融合深度数据的人机交互手势识别研究
|
摘要
基于图像信息的生物特征识别是近些年来计算机视觉研究中的一个重要领域,其中针对人类的各种生物特征的识别是该领域的主要研究内容,相关研究成果多用于自然人机交互、虚拟现实和智能视频监控等方面。进一步地,人类的手势识别研究是人类的生物特征识别中重要的研究内容,它主要从图像数据中分割、跟踪和识别出不同的手势,最终对其加以描述和理解。然而,由于人手的个体差异性,加之其复杂的各种形变,再加上手势在空间和时间上的变化性,以及视觉问题与生俱来的不适定性,这些困难和原因使手势识别成为了一个非常具有挑战性的研究领域。
经典的手势识别研究一般包括手势分割、手势跟踪、手势识别等三个阶段,这三个阶段分别对应于计算机视觉研究的图像分析和图像理解两个研究层次。其中手势分割属于图像分析层次,这一阶段把图像中属于手势的像素点划分标识出来,这是整个研究的起点也是最为重要的部分,其结果的优劣会直接影响到后续的研究阶段。手势跟踪也属于图像分析层次,它对图像序列的每一帧图像中属于手势的像素点进行连续的定位和标注。手势识别则属于图像理解层次,它首先将海量的图像数据经过表示与描述成为一系列特征或特征组合,而后在特征空间中对其中的特征点进行分类,最终实现手势的识别。
另一方面,多模态数据融合理论认为单一种类传感器数据只能获得被测物体的不完备信息并且较易受环境影响,而多模态信息融合将多种传感器数据进行组合,可以提高系统的可靠性。基于此,本文在传统视觉数据的基础上引入了深度数据,在深度与图像数据融合的基础上分别研究了手势的分割、跟踪和识别三个阶段的算法。
基于动态深度阈值的手势分割算法。首先基于MCG-Skin(A BenchMark Human Skin Database,中国科学院计算技术研究所多媒体计算课题组)数据库建立肤色的高斯模型,并获得模型的均值与方差；其次根据深度信息建立人体包括手势部分的深度的高斯混合模型；再次根据深度高斯模型可以得到粗略的动态深度阈值,从而划分出包括手势在内的部分图像；最后将这部分图像输入第一步得到的肤色高斯模型,即可得出每个像素点与肤色的相似度,进而得到肤色相似度图像,然后对该图像应用Otsu's算法得到手势分割结果。通过多个实验从不同的角度对手势分割算法的可用性进行了检验。
基于权重漂移重采样的手势跟踪算法。首先建立相对深度直方图及其相似性概念,以此作为手势跟踪的模板；其次针对传统粒子重采样算法中的粒子退化问题,以后验概率密度梯度非递减为原则进行了粒子重采样,在重采样的过程中不删除粒子,更能保证粒子的多样性。通过多个实验从不同的角度对手势跟踪算法的可用性进行了检验。
基于相对径向距离的手势识别算法。针对超球支持向量机在超球相交时类别划分可能出现的问题,提出了不仅基于绝对距离,还要同时基于相对径向距离的超球支持向量机,通过特征点到超球球心的距离与超球半径之比来确定特征点的归属,即满足这个值最小的超球为该特征点的最终归属。通过多个实验从不同的角度对手势识别算法的可用性进行了检验。
最后建立了一个面向手势识别的手势图像数据集合,并在上述研究的基础上,设计开发了基于Matlab的手势识别工具箱,实现了手势的分割、跟踪和识别等功能。
Image based biometric receives more and more attentions in recent years. Human biometric is one of the most important parts in biometric, which can be used widely in natural human computer interaction, intelligent video surveillance and virtual reality. Further, the research on human hand posture and gesture recognition belongs to the research on human biometric, that segments, tracks and recognizes series of hand gestures and understands the meaning of the gestures finally. However, due to individual differences among difference hands, intricate deformation, spatio-temporal variability and the inherent ill-posedness of visual problems, hand gesture recognition becomes highly challenging.
Classic hand recognition research is composed of three stages:hand segmentation, tracking and recognition. The three stages correspond to image analysis and image understanding level in computer vision. The hand segmentation stage belongs to image analysis level, and it labels the hand(s) pixels in images. This stage is the start point and the most important part, whose results will have the direct influence on the following stages. The hand tracking stage also belongs to image analysis level, and it labels hand(s) pixels in each frame in image sequence. The hand recognition stage belongs to image understanding level, and it represents the image into series image eigenvectors and classifies these eigenvectors in feature space. In this way, hand gestures will be classified and recognized.
On the other hand, multi-modal data fusion field believes that single type of sensor can only acquire incomplete Information of measured object and have environmental instability, and a variety of sensors data can improve the reliability of the system. Based on these views, depth date is introduced into visual data. The hand segmentation, tracking and recognition algorithms will be studied based on visual and depth data fusion.
Dynamic depth threshold based hand gestures segmentation algorithm. First of all, the skin gaussian model (mean and variance) is constructed by using MCG-Skin. Secondly, the body depth gaussian mixture model is constructed according to the depth information of the body. Thirdly, the rough dynamic depth threshold can be get, with which hand gestures can be labeled roughly. Lastly, the skin similarity of each pixel can be get by putting the rough hand gestures image into the skin Gaussian model, and Otsu's algorithm is applied on the skin similarity image to acquire the hand gesture segmentation result. The availability of the algorithm is investigated by different perspective and experiments.
Weight shift resampling based hand gestures tracking algorithm. Firstly, Relative depth histogram and its similarity measure are proposed, which is the hand gesture template for tracking. Secondly, to be aimed at particle degradation in traditional particle resampling algorithm, a new resampling method is proposed that resamples particles by non-decreasing posterior probability density gradient. This method do not delete particle in the process of resampling which can keep the diversity of the particles. The availability of the algorithm is investigated by different perspective and experiments.
