Abstract
It is argued that traditional pattern recognition methods are inadequate for the tasks confronting computer vision. In an effort to overcome their limitations, a new approach has been developed, in which the concept of pattern is replaced by the group-theoretical notions of representations and invariants. By applying these ideas to the symbolic representation of images, it is possible to derive some very general constraints on the effectiveness of symbolic descriptions from the structure of the image vector space and the transformations which act upon it. The theory is illustrated with some simple examples and then applied to a number of practical problems, including feature description, texture analysis and segmentation. The paper is concluded with a discussion of some generalisations and extensions.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Duda, R. O., Hart, P. E., Pattern Classification and Scene Analysis, New York, Wiley, 1973.
Marr, D., Vision, San Francisco, Freeman, 1982.
Barrow, H. G., Tenenbaum, J. M., Computational Vision, Proc. IEEE, 69, 5, 572–595, 1981.
Rumelhart, D. E., McClelland, J. L., Parallel Distributed Processing Vol. 1, Cambridge, M.I.T., 1986.
—, PDP Vol. 2, Cambridge, M.I.T., 1986.
Granlund, G. H., In Search of a General Picture Processing Operator, Comp. Graphics and Image Proc., 8, 155–173, 1978.
Knutsson, H., Filtering and Reconstruction in Image Processing, Linköping Univ., Ph.D. Thesis, 1982.
Wilson, R., Knutsson, H., Granlund, G. H., The Operational Definition of the Position of Line and Edge, Proc. 6th Int'l Conf. on Patt. Rec., 846–849, Munich, 1982.
Wilson, R., Granlund, G. H., The Uncertainty Principle in Image Processing, IEEE Trans. on Patt. Anal. and Machine Intell., PAMI-6, 758–767, 1984.
Spann, M., Wilson, R., A Quad-tree Approach to Image Segmentation that Combines Statistical and Spatial Information, Patt. Recog., 18, 257–269, 1985.
Wilson, R., Spann, M., The Finite Prolate Spheroidal Sequences and their Applications pt I, II. (Accepted for publication) IEEE Trans. on Patt. Anal. and Machine Intell., 1987.
Wilson, R., Spann, M., Image Segmentation and Uncertainty, Chichester, Research Studies Pr., 1988.
Wilson, R., Knutsson, H., Uncertainty and Inference in the Visual System, (Accepted for publication) IEEE Trans. on Sys. Man and Cybern., 1987.
Weyl, H., The Theory of Groups and Quantum Mechanics, New York, Dover, 1950.
Frei, W., Chen, C. C., Fast Boundary Detection: A Generalisation and a New Algorithm, IEEE Trans. Comp., C-26, 988–998, 1977.
Gabor, D., Theory of Communication, Proc. IEE, 93, 26, 429–441, 1946.
Canny, J., A Computational Approach to Edge Detection, IEEE Trans. Patt. Anal. and Machine Intell., PAMI-8, 679–698, 1986.
Nering, E. D., Linear Algebra and Matrix Theory (2nd Ed.), New York, Wiley, 1970.
Wilson, R., Knutsson, H., Uncertainty and Inference in the Visual System II: Motion and Stereopsis without Matching, To be published.
Adelson, E. H., Bergen, J. R., Spatiotemporal Energy Models for the Perception of Motion, J. Opt. Soc. Am. A, 2, 284–299, 1985.
Watson, A. B., Ahumada, A. J., Model of Human Visual-Motion Sensing, J. Opt. Soc. Am. A, 2, 322–342, 1985.
Knutsson, H., A Tensor Representation of 3-d Structure, IEEE ASSP Soc. Workshop on Multidimensional S.P., Noordwijkerhout, Holland, 1987.
Granlund, G. H., Knutsson, H., Contrast of Structural and Homogeneous Representations, in Physical and Biological Processing of Images, ed. O. Braddick, Berlin, Springer-Verlag, 282–303, 1983.
Jauch, J. M., Foundations of Quantum Mechanics, Reading, Addison-Wesley, 1968.
Calway, A. D., Hierarchical Descriptors for Nonstationary 1 and 2-d Signal Processing, Warwick Univ. Comp. Sci. Rept. no. RR108, 1987.
Clippingdale, S., Wilson, R., Quad-tree Image Estimation: a New Image Model and its Application to Minimum Mean Square Error Image Restoration, Proc. 5th Scand. Conf. on Image Anal., 699–706, Stockholm, 1987.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1988 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wilson, R. (1988). Is vision a pattern recognition problem?. In: Kittler, J. (eds) Pattern Recognition. PAR 1988. Lecture Notes in Computer Science, vol 301. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-19036-8_1
Download citation
DOI: https://doi.org/10.1007/3-540-19036-8_1
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-19036-3
Online ISBN: 978-3-540-38947-7
eBook Packages: Springer Book Archive