Facial Feature Extraction and Determination of Pose

Abstract

The present paper describes a set of methods for the extraction of facial features as well as for the determination of the gaze direction. The ultimate goal of the approach followed is to define a sufficient set of feature distances so that a unique description of the structure of a face is produced. Eyebrows, eyes, nostrils, mouth, cheeks and chin are considered as interesting features. The candidates for eyes, nostrils and mouth are determined by searching for minima and maxima in the x- and y- projections of the greylevel relief. The candidates for cheek borders and chin are determined by performing an adaptive Hough transform on a relevant subimage defined according to the position of an ellipse containing the main face region of the image. A technique based on dynamic programming is applied that exploits this ellipse in order to acquire a more accurate model of the face. The candidates for eyebrows are determined by adapting a proper greylevel mask to an area defined by the eye position. Finally, the orientation of face is determined using the symmetric properties of certain facial features. The algorithms presented were tested on the M2VTS multimodal face database.