Automatic detection of acne scars: Preliminary results

Acne scars are of great cosmetic concern, and there are several methods of treatment towards reducing the appearance of scars. Automatic detection of acne scar-pixels from digital color images would be helpful in quantitative assessment of the success of treatment. This paper addresses detection of acne scar-pixels based on color image processing. The RGB model is used to representing the data. Pixels from the background (skin) and from the lesions of interest (acne scars) were recorded from the images of 7 subjects, to build a knowledge-base i.e., clusters associated with the skin and acne scars, respectively. The clusters were found to be fairly distinct in the RGB space. Consequently, classification (segmentation) is performed by minimum-distance-rule in the RGB space, by using Mahalanobis distance (MD). We have also implemented Bayes' method. The results have been validated with respect to the ground-truth extracted by manual segmentation of scars. The classifier based on MD performs better than that based on Bayes, with the average values of sensitivity and specificity of the former being 90.36 and 93.82, respectively.