Relative radial distance based hand gestures recognition algorithm. To be against category problem when hypersphere support vector machines intersect the hypersphere, the relative radial distance based is proposed. This method determines the category of feature points by the ratio between the distance feature points to the center of the hypersphere and hypersphere radius. The feature points belong to the hypersphere which make the ratio minimum. The availability of the algorithm is investigated by different perspective and experiments.
Finally, a hand recognition oriented image dataset is constructed. Furthermore, On the basis of the above research, a hand recognition toolbox based on Matlab is designed and implemented which can segment, track and recognize hand gestures.
经典的手势识别研究一般包括手势分割、手势跟踪、手势识别等三个阶段,这三个阶段分别对应于计算机视觉研究的图像分析和图像理解两个研究层次。其中手势分割属于图像分析层次,这一阶段把图像中属于手势的像素点划分标识出来,这是整个研究的起点也是最为重要的部分,其结果的优劣会直接影响到后续的研究阶段。手势跟踪也属于图像分析层次,它对图像序列的每一帧图像中属于手势的像素点进行连续的定位和标注。手势识别则属于图像理解层次,它首先将海量的图像数据经过表示与描述成为一系列特征或特征组合,而后在特征空间中对其中的特征点进行分类,最终实现手势的识别。
另一方面,多模态数据融合理论认为单一种类传感器数据只能获得被测物体的不完备信息并且较易受环境影响,而多模态信息融合将多种传感器数据进行组合,可以提高系统的可靠性。基于此,本文在传统视觉数据的基础上引入了深度数据,在深度与图像数据融合的基础上分别研究了手势的分割、跟踪和识别三个阶段的算法。
基于动态深度阈值的手势分割算法。首先基于MCG-Skin(A BenchMark Human Skin Database,中国科学院计算技术研究所多媒体计算课题组)数据库建立肤色的高斯模型,并获得模型的均值与方差；其次根据深度信息建立人体包括手势部分的深度的高斯混合模型；再次根据深度高斯模型可以得到粗略的动态深度阈值,从而划分出包括手势在内的部分图像；最后将这部分图像输入第一步得到的肤色高斯模型,即可得出每个像素点与肤色的相似度,进而得到肤色相似度图像,然后对该图像应用Otsu's算法得到手势分割结果。通过多个实验从不同的角度对手势分割算法的可用性进行了检验。
基于权重漂移重采样的手势跟踪算法。首先建立相对深度直方图及其相似性概念,以此作为手势跟踪的模板；其次针对传统粒子重采样算法中的粒子退化问题,以后验概率密度梯度非递减为原则进行了粒子重采样,在重采样的过程中不删除粒子,更能保证粒子的多样性。通过多个实验从不同的角度对手势跟踪算法的可用性进行了检验。
基于相对径向距离的手势识别算法。针对超球支持向量机在超球相交时类别划分可能出现的问题,提出了不仅基于绝对距离,还要同时基于相对径向距离的超球支持向量机,通过特征点到超球球心的距离与超球半径之比来确定特征点的归属,即满足这个值最小的超球为该特征点的最终归属。通过多个实验从不同的角度对手势识别算法的可用性进行了检验。
最后建立了一个面向手势识别的手势图像数据集合,并在上述研究的基础上,设计开发了基于Matlab的手势识别工具箱,实现了手势的分割、跟踪和识别等功能。
Image based biometric receives more and more attentions in recent years. Human biometric is one of the most important parts in biometric, which can be used widely in natural human computer interaction, intelligent video surveillance and virtual reality. Further, the research on human hand posture and gesture recognition belongs to the research on human biometric, that segments, tracks and recognizes series of hand gestures and understands the meaning of the gestures finally. However, due to individual differences among difference hands, intricate deformation, spatio-temporal variability and the inherent ill-posedness of visual problems, hand gesture recognition becomes highly challenging.
Classic hand recognition research is composed of three stages:hand segmentation, tracking and recognition. The three stages correspond to image analysis and image understanding level in computer vision. The hand segmentation stage belongs to image analysis level, and it labels the hand(s) pixels in images. This stage is the start point and the most important part, whose results will have the direct influence on the following stages. The hand tracking stage also belongs to image analysis level, and it labels hand(s) pixels in each frame in image sequence. The hand recognition stage belongs to image understanding level, and it represents the image into series image eigenvectors and classifies these eigenvectors in feature space. In this way, hand gestures will be classified and recognized.
On the other hand, multi-modal data fusion field believes that single type of sensor can only acquire incomplete Information of measured object and have environmental instability, and a variety of sensors data can improve the reliability of the system. Based on these views, depth date is introduced into visual data. The hand segmentation, tracking and recognition algorithms will be studied based on visual and depth data fusion.
Dynamic depth threshold based hand gestures segmentation algorithm. First of all, the skin gaussian model (mean and variance) is constructed by using MCG-Skin. Secondly, the body depth gaussian mixture model is constructed according to the depth information of the body. Thirdly, the rough dynamic depth threshold can be get, with which hand gestures can be labeled roughly. Lastly, the skin similarity of each pixel can be get by putting the rough hand gestures image into the skin Gaussian model, and Otsu's algorithm is applied on the skin similarity image to acquire the hand gesture segmentation result. The availability of the algorithm is investigated by different perspective and experiments.
Weight shift resampling based hand gestures tracking algorithm. Firstly, Relative depth histogram and its similarity measure are proposed, which is the hand gesture template for tracking. Secondly, to be aimed at particle degradation in traditional particle resampling algorithm, a new resampling method is proposed that resamples particles by non-decreasing posterior probability density gradient. This method do not delete particle in the process of resampling which can keep the diversity of the particles. The availability of the algorithm is investigated by different perspective and experiments.
