This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Discriminative Face Alignment
November 2009 (vol. 31 no. 11)
pp. 1941-1954
ASCII Text
x 
 
Xiaoming Liu, "Discriminative Face Alignment," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 31, no. 11, pp. 1941-1954, November, 2009.
 
 
BibTex
x
 
@article{ 10.1109/TPAMI.2008.238,
author = {Xiaoming Liu},
title = {Discriminative Face Alignment},
journal ={IEEE Transactions on Pattern Analysis and Machine Intelligence},
volume = {31},
number = {11},
issn = {0162-8828},
year = {2009},
pages = {1941-1954},
doi = {http://doi.ieeecomputersociety.org/10.1109/TPAMI.2008.238},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - JOUR
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
TI - Discriminative Face Alignment
IS - 11
SN - 0162-8828
SP1941
EP1954
EPD - 1941-1954
A1 - Xiaoming Liu,
PY - 2009
KW - Face
KW - alignment
KW - boosting
KW - active appearance models
KW - AAM
KW - boosted appearance models
KW - BAM
KW - image alignment
KW - gradient descent
KW - landmark
KW - generative versus discriminative model.
VL - 31
JA - IEEE Transactions on Pattern Analysis and Machine Intelligence
ER -
 
Xiaoming Liu, GE Global Research, Schenectady
This paper proposes a discriminative framework for efficiently aligning images. Although conventional Active Appearance Models (AAMs)-based approaches have achieved some success, they suffer from the generalization problem, i.e., how to align any image with a generic model. We treat the iterative image alignment problem as a process of maximizing the score of a trained two-class classifier that is able to distinguish correct alignment (positive class) from incorrect alignment (negative class). During the modeling stage, given a set of images with ground truth landmarks, we train a conventional Point Distribution Model (PDM) and a boosting-based classifier, which acts as an appearance model. When tested on an image with the initial landmark locations, the proposed algorithm iteratively updates the shape parameters of the PDM via the gradient ascent method such that the classification score of the warped image is maximized. We use the term Boosted Appearance Models (BAMs) to refer to the learned shape and appearance models, as well as our specific alignment method. The proposed framework is applied to the face alignment problem. Using extensive experimentation, we show that, compared to the AAM-based approach, this framework greatly improves the robustness, accuracy, and efficiency of face alignment by a large margin, especially for unseen data.

