COLOR IMAGE SEGMENTATION USING COMPETITIVE LEARNING

Authors
UCHIYAMA T ARBIB MA
Citation
T. Uchiyama et Ma. Arbib, COLOR IMAGE SEGMENTATION USING COMPETITIVE LEARNING, IEEE transactions on pattern analysis and machine intelligence, 16(12), 1994, pp. 1197-1206
Citations number
25
Categorie Soggetti
Computer Sciences","Computer Science Artificial Intelligence","Engineering, Eletrical & Electronic
Journal title
IEEE transactions on pattern analysis and machine intelligence → ACNP
ISSN journal
01628828
Volume
16
Issue
12
Year of publication
1994
Pages
1197 - 1206
Database
ISI
SICI code
0162-8828(1994)16:12<1197:CISUCL>2.0.ZU;2-A
Abstract
This paper presents a color image segmentation method which divides co lor space into clusters. Competitive learning is used as a tool for cl ustering color space based on the least sum of squares criterion. We s how that competitive learning converges to approximate the optimum sol ution based on this criterion theoretically and experimentally. We app lied this method to various color scenes and show its efficiency as a color image segmentation method. We also show the effects of using dif ferent color coordinates to be clustered by some experimental results.