3D face recognition with the average-half-face

We present a promising analysis on using the pattern of symmetry in the face to increase the accuracy of three-dimensional face recognition. We introduce the concept of the ‘average-half-face’, motivated by the Symmetry Preserving Singular Value Decomposition. We compare face recognition results using the eigenfaces face recognition algorithm with average-half-face data and full face data in several experiments on a 3D face data set of 1126 images. We show that the results from the eigenfaces face recognition system using the average-half-face is more accurate than using the full face, only the left or right half of the face or a random choice of half of the face.

• Type: Conference
• Year: 2008
• Where: ICPR
• Authors: Josh Harguess, Shalini Gupta, Jake K. Aggarwal
• Keywords: Computer Vision, Eigenfaces Face Recognition, Face Recognition, ICPR 2008, Three-dimensional Face Recognition