Automatic methods for classification of visual based viral and bacterial disease symptoms in plants

In this research, machine vision system is developed for the automatic identification of plant disease symptoms, from color images. Visual symptoms based identification of viral and bacterial diseases in plants using image processing and pattern classification is presented. Viral and bacterial plant...

Full description

Saved in:
Bibliographic Details
Published in:International journal of information technology (Singapore. Online) 2022-02, Vol.14 (1), p.287-299
Main Authors: Yakkundimath, Rajesh, Saunshi, Girish, Palaiah, Surendra
Format: Article
Language:English
Subjects:
Artificial Intelligence
Computer Imaging
Computer Science
Image Processing and Computer Vision
Machine Learning
Original Research
Pattern Recognition and Graphics
Software Engineering
Vision
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this research, machine vision system is developed for the automatic identification of plant disease symptoms, from color images. Visual symptoms based identification of viral and bacterial diseases in plants using image processing and pattern classification is presented. Viral and bacterial plant disease symptoms affecting leaf, stem and fruit are segmented and features are selected based on co-occurrence based multispectral approach and co-occurrence based color moments approach. The artificial neural network (ANN), support vector machine (SVM) and convolutional neural network (CNN) are deployed for image-based disease symptoms classification. The maximum mean classification result of 90.72% is achieved using co-occurrence based color moments approach with SVM, on the held-out dataset comprising 4000 images of 20 plant disease symptoms. The method developed has shown applications in building intelligent systems which can be used automatically to identify the visual symptoms of plant disease and assist farmers.
ISSN:2511-2104
2511-2112
DOI:10.1007/s41870-021-00701-2