Detection of Leaf Diseases in Soybean Plant using Autoencoder and Multinomial Logistic Regression

Background: Soybean is one of the important leguminous crops grown mainly in the middle states of India. Soybean plants are prone to leaf diseases like spot and bacterial blight. Early detection of such diseases is an important task for the farmers to avoid loss in production. In this background, deep learning techniques are used for identifying the diseases in leaves of Soybean plants. Methods: This study investigates the utilization of convolutional autoencoder in extracting features from the lesion leaf images. Images are preprocessed and converted to latent space features using convolutional autoencoder. Multinomial logistic regression model is employed over the extracted features to find the type of disease in Soybean plants. Result: The experimental result shows that convolutional autoencoder model along with multinomial logistic regression model achieves an average accuracy of 92% in disease identification. In addition to providing disease identification, the ideas in this paper provide support for food security through the application of deep learning techniques.