Reliable Face Alignment Using Two-Stage AAM

AAM (active appearance model) has been successfully applied to face and facial feature localization. However, its performance is sensitive to initial parameter values. In this paper, we propose a two-stage AAM for robust face alignment, which first fits an inner face-AAM model to the inner facial feature points of the face and then localizes the whole face and facial features by optimizing the whole face-AAM model parameters. Experiments show that the proposed face alignment method using two-stage AAM is more reliable to the background and the head pose than the standard AAM-based face alignment method.

Authors:

• Sunho Ki
• Daehwan Kim
• Seongwon Cho
• Sun-Tae Chung
• Jaemin Kim
• Yun-Kwang Hong
• Chang Joon Park
• Dongmin Kwon
• Minhee Kang
• Yusung Kim
• Younghan Yoon

Keywords:

• AAM
• Face Alignment
• Feature Extraction
• PCA

References:

[1] Li, S.Z., Jain, A.K.: Handbook of Face Recognition. Springer (2004).
[2] Shan, S., Chang, Y., Gao, W., Cao, B., Yang, P.: Curse of Mis-alignment in Face Recognition: Problem and a Novel Mis-alignment Learning
Solution, Proc. 6th IEEE Conf. on Automatic Face and Gesture Recognition, (2004) 314 - 3203.
[3] Li, S.Z., Cheng, Y. S., Zhang, H. J., Cheng, Q. S.: Multi-View Face
Alignment Using Direct Appearance Models. Proc. 5th IEEE Conf. on
Automatic Face and Gesture Recognition, (2004) 309-314.
[4] Jiao, F., Li, S.Z., Shum, H-Y., Schuurmans, D.: Face Alignment Using
Statistical Models and Wavelet Features. Proc. 2003 IEEE Computer
Society Conf. on Computer Vision and Pattern Recognition, Vol.1, (2003)
I-321 - I-327.
[5] Huang, Y., Lin, S., Li, S.Z., Lu, H., Shum, H.-Y.: Face Alignment Under
Variable Illumination. Proc. 6th IEEE Int-l Conf. on Automatic Face and
Gesture Recognition, (2004) 85-90.
[6] Xin, S., Ai, H.: Face Alignment under Various Poses and Expressions.
ACII2005, LNCS 3784, (2005) 40-47.
[7] Zhang, L., Haizhou A., Xin, Huang, C., Tsukiji, S.: Robust Face
Alignment Based on Local Texture Classifiers. IEEE Conf. on Image
Processing, Vol. 2, (2005) 354-357.
[8] Edwards, G., Taylor, C. J., Cootes, T. F.: Interpreting Face Images using
Active Appearance Models. Proc. IEEE Int. Conf. Automatic Face and
Gesture Recognition, (1998) 300-305.
[9] Cootes, T. F., Edwards, G. J., Taylor, C. J., Burkhardt, H., Neuman, B.:
Active appearance models. Proc. Eur. Conf. Computer Vision, Vol. 2,
(1998) 484-498.
[10] Cootes, T. F., Edwards, G. J., Taylor, C. J.: Active Appearance Models.
IEEE Trans. Pattern Anal. Mach. Intell., Vol. 23, no. 6, (2001) 681-685.
[11] Matthews, I., Baker, S.: Active Appearance Models Revisited. Int. Journal
of Computer Vision, Vol. 60, No. 2, (2004) 135 - 164.
[12] Batur, A.U., Hayes, M.H.: Adaptive Active Appearance Models. IEEE
Trans. Image Processing, Vol. 14, Issue 11, (2005) 1707- 1721.
[13] Cristinancce, D., Cootes, T. , Scott, I.: A Multi-Stage Approach to Facial
Feature Detection. Proc. British Machine Vision Conference, Vol.1,
(2004) 277-286.
[14] Boyd. S., Vandenberghe, L.: Convex Optimization. Cambridge
University Press.
[15] Gower, J. C.: Generalized Procrustes analysis. Psychometrika, Vol. 40,
(1975) 33-51.
[16] Lee, D. T., Lee, D. T., Schachter, B. J.: Two Algorithms for Constructing
a Delaunay Triangulation. Int. J. Computer Information Sci. Vol.9, (1980) 219-242.
[17] DTU(Technical university of Denmark) IMM face
database,http://www2.imm.dtu.dk/~aam/.