基于词根的中国手语识别方法  

A Subword-Based Approach to Large Vocabulary Chinese Sign Language Recognition

作　　者：王春立[1] 高文[2,3] 马继勇[4] 高秀娟[5] 

机构地区：[1]大连理工大学电信学院计算机系 [2]中国科学院计算技术研究所 [3]哈尔滨工业大学计算机科学系哈尔滨150001 [4]科罗拉多大学口语研究中心 [5]哈尔滨工业大学计算机科学系

出　　处：《计算机研究与发展》2003年第2期150-156,共7页Journal of Computer Research and Development

基　　金：国家自然科学基金 (697893 0 1);中国科学院百人工程计划基金

摘　　要：迄今为止 ,手语识别面临的最大问题是如何解决词汇集易扩充的连续识别 提出一种大词汇量连续中国手语识别方法 ,将词根作为识别基元 ,由于基元的数目是有限的 ,因此基于HMM的手语信号的训练和识别变得比较容易处理 ,可以实现更大词汇量的识别 除此之外 ,所提方法还有利于实现手势语和手指语的混合识别 从中国手语中共整理出2 4 0 0多个词根 ,为每个词根建一个并行的HMM模型 ,对各数据流的HMM模型进行聚类 ,确定出手语识别的基元 根据这些基元对手势词编码 ,并建立了树状搜索网格 ,使用状态结点上高斯密度函数聚类、语言模型和N Best方法提高系统的速度和精度 对 5 119个手语词做了实验 ,连续语句的识别率可在 90Up to this time, the major challenge to sign language recognition is how to develop approaches that scale well with increasing vocabulary size In this paper, an approach to large vocabulary, continuous Chinese sign language(CSL) recognition is presented, which uses subwords instead of whole signs as the basic units Since the number of subwords is limited, HMM based training and recognition of the CSL signal become more tractable and have the potential to recognize enlarged vocabularies Furthermore, the proposed method facilitates the CSL recognition when finger alphabet is blended with gestures About 2400 subwords are defined for CSL One HMM is built for each subword, and then the signs are encoded based on these subwords A decoder that uses tree structured network is presented Clustering of the Gaussians on the state, language model and N best is used to improve the performance of the system Experiments on a 5119 sign vocabulary are carried out, and the correct rate is over 90% for continuous sign recognition

关 键 词：词根 中国手语识别方法 HMM模型 图像处理 快速匹配算法 计算机 手语自动翻译系统 

分 类 号：TP391.2[自动化与计算机技术—计算机应用技术] TP391.41[自动化与计算机技术—计算机科学与技术]