Study on skin color image segmentation used by Fuzzy-c-means arithmetic

Skin color image segmentation is an important part in skin image analysis. Segmentation feature parameter and segmentation arithmetic significantly influence the segmentation result. In this article, we compared RGB, HSV, and Lab color spaces and found that HSV color space as segmentation feature parameter has the advantage. Furthermore, we used an improved Fuzzy-c-means arithmetic (IFCM) in skin color image segmentation and found that the new method improved the segmentation results.

[1]  Yves Vander Haeghen,et al.  An imaging system with calibrated color image acquisition for use in dermatology , 2000, IEEE Transactions on Medical Imaging.

[2]  G. Piérard,et al.  Quantification of skin color in patients undergoing maintenance hemodialysis. , 1992, Journal of the American Academy of Dermatology.

[3]  Ying Liu,et al.  Study on digital imaging colorimeter in dermatology , 2004, The Second Asian and Pacific Rim Symposium on Biophotonics, 2004. APBP 2004..

[4]  Jerry L. Prince,et al.  Adaptive fuzzy segmentation of magnetic resonance images , 1999, IEEE Transactions on Medical Imaging.

[5]  W. A. Sandham,et al.  Fuzzy clustering based applications to medical image segmentation , 2003, Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No.03CH37439).

[6]  H. Schaefer,et al.  Quantification of skin‐colour changes induced by topical corticosteroid preparations using the Minolta Chroma Meter , 1991, The British journal of dermatology.