首页 | 本学科首页   官方微博 | 高级检索  
     

结合HMM和SPSM的手语识别方法
引用本文:周宇,陈熙霖,王春立,赵德斌,高文.结合HMM和SPSM的手语识别方法[J].计算机工程与应用,2008,44(21):37-40.
作者姓名:周宇  陈熙霖  王春立  赵德斌  高文
作者单位:1. 哈尔滨工业大学,计算机科学与技术学院,哈尔滨,150001
2. 中国科学院,计算技术研究所,北京,100190
3. 大连海事大学,计算机科学与技术学院,辽宁,大连,116026
4. 哈尔滨工业大学,计算机科学与技术学院,哈尔滨,150001;北京大学,数字媒体研究所,北京,100871
基金项目:国家自然科学基金 , 北京市自然科学基金
摘    要:手语识别的研究具有重大的学术价值和广泛的应用前景。在近些年的手语识别工作中,隐马尔可夫模型(Hidden Markov Models,简称HMMs)起到了重要的作用,但是,HMMs假设同一状态内的观察值之间是独立同分布的,这个假设同某些手语信号的帧间相关性相背离。受到多项式片段模型(Polynomial Segment Models,简称PSMs)能够显式描述帧间相关性的启发,提出了一种简化的PSMs,其中应用马氏距离作为距离测度。实验表明,这种简化的PSMs在同传统的HMMs进行后验概率归一化求和的融合之后,手语词的平均相对正确率得到了13.38%的提升,从而证明此方法是一种更加精确的手语识别方法。

关 键 词:手语识别  人机交互  隐马尔可夫模型  多项式片段模型
收稿时间:2008-4-30
修稿时间:2008-5-26  

Combining HMM and SPSM for sign language recognition
ZHOU Yu,CHEN Xi-lin,WANG Chun-li,ZHAO De-bin,GAO Wen.Combining HMM and SPSM for sign language recognition[J].Computer Engineering and Applications,2008,44(21):37-40.
Authors:ZHOU Yu  CHEN Xi-lin  WANG Chun-li  ZHAO De-bin  GAO Wen
Affiliation:1.School of Computer Science and Technology,Harbin Institute of Technology,Harbin 150001,China 2.Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190,China 3.Institute of Digital Media,Peking University,Beijing 100871,China 4.School of Computer Science and Technology,Dalian Maritime University,Dalian,Liaoning 116026,China
Abstract:The research of sign language recognition has great academic value and broad application prospect.In recent works on sign language recognition,Hidden Markov Models(HMMs) has played an important role.But the framework of HMMs makes an assumption that the observations in the same state are independent and identically distributed,which is not consistent with sign language signals sometimes.Inspired by Polynomial Segment Models(PSMs) that can model the consecutive frame correlation well,in this paper we propose a type of simplified PSMs,in which Mahalanobis distance is used as the similarity metric.Experimental results show that after combining conventional HMMs and the simplified PSMs with summation of normalized posteriori,the average relative accuracy can be improved by 13.38%.As result,our method is superior to conventional HMMs.
Keywords:sign language recognition  human-computer interaction  hidden Markov models  polynomial segment models
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《计算机工程与应用》浏览原始摘要信息
点击此处可从《计算机工程与应用》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号