Relative radial distance based hand gestures recognition algorithm. To be against category problem when hypersphere support vector machines intersect the hypersphere, the relative radial distance based is proposed. This method determines the category of feature points by the ratio between the distance feature points to the center of the hypersphere and hypersphere radius. The feature points belong to the hypersphere which make the ratio minimum. The availability of the algorithm is investigated by different perspective and experiments.
Finally, a hand recognition oriented image dataset is constructed. Furthermore, On the basis of the above research, a hand recognition toolbox based on Matlab is designed and implemented which can segment, track and recognize hand gestures.
引文
[1]Association for Computing Machinery, Special Interest Group on Computer-Human Interaction, Curriculum Development Group. ACM SIGCHI Curricula for Humancomputer Interaction[R]. New York:ACM,2009:5-27.
[2]Joshua Blake. Natural User Interfaces in.NET [M]. New York:Manning,2013:2-42.
[3]D. McNeill. Language and gesture [M]. Cambridge:Cambridge University Press,2000:11-25.
[4]沙亮.基于无标记全手势视觉的人机交互技术[D].清华大学,2010.
[5]Vladimir I. Pavlovic, Rajeev Sharma, Thomas S. Huang Visual interpretation of hand gestures for human-computer interaction:A review [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(7):677-695.
[6]任海兵,祝远新,徐光佑等.基于视觉手势识别的研究[J].电子学报,2000,28(2)：118-121.
[7]X. Zabulisy, H. Baltzakisy, A. Argyros. Vision-based hand gesture recognition for human-computer interaction[C].32nd International Conference on Information Technology Interfaces (ITI),2010,289-294.
[8]韩崇昭.信息融合理论与应用[J].中国基础科学,2000,7：14-18.
[9]Franklin E White. Data fusion lexicon [G]. DTIC Document,1991.
[10]戎翔.多模态数据融合的研究[D].南京邮电大学,2012.
[11]Min C. Shin, Kyong I. Chang, Leonid V. Tsap. Does Colorspace Transformation Make Any Difference on Skin Detection[C]? The Sixth IEEE workshop on Applications of Computer Vision (WACV'02),2002,275-279.
[12]Lei Huang, Tian Xia, Yongdong Zhang, et al. Human Skin Detection in Images by MSER Analysis[C]. IEEE The International Conference on Image Processing (ICIP),2011,1281-1284.
[13]Shipeng Xie, Jing Pan. Hand Detection Using Robust Color Correction and Gaussian Mixture Model[C].2011 Sixth International Conference on Image and Graphics (ICIG),2011,553-557.
[14]A. Mittal, A. Zisserman, P. H. S. Torn Hand detection using multiple proposals[C]. British Machine Vision Conference,2011,1-11.
[15]Chao Sui, Ngai Ming Kwok, Tianran Ren. A Restricted Coulomb Energy (RCE) Neural Network System for Hand Image Segmentation[C]. Canadian Conference on Computer and Robot Vision, 2011,270-277.
[16]V. Spruyt, A. Ledda, and S. Geerts. Real-time multi-colourspace hand segmentation[C]. IEEE The International Conference on Image Processing (ICIP),2010,3117-3120.
[17]Zhan Song, Hanxuan Yang, Yanguo Zhao, et al. Hand Detection and Gesture Recognition Exploit Motion Times Image in Complicate Scenarios[C]. The 6th international conference on Advances in visual computing,2010,628-636.
[18]Qi Wang, Xilin Chen, Wen Gao. Skin Color Weighted Disparity Competition for Hand Segmentation from Stereo Camera[C]. British Machine Vision Conference,2010,66.1-66.11.
[19]Jean-Christophe Terrillon, Hideo Fukamachi, Shigeru Akamatsu, et al. Comparative performance of different skin chrominance models and chrominance spaces for the automatic detection of human faces in color images[C]. IEEE International Conference on Automatic Face and Gesture Recognition,2000,54-61.
[20]Turgay Celik, Tardi Tjahjadi. Crowley. Adaptive colour constancy algorithm using discrete wavelet transform [J]. Computer Vision and Image Understanding,2012,116(4):561-571.
[21]Gary R. Bradski. A Data-Driven Approach to Hue-Preserving Color-Blending [J]. IEEE Transaction on Visualization and Computer Graphics,2012,18(12):2122-2129.
[22]Archana S. Ghotkar, Gajanan K. Kharate. Hand Segmentation Techniques to Hand Gesture Recognition for Natural Human Computer Interaction [J]. International Journal of Human Computer Interaction,2012,29(3):15-25.
[23]Alexandre R.J. Francois, Gerard G. Medioni. Adaptive color background modeling for real-time segmentation of video streams[C]. The International Conference on Imaging Science, Systems, and Technology,1999,227-232.
[24]Y Shen, SK Ong, AYC Nee. Vision-based hand interaction in augmented reality environment [J]. International Journal of Human Computer Interaction,2011,27(6):523-544.
[25]Qiong Xu, Hengyong Yu, James Bennett, et al. Image Reconstruction for Hybrid True-Color Micro-CT [J]. IEEE Transactions on Biomedical Engineering,2012,59(6):1711-1719.
[26]Saxe David, Foulds Richard. Evaluating a color-based active basis model for object recognition [J]. Computer Vision and Image Understanding,2012,116(11):1111-1120.
[27]Chai Douglas, Ngan King N. Locating the facial region of a head and shoulders color image[C]. The Third IEEE International Conference on Automatic Face and Gesture Recognition,1998, 124-129.
