Title :
Color Segmentation for Skin Lesions Classification
Author :
Masood, N.A. ; Mashali, H.M. ; Mohamed, Abdalla S A
Author_Institution :
Dept. of Med. Eng., Menia Univ., Menia
Abstract :
Differential diagnosis of Erythemato-Squamos diseases is considered a real problem in dermatology. They all share the clinical features of erythematic and scaling, with very little differences. This paper introduces an unsupervised color segmentation procedure applied to one disease of this group named Atopic Dermatitis. Evaluation of different color models is done to select the most appropriate model for representing skin lesions. Two steps of color segmentation were done to detect skin lesions with less computation. First is coarse segmentation with optimal threshold of the CIE color model, and second is fine segmentation with K-means clustering technique. Results of the proposed algorithm prove its success as the manual segmentation with expertise.
Keywords :
biomedical optical imaging; feature extraction; image classification; image colour analysis; image representation; image segmentation; pattern clustering; skin; unsupervised learning; Atopic Dermatitis; CIE color models; Erythemato-Squamos diseases; K-means clustering technique; clinical feature extraction; dermatology; differential diagnosis; image representation; skin lesion classification; unsupervised color segmentation; Biological system modeling; Biomedical engineering; Biomedical imaging; Diseases; Humans; Image color analysis; Image segmentation; Lesions; Medical diagnostic imaging; Skin; K-means clustering; color models; image segmentation; optimal threshold; skin lesions;
Conference_Titel :
Biomedical Engineering Conference, 2008. CIBEC 2008. Cairo International
Conference_Location :
Cairo
Print_ISBN :
978-1-4244-2694-2
Electronic_ISBN :
978-1-4244-2695-9
DOI :
10.1109/CIBEC.2008.4786059