article

On transforming statistical models for non-frontal face verification

Authors:

Conrad Sanderson,

Yongsheng GaoAuthors Info & Claims

Pattern Recognition, Volume 39, Issue 2

Pages 288 - 302

https://doi.org/10.1016/j.patcog.2005.07.001

Published: 01 February 2006 Publication History

Abstract

We address the pose mismatch problem which can occur in face verification systems that have only a single (frontal) face image available for training. In the framework of a Bayesian classifier based on mixtures of gaussians, the problem is tackled through extending each frontal face model with artificially synthesized models for non-frontal views. The synthesis methods are based on several implementations of maximum likelihood linear regression (MLLR), as well as standard multi-variate linear regression (LinReg). All synthesis techniques rely on prior information and learn how face models for the frontal view are related to face models for non-frontal views. The synthesis and extension approach is evaluated by applying it to two face verification systems: a holistic system (based on PCA-derived features) and a local feature system (based on DCT-derived features). Experiments on the FERET database suggest that for the holistic system, the LinReg-based technique is more suited than the MLLR-based techniques; for the local feature system, the results show that synthesis via a new MLLR implementation obtains better performance than synthesis based on traditional MLLR. The results further suggest that extending frontal models considerably reduces errors. It is also shown that the local feature system is less affected by view changes than the holistic system; this can be attributed to the parts based representation of the face, and, due to the classifier based on mixtures of gaussians, the lack of constraints on spatial relations between the face parts, allowing for deformations and movements of face areas.

References

[1]

M. Lockie (Ed.), Facial verification bureau launched by police IT group, Biometric Technol. Today 10(3) (2002) 3-4.

[2]

Hampapur, A., Brown, L., Connell, J., Ekin, A., Haas, N., Lu, M., Merkl, H., Pankanti, S., Senior, A., Shu, C.-F. and Tian, Y.L., Smart video surveillance: exploring the concept of multiscale spatiotemporal tracking. IEEE Signal Process. Mag. v22 i2. 38-51.

[3]

Ortega-Garcia, J., Bigun, J., Reynolds, D. and Gonzales-Rodriguez, J., Authentication gets personal with biometrics. IEEE Signal Process. Mag. v21 i2. 50-62.

[4]

Woodward, J.D., Biometrics: privacy's foe or privacy's friend?. Proc. IEEE. v85 i9. 1480-1492.

[5]

Czyz, J., Kittler, J. and Vandendorpe, L., Multiple classifier combination for face-based identity verification. Pattern Recognition. v37 i7. 1459-1469.

[6]

Messer, K., Kittler, J., Sadeghi, M., Marcel, S., Marcel, C., Bengio, S., Cardinaux, F., Sanderson, C., Czyz, J., Vandendorpe, L., Srisuk, S., Petrou, M., Kurutach, W., Kadyrov, A., Paredes, R., Kepenekci, B., Tek, F.B., Akar, G.B., Deravi, F. and Mavity, N., Face verification competition on the XM2VTS database. In: Proceedings of the Fourth International Conference on Audio- and Video-Based Biometric Person Authentication (AVBPA), pp. 964-974.

Digital Library

[7]

Graham, D. and Allinson, N., Face recognition from unfamiliar views: subspace methods and pose dependency. In: Proceedings of the Third IEEE International Conference on Automatic Face and Gesture Recognition (AFGR), Avon Books, New York. pp. 348-353.

Digital Library

[8]

R. Gross, J. Yang, A. Waibel, Growing gaussian mixture models for pose invariant face recognition, in: Proceedings of the 15th International Conference Pattern Recognition (ICPR), vol. 1, Barcelona, 2000, pp. 1088-1091.

Digital Library

[9]

Pentland, A., Moghaddam, B. and Starner, T., View-based and modular eigenspaces for face recognition. In: Proceedings of the International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 84-91.

[10]

Atick, J.J., Griffin, P.A. and Redlich, A.N., Statistical approach to shape from shading: reconstruction of three-dimensional face surfaces from single two-dimensional images. Neural Comput. v8. 1321-1340.

Digital Library

[11]

Blanz, V., Romdhani, S. and Vetter, T., Face identification across different poses and illuminations with a 3D morphable model. In: Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition (AFGR), pp. 192-197.

Digital Library

[12]

Sanderson, C. and Paliwal, K.K., Fast features for face authentication under illumination direction changes. Pattern Recogn. Lett. v24 i14. 2409-2419.

Digital Library

[13]

S. Lucey, T. Chen, A GMM parts based face representation for improved verification through relevance adaptation, in: Proceedings of Computer Vision and Pattern Recognition (CVPR), vol. 2, Washington, DC, 2004, pp. 855-861.

