A novel feature extraction method for identifying quality seed selection
by M. Suganthi; J.G.R. Sathiaseelan
International Journal of Intelligent Engineering Informatics (IJIEI), Vol. 10, No. 5, 2022

Abstract: Nowadays, research works in the agriculture field have been widely incorporated and showing promising growth. Digital image mining techniques were used in this paper to test different seeds. Analysis of physical purity tells us the proportion of pure seed in many seeds. The software that allows seed images to be predicted on seed lots is developed with digital image mining techniques. As seeds are the main part of any cultivation, healthy seeds yield healthy crops. So, it becomes necessary to provide the farmers with healthy seeds. The seed disease, which is only classified into healthy and unhealthy seeds, is difficult for most farmers to describe. The seed's spatial, colour, texture, shape and statistical properties are connected to feature extraction. In order to get the best results, this study utilises a brand-new feature extraction technique for classifying high-quality seeds. It was concluded that Bresenham's Line Technique plus a few textural qualities might be utilised to compare the digital differential analyser (DDA) line drawing algorithm and determine the seed type.

Online publication date: Fri, 17-Feb-2023

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Intelligent Engineering Informatics (IJIEI):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com