A rotation invariant printed Chinese character recognition system

In this paper, we present an approach to construct an optical character rec ognition (OCR) system for recognizing rotated printed Chinese characters. O ur system includes preprocessing, feature extraction, candidates selection, and target character recognition. The proposed system has a three-stage st ructure designed mainly to reduce the time complexity in the recognition pr ocess. Our goal is to recognize the complete set of frequently used 13053 p rinted Chinese characters with arbitrary orientations. The overall recognit ion rate of our system reaches 97.4%. (C) 2001 Elsevier Science B.V. All ri ghts reserved.