Digital Library

[14]

Kirby, M. and Sirovich, L., Application of the Karhunen-Loève procedure for the characterization of human faces. IEEE Trans. Pattern Anal. Mach. Intell. v12 i1. 103-108.

Digital Library

[15]

Turk, M. and Pentland, A., Eigenfaces for recognition. J. Cognitive Neurosci. v3 i1. 71-86.

Digital Library

[16]

Duda, R.O., Hart, P.E. and Stork, D.G., Pattern Classification. Wiley, USA.

Digital Library

[17]

Reynolds, D., Quatieri, T. and Dunn, R., Speaker verification using adapted gaussian mixture models. Digital Signal Process. v10 i1-3. 19-41.

[18]

Cardinaux, F., Sanderson, C. and Marcel, S., Comparison of MLP and GMM classifiers for face verification on XM2VTS. In: Proceedings of the Fourth International Conference on Audio- and Video-Based Biometric Person Authentication (AVBPA), pp. 911-920.

[19]

C. Sanderson, F. Cardinaux, S. Bengio, On accuracy/robustness/complexity trade-offs in face verification, in: Proceedings of the Third International Conference on Information Technology and Applications, vol. 1, Sydney, 2005, pp. 650-655.

Digital Library

[20]

Brunelli, R. and Poggio, T., Face recognition: features versus templates. IEEE Trans. Pattern Anal. Mach. Intell. v15 i10. 1042-1052.

Digital Library

[21]

Cardinaux, F., Sanderson, C. and Bengio, S., Face verification using adapted generative models. In: Proceedings of the Sixth IEEE International Conference Automatic Face and Gesture Recognition (AFGR), pp. 825-830.

Digital Library

[22]

Eickeler, S., Müller, S. and Rigoll, G., Recognition of JPEG compressed face images based on statistical methods. Image Vision Comput. v18 i4. 279-287.

[23]

F. Samaria, Face recognition using hidden Markov models, Ph.D. Thesis, University of Cambridge, UK, 1994.

[24]

Duc, B., Fischer, S. and Bigün, J., Face authentication with Gabor information on deformable graphs. IEEE Trans. Image Process. v8 i4. 504-516.

Digital Library

[25]

Lades, M., Vorbrüggen, J.C., Buhmann, J., Lange, J., Malsburg, C.v.d., Würtz, R.P. and Konen, W., Distortion invariant object recognition in the dynamic link architecture. IEEE Trans. Comput. v42 i3. 300-311.

Digital Library

[26]

Chellappa, R., Wilson, C.L. and Sirohey, S., Human and machine recognition of faces: a survey. Proc. IEEE. v83 i5. 705-740.

[27]

Grudin, M.A., On internal representations in face recognition systems. Pattern Recognition. v33 i7. 1161-1177.

[28]

Kong, S.G., Heo, J., Abidi, B.R., Paik, J. and Abidi, M.A., Recent advances in visual and infrared face recognition-a review. Comput. Vision Image Understanding. v97 i1. 103-135.

Digital Library

[29]

Zhang, J., Yan, Y. and Lades, M., Face recognition: eigenfaces, elastic matching, and neural nets. Proc. IEEE. v85 i9. 1422-1435.

[30]

J.-L. Dugelay, J.-C. Junqua, C. Kotropoulos, R. Kuhn, F. Perronnin, I. Pitas, Recent advances in biometric person authentication, in: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. IV, Orlando, 2002, pp. 4060-4063.

[31]

Sanderson, C. and Paliwal, K.K., Identity verification using speech and face information. Digital Signal Process. v14 i5. 449-480.

[32]

J.L. Wayman, Digital signal processing in biometric identification: a review, in: Proceedings of IEEE International. Conference on Image Processing (ICIP), vol. 1, Rochester, 2002, pp. 37-40.

[33]

Hjelmås, E. and Low, B.K., Face detection: a survey. Comput. Vision Image Understanding. v83 i3. 236-274.

[34]

Yang, M-H., Kriegman, D.J. and Ahuja, N., Detecting faces in images: a survey. IEEE Trans. Pattern Anal. Mach. Intell. v24 i1. 34-58.

Digital Library

[35]

Kamgar-Parsi, B., Kamgar-Parsi, B., Jain, A. and Dayhoff, J., Aircraft detection: a case study in using human similarity measure. IEEE Trans. Pattern Anal. Mach. Intell. v23 i12. 1404-1414.

Digital Library

[36]

Leggetter, C.J. and Woodland, P.C., Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models. Comput. Speech Language. v9 i2. 171-185.

