Classification and recognition of soyabean leaf disease detection using Convolutional neural network (CNN)

Abstract

The majority of agricultural research is focused on the classification and detection of crop disease. This study is based on the use of deep learning in image processing for the classification of various soybean leaf diseases. This study has proposed a Convolutional Neural Network (CNN)-based technique for soyabean leaf classification and detection. CNN is used in back word propagation for training the algorithms in order to improve accuracy and the overall system produces better results with higher accuracy. In order to segment the diseased portion, texture segmentation is accomplished through the utilization of k-means clustering. The confusion matrix is computed by using the neural network toolbox. This research employs a standard data set of soybean leaves as well as real-time data collection. Keywords - Convolutional neural network (CNN), disease detection, Texture segmentation.