Fast pose invariant face recognition using super coupled multiresolution Markov Random Fields on a GPU

被引:18
作者
Arashloo, Shervin Rahimzadeh [1 ]
Kittler, Josef [2 ]
机构
[1] Urmia Univ, Fac Engn, Dept Elect Engn, Orumiyeh, West Azarbaijan, Iran
[2] Univ Surrey, CVSSP, Guildford GU2 5XH, Surrey, England
基金
英国工程与自然科学研究理事会;
关键词
Multiresolution MRFs; Renormalisation group transform; Super coupling transform; Image matching; Unconstrained-pose face recognition; IMAGE; MODEL; PATTERNS;
D O I
10.1016/j.patrec.2014.05.017
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We discuss the problem of pose invariant face recognition using a Markov Random Field (MRF) model. MRF image to image matching has been shown to be very promising in earlier studies (Arashloo and Kittler, 2011) [4]. Its demanding computational complexity has been addressed in Arashloo et al. (2011) [6] by means of multiresolution MRFs linked by the super coupling transform advocated by Petrou et al. (1998) [37, 11]. In this paper, we benefit from the daisy descriptor for face image representation in image matching. Most importantly, we design an innovative GPU implementation of the proposed multiresolution MRF matching process. The significant speed up achieved (factor of 25) has multiple benefits: It makes the MRF approach a practical proposition. It facilitates extensive empirical optimisation and evaluation studies. The latter conducted on benchmarking databases, including the challenging labelled faces in the wild (LFW) database show the outstanding potential of the proposed method, which consistently achieves state-of-the-art performance in standard benchmarking tests. The experimental studies also show that the super coupled multiresolution MRFs deliver a computational speed up by a factor of 5 over and above the speed up achieved using the GPU implementation. (C) 2014 Elsevier B. V. All rights reserved.
引用
收藏
页码:49 / 59
页数:11
相关论文
共 62 条
[1]   Face description with local binary patterns:: Application to face recognition [J].
Ahonen, Timo ;
Hadid, Abdenour ;
Pietikainen, Matti .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2006, 28 (12) :2037-2041
[2]  
[Anonymous], 1999, Athena scientific Belmont
[3]  
[Anonymous], 2008, FAC REAL LIF IM WORK
[4]  
[Anonymous], PAMI
[5]  
[Anonymous], 2011, SIMPLE FEATURES LARG
[6]  
[Anonymous], 2008, PROC WORKSHOP FACES
[7]  
Arashloo S.R., P IEEE 4 INT C BIOM
[8]  
Arashloo S.R., 2009, BMVC
[9]   Pose-invariant face recognition by matching on multi-resolution MRFs linked by supercoupling transform [J].
Arashloo, Shervin Rahimzadeh ;
Kittler, Josef ;
Christmas, William J. .
COMPUTER VISION AND IMAGE UNDERSTANDING, 2011, 115 (07) :1073-1083
[10]   Energy Normalization for Pose-Invariant Face Recognition Based on MRF Model Image Matching [J].
Arashloo, Shervin Rahimzadeh ;
Kittler, Josef .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2011, 33 (06) :1274-1280