Principal Curvature Measures Estimation and Application to 3D Face Recognition

Handle URI:
http://hdl.handle.net/10754/623896
Title:
Principal Curvature Measures Estimation and Application to 3D Face Recognition
Authors:
Tang, Yinhang; Li, Huibin; Sun, Xiang ( 0000-0003-0242-0319 ) ; Morvan, Jean-Marie; Chen, Liming
Abstract:
This paper presents an effective 3D face keypoint detection, description and matching framework based on three principle curvature measures. These measures give a unified definition of principle curvatures for both smooth and discrete surfaces. They can be reasonably computed based on the normal cycle theory and the geometric measure theory. The strong theoretical basis of these measures provides us a solid discrete estimation method on real 3D face scans represented as triangle meshes. Based on these estimated measures, the proposed method can automatically detect a set of sparse and discriminating 3D facial feature points. The local facial shape around each 3D feature point is comprehensively described by histograms of these principal curvature measures. To guarantee the pose invariance of these descriptors, three principle curvature vectors of these principle curvature measures are employed to assign the canonical directions. Similarity comparison between faces is accomplished by matching all these curvature-based local shape descriptors using the sparse representation-based reconstruction method. The proposed method was evaluated on three public databases, i.e. FRGC v2.0, Bosphorus, and Gavab. Experimental results demonstrated that the three principle curvature measures contain strong complementarity for 3D facial shape description, and their fusion can largely improve the recognition performance. Our approach achieves rank-one recognition rates of 99.6, 95.7, and 97.9% on the neutral subset, expression subset, and the whole FRGC v2.0 databases, respectively. This indicates that our method is robust to moderate facial expression variations. Moreover, it also achieves very competitive performance on the pose subset (over 98.6% except Yaw 90°) and the occlusion subset (98.4%) of the Bosphorus database. Even in the case of extreme pose variations like profiles, it also significantly outperforms the state-of-the-art approaches with a recognition rate of 57.1%. The experiments carried out on the Gavab databases further demonstrate the robustness of our method to varies head pose variations.
KAUST Department:
King Abdullah University of Science and Technologh, V.C.C. Research Center, Thuwal, 23955-6900, , Saudi Arabia
Citation:
Tang Y, Li H, Sun X, Morvan J-M, Chen L (2017) Principal Curvature Measures Estimation and Application to 3D Face Recognition. Journal of Mathematical Imaging and Vision. Available: http://dx.doi.org/10.1007/s10851-017-0728-2.
Publisher:
Springer Nature
Journal:
Journal of Mathematical Imaging and Vision
Issue Date:
6-Apr-2017
DOI:
10.1007/s10851-017-0728-2
Type:
Article
ISSN:
0924-9907; 1573-7683
Sponsors:
This work was supported in part by the French research agency, l’Agence Nationale de Recherche (ANR), through the Biofence project under the Grant ANR-13-INSE-0004-02. Huibin Li was supported in part by the National Natural Science Foundation of China (NSFC) under Grant No. 11401464, the China Postdoctoral Science Foundation (No. 2014M560785), and the International Exchange Funds for the Central Universities No. 2014gjhz07.
Additional Links:
http://link.springer.com/article/10.1007/s10851-017-0728-2
Appears in Collections:
Articles

Full metadata record

DC FieldValue Language
dc.contributor.authorTang, Yinhangen
dc.contributor.authorLi, Huibinen
dc.contributor.authorSun, Xiangen
dc.contributor.authorMorvan, Jean-Marieen
dc.contributor.authorChen, Limingen
dc.date.accessioned2017-05-31T11:23:12Z-
dc.date.available2017-05-31T11:23:12Z-
dc.date.issued2017-04-06en
dc.identifier.citationTang Y, Li H, Sun X, Morvan J-M, Chen L (2017) Principal Curvature Measures Estimation and Application to 3D Face Recognition. Journal of Mathematical Imaging and Vision. Available: http://dx.doi.org/10.1007/s10851-017-0728-2.en
dc.identifier.issn0924-9907en
dc.identifier.issn1573-7683en
dc.identifier.doi10.1007/s10851-017-0728-2en
dc.identifier.urihttp://hdl.handle.net/10754/623896-
dc.description.abstractThis paper presents an effective 3D face keypoint detection, description and matching framework based on three principle curvature measures. These measures give a unified definition of principle curvatures for both smooth and discrete surfaces. They can be reasonably computed based on the normal cycle theory and the geometric measure theory. The strong theoretical basis of these measures provides us a solid discrete estimation method on real 3D face scans represented as triangle meshes. Based on these estimated measures, the proposed method can automatically detect a set of sparse and discriminating 3D facial feature points. The local facial shape around each 3D feature point is comprehensively described by histograms of these principal curvature measures. To guarantee the pose invariance of these descriptors, three principle curvature vectors of these principle curvature measures are employed to assign the canonical directions. Similarity comparison between faces is accomplished by matching all these curvature-based local shape descriptors using the sparse representation-based reconstruction method. The proposed method was evaluated on three public databases, i.e. FRGC v2.0, Bosphorus, and Gavab. Experimental results demonstrated that the three principle curvature measures contain strong complementarity for 3D facial shape description, and their fusion can largely improve the recognition performance. Our approach achieves rank-one recognition rates of 99.6, 95.7, and 97.9% on the neutral subset, expression subset, and the whole FRGC v2.0 databases, respectively. This indicates that our method is robust to moderate facial expression variations. Moreover, it also achieves very competitive performance on the pose subset (over 98.6% except Yaw 90°) and the occlusion subset (98.4%) of the Bosphorus database. Even in the case of extreme pose variations like profiles, it also significantly outperforms the state-of-the-art approaches with a recognition rate of 57.1%. The experiments carried out on the Gavab databases further demonstrate the robustness of our method to varies head pose variations.en
dc.description.sponsorshipThis work was supported in part by the French research agency, l’Agence Nationale de Recherche (ANR), through the Biofence project under the Grant ANR-13-INSE-0004-02. Huibin Li was supported in part by the National Natural Science Foundation of China (NSFC) under Grant No. 11401464, the China Postdoctoral Science Foundation (No. 2014M560785), and the International Exchange Funds for the Central Universities No. 2014gjhz07.en
dc.publisherSpringer Natureen
dc.relation.urlhttp://link.springer.com/article/10.1007/s10851-017-0728-2en
dc.subject3D keypoint detection, description and matchingen
dc.subjectExpression, pose and occlusionen
dc.subjectMesh-based 3D face recognitionen
dc.subjectPrincipal curvature measuresen
dc.titlePrincipal Curvature Measures Estimation and Application to 3D Face Recognitionen
dc.typeArticleen
dc.contributor.departmentKing Abdullah University of Science and Technologh, V.C.C. Research Center, Thuwal, 23955-6900, , Saudi Arabiaen
dc.identifier.journalJournal of Mathematical Imaging and Visionen
dc.contributor.institutionUniversité de Lyon, CNRS, Ecole Centrale de Lyon, LIRIS, Lyon, 69134, , Franceen
dc.contributor.institutionSchool of Mathematics and Statistics, Xi’an Jiaotong University, No.28, Xianning West Road, Xi’an, Shaanxi, 710049, , Chinaen
dc.contributor.institutionUniversité de Lyon, CNRS, Université Claude Bernard Lyon 1, ICJ UMR 5208, Villeurbanne, 69622, , Franceen
kaust.authorSun, Xiangen
kaust.authorMorvan, Jean-Marieen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.