Published January 21, 2008 | Version 12161

Color Image Segmentation Using Competitive and Cooperative Learning Approach

Authors/Creators

Description

Color image segmentation can be considered as a cluster procedure in feature space. k-means and its adaptive version, i.e. competitive learning approach are powerful tools for data clustering. But k-means and competitive learning suffer from several drawbacks such as dead-unit problem and need to pre-specify number of cluster. In this paper, we will explore to use competitive and cooperative learning approach to perform color image segmentation. In competitive and cooperative learning approach, seed points not only compete each other, but also the winner will dynamically select several nearest competitors to form a cooperative team to adapt to the input together, finally it can automatically select the correct number of cluster and avoid the dead-units problem. Experimental results show that CCL can obtain better segmentation result.

Files

12161.pdf

Files (1.6 MB)

Name Size
md5:a5f093583d09c71e4b5bee6bf8fb510b
1.6 MB Preview Download

Additional details

References

  • N. R. Pal, S.K. Pal, "A review on image segmentation techniques," Pattern Recognition, vol. 26, pp. 1277-1291, Sep. 1993.
  • H. D. Chen, X. H. Jiang, Y. Sun, J.L. Wang, "Color image segmentation: advances and prospects," Pattern Recognition, vol. 34, pp. 2259-2281, 2001.
  • T. Uchiyama, M. A. Arbib, "Color image segmentation using competitive learning," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, Dec. 1994, pp.1197-1206.
  • D. Comanniciu, E. Meer, "Robust analysis of feature space: color image segmentation," in In Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Puerto Rico, 1997, pp. 750-755.
  • H. Palus, M. Bogdanski, "Clustering techniques in color image segmentation," in Proc. of Methods of Artificial Intelligence, Gliwice, Poland, 2003, pp. 103-104.
  • D. E. Rumelhart, D. Zipser, "Feature discovery by competitive learning," Cognitive Science, vol. 9, pp. 75-112, 1985.
  • L. Xu, A. Krzyzak, E. Oja, "Rival penalized competitive learning for clustering analysis, RBF net, and curve detection," IEEE Trans. Neural Network, vol. 4, pp.636-649, July, 1993.
  • S. C. Ahalt, A. K. Krishnamurthy, P. Chen, D. E. Melton, "Competitive learning algorithms for vector quantization," Neural Networks, vol. 3, pp. 277-291, 1990.
  • Y. M. Cheung, "A competitive and cooperative learning approach to robust data clustering," Dept. of Computer Science, Hong Kong Baptist University, Technical Report: COMP-03-021, 2003. [10] Y. Ohta, T. Kanade, T. Sakai, "Color information for region segmentation," Computer Graphics Image Process. vol. 13, pp. 222-241, 1980.