[37]

Mariéthoz, J. and Bengio, S., A comparative study of adaptation methods for speaker verification. In: Proceedings of the International Conference on Spoken Language Processing (ICSLP), pp. 581-584.

[38]

Beymer, D. and Poggio, T., Face recognition from one example view. In: Proceedings of the Fifth International Conference on Computer Vision (ICCV), pp. 500-507.

Digital Library

[39]

Niyogi, P., Girosi, F. and Poggio, T., Incorporating prior information in machine learning by creating virtual examples. Proc. IEEE. v86 i11. 2196-2209.

[40]

Vetter, T. and Poggio, T., Linear object classes and image synthesis from a single example image. IEEE Trans. Pattern Anal. Mach. Intell. v19 i7. 733-742.

Digital Library

[41]

Maurer, T. and Malsburg, C.v.d., Learning feature transformations to recognize faces rotated in depth. In: Proceedings of the International Conference on Artificial Neural Networks (ICANN), pp. 353-358.

[42]

Phillips, P.J., Moon, H., Rizvi, S.A. and Rauss, P.J., The FERET evaluation methodology for face-recognition algorithms. IEEE Trans. Pattern Anal. Mach. Intell. v22 i10. 1090-1104.

Digital Library

[43]

Chen, L-F., Liao, H-Y., Lin, J-C. and Han, C-C., Why recognition in a statistics-based face recognition system should be based on the pure face portion: a probabilistic decision-based proof. Pattern Recognition. v34 i7. 1393-1403.

[44]

Gonzales, R.C. and Woods, R.E., Digital Image Processing. Addison-Wesley, Reading, MA.

Digital Library

[45]

C. Sanderson, M. Saban, Y. Gao, On local features for GMM based face verification, in: Proceedings of Third International Conference on Information Technology and Applications, vol. 1, Sydney, 2005, pp. 638-643.

Digital Library

[46]

Webb, A., Statistical Pattern Recognition. Wiley, UK.

[47]

Dempster, A.P., Laird, N.M. and Rubin, D.B., Maximum likelihood from incomplete data via the EM algorithm. J. R. Stat. Soc. Ser. B. v39 i1. 1-38.

[48]

Gauvain, J.-L. and Lee, C.-H., Maximum a posteriori estimation for multivariate gaussian mixture observations of Markov chains. IEEE Trans. Speech Audio Process. v2 i2. 291-298.

[49]

S. Bengio, J. Mariethoz, S. Marcel, Evaluation of biometric technology on XM2VTS, IDIAP Research Report 01-21, Martigny, Switzerland, 2001.

[50]

Doddington, G.R., Przybycki, M.A., Martin, A.F. and Reynolds, D.A., The NIST speaker recognition evaluation-Overview, methodology, systems, results, perspective. Speech Commun. v31 i2-3. 225-254.

Digital Library

[51]

Bengio, S. and Mariéthoz, J., The expected performance curve: a new assessment measure for person authentication. In: Proceedings of the Odyssey 2004: The Speaker and Language Recognition Workshop, pp. 279-284.

[52]

M.J.F. Gales, P.C. Woodland, Variance compensation within the MLLR framework, Technical Report 242, Cambridge University Engineering Department, UK, 1996.

[53]

Rice, J.A., Mathematical Statistics and Data Analysis. second ed. Duxbury Press.

[54]

Martelli, M., Majaj, N.J. and Pelli, D.G., Are faces processed like words? A diagnostic test for recognition by parts. J. Vision. v5 i1. 58-70.

[55]

J.A. Bilmes, A gentle tutorial of the EM algorithm and its applications to parameter estimation for gaussian mixture and hidden Markov models, Technical Report TR-97-021, International Computer Science Institute, Berkeley, California, 1998.

Cited By

Hassaballah MAly S(2015)Face recognitionIET Computer Vision10.1049/iet-cvi.2014.00849:4(614-626)Online publication date: 1-Aug-2015
https://dl.acm.org/doi/10.1049/iet-cvi.2014.0084
García-Zurdo R(2014)Three-Dimensional Face Shape by Local Fitting to a Single Reference ModelInternational Journal of Computer Vision and Image Processing10.4018/ijcvip.20140101024:1(17-29)Online publication date: 1-Jan-2014
https://dl.acm.org/doi/10.4018/ijcvip.2014010102
Hanilçi CKinnunen T(2014)Source cell-phone recognition from recorded speech using non-speech segmentsDigital Signal Processing10.1016/j.dsp.2014.08.00835:C(75-85)Online publication date: 1-Dec-2014
https://dl.acm.org/doi/10.1016/j.dsp.2014.08.008
Show More Cited By

