Dr. T. Karthikeyan, T. K. Sumathi
Abstract: As one of the most successful applications of image analysis and understanding, face recognition has received significant attention during the past several years. Among various types of face images, a 2D intensity image has been the most popular and common image data used for face recognition, since it is easy to acquire and utilize. However, 2D image has the intrinsic problem that it is vulnerable to the variations in illumination and poses. To overcome the limitation of 2D intensity images, 3D images are being used. In this paper, 3D range images of human faces are considered and a novel approach for 3D frontal face recognition is proposed using local ternary patterns with multi-linear discriminant analysis algorithm.
Keywords: Local Ternary Patterns, DOG filtering, LDA, Multi-Linear Discriminant analysis, LBP