基于虚拟立体视约束的视角无关手语识别研究
|
摘要
手语识别研究致力于通过计算机将手语翻译成文字或者语音,以方便聋人与健听人之间的交流和帮助聋人更好地融入社会。
依手语数据获取方式的不同,手语识别研究通常分为基于数据手套的手语识别和基于视觉的手语识别两个类别。二者当中,基于视觉的手语识别研究,由于应用起来更为方便和自然,备受研究者所关注。然而,大多数基于视觉的手语识别研究限定摄像机的捕获视角,通常限定为正面视角。限定捕获视角意味着手语者只能在特定的空间以特定的朝向执行手语,这严重地限制着手语者的自由。
本文针对单摄像机应用中、一定范围内视角无关的手语识别,也即观测手语样本的捕获视角在一定范围内任意且未知情况下的手语识别进行研究,以在一定程度上解除对摄像机捕获视角的限定,从而方便用户的使用。这里的一定范围,是指摄像机的光轴方向与手语者正面朝向之间的角度限制在45?范围之内。数据规模初步定于中等词汇集。
重点研究如下两方面内容:
一是基于视角相关特征的视角无关手语识别研究。基于虚拟立体视约束,即“同一手语不同捕获视角下的两个样本,对齐之后可解释为由某一虚拟的立体视觉系统同步捕获的一个样本对”,本文提出一种新颖的、使用视角相关特征的视角无关手语识别框架。此框架将两个手语序列的匹配问题转化为极几何中的一个验证问题,通过验证“两个手语序列是否能被解释为由某一虚拟立体视觉系统同步捕获的一个样本对”来完成识别。由于是直接基于特征点的图像坐标进行识别,此框架提供了一种使用视角相关特征而实现视角无关手语识别的可能性。基于此框架,本文提出了三种具体的使用视角相关特征的视角无关手语识别方法,分别是基于基础矩阵唯一性的视角无关手语识别方法、基于证据理论的验证基础矩阵唯一性的视角无关手语识别方法以及基于复合帧对应的视角无关手语识别方法。实验显示了这些方法的有效性。
二是短时数据缺失下稳定而有效的视角无关手语识别方法研究。所谓数据缺失,是指手语样本中某些时刻只能提供很少的有用特征以供匹配之用或者不能提供任何有用特征的情况。很多因素都能导致数据缺失的出现,比如自遮挡、成像因素导致的图像模糊、以及特征提取算法的不完善等因素。除此之外,在视角无关的手语识别中,同一手语不同捕获视角的样本之间可视特征的不尽一致,也能够导致数据缺失的出现。数据缺失影响识别算法的有效性和可行性。本文针对短时数据缺失下稳定而有效的视角无关手语识别方法进行重点研究,提出了基于运动元顺序出现单应性的视角无关手语识别方法以及基于基础矩阵的局部采样(Sample)加全局验证(Consensus)的视角无关手语识别方法。这两种方法基于多帧图像来进行序列匹配的考察,由于多帧图像可以提供更多的有用特征,这两种方法能够有效地处理短时数据缺失情况。实验显示了这两种方法的有效性。
值得指出的是,本文提出的基于虚拟立体视约束的视角无关识别框架和因之而提出的各种视角无关识别方法不仅仅适用于手语识别,还能应用到更为广泛的领域,比如视角无关的动作识别和刚体运动分析等。
Sign language recognition aims to translate sign language into text or speechby computer, so as to facilitate the communication between the deaf and the hearingpeople and help the deaf or hard-of-hearing better integrate into the society.
According to data collection of sign language, sign language recognition are gen-erally divided into two major categories: dataglove-based sign language recognitionand vision-based sign language recognition. Since the vision-based method is moreconvenient to the end-users than dataglove-based method,it attracts more attention ofthe researchers. However, most of the current methods require a specific view of thesigners, generally the frontal view. This constraint means that the signers can onlyperform with specific location and orientation, and limits the freedom of the signer.
The thesis aims to achieve viewpoint free sign language recognition within acertain scope with only one camera, so as to remove the restriction of a specified viewand provide convenience for the user. The scope now covers a range from 0? to 45?from the point of view of the angle between the optical axis of the camera and theorientation of the signer. The size of sign language vocabulary is preliminarily set tomedium.
The thesis focuses on the following two aspects:
(A) Viewpoint free sign language recognition based on viewpoint dependent fea-tures. Based on the FSV (Fictitious Stereo Vision) constraint that all correspondingframe pairs between two sequences of the same sign but from different viewpointscan be explained as captured synchronously in some fictitious stereo vision system,the thesis proposes a novel FSV recognition framework for viewpoint free sign lan-guage recognition. The proposed FSV recognition framework converts the recogni-tion task to a verification task in the framework of epipolar geometry and achievesrecognition by verifying whether two sign sequences can be explained as capturedsynchronously in some fictitious stereo vision system. Because the FSV recognitionframework employs the image coordinate of feature points, it is a way to viewpointfree sign language recognition from viewpoint dependent features. Based on the pro-posed FSV recognition framework, the thesis proposes three methods for viewpoint free sign language recognition, including the method based on the uniqueness of fun-damental matrices, the method of employing evidence theory to verify the uniquenessof fundamental matrices and the method based on the correspondence between thecompounded frame pair. Experiments show the efficiency of the proposed three meth-ods.
(B) Viewpoint free sign language recognition under short-duration data defi-ciency. Data deficiency refers to the case that some frames in a sign language sequencecan provide only small number of efficient features or no efficient feature for match-ing. Data deficiency may be caused by many factors such as self-occlusion, the imageblur and the imperfection of the feature extraction algorithm. Besides, in the appli-cation of viewpoint free sign language recognition, the observable feature set of anobservation sample may be different from that of its matched template sample, whichmay also cause data deficiency. Data deficiency may affect the efficiency and feasi-bility of recognition algorithm. The thesis emphasizes the case of short-duration datadeficiency and aims to achieve robust and efficient methods for viewpoint free signlanguage recognition under such cases. In the light of more frames providing morefeatures, the thesis proposes two novel methods for short-duration data deficiency,including the method based on the homography of tiny motions and the fundamental-matrix-centered Sample-Consensus method. Experiments show the efficiency of theproposed two methods.
It is worth noting that the proposed FSV recognition framework and all the pro-posed methods for viewpoint free sign language recognition not only fit for sign lan-guage recognition, but also can be applied to more broad fields such as viewpoint freemotion recognition and rigid-motion analysis.
