A novel approach to nose-tip and eye-corners detection using HK-classification in case of 3D face analysis

In this paper, we present an automatic 3D face analysis algorithm and demonstrate its performance on CASIA 3D data. The idea is to develop an automatic extraction approach of 3D facial features, using a geometric approach based on an analysis of the curves. 3D Face analysis has been considered as a major solution to deal with unsolved issues of reliable 2D face recognition. Facial feature extraction is important in many face related applications, such as face recognition, pose normalization, expression understanding and face tracking. Experimental results, using a common experimental setup on CASIA 3D dataset, are presented to demonstrate the accuracy and relevance of the proposed approach. Our technique displays, a 100% of good nose tip localization in 8 mm precision and 100% of good localization for the eye inner corner in 10 mm precision.