On transforming statistical models for non-frontal face verification
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision problems

Recommendations

Face Localization in 2D Frontal Face Images Using Luminosity Profiles Analysis
Multimodal Signals: Cognitive and Algorithmic Issues

Face detection from a single image represents a challenging task because of variability in scale, location, orientation and pose. Facial expression, occlusion, and lighting conditions also change the overall appearance of faces. In this work we propose ...
2D Pose-Invariant Face Recognition Using Single Frontal-View Face Database
Abstract
Personal identification systems that use face recognition work well for test images with frontal view face, but often fail when the input face is a pose view. Most face databases come from picture ID sources such as passports or driver’s licenses. ...
Frontal face synthesis based on multiple pose-variant images for face recognition
ICB'07: Proceedings of the 2007 international conference on Advances in Biometrics

Pose variance remains a challenging problem for face recognition. In this paper, a stereoscopic synthesis method for generating a frontal face image is proposed to improve the performance of automatic face recognition system. Through this method, a ...

Comments

Information & Contributors

Information

Published In

cover image Pattern Recognition

Pattern Recognition Volume 39, Issue 2

February, 2006

156 pages

ISSN:0031-3203

Issue’s Table of Contents

Copyright © Pattern Recognition Society © 2005.

Publisher

Elsevier Science Inc.

United States

Publication History

Published: 01 February 2006

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

15
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 03 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Hassaballah MAly S(2015)Face recognitionIET Computer Vision10.1049/iet-cvi.2014.00849:4(614-626)Online publication date: 1-Aug-2015
https://dl.acm.org/doi/10.1049/iet-cvi.2014.0084
García-Zurdo R(2014)Three-Dimensional Face Shape by Local Fitting to a Single Reference ModelInternational Journal of Computer Vision and Image Processing10.4018/ijcvip.20140101024:1(17-29)Online publication date: 1-Jan-2014
https://dl.acm.org/doi/10.4018/ijcvip.2014010102
Hanilçi CKinnunen T(2014)Source cell-phone recognition from recorded speech using non-speech segmentsDigital Signal Processing10.1016/j.dsp.2014.08.00835:C(75-85)Online publication date: 1-Dec-2014
https://dl.acm.org/doi/10.1016/j.dsp.2014.08.008
Watanabe SNakamura AJuang B(2014)Structural Bayesian Linear Regression for Hidden Markov ModelsJournal of Signal Processing Systems10.1007/s11265-013-0785-874:3(341-358)Online publication date: 1-Mar-2014
https://dl.acm.org/doi/10.1007/s11265-013-0785-8
Wang CLi YSong X(2013)Video-to-video face authentication system robust to pose variationsExpert Systems with Applications: An International Journal10.1016/j.eswa.2012.08.00940:2(722-735)Online publication date: 1-Feb-2013
https://dl.acm.org/doi/10.1016/j.eswa.2012.08.009
Liu QNgan K(2012)Overlapping local phase feature (OLPF) for robust face recognition in surveillanceProceedings of the 14th international conference on Advanced Concepts for Intelligent Vision Systems10.1007/978-3-642-33140-4_22(246-257)Online publication date: 4-Sep-2012
https://dl.acm.org/doi/10.1007/978-3-642-33140-4_22
Chen SMau SHarandi MSanderson CBigdeli ALovell B(2011)Face recognition from still images to video sequencesJournal on Image and Video Processing10.1155/2011/7905982011(1-14)Online publication date: 1-Jan-2011
https://dl.acm.org/doi/10.1155/2011/790598
Jadhav DHolambe R(2010)Rotation, illumination invariant polynomial kernel Fisher discriminant analysis using Radon and discrete cosine transforms based features for face recognitionPattern Recognition Letters10.1016/j.patrec.2009.12.02631:9(1002-1009)Online publication date: 1-Jul-2010
https://dl.acm.org/doi/10.1016/j.patrec.2009.12.026
Sukno FGuerrero JFrangi A(2010)Projective active shape models for pose-variant image analysis of quasi-planar objectsPattern Recognition10.1016/j.patcog.2009.07.00143:3(835-849)Online publication date: 1-Mar-2010
https://dl.acm.org/doi/10.1016/j.patcog.2009.07.001
Lucey SChen T(2008)A Viewpoint Invariant, Sparsely Registered, Patch Based, Face VerifierInternational Journal of Computer Vision10.1007/s11263-007-0119-z80:1(58-71)Online publication date: 1-Oct-2008
https://dl.acm.org/doi/10.1007/s11263-007-0119-z
Show More Cited By

View Options

View options

Figures

Tables

Media

View Issue’s Table of Contents