依手语数据获取方式的不同,手语识别研究通常分为基于数据手套的手语识别和基于视觉的手语识别两个类别。二者当中,基于视觉的手语识别研究,由于应用起来更为方便和自然,备受研究者所关注。然而,大多数基于视觉的手语识别研究限定摄像机的捕获视角,通常限定为正面视角。限定捕获视角意味着手语者只能在特定的空间以特定的朝向执行手语,这严重地限制着手语者的自由。
本文针对单摄像机应用中、一定范围内视角无关的手语识别,也即观测手语样本的捕获视角在一定范围内任意且未知情况下的手语识别进行研究,以在一定程度上解除对摄像机捕获视角的限定,从而方便用户的使用。这里的一定范围,是指摄像机的光轴方向与手语者正面朝向之间的角度限制在45?范围之内。数据规模初步定于中等词汇集。
重点研究如下两方面内容:
一是基于视角相关特征的视角无关手语识别研究。基于虚拟立体视约束,即“同一手语不同捕获视角下的两个样本,对齐之后可解释为由某一虚拟的立体视觉系统同步捕获的一个样本对”,本文提出一种新颖的、使用视角相关特征的视角无关手语识别框架。此框架将两个手语序列的匹配问题转化为极几何中的一个验证问题,通过验证“两个手语序列是否能被解释为由某一虚拟立体视觉系统同步捕获的一个样本对”来完成识别。由于是直接基于特征点的图像坐标进行识别,此框架提供了一种使用视角相关特征而实现视角无关手语识别的可能性。基于此框架,本文提出了三种具体的使用视角相关特征的视角无关手语识别方法,分别是基于基础矩阵唯一性的视角无关手语识别方法、基于证据理论的验证基础矩阵唯一性的视角无关手语识别方法以及基于复合帧对应的视角无关手语识别方法。实验显示了这些方法的有效性。
二是短时数据缺失下稳定而有效的视角无关手语识别方法研究。所谓数据缺失,是指手语样本中某些时刻只能提供很少的有用特征以供匹配之用或者不能提供任何有用特征的情况。很多因素都能导致数据缺失的出现,比如自遮挡、成像因素导致的图像模糊、以及特征提取算法的不完善等因素。除此之外,在视角无关的手语识别中,同一手语不同捕获视角的样本之间可视特征的不尽一致,也能够导致数据缺失的出现。数据缺失影响识别算法的有效性和可行性。本文针对短时数据缺失下稳定而有效的视角无关手语识别方法进行重点研究,提出了基于运动元顺序出现单应性的视角无关手语识别方法以及基于基础矩阵的局部采样(Sample)加全局验证(Consensus)的视角无关手语识别方法。这两种方法基于多帧图像来进行序列匹配的考察,由于多帧图像可以提供更多的有用特征,这两种方法能够有效地处理短时数据缺失情况。实验显示了这两种方法的有效性。
值得指出的是,本文提出的基于虚拟立体视约束的视角无关识别框架和因之而提出的各种视角无关识别方法不仅仅适用于手语识别,还能应用到更为广泛的领域,比如视角无关的动作识别和刚体运动分析等。
Sign language recognition aims to translate sign language into text or speechby computer, so as to facilitate the communication between the deaf and the hearingpeople and help the deaf or hard-of-hearing better integrate into the society.
According to data collection of sign language, sign language recognition are gen-erally divided into two major categories: dataglove-based sign language recognitionand vision-based sign language recognition. Since the vision-based method is moreconvenient to the end-users than dataglove-based method,it attracts more attention ofthe researchers. However, most of the current methods require a specific view of thesigners, generally the frontal view. This constraint means that the signers can onlyperform with specific location and orientation, and limits the freedom of the signer.
The thesis aims to achieve viewpoint free sign language recognition within acertain scope with only one camera, so as to remove the restriction of a specified viewand provide convenience for the user. The scope now covers a range from 0? to 45?from the point of view of the angle between the optical axis of the camera and theorientation of the signer. The size of sign language vocabulary is preliminarily set tomedium.
The thesis focuses on the following two aspects:
(A) Viewpoint free sign language recognition based on viewpoint dependent fea-tures. Based on the FSV (Fictitious Stereo Vision) constraint that all correspondingframe pairs between two sequences of the same sign but from different viewpointscan be explained as captured synchronously in some fictitious stereo vision system,the thesis proposes a novel FSV recognition framework for viewpoint free sign lan-guage recognition. The proposed FSV recognition framework converts the recogni-tion task to a verification task in the framework of epipolar geometry and achievesrecognition by verifying whether two sign sequences can be explained as capturedsynchronously in some fictitious stereo vision system. Because the FSV recognitionframework employs the image coordinate of feature points, it is a way to viewpointfree sign language recognition from viewpoint dependent features. Based on the pro-posed FSV recognition framework, the thesis proposes three methods for viewpoint free sign language recognition, including the method based on the uniqueness of fun-damental matrices, the method of employing evidence theory to verify the uniquenessof fundamental matrices and the method based on the correspondence between thecompounded frame pair. Experiments show the efficiency of the proposed three meth-ods.
(B) Viewpoint free sign language recognition under short-duration data defi-ciency. Data deficiency refers to the case that some frames in a sign language sequencecan provide only small number of efficient features or no efficient feature for match-ing. Data deficiency may be caused by many factors such as self-occlusion, the imageblur and the imperfection of the feature extraction algorithm. Besides, in the appli-cation of viewpoint free sign language recognition, the observable feature set of anobservation sample may be different from that of its matched template sample, whichmay also cause data deficiency. Data deficiency may affect the efficiency and feasi-bility of recognition algorithm. The thesis emphasizes the case of short-duration datadeficiency and aims to achieve robust and efficient methods for viewpoint free signlanguage recognition under such cases. In the light of more frames providing morefeatures, the thesis proposes two novel methods for short-duration data deficiency,including the method based on the homography of tiny motions and the fundamental-matrix-centered Sample-Consensus method. Experiments show the efficiency of theproposed two methods.
It is worth noting that the proposed FSV recognition framework and all the pro-posed methods for viewpoint free sign language recognition not only fit for sign lan-guage recognition, but also can be applied to more broad fields such as viewpoint freemotion recognition and rigid-motion analysis.
