| | This Article | |
| |
| |
| | Share | |
| |
| |
| | Bibliographic References | |
| |
| |
| | Add to: | |
| |
 Digg
 Furl
 Spurl
 Blink
 Simpy
 Google
 Del.icio.us
 Y!MyWeb
| |
| | Search | |
| |
| |
| | |
Shape Understanding: Knowledge Generation and Learning
March 2004 (vol. 16 no. 3)
pp. 343-353
Abstract—In this paper, a method of knowledge generation as part of a shape-understanding method is presented. The proposed method of knowledge generation consists of: learning the description of new a posteriori classes, learning the concept of visual objects, and generation of the visual representation of "inner” objects. The visual concept, as part of the concept of the visual object, is expressed as a set of symbolic names that refers to possible classes of shape. The visual concept can be used to find the visual similarities between different visual objects, perform visual transformations as part of visual thinking capabilities of a system, and memorize a visual object as a symbolic representation. The knowledge obtained in the process of knowledge generation is integrated with an existing knowledge of a shape understanding system and used in the explanatory process. This system of shape understanding (SUS), that is, the implementation of the shape understanding method, is designed to imitate the visual thinking capabilities of the human visual system. The SUS consists of different types of experts that perform different processing and reasoning tasks and is designed to perform visual diagnosis in medical applications.
[1] Z. Les, Shape Understanding. Possible Classes of Shapes Int'l J. Shape Modeling, no. 7, vol. 1, pp. 75-109, 2001.
[2] Z. Les, Shape Understanding System: Understanding the Thin Object Int'l J. Computers and Graphics, vol. 26, no. 6, 2002.
[3] Z. Les and M. Les, Shape Understanding System: The Visual Reasoning Process Int'l J. Pattern Recognition and Artificial Intelligence, 2002.
[4] Z. Les and M. Les, Understanding as a New Paradigm in the Design of the Intelligent Systems in Automotive and Transportation Technology Proc. Automotive and Transportation Technology Int'l Conf. (ATT), 2001.
[5] Z. Les and M. Les, Shape Understanding System: Learning of the Visual Concepts Proc. Int'l Conf. Information Systems Analysis and Synthesis and World Multiconf. Systemics, Cybernetics and Informatics, 2001.
[6] Z. Les and M. Les, Visual Thinking as a Part of Understanding Process A New Way of Problem Solving and Communication of the Intelligent Systems in Automotive and Transportation Technology Proc. Automotive and Transportation Technology Int'l Conf. (ATT), 2002.
[7] K.C. You and K.S. Fu, Distorted Shape Recognition Using Attributed Grammars and Error-Correcting Techniques Computer Graphics and Image Processing, vol. 13, pp. 1-16, 1980.
[8] L.G. Shapiro, A Structural Model of Shape IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 2, pp. 111-126, 1980.
[9] U. Grenander, Y. Chow, and D.M. Keenan, Hands: A Pattern Theoretic Study of Biological Shapes. New York: Springer-Verlag, 1991.
[10] M. Kass, A. Witkin, and D. Terzopoulos, Snake: Active Contour Models Int'l J. Computer Vision, vol. 1, pp. 321-331, 1988.
[11] S. Loncaric, A Survey of Shape Analysis Techniques Pattern Recognition, vol. 31, no. 8, pp. 983-1001, 1998.
[12] T.H. Reiss, Recognizing Planar Objects Using Invariant Image Features. Berlin: Springer-Verlag, 1991.
[13] C. Zahn and R. Roskies, Fourier Descriptors for Plane Closed Curves Computer Graphics Image Process, vol. 21, pp. 195-201, 1972.
[14] M. Maes, Polygonal Shape Recognition Using String Matching Techniques Pattern Recognition, vol. 24, pp. 433-440, 1991.
[15] K. Roh and I. Kweon, 2D Object Recognition Using Invariant Contour Descriptor and Projective Refinement Pattern Recognition, vol. 31, no. 4, pp. 441-455, 1998.
[16] T. Pavlidis and F. Ali, A Hierarchical Syntactic Shape Analyzer IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 1, no. 1, pp. 2-9, 1977.
[17] J. Bala and H. Wechsler, Shape Analysis Using Hybrid Learning Pattern Recognition, vol. 29, no. 8, pp. 1323-1333, 1996.
[18] Y. He and A. Kundu, 2-D Shape Classification Using Hidden Markov Model IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 11, pp. 1172-1184, Nov. 1991.
[19] N.R. Pal, P. Pal, and A.K. Basu, A New Shape Representation Scheme and Its Application to Shape Discrimination Using a Neural Network Pattern Recognition, vol. 26, no. 4, pp. 543-551, 1993.
