This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Unsupervised Object Segmentation with a Hybrid Graph Model (HGM)
May 2010 (vol. 32 no. 5)
pp. 910-924
Guangcan Liu, Shanghai Jiao Tong University, Shanghai
Zhouchen Lin, Microsoft Research Asia, Beijing
Yong Yu, The Chinese University of Hong Kong, Hong Kong
Xiaoou Tang, Shanghai Jiao Tong University, Shanghai
In this work, we address the problem of performing class-specific unsupervised object segmentation, i.e., automatic segmentation without annotated training images. Object segmentation can be regarded as a special data clustering problem where both class-specific information and local texture/color similarities have to be considered. To this end, we propose a hybrid graph model (HGM) that can make effective use of both symmetric and asymmetric relationship among samples. The vertices of a hybrid graph represent the samples and are connected by directed edges and/or undirected ones, which represent the asymmetric and/or symmetric relationship between them, respectively. When applied to object segmentation, vertices are superpixels, the asymmetric relationship is the conditional dependence of occurrence, and the symmetric relationship is the color/texture similarity. By combining the Markov chain formed by the directed subgraph and the minimal cut of the undirected subgraph, the object boundaries can be determined for each image. Using the HGM, we can conveniently achieve simultaneous segmentation and recognition by integrating both top-down and bottom-up information into a unified process. Experiments on 42 object classes (9,415 images in total) show promising results.

[1] G. Liu, Z. Lin, X. Tang, and Y. Yu, "A Hybrid Graph Model for Unsupervised Object Segmentation," Proc. 11th IEEE Int'l Conf. Computer Vision, pp. 1-8, 2007.
[2] E. Sharon, A. Brandt, and R. Basri, "Segmentation and Boundary Detection Using Multiscale Intensity Measurements," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 469-476, 2001.
[3] M. Galun, E. Sharon, R. Basri, and A. Brandt, "Texture Segmentation by Multiscale Aggregation of Filter Responses and Shape Elements," Proc. IEEE Int'l Conf. Computer Vision, pp. 716-723, 2003.
[4] E. Sharon, M. Galun, D. Sharon, R. Basri, and A. Brandt, "Hierarchy and Adaptivity in Segmenting Visual Scenes," Nature, vol. 442, no. 7104, pp. 810-813, June 2006.
[5] J. Shi and J. Malik, "Normalized Cuts and Image Segmentation," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 8, pp. 888-905, Aug. 2000.
[6] Y. Ma, H. Derksen, W. Hong, and J. Wright, "Segmentation of Multivariate Mixed Data via Lossy Data Coding and Compression," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 29, no. 9, pp. 1546-1562, Sept. 2007.
[7] B. Leibe, A. Leonardis, and B. Schiele, "Combined Object Categorization and Segmentation with an Implicit Shape Model," Proc. Workshop Sixth European Conf. Computer Vision, pp. 17-32, 2004.
[8] S. Agarwal and D. Roth, "Learning a Sparse Representation for Object Detection," Proc. Seventh European Conf. Computer Vision, pp. 113-130, 2002.
[9] Z. Tu, X. Chen, A.L. Yuille, and S.C. Zhu, "Image Parsing: Unifying Segmentation, Detection, and Recognition," Proc. Toward Category-Level Object Recognition, pp. 545-576, 2006.
[10] S.X. Yu and J. Shi, "Object-Specific Figure-Ground Segregation," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 39-45, 2003.
[11] T.F. Cootes, C.J. Taylor, D.H. Cooper, and J. Graham, "Active Shape Models, Their Training and Application," Computer Vision and Image Understanding, vol. 61, no. 1, pp. 38-59, 1995.
[12] H.E.A.E. Munim and A.A. Farag, "A Shape-Based Segmentation Approach: An Improved Technique Using Level Sets," Proc. 10th IEEE Int'l Conf. Computer Vision, pp. 930-935, 2005.
[13] A.L. Yuille, P.W. Hallinan, and D.S. Cohen, "Feature Extraction from Faces Using Deformable Templates," Int'l J. Computer Vision, vol. 8, no. 2, pp. 99-111, 1992.
[14] L. Zhao and L.S. Davis, "Closely Coupled Object Detection and Segmentation," Proc. 10th IEEE Int'l Conf. Computer Vision, pp. 454-461, 2005.
[15] S.X. Yu, R. Gross, and J. Shi, "Concurrent Object Recognition and Segmentation by Graph Partitioning," Proc. Neural Information Processing Systems, pp. 1383-1390, 2002.
[16] E. Borenstein and S. Ullman, "Class-Specific, Top-Down Segmentation," Proc. Seventh European Conf. Computer Vision, pp. 109-124, 2002.
[17] T. Cour and J. Shi, "Recognizing Objects by Piecing Together the Segmentation Puzzle," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1-8, 2007.
