By Topic

A novel method for image retrieval in distributed multimedia system

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Sun, S.-X. ; Dept. of Comput. Sci., Univ. of Electron. Sci. & Technol. of China, Chengdu, China ; Huang, T.Y. ; Pang, C.Y.

With the development of Internet and multimedia technologies, Images retrieval based on their visual features becomes an important research area in distributed multimedia system. In this paper, we propose a new method for images retrieval by their visual appearance-Multi Scale Gauss-filtering Representation (MSGF). Images are first filtered in several scales with Gauss derivative filters, and the feature vectors are constructed on filtering outputs in several scales. Next, images are matched by their feature vectors, the matching results are scored and returned to user. We develop a fast search algorithm of index structure for local similarity retrieval of images. We then generalize the idea to a wide range of image retrieval by global similarity. Experiment shows that this method is effective in feature extraction and images retrieval by their visual appearance

Published in:

Computer Supported Cooperative Work in Design, The Sixth International Conference on, 2001

Date of Conference: