or deep learning models aid farmers in reducing potential losses. Model-based detection necessitates a large number of training samples and high-quality images. Thus, this study generates new datasets to diagnose soybean and cotton plant diseases. The images are collected with the help of the Central Institute for Cotton Research (CICR) in Nagpur, Maharashtra, to create a clean and comprehensive dataset for research purposes. The dataset contains 5200 images, including both diseased and healthy images. The collected images are labelled using the Robo flow tool, masked with the Photoshop tool and stored in the dataset. The generated dataset is examined through pre-processing and classification using the novel proposed algorithms. Initially, the Gabor filter is used for pre-processing to eliminate unwanted noise from the collected images. Afterwards, the Position attention-based capsule network (PA-CapNet) model is proposed to perform multidisease classification for the soybean and cotton datasets. Finally, the performances are assessed by evaluating varied metrics. The result analysis shows that the proposed method obtains better results than the other existing models. The proposed method obtains an accuracy of 98% for the soybean dataset and 96.89% for the cotton dataset.