Image semantic classification by using SVM

Wan, Hua-Lin and Chowdhury, Morshed 2003, Image semantic classification by using SVM, Journal of software, vol. 14, no. 11, pp. 1891-1899.

Attached Files
Name Description MIMEType Size Downloads

Title Image semantic classification by using SVM
Author(s) Wan, Hua-Lin
Chowdhury, Morshed
Journal name Journal of software
Volume number 14
Issue number 11
Start page 1891
End page 1899
Publisher Chinese Academy of Sciences, Institute of Software
Place of publication Beijing, China
Publication date 2003
ISSN 1000-9825
Keyword(s) content-based
image feature descriptor
color
texture
edge
classification
SVM
Summary There exists an enormous gap between low-level visual feature and high-level semantic information, and the accuracy of content-based image classification and retrieval depends greatly on the description of low-level visual features. Taking this into consideration, a novel texture and edge descriptor is proposed in this paper, which can be represented with a histogram. Furthermore, with the incorporation of the color, texture and edge histograms searnlessly, the images are grouped into semantic classes using a support vector machine (SVM). Experiment results show that the combination descriptor is more discriminative than other feature descriptors such as Gabor texture.
Language eng
Field of Research 080106 Image Processing
HERDC Research category C1 Refereed article in a scholarly journal
Copyright notice ©2003, Journal of Software
Persistent URL http://hdl.handle.net/10536/DRO/DU:30008594

Document type: Journal Article
Collection: School of Information Technology
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 34 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 2088 Abstract Views, 0 File Downloads  -  Detailed Statistics
Created: Mon, 13 Oct 2008, 15:36:31 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.