[28]Yannis Avrithis, Yannis Kalantidis. Approximate Gaussian Mixtures for Large Scale Vocabularies [C]. The European Conference on Computer Vision,2012,1-14.
[29]Argyros Antonis, Lourakis Manolis. Vision-based interpretation of hand gestures for remote control of a computer mouse[J]. Computer Vision in Human-Computer Interaction,2006, 3979:40-51.
[30]Albiol Alberto, Torres Luis, Delp Edward J. Optimum Color Spaces of Skin Detection[C]. The International Conference on Image Processing,2001,122-124.
[31]徐战武.静态图像肤色检测研究[D].浙江大学.2006.
[32]Yookyung Kim, M.S. Nadar, A. Bilgin. Wavelet-Based Compressed Sensing Using a Gaussian Scale Mixture Model [J]. IEEE Transaction on Image Process,2012,21(6):3102-3108.
[33]Yingyue Zhou, Zhongfu Ye, Yao Xiao. A restoration algorithm for images contaminated by mixed Gaussian plus random-valued impulse noise [J]. Journal of Visual Communication and Image Representation,2013,24(3):283-294.
[34]Dominguez Sylvia M, Keaton Trish, Sayed, Ali HA. Robust finger tracking method for wearable computer interfacing[C]. The 2001 workshop on Perceptive user interfaces,2001,1-5.
[35]Jones Michael J, Rehg, James M. Statistical color models with application to skin detection [J]. International Journal of Computer Vision,2002,46(1):81-96.
[36]Sigal Leonid, Sclaroff Stan, Athitsos Vassilis. Skin color-based video segmentation under time-varying illumination [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004,26(7):862-877.
[37]Wachs Juan, Kartoun Uri, Stern Helman, et al. Real-time hand gesture telerobotic system using fuzzy c-means clustering[C]. The 5th Biannual World Automation Congress,2002,13:403-409.
[38]Vibhav Vineet, Jonathan Warrell, Paul Sturgess, et al. Improved Initialisation and Gaussian Mixture Pairwise Terms for Dense Random Fields with Mean-field Inference [C]. British Machine Vision Conference,2012,1-11.
[39]Yingyue Zhou, Zhongfu Ye, Yao Xiao. A restoration algorithm for images contaminated by mixed Gaussian plus random-valued impulse noise [J]. Journal of Visual Communication and Image Representation,2013,24(3):283-294.
[40]M. Makitalo, Alessandro Foi. Optimal Inversion of the Generalized Anscombe Transformation for Poisson-Gaussian Noise [J]. IEEE Transaction on Image Process,2013,22(1):91-103.
[41]Wei Liu, Weisi Lin. Additive White Gaussian Noise Level Estimation in SVD Domain for Images [J]. IEEE Transaction on Image Process,2013,22(3):872-883.
[42]M. Staring, Yaonan Wang, D. P. Shamonin, et al. Multiscale Bi-Gaussian Filter for Adjacent Curvilinear Structures Detection with Application to Vasculature Images [J]. IEEE Transaction on Image Process,2013,22(1):174-188.
[43]Takayuki Katsuki, Akira Torii, Masato Inoue. Posterior-Mean Super-Resolution with a Causal Gaussian Markov Random Field Prior [J]. IEEE Transaction on Image Process,2013, 21(7):3182-3193.
[44]Jebara Tony, Russell, Kenneth, Pentland Alex. Gaussian process motion graph models for smooth transitions among multiple actions [J].Computer Vision and Image Understanding,2012, 116(4):500-509.
[45]Suryanarayan Poonam, Subramanian Anbumani and Mandalapu Dinesh. Dynamic Hand Pose Recognition Using Depth Data[C]. The 20th International Conference on Pattern Recognition, 2010,3105-3108.
[46]Oikonomidis Iason, Kyriazis Nikolaos, Argyros Antonis. Efficient model-based 3d tracking of hand articulations using kinect[C]. British Machine Vision Conference,2011,2:1-11.
[47]Etoh Minoru, Tomono Akira, Kishino Fumio. Stereo-based description by generalized cylinder complexes from occluding contours [J]. Systems and Computers in Japan,2007,22(12):79-89.
[48]Yuan Quan, Sclaroff Stan, Athitsos Vassilis. Automatic 2D hand tracking in video sequences[C]. The Seventh IEEE Workshops on Application of Computer Vision,2005,250-256.
[49]Fukunaga Keinosuke, Hostetler Larry. The estimation of the gradient of a density function, with applications in pattern recognition [J]. IEEE Transactions on Information Theory,1975. 21(1):32-40.
[50]Yizong Cheng. Mean shift, mode seeking, and clustering [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1995.17(8):790-799.
[51]Comaniciu Dorin, Meer Peter. Mean Shift:a robust approach toward feature space analysis [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):603-619.
[52]Comaniciu Dorin, Ramesh Visvanathan, Meer Peter. Real-time tracking of non-rigid objects using mean shift[C]. IEEE Conference on Computer Vision and Pattern Recognition,2000,2:142-149.
[53]Collins Robert T. Mean-shift Blob Tracking through Scale Space[C]. IEEE Conference on Computer Vision and Pattern Recognition,2003,2:227-234.
[54]Rui Caseiro, Joao F. Henriques, Pedro Martins, et al. Semi-Intrinsic Mean shift on Riemannian Manifolds [C]. European Conference on Computer Vision,2012,342-355.
[55]Meer Peter. Kernel-based object tracking [J]. IEEE Transactions on pattern analysis and machine intelligence,2003,25(5):564-577.
[56]Chen Hwann-Tzong, Liu Tyng-Luh. Trust-region methods for real-time tracking[C]. The Eighth IEEE International Conference on Computer Vision,2001,2:717-722.
[57]I. Leichter. Mean Shift Trackers with Cross-Bin Metrics [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(4):695-706.
