A comprehensive review of deep learning models for plant disease identification and prediction. (28th May 2021)

• Record Type: Journal Article
• Authors: Rathore, Narendra Pal Singh; Prasad, Lalji
• Is Part Of: International journal of engineering systems modelling and simulation. Volume 12:Number 2/3(2021)
• Page Start: 165
• Page End: 179
• Publication Date: 2021-05-28
• Subjects: machine learning -- deep learning -- convolutional neural network -- CNN -- deep-CNN -- crop disease; Engineering systems -- Computer simulation -- Periodicals; Engineering systems -- Mathematical models -- Periodicals; 620.0042
• Languages: English
• ISSNs: 1755-9758

Abstract

Deep learning is providing importance in all fields of real-world problems due to its adaptive and flexible features. A lot of researchers have published their work for detecting crop diseases using deep learning algorithms, especially for early detection of the disease so that crops can be saved, and farmers can take decision on-time for saving crop loss. This paper aims to provide the survey of deep learning models for different types of crop disease detection. The paper introduces deep learning and its various models that can be used for various types of crop disease detection namely wheat, rice, tomato, vine leaf, and cassava. The basic framework of this study is about how deep learning algorithms work on disease detection of plants, i.e., preprocessing of images, segmentation, and post processing. The purpose of this paper is to provide an exhaustive review on available deep learning techniques for plant diseases detection along with a comparative analysis of existing techniques. The paper also demonstrates experimental analysis performed on potato images for the prediction of diseases using a convolution neural network.