Abstract
Object recognition in digital images is a primary issue in robotics. We consider the model-based vision problem, where objects to be recognized come from a database of geometrically precise models. However, the modeling process involves uncertainties, and thus predicted collections of features will be subject to possible variations. Likewise, the image analysis problem using digital images must deal with sensor noise and ambiguity in the imaging process. Accordingly, object recognition is not a simple matter of matching features sets, but must deal with variabilities in the models and in the extracted features in the scenes. In this paper, we consider how these uncertainties should be handled. We describe how predicted variability can be used to compute a match metric, in order to assess the quality of possible models. We discuss two methods for dealing with extracted uncertainty. Finally, we speculate on other methods of assessing uncertainty in the recognition process.
Discussions with Davi Geiger and Martin Garcia-Keller are gratefully acknowledged. The author can be contacted at hummel@cs.nyu.edu.
Preview
Unable to display preview. Download preview PDF.
References
Hummel, R., Landy, M., A statistical viewpoint on the theory of evidence, IEEE Transactions on Pattern Analysis and Machine Intelligence, 1988, pp. 235–247.
Hummel, R., Manevitz, L., Combination Calculi for Uncertainty Reasoning: Representing Uncertainty Using Distributions, To appear in Annals of AI and Mathematics, 1996, available by anonymous ftp to cs.nyu.edu under pub/local/hummel/papers/uncertainty.ps.Z.
Ayache, N. and O. Faugeras, HYPER: A New Approach for the Recognition and Positioning of Two-dimensional Objects, IEEE Transactions on Pattern Analysis and Machine Intelligence 8(1), 1986, pp. 44–54.
Rigoutsos, I., R. Hummel, Massively parallel model matching: Geometric hashing on the Connection Machine, IEEE Computer 25(2), February, 1992, pp. 33–42.
Jyh-Jong Liu, A model-based 3-D object recognition system using geometric hashing with attributed features, Ph.D. thesis, October, 1995, available by anonymous ftp to cs.nyu.edu, under pub/theses/liu.tar.Z.
Rigoutsos and Hummel, A Bayesian approach to model matching with geometric hashing, Computer vision and image processing, Vol. 62(1), 1995, pp. 11–26.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hummel, R. (1996). Uncertainty reasoning in object recognition by image processing. In: Dorst, L., van Lambalgen, M., Voorbraak, F. (eds) Reasoning with Uncertainty in Robotics. RUR 1995. Lecture Notes in Computer Science, vol 1093. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0013956
Download citation
DOI: https://doi.org/10.1007/BFb0013956
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61376-3
Online ISBN: 978-3-540-68506-7
eBook Packages: Springer Book Archive