3D Face Recognition based on Deformation Invariant Image using Symbolic LDA
Prakash S. Hiremath, Manjunatha Hiremath · 2013
Face recognition is one of the most important abilities that the humans possess. There are several reasons for the growing interest in automated face recognition, including rising concerns for public security, the need for identity verification for physical and logical access to shared resources, and the need for face analysis and modeling techniques in multimedia data management and digital entertainment. In recent years, significant progress has been made in this area, with a number of face recognition and modeling systems have been developed and deployed. However, accurate and robust face recognition still offers a number of challenges to computer vision and pattern recognition researchers, especially under unconstrained environments. In this paper, a novel deformation invariant image based 3D face recognition is proposed. The experiments are done using the 3D CASIA Face Database, which includes 123 individuals with complex expressions. Experimental results show that the proposed method substantially improves the recognition performance under various facial expressions. Key words: 3D face recognition, facial expression, geodesic distance, symbolic LDA, deformation invariant image. 1.