Abstract
In this paper, we present a framework for object categorization via sketch graphs, structures that incorporate shape and structure information. In this framework, we integrate the learnable And-Or graph model, a hierarchical structure that combines the reconfigurability of a stochastic context free grammar(SCFG) with the constraints of a Markov random field(MRF), and we sample object configurations as training templates from this generative model. Based on these synthesized templates, four steps of discriminative approaches are adopted for cascaded pruning, while a template matching method is developed for top-down verification. These synthesized templates are sampled from the whole configuration space following the maximum entropy constraints. In contrast to manually choosing data, they have a great ability to represent the variability of each object category. The generalizability and flexibility of our framework is illustrated on 20 categories of sketch-based objects under different scales.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Berg, A., Berg, T., Malik, J.: Shape Matching and Object Recognition using Low Distortion Correspondence. CVPR (2005)
Lowe, D.G.: Distinctive image features from scaleinvariant keypoints. IJCV 60(2), 91–110 (2004)
Estrada, F., Jepson, A.: Perceptual Grouping for Contour Extraction. ICPR (2004)
Han, F., Zhu, S.C.: Bottom-up/top-down image parsing by attribute graph grammar, ICCV 2 (2005)
Jurie, F., Triggs, B.: Creating Efficient Codebooks for Visual Recognition. ICCV (2005)
Csurka, G., Dance, C., Fan, L., Willamowski, J., Bray, C.: Visual Categorization with Bags of Keypoints. In: SLCV workshop in conjunction with ECCV (2004)
Dorko, G., Schmid, C.: Selection of Scale-Invariant Parts for Object Class Recognition. ICCV (2003)
Chen, H., Xu, Z., Liu, Z., Zhu, S.C.: Composite Templates for Cloth Modeling and Sketching. CVPR 1, 943–950 (2006)
Porway, J., Yao, Z., Zhu, S.C.: Learning an and-or graph for modeling and recognizing object categories. In: CVPR 2007, NO. 1892 (submitted, 2007)
Lin, L., Zhu, S.C., Wang, Y.: Layered Graph Match with Graph Editing. In: CVPR 2007, NO. 2755 (submitted, 2007)
Fischler, M., Elschlager, R.: The representation and matching of pictorial structures. IEEE Transactions on Computers 22(1), 67–92 (1973)
Weber, M., Welling, M., Perona, P.: Towards automatic discovery of object categories. CVPR (2000)
Felzenszwalb, P., Hut tenlocher, D.: Pictorial Structures for Object Recognition. IJCV 61(1), 55–79 (2005)
Viola, P., Jones, M.: Rapid Object Detection using a Boosted Cascade of Simple Features. CVPR (2001)
Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale- invariant learning. CVPR (2003)
Zhu, S.C., Yuille, A.L.: Forms: A flexible object recognition and modeling system. IJCV 20(3), 187–212 (1996)
Zhu, S.C., Mumford, D.: Quest for a Stochastic Grammar of Images, Foundations and Trends in Computer Graphics and Vision (to appear, 2007)
Ullman, S., Sali, E., Vidal-Naquet, M.: A Fragment-Based Approach to Object Representation and Classification. In: Proc. 4th Intl. Workshop on Visual Form, Capri, Italy (2001)
Nayar, S.K., Murase, H., Nene, S.A.: Parametric Appearance Representation. In: Nayar, S.K., Poggio, T. (eds.) Early Visual Learning (1996)
Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. PAMI 24(4), 509–522 (2002)
Ferrari, V., Tuytelaars, T., Van Gool, L.: Object Detection by Contour Segment Networks. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3954, Springer, Heidelberg (2006)
Tu, Z.W.: Probabilistic Boosting Tree: Learning Discriminative Models for Classification, Recognition, and Clustering, ICCV (2005)
Chi, Z., Geman, S.: Estimation of probabilistic context-free grammars, Computational Linguistics 24(2) (1998)
Yao, Z., Yang, X., Zhu, S.C.: An Integrated Image Annotation Tool and Large Scale Ground Truth Database. In: CVPR 2007, NO. 1407 (submitted, 2007)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Peng, S., Lin, L., Porway, J., Sang, N., Zhu, SC. (2007). Object Category Recognition Using Generative Template Boosting . In: Yuille, A.L., Zhu, SC., Cremers, D., Wang, Y. (eds) Energy Minimization Methods in Computer Vision and Pattern Recognition. EMMCVPR 2007. Lecture Notes in Computer Science, vol 4679. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74198-5_16
Download citation
DOI: https://doi.org/10.1007/978-3-540-74198-5_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74195-4
Online ISBN: 978-3-540-74198-5
eBook Packages: Computer ScienceComputer Science (R0)