Abstract
We propose a new scheme in representing and memorizing an image for pattern matching, scene understanding, and image database retrieval. A pattern in a visual space is evaluated in terms of uniqueness that reflects how stable and distinguishable the pattern is in its matching and recognition process. Features are accessed in the images in two fashions that are similar to saccade and smooth search in human vision, which makes the matching process to any particular feature be controllable. A view is organized in a structure linking unique patterns to less unique ones. Our uniqueness of a pattern is measured from both attributes of the pattern and its spatial relationship with others in its visual context. Establishing correspondence between two close views using this representation is not only efficient in accessing image primitives, but also reliable compared with conventional matching approaches that are based on restricted geometry constraints. It will be effective in active vision, memory based recognition, qualitative description and reasoning of scenes.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Y. Ohta and T. Kanade, “Stereo by two-level dynamic programming” Proc. IJCAI-85, Vol. 2 pp. 1120–1126, 1985.
M. Yachida, M. Asada, and S. Tsuji, “Automatic analysis of moving images”, PAMI, Vol. 3, No.1, pp 12–19, 1981.
J.Y. Zheng and S. Tsuji, “Panoramic representation for route recognition by a mobile robot”, IJCV, Vol. 9, No.1, pp. 55–76, 1992.
J.Y. Zheng, M. Barth and S. Tsuji, “Qualitative route scene description using autonomous landmark detection”, Proc. 3rd-ICCV, pp. 558–562, 1990.
P. J. Burt, “Smart sensing within a pyramic vision machine”, IEEE Proceedings on Computer Vision, pp.1006–1015, 1988.
A. Witkin, “Scale-space filtering”, in IJCAI, Karlsruhe, pp.1019–1021. 1983.
P. Perona and J. Maliik, “Scale-space and edge detection using anisotropic diffusion”, IEEE Trans. on PAMI, Vol. 12, No.7, July 1990.
T. Lindeberg, and J. Eklundh, “Scale detection and region extraction from a scale-space primal sketch”, Proc. 3rd-ICCV, pp.416–426, 1990.
D.H. Ballard, “Reference frame for animate vision”, Proc. IJCAI-89, pp.1635–1641 (1989).
R. Bajcsy, “Active perception”, Proc. IEEE special issue on Computer Vision, August 1988. pp.996–1005.
N. Ahuja and M. Tuceryan, “Extraction of early perceptual structure in dot patterns: integrating region, boundary, and component Gestalt”, CVGIP 48, pp. 304–356, 1989.
A. Sha'ashua and S. Ullman, “Structural saliency: The detection of globally salient structures using a locally connected network”, Proc. 2nd-ICCV, pp.321–327, 1988.
G. Cohen, Memory in the Real World, Lawrence Erlbaum Associates, Hove. 1989.
J. Y. Zheng, Q. Chen and S. Tsuji, “Active camera guided manipulation”, 1991 IEEE Int. Conf. Robotics and Automation, Vol. 1, pp. 632–638, 1991.
J. Y. Zheng, M. Barth, and S. Tsuji, “Landmark detection for route recognitioni by a mobile robot”, 1991 IEEE Int. Conf. Robotics and Automation, Vol. 3, pp. 2004–2009, 1991.
B. Dubuc, and S. W. Zucker, “Indexing visual representations through the complexity map”, 5th ICCV, pp.142–149, 1995.
M. Jagersand ”Saliency maps and attention selection in scale coordinates: an information theoretic approach”, 5th ICCV, pp. 195–202, 1995.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zheng, JY. (1996). Constructing a visual memory in terms of uniqueness. In: Li, S.Z., Mital, D.P., Teoh, E.K., Wang, H. (eds) Recent Developments in Computer Vision. ACCV 1995. Lecture Notes in Computer Science, vol 1035. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-60793-5_82
Download citation
DOI: https://doi.org/10.1007/3-540-60793-5_82
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-60793-9
Online ISBN: 978-3-540-49448-5
eBook Packages: Springer Book Archive