期刊文献+

基于数据生成的手语识别自适应方法

An adaptive Chinese sign language recognition method based on data generating
下载PDF
导出
摘要 采用自适应技术来解决非特定人手语识别问题,提出了一种基于数据生成的手语识别自适应方法。首先,对非特定人模型的均值向量进行自动聚类,寻找聚类中心生成手语词码本,然后,根据此码本选择词根子集,该子集能覆盖手语词码本的所有码字,继而,使用新用户的词根子集数据通过遗传算法生成其它词根的数据,最后,结合词根子集的真实数据和其它词根的生成数据,利用最大似然线性回归(MLLR)和最大后验概率(MAP)算法对非特定人模型进行自适应。实验结果表明,该方法既能够降低所需要的自适应数据量,又能够在非特定人模型基础上取得识别正确率的大幅提高。 This paper proposes an adaptive Chinese sign language recognition method based on data generating to solve the signer-independent (SI) problem using the adaptation technology. The method is described as below. First, the SI models' means are automatic clustered, and then the cluster centers are taken as codebooks of all etyma. A subset of all etyma is selected to cover all codewords. The data of the subset for a new signer are used to generate the data of other etyma with the genetic algorithm. By utilizing the original data and generated data with the algorithms of Maximum Likelihood Linear Regression (MLLR) & Maximum a Posteriori (MAP), SI models' means are adapted to the new signer. The experimental resuhs show that this method can both decrease the adaptation data and increase the recognition rate compared with the SI models.
出处 《高技术通讯》 EI CAS CSCD 北大核心 2009年第12期1258-1264,共7页 Chinese High Technology Letters
基金 863计划(2007AA01Z163) 北京市自然科学基金(4061001) 国家自然科学基金(60533030 60603023)资助项目
关键词 手语识别 自适应 最大似然线性回归(MLLR) 最大后验概率(MAP) 遗传算法 sign language recognition, adaptation, Maximum Likelihood Linear Regression (MLLR), Maximum a Posteriori (MAP), genetic algorithm
  • 相关文献

参考文献9

  • 1Starner T, Weaver J, Pentland A. Real-time American sign language reeognition using desk and wearable computer based video. IEEE Trans PAMI, 1998, 20(12): 1371-1375.
  • 2Liang R H, Ouhyoung M. A real-time continuous gesture recognition system for sign language. In: Proceedings of the IEEE Conference on Automatic Face and Gesture Recognition, Nara, Japan, 1998. 558-665.
  • 3Shanableh T, Assaleh K, Al-Rousan M. Spatio-temporal feature-extraction techniques for isolated gesture recognition in Arabic sign language. IEEE Trans SMC-B, 2007, 37 (3) : 641-650.
  • 4吴江琴,高文,庞博,韩静萍.中国手语手势词识别的一种快速方法[J].高技术通讯,2001,11(6):23-27. 被引量:5
  • 5Wang C, Chen X, Gao W. A comparison between etymon- and word-based Chinese sign language recognition systems. In: Proceedings of the 6th International Gesture Workshop on Gesture and Sign Languages in Human-Computer Interaction (GW 2005), Berder Island, France, 2005. 84-87.
  • 6Chen J, Chen X, Gao W. Expand training set for face detection by GA re-sampling. In: Proceedings of the 6th IEEE International Conference on Automatic Face and Gesture Recognition, Seoul, Korea, 2004. 73-78.
  • 7王一梅,贾克斌,庄新月.一种基于动态时间规划的视频特征检索改进算法[J].高技术通讯,2007,17(5):464-469. 被引量:1
  • 8Leggetter C J, Woodland P C. Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models. Computer Speech & Language, 1995, 9(2) : 171-185.
  • 9Gauvain J L, Lee C H. Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains. IEEE Trans. Audio Speech Lang Process, 1994, 2(2): 291- 298.

二级参考文献12

  • 1中国聋人协会.中国手语[M].北京:华夏出版社,1991..
  • 2马继勇.话者识别算法研究:[学位论文].哈尔滨:哈尔滨工业大学计算机系,1999..
  • 3马继勇,学位论文,1999年
  • 4中国聋人协会,中国手语,1991年
  • 5Bolle R M,Yeo B L,Yeung M M.Video query:research directions.IBM Journal of Research & Development,1998,42(2):233-252.
  • 6Takahashi K.A proposal of“video fingerprints”for MEPG-7 visual descriptor.ISO/IEC JTC1/SC29/WG11 N2462 section 4.1,1998.
  • 7Zhuang X Y,Jia K B.An effective video matching algorithm for adaptive video fingerprints.In:proceedings of-IEEE International Conference on Nonlinear Signal & Image Processing,Japan,2005,24-28.
  • 8Chang S,Smith J,Beigi M,et al.Visual information retrieval from large distributed online repositories.Communications of ACM,1997,40(2):63-71.
  • 9Gupta V,Jain R.Visual information retrieval.Communications of ACM,1997,40(5):70-79.
  • 10Zhuang X Y,Jia K B,Zhang L.An improved video retrieval algorithm based on video fingerprints.In:Proceedings of International Symposium on Computing and Information,Guangdong,China.2004,1147-1151.

共引文献4

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部