This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Unsupervised Image Matching Based on Manifold Alignment
Aug. 2012 (vol. 34 no. 8)
pp. 1658-1664
Fengchun Huang, Dept. ofMachine Intell., Peking Univ., Beijing, China
Yuru Pei, Dept. ofMachine Intell., Peking Univ., Beijing, China
Fuhao Shi, Dept. ofMachine Intell., Peking Univ., Beijing, China
Hongbin Zha, Dept. ofMachine Intell., Peking Univ., Beijing, China
This paper challenges the issue of automatic matching between two image sets with similar intrinsic structures and different appearances, especially when there is no prior correspondence. An unsupervised manifold alignment framework is proposed to establish correspondence between data sets by a mapping function in the mutual embedding space. We introduce a local similarity metric based on parameterized distance curves to represent the connection of one point with the rest of the manifold. A small set of valid feature pairs can be found without manual interactions by matching the distance curve of one manifold with the curve cluster of the other manifold. To avoid potential confusions in image matching, we propose an extended affine transformation to solve the nonrigid alignment in the embedding space. The comparatively tight alignments and the structure preservation can be obtained simultaneously. The point pairs with the minimum distance after alignment are viewed as the matchings. We apply manifold alignment to image set matching problems. The correspondence between image sets of different poses, illuminations, and identities can be established effectively by our approach.

[1] C. Wang and S. Mahadevan, "Manifold Alignment Using Procrustes Analysis," Proc. Int'l Conf. Machine Learning, pp. 1120-1127, 2008.
[2] F. Diaz and D. Metzler, "Pseudo-Aligned Multilingual Corpora," Proc. Int'l Joint Conf. Artificial Intelligence, pp. 2727-2732, 2007.
[3] J. Ham, I. Ahn, and D. Lee, "Learning a Manifold-Constrained Map between Image Sets: Applications to Matching and Pose Estimation," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 817-824, 2006.
[4] R. Wang and X. Chen, "Manifold Discriminant Analysis," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 429-436, 2009.
[5] N. Grujic, S. Ilic, V. Lepetit, and P. Fua, "3D Facial Pose Estimation by Image Retrieval," Proc. Int'l Conf. Automatic Face and Gesture Recognition, 2008.
[6] I. Fodor, "A Survey of Dimension Reduction Techniques," technical report, Center for Applied Scientific Computing, Lawrence Livermore Nat'l Laboratory, 2002.
[7] J. Tenenbaum, V. Silva, and J. Langford, "A Global Geometric Framework for Nonlinear Dimensionality Reduction," Science, vol. 290, no. 5500, pp. 2319-2323, 2000.
[8] S. Roweis and L. Saul, "Nonlinear Dimensionality Reduction by Locally Linear Embedding," Science, vol. 290, no. 5500, pp. 2323-2326, 2000.
[9] M. Belkin and P. Niyogi, "Laplacian Eigenmaps for Dimensionality Reduction and Data Representation," Neural Computation, vol. 15, no. 6, pp. 1373-1396, 2003.
[10] C. Wang and S. Mahadevan, "Manifold Alignment without Correspondence," Proc. Int'l Joint Conf. Artificial Intelligence, pp. 1273-1278, 2009.
[11] S. Lafon, Y. Keller, and R. Coifman, "Data Fusion and Multicue Data Matching by Diffusion Maps," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 28, no. 11, pp. 1784-1797, Nov. 2006.
[12] J. Ham, D. Lee, and L. Saul, "Semisupervised Alignment of Manifolds," Proc. 10th Int'l Workshop Artificial Intelligence and Statistics, pp. 120-127, 2005.
[13] L. Xiong, F. Wang, and C. Zhang, "Semi-Definite Manifold Alignment," Proc. European Conf. Machine Learning, pp. 773-781, 2007.
[14] P. Besl and H. McKay, "A Method for Registration of 3-D Shapes," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 14, no. 2, pp. 239-256, Feb. 1992.
[15] R.W. Sumner and J. Popović, "Deformation Transfer for Triangle Meshes," Proc. ACM Conf. Computer Graphics and Interactive Techniques, pp. 399-405, 2004.
[16] B. Allen, B. Curless, and Z. Popović, "The Space of All Body Shapes: Reconstruction and Parameterization from Range Scans," Proc. ACM Conf. Computer Graphics and Interactive Techniques, pp. 587-594, 2003.
[17] B. Allen, B. Curless, and Z. Popovic, "Articulated Body Deformation from Range Scan Data," Proc. ACM Conf. Computer Graphics and Interactive Techniques, pp. 612-619, 2002.
[18] R.L. Burden and J.D. Faires, Numerical Analysis, seventh ed. Brooks Cole, 2000.
[19] L. Yin, X. Chen, Y. Sun, T. Worm, and M. Reale, "A High-Resolution 3D Dynamic Facial Expression Database," Proc. Int'l Conf. Automatic Face and Gesture Recognition, 2008.
[20] M. Avriel, Nonlinear Programming: Analysis and Methods. Dover Publications, 2003.
[21] P. Phillips, H. Moon, S. Rizvi, and P. Rauss, "The FERET Evaluation Methodology for Face-Recognition Algorithms," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 10, pp. 1090-1104, Oct. 2000.
[22] I. Matthews and S. Baker, "Active Appearance Models Revisited," Int'l J. Computer Vision, vol. 60, no. 2, pp. 135-164, 2004.
[23] The ORIENTAL Face Database, http://www.aiar.xjtu.edu.cn/groups/face/ EnglishHomePage.htm, 2011.
[24] Autodesk MotionBuilder, http://usa.autodesk.com/adsk/servlet/pc index?siteID=123112&id=13581855 , 2011.
[25] H.M. Berman, J. Westbrook, Z. Feng, G. Gillilandand, T.N. Bhat, H. Weissig, I. Shindyalov, and P.E. Bourne, "The Protein Data Bank," Nucleic Acids Research, vol. 28, pp. 235-242, 2000.

Index Terms:
unsupervised learning,image matching,structure preservation,unsupervised image matching,manifold alignment,automatic matching,image sets,intrinsic structures,unsupervised manifold alignment framework,mutual embedding space,mapping function,data sets,parameterized distance curves,Manifolds,Face,Image matching,Vectors,Databases,Lighting,Optimization,parameterized distance curve.,Manifold alignment,unsupervised image set matching,nonrigid transformation
Citation:
Fengchun Huang, Yuru Pei, Fuhao Shi, Hongbin Zha, "Unsupervised Image Matching Based on Manifold Alignment," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 8, pp. 1658-1664, Aug. 2012, doi:10.1109/TPAMI.2011.229
Usage of this product signifies your acceptance of the Terms of Use.