Is there a connection between face symmetry and face recognition?

Abstract

Recent research in the area of automatic machine recognition of human faces has shown that there may be an advantage in utilizing face symmetry to improve recognition accuracy. While promising, this work has led to several open questions. What is a good feature description or score of the symmetry of the face? Is there a statistical significance between face symmetry and face recognition? We present new symmetry scores of the face and use the scores to compare the symmetry in several subgroups of a face database. A 3D face database is used to remove the effects of illumination which should improve the reliability of the symmetry score. We find a significant difference in face symmetry between the men and women subjects in the database. The database is then partitioned into most symmetric and least symmetric subjects based on the symmetry scores. The average-half-face is utilized in our face recognition experiments to take into account the symmetry of the face. Face recognition with eigenfaces using the average-half-face is significantly higher than using the full face in all subgroups regardless of symmetry score. However, face recognition using the full face does depend on the symmetry score and generally favors the least symmetric subjects.