Crop disease diagnosis is of great significance to crop yield and agricultural production. Optimization algorithms have become the main research direction to solve the issues related to diagnosis of crop diseases. Crop diseases are a major threat to global vegetable supply security, and the latest technologies need to be applied to the agriculture field to control diseases. This paper provides methodology en route for identification and classification of plant leaf ailments. Image acquisition, image preprocessing, feature extraction, feature selection, and eventually classification of plant diseases are all steps in the methodology. The training of a deep convolutional neural network to extract the features from the source image. An optimal set of features is selected using Populationbased incremental learning (PBIL) and are categorized into 20 various classes, containing together healthy and diseased categories. Presented method provides better classification accuracy.

Population-based incremental learning, CNN, Image acquisition, Feature extraction