[58]Kurata Takeshi, Okuma Takashi, Kourogi Masakatsu, et al. The hand mouse:Gmm hand-color classication and mean shift tracking[C].IEEE ICCV Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems,2001,119-124.
[59]Hammersley John M, Morton K William. Poor man's Monte Carlo [J]. Journal of the Royal Statistical Society,1954,23-38.
[60]Handschin JE, Mayne David Q. Monte Carlo techniques to estimate the conditional expectation in multi-stage non-linear filtering [J]. International journal of control,1969,9(5):547-559.
[61]Handschin JE. Monte Carlo techniques for prediction and filtering of non-linear stochastic processes [J]. Automatica,1970,6(4):555-563.
[62]Hajime Akashi, Hiromitsu Kumamoto. Construction of discrete time nonlinear filter by Monte Carlo methods with variance-reducing [J]. Systems and Control 19,1975,211-221.
[63]Zaritskii V.S., Svetnik V.B., and Shimelevich L.I. Monte Carlo technique in problems of optimal data processing [J]. Automation and Remote Control 12,1975,95-103.
[64]Hajime Akashi, Hiromitsu Kumamoto. Random sampling approach to state estimation in switching environments [J]. Automatica,1977,13(4):429-434.
[65]Geweke John, Tanizaki Hisashi. On Markov chain Monte Carlo methods for nonlinear and non-Gaussian state-space models [J]. Communications in Statistics-Simulation and Computation, 1999,28(4):867-894.
[66]Geweke John, Tanizaki Hisashi. Note on the sampling distribution for the Metropolis-Hastings algorithm [J]. Communications in Statistics-Theory and Methods,2003,32(4):775-789.
[67]Geweke John, Tanizaki Hisashi. Bayesian estimation of state-space models using the Metropolis-Hastings algorithm within Gibbs sampling [J]. Computational statistics & data analysis,2001,37(2):151-170.
[68]Tanizaki Hisashi. Nonlinear and non-Gaussian state-space modeling with Monte Carlo techniques: A survey and comparative study [J]. Handbook of Statistics,2003,21:871-929.
[69]Smith Adrian FM, Gelfand Alan E. Bayesian statistics without tears:a sampling-resampling perspective [J]. The American Statistician,1992,46(2):84-88.
[70]Gordon Neil J, Salmond David J, Smith Adrian FM. Novel approach to nonlinear/non-Gaussian Bayesian state estimation [J]. lee Proceedings F Radar and Signal Processing,1993, 140(2):107-113.
[71]Doucet Arnaud, De Freitas Nando, Murphy Kevin, et al. Stuart Rao-Blackwellised particle filtering for dynamic Bayesian networks[C]. The Sixteenth conference on Uncertainty in artificial intelligence,2000,176-183.
[72]Su H-T, Wu T-P, Liu H-W, et al. Rao-Blackwellised particle filter based trackbefore-detect algorithm [J]. Signal Processing,2008,2(2):169-176.
[73]Branko Ristic, Sanjeev Arulampalm, Neil James Gordon. Beyond the Kalman filter:Particle filters for tracking applications [M]. Boston:Artech House,2004:35-62.
[74]Doucet Arnaud, Freitas Nando de, Gordon Neil. Sequential Monte Carlo Methods in Practice [G]. New York:Springer-Verlag,2001:17-73.
[75]Waqas Hassan, Nagachetan Bangalore, Philip Birch. An Adaptive sample count particles filter [J]. Computer Vision and Image Understanding,2012,116(12):1208-1222.
[76]Li Bai, Yan Wang. Road tracking using particle filters with partition sampling and auxiliary variables [J]. Computer Vision and Image Understanding,2011,115(10):1463-1471.
[77]Alberto Del Bimbo, Fabrizio Dini. Particle filter-based visual tracking with a first order dynamic model and uncertainty adaptation [J]. Computer Vision and Image Understanding,2011, 115(6):771-786.
[78]Mammen James P, Chaudhuri Subhasis, Agrawal Tushar. Dimensionality reduction using a Gaussian Process Annealed Particle Filter for tracking and classification of articulated body motions [J]. Computer Vision and Image Understanding,2011,115(4):503-519.
[79]Shimin Yin, Jin Hee Na, Jin Young Choi, et al. Hierarchical Kalman-particle filter with adaptation to motion changes for object tracking [J]. Computer Vision and Image Understanding,2011, 115(6):885-900.
[80]Ros German, del Rincon Jesus Martinez, Mateos Gines Garcia. Articulated particle filter for hand tracking[C]. The 21st International Conference on Pattern Recognition,2012,3581-3585.
[81]Yuan Quan, Thangali Ashwin, Ablavsky Vitaly, et al. Multiplicative Kernels:Object Detection, Segmentation and Pose Estimation[C]. IEEE Conference on Computer Vision and Pattern Recognition,2008:1-8.
[82]Marcel Sebastien, Bernier Olivier, Viallet J-E, et al. Hand gesture recognition using Input/Ouput Hidden Markov Models[C]. The Fourth IEEE International Conference on Automatic Face and Gesture Recognition,2000,456-461.
[83]Triesch Jochen, Von Der Malsburg Christoph. Robust Classification of Hand Postures against Complex Backgrounds[C]. The Second IEEE International Conference on Automatic Face and Gesture Recognition,1996,170-175.
[84]Triesch Jochen, Von Der Malsburg Christoph. A System for Person-Independent Hand Posture Recognition against Complex Backgrounds [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2001,23(12):1449-1453.
[85]Marcel Sebastien, Bernier Olivier. Hand posture recognition in a body-face centered space [J]. Gesture-Based Communication in Human-Computer Interaction,1999,97-100.
