Pen Pressure Features for Writer-Independent On-Line Handwriting Recognition Based on Substroke HMM
ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 3 - Volume 3
Substroke Approach to HMM-Based On-line Kanji Handwriting Recognition
ICDAR '01 Proceedings of the Sixth International Conference on Document Analysis and Recognition
On-line Overlaid-Handwriting Recognition Based on Substroke HMMs
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
Online Recognition of Chinese Characters: The State-of-the-Art
IEEE Transactions on Pattern Analysis and Machine Intelligence
LAMPS: A sketch recognition-based teaching tool for Mandarin Phonetic Symbols I
Journal of Visual Languages and Computing
| Hi-index | 0.02 |
This paper describes a method of generating a Kanjihierarchical structured dictionary for stroke-number andstroke-order free handwriting recognition based on sub-strokeHMM. In stroke-based methods, a large numberof stroke-order variations can be easily expressed by justadding dierent stroke sequences to the dictionary and itis not necessary to train new reference patterns. The hierarchicalstructured dictionary has an advantage that thousandsof stroke-order variations of Kanji characters can beproduced using a small number of stroke-order rules definingKanji parts. Moreover, the recognition speed is fastsince common sequences are shared in a substroke network,even if the total number of stroke-order combinations becomesenormous practically. In experiments, 300 dierentstroke-order rules of Kanji parts were statistically chosen byusing 60 writers' handwritings of 1,016 educational Kanjicharacters. By adding these new stroke-order rules to thedictionary, about 9,000 variations of dierent stroke-orderswere generated for 2,965 JIS 1st level Kanji characters. Asa result, we successfully improved the recognition accuracyfrom 82.6% to 90.2% for stroke-order free handwritings.