引文
1 G. Grimes. Digital Data Entry Glove Interface Device. Technical Report, BellTelephone Laboratories. 1983
2 G. Fang, W. Gao, D. Zhao. Large-vocabulary Continuous Sign LanguageRecognition Based on Transition-movement Models. IEEE Transactions onSystems, Man, and Cybernetics Part A:Systems and Humans. 2007, 37(1):1–9
3 H. Haberdar, S. Albayrak. Real Time Isolated Turkish Sign Language Recog-nition from Video Using Hidden Markov Models with Global Features, 2005
4 H. Sagawa, M. Takeuchi. A Recognition Method of Sign Language Sentencesfor Japanese Sign Language Translation. Proceedings of the Joint Conferenceon Information Sciences. 2000:858–861
5 J. S. Kim, W. Jang, Z. Bien. A Dynamic Gesture Recognition System for theKorean Sign Language (ksl). IEEE Transactions on Systems, Man, and Cyber-netics, Part B: Cybernetics. 1996, 26(2):354–359
6 J. H. Kim, K. S. Hong. An Implementation of the Korean Sign Language Rec-ognizer Using Neural Network Based on the Post Pc, 2006
7 H. G. Wang, M. C. Leu, C. Oz. American Sign Language Recognition UsingMulti-dimensional Hidden Markov Models. Journal of Information Science andEngineering. 2006, 22(5):1109–1123
8 R. M. McGuire, J. Hernandez-Rebollar, T. Starner, et al. Towards a One-wayAmerican Sign Language Translator. IEEE International Conference on Auto-matic Face and Gesture Recognition. Seoul, 2004:620–625
9 R. Bowden, M. Sarhadi. A Non-linear Model of Shape and Motion for TrackingFinger Spelt American Sign Language. Image and Vision Computing. 2002,20(9-10):597–607
10 C. Vogler, D. Metaxas. A Framework for Recognizing the Simultaneous As-pects of American Sign Language. Computer Vision and Image Understanding.2001, 81(3):358–384
11 T. Starner, J. Weaver, A. Pentland. Real-time American Sign Language Recog-nition Using Desk and Wearable Computer Based Video. IEEE Transactions onPattern Analysis and Machine Intelligence. 1998, 20(12):1371–1375
12 B. Bauer, H. Hienz. Relevant Features for Video-based Continuous Sign Lan-guage Recognition. IEEE International Conference on Automatic Face and Ges-ture Recognition. 2000:440–445
13 B. Bauer, K. F. Kraiss. Video-based Sign Recognition Using Self-organizingSubunits. Proceedings - International Conference on Pattern Recognition. 2002,16:434–437
14 O. Al-Jarrah, A. Halawani. Recognition of Gestures in Arabic Sign LanguageUsing Neuro-fuzzy Systems. Artificial Intelligence. 2001, 133(1-2):117–138
15 A. Shamaie, A. Sutherlan. Accurate Recognition of Large Number of HandGesture. The Second Iranian Conference on Machine Vision and Image Pro-cessin. Iran, 2003
16 W. Hai, A. Sutherland. Irish Sign Language Recognition Using Pca, Multi-scaleTheory, and Discrete Hidden Markov Models. Proceedings of the Irish MachineVision Conference. 2004:66–73
17 G. Awad, J. Han, A. Sutherland. A Unified System for Segmentation and Track-ing of Face and Hands in Sign Language Recognition. Proceedings - Interna-tional Conference on Pattern Recognition. Hong Kong, 2006:239–242
18 T. Shanableh, K. Assaleh. Two Tier Feature Extractions for Recognition ofIsolated Arabic Sign Language Using Fisher’s Linear Discriminants. IEEE In-ternational Conference on Acoustics, Speech and Signal Processing. Honolulu,HI, 2007
19 T. Shanableh, K. Assaleh, M. Al-Rousan. Spatio-temporal Feature-extractionTechniques for Isolated Gesture Recognition in Arabic Sign Language. IEEETransactions on Systems Man and Cybernetics Part B-Cybernetics. 2007,37(3):641–650
20 H. Haberdar, S. Albayrak. A Two-stage Visual Turkish Sign Language Recog-nition System Based on Global and Local Features, 2006
21 M. A. Guvensan, M. A. Guvensan, H. Haberdar. Detection and Tracking ofFace and Facial Features for Recognition of Turkish Sign Language. H. Haber-dar, (Editor) Signal Processing and Communications Applications. IEEE 15th.2007:1–4
22 E. J. Holden, G. Lee, R. Owens. Automatic Recognition of Colloquial Aus-tralian Sign Language. Proceedings - IEEE Workshop on Motion and VideoComputing. 2005:183–188
23 T. Takahashi, F. Kishino. A Hand Gesture Recognition Method and its Appli-cation. Systems and Computers in Japan. 1992, 23(3):11
24 K. Murakami, H. Taguchi. Gesture Recognition Using Recurrent Neural Net-works. CHF91 Human Factors in Computing Systems. New York, 1991:237–24225 C. Lee, Y. S. Xu. Online, Interactive Learning of Gestures for Human/robotInterfaces. IEEE International Conference on Robotics and Automation, Pro-ceedings, Vols 1-4. 1996:2982–2987
26 J. Triesch, C. Malsburg. Robust Classification of Hand Postures Against Com-plex Background. IEEE International Conference on Automatic Face and Ges-ture Recognition. 1996
27 R. Lockton, A. W. Fitzgibbon. Real-time Gesture Recognition Using Determin-istic Boosting. Proceedings of British Machine Vision Conference. 2002
28 L. Gupta, S. Ma. Gesture-based Interaction and Communication: AutomatedClassification of Hand Gesture Contours. IEEE Transactions on Systems, Manand Cybernetics Part C: Applications and Reviews. 2001, 31(1):114–120
29 S. Fels, G. Hinton. Glove-talkii: A Neural Network Interface Which MapsGestures to Parallel Formant Speech Synthesizer Controls. 1998, 9(1):205–212
30 M. Waldron, S. Kim. Isolated Asl Sign Recognition System for Deaf Persons.IEEE Transaction on Rehabilitation Engineering. 1995, 3(3):261–271
31 H. Sagawa, M. Takeuchi, M. Ohki. Description and Recognition Methods forSign Language Based on Gesture Components. International Conference onIntelligent User Interfaces. 1997:97–104
32 J. L. Hernandez-Rebollar, N. Kyriakopoulos, R. W. Lindeman. A New In-strumented Approach for Translating American Sign Language Into Sound andText. IEEE International Conference on Automatic Face and Gesture Recogni-tion. 2004:547–552
33 Y. Cui, J. Weng. Appearance-based Hand Sign Recognition from Intensity Im-age Sequences. Computer Vision and Image Understanding. 2000, 78(2):157–17634 C. Vogler, D. Metaxas. Asl Recognition Based on a Coupling between Hmmsand 3d Motion Analysis. Proceedings of the IEEE International Conference onComputer Vision. 1998:363–369
35 R. Bowden, D. Windridge, T. Kadir, et al. A Linguistic Feature Vector for theVisual Interpretation of Sign Language. European Conference on ComputerVision. 2004:390–401
36 M. H. Yang, N. Ahuja, M. Tabb.”extraction of 2-d Motion Trajectories andits Application to Hand Gesture Recognition”. IEEE Transactions on PatternAnalysis and Machine Intelligence. 2002, 29(8):1062–1074
