Detecting specular highlights in dermatological images

There is an increasing interest in computer-aided diagnosis of skin cancers through analysis of dermatological images. This is processing that attempts to correlate diagnosis with skin lesion appearance (i.e., the image), by extracting visual features such as colour, pigmentation, size, etc. Presence of glare (specular highlights) can confuse such systems; highlights may obscure skin surface details and appear as additional features that are not intrinsic to the lesion. In this paper, we put forward a simple method to detect specular highlights specific to dermatological images. Knowledge of the location of specularities is advantageous since it allows us to then deal with them, either by excluding them from further processing or by attempting to recover the image data in specular regions. The proposed method is built on the dichromatic reflection model and, in a novel step, uses non-negative matrix factorization with sparseness constraints to separate the specular component.