Character normalization is to recover distortions happened in character images. There are two kinds of character distortions: local and global. Local distortion has been discussed in literature, but global distortion that is usually produced by geometric transformation is not formally invited. In this paper, a novel method for solving global character distortion problem is proposed. The global character distortion problem will be regarded as a constrained geometric transformation problem, and an adaptive optimization approach using genetic algorithms is proposed to solve the problem. Experiments on Chinese characters with six kinds of distortions show satisfactory results.
|Number of pages||6|
|Journal||Proceedings of the IEEE International Conference on Systems, Man and Cybernetics|
|State||Published - 1996|
|Event||Proceedings of the 1996 IEEE International Conference on Systems, Man and Cybernetics. Part 3 (of 4) - Beijing, China|
Duration: 14 Oct 1996 → 17 Oct 1996