Abstract
We describe an approach to object recognition in which the image-to-model match is based on stochastic optimization. During the recognition process, an internal model is matched with a novel object view. To compensate for changes in viewing conditions (such as illumination, viewing direction), the model is controlled by a number of parameters. The matching is obtained by seeking a setting of the parameters that minimizes the discrepancy between the image and the model. The search is performed in our examples in a six-dimensional space with multiple local minima. We developed an efficient minimization method based on the stochastic optimization approach (Mockus 1989). The search is bi-directional (applied to both the model and the image) and avoids the difficult problem of establishing image-to-model correspondence. It proceeds by evolving a population of candidate solutions using simple generation rules, based on the autocorrelation of the search space. We describe the method, its application to objects in several domains (cars, faces, printed symbols), and experimental comparisons with alternative methods, such as simulated annealing.
Preview
Unable to display preview. Download preview PDF.
References
Baird, H.S. 1985. Model-Based Image Matching Using Location. Cambridge, MA: MIT Press.
Beymer, D. & Poggio, T. 1996. Image Representations for Visual Learning. Science, 272, 5270, 1905–1909.
Biederman, I. & Ju, G. 1988. Surface versus Edge-Based Determinants of Visual Recognition. Cognitive Psychology, 20, 38–64.
Cass, T.A. 1992. Polynomial time object recognition in the presence of clutter, occlusion, and uncertainty. Proceedings of European Conference on Computer Vision, 834–842.
Canny, J. 1986. A computational approach to edge detection. IEEE PAMI, 8, 6:679–698.
De Champeaux, D., Sint, L. 1977. An Improved Bidirectional Heuristic Search Algorithm. J. of the Association for Computing Machinery, 24, 2, 177–191.
Fogel, D. B. 1994. An Introduction to Simulated Evolutionary Optimization. IEEE Transactions on Neural Networks, 5(1), 3–14.
Goldberg, D. E. 1994. Genetic and Evolutionary Algorithms Come of Age. Communications of the ACM. 37(3), 113–119.
Grimson, W.E.L. 1990. The combinatorics of heuristic search termination for object recognition in cluttered environments. Proceedings of the European Conference on Computer Vision, 552–556.
Hill, A., Taylor, C.J. & Cootes, T. 1992. Object Recognition by Flexible Template Matching using Genetic Algorithms. Proceedings of the European Conference on Computer Vision, 852–856.
Holland, J.H. 1975. Adaptation in Neural and Artificial Systems. Ann Arbor: University of Michigan Press.
Kirkpatrick, S., Gelatt, C.D. & Vecchi, M.P. 1983. Optimization by simulated annealing. Science, 220, 671.
Mockus, J. 1989. Bayesian Approach to Global Optimization. Boston: Kluwer Academic Publishers.
Marr, D. & Hildreth, E.C. 1980. Theory of edge detection. Proceedings of the Royal Society, London, B, 207, 187–217.
Poggio, T. 1990. 3D object recognition: on result by Basri and Ullman. Technical Report # 9005-03, IRST, Povo, Italy.
Pohl, I. 1971. Bi-Directional Search. Machine Intelligence. 6, 127–140.
Rosch, E. 1975. The nature of mental codes for color categories. Journal of Experimental Psychology: Human Perception and Performance, 1, 303–322.
Rosch, E., Mervis, C.B., Gray, W.D., Johnson, D.M. and Boyes-Bream, P., 1976. Basic objects in natural categories. Cognitive Psychology, 8, 382–439.
Shashua, A. 1995, Algebraic function for recognition. IEEE Transaction on Pattern Analysis and Machine Perception, 17(8), 779–789.
Ullman, S. and Basri, R. 1991. Recognition by linear combinations of models. IEEE PAMI, 13, 10:992–1006.
Yuille, A.L., Cohen, D.S. & Hallinan, P.W. 1989. Feature extraction from faces using deformable templates. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 104–109.
Yuille, A.L. & Hallinan, P.W. 1992. Deformable templates. In: A. Blake and A. Yuille (eds.), Active Vision, Cambridge: MIT Press.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ullman, S., Zeira, A. (1997). Object recognition using stochastic optimization. In: Pelillo, M., Hancock, E.R. (eds) Energy Minimization Methods in Computer Vision and Pattern Recognition. EMMCVPR 1997. Lecture Notes in Computer Science, vol 1223. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-62909-2_89
Download citation
DOI: https://doi.org/10.1007/3-540-62909-2_89
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-62909-2
Online ISBN: 978-3-540-69042-9
eBook Packages: Springer Book Archive