ENHANCED PHASE–BASED DISPLACEMENT ESTIMATION - An Application to Facial Feature Extraction and Tracking

Mohamed Dahmane, Jean Meunier

Abstract

In this work, we develop a multi-scale approach for automatic facial feature detection and tracking. The method is based on a coarse to fine paradigm to characterize a set of facial fiducial points using a bank of Gabor filters that have interesting properties such as directionality, scalability and hierarchy. When the first face image is captured, a trained grid is used on the coarsest level to estimate a rough position for each facial feature. Afterward, a refinement stage is performed from the coarsest to the finest (original) image level to get accurate positions. These are then tracked over the subsequent frames using a modification of a fast phase– based technique. This includes a redefinition of the confidence measure and introduces a conditional disparity estimation procedure. Experimental results show that facial features can be localized with high accuracy and that their tracking can be kept during long periods of free head motion.

References

  1. Cohen, J., Zlochower, A., Lien, J., and Kanade, T. (1999). Face Analysis by Feature Point Tracking Has Concurrent Validity with Manual FACS Coding. Psychophysiology 36(1):35-43.
  2. Cottrell, G., Dailey, M., and Padgett, C. (2003). Is All Faces Processing Holistic? The view from UCSD. M. Wenger, J Twnsend (Eds), Computational, Geometric and Process Perspectives on Facial Recognition, Contexts and Challenges: Contexts and Challenges, Erlbaum.
  3. Flaton, K. and Toborg, S. (1989). An approach to image recognition using sparse filter graphs. In International Joint Conference on Neural Networks, (1):313-320.
  4. Fleet, D. and Jepson, A. (1993). Stability of phase information. In IEEE Trans. on PAMI, 15(12):1253-1268.
  5. Hammal, Z., Couvreur, L., Caplier, A., and Rombaut, M. (2007). Facial expression classification: An approach based on the fusion of facial deformation unsing the transferable belief model. In Int. Jour. of Approximate Reasonning.
  6. Hu, Y., Chen, L., Zhou, Y., and Zhang, H. (2004). Estimating face pose by facial asymmetry and geometry. In IEEE International Conference on Automatic Face and Gesture Recognition.
  7. Jiao, F., Li, S., Shum, H.-Y., and Schuurmans, D. (2003). Face alignment using statistical models and wavelet features. In Computer Vision and Pattern Recognition (1) p. 321-327.
  8. Lades, M., Vorbrüggen, J. C., Buhmann, J., Lange, J., von der Malsburg, C., Würtz, R. P., and Konen, W. (1993). Distortion invariant object recognition in the dynamic link architecture. In IEEE Transactions on Computers 3(42):300-311.
  9. Liu, C. and Wechsler, H. (2003). Independent component analysis of gabor features for face recognition. In IEEE Trans. on Neural Networks, (14):4, 919-928.
  10. Maurer, T. and von der Malsburg, C. (1996). Tracking and learning graphs and pose on image sequences of faces. In 2nd International Conference on Automatic Face and Gesture Recognition, p. 76.
  11. McKenna, S., Gong, S., Würtz, R., Tanner, J., and Banin, D. (1997). Tracking facial feature points with gabor wavelets and shape models. In Proceedings of the First International Conference on Audio- and Videobased Biometric Person Authentication, 1206(3):35- 42. Springer Verlag.
  12. Shen, L. and Bai, L. (2006). A review on gabor wavelets for face recognition. In Pattern Analysis and Applications, (9):2,273-292.
  13. Theimer, W. and Mallot, H. (1994). Phase-based binocular vergence control and depth reconstruction using active vision. In CVGIP: Image Understanding, 60(3):343- 358.
  14. Tian, Y., Kanade, T., and Cohn, J. (2002). Evaluation of gabor wavelet-based facial action unit recognition in image sequences of increasing complexity. In In Proc. of the 5th IEEE Int. Conf. on Automatic Face and Gesture Recognition.
  15. Valstar, M. and Pantic, M. (2006). Fully automatic facial action unit detection and temporal analysis. In CVPRW, p. 149.
  16. Wiskott, L., Fellous, J., Krüger, N., and von der Malsburg, C. (1997). Face recognition by elastic bunch graph matching. In IEEE Transactions on Pattern Analysis and Machine Intelligence. 19(7):775-779.
  17. Yang, M. (2004). Recent advances in face detection. In Tutorial of IEEE Conferece on Pattern Recognition.
  18. Zhang, B., Gao, W., Shan, S., and Wang, W. (2003). Constraint shape model using edge constraint and gabor wavelet based search. In AVBPA03, 52-61.
  19. Zhang, B., Shan, S., Chen, X., and Gao, W. (2007). Histogram of gabor phase patterns (HGPP): A novel object representation approach for face recognition. In IEEE Tran. on Image Processing (16):1, pp.57-68.
  20. Zhu, Z. and Ji, Q. (2006). Robust pose invariant facial feature detection and tracking in real-time. In ICPR, 1092-1095.
Download


Paper Citation


in Harvard Style

Dahmane M., Meunier J. and Meunier J. (2008). ENHANCED PHASE–BASED DISPLACEMENT ESTIMATION - An Application to Facial Feature Extraction and Tracking . In Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008) ISBN 978-989-8111-21-0, pages 427-433. DOI: 10.5220/0001081804270433


in Bibtex Style

@conference{visapp08,
author={Mohamed Dahmane and Jean Meunier and Jean Meunier},
title={ENHANCED PHASE–BASED DISPLACEMENT ESTIMATION - An Application to Facial Feature Extraction and Tracking},
booktitle={Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)},
year={2008},
pages={427-433},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001081804270433},
isbn={978-989-8111-21-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)
TI - ENHANCED PHASE–BASED DISPLACEMENT ESTIMATION - An Application to Facial Feature Extraction and Tracking
SN - 978-989-8111-21-0
AU - Dahmane M.
AU - Meunier J.
AU - Meunier J.
PY - 2008
SP - 427
EP - 433
DO - 10.5220/0001081804270433