A graph coloring approach for image segmentation

In this paper we develop a segmentation scheme for digital images based upon an iterative binary coloring technique that takes into account changing behavior of adjacent pixels. The output is a hierarchical structure of images which allows a better understanding of complex images. In particular, we propose two algorithms that should be considered as image preprocessing techniques.

[1]  J. Bezdek,et al.  Fuzzy partitions and relations; an axiomatic basis for clustering , 1978 .

[2]  Javier Yáñez,et al.  The robust coloring problem , 2003, Eur. J. Oper. Res..

[3]  Vincenzo Cutello,et al.  Fuzzy classification systems , 2004, Eur. J. Oper. Res..

[4]  J. Montero,et al.  On the principles of fuzzy classification , 1999, 18th International Conference of the North American Fuzzy Information Processing Society - NAFIPS (Cat. No.99TH8397).

[5]  Gregory S. Biging,et al.  Relevance and redundancy in fuzzy classification systems , 2001 .

[6]  Sankar K. Pal,et al.  Soft Computing for Image Processing , 2000 .

[7]  Etienne Kerre,et al.  Fuzzy techniques in image processing , 2000 .

[8]  Javier Montero,et al.  Spectral fuzzy classification: an application , 2002, IEEE Trans. Syst. Man Cybern. Part C.

[9]  James C. Bezdek,et al.  Pattern Recognition with Fuzzy Objective Function Algorithms , 1981, Advanced Applications in Pattern Recognition.

[10]  J. Montero,et al.  CLASSIFYING PIXELS BY MEANS OF FUZZY RELATIONS , 2000 .

[11]  Javier Yáñez,et al.  Coloring fuzzy graphs , 2005 .

[12]  P. Pardalos,et al.  The Graph Coloring Problem: A Bibliographic Survey , 1998 .

[13]  P. Pardalos,et al.  Handbook of Combinatorial Optimization , 1998 .

[14]  G. M. Foody The Continuum of Classification Fuzziness in Thematic Mapping , 1999 .