The detection and diagnosis of plant leaf diseases is a major concern in agriculture. Farmers need to track crop fields and recognize signs of disease at early as possible. The images processing is an aid to the identification and classification of leaf diseases. For the identification of leaf disease, there are three image features, i.e., texture, color, and shape. Textures are the most important feature out of the three. Image features value entered in CNN. The k-fold methods are used for train the model greater accuracy evaluation. The image features provide input for the identification of a disease and are reliable using the GLCM algorithm. CNN provides 92.53 % accuracy.