This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Selective Feature-to-Feature Adhesion for Recognition of Cursive Handprinted Characters
February 1999 (vol. 21 no. 2)
pp. 184-191

Abstract—A structural-feature-to-structural-feature configuration is naturally constructed using a set of sampled features from a cursive pattern. These features are sampled by maximally fitting bended ellipses in local strokes. This configuration is transformed into an undirected graph to resolve the asymmetric difficulty. The compatibility associated with the graph is further formulated into a devised Hopfield network, where both interfeature and interlink similarities are incorporated into the compatibility. We operate this network to recognize a radical as a whole in a handprinted pattern to accomplish the selective attention task.

[1] J. Rocha and T. Pavlidis, "A Shape Analysis Model With Applications to a Character Recognition System," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, pp. 393-404, 1994.
[2] J. Rocha and T. Pavlidis, "Character Recognition Without Segmentation" IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 17, pp. 903-909, 1995.
[3] S. W.Lu, Y. Ren, and C.Y. Suen, "Hierarchical Attributed Graph Representation And Recognition Of Handwritten Chinese Characters," Pattern Recognition, vol. 24, pp. 617-632, 1991.
[4] R. Fukushima and T. Imagawa, "Recognition And Segmentation of Connected Characters With Selective Attention," Neural Networks, vol. 6, pp. 33-41, 1993.
[5] H.C. Yang and C.Y. Liou, "Self-Organization of High-Order Receptive Fields for Handprinted Character Recognition," Proc. Int'l Conf. Artificial Neural Networks, pp. 245-250,Paris, France, 1995.
[6] A. Dobbins, S.W. Zucker, and M.S. Cynader, "Endstopped Neurons In The Visual Cortex As A Substrate For Calculating Curvature," Nature, vol. 329, pp. 438-441, 1987.
[7] G. Gaál, "Population Coding By Simultaneous Activities of Neurons in Intrinsic Coordinate Systems Defined by Their Receptive Field Weighting Functions," Neural Networks, vol. 6, pp. 499-515, 1993.
[8] T. Kohonen, "Self-Organization and Associated Memory," Berlin Heidelberg. New York: Springer-Verlag, 1988.
[9] C.Y. Liou and H.C. Yang, “Handprinted Character Recognition Based on Spatial Topology Distance Measurement,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, no. 9, pp. 941-944, Sept. 1996.
[10] J. Basak, S. Chaudhury, S.K. Pal, and D.D. Majumder, "Matching of Structural Shape Descriptions With Hopfield Net," Int'l J. Pattern Recognition and Artificial Intelligence, vol. 7, pp. 377-404, 1993.
[11] A. Moscona and H. Moscona, "Dissociation and Aggregation of Cells From Organ Rudiments of the Early Chick Embryos," J. Anatomy, vol. 86, pp. 287-301, 1952.
[12] P.L. Townes and J. Holtfreter, "Directed Movements and Selective Adhesion of Embryonic Amphibian Cells," J. Experimental Zoology, vol. 128, pp. 53-120, 1955.
[13] S. Mori, K. Yamamoto, and M. Yasuda, "Research on Machine Recognition of Handprinted Characters," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 6, pp. 386-405, 1984.
[14] J.J. Hopfield and D.W. Tank, "Neural Computation of Decisions in Optimization Problems," Biological Cybernetics, vol. 52, pp. 141-152, 1985.
[15] N.M. Nasrabadi and W. Li, "Object Recognition by a Hopfield Neural Network," IEEE Trans. Systems, Man, and Cybernetics, vol. 21, pp. 1,523-1,535, 1991.
[16] W.C. Lin, F.Y. Liao, C.K. Tsao, and T. Lingutla, "A Hierarchical Multiple-View Approach to Three-Dimensional Object Recognition," IEEE Trans. Neural Networks, vol. 2, pp. 84-92, 1991.
[17] P. Kuner and B. Ueberreiter, "Pattern Recognition by Graph Matching-Combinatorial Versus Continuous Optimization," Int'l J. Pattern Recognition and Artificial Intelligence, vol. 2, pp. 527-542, 1988.
[18] P.N. Suganthan, E.K. Teoh, and D.P. Mital, "Pattern Recognition by Homomorphic Graph Matching Using Hopfield Neural Networks," Image and Vision Computing, vol. 13, pp. 45-60, 1995.
[19] H. Szu, "Fast TSP Algorithm Based on Binary Neuron Output and Analog Neuron Input Using The Zero-Diagonal Interconnect Matrix and Necessary and Sufficient Constraints of the Permutation Matrix," Proc. IEEE Int'l Conf. Neural Networks, vol. 2, pp. 259-266,San Diego, Calif., 1988.
[20] S.V.B. Aiyer, M. Niranjan, and F. Fallside, "A Theoretical Investigation Into the Performance of the Hopfield Model," IEEE Trans. Neural Networks, vol. 1, pp. 204-215, 1990.
[21] D.E. Rumelhart, G.E. Hinton, and R.J. Williams, Parallel Distributed Processing: Explorations in the Microstructure of Cognition, pp. 318-362.Cambridge, Mass.: MIT Press, 1986.
[22] C.Y. Liou and W.J. Yu, "Ambiguous Binary Representation in Multilayer Neural Networks," Proc. IEEE Int'l Conf. Neural Networks,Perth, Australia, vol. 1, pp. 379-384, 1995.
[23] G.E. Hinton, C.K.I. Williams, and M.D. Revow, "Adaptive Elastic Models for Hand-Printed Character Recognition," Advances in Neural Information Processing Systems, vol. 4, pp. 512-522. Parallel Distributed Processing: Explorations in the Microstructure of Cognition, pp. 318-362. Cambridge, Mass.: MIT Press, 1992.

Index Terms:
Handprinted character recognition, topological order, receptive field, Hopfield network, subgraph matching, signature recognition, cell-cell adhesion, selective attention.
Citation:
Cheng-Yuan Liou, Hsin-Chang Yang, "Selective Feature-to-Feature Adhesion for Recognition of Cursive Handprinted Characters," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 21, no. 2, pp. 184-191, Feb. 1999, doi:10.1109/34.748829
Usage of this product signifies your acceptance of the Terms of Use.