Abstract
The Distributed Associative Memory (DAM) has been described previously as a powerful method for pattern recognition. We show that it also can be used for preattentive and attentive vision. The basis for the preattentive system is that both the visual input features as well as the memory are arranged in a pyramid. This enables the system to provide fast preselection of regions of visual interest. The selected areas of interest are used in an attentive recognition stage, where the memory and the features work at full resolution. The reason for application of DAM is based on a statistical theory of rejection. The availability of a reject option in the DAM is the prerequisite for novelty detection and preattentive selection. We demonstrate the performance of the method on two diverse applications.
Wolfgang Pölzleitner has been supported by Joanneum Research. Harry Wechsler has been partly supported by DARPA under Contract #MDA972-91-C-004 and the C3I Center at George Mason University.
A long version of this paper is available from the first author as Joanneum Research technical report DIB-56.
Chapter PDF
Similar content being viewed by others
Keywords
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.
References
R. Bajcsy. Active Perception. IEEE Proceedings, 76(8):996–1005, August 1988.
P. J. Burt. Smart Sensing within a Pyramid Vision Machine. IEEE Proceedings, 76(8):1006–1015, August 1988.
V. Cherkassky. Linear Algebra Approach to Neural Associative Memories. To appear.
R. W. Conners and C. T. Ng. Developing a Quantitative Model of Human Preattentive Vision. IEEE Trans. Syst. Man Cybern., 19(6):1384–1407, November/December 1989.
T. Kohonen. Self-Organization and Associative Memory. Springer-Verlag, 2nd edition, 1988.
U. Neisser. Direct Perception and Recognition as Distinct Perceptual Systems. Cognitive Science Society Address, 1989.
P. Olivier. Optimal Noise Rejection in Linear Associative Memories. IEEE Trans. Syst Man Cybern., 18(5):814–815, 1988.
W. Pölzleitner and H. Wechsler. Invariant Pattern Recognition Using Associative Memory. Technical Report DIB-48, Joanneum Research, Institute for Image Processing and Computer Graphics, March 1990.
W. Pölzleitner and H. Wechsler. Selective and Focused Invariant Recognition Using Distributed Associative Memories (DAM). IEEE Trans. Pattern Anal Machine Intell., 11(8):809–814, August 1990.
W. Pölzleitner, G. Paar, and G. Schwingshakl. Natural Feature Tracking for Space Craft Guidance by Vision in the Descent and Landing Phases. In ESA Workshop on Computer Vision and Images Processing for Spaceborn Applications, Noordwijk, June 10–12, 1991.
M. Sandini and M. Tistarelli. Vision and Space-Variant Sensing. Volume 1, Academic Press, 1991.
P. A. Sandon. Simulating Visual Attention. Journal of Cognitive Neuroscience, 2(3):213–231, 1990.
B. Telfer and D. Casasent. Ho-Kashyap Optical Associative Processors. Applied Optics, 29:1191–1202, March 10, 1990.
J. K. Tsotsos. Analysing Vision at the Complexity Level. Technical Report RCBV-TR-78-20, Univ. Toronto, March 10, 1987.
L. Uhr. Parallel Computer Vision. Academic Press, 1987.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1992 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Polzleitner, W., Wechsler, H. (1992). Active perception using DAM and estimation techniques. In: Sandini, G. (eds) Computer Vision — ECCV'92. ECCV 1992. Lecture Notes in Computer Science, vol 588. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-55426-2_56
Download citation
DOI: https://doi.org/10.1007/3-540-55426-2_56
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-55426-4
Online ISBN: 978-3-540-47069-4
eBook Packages: Springer Book Archive