37 H. Matsuo, S. Igi, S. Lu, et al. The Recognition Algorithm with Non-contactfor Japanese Sign Language Using Morphological Analys. The InternationalGesture Workshop (GW’97). Germany, 1997:273–284
38 J. Deng, H. Ts. A Two-step Approach Based on Pahmm for the Recognitionof as. The Fifth Asian Conference on Computer Vision. Melbourne, Australia,2002:126–13
39 H. Sagawa, M. Takeuchi. A Method for Recognizing a Sequence of Sign Lan-guage Words Represented in a Japanese Sign Language Sentence. IEEE In-ternational Conference on Automatic Face and Gesture Recognition. France,2000:434–439
40 H. Sagawa, M. Takeuchi. Development of an Information Kiosk with a SignLanguage Recognition System. Proceedings of the Conference on UniversalUsability. 2000:149–150
41 H. Sagawa, M. Takeuchi. The Structure and Valuation of an Information Kioskwith a Sign-language Recognition System. International Conference on Intelli-gent User Interfaces. USA, 2001
42 R. H. Liang, M. Ouhyoung. A Real-time Continuous Gesture Recognition Sys-tem for Sign Language. IEEE International Conference Proceedings on Auto-matic Face and Gesture Recognition. 1998:558–567
43 T. Starner, A. Pentland. Real-time American Sign Language Recognition fromVideo Using Hidden Markov Models. Proceedings of the IEEE InternationalConference on Computer Vision. 1995:265–270
44 B. Bauer, H. Hienz, K. F. Kraiss. Video-based Continuous Sign LanguageRecognition Using Statistical Methods. Proceedings - International Conferenceon Pattern Recognition. 2000, 15:463–466
45 J. B. Kim, K. H. Park, W. C. Bang, et al. Continuous Gesture RecognitionSystem for Korean Sign Language Based on Fuzzy Logic and Hidden MarkovModel. Proceedings of IEEE International Conference on Fuzzy Systems.2002:1574–1579
46 V. I. Pavlovic, R. Sharma, T. S. Huang. Visual Interpretation of Hand Gesturesfor Human-computer Interaction: A Review. IEEE Transactions on PatternAnalysis and Machine Intelligence. 1997, 19(7):677–695
47 Y. Wu, T. S. Huang. Vision-based Gesture Recognition: A Review. Gesture-Based Communication in Human-Computer Interaction (A. Braffort, R. Gherbi,S. Gibet, J. Richardson, and D. Teil, Eds.), Lecture Notes in Artificial Intelli-gence. 1999, 1739:103–115
48 S. C. W. Ong, S. Ranganath. Automatic Sign Language Analysis: A Survey andthe Future Beyond Lexical Meaning. IEEE Transactions on Pattern Analysisand Machine Intelligence. 2005, 27(6):873–891
49 A. Erol, G. Bebis, M. Nicolescu, et al. Vision-based Hand Pose Estimation: AReview. Computer Vision and Image Understanding. 2007, 108(1-2):52–73
50 U. von Agris, J. Zieren, U. Canzler, et al. Recent Developments in Visual SignLanguage Recognition. Universal Access in the Information Society. 2008,6(4):323–362
51 W. Stokoe. Sign Language Structure: An Outline of the Visual Communica-tion System of the American Deaf. Studies in Linguistics, Occasional papers 8(revised 1978), University of Buffalo: Linstok Press, 1960
52 C. Vogler, S. Goldenstein. Facial Movement Analysis in Asl. Universal Accessin the Information Society. 2008, 6(4):363–374
53 J.-W. Deng, H. Tsui. A Novel Two-layer Pca/mda Scheme for Hand PostureRecognition. International Conference on Pattern Recognition. 2002:283–286
54 S. Akyol, P. Alvarado. Finding Relevant Image Content for Mobile Sign Lan-guage Recognition. Proceedings - IASTED International Conference on SignalProcessing, Pattern Recognition and Application. 2001:48–52
55 K. Imagawa, S. Lu, S. Igi. Color-based Hand Tracking System for Sign Lan-guage Recognition. IEEE International Conference on Automatic Face and Ges-ture Recognition. 1998:462–467
56 K. Imagawa, H. Matsuo, R. I. Taniguchi, et al. Recognition of Local Features forCamera-based Sign Language Recognition System. Proceedings - InternationalConference on Pattern Recognition. 2000, 15(4):849–853
57 J. C. Terrillon, A. Pilpre, Y. Niwa, et al. Robust Face Detection and Hand Pos-ture Recognition in Color Images for Human-machine Interaction. Proceedings- International Conference on Pattern Recognition. 2002, 16(1):204–209
58 Y. Cui, J. Weng. A Learning-based Prediction-and-verification SegmentationScheme for Hand Sign Image Sequence. IEEE Transactions on Pattern Analysisand Machine Intelligence. 1999, 21(8):798–804
59 C. L. Huang, W. Y. Huang. Sign Language Recognition Using Model-basedTracking and a 3d Hopfield Neural Network. Machine Vision and Applications.1998, 10(5-6):292–307
60 C. Huang, S. Jeng. A Model-based Hand Gesture Recognition System. MachineVision and Applications. 2001, 12(5):243–258
61 F. Chen, C. Fu, C. Huang. Hand Gesture Recognition Using a Real-time Track-ing Method and Hidden Markov Models. Image and Vision Computing. 2003,21(8):745–758
62 N. Tanibata, N. Shimada, Y. Shirai. Extraction of Hand Features for Recognitionof Sign Language Words. Proceedings - International Conference on VisionInterface. 2002:391–398
63 M. Assan, K. Grobel. Video-based Sign Language Recognition Using HiddenMarkov Models. The International Gesture Workshop. 1997:97–109
64 S. Tamura, S. Kawasaki. Recognition of Sign Language Motion Images. PatternRecognition. 1988, 21(4):343–353
65 J. Sherrah, S. Gong. Resolving Visual Uncertainty and Occlusion ThroughProbabilistic Reasoning. Proceedings of British Machine Vision Conference.2000:252–261
66 J. Zieren, N. Unger, S. Akyol. Hands Tracking from Frontal View for Vision-based Gesture Recognition. Proc. 24th DAGM Symp. 2002:531–539
67 A. Downton, H. Drouet. Model-based Image Analysis for Unconstrained Hu-man Upper-body Motion. Proceedings - International Conference on ImageProcessing and Its Applications. 1992:274–277
68 C. Vogler, D. Metaxas. Adapting Hidden Markov Models for Asl Recognitionby Using Three-dimensional Computer Vision Methods. IEEE InternationalConference on Systems, Man and Cybernetics. 1997, 1:156–161
69 T. Kobayashi, S. Haruyama. Partly-hidden Markov Model and its Applicationto Gesture Recognition. Proceedings - International Conference on Acoustics,Speech and Signal Processing. 1997, 4:3081–3084
70 Y. Wu, T. S. Huang. View-independent Recognition of Hand Postures. IEEEInternational Conference on Computer Vision and Pattern Recognition. 2000,2:88–94
71 M. Handouyahia, D. Ziou, S. Wang. Sign Language Recognition UsingMoment-based Size Functions. Proceedings - International Conference on Vi-sion Interface. 1999:210–216
72 E. Holden, R. Owens. Visual Sign Language Recognition. Proceedings - Inter-national Workshop on Theoretical Foundations of Computer Vision. 2000:270–28773 C. Nolker, H. Ritter. Visual Recognition of Continuous Hand Postures. IEEETransactions on Neural Networks. 2002, 13(4):983–994
