The State of the Art in Online Handwriting Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
ICDAR '97 Proceedings of the 4th International Conference on Document Analysis and Recognition
Recognizing on-line handwritten Chinese character via FARG matching
ICDAR '97 Proceedings of the 4th International Conference on Document Analysis and Recognition
Robust and Highly Customizable Recognition of On-Line Handwritten Japanese Characters
ICPR '96 Proceedings of the International Conference on Pattern Recognition (ICPR '96) Volume III-Volume 7276 - Volume 7276
On-Line Cursive Kanji Character Recognition Using Stroke-Based Affine Transformation
ICPR '96 Proceedings of the International Conference on Pattern Recognition (ICPR '96) Volume III-Volume 7276 - Volume 7276
ICPR '96 Proceedings of the International Conference on Pattern Recognition (ICPR '96) Volume III-Volume 7276 - Volume 7276
Radical-Based Neighboring Segment Matching Method for On-Line Chinese Character Recognition
ICPR '96 Proceedings of the International Conference on Pattern Recognition (ICPR '96) Volume III-Volume 7276 - Volume 7276
Online Recognition of Chinese Characters: The State-of-the-Art
IEEE Transactions on Pattern Analysis and Machine Intelligence
Hi-index | 0.00 |
Several years ago, the on-line Japanese character recognition system was developed for the pen based mobile computer "Japanese AMITY", a product of Mitsubishi Electric Corporation. By modifYing and improving it, the on-line Chinese character recognition system has been developedfor "Chinese AMITY".Most of the Chinese characters are thought the same shape to the Japanese Kanji characters, if they are in the same category. This is roughly true for printed characters but is not true for the on-line handwriting characters.This paper describes first the differences of the character patterns handwritten by the people of China and Japan, in their own style as usual. Total of 8,063 categories of Chinese character patterns were collected in Shanghai and investigated, where 3,942 categories of the basic set were written by 400 persons and 4,121 categories of the optional set by 50 persons.Secondly, it is shown that Chinese characters are difficult to be recognized by adapting our original on-line Kanji recognition algorithm, because of their varieties of the number of strokes, the order of strokes and the shapes. So we have modified and improved the recognition algorithm and show the experimental results.