Application to the Image Coding by the Modified Fuzzy Cornpetitive Iing Network


The Transactions of the Korea Information Processing Society (1994 ~ 2000), Vol. 5, No. 7, pp. 1933-1942, Jul. 1998
10.3745/KIPSTE.1998.5.7.1933,   PDF Download:

Abstract

In designing a subcode book of the Classified Vector Quantization (CVQ), the Competitive Learning Network has a weakness to ignore some code vectors with considerate membership, because of their binary representation. Fuzzy Competitive Learning Network corrects such weakness with an adoption of the concept that each cluster has its continuous membership. But the algorithm must determine the size of subcode book by applying a trial and error procedure. In this paper, modified fuzzy competitive learning network, which has continuous membership extending binary membership, is proposed, as an algorithms applying to CVQ. The proposed algorithm yields an adaptive determination of the size of each subcode book according to the given sample vector in learning process, and prevents the designed subcode book from coming to a local minimum point by applying fuzzy concept to the competitive learning algorithm.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
L. B. Ro and C. C. Hyun, "Application to the Image Coding by the Modified Fuzzy Cornpetitive Iing Network," The Transactions of the Korea Information Processing Society (1994 ~ 2000), vol. 5, no. 7, pp. 1933-1942, 1998. DOI: 10.3745/KIPSTE.1998.5.7.1933.

[ACM Style]
Lee Bum Ro and Chung Chin Hyun. 1998. Application to the Image Coding by the Modified Fuzzy Cornpetitive Iing Network. The Transactions of the Korea Information Processing Society (1994 ~ 2000), 5, 7, (1998), 1933-1942. DOI: 10.3745/KIPSTE.1998.5.7.1933.