74 J. Rehg, T. Kanade. Visual Tracking of High Dof Articulated Structures: AnApplication to Human Hand Tracking. European Conference on Computer Vi-sion. 1994, 2:35–46
75 H. Fillbrandt, S. Akyol, K. F. Kraiss. Extraction of 3d Hand Shape and Posturefrom Image Sequences for Sign Language Recognition. IEEE InternationalWorkshop on Analysis and Modeling of Face and Gestures. 2003:181–186
76 H. Hienz, K. Grobel, G. Offner. Real-time Hand-arm Motion Analysis Using aSingle Video Camera. IEEE International Conference on Automatic Face andGesture Recognition. 1996:323–327
77 A. Sutherland. Real-time Video-based Recognition of Sign Language Ges-tures Using Guided Template Matching. The International Gesture Workshop.1996:31–38
78 J. Wu, W. Gao. The Recognition of Finger-spelling for Chinese Sign Language.The International Gesture Workshop. 2001:96–100
79 M. Su. A Fuzzy Rule-based Approach to Spatio-temporal Hand Gesture Recog-nition. IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applica-tion Rev. 2000, 30(2):276–281
80 J. Bridle. Alphanets: A Recurrent‘neural’Network Architecture with a HiddenMarkov Model Interpretation. Speech Communication. 1990, 9(1):83–92
81 E. Trentin, M. Gori. A Survey of Hybrid Ann/hmm Models for AutomaticSpeech Recognition. Neurocomputing. 2001, 37(1/4):91–126
82 G. L. Fang, W. Gao. A Srn/hmm System for Signer-independent ContinuousSign Language Recognition. IEEE International Conference on Automatic Faceand Gesture Recognition. 2002:312–317
83 W. Gao, G. Fang, D. Zhao, et al. Transition Movement Models for Large Vocab-ulary Continuous Sign Language Recognition. IEEE International Conferenceon Automatic Face and Gesture Recognition. Seoul, 2004:553–558
84 C. Vogler. American Sign Language Recognition: Reducing the Complexity ofthe Task with Phoneme-based Modeling and Parallel Hidden Markov Models.Phd thesis, University of Pennsylvania. 2003
85 W. Gao, J. Ma, J. Wu, et al. Sign Language Recognition Based on Hmm/ann/dp.International Journal of Pattern Recognition and Artificial Intelligence. 2000,14(5):587–602
86 M. Kadous. Machine Recognition of Auslan Signs Using Powergloves: To-wards Large-lexicon Recognition of Sign Language. Proc. Workshop Integra-tion of Gestures in Language and Speech. 1996:165–174
87 P. Vamplew, A. Adams. Recognition of Sign Language Gestures Using NeuralNetworks. Australian Journal on Intelligence Information Processing Systems.1998, 5(2):94–102
88 S. C. W. Ong, S. Ranganath. Deciphering Gestures with Layered Meaningsand Signer Adaptation. IEEE International Conference on Automatic Face andGesture Recognition. Seoul, 2004:559–564
89祝远新,徐光祐,黄浴.基于表观的动态孤立手势识别.软件学报. 2000,11(1):54–61
90任海兵,祝远新,徐光祐,等.连续动态手势的时空表观建模及识别.计算机学报. 2000,23(8):824–828
91邹伟.中国手语单手词汇识别方法和技术研究.中科院自动化所博士学位论文. 2003
92 C. L. Wang, W. Gao, S. G. Shan. An Approach Based on Phonemes to Large Vo-cabulary Chinese Sign Language Recognition. IEEE International Conferenceon Automatic Face and Gesture Recognition. 2002:411–416
93 L. G. Zhang, Y. Chen, G. Fang, et al. A Vision-based Sign Language Recog-nition System Using Tied-mixture Density Hmm. International Conference onMultimodal Interfaces. 2004:198–204
94张良国,高文,陈熙霖,等.面向中等词汇量的中国手语视觉识别系统.计算机研究与发展. 2006,43(3):476–482
95易克初,田斌.语音信号处理.国防工业出版社, 2000
96 J. Q. Wu, W. Gao. A Fast Sign Word Recognition Method for Chinese SignLanguage. Advances in Multimodal Interfaces - ICMI. 2000, 1948:599–606
97 P. Brown, V. Pietra, P. deSouza, et al. Class-based N-gram Models of NaturalLanguage. Computational Linguistics. 1992, 18(4):467–479
98 M. Jardino. Multilingual Stochastic N-gram Class Language Models. IEEEInternational Conference on Acoustics, Speech and Signal Processing. Atlanta,1996:161–163
99 L. Bahl, P. Brown, P. DeSouza, et al. A Tree-based Language Model for Natu-ral Language Speech Recognition. IEEE Transactions on Information Theory,Speech and Signal Processing. 1989, 37:1001–1008
100 J. Foote. Decision-tree Probability Modeling for Hmm Speech Recognition.Phd thesis, Brown University. 1994
101 M. Siu, M. Ostendorf. Variable N-grams and Extensions for ConversationalSpeech Language Modeling. IEEE Transactions on Speech and Audio Process-ing. 2000, 8(1):63–75
102 S. D. Pietra, V. D. Pietra, R. Mercer, et al. Adaptive Language Modeling UsingMinimum Discriminant Estimation. The Internation Conference on Acoustics,Speech and Signal Processing. San Francisco, 1992
103 S. D. Pietra, V. D. Pietra, J. Lafferty. Inducing Features of Random Fields. IEEETransactions on Pattern Analysis and Machine Intelligence. 1997, 19(4):380–393104 R. Rosenfeld. A Maximum Entropy Approach to Adaptive Statistical Lan-guage Model for Speech Recognition. Computer Speech and Language. 1996,10(3):187–228
105 F. Jelinek, J. Lafferty. Basic Methods of Probabilistic Context Free Gram-mars. Technical Report RC 16374 (72684), IBM, Yorktown Heights, New York10598. 1990
106李勇,高文,姚鸿勋.基于颜色手套的中国手指语字母的动静态识别.计算机工程与应用. 2002,38(17):55–58
107 V. Athitsos, J. Alon, S. Sclaroff, et al. Boostmap: A Method for Efficient Ap-proximate Similarity Rankings. IEEE International Conference on ComputerVision and Pattern Recognition. 2004:268–275
108 R. Hartley, A. Zisserman. Multiple View Geometry in Computer Vision. Cam-bridge University Press, 2003
109 H. C. Longuet-Higgins. A Computer Algorithm for Reconstructing a Scenefrom Two Projections. Nature. 1981, 293(10):133–135
110 Q. Luong, O. D. Faugeras. Determining the Fundamental Matrix with Planes:Unstability and New Algorithms. IEEE International Conference on ComputerVision and Pattern Recognition. New-York, 1993:489–494
111 C. Rao, A. Gritai, M. Shah, et al. View-invariant Alignment and Matching ofVideo Sequences. Proceedings of the IEEE International Conference on Com-puter Vision. 2003, 2:939–945
112 A. Gritai, Y. Sheikh, M. Shah. On the Use of Anthropometry in the InvariantAnalysis of Human Actions. Proceedings - International Conference on PatternRecognition. 2004:923–926
113 G. Shafer. A Mathematical Theory of Evidence. Princeton, New Jersey: P. U.Press, 1976
114 M. A. Fischler, R. C. Bolles. Random Sample Consensus: A Paradigm forModel Fitting with Applications to Image Analysis and Automated Cartogra-phy. Communications of the ACM. 1981, 24(6):381–395
115 S. M. Smith, J. M. Brady. Susan. a New Approach to Low Level Image Pro-cessing. International Journal of Computer Vision. 1997, 23(1):45–78
