Browse Bar: Browse by Author | Browse by Category | Browse by Citation | Advanced Search
Author(s): Kim, H.J. | Kim, J.W. | Kim, S.K. |
Year: 1996
Citation: NEUROCOMPUTING Volume: 10 Issue: 3 Pages: 291-305
Abstract: This paper proposes an efficient method for on-line recognition of cursive Korean characters. Since Korean characters are composed of two or three graphemes in two dimensions, strokes, primitive components of the characters, are usually warped into a cursive form. To classify automatically such cursive strokes, an Adaptive Resonance Theory (ART) neural network is used. Fuzzy membership functions are used to adjust the system according to the writing habits of individual users. The positional relation between two consecutive strokes is also computed with fuzzy functions. With a sequence of strokes classified by the ART neural network and their positional relations computed by fuzzy functions, a character is recognized on a multilayer perceptron for character construction. The proposed method works well with the variation of different writing styles. A test with 17,500 hand-written characters shows a recognition rate of 96.5 per cent and a speed of 0.3 second per character.
Topics:
Image Analysis,
Applications:
Character Recognition,
Models:
ART 1,
