Integration of a three-colour channel with the four diagonals of the GLCM approach for similar image retrieval. (3rd February 2023)

• Record Type: Journal Article
• Authors: Bosco, P. John
• Is Part Of: International journal of intelligent engineering informatics. Volume 10:Number 4(2022)
• Page Start: 271
• Page End: 289
• Publication Date: 2023-02-03
• Subjects: content based image retrieval (CBIR) -- colour feature: texture feature -- integration of three colours with diagonal approach method (ITDM) -- GLCM -- RGB; Artificial intelligence -- Engineering applications -- Periodicals; Engineering -- Computer programs -- Periodicals; Knowledge management -- Periodicals; 620.0028563
• Languages: English
• ISSNs: 1758-8715

Abstract

Feature extractions are perceptive problems due to differences of opinion in image assets and contents. An image has strong texture and colour channels, i.e., a gray-level cooccurrence matrix (GLCM) and a Red, Green and Blue (RGB) channel. We proposed an algorithm for the integration of three colours with diagonal approach method (ITDM) in combined colour and GLCM significant image features, which are used for image retrieval and reduced time. It has four steps: 1) Extract the colour channel, which is RGB, YCbCr, and L* a* b*; 2) Extract the colour channel of G, Y, and L*; 3) Apply the GLCM method in the G, Y, and L* channels and 4) Image features are based on the classification of features by the C-means algorithm and re-ranking methods. To develop an image, simplify the computation of image retrieval methods. A series of analyses and comparisons are performed in the experiment and proven to enhance the retrieval rate.