Elastic Face, An Anatomy-Based Biometrics Beyond Visible Cue

This paper describes a face recognition method that is designed based on the consideration of anatomical and biomechanical characteristics of facial tissues. Elastic strain pattern inferred from facial expression can reveal an individual's biometric signature associated with the underlying anatomical structure, and thus has the potential for face recognition. A method based on the continuum mechanics in finite element formulation is employed to compute the strain pattern. Experiments show very promising results. The proposed method is quite different from other face recognition methods, and both its advantages and limitations, as well as future research for improvement are discussed.

• Type: Conference
• Year: 2004
• Where: ICPR
• Authors: Dmitry B. Goldgof, Leonid V. Tsap, Sangeeta J. Kundu, Sudeep Sarkar, Yong Zhang
• Keywords: Computer Vision, Elastic Strain Pattern, Face Recognition Method, Face Recognition Methods, ICPR 2004