A recognition algorithm for Chinese characters in diverse fonts

The paper proposes an algorithm for recognizing Chinese characters in many diverse fonts including Song, Fang, Kai, Hei, Yuan, Lishu, Weibei and Xingkai. The algorithm is based on features derived from peripheral direction contributions and utilizes a set of dictionaries. A 3-level matching is first performed with respect to each dictionary. The distance measures associated with these matches are then fed into a central discriminator to output the final recognition result. We propose a new multi-dictionary matching algorithm for use in the central discriminator that utilizes estimated information of neighborhood fonts. Experiments have been performed on a practical OCR software system whose recognition kernel is based on the proposed algorithm. Fast and accurate recognition has been accomplished both in title recognition, involving all of the 8 fonts, and in main-body recognition, that usually involves only the first 4 most commonly used fonts.