Recognition of geons by parametric deformable contour models
Conference paper
First Online:
Abstract
This paper presents a novel approach to the detection and recognition of qualitative parts like geons from real 2D intensity images. Previous works relied on semi-local properties of either line drawings or good region segmentation. Here, in the framework of Model-Based Optimisation, whole geons or substantial sub-parts are recognised by fitting parametric deformable contour models to the edge image by means of a Maximum A Posteriori estimation performed by Adaptive Simulated Annealing, accounting for image clutter and limited occlusions. A number of experiments, carried out both on synthetic and real edge images, are presented.
Keywords
Edge Image Qualitative Part Adaptive Simulated Annealing Occlude Contour Model Prior Probability
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.
Download
to read the full conference paper text
References
- 1.R. Bergevin. Primal access recognition of visual objects. Technical Report TR-CIM-90-5, Mc Gill University, Canada, February 1990.Google Scholar
- 2.I. Biederman. Recognition-by-components: A theory of human image understanding. Psychological Review, 94:115–147, 1987.Google Scholar
- 3.T.O. Binford. Visual perception by computer. In Proceedings of the IEEE System Science and Cybernetic Conference, Miami, December 1971.Google Scholar
- 4.S.J. Dickinson, A.P. Pentland, and A. Rosenfeld. 3-D Shape Recovery Using Distributed Aspect Matching. IEEE PAMI, 14(2):130–154, 1992.Google Scholar
- 5.D. Eggert, L. Stark, and K. Bowyer. Aspect graphs and their use in object recognition. Annals of Mathematics and Artificial Intelligence, 13:347–375, 1995.Google Scholar
- 6.P. Fua and A.J. Hanson. Objective functions for feature discrimination: Applications to semiautomated and automated feature extraction. In DARPA Image Understanding Workshop, pages 676–694, 1989.Google Scholar
- 7.J.E. Hummel and I. Biederman. Dynamic binding in a neural net model for shape recognition. Psychological Review, 99:480–517, 1992.Google Scholar
- 8.L. Ingber. Adaptive Simulated Annealing. Lester Ingber Research, Mc Lean, VA, 1993. [ftp.alumni.caltech.edu./pub/ingber/ASA.tar.zip].Google Scholar
- 9.J.R. Kender and D.G. Freudenstain. What is a “degenerate” view? In DARPA Image Understanding Workshops, pages 589–598, 1987.Google Scholar
- 10.S. Kirkpatrick, C.D. Gelatt, and M.P. Vecchi. Optimization by simulated annealing. Science, 220:671–680, 1983.Google Scholar
- 11.Y.G. Leclerc. Constructing simple stable description for image partitioning. International Journal of Computer Vision, 3:73–102, 1989.Google Scholar
- 12.D. Lowe. Fitting parametrized 3D models to images. PAMI, 13(5):441–450, May 1991.Google Scholar
- 13.D. Metaxas, S.J. Dickinson, R.C., Munck-Fairwood, and L. Du. Integration of quantitative and qualitative techniques for deformable model fitting from orthographic, perspective and stereo projection. In Fourth International Conference on Computer Vision, pages 364–371, 1993.Google Scholar
- 14.A.P. Pentland. Perceptual organization and the representation of natural form. Artificial Intelligence, 28:293–331, 1986.Google Scholar
- 15.N.S. Raja and A.K. Jain. Obtaining generic parts from range data using a multiview representation. In Appl. Artif. Intell. X: Machine Vision and Robotics, Proc. SPIE 1708, pages 602–613, Orlando, FL, April 1992.Google Scholar
- 16.F. Solina and R. Bajcsy. Recovery of parametric models from range images: The case of superquadrics with global deformations. IEEE PAMI, 12(2):131–147, February 1990.Google Scholar
- 17.K. Wu and M.D. Levine. Recovering of parametric geons from multiview range data. In IEEE Conference on Computer Vision and Pattern Recognition, Seattle, WA, 1994.Google Scholar
Copyright information
© Springer-Verlag Berlin Heidelberg 1996