Estimation of Improvement in Rosacea Using Image Processing

This paper addresses a need by dermatologists of being able to assess quantitatively the change in severity of the skin disease rosacea. Traditionally, the efficacy of a treatment could only be assessed subjectively, such as by a dermatologist at weekly intervals giving a patient under treatment a score related to the degree of severity of the rosacea, with say a score of 5 meaning “severe” and a score of 1 “mild”. The method proposed in this paper is the first to offer an objective measure of the change in severity of rosacea; the basic idea is to use image processing techniques to find, assess and compare the sizes and degrees of redness of skin in photographs of a patient’s face taken over a period of time. Challenges include the need to take into account the different lighting conditions and orientations of the photographs.