[86]顾立忠.基于表观的手势识别及人机交互研究[D].上海交通大学,2008.
[87]Mahmoud Othman Selim Mahmoud Elmezain. Hand Gesture Spotting and Recognition Using HMMs and CRFs in Color Image Sequences [D]. OTTO VON GUERICKE UNIVERSITAT MAGDEBURG,2010.
[88]于洋.基于手形特征的静态手势识别[D].河北工业大学,2007.
[89]甘志杰.基于Hu矩和支持向量机的静态手势识别及应用[D].青岛科技大学,2008.
[90]程小鹏.基于特征提取的手势识别技术研究[D].武汉理工大学,2012.
[91]Przemyslaw Glomb, Michal Romaszewski, Sebastian Opozda, et al.Choosing and Modeling the Hand Gesture Database for a Natural User Interface[J]. Gesture and Sign Language in Human-Computer Interaction and Embodied Communication,2012,7206:24-35.
[92]Vladimir N Vapnik. An overview of statistical learning theory [J]. IEEE Transactions on Neural Networks,1999,10(5):988-999.
[93]朱美琳,刘向东,陈世福..用球结构的支持向量机解决多分类问题[J].南京大学学报：自然科学版,2003,39(2)：153-158.
[94]周绍磊,秦亮,史贤俊等.基于模糊机会约束的超球支持向量机[J].华中科技大学学报(自然科学版),2012,40(7)：29-33.
[951 吴石,林连冬,肖飞等.基于多类超球支持向量机的铣削颤振预测方法[J].仪器仪表学报,2012,33(11)：2415-2421.
[96]艾青,赵骥,秦玉平.基于最大间隔最小体积超球支持向量机的多主题分类算法[J].计算机科学,2012,39(8)：237-238.
[97]Iain E. G. Richardson. H.264 and MPEG-4 Video Compression, Video Coding for Next-generation Multimedia [M]. Aberdeen:Wiley,2003:9-24.
[98]Fukunaga Keinosuke, Hostetler Larry. The Estimation of the Gradient of a Density Function, with Applications in Pattern Recognition [J]. IEEE Transactions on Information Theory,1975, 21(1):32-40.
[99]冈萨雷斯.数字图像处理[M].第二版中文版.北京：电子工业出版社,2003：59-112.
[100]Everingham Mark, Van Gool Luc, Williams Christopher K.I, et al. The pascal visual object classes (voc) challenge [J]. International journal of computer vision,2010,88(2):303-338.
[101]Juan Pablo Wachs, Mathias Kolsch, Helman Stern, et al. Vision-based hand-gesture applications [J]. Communication of ACM,2011,54(2):60-71.
[102]Mahmoud Elmezain, Ayoub Al-Hamadi, Appenrodt, Jorg, et al. A Hidden Markov Model-Based Continuous Gesture Recognition System for Hand Motion Trajectory[C]. The 19th International Conference on Pattern Recognition,2008:1-4.
[103]李文生,解梅,姚琼.基于Laguerre正交基神经网络的动态手势识别[J].南京大学学报：自然科学版,2011,47(5)：515-523.
[104]Thangali, A., Nash, J.P., Sclaroff, S., et al. Exploiting phonological constraints for handshape inference in ASL video[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2011:521-528.
[105]Oikonomidis, I., Kyriazis, N., Argyros, A. Full dof tracking of a hand interacting with an object by modeling occlusions and physical constraints[C]. The 13th International Conference on Computer Vision,2011,2088-2095.
[106]Kong WW, Ranganath S. Automatic Hand Trajectory Segmentation and Phoneme Transcription for Sign Language[C]. IEEE International Conference on Automatic Face & Gesture Recognition, 2008,1-6.
[107]Scherr, R.E.Gesture analysis for physics education researchers [J]. Physical Review Special Topics-Physics Education Research,2008,4(1):101-115.
[108]Batmaz, F., Stone, R.G. Using Hand Gestures to Capture Students'Design Rationale[C]. Computers and Advanced Technology in Education,2011,12-20.
[109]Kelly Spencer D, Manning Sarah M, Rodak Sabrina. Gesture gives a hand to language and learning:Perspectives from cognitive neuroscience, developmental psychology and education [J]. Language and Linguistics Compass,2008,2(4):569-588.
[110]Jan Flusser. On the Independence of Rotation Moment Invariants [J]. Pattern Recognition,2000, 33(9):1405-1410.
[111]Jan Flusser, Tomas Suk. Rotation Moment Invariants for Recognition of Symmetric Objects [J]. IEEE Transactions on Image Processing,2006,15(12):3784-3790.
[112]Bourennane S, Fossati C. Comparison of shape descriptors for hand posture recognition in video [J]. Signal, image and video processing,2012,6(1):147-157.
[113]3D moment forms:their construction and application to object identification and positioning [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1989,11(10):1053-1064.
[114]朱继玉,王西颖,王威信等.基于结构分析的手势识别[J].计算机学报,2006,29(12)2130-2137.
[115]Ming-Kuei Hu. Visual pattern recognition by moment invariants [J]. IRE Transactions on Information Theory,1962,8(2):179-187.
[116]Jun Cheng, Can Xie, Wei Bian, et al. DachengFeature fusion for 3D hand gesture recognition by learning a shared hidden space [J]. Pattern Recognition Letters,2012,33(4):476-484.
[117]Yoon Ho-Sub, Soh Jung, Bae Younglae J, et al. Hand Gesture Recognition Using Combined Features of Location [J]. Pattern Recognition,2001,34(7):1491-1501.
[2]Joshua Blake. Natural User Interfaces in.NET [M]. New York:Manning,2013:2-42.
[3]D. McNeill. Language and gesture [M]. Cambridge:Cambridge University Press,2000:11-25.