2 G. Fang, W. Gao, D. Zhao. Large-vocabulary Continuous Sign LanguageRecognition Based on Transition-movement Models. IEEE Transactions onSystems, Man, and Cybernetics Part A:Systems and Humans. 2007, 37(1):1–9
3 H. Haberdar, S. Albayrak. Real Time Isolated Turkish Sign Language Recog-nition from Video Using Hidden Markov Models with Global Features, 2005
4 H. Sagawa, M. Takeuchi. A Recognition Method of Sign Language Sentencesfor Japanese Sign Language Translation. Proceedings of the Joint Conferenceon Information Sciences. 2000:858–861
5 J. S. Kim, W. Jang, Z. Bien. A Dynamic Gesture Recognition System for theKorean Sign Language (ksl). IEEE Transactions on Systems, Man, and Cyber-netics, Part B: Cybernetics. 1996, 26(2):354–359
6 J. H. Kim, K. S. Hong. An Implementation of the Korean Sign Language Rec-ognizer Using Neural Network Based on the Post Pc, 2006
7 H. G. Wang, M. C. Leu, C. Oz. American Sign Language Recognition UsingMulti-dimensional Hidden Markov Models. Journal of Information Science andEngineering. 2006, 22(5):1109–1123
8 R. M. McGuire, J. Hernandez-Rebollar, T. Starner, et al. Towards a One-wayAmerican Sign Language Translator. IEEE International Conference on Auto-matic Face and Gesture Recognition. Seoul, 2004:620–625
9 R. Bowden, M. Sarhadi. A Non-linear Model of Shape and Motion for TrackingFinger Spelt American Sign Language. Image and Vision Computing. 2002,20(9-10):597–607
10 C. Vogler, D. Metaxas. A Framework for Recognizing the Simultaneous As-pects of American Sign Language. Computer Vision and Image Understanding.2001, 81(3):358–384
11 T. Starner, J. Weaver, A. Pentland. Real-time American Sign Language Recog-nition Using Desk and Wearable Computer Based Video. IEEE Transactions onPattern Analysis and Machine Intelligence. 1998, 20(12):1371–1375
12 B. Bauer, H. Hienz. Relevant Features for Video-based Continuous Sign Lan-guage Recognition. IEEE International Conference on Automatic Face and Ges-ture Recognition. 2000:440–445
13 B. Bauer, K. F. Kraiss. Video-based Sign Recognition Using Self-organizingSubunits. Proceedings - International Conference on Pattern Recognition. 2002,16:434–437
14 O. Al-Jarrah, A. Halawani. Recognition of Gestures in Arabic Sign LanguageUsing Neuro-fuzzy Systems. Artificial Intelligence. 2001, 133(1-2):117–138
15 A. Shamaie, A. Sutherlan. Accurate Recognition of Large Number of HandGesture. The Second Iranian Conference on Machine Vision and Image Pro-cessin. Iran, 2003
16 W. Hai, A. Sutherland. Irish Sign Language Recognition Using Pca, Multi-scaleTheory, and Discrete Hidden Markov Models. Proceedings of the Irish MachineVision Conference. 2004:66–73
17 G. Awad, J. Han, A. Sutherland. A Unified System for Segmentation and Track-ing of Face and Hands in Sign Language Recognition. Proceedings - Interna-tional Conference on Pattern Recognition. Hong Kong, 2006:239–242
18 T. Shanableh, K. Assaleh. Two Tier Feature Extractions for Recognition ofIsolated Arabic Sign Language Using Fisher’s Linear Discriminants. IEEE In-ternational Conference on Acoustics, Speech and Signal Processing. Honolulu,HI, 2007
19 T. Shanableh, K. Assaleh, M. Al-Rousan. Spatio-temporal Feature-extractionTechniques for Isolated Gesture Recognition in Arabic Sign Language. IEEETransactions on Systems Man and Cybernetics Part B-Cybernetics. 2007,37(3):641–650
20 H. Haberdar, S. Albayrak. A Two-stage Visual Turkish Sign Language Recog-nition System Based on Global and Local Features, 2006
21 M. A. Guvensan, M. A. Guvensan, H. Haberdar. Detection and Tracking ofFace and Facial Features for Recognition of Turkish Sign Language. H. Haber-dar, (Editor) Signal Processing and Communications Applications. IEEE 15th.2007:1–4
22 E. J. Holden, G. Lee, R. Owens. Automatic Recognition of Colloquial Aus-tralian Sign Language. Proceedings - IEEE Workshop on Motion and VideoComputing. 2005:183–188
23 T. Takahashi, F. Kishino. A Hand Gesture Recognition Method and its Appli-cation. Systems and Computers in Japan. 1992, 23(3):11
24 K. Murakami, H. Taguchi. Gesture Recognition Using Recurrent Neural Net-works. CHF91 Human Factors in Computing Systems. New York, 1991:237–24225 C. Lee, Y. S. Xu. Online, Interactive Learning of Gestures for Human/robotInterfaces. IEEE International Conference on Robotics and Automation, Pro-ceedings, Vols 1-4. 1996:2982–2987
26 J. Triesch, C. Malsburg. Robust Classification of Hand Postures Against Com-plex Background. IEEE International Conference on Automatic Face and Ges-ture Recognition. 1996
27 R. Lockton, A. W. Fitzgibbon. Real-time Gesture Recognition Using Determin-istic Boosting. Proceedings of British Machine Vision Conference. 2002
28 L. Gupta, S. Ma. Gesture-based Interaction and Communication: AutomatedClassification of Hand Gesture Contours. IEEE Transactions on Systems, Manand Cybernetics Part C: Applications and Reviews. 2001, 31(1):114–120
29 S. Fels, G. Hinton. Glove-talkii: A Neural Network Interface Which MapsGestures to Parallel Formant Speech Synthesizer Controls. 1998, 9(1):205–212
30 M. Waldron, S. Kim. Isolated Asl Sign Recognition System for Deaf Persons.IEEE Transaction on Rehabilitation Engineering. 1995, 3(3):261–271
31 H. Sagawa, M. Takeuchi, M. Ohki. Description and Recognition Methods forSign Language Based on Gesture Components. International Conference onIntelligent User Interfaces. 1997:97–104
32 J. L. Hernandez-Rebollar, N. Kyriakopoulos, R. W. Lindeman. A New In-strumented Approach for Translating American Sign Language Into Sound andText. IEEE International Conference on Automatic Face and Gesture Recogni-tion. 2004:547–552
33 Y. Cui, J. Weng. Appearance-based Hand Sign Recognition from Intensity Im-age Sequences. Computer Vision and Image Understanding. 2000, 78(2):157–17634 C. Vogler, D. Metaxas. Asl Recognition Based on a Coupling between Hmmsand 3d Motion Analysis. Proceedings of the IEEE International Conference onComputer Vision. 1998:363–369
35 R. Bowden, D. Windridge, T. Kadir, et al. A Linguistic Feature Vector for theVisual Interpretation of Sign Language. European Conference on ComputerVision. 2004:390–401
36 M. H. Yang, N. Ahuja, M. Tabb.”extraction of 2-d Motion Trajectories andits Application to Hand Gesture Recognition”. IEEE Transactions on PatternAnalysis and Machine Intelligence. 2002, 29(8):1062–1074
37 H. Matsuo, S. Igi, S. Lu, et al. The Recognition Algorithm with Non-contactfor Japanese Sign Language Using Morphological Analys. The InternationalGesture Workshop (GW’97). Germany, 1997:273–284
