Abstract
This paper presents a novel and effective Bayesian belief network that integrates object segmentation and recognition. The network consists of three latent variables that represent the local features, the recognition hypothesis, and the segmentation hypothesis. The probabilities are the result of approximate inference based on stochastic simulations with Gibbs sampling, and can be calculated for large databases of objects. Experimental results demonstrate that this framework outperforms a feed-forward recognition system that ignores the segmentation problem.
This is a preview of subscription content, log in via an institution to check access.
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
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60, 91–110 (2004)
Murphy-Chutorian, E., Triesch, J.: Shared features for scalable appearance-based object recognition. In: Proc. of IEEE Workshop on Applications of Computer Vision, Breckenridge, Colorado, USA (2005)
Torralba, A.B., Murphy, K.P., Freeman, W.T.: Sharing features: Efficient boosting procedures for multiclass object detection. Computer Vision and Pattern Recognition 2, 762–769 (2004)
Peterson, M.A.: Shape recognition can and does occur before figure-ground organization. Current Directions in Psychological Science 3, 105–111 (1994)
Leibe, B., Schiele, B.: Interleaved object categorization and segmentation. In: British Machine Vision Conference (2003)
Leibe, B., Leonardis, A., Schiele, B.: Combined object categorization and segmentation with an implicit shape model. In: ECCV 2004 Workshop on Statistical Learning in Computer Vision, Prague, Czech Republic, pp. 17–32 (2004)
Leibe, B., Seemann, E., Schiele, B.: Pedestrian detection in crowded scenes. In: Computer Vision and Pattern Recognition, pp. 878–885 (2005)
Tu, Z., Chen, X., Yuille, A., Zhu, S.C.: Image parsing: Segmentation, detection, and object recognition. In: International Conference on Computer Vision (2003)
Yu, S., Gross, R., Shi, J.: Concurrent object segmentation and recognition with graph partitioning. In: Proceedings of Neural Information Processing Systems (2002)
Murphy-Chutorian, E., Aboutalib, S., Triesch, J.: Analysis of a biologically-inspired system for real- time object recognition. Cognitive Science Online (accepted paper) (2005)
Martin, D., Fowlkes, C., Malik, J.: Learning to detect natural image boundaries using local brightness, color and texture cues. In: Pattern Recognition and Machine Intelligence, vol. 26, pp. 530–549 (2004)
Shi, J., Tomasi, C.: Good features to track. In: Proc. of IEEE Conf. on computer Vision and Pattern Recognition (1994)
Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active contour models. In: International Conference on Computer Vision, pp. 259–268 (1987)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chen, HJ., Lee, KC., Murphy-Chutorian, E., Triesch, J. (2005). Toward a Unified Probabilistic Framework for Object Recognition and Segmentation. In: Bebis, G., Boyle, R., Koracin, D., Parvin, B. (eds) Advances in Visual Computing. ISVC 2005. Lecture Notes in Computer Science, vol 3804. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11595755_14
Download citation
DOI: https://doi.org/10.1007/11595755_14
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-30750-1
Online ISBN: 978-3-540-32284-9
eBook Packages: Computer ScienceComputer Science (R0)