A novel feature extraction method for identifying quality seed selection. (5th February 2023)

• Record Type: Journal Article
• Authors: Suganthi, M.; Sathiaseelan, J.G.R.
• Is Part Of: International journal of intelligent engineering informatics. Volume 10:Number 5(2022)
• Page Start: 359
• Page End: 378
• Publication Date: 2023-02-05
• Subjects: image mining -- feature extraction -- seeds -- MSE -- mean square error Bresenham's line algorithm -- SSIM -- structural similarity index metric -- DDA -- digital differential analyser -- PSNR -- peak signal to noise ratio; Artificial intelligence -- Engineering applications -- Periodicals; Engineering -- Computer programs -- Periodicals; Knowledge management -- Periodicals; 620.0028563
• Languages: English
• ISSNs: 1758-8715

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.