Facial feature extraction using Adaptive Hough Transform, template matching and active contour models

The present paper describes an extention to the methods proposed in [1] for the extraction of facial features with ultimate goal to be used in defining a sufficient set of distances between them so that a unique description of the structure of a face is obtained. Eyebrows, eyes, nostril, mouth, cheeks and chin are considered as interesting features. Candidates for eyes, nostrils and mouth are determined by searching for minima and maxima in the x- and g- projections of the greylevel relief. Candidates for cheeks and chin are determined by performing adaptive hough transform on a relevant subimage defined according to the position of the eyes and mouthe and the ellipse containing the main connected component of the image. A deforming technique is also applied to the ellipse representing the main face region, in order to acquire a more accurate model of the face. Candidates for eyebrows are determined by adapting a proper greylevel template to an area restricted by the position of the eyes. The algorithms presented were tested on a set of 37 different color images, containing features as beard, glasses nad changing facial expressions.