Periocular biometrics: constraining the elastic graph matching algorithm to biologically plausible distortions. Issue 4 (1st December 2014)

• Record Type: Journal Article
• Authors: Proença, Hugo; Briceño, Juan C.
• Is Part Of: IET biometrics. Volume 3:Issue 4(2014)
• Page Start: 167
• Page End: 175
• Publication Date: 2014-12-01
• Subjects: biometrics (access control) -- graph theory -- image matching -- statistical analysis; periocular biometrics -- elastic graph matching algorithm constraint -- biologically plausible distortions -- periocular region -- unconstrained data acquisition -- facial expressions -- vertex locations -- biological tissue -- globally‐coherent EGM algorithm -- GC‐EGM algorithm -- local angular movement avoidance -- nonlinear distortion modelling -- vertex similarity measurement -- edge‐cost function -- model graphs -- test graphs -- synthetic data -- real data -- recognition performance -- statistical analysis -- error rate improvement -- biometric recognition systems; Biometric identification -- Periodicals; 570.15195
• DOI: 10.1049/iet-bmt.2013.0039
• Languages: English
• ISSNs: 2047-4938

Abstract

Abstract : In biometrics research, the periocular region has been regarded as an interesting trade‐off between the face and the iris, particularly in unconstrained data acquisition setups. As in other biometric traits, the current challenge is the development of more robust recognition algorithms. Having investigated the suitability of the 'elastic graph matching' (EGM) algorithm to handle non‐linear distortions in the periocular region because of facial expressions, the authors observed that vertices locations often not correspond to displacements in the biological tissue. Hence, they propose a 'globally coherent' variant of EGM (GC‐EGM) that avoids sudden local angular movements of vertices while maintains the ability to faithfully model non‐linear distortions. Two main adaptations were carried out: (i) a new term for measuring vertices similarity and (ii) a new term in the edges‐cost function penalises changes in orientation between the model and test graphs. Experiments were carried out both in synthetic and real data and point for the advantages of the proposed algorithm. Also, the recognition performance when using the EGM and GC‐EGM was compared, and statistically significant improvements in the error rates were observed when using the GC‐EGM variant. .