Plant Disease Classification using Residual Networks with MATLAB

Main Article Content

N.Alivelu Manga, et. al.


In a developing country like India, agricultural production mainly depends on smallholder farmers and more than 50% yield loss due to pests and various diseases affected by plants. Diseases can be managed by identifying the diseases as soon as it appears on the plant. In addition, the digital era makes the diagnosis information of any disease available at the fingertips. In other words, smartphones with high resolution cameras can aid in identification of a plant disease through images and thereby help in early diagnosis of the disease. This paper makes an attempt at resolving the present problem of undiagnosed plant diseases using Deep Learning for detecting and classifying the plant diseases using images of the plant. This helps the farmers to take necessary action to avoid the disease from aggravating without having to wait for an agriculturist to identify and resolve the problem.

In a nutshell, the paper aims at designing a Deep Learning model for the classification of an image of plant disease. The algorithm makes use of a Convolutional Neural Network with Residual Network architecture, commonly known as ResNet using Matrix Laboratory (MATLAB). The model will be trained using a public dataset of 54,305 colour images of diseased and healthy plants which when segregated result in 38 classes.


Download data is not yet available.


Metrics Loading ...

Article Details

How to Cite
et. al., N. M. . (2021). Plant Disease Classification using Residual Networks with MATLAB. Turkish Journal of Computer and Mathematics Education (TURCOMAT), 12(10), 3923–3933. Retrieved from