Towards Pose-Invariant 2D Face Classification for Surveillance

  • Conrad Sanderson
  • Ting Shang
  • Brian C. Lovell
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4778)


A key problem for “face in the crowd” recognition from existing surveillance cameras in public spaces (such as mass transit centres) is the issue of pose mismatches between probe and gallery faces. In addition to accuracy, scalability is also important, necessarily limiting the complexity of face classification algorithms. In this paper we evaluate recent approaches to the recognition of faces at relatively large pose angles from a gallery of frontal images and propose novel adaptations as well as modifications. Specifically, we compare and contrast the accuracy, robustness and speed of an Active Appearance Model (AAM) based method (where realistic frontal faces are synthesized from non-frontal probe faces) against bag-of-features methods (which are local feature approaches based on block Discrete Cosine Transforms and Gaussian Mixture Models). We show a novel approach where the AAM based technique is sped up by directly obtaining pose-robust features, allowing the omission of the computationally expensive and artefact producing image synthesis step. Additionally, we adapt a histogram-based bag-of-features technique to face classification and contrast its properties to a previously proposed direct bag-of-features method. We also show that the two bag-of-features approaches can be considerably sped up, without a loss in classification accuracy, via an approximation of the exponential function. Experiments on the FERET and PIE databases suggest that the bag-of-features techniques generally attain better performance, with significantly lower computational loads. The histogram-based bag-of-features technique is capable of achieving an average recognition accuracy of 89% for pose angles of around 25 degrees.


Face Recognition Discrete Cosine Transform Face Image Gaussian Mixture Model Active Appearance Model 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    McCahill, M., Norris, C.: Urbaneye: CCTV in London. Centre for Criminology and Criminal Justice, University of Hull, UK (2002)Google Scholar
  2. 2.
    Phillips, P., Grother, P., Micheals, R., Blackburn, D., Tabassi, E., Bone, M.: Face recognition vendor test 2002. In: Proc. Analysis and Modeling of Faces and Gestures, p. 44 (2003)Google Scholar
  3. 3.
    Blanz, V., Grother, P., Phillips, P., Vetter, T.: Face recognition based on frontal views generated from non-frontal images. In: Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 454–461. IEEE Computer Society Press, Los Alamitos (2005)Google Scholar
  4. 4.
    Shan, T., Lovell, B., Chen, S.: Face recognition robust to head pose from one sample image. In: Proc. 18th Int. Conf. Pattern Recognition (ICPR), vol. 1, pp. 515–518 (2006)Google Scholar
  5. 5.
    Sanderson, C., Bengio, S., Gao, Y.: On transforming statistical models for non-frontal face verification. Pattern Recognition 39, 288–302 (2006)CrossRefGoogle Scholar
  6. 6.
    Cardinaux, F., Sanderson, C., Bengio, S.: User authentication via adapted statistical models of face images. IEEE Trans. Signal Processing 54, 361–373 (2006)CrossRefGoogle Scholar
  7. 7.
    Lucey, S., Chen, T.: Learning patch dependencies for improved pose mismatched face verification. In: IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 909–915. IEEE Computer Society Press, Los Alamitos (2006)Google Scholar
  8. 8.
    Wiskott, L., Fellous, J., Kuiger, N., Malsburg, C.V.: Face recognition by elastic bunch graph matching. IEEE Trans. Pattern Analysis and Machine Intelligence 19, 775–779 (1997)CrossRefGoogle Scholar
  9. 9.
    Bowyer, K., Chang, K., Flynn, P.: A survey of approaches and challenges in 3D and multi-modal 3D+2D face recognition. Computer Vision and Image Understanding 101, 1–15 (2006)CrossRefGoogle Scholar
  10. 10.
    Csurka, G., Dance, C., Fan, L., Willamowski, J., Bray, C.: Visual cetegorization with bags of keypoints. In: Workshop on Statistical Learning in Computer Vision (co-located with ECCV 2004) (2004)Google Scholar
  11. 11.
    Sivic, J., Zisserman, A.: Video google: A text retrieval approach to object matching in videos. In: Proc. 9th International Conference on Computer Vision (ICCV), vol. 2, pp. 1470–1477 (2003)Google Scholar
  12. 12.
    Nowak, E., Jurie, F., Triggs, B.: Sampling strategies for bag-of-features image classification. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3954, pp. 490–503. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  13. 13.
    Phillips, P., Moon, H., Rizvi, S., Rauss, P.: The FERET evaluation methodology for face-recognition algorithms. IEEE Trans. Pattern Analysis and Machine Intelligence 22, 1090–1104 (2000)CrossRefGoogle Scholar
  14. 14.
    Sim, T., Baker, S., Bsat, M.: The CMU pose, illumination, and expression database. IEEE. Trans. Pattern Analysis and Machine Intelligence 25, 1615–1618 (2003)CrossRefGoogle Scholar
  15. 15.
    Cootes, T., Taylor, C.: Active shape models - ‘smart snakes’. In: Proc. British Machine Vision Conference, pp. 267–275 (1992)Google Scholar
  16. 16.
    Cootes, T., Edwards, G., Taylor, C.: Active appearance models. IEEE Trans. Pattern Analysis and Machine Intelligence 23, 681–685 (2001)CrossRefGoogle Scholar
  17. 17.
    Duda, R., Hart, P., Stork, D.: Pattern Classification, 2nd edn. Wiley, Chichester (2001)zbMATHGoogle Scholar
  18. 18.
    Cootes, T., Walker, K., Taylor, C.: View-based active appearance models. In: Proc. 4th IEEE International Conference on Automatic Face and Gesture Recognition, pp. 227–232. IEEE Computer Society Press, Los Alamitos (2000)Google Scholar
  19. 19.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60, 91–110 (2004)CrossRefGoogle Scholar
  20. 20.
    Lee, T.S.: Image representation using 2D Gabor wavelets. IEEE Trans. Pattern Analysis and Machine Intelligence 18, 959–971 (1996)CrossRefGoogle Scholar
  21. 21.
    Gonzales, R., Woods, R.: Digital Image Processing. Addison-Wesley, Reading (1992)Google Scholar
  22. 22.
    Rodriguez, Y., Cardinaux, F., Bengio, S., Mariethoz, J.: Measuring the performance of face localization systems. Image and Vision Computing 24, 882–893 (2006)CrossRefGoogle Scholar
  23. 23.
    Wallraven, C., Caputo, B., Graf, A.: Recognition with local features: the kernel recipe. In: Proc. 9th International Conference on Computer Vision (ICCV), vol. 1, pp. 257–264 (2003)Google Scholar
  24. 24.
    Kadir, T., Brady, M.: Saliency, scale and image description. International Journal of Computer Vision 45, 83–105 (2001)zbMATHCrossRefGoogle Scholar
  25. 25.
    Schraudolph, N.: A fast, compact approximation of the exponential function. Neural Computation 11, 853–862 (1999)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Conrad Sanderson
    • 1
  • Ting Shang
    • 1
    • 2
  • Brian C. Lovell
    • 1
    • 2
  1. 1.NICTA, 300 Adelaide St, Brisbane, QLD 4000Australia
  2. 2.ITEE, University of Queensland, Brisbane, QLD 4072Australia

Personalised recommendations