Abstract (EN):
The aim of this work is to assess what is the role of color features in Computer-Aided Diagnosis (CAD) systems for melanoma classification. This assessment was performed by developing two CAD systems, each based on a different feature extraction method, whose classification is solely based on color features. The best performance (SE = 100% and SP = 93%) was achieved by both systems by using the unidimensional color histogram as the image descriptor and images represented in the opponent color space. These results show that color features play a major role in dermoscopy analysis.
Language:
English
Type (Professor's evaluation):
Scientific
No. of pages:
8