[1] B. Lucas and T. Kanade, “An Iterative Technique of Image Registration and Its Application to Stereo,” Proc. Seventh Int'l Joint Conf. Artificial Intelligence, pp. 674-679, 1981.
[2] I. Matthews and S. Baker, “Active Appearance Models Revisited,” Int'l J. Computer Vision, vol. 60, no. 2, pp. 135-164, 2004.
[3] S. Baker, I. Matthews, and J. Schneider, “Automatic Construction of Active Appearance Models as an Image Coding Problem,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 10, pp.1380-1384, Oct. 2004.
[4] M. Black and A. Jepson, “Eigentracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation,” Int'l J. Computer Vision, vol. 26, no. 1, pp. 63-84, 1998.
[5] G. Hager and P. Belhumeur, “Efficient Region Tracking with Parametric Models of Geometry and Illumination,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 10, pp. 1025-1039, Oct. 1998.
[6] H.-Y. Shum and R. Szeliski, “Construction of Panoramic Image Mosaics with Global and Local Alignment,” Int'l J. Computer Vision, vol. 36, no. 2, pp. 101-130, 2000.
[7] J.G. Bosch, S.C. Mitchell, B.P.F. Lelieveldt, F. Nijland, O. Kamp, M. Sonka, and J.H.C. Reiber, “Automatic Segmentation of Echocardiographic Sequences by Active Appearance Motion Models,” IEEE Trans. Medical Imaging, vol. 21, no. 11, pp. 1374-1383, Nov. 2002.
[8] B. Rolfe, M. Cardew-Hall, S. Abdallah, and G. West, “Geometric Shape Errors in Forging: Developing a Metric and an Inverse Model,” Proc. Inst. of Mechanical Engineers Part B—J. Eng. Manufacture, vol. 215, no. 9, pp. 1229-1240, 2001.
[9] T. Cootes, D. Cooper, C. Tylor, and J. Graham, “A Trainable Method of Parametric Shape Description,” Proc. Second British Machine Vision Conf., pp. 54-61, Sept. 1991.
[10] T.F. Cootes, G.J. Edwards, and C.J. Taylor, “Active Appearance Models,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 6, pp. 681-685, June 2001.
[11] S. Baker and I. Matthews, “Lucas-Kanade 20 Years on: A Unifying Framework,” Int'l J. Computer Vision, vol. 56, no. 3, pp. 221-255, 2004.
[12] R. Gross, I. Matthews, and S. Baker, “Generic vs. Person Specific Active Appearance Models,” Image and Vision Computing, vol. 23, no. 11, pp. 1080-1093, 2005.
[13] X. Liu, P. Tu, and F. Wheeler, “Face Model Fitting on Low Resolution Images,” Proc. 17th British Machine Vision Conf., vol. 3, pp. 1079-1088, 2006.
[14] P. Viola and M. Jones, “Robust Real-Time Face Detection,” Int'l J. Computer Vision, vol. 57, no. 2, pp. 137-154, 2004.
[15] C.P. Papageorgiou, M. Oren, and T. Poggio, “A General Framework for Object Detection,” Proc. Sixth Int'l Conf. Computer Vision, pp. 555-562, 1998.
[16] S. Yan, C. Liu, S.Z. Li, H. Zhang, H.-Y. Shum, and Q. Cheng, “Face Alignment Using Texture-Constrained Active Shape Models,” Image and Vision Computing, vol. 21, no. 1, pp. 69-75, 2003.
[17] D. Cristinacce and T. Cootes, “Facial Feature Detection and Tracking with Automatic Template Selection,” Proc. Seventh Int'l Conf. Automatic Face and Gesture Recognition, pp. 429-434, 2006.
[18] G. Dedeoglu, T. Kanade, and S. Baker, “The Asymmetry of Image Registration and Its Application to Face Tracking,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 29, no. 5, pp. 807-823, May 2007.
[19] R. Beichel, H. Bischof, F. Leberl, and M. Sonka, “Robust Active Appearance Models and Their Application to Medical Image Analysis,” IEEE Trans. Medical Imaging, vol. 24, no. 9, pp. 1151-1169, Sept. 2005.
[20] E. Jones and S. Soatto, “Layered Active Appearance Models,” Proc. 10th Int'l Conf. Computer Vision, vol. 2, pp. 1097-1102, 2005.
[21] T. Cootes and C. Taylor, “Statistical Models of Appearance for Computer Vision,” technical report, Imaging Science and Biomedical Eng., Univ. of Manchester, Mar. 2004.
[22] Y. Zhou, L. Gu, and H. Zhang, “Bayesian Tangent Shape Model: Estimating Shape and Pose Parameters via Bayesian Inference,” Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 109-116, 2003.
[23] Y. Zhou, W. Zhang, X. Tang, and H. Shum, “A Bayesian Mixture Model for Multi-View Face Alignment,” Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 741-746, 2005.
[24] L. Liang, F. Wen, Y. Xu, X. Tang, and H. Shum, “Accurate Face Alignment Using Shape Constrained Markov Network,” Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, vol. 1, pp.1313-1319, 2006.
[25] D. Cristinacce and T. Cootes, “Boosted Regression Active Shape Models,” Proc. 18th British Machine Vision Conf., vol. 2, pp. 880-889, 2007.
[26] A.U. Batur and M.H. Hayes, III, “Adaptive Active Appearance Models,” IEEE Trans. Image Processing, vol. 14, no. 11, pp. 1707-1721, Nov. 2005.
