Online Handwriting Mongolia Words Recognition Based on HMM Classifier

摘要：

In this paper, we give a recognition method for Online Handwriting Mongolia words which being often used among the Mongolia people in the North China. We introduced the HMM technique for handwriting recognition. We make use of local dynamic information for feature selection, and k-means clustering algorithm base on HMM. Experimental results show that writer-dependent words achieve recognition rates above 90％. The system runs well and is good stability. Recognition rate achieves just to the level of utility.

关键词： Mongolia Words Handwriting Recognition HMM

作者: Wu Wei Gao Guanglai

作者单位: College of Computer Science, Inner Mongolia University, Hohhot 010021, China

会议类型: 国际会议

会议名称: 2009年中国控制与决策会议(2009 Chinese Control and Decision Conference)

会议地点: 广西桂林

会议语种:英文

页码: 3912-3914

在线出版日期: 2009-06-17（万方平台首次上网日期，不代表论文的发表时间）