Skin lesions color analysis based on RGB reflectance indices

This paper presents a contribution in the field of color image processing of selected skin lesions for dermatologists. In their morphological learning method for skin lesion classification, RGB color variations and variegations are useful features used to discriminate between lesions. In this work, nine sets of skin lesion images are digitally captured under standard and control environment. The identified regions of interest (ROI) of these lesions´ images are processed to quantify the conventional normal and differential reflectance indices in RGB color model. Then the data will be statistically plotted as well as analyzed. Inference tests are further applied in order to compare with any visual findings from the available statistical plots.