Elastic Face, An Anatomy-Based Biometrics Beyond Visible Cue

Conference · Mon Mar 29 00:00:00 EST 2004

OSTI ID:15013920

Tsap, L V; Zhang, Y; Kundu, S J; Goldgof, D B; Sarkar, S

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 face 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.

• Research Organization: Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
• Sponsoring Organization: USDOE
• DOE Contract Number: W-7405-ENG-48
• OSTI ID: 15013920
• Report Number(s): UCRL-PROC-203268; TRN: US200803%%954
• Resource Relation: Conference: Presented at: International Conference of Pattern Recognition ICPR 2004, Cambridge, United Kingdom, Aug 23 - Aug 26, 2004
• Country of Publication: United States
• Language: English

Related Subjects

42 ENGINEERING
99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE
PATTERN RECOGNITION
STRAINS
LAWRENCE LIVERMORE NATIONAL LABORATORY