[4]沙亮.基于无标记全手势视觉的人机交互技术[D].清华大学,2010.
[5]Vladimir I. Pavlovic, Rajeev Sharma, Thomas S. Huang Visual interpretation of hand gestures for human-computer interaction:A review [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(7):677-695.
[6]任海兵,祝远新,徐光佑等.基于视觉手势识别的研究[J].电子学报,2000,28(2)：118-121.
[7]X. Zabulisy, H. Baltzakisy, A. Argyros. Vision-based hand gesture recognition for human-computer interaction[C].32nd International Conference on Information Technology Interfaces (ITI),2010,289-294.
[8]韩崇昭.信息融合理论与应用[J].中国基础科学,2000,7：14-18.
[9]Franklin E White. Data fusion lexicon [G]. DTIC Document,1991.
[10]戎翔.多模态数据融合的研究[D].南京邮电大学,2012.
[11]Min C. Shin, Kyong I. Chang, Leonid V. Tsap. Does Colorspace Transformation Make Any Difference on Skin Detection[C]? The Sixth IEEE workshop on Applications of Computer Vision (WACV'02),2002,275-279.
[12]Lei Huang, Tian Xia, Yongdong Zhang, et al. Human Skin Detection in Images by MSER Analysis[C]. IEEE The International Conference on Image Processing (ICIP),2011,1281-1284.
[13]Shipeng Xie, Jing Pan. Hand Detection Using Robust Color Correction and Gaussian Mixture Model[C].2011 Sixth International Conference on Image and Graphics (ICIG),2011,553-557.
[14]A. Mittal, A. Zisserman, P. H. S. Torn Hand detection using multiple proposals[C]. British Machine Vision Conference,2011,1-11.
[15]Chao Sui, Ngai Ming Kwok, Tianran Ren. A Restricted Coulomb Energy (RCE) Neural Network System for Hand Image Segmentation[C]. Canadian Conference on Computer and Robot Vision, 2011,270-277.
[16]V. Spruyt, A. Ledda, and S. Geerts. Real-time multi-colourspace hand segmentation[C]. IEEE The International Conference on Image Processing (ICIP),2010,3117-3120.
[17]Zhan Song, Hanxuan Yang, Yanguo Zhao, et al. Hand Detection and Gesture Recognition Exploit Motion Times Image in Complicate Scenarios[C]. The 6th international conference on Advances in visual computing,2010,628-636.
[18]Qi Wang, Xilin Chen, Wen Gao. Skin Color Weighted Disparity Competition for Hand Segmentation from Stereo Camera[C]. British Machine Vision Conference,2010,66.1-66.11.
[19]Jean-Christophe Terrillon, Hideo Fukamachi, Shigeru Akamatsu, et al. Comparative performance of different skin chrominance models and chrominance spaces for the automatic detection of human faces in color images[C]. IEEE International Conference on Automatic Face and Gesture Recognition,2000,54-61.
[20]Turgay Celik, Tardi Tjahjadi. Crowley. Adaptive colour constancy algorithm using discrete wavelet transform [J]. Computer Vision and Image Understanding,2012,116(4):561-571.
[21]Gary R. Bradski. A Data-Driven Approach to Hue-Preserving Color-Blending [J]. IEEE Transaction on Visualization and Computer Graphics,2012,18(12):2122-2129.
[22]Archana S. Ghotkar, Gajanan K. Kharate. Hand Segmentation Techniques to Hand Gesture Recognition for Natural Human Computer Interaction [J]. International Journal of Human Computer Interaction,2012,29(3):15-25.
[23]Alexandre R.J. Francois, Gerard G. Medioni. Adaptive color background modeling for real-time segmentation of video streams[C]. The International Conference on Imaging Science, Systems, and Technology,1999,227-232.
[24]Y Shen, SK Ong, AYC Nee. Vision-based hand interaction in augmented reality environment [J]. International Journal of Human Computer Interaction,2011,27(6):523-544.
[25]Qiong Xu, Hengyong Yu, James Bennett, et al. Image Reconstruction for Hybrid True-Color Micro-CT [J]. IEEE Transactions on Biomedical Engineering,2012,59(6):1711-1719.
[26]Saxe David, Foulds Richard. Evaluating a color-based active basis model for object recognition [J]. Computer Vision and Image Understanding,2012,116(11):1111-1120.
[27]Chai Douglas, Ngan King N. Locating the facial region of a head and shoulders color image[C]. The Third IEEE International Conference on Automatic Face and Gesture Recognition,1998, 124-129.
[28]Yannis Avrithis, Yannis Kalantidis. Approximate Gaussian Mixtures for Large Scale Vocabularies [C]. The European Conference on Computer Vision,2012,1-14.
[29]Argyros Antonis, Lourakis Manolis. Vision-based interpretation of hand gestures for remote control of a computer mouse[J]. Computer Vision in Human-Computer Interaction,2006, 3979:40-51.
[30]Albiol Alberto, Torres Luis, Delp Edward J. Optimum Color Spaces of Skin Detection[C]. The International Conference on Image Processing,2001,122-124.
[31]徐战武.静态图像肤色检测研究[D].浙江大学.2006.
[32]Yookyung Kim, M.S. Nadar, A. Bilgin. Wavelet-Based Compressed Sensing Using a Gaussian Scale Mixture Model [J]. IEEE Transaction on Image Process,2012,21(6):3102-3108.
[33]Yingyue Zhou, Zhongfu Ye, Yao Xiao. A restoration algorithm for images contaminated by mixed Gaussian plus random-valued impulse noise [J]. Journal of Visual Communication and Image Representation,2013,24(3):283-294.
