Abstract
A novel proposal for a compositional model for object recognition is presented. The proposed method is based on visual grammars and Bayesian networks. An object is modeled as a hierarchy of features and spatial relationships. The grammar is learned automatically from examples. This representation is automatically transformed into a Bayesian network. Thus, recognition is based on probabilistic inference in the Bayesian network representation. Preliminary results in recognition of natural objects are presented. The main contribution of this work is a general methodology for building object recognition systems which combines the expressivity of a grammar with the robustness of probabilistic inference.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Chang, L., Jin, Y., Zhang, W., Borenstein, E., Geman, S.: Context, computation, and optimal roc performance in hierarchical models. IJCV 93(2), 117–140 (2011)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, vol. 1, pp. 886–893. IEEE Computer Society (2005)
Felzenszwalb, P.F.: Object detection grammars. In: ICCV Workshops, p. 691. IEEE (2011)
Ferrucci, F., Pacini, G., et al.: Symbol-relation grammars: a formalism for graphical languages. Inf. Comput. 131(1), 1–46 (1996)
Griffin, G., Holub, A., Perona, P.: Caltech-256 object category dataset. Technical Report 7694, California Institute of Technology (2007)
Leibe, B., Schiele, B.: Analyzing appearance and contour based methods for object categorization. In: CVPR, pp. 409–415. IEEE (2003)
Linde, O., Lindeberg, T.: Composed complex-cue histograms: An investigation of the information content in receptive field based image descriptors for object recognition. CVIU 116(4), 538–560 (2012)
Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, San Mateo (1988)
Ruiz, E., Sucar, L.E.: An object recognition model based on visual grammars and bayesian networks. In: Klette, R., Rivera, M., Satoh, S. (eds.) PSIVT 2013. LNCS, vol. 8333, pp. 349–359. Springer, Heidelberg (2014)
Zhu, S.C., Mumford, D.: A stochastic grammar of images. Foundations and Trends in Computer Graphics and Vision 2(4), 259–362 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Ruiz, E., Sucar, L.E. (2014). Recognizing Visual Categories with Symbol-Relational Grammars and Bayesian Networks. In: Bayro-Corrochano, E., Hancock, E. (eds) Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. CIARP 2014. Lecture Notes in Computer Science, vol 8827. Springer, Cham. https://doi.org/10.1007/978-3-319-12568-8_66
Download citation
DOI: https://doi.org/10.1007/978-3-319-12568-8_66
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-12567-1
Online ISBN: 978-3-319-12568-8
eBook Packages: Computer ScienceComputer Science (R0)