[18] E. Borenstein and S. Ullman, "Learning to Segment," Proc. Eighth European Conf. Computer Vision, pp. 315-328, 2004.
[19] J.M. Winn and N. Jojic, "Locus: Learning Object Classes with Unsupervised Segmentation," Proc. 10th IEEE Int'l Conf. Computer Vision, pp. 756-763, 2005.
[20] C. Rother, T. Minka, A. Blake, and V. Kolmogorov, "Cosegmentation of Image Pairs by Histogram Matching—Incorporating a Global Constraint into MRFs," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 993-1000, 2006.
[21] B.C. Russell, W.T. Freeman, A.A. Efros, J. Sivic, and A. Zisserman, "Using Multiple Segmentations to Discover Objects and Their Extent in Image Collections," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 1605-1614, 2006.
[22] A. Levin and Y. Weiss, "Learning to Combine Bottom-Up and Top-Down Segmentation," Proc. Ninth European Conf. Computer Vision, pp. 581-594, 2006.
[23] C. Harris and M. Stephens, "A Combined Corner and Edge Detection," Proc. Fourth Alvey Vision Conf., pp. 147-151, 1988.
[24] G. Mori, "Guiding Model Search Using Segmentation," Proc. 10th IEEE Int'l Conf. Computer Vision, pp. 1417-1423, 2005.
[25] L. Cao and L. Fei-Fei, "Spatially Coherent Latent Topic Model for Concurrent Segmentation and Classification of Objects and Scenes," Proc. 11th IEEE Int'l Conf. Computer Vision, pp. 1-8, 2007.
[26] M. Belkin, P. Niyogi, and V. Sindhwani, "Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples," J. Machine Learning Research, vol. 7, pp. 2399-2434, 2006.
[27] S. Brin and L. Page, "The Anatomy of a Large-Scale Hypertextual Web Search Engine," Computer Networks and ISDN Systems, pp. 107-117, 1998.
[28] D. Zhou, J. Huang, and B. Schölkopf, "Learning from Labeled and Unlabeled Data on a Directed Graph," Proc. 22nd Int'l Conf. Machine Learning, pp. 1036-1043, 2005.
[29] M. Meila and J. Shi, "Learning Segmentation by Random Walks," Proc. Neural Information Processing Systems, pp. 873-879, 2000.
[30] T. Cour, N. Gogin, and J. Shi, "Learning Spectral Graph Segmentation," Proc. 10th Int'l Workshop Artificial Intelligence and Statistics, 2005.
[31] E. Borenstein, E. Sharon, and S. Ullman, "Combining Top-Down and Bottom-Up Segmentation," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2004.
[32] J. Puzicha, T. Hofmann, and J.M. Buhmann, "Non-Parametric Similarity Measures for Unsupervised Texture Segmentation and Image Retrieval," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 267-272, 1997.
[33] R. Fergus, P. Perona, and A. Zisserman, "A Sparse Object Category Model for Efficient Learning and Exhaustive Recognition," Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 380-387, 2005.
[34] "Corel Photo Library," Corel Corp., 2006.
[35] L. Fei-Fei, R. Fergus, and P. Perona, "Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2004.
[36] J.B. MacQueen, "Some Methods for Classification and Analysis of Multivariate Observations," Proc. Fifth Berkeley Symp. Math. Statistics and Probability, pp. 281-297, 1967.
[37] J.C. Dunn, "A Fuzzy Relative of the Isodata Process and Its Use in Detecting Compact Well-Separated Clusters," J. Cybernetics, vol. 3, pp. 32-57, 1973.
[38] A.Y. Ng, M.I. Jordan, and Y. Weiss, "On Spectral Clustering: Analysis and an Algorithm." Proc. Neural Information Processing Systems, pp. 849-856, 2001.
[39] M. Szummer and T. Jaakkola, "Partially Labeled Classification with Markov Random Walks," Proc. Neural Information Processing Systems, pp. 945-952, 2001.
[40] N. Tishby and N. Slonim, "Data Clustering by Markovian Relaxation and the Information Bottleneck Method," Proc. Neural Information Processing Systems, pp. 640-646, 2000.
[41] G.H. Golub and C.F.V. Loan, Matrix Computations, second ed. Johns Hopkins Press, 1989.
[42] J. Shotton, J.M. Winn, C. Rother, and A. Criminisi, "TextonBoost: Joint Appearance, Shape and Context Modeling for Multi-Class Object Recognition and Segmentation," Proc. Sixth European Conf. Computer Vision, pp. 1-15, 2006.

Index Terms:
Segmentation, graph-theoretic methods, spectral clustering.
Citation:
Guangcan Liu, Zhouchen Lin, Yong Yu, Xiaoou Tang, "Unsupervised Object Segmentation with a Hybrid Graph Model (HGM)," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, no. 5, pp. 910-924, May 2010, doi:10.1109/TPAMI.2009.40
Usage of this product signifies your acceptance of the Terms of Use.