By Topic

Fuzzy-ART based image compression for hardware implementation

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

4 Author(s)
Lim, C.S. ; Centre for High Performance Embedded Syst., Nanyang Technol. Univ., Singapore ; Srikanthan, T. ; Asari, K.V. ; Lam, S.K.

A novel VLSI efficient image compression technique employing fuzzy-ART neural network and 2D run-length encoding is presented. This technique involves the segmentation of the original image into smaller regular blocks and these blocks are subsequently applied to the fuzzy-ART network for classification. The class indices generated by the fuzzy-ART network are further reduced with 2D run-length encoding. For the implementation of the fuzzy-ART network in VLSI, a force class fuzzy-ART network had been derived, where the maximum number of possible output classes is fixed. In this new network, input vectors will be forced into its closest class, when all classes are occupied. The results for force class fuzzy-Art network demonstrate that it is capable of large compression ratios and this network can easily be ported into hardware architecture.

Published in:

Circuits and Systems, 2002. APCCAS '02. 2002 Asia-Pacific Conference on  (Volume:2 )

Date of Conference: