Efficient and fast multi layer statistical approach for colour based image retrieval

In this paper a new efficient and fast technique for colour-based image retrieval is presented. The technique is based on utilizing singular feature in a multi layer system (SFMLSA). The colour features are extracted from image query and images database then distance measure based on city block is u...

Full description

Bibliographic Details
Main Authors: Odeh, , JQ, Johari,, R, Othman,, M, Ahmad,, F
Format: Article
Published: 2003
Subjects:
Online Access:http://shdl.mmu.edu.my/2596/
_version_ 1848790098435375104
author Odeh, , JQ
Johari,, R
Othman,, M
Ahmad,, F
author_facet Odeh, , JQ
Johari,, R
Othman,, M
Ahmad,, F
author_sort Odeh, , JQ
building MMU Institutional Repository
collection Online Access
description In this paper a new efficient and fast technique for colour-based image retrieval is presented. The technique is based on utilizing singular feature in a multi layer system (SFMLSA). The colour features are extracted from image query and images database then distance measure based on city block is used to filter a set of images in each layer. Our approach attempts to overcome the computational complexity of applying bin-to-bin comparison as a multi dimensional feature vectors in the colour histogram approach. Furthermore, the proposed technique eliminate the needs of using the weight matrix, which is usually applied when more than one feature is combined together to judge on the similarity. This needs pre-knowledge of the conditions under which the images are captured. Throughout this paper a comparative study is carried out to examine the performance of the proposed approach with reference to an information theoretic approach using entropy as a discriminator for huge image database. Moreover, we examined the possibility of using the eigenvalues as a discernment feature for colour images, so we developed the necessary algorithms to test this approach. Different database sets has been used and the related algorithms are presented.
first_indexed 2025-11-14T18:07:13Z
format Article
id mmu-2596
institution Multimedia University
institution_category Local University
last_indexed 2025-11-14T18:07:13Z
publishDate 2003
recordtype eprints
repository_type Digital Repository
spelling mmu-25962011-08-24T00:12:43Z http://shdl.mmu.edu.my/2596/ Efficient and fast multi layer statistical approach for colour based image retrieval Odeh, , JQ Johari,, R Othman,, M Ahmad,, F QA75.5-76.95 Electronic computers. Computer science In this paper a new efficient and fast technique for colour-based image retrieval is presented. The technique is based on utilizing singular feature in a multi layer system (SFMLSA). The colour features are extracted from image query and images database then distance measure based on city block is used to filter a set of images in each layer. Our approach attempts to overcome the computational complexity of applying bin-to-bin comparison as a multi dimensional feature vectors in the colour histogram approach. Furthermore, the proposed technique eliminate the needs of using the weight matrix, which is usually applied when more than one feature is combined together to judge on the similarity. This needs pre-knowledge of the conditions under which the images are captured. Throughout this paper a comparative study is carried out to examine the performance of the proposed approach with reference to an information theoretic approach using entropy as a discriminator for huge image database. Moreover, we examined the possibility of using the eigenvalues as a discernment feature for colour images, so we developed the necessary algorithms to test this approach. Different database sets has been used and the related algorithms are presented. 2003 Article NonPeerReviewed Odeh, , JQ and Johari,, R and Othman,, M and Ahmad,, F (2003) Efficient and fast multi layer statistical approach for colour based image retrieval. DIGITAL LIBRARIES: TECHNOLOGY AND MANAGEMENT OF INDIGENOUS KNOWLEDGE FOR GLOBAL ACCESS, 2911 . pp. 134-148. ISSN 0302-9743
spellingShingle QA75.5-76.95 Electronic computers. Computer science
Odeh, , JQ
Johari,, R
Othman,, M
Ahmad,, F
Efficient and fast multi layer statistical approach for colour based image retrieval
title Efficient and fast multi layer statistical approach for colour based image retrieval
title_full Efficient and fast multi layer statistical approach for colour based image retrieval
title_fullStr Efficient and fast multi layer statistical approach for colour based image retrieval
title_full_unstemmed Efficient and fast multi layer statistical approach for colour based image retrieval
title_short Efficient and fast multi layer statistical approach for colour based image retrieval
title_sort efficient and fast multi layer statistical approach for colour based image retrieval
topic QA75.5-76.95 Electronic computers. Computer science
url http://shdl.mmu.edu.my/2596/