A meta-analysis of face recognition covariates

This paper presents a meta-analysis for covariates that affect performance of face recognition algorithms. Our review of the literature found six covariates for which multiple studies reported effects on face recognition performance. These are: age of the person, elapsed time between images, gender of the person, the person's expression, the resolution of the face images, and the race of the person. The results presented are drawn from 25 studies conducted over the past 12 years. There is near complete agreement between all of the studies that older people are easier to recognize than younger people, and recognition performance begins to degrade when images are taken more than a year apart. While individual studies find men or women easier to recognize, there is no consistent gender effect. There is universal agreement that changing expression hurts recognition performance. If forced to compare different expressions, there is still insufficient evidence to conclude that any particular expression is better than another. Higher resolution images improve performance for many modern algorithms. Finally, given the studies summarized here, no clear conclusions can be drawn about whether one racial group is harder or easier to recognize than another.

[1]  Larry S. Davis,et al.  Smiling faces are better for face recognition , 2002, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.

[2]  Stefano Soatto,et al.  A Study of Face Recognition as People Age , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[3]  Paul A. Watters,et al.  Are Younger People More Difficult to Identify or Just a Peer-to-Peer Effect , 2007, CAIP.

[4]  Luuk J. Spreeuwers,et al.  The Effect of Image Resolution on the Performance of a Face Recognition System , 2006, 2006 9th International Conference on Control, Automation, Robotics and Vision.

[5]  Rama Chellappa,et al.  Face Verification Across Age Progression , 2006, IEEE Trans. Image Process..

[6]  Bruce A. Draper,et al.  How features of the human face affect recognition: a statistical comparison of three face recognition algorithms , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[7]  K. Ricanek,et al.  The effect of normal adult aging on standard PCA face recognition accuracy rates , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[8]  Patrick J. Flynn,et al.  Overview of the face recognition grand challenge , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[9]  Bruce A. Draper,et al.  FRVT 2006: Quo Vidas Face Quality , 2009 .

[10]  P. Phillips,et al.  How features of the human face affect recognition: a statistical comparison of three face recognition algorithms , 2004, CVPR 2004.

[11]  Yiying Tong,et al.  Face recognition with temporal invariance: A 3D aging model , 2008, 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition.

[12]  Terrance E. Boult,et al.  FAAD: face at a distance , 2008, SPIE Defense + Commercial Sensing.

[13]  Sudeep Sarkar,et al.  Baseline results for the challenge problem of HumanID using gait analysis , 2002, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.

[14]  Xiaoming Liu,et al.  Multi-Frame Image Restoration for Face Recognition , 2007 .

[15]  Ralph Gross,et al.  Quo vadis Face Recognition , 2001 .

[16]  Alice J. O'Toole,et al.  Face recognition algorithms and the other-race effect: computational mechanisms for a developmental contact hypothesis , 2002, Cogn. Sci..

[17]  Xiaoming Liu,et al.  Multi-Frame Super-Resolution for Face Recognition , 2007, 2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems.

[18]  Marios Savvides,et al.  Redundant Class-Dependence Feature Analysis Based on Correlation Filters Using FRGC2.0 Data , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops.

[19]  Jiri Matas,et al.  XM2VTSDB: The Extended M2VTS Database , 1999 .

[20]  Richa Singh,et al.  Face recognition with disguise and single gallery images , 2009, Image Vis. Comput..

[21]  Alice J. O'Toole,et al.  FRVT 2006 and ICE 2006 Large-Scale Experimental Results , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  David J. Kriegman,et al.  From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[23]  H Moon,et al.  Computational and Performance Aspects of PCA-Based Face-Recognition Algorithms , 2001, Perception.

[24]  Hyeonjoon Moon,et al.  The FERET Evaluation Methodology for Face-Recognition Algorithms , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  Bruce A. Draper,et al.  Focus on quality, predicting FRVT 2006 performance , 2008, 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition.

[26]  Luc Vandendorpe,et al.  Evaluation of LDA based face verification with respect to available computational resources , 2002, PRIS.

[27]  Bruce A. Draper,et al.  FRVT 2006: Quo Vadis face quality , 2010, Image Vis. Comput..

[28]  Bruce A. Draper,et al.  A Statistical Assessment of Subject Factors in the PCA Recognition of Human Faces , 2003, 2003 Conference on Computer Vision and Pattern Recognition Workshop.

[29]  B. Martin,et al.  Quality Assessment of Facial Images , 2006, 2006 Biometrics Symposium: Special Session on Research at the Biometric Consortium Conference.

[30]  Alex Pentland,et al.  Probabilistic Visual Learning for Object Representation , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[31]  Patrick J. Flynn,et al.  Assessment of Time Dependency in Face Recognition: An Initial Study , 2003, AVBPA.

[32]  Bruce A. Draper,et al.  The CSU Face Identification Evaluation System: Its Purpose, Features, and Structure , 2003, ICVS.

[33]  M. Abdel-Mottaleb,et al.  Application notes - Algorithms for Assessing the Quality of Facial Images , 2007, IEEE Computational Intelligence Magazine.

[34]  Andy Adler,et al.  Human Vs. Automatic Measurement of Biometric Sample Quality , 2006, 2006 Canadian Conference on Electrical and Computer Engineering.

[35]  E.M. Newton,et al.  Meta-Analysis of Third-Party Evaluations of Iris Recognition , 2007, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[36]  Chengjun Liu,et al.  Capitalize on dimensionality increasing techniques for improving face recognition grand challenge performance , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[37]  Raymond N. J. Veldhuis,et al.  Hand-geometry recognition based on contour parameters , 2005, SPIE Defense + Commercial Sensing.

[38]  Richa Singh,et al.  Age Transformation for Improving Face Recognition Performance , 2007, PReMI.

[39]  Bruce A. Draper,et al.  Factors that influence algorithm performance in the Face Recognition Grand Challenge , 2009, Comput. Vis. Image Underst..

[40]  P. Jonathon Phillips,et al.  Meta-Analysis of Third-Party Evaluations of Iris Recognition , 2007, 2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems.

[41]  David Masip,et al.  Preferred Spatial Frequencies for Human Face Processing Are Associated with Optimal Class Discrimination in the Machine , 2008, PloS one.

[42]  M. Bartlett,et al.  Face image analysis by unsupervised learning and redundancy reduction , 1998 .

[43]  Sudeep Sarkar,et al.  Outdoor recognition at a distance by fusing gait and face , 2007, Image Vis. Comput..

[44]  J.-J. Wang,et al.  Face Image Resolution versus Face Recognition Performance Based on Two Global Methods , 2004 .

[45]  Alice J. O'Toole,et al.  Humans versus algorithms: Comparisons from the Face Recognition Vendor Test 2006 , 2008, 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition.

[46]  Bruce A. Draper,et al.  Repeated Measures GLMM Estimation of Subject-Related and False Positive Threshold Effects on Human Face Verification Performance , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops.

[47]  Alice J. O'Toole,et al.  FRVT 2006 and ICE 2006 large-scale results , 2007 .

[48]  Terence Sim,et al.  The CMU Pose, Illumination, and Expression Database , 2003, IEEE Trans. Pattern Anal. Mach. Intell..