[27] C. Butakoff and A. Frangi, “A Framework for Weighted Fusion of Multiple Statistical Models of Shape and Appearance,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 28, no. 11, pp.1847-1857, Nov. 2006.
[28] R. Donner, M. Reiter, G. Langs, P. Peloschek, and H. Bischof, “Fast Active Appearance Model Search Using Canonical Correlation Analysis,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 28, no. 10, pp. 1690-1694, Oct. 2006.
[29] A. Kanaujia and D. Metaxas, “Large Scale Learning of Active Shape Models,” Proc. 2007 Int'l Conf. Image Processing, vol. 1, pp.265-268, 2007.
[30] J. Tu, Z. Zhang, Z. Zeng, and T. Huang, “Face Localization via Hierarchical Condensation with Fisher Boosting Feature Selection,” Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 719-724, 2004.
[31] F.D. la Torre Frade, A.C. Romea, J. Cohn, and T. Kanade, “Filtered Component Analysis to Increase Robustness to Local Minima in Appearance Models,” Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, 2007.
[32] F. Jiao, S. Li, H.-Y. Shum, and D. Schuurmans, “Face Alignment Using Statistical Models and Wavelet Features,” Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 321-327, 2003.
[33] C. Hu, R. Feris, and M. Turk, “Active Wavelet Networks for Face Alignment,” Proc. 14th British Machine Vision Conf., 2003.
[34] S. Avidan, “Support Vector Tracking,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 8, pp. 1064-1072, Aug. 2004.
[35] O. Williams, A. Blake, and R. Cipolla, “Sparse Bayesian Learning for Efficient Visual Tracking,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 27, no. 8, pp. 1292-1304, Aug. 2005.
[36] A. Hidaka, K. Nishida, and T. Kurita, “Face Tracking by Maximizing Classification Score of Face Detector Based on Rectangle Features,” Proc. IEEE Int'l Conf. Computer Vision Systems, p. 48, 2006.
[37] K. Chang, K. Bowyer, and P. Flynn, “Face Recognition Using 2D and 3D Facial Data,” Proc. ACM Workshop Multimodal User Authentication, pp. 25-32, Dec. 2003.
[38] M. Turk and A. Pentland, “Eigenfaces for Recognition,” J.Cognitive Neuroscience, vol. 3, no. 1, pp. 71-86, 1991.
[39] N. Dalal and W. Triggs, “Histograms of Oriented Gradients for Human Detection,” Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 886-893, 2005.
[40] D.G. Lowe, “Distinctive Image Features from Scale-Invariant Keypoints,” Int'l J. Computer Vision, vol. 60, no. 2, pp. 91-110, 2004.
[41] Y. Freund and R.E. Schapire, “A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting,” J.Computer and System Sciences, vol. 55, no. 1, pp. 119-139, 1997.
[42] J. Friedman, T. Hastie, and R. Tibshirani, “Additive Logistic Regression: A Statistical View of Boosting,” The Annals of Statistics, vol. 38, no. 2, pp. 337-374, 2000.
[43] R. Meir and G. Raetsch, An Introduction to Boosting and Leveraging, S. Mendelson and A. Smola, eds. Springer, 2003.
[44] R. Lienhart, A. Kuranov, and V. Pisarevsky, “Empirical Analysis of Detection Cascades of Boosted Classifiers for Rapid Object Detection,” Proc. 25th Pattern Recognition Symp., pp. 297-304, 2003.
[45] Y. Li and W. Ito, “Shape Parameter Optimization for Adaboosted Active Shape Model,” Proc. 10th Int'l Conf. Computer Vision, vol. 1, pp. 251-258, 2005.
[46] L. Gu, E. Xing, and T. Kanade, “Learning GMRF Structures for Spatial Priors,” Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, 2007.
[47] S. Lucey, A.B. Ashraf, and J. Cohn, “Investigating Spontaneous Facial Action Recognition through AAM Representations of the Face,” Face Recognition Book, K. Kurihara, ed., Pro Literatur Verlag, Apr. 2007.
[48] P.J. Phillips, H. Moon, P.J. Rauss, and S. Rizvi, “The FERET Evaluation Methodology for Face Recognition Algorithms,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 10, pp.1090-1104, Oct. 2000.
[49] M.B. Stegmann, B.K. Ersboll, and R. Larsen., “FAME—A Flexible Appearance Modeling Environment,” IEEE Trans. Medical Imaging, vol. 22, no. 10, pp. 1319-1331, Oct. 2003.
[50] O. Jesorsky, K.J. Kirchberg, and R.W. Frischholz, “Robust Face Detection Using the Hausdorff Distance,” Proc. Third Int'l Conf. Audio- and Video-Based Biometric Person Authentication, pp. 90-95, 2001.

Index Terms:
Face, alignment, boosting, active appearance models, AAM, boosted appearance models, BAM, image alignment, gradient descent, landmark, generative versus discriminative model.
Citation:
Xiaoming Liu, "Discriminative Face Alignment," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 31, no. 11, pp. 1941-1954, Nov. 2009, doi:10.1109/TPAMI.2008.238
Usage of this product signifies your acceptance of the Terms of Use.