Abstract
This paper examines the problem of shape based object recognition and proposes an approach to it based on certain characteristic planes of an object. It deals with a certain class of 3-D objects and their shapes. A shape distance for such objects is proposed on the basis of which shape discrimination between 3-D objects is possible. Two objects have the same shape if and only if one is a translation, dilation and rotation of the other. Thus, for shape matching, an object has to be normalized in terms of its position, size and orientation. Normalization of an object in terms of its position and size can easily be achieved. The main problem in shape matching involves normalization of orientation of an object. Here this problem is solved by using certain characteristic planes of an object. Thus, in order to compare shapes of two 3-D objects, first their position and volume are normalized. Then after normalizing their 3-dimensional orientation using the characteristic planes, they are superimposed on each other. The resulting volume of mismatch is taken to be a shape distance between the two objects. In the analog domain, this shape distance satisfies all the four metric properties.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Asada H and Brady M. The curvature primal sketch. IEEE PAMI, 8(1), pp.2–14, 1986.
Biderman I. Human image understanding: Recent research and a theory. Comp. Vision, Graphics and Image Processing, 32, pp.29–73, 1985.
Brooks R. Symbolic reasoning among 3-dimensional models and 2-dimensional images. Art. Int., 17, pp.285–349, 1981.
Chien CH and Aggarwal JK. Identification of 3-D objects from multiple silhouettes using quadtrees/octrees. Comp. Vision, Graphics and Image Processing, 36, pp.256–273, 1986.
Connel JH. Learning Shape descriptions: Generating and generalizing models of visual objects. MIT AI Tech. Report 853, 1985.
Gibson JJ. The Ecological Approach To Visual Perception. Boston, Houghton Mifflin, 1979.
Hoffman D. The interpretation of visual illusions. Scientific American, 249(6), pp.154–162, 1983.
Hoffman JJ and Richards W. Parts of recognition. In: A.P. Pentland(ed), From Pixels to Predicates, Norwood N.J.: Ablex Publishing Corp., 1986.
Marr D and Nishihara HK. Representation and recognition of three dimensional shapes. Proc. Roy. Soc. B., 200, pp.269–291, 1978.
Parui SK, Some Studies in Analysis and Recognition of 2-Dimensional Shapes. Ph.D. Thesis, Indian Statistical Institute, Calcutta, 1984.
Parui SK and Dutta Majumder D. How to quantify shape distance for 2-dimensional regions. Proc. 7th Int. Conf. on Pattern Recognition, Montreal, pp.72–74, 1984.
Parui SK and Banerjee DK. A shape distance for 3-D objects. Tech. Report, ECSU, ISI, 1987.
Parui SK and Banerjee DK. Some operations on 3-D binary images for shape matching. Proc. IEEE Int. Conf. on Systems, Man and Cybernetics, Shenyang and Beijing, 1988.
Srihari SN. Representation of 3-D digital images. ACM Comp. Surveys, 13, pp.399–424, 1981.
Ullman S. Visual routines. Cognition, 18, pp.97–159, 1984.
Ullman S. An approach to object recognition: Aligning pictorial descriptions. MIT AI Memo No.931, 1986.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1990 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Banerjee, D., Parui, S., Majumder, D.D. (1990). Shape based object recognition. In: Ramani, S., Chandrasekar, R., Anjaneyulu, K.S.R. (eds) Knowledge Based Computer Systems. KBCS 1989. Lecture Notes in Computer Science, vol 444. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0018394
Download citation
DOI: https://doi.org/10.1007/BFb0018394
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-52850-0
Online ISBN: 978-3-540-47168-4
eBook Packages: Springer Book Archive