一种基于DTW/ISODATA算法的多层分类器手语识别方法  

A Method of Sign Language Recognition Based on DTW/ISODATA Algorithm Multilayer-classifier

作　　者：姚桂林[1] 姚鸿勋[1] 姜峰[1] 

机构地区：[1]哈尔滨工业大学计算机系,哈尔滨150001

出　　处：《计算机工程与应用》2005年第8期45-47,200,共4页Computer Engineering and Applications

基　　金：国家863高技术研究发展计划项目资助

摘　　要：为提高大词汇量手语识别速度,论文提出了一种将动态时间规整(DTW)和隐马尔可夫模型(HMM)相结合的多层次的大词汇量手语识别方法。该方法思想是先进行全局粗略搜索,将要识别的手势词归入某一组范围较小的词表中,然后通过更加精确的HMM局部搜索将词识别出来。各个词汇表用DTW/ISODATA算法来产生。对4942个孤立手语词作了实验,结果表明,相对于仅用HMM单层识别而言,识别速度从原来每个词的2.364秒提高到0.137秒,提高了94.2%,识别准确率也提高了4.66%。In this paper,a multilayer architecture of sign language recognition linking DTW and HMM for large vocabulary is proposed for the purpose of speeding up the recognition process.The gesture sequence to be recognized is first located at a set of words through a global cursory search and then the gesture is recognized through a more aborative local search and the generation of words set is realized by DTW/ISODATA algorithm.The authors select 4942 isolated words to test.Experiment shows that the average recognition speed is increased by 94.2% and the recognition accuracy is raised by 4.66% more than the HMM-based recognition method.

关 键 词：手语识别 DTW/ISODATA 多层结构 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]