Pose classification of human faces by weighting mask function approach

摘要

This paper presents a novel method for automatic estimation of the poses/degrees of human faces. The proposed system consists of two main parts. The first part is the searching of potential face regions that are gotten from the isosceles-triangle criteria based on the rules of "the combination of two eyes and one mouth". The second part of the proposed system is the performing the task of pose verification by utilitizing face weighting mask function, direction weighting mask function, and pose weighting mask function. The proposed face poses/degrees classification system can also determine the poses of multiple faces. Experimental results demonstrate that an approximately 99% success rate is achieved and the relative false estimation rate is very low.