38 J. Deng, H. Ts. A Two-step Approach Based on Pahmm for the Recognitionof as. The Fifth Asian Conference on Computer Vision. Melbourne, Australia,2002:126–13
39 H. Sagawa, M. Takeuchi. A Method for Recognizing a Sequence of Sign Lan-guage Words Represented in a Japanese Sign Language Sentence. IEEE In-ternational Conference on Automatic Face and Gesture Recognition. France,2000:434–439
40 H. Sagawa, M. Takeuchi. Development of an Information Kiosk with a SignLanguage Recognition System. Proceedings of the Conference on UniversalUsability. 2000:149–150
41 H. Sagawa, M. Takeuchi. The Structure and Valuation of an Information Kioskwith a Sign-language Recognition System. International Conference on Intelli-gent User Interfaces. USA, 2001
42 R. H. Liang, M. Ouhyoung. A Real-time Continuous Gesture Recognition Sys-tem for Sign Language. IEEE International Conference Proceedings on Auto-matic Face and Gesture Recognition. 1998:558–567
43 T. Starner, A. Pentland. Real-time American Sign Language Recognition fromVideo Using Hidden Markov Models. Proceedings of the IEEE InternationalConference on Computer Vision. 1995:265–270
44 B. Bauer, H. Hienz, K. F. Kraiss. Video-based Continuous Sign LanguageRecognition Using Statistical Methods. Proceedings - International Conferenceon Pattern Recognition. 2000, 15:463–466
45 J. B. Kim, K. H. Park, W. C. Bang, et al. Continuous Gesture RecognitionSystem for Korean Sign Language Based on Fuzzy Logic and Hidden MarkovModel. Proceedings of IEEE International Conference on Fuzzy Systems.2002:1574–1579
46 V. I. Pavlovic, R. Sharma, T. S. Huang. Visual Interpretation of Hand Gesturesfor Human-computer Interaction: A Review. IEEE Transactions on PatternAnalysis and Machine Intelligence. 1997, 19(7):677–695
47 Y. Wu, T. S. Huang. Vision-based Gesture Recognition: A Review. Gesture-Based Communication in Human-Computer Interaction (A. Braffort, R. Gherbi,S. Gibet, J. Richardson, and D. Teil, Eds.), Lecture Notes in Artificial Intelli-gence. 1999, 1739:103–115
48 S. C. W. Ong, S. Ranganath. Automatic Sign Language Analysis: A Survey andthe Future Beyond Lexical Meaning. IEEE Transactions on Pattern Analysisand Machine Intelligence. 2005, 27(6):873–891
49 A. Erol, G. Bebis, M. Nicolescu, et al. Vision-based Hand Pose Estimation: AReview. Computer Vision and Image Understanding. 2007, 108(1-2):52–73
50 U. von Agris, J. Zieren, U. Canzler, et al. Recent Developments in Visual SignLanguage Recognition. Universal Access in the Information Society. 2008,6(4):323–362
51 W. Stokoe. Sign Language Structure: An Outline of the Visual Communica-tion System of the American Deaf. Studies in Linguistics, Occasional papers 8(revised 1978), University of Buffalo: Linstok Press, 1960
52 C. Vogler, S. Goldenstein. Facial Movement Analysis in Asl. Universal Accessin the Information Society. 2008, 6(4):363–374
53 J.-W. Deng, H. Tsui. A Novel Two-layer Pca/mda Scheme for Hand PostureRecognition. International Conference on Pattern Recognition. 2002:283–286
54 S. Akyol, P. Alvarado. Finding Relevant Image Content for Mobile Sign Lan-guage Recognition. Proceedings - IASTED International Conference on SignalProcessing, Pattern Recognition and Application. 2001:48–52
55 K. Imagawa, S. Lu, S. Igi. Color-based Hand Tracking System for Sign Lan-guage Recognition. IEEE International Conference on Automatic Face and Ges-ture Recognition. 1998:462–467
56 K. Imagawa, H. Matsuo, R. I. Taniguchi, et al. Recognition of Local Features forCamera-based Sign Language Recognition System. Proceedings - InternationalConference on Pattern Recognition. 2000, 15(4):849–853
57 J. C. Terrillon, A. Pilpre, Y. Niwa, et al. Robust Face Detection and Hand Pos-ture Recognition in Color Images for Human-machine Interaction. Proceedings- International Conference on Pattern Recognition. 2002, 16(1):204–209
58 Y. Cui, J. Weng. A Learning-based Prediction-and-verification SegmentationScheme for Hand Sign Image Sequence. IEEE Transactions on Pattern Analysisand Machine Intelligence. 1999, 21(8):798–804
59 C. L. Huang, W. Y. Huang. Sign Language Recognition Using Model-basedTracking and a 3d Hopfield Neural Network. Machine Vision and Applications.1998, 10(5-6):292–307
60 C. Huang, S. Jeng. A Model-based Hand Gesture Recognition System. MachineVision and Applications. 2001, 12(5):243–258
61 F. Chen, C. Fu, C. Huang. Hand Gesture Recognition Using a Real-time Track-ing Method and Hidden Markov Models. Image and Vision Computing. 2003,21(8):745–758
62 N. Tanibata, N. Shimada, Y. Shirai. Extraction of Hand Features for Recognitionof Sign Language Words. Proceedings - International Conference on VisionInterface. 2002:391–398
63 M. Assan, K. Grobel. Video-based Sign Language Recognition Using HiddenMarkov Models. The International Gesture Workshop. 1997:97–109
64 S. Tamura, S. Kawasaki. Recognition of Sign Language Motion Images. PatternRecognition. 1988, 21(4):343–353
65 J. Sherrah, S. Gong. Resolving Visual Uncertainty and Occlusion ThroughProbabilistic Reasoning. Proceedings of British Machine Vision Conference.2000:252–261
66 J. Zieren, N. Unger, S. Akyol. Hands Tracking from Frontal View for Vision-based Gesture Recognition. Proc. 24th DAGM Symp. 2002:531–539
67 A. Downton, H. Drouet. Model-based Image Analysis for Unconstrained Hu-man Upper-body Motion. Proceedings - International Conference on ImageProcessing and Its Applications. 1992:274–277
68 C. Vogler, D. Metaxas. Adapting Hidden Markov Models for Asl Recognitionby Using Three-dimensional Computer Vision Methods. IEEE InternationalConference on Systems, Man and Cybernetics. 1997, 1:156–161
69 T. Kobayashi, S. Haruyama. Partly-hidden Markov Model and its Applicationto Gesture Recognition. Proceedings - International Conference on Acoustics,Speech and Signal Processing. 1997, 4:3081–3084
70 Y. Wu, T. S. Huang. View-independent Recognition of Hand Postures. IEEEInternational Conference on Computer Vision and Pattern Recognition. 2000,2:88–94
71 M. Handouyahia, D. Ziou, S. Wang. Sign Language Recognition UsingMoment-based Size Functions. Proceedings - International Conference on Vi-sion Interface. 1999:210–216
72 E. Holden, R. Owens. Visual Sign Language Recognition. Proceedings - Inter-national Workshop on Theoretical Foundations of Computer Vision. 2000:270–28773 C. Nolker, H. Ritter. Visual Recognition of Continuous Hand Postures. IEEETransactions on Neural Networks. 2002, 13(4):983–994
