Production of crops with better quality is the necessary attribute for the economic growth of any country. The agricultural sector provides employment to many people and accounts for major portion of gross domestic product in many countries around the world. Therefore, for enhanced agricultural productivity the detection of diseases in plants at an early stage is quite significant. The traditional approaches for disease detection in plants required considerable amount of time, intense research, and constant monitoring of the farm. However, optimized solutions have been obtained over the past few years due to technological advances that have resulted in better yields for the farmers. Machine learning and image processing are used to detect the disease on the agricultural harvest. The image processing steps for plant disease identification include acquiring of images, pre-processing, segmentation and feature extraction. In this review paper, we focused mainly on the most utilized classification mechanisms in disease detection of plants such as Convolutional Neural Network, Support Vector Machine, KNearest Neighbor, and Artificial Neural Network. It has been observed from the analysis that Convolutional Neural Network approach provides better accuracy compared to the traditional approaches.
Plant disease detection using hybrid model based on convolutional autoencoder and convolutional neural network
