Skin image segmentation based on energy transformation

Abstract

In this paper, a new method on extraction of human skin grid centerlines is proposed. The method introduces the physics concepts of kinetic and potential energy into image processing. Regional energy is calculated. Energy transformation is performed to map the pixels from the grayscale space into energy space. Then, the energy image undergoes a morphological filter to remove noises and spurious minima. The amount of filtering can be manually tuned to get a different result. Subsequently, normal curvature of the energy surface is utilized to identify the principal direction and principal curvatures. The ridge centerlines can be detected at the image locations where the principal direction is perpendicular to the normal vector. The experiment shows that this method is an effective one for the purpose of extracting human skin grid.