74 J. Rehg, T. Kanade. Visual Tracking of High Dof Articulated Structures: AnApplication to Human Hand Tracking. European Conference on Computer Vi-sion. 1994, 2:35–46
75 H. Fillbrandt, S. Akyol, K. F. Kraiss. Extraction of 3d Hand Shape and Posturefrom Image Sequences for Sign Language Recognition. IEEE InternationalWorkshop on Analysis and Modeling of Face and Gestures. 2003:181–186
76 H. Hienz, K. Grobel, G. Offner. Real-time Hand-arm Motion Analysis Using aSingle Video Camera. IEEE International Conference on Automatic Face andGesture Recognition. 1996:323–327
77 A. Sutherland. Real-time Video-based Recognition of Sign Language Ges-tures Using Guided Template Matching. The International Gesture Workshop.1996:31–38
78 J. Wu, W. Gao. The Recognition of Finger-spelling for Chinese Sign Language.The International Gesture Workshop. 2001:96–100
79 M. Su. A Fuzzy Rule-based Approach to Spatio-temporal Hand Gesture Recog-nition. IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applica-tion Rev. 2000, 30(2):276–281
80 J. Bridle. Alphanets: A Recurrent‘neural’Network Architecture with a HiddenMarkov Model Interpretation. Speech Communication. 1990, 9(1):83–92
81 E. Trentin, M. Gori. A Survey of Hybrid Ann/hmm Models for AutomaticSpeech Recognition. Neurocomputing. 2001, 37(1/4):91–126
82 G. L. Fang, W. Gao. A Srn/hmm System for Signer-independent ContinuousSign Language Recognition. IEEE International Conference on Automatic Faceand Gesture Recognition. 2002:312–317
83 W. Gao, G. Fang, D. Zhao, et al. Transition Movement Models for Large Vocab-ulary Continuous Sign Language Recognition. IEEE International Conferenceon Automatic Face and Gesture Recognition. Seoul, 2004:553–558
84 C. Vogler. American Sign Language Recognition: Reducing the Complexity ofthe Task with Phoneme-based Modeling and Parallel Hidden Markov Models.Phd thesis, University of Pennsylvania. 2003
85 W. Gao, J. Ma, J. Wu, et al. Sign Language Recognition Based on Hmm/ann/dp.International Journal of Pattern Recognition and Artificial Intelligence. 2000,14(5):587–602
86 M. Kadous. Machine Recognition of Auslan Signs Using Powergloves: To-wards Large-lexicon Recognition of Sign Language. Proc. Workshop Integra-tion of Gestures in Language and Speech. 1996:165–174
87 P. Vamplew, A. Adams. Recognition of Sign Language Gestures Using NeuralNetworks. Australian Journal on Intelligence Information Processing Systems.1998, 5(2):94–102
88 S. C. W. Ong, S. Ranganath. Deciphering Gestures with Layered Meaningsand Signer Adaptation. IEEE International Conference on Automatic Face andGesture Recognition. Seoul, 2004:559–564
89祝远新,徐光祐,黄浴.基于表观的动态孤立手势识别.软件学报. 2000,11(1):54–61
90任海兵,祝远新,徐光祐,等.连续动态手势的时空表观建模及识别.计算机学报. 2000,23(8):824–828
91邹伟.中国手语单手词汇识别方法和技术研究.中科院自动化所博士学位论文. 2003
92 C. L. Wang, W. Gao, S. G. Shan. An Approach Based on Phonemes to Large Vo-cabulary Chinese Sign Language Recognition. IEEE International Conferenceon Automatic Face and Gesture Recognition. 2002:411–416
93 L. G. Zhang, Y. Chen, G. Fang, et al. A Vision-based Sign Language Recog-nition System Using Tied-mixture Density Hmm. International Conference onMultimodal Interfaces. 2004:198–204
94张良国,高文,陈熙霖,等.面向中等词汇量的中国手语视觉识别系统.计算机研究与发展. 2006,43(3):476–482
95易克初,田斌.语音信号处理.国防工业出版社, 2000
96 J. Q. Wu, W. Gao. A Fast Sign Word Recognition Method for Chinese SignLanguage. Advances in Multimodal Interfaces - ICMI. 2000, 1948:599–606
97 P. Brown, V. Pietra, P. deSouza, et al. Class-based N-gram Models of NaturalLanguage. Computational Linguistics. 1992, 18(4):467–479
98 M. Jardino. Multilingual Stochastic N-gram Class Language Models. IEEEInternational Conference on Acoustics, Speech and Signal Processing. Atlanta,1996:161–163
99 L. Bahl, P. Brown, P. DeSouza, et al. A Tree-based Language Model for Natu-ral Language Speech Recognition. IEEE Transactions on Information Theory,Speech and Signal Processing. 1989, 37:1001–1008
100 J. Foote. Decision-tree Probability Modeling for Hmm Speech Recognition.Phd thesis, Brown University. 1994
101 M. Siu, M. Ostendorf. Variable N-grams and Extensions for ConversationalSpeech Language Modeling. IEEE Transactions on Speech and Audio Process-ing. 2000, 8(1):63–75
102 S. D. Pietra, V. D. Pietra, R. Mercer, et al. Adaptive Language Modeling UsingMinimum Discriminant Estimation. The Internation Conference on Acoustics,Speech and Signal Processing. San Francisco, 1992
103 S. D. Pietra, V. D. Pietra, J. Lafferty. Inducing Features of Random Fields. IEEETransactions on Pattern Analysis and Machine Intelligence. 1997, 19(4):380–393104 R. Rosenfeld. A Maximum Entropy Approach to Adaptive Statistical Lan-guage Model for Speech Recognition. Computer Speech and Language. 1996,10(3):187–228
105 F. Jelinek, J. Lafferty. Basic Methods of Probabilistic Context Free Gram-mars. Technical Report RC 16374 (72684), IBM, Yorktown Heights, New York10598. 1990
106李勇,高文,姚鸿勋.基于颜色手套的中国手指语字母的动静态识别.计算机工程与应用. 2002,38(17):55–58
107 V. Athitsos, J. Alon, S. Sclaroff, et al. Boostmap: A Method for Efficient Ap-proximate Similarity Rankings. IEEE International Conference on ComputerVision and Pattern Recognition. 2004:268–275
108 R. Hartley, A. Zisserman. Multiple View Geometry in Computer Vision. Cam-bridge University Press, 2003
109 H. C. Longuet-Higgins. A Computer Algorithm for Reconstructing a Scenefrom Two Projections. Nature. 1981, 293(10):133–135
110 Q. Luong, O. D. Faugeras. Determining the Fundamental Matrix with Planes:Unstability and New Algorithms. IEEE International Conference on ComputerVision and Pattern Recognition. New-York, 1993:489–494
111 C. Rao, A. Gritai, M. Shah, et al. View-invariant Alignment and Matching ofVideo Sequences. Proceedings of the IEEE International Conference on Com-puter Vision. 2003, 2:939–945
112 A. Gritai, Y. Sheikh, M. Shah. On the Use of Anthropometry in the InvariantAnalysis of Human Actions. Proceedings - International Conference on PatternRecognition. 2004:923–926
113 G. Shafer. A Mathematical Theory of Evidence. Princeton, New Jersey: P. U.Press, 1976
114 M. A. Fischler, R. C. Bolles. Random Sample Consensus: A Paradigm forModel Fitting with Applications to Image Analysis and Automated Cartogra-phy. Communications of the ACM. 1981, 24(6):381–395
115 S. M. Smith, J. M. Brady. Susan. a New Approach to Low Level Image Pro-cessing. International Journal of Computer Vision. 1997, 23(1):45–78
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |