| Boosting the Expense and Performance of Ann／Hmm Approch for on-line Handwriting Recognition |
| |
| 引用本文： | 李海峰,HAN Jiqing,Zheng Tieran,Ma Lin,Gallinari P.Boosting the Expense and Performance of Ann／Hmm Approch for on-line Handwriting Recognition[J].高技术通讯(英文版),2003,9(4):83-87. |
| |
| 作者姓名： | 李海峰 HAN Jiqing Zheng Tieran Ma Lin Gallinari P |
| |
| 作者单位： | [1]ScloolofComputerScienceandTechnology,HarbinInstituteofTechnology,Harbin150001,P.R.China [2]ComputerScienceLaboratory,UniversityParis6,Paris75015,France |
| |
| 摘 要： | This paper focuses on a state sharing method for an artificial neural network (ANN) and hidden Markov model (HMM) hybrid on-line handwriting recognition system. A modeling precisionbased distance measure is proposed to describe similarity between two ANNs, which are used as HMM state-models. Limiting maximum system performance loss, a minimum quantification error aimed hierarchical clustering algorithm is designed to choose the most representative models. The system performance is improved by about 1.5% while saving 40% of the system expense. About 92% of the performance may also be maintained while reducing 70% of system pararfieters. The suggested method is quite useful for designing pen-based interface for various handheld devices.
|
| 关 键 词： | 人工神经网络 ANN 隐藏Markov法 HMM 在线笔迹识别系统 |
Boosting the Expense and Performance of Ann/Hmm Approch for on-line Handwriting Recognition |
| |
| HAN Jiqing,Zheng Tieran,Ma Lin,Gallinari P.Boosting the Expense and Performance of Ann/Hmm Approch for on-line Handwriting Recognition[J].High Technology Letters,2003,9(4):83-87. |
| |
| Authors: | HAN Jiqing Zheng Tieran Ma Lin Gallinari P |
| |
| Abstract: | This paper focuses on a state sharing method for an artificial neural network (ANN) and hidden Markov model (HMM) hybrid on line handwriting recognition system. A modeling precision based distance measure is proposed to describe similarity between two ANNs, which are used as HMM state models. Limiting maximum system performance loss, a minimum quantification error aimed hierarchical clustering algorithm is designed to choose the most representative models. The system performance is improved by about 1.5% while saving 40% of the system expense. About 92% of the performance may also be maintained while reducing 70% of system parameters. The suggested method is quite useful for designing pen based interface for various handheld devices. |
| |
| Keywords: | boosting state sharing hierarchical clustering on line handwriting recognition |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
