The Community for Technology Leaders
Green Image
<p>The constraint graph is introduced as a general character representation framework for recognizing multifont, multiple-size Chinese characters. Each character class is described by a constraint graph model. Sampling points on a character skeleton are taken as nodes in the graph. Connection constraints and position constraints are taken as arcs in the graph. For patterns of the same character class, the model captures both the topological invariance and the geometrical invariance in a general and uniform way. Character recognition is then formulated as a constraint-based optimization problem. A cooperative relaxation matching algorithm that solves this optimization problem is developed. A practical optical character recognition (OCR) system that is able to recognize multifont, multiple-size Chinese characters with a satisfactory performance was implemented.</p>
connection constraints; sampling points; multifont Chinese character recognition; constraint graph; character skeleton; position constraints; topological invariance; geometrical invariance; constraint-based optimization; cooperative relaxation matching algorithm; OCR; character recognition; graph theory; optimisation; topology

Y. Wu, X. Huang and J. Gu, "A Constrained Approach to Multifont Chinese Character Recognition," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 15, no. , pp. 838-843, 1993.
82 ms
(Ver 3.3 (11022016))