[20] R.T. Chin and C.R. Dyer, Model-Based Recognition in Robot Vision Computing Surveys, vol. 18, no. 1, pp. 67-108, 1986.
[21] A.R. Pope, Model-Based Object Recognition, a Survey of Recent Research Dept. Computer Science, The Univ. of British Columbia, 1994.
[22] W.E.L. Grimson, Object Recognition by Computer: The Role of Geometric Constraints. Boston: MIT Press, 1990.
[23] J. Segen, Learning Structural Description of Shape Proc. IEEE Int'l Conf. Computer Vision and Pattern Recognition, 1985.
[24] A.R. Pope and D.G. Lowe, "Learning Object Recognition Models From Images," ICCV, 1993, pp. 296-301.
[25] P. Pellegretti, F. Roli, S.B. Serplco, and G. Vernazza, Supervised Learning of Descriptions for Image Recognition Purposes IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, no. 1, pp. 92-98, 1994.
[26] J.C. Hsu and S.-Y. Hwang, A Machine Learning Approach for Acquiring Descriptive Classification Rules of Shape Contours Pattern Recognition, vol. 30, no. 2, pp. 245-252, 1997.
[27] B. Bhanu and T.A. Poggio, Introduction to the Special Section on Learning in Computer Vision IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, no. 9, pp. 865-868, Sept. 1994.
[28] A. Sowmya and E. Lee, Generating Symbolic Descriptions of Two-Dimensional Blocks World Proc. IAPR Int'l Workshop Machine Vision Applications, 1994.
[29] T.M. Mitchell, Machine Learning. New York: McGraw-Hill, 1997.
[30] J.R. Quinlan, Induction of Decision Trees Machine Learning, vol. 1, pp. 81-106, 1986.
[31] Parallel Distributed Processing: Explorations in the Microstructure of Cognition, J. McClelland and D. Rumelhart, eds. Bradford Books, 1986.
[32] W. Ziarko, Discovery through Rough Set Theory Comm ACM, vol. 42, no. 11, pp. 47-50, 1999.
[33] L. Fu, Knowledge Discovery Based on Neural Networks Comm. ACM, vol. 42, 11, pp. 47-50, 1999.
[34] I. Bratko and S. Mugletton, Application of Inductive Logic Programming Comm. ACM, vol. 38, no. 11, pp. 65-70, 1995.
[35] K.A. De Jong, Evolutionary Computation for Discovery Comm. ACM, vol. 42, no. 11, pp. 47-50, 1999.
[36] Z. Les and M. Les, System of Experts to Perform an Epistemological Task of Shape Understanding Proc. IASTED Int'l Conf. Software Eng., 2000.
[37] Z. Les, R. Tadeusiewicz, and M. Les, Shape Understanding: Knowledge Generation and Learning Proc. Seventh Australian and New Zealand Intelligent Information Systems Conf., 2001.
[38] Z. Les, The Processing Method as a Set of Image Transformations in Shape Understanding Int'l J. Computers and Graphics, vol. 25, pp. 223-233, 2001.
[39] Z. Les and R. Tadeusiewicz, Shape Understanding System. Concave Class Processing Methods Proc. Int'l Conf. Signal Processing and Comm., 2000.
[40] V.K. Govindan and A.P. Shivaprasad, Character Recognition A Review Pattern Recognition, vol. 23, no. 7, pp. 671-683, 1990.
[41] C.Y. Suen, “Computer Recognition of Unconstrained Handwritten Numerals,” Proc. IEEE, vol. 80, pp. 1,162-1,180, 1992.
[42] M. Revow, C.K.I. Williams, and G.E. Hinton, “Using Generative Models for Handwritten Digit Recognition,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, no. 6, pp. 592-606, June 1996.
[43] M. Pahlang and A. Sowmya, Learning Object Models from Real Images Proc. First Int'l Conf. Visual Systems, 1996.
[44] A. Ghosh and A.P. Shivaprasad, An Analytic Approach for Generation of Artificial Hand-Printed Character Database from Given Generative Model Pattern Recognition, vol. 32, pp. 907-920, 1999.
[45] Z. Les and M. Les, Shape Understanding System: Application of Fuzzy Sets, Neural Networks and Statistical Methods in the Process of Visual Thinking Proc. 10th IEEE Conf. Fuzzy Systems, 2001.
Index Terms:
Knowledge discovery, knowledge generation, shape understanding, shape classes, visual concept.
Citation:
Zbigniew Les, Magdalena Les, "Shape Understanding: Knowledge Generation and Learning," IEEE Transactions on Knowledge and Data Engineering, vol. 16, no. 3, pp. 343-353, Mar. 2004, doi:10.1109/TKDE.2003.1262188
