Abstract
Object representation is a fundamental issue in computer vision. While an image is, after capture an unstructured array of individual pixels, the vision process will try to give significance to this set. This requires to extract information from the pixels, and, in most situations where the image represents a real world scene, to group neighboring pixels into higher level features (contour, regions) according to some criterions. If the segmentation process was efficient enough, these connected regions will more or less closely correspond to objects, or parts of objects of the scene, and it will be possible to apply some recognition methods to match them against some object models.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Henk J. A. M. Heijmans. Connected morphological operators for binary images. Computer Vision and Image Understanding: CVIU, 73(1):99–120, 1999. URL citeseer.nj.nee.com/14301.html.
D. H. Hubel. Eye, brain and the computer. Scientific american books, New-York, 1998.
D. Marr. Vision: A Computational Investigation into the Human Processing and Representation of Information. W. H. Freeman and Co., San Francisco, 1982.
L. Uhr. Layered ‘recognition cones’ networks that preprocess, classify, and describe. IEEE Trans. Computers, C-21(7):758–768, 1972.
V. Cantoni and M. Ferretti. Pyramidal architectures for computer vision. Advances in computer vision and machine intelligence. Plenum Press, 1994.
A. Mérigot, P. Clermont, J. Méhat, F. Devos, and B. Zavidovique. A pyramidal system for image processing. In Virginio Cantoni and Stefano Levialdi, editors, Pyramidal Systems for Image Processing and Computer Vision, NATO ASI Series, pages 109–124. Springer Verlag, 1986.
V. Cantoni and S. Levialdi. PAPIA: a case history. In L. Uhr, editor, Parallel Computer Vision, pages 3–13. Academic Press, 1987.
A. L. Yuile and T. A. Poggio. Scaling theorems for zero crossings. IEEE Trans. Pattern Anal. Machine Intell., PAMI-8(2): 15–25, 1986.
P. J. Burt and E. H. Anderson. The Laplacian pyramid as a compact image code. IEEE Trans. Comm., COM-31:532–540, april 1983.
D. Marr and E. C. Hildreth. Theory of edge detection. Proc. Roy. Soc. London, B-207:187–217, 1980.
I. Daubechies. Orthonormal bases of compactly supported wavelets. Comm. Pure Appl. Math, XLL:909–996, 1988.
S. Mallat. A theory for multidimensional signal decomposition: The wavelet representation. IEEE Trans. Pattern Anal. Machine Intell., PAMI-11:674–693, june 1989.
H. Samet. The quadtree and related hierachical data structures. Computing surveys, 16(2):187–260, 984.
E. G. Hoel and H. Samet. Data-parallel primitives for spatial operations using PM quadtrees. In Cantoni et al.36, pages 266–273.
P. Meer. Stochastic image pyramids. CVGIP, 45:269–294, 1989.
J. M. Jolion and A. Montanvert. The adaptative pyramid: a framework for 2D image analysis. CVGIP, 55(3) :339–348, 1992.
A. Rosenfeld, editor.Multiresolution image processing and analysis. Springer Verlag, 1984.
C. R. Dyer. Multiscale image understanding. In L. Uhr, editor, Parallel Computer Vision, pages 171–213. Academic Press, New York, 1987.
Jean-Michel Jolion and Azriel Rosenfeld. A Pyramid Framework for Early Vision. Kluwer, 1994.
W. Hackbusch. Multigrid methods and applications. Springer-Verlag, 1985.
D. Terzopoulos. Multilevel computational processes for visual surface reconstruction. CVGIP, 24:52–96, 1983.
D. Terzopoulos. Image analysis using multigrid relaxation techniques. IEEE Trans. Pattern. Anal. and Mach. Intell.,PAMI-8(2): 129–139, 1986.
F. Glazer. Multilevel relaxation in low-level image processing. In Rosenfeld17, pages 312–330.
S. Tanimoto. Template matching in pyramids. CVGIP, 16:356–369, 1981.
J. M. Jolion and A. Rosenfeld. An o(log n) pyramid hough transform. Pattern Recognit Lett., 9:343–349, 1989.
G. Bongiovanni, C. Guerra, and S. Levialdi. Computing the hough transform on a pyramid architecture.Machine Vision Appl., 3(2):57–77, 1990.
P. J. Burt, T. H. Hong, and A. Rosenfeld. Segmentation and estimation of image region properties through cooperative hierarchical computation. IEEE Trans. on Systems, Man and Cybernetics, 11(12), December 1981.
T. Hong and A. Rosenfeld. Compact region extraction using wieghted pixel linking in a pyramid. IEEE Trans. Patter Anal. and Mach. Intell., PAMI-6(2):222–229, 1984.
M. Spann. Figure/ground separatio n nusing stochastic pyramid linking. Pattern Recognition, 24(10):993–1002, 1991.
N. Sicard, B. Ducourthial, and A. Mérigot. Parallel image analysis with anet, a graph-based programming environment. In C. Guerra, editor, Computer architecture for machine perception, Padova, Italy, September 2000. IEEE.
D. Dulac, S. Mohammadi, and A. Mérigot. Implementation and evaluation of a parallel architecture using asynchronous communications. In Cantoni et al.36, pages 106–111.
B. Ducourthial.Les réseaux associatifs : un modèle de programmation à parallélisme de données, pour algorithmes et données irréguliers, à primitives de calcul asynchrones. These de doctorat, Université Paris sud, jan. 1999.
Guy E. Blelloch. Vector Models for Data-Parallel Computing. MIT Press, Cambridge, MA, USA, 1990.
Alain Mérigot. Associative nets: A graph-based parallel computing model. IEEE Transactions on Computers46(5):558–571, 1997.
B. Ducourthial and A. Mérigot. Graph embedding in the associative mesh model. Technical Report 96-002, Institut d’Electronique Fondamentale, Bât. 220. Université Paris Sud, 91405 Orsay, France, 1996.
V. Cantoni, L. Lombardi, M. Mosconi, M. Savini, and A. Setti, editors. Pavia, Italia, September 1995. IEEE Press.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer Science+Business Media New York
About this chapter
Cite this chapter
Mérigot, A. (2002). Multiresolution and Associative Representation of Objects. In: Cantoni, V., Marinaro, M., Petrosino, A. (eds) Visual Attention Mechanisms. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-0111-4_23
Download citation
DOI: https://doi.org/10.1007/978-1-4615-0111-4_23
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-4928-0
Online ISBN: 978-1-4615-0111-4
eBook Packages: Springer Book Archive