This includes the creation of a personalized surface model from a set of color and depth camera images, detection and classification of dermatological findings, such as psoriasis lesions and plaques, as well as longitudinal analysis of changes.
Description: We are researching and developing image processing algorithms for dermatological applications in diagnostic and decision making systems as well as for education.
Segmenting psoriasis lesions and plaques We are studying the possibilities of using the predominant color differences between normal and irritated psoriasis images regions as primary features to differentiate.
Below are some preliminary examples of segmentation of various types of psoriasis manifestation using different color spaces.
Original image leftprocessed color space centerbinary output right without morphological postprocessing. Segmenting the plaques scales in the Lab color space Segmenting irritated red dish skin regions in the B-G color space with preprocessing, thresholding, and hole filling Segmenting irritated red dish skin regions in the HSV H and YUV V color space separately, then thresholding and taking the intersection.