Abstract
We propose a compositionality architecture for perceptual organization which establishes a novel, generic, algorithmic framework for feature binding and condensation of semanticemm information in images. The underlying algorithmic ideas require a hierarchical structure for various types of objects and their groupings, which are guided by gestalt laws from psychology. A rich set of predefined feature detectors with uncertainty that perform real-valued measurements of relationships between objects can be combined in this flexible Bayesian framework. Compositions are inferred by minimizing the negative posterior grouping probability. The model structure is founded on the fundamental perceptual law of Prägnanz. The grouping algorithm performs hierarchical agglomerative clustering and it is rendered computationally feasible by visual pop-out. Evaluation on the edgel grouping task confirms the robustness of the architecture and its applicability to grouping in various visual scenarios.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Amir, A., Lindenbaum, M.: A generic grouping algorithm and its quantitative analysis. IEEE Trans. Pattern Anal. Machine Intell. 20(2), 186–192 (1998)
Attneave, F.: Some informational aspects of visual perception. Psychological Review 61(3), 183–193 (1954)
Biederman, I.: Recognition-by-components: A theory of human image understanding. Psychological Review 94(2), 115–147 (1987)
Bienenstock, E.: Notes on the growth of a composition machine. In: Proceedings of the Royaumont Interdisciplinary Workshop on Compositionality in Cognition and Neural Networks (1991)
Bruce, V., Green, P.R., Georgeson, M.A.: Visual Perception: Physiology, Psychology, and Ecology, 3rd edn. Psychology Press, San Diego (1996)
Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn. John Wiley & Sons, New York (2001)
Geman, S., Potter, D.F., Chi, Z.: Composition Systems. Technical report, Division of Applied Mathematics, Brown University, Providence, RI (1998)
Goldstein, E.B.: Sensation and Perception, 3rd edn. Wadsworth, Belmont (1989)
Jacobs, D.W.: Grouping for recognition. In: MIT AI Lab Memo 1177. MIT, Cambridge (1989)
Li, Z.: A V1 model of pop out and asymmetry in visual search. Advances in Neural Information Processing Systems 11 (1999)
Lowe, D.G.: Perceptual Organization and Visual Recognition. Kluwer Academic Publishers, Norwell (1985)
Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: ICCV-WS 1999, vol. 8 ( July 2001)
Ommer, B.: An algorithmic framework for visual grouping by perceptual organization. Diploma thesis, Rheinische Friedrich-Wilhelms-Universität Bonn (2003)
Shashua, A., Ullman, S.: Structural saliency: The detection of globally salient structures using a locally connected network. In: ICCV (1988)
Tagare, H.D., Toyama, K., Wang, J.G.: A maximumlikelihood strategy for directing attention during visual search. IEEE Trans. Pattern Anal. Machine Intell. 23(5), 490–500 (2001)
Treisman, A.: Features and objects in visual processing. Scientific American 254(11), 114–125 (1986)
Williams, L.R., Thornber, K.K.: A comparison of measures for detecting natural shapes in cluttered backgrounds. J. Computer Vision 34, 81–96 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ommer, B., Buhmann, J.M. (2003). A Compositionality Architecture for Perceptual Feature Grouping. In: Rangarajan, A., Figueiredo, M., Zerubia, J. (eds) Energy Minimization Methods in Computer Vision and Pattern Recognition. EMMCVPR 2003. Lecture Notes in Computer Science, vol 2683. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45063-4_18
Download citation
DOI: https://doi.org/10.1007/978-3-540-45063-4_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40498-9
Online ISBN: 978-3-540-45063-4
eBook Packages: Springer Book Archive