Loading...
Please wait, while we are loading the content...
Similar Documents
8th International Workshop on Frontiers in Handwriting Recognition (IWFHR-8), pp.78-83 (2002-08) Context-dependent Substroke Model for HMM-based On-line Handwriting Recognition
| Content Provider | CiteSeerX |
|---|---|
| Author | Tokuno, Junko Inami, Nobuhito Matsuda, Shigeki Nakai, Mitsuru Shimodaira, Hiroshi Sagayama, Shigeki |
| Abstract | This paper describes context-dependent substroke hidden Markov models (HMMs) for on-line handwritten recognition of cursive Kanji and Hiragana characters. As there are more than 6,000 distinctive characters including Kanji and Hiragana in Japanese, modeling each character by an HMM leads to an infeasible character-recognition system requiring huge amount of memory and enormous computation time. In order to tackle this problem, we have proposed the substroke HMM approach where a modeling unit “substroke” that is much smaller than a whole character is employed and each character is modeled as a concatenation of only 25 kinds of substroke HMMs. One of the drawback of this approach is that the recognition accuracy deteriorates in case of scribbled characters, and characters where the shape of the substrokes varies a lot. In this paper, we show that the context-dependent substroke modeling which depends on how the substroke connects to the adjacent substrokes is effective to achieve robust recognition of low quality characters. The Successive State Splitting (SSS) algorithm which was mainly developed for speech recognition is employed to construct the context dependent substroke HMMs. Experimental results show that the correct recognition rate improved from 88 % to 92 % for cursive Kanji handwritings and from 90 % to 98 % for Hiragana handwritings. 1. |
| File Format | |
| Access Restriction | Open |
| Subject Keyword | Hmm-based On-line Handwriting Recognition International Workshop Handwriting Recognition Context-dependent Substroke Model Cursive Kanji Cursive Kanji Handwriting Scribbled Character Hiragana Handwriting Infeasible Character-recognition System Recognition Accuracy Context-dependent Substroke Hidden Markov Model Whole Character Experimental Result Speech Recognition Substroke Hmms On-line Handwritten Recognition Modeling Unit Context-dependent Substroke Successive State Splitting Low Quality Character Substroke Hmm Approach Correct Recognition Rate Hiragana Character Distinctive Character Enormous Computation Time Huge Amount Adjacent Substrokes Robust Recognition |
| Content Type | Text |
| Resource Type | Article |
