Abstract
In this paper, a revised SEJONG-NET with adaptability for recognizing transformed on-line Hangul pattern is proposed. It is based on the structural characteristics of Hangul and the hypotheses on the processes of human Hangul recognition. Unlike the existing SEJONG-NET, the proposed model extracts the information about the orientation and the curvature of strokes in the lower layers. In the higher layers, it represents the information on graphemes as conceptual graphs, and detects a particular grapheme using the conceptual graph. The conceptual graph is composed of two kinds of nodes, concept nodes and relation nodes. The concept node has the orientation and curvature information, and the relation node describes the positional relations between two concept nodes. Through the computer simulations, we showed that the adaptive SEJONG-NET could recognize the transformed Hangul patterns after training the basic grapheme patterns, and also that untrained or severely deformed patterns can be efficiently recognized by creating a new graph or adjusting the values of the existing conceptual graphs. Hence, SEJONG-NET with adaptability can be considered as an efficient model for recognizing Hangul patterns with transformation.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
J.Kim, “A Review of Psychological Studies of Korean Letters and Syllables” Proc. of Conference on Hangul and Korean Information Processing in Korea, pp.114–119, 1989.
J.Kim and J.Kim, “Syllabic Processing and Letter Perception in Korean Word Recognition,” Korean Journal of Experimental and Cognitive Psychology, Vol. 4, pp. 36–51, 1992.
K.Do, “The Combination of Korean Letters in the Perception of Hangul,” Korean Journal of Experimental and Cognitive Psychology, Vol. 4, pp. 1–15, 1992.
Y.Lee and A.-Y.Chung, “Sejong-Net: A Dynamic Visual Pattern Recognition Neural Net,” Proc. of Int. Joint Conference on Neural Networks 90 WASH. DC, Vol. 1, pp. 412–415, 1990
J.Cho, J.Kim, A.-Y.Chung and Y.Lee, “Sejong-Net: A Neural Net Model for Dynamic Character Recognition,” Proc. of Int. Conference on Fuzzy Logic and Neural Networks IIZUKA '90, Vol. 1, pp. 315–318, 1990.7
J.Kim and Y.Lee, “Handwritten English Alphabet Recognition using SEJONG-NET,” Proc. of 1990 Fall Conference of SIG-AI of Korean Information Science Society, pp.107–111, 1990 (in Korean)
S.Kim and Y.Lee, “On-line Recognition of Handwriting Chinese Character(Radical) using SEJONG-NET,” Proc. of 1991 Fall Conference of SIG-AI of KISS, pp.25–29, 1991 (in Korean)
S.Lee, K.Lee and Y.Lee, “A Generalized Character Recognition using SEJONG-NET,” Proc. of the 2nd Pacific Rim Int. Conference on Artificial Intelligence, Vol. 2, pp. 947–952, 1992
K.Lee and Y.Lee, “SEJONG-NET with Analysis-by-Synthesis,” Proc. of World Congress on Neural Networks-San Diego, Vol. 1, pp. 649–657, 1994
Audice G. Leventhal, The Neural Basis of Visual Function, Macmillan Press, 1991
Dobbins, Zucker, and Cynader, “Endstopped neurons in the visual cortex as a substrate for calculating curvature,” Nature, Vol. 329, No.1, pp. 438–441, 1987
John F.Sowa, CONCEPTUAL STRUCTURES: Information Processing in Mind and Machine, Addison-Wesley,1984
Kandel, Schwartz, and Jessell, PRINCIPLES OF NEURAL SCIENCE, Elsevier, 3rd Ed., 1991
Versavel, Orban, and Lagae, “Responses of Visual Cortical Neurons to Curved Stimulus and Chevrons,” Vision Research, Vol. 30, No.2, pp. 235–248, 1990
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Park, H., Lee, K., Byun, H., Lee, Y. (1996). Adaptive SEJONG-NET for on-line Hangul recognition. In: Foo, N., Goebel, R. (eds) PRICAI'96: Topics in Artificial Intelligence. PRICAI 1996. Lecture Notes in Computer Science, vol 1114. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-61532-6_38
Download citation
DOI: https://doi.org/10.1007/3-540-61532-6_38
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61532-3
Online ISBN: 978-3-540-68729-0
eBook Packages: Springer Book Archive