[34]Dominguez Sylvia M, Keaton Trish, Sayed, Ali HA. Robust finger tracking method for wearable computer interfacing[C]. The 2001 workshop on Perceptive user interfaces,2001,1-5.
[35]Jones Michael J, Rehg, James M. Statistical color models with application to skin detection [J]. International Journal of Computer Vision,2002,46(1):81-96.
[36]Sigal Leonid, Sclaroff Stan, Athitsos Vassilis. Skin color-based video segmentation under time-varying illumination [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004,26(7):862-877.
[37]Wachs Juan, Kartoun Uri, Stern Helman, et al. Real-time hand gesture telerobotic system using fuzzy c-means clustering[C]. The 5th Biannual World Automation Congress,2002,13:403-409.
[38]Vibhav Vineet, Jonathan Warrell, Paul Sturgess, et al. Improved Initialisation and Gaussian Mixture Pairwise Terms for Dense Random Fields with Mean-field Inference [C]. British Machine Vision Conference,2012,1-11.
[39]Yingyue Zhou, Zhongfu Ye, Yao Xiao. A restoration algorithm for images contaminated by mixed Gaussian plus random-valued impulse noise [J]. Journal of Visual Communication and Image Representation,2013,24(3):283-294.
[40]M. Makitalo, Alessandro Foi. Optimal Inversion of the Generalized Anscombe Transformation for Poisson-Gaussian Noise [J]. IEEE Transaction on Image Process,2013,22(1):91-103.
[41]Wei Liu, Weisi Lin. Additive White Gaussian Noise Level Estimation in SVD Domain for Images [J]. IEEE Transaction on Image Process,2013,22(3):872-883.
[42]M. Staring, Yaonan Wang, D. P. Shamonin, et al. Multiscale Bi-Gaussian Filter for Adjacent Curvilinear Structures Detection with Application to Vasculature Images [J]. IEEE Transaction on Image Process,2013,22(1):174-188.
[43]Takayuki Katsuki, Akira Torii, Masato Inoue. Posterior-Mean Super-Resolution with a Causal Gaussian Markov Random Field Prior [J]. IEEE Transaction on Image Process,2013, 21(7):3182-3193.
[44]Jebara Tony, Russell, Kenneth, Pentland Alex. Gaussian process motion graph models for smooth transitions among multiple actions [J].Computer Vision and Image Understanding,2012, 116(4):500-509.
[45]Suryanarayan Poonam, Subramanian Anbumani and Mandalapu Dinesh. Dynamic Hand Pose Recognition Using Depth Data[C]. The 20th International Conference on Pattern Recognition, 2010,3105-3108.
[46]Oikonomidis Iason, Kyriazis Nikolaos, Argyros Antonis. Efficient model-based 3d tracking of hand articulations using kinect[C]. British Machine Vision Conference,2011,2:1-11.
[47]Etoh Minoru, Tomono Akira, Kishino Fumio. Stereo-based description by generalized cylinder complexes from occluding contours [J]. Systems and Computers in Japan,2007,22(12):79-89.
[48]Yuan Quan, Sclaroff Stan, Athitsos Vassilis. Automatic 2D hand tracking in video sequences[C]. The Seventh IEEE Workshops on Application of Computer Vision,2005,250-256.
[49]Fukunaga Keinosuke, Hostetler Larry. The estimation of the gradient of a density function, with applications in pattern recognition [J]. IEEE Transactions on Information Theory,1975. 21(1):32-40.
[50]Yizong Cheng. Mean shift, mode seeking, and clustering [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1995.17(8):790-799.
[51]Comaniciu Dorin, Meer Peter. Mean Shift:a robust approach toward feature space analysis [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):603-619.
[52]Comaniciu Dorin, Ramesh Visvanathan, Meer Peter. Real-time tracking of non-rigid objects using mean shift[C]. IEEE Conference on Computer Vision and Pattern Recognition,2000,2:142-149.
[53]Collins Robert T. Mean-shift Blob Tracking through Scale Space[C]. IEEE Conference on Computer Vision and Pattern Recognition,2003,2:227-234.
[54]Rui Caseiro, Joao F. Henriques, Pedro Martins, et al. Semi-Intrinsic Mean shift on Riemannian Manifolds [C]. European Conference on Computer Vision,2012,342-355.
[55]Meer Peter. Kernel-based object tracking [J]. IEEE Transactions on pattern analysis and machine intelligence,2003,25(5):564-577.
[56]Chen Hwann-Tzong, Liu Tyng-Luh. Trust-region methods for real-time tracking[C]. The Eighth IEEE International Conference on Computer Vision,2001,2:717-722.
[57]I. Leichter. Mean Shift Trackers with Cross-Bin Metrics [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(4):695-706.
[58]Kurata Takeshi, Okuma Takashi, Kourogi Masakatsu, et al. The hand mouse:Gmm hand-color classication and mean shift tracking[C].IEEE ICCV Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems,2001,119-124.
[59]Hammersley John M, Morton K William. Poor man's Monte Carlo [J]. Journal of the Royal Statistical Society,1954,23-38.
[60]Handschin JE, Mayne David Q. Monte Carlo techniques to estimate the conditional expectation in multi-stage non-linear filtering [J]. International journal of control,1969,9(5):547-559.
[61]Handschin JE. Monte Carlo techniques for prediction and filtering of non-linear stochastic processes [J]. Automatica,1970,6(4):555-563.
[62]Hajime Akashi, Hiromitsu Kumamoto. Construction of discrete time nonlinear filter by Monte Carlo methods with variance-reducing [J]. Systems and Control 19,1975,211-221.
[63]Zaritskii V.S., Svetnik V.B., and Shimelevich L.I. Monte Carlo technique in problems of optimal data processing [J]. Automation and Remote Control 12,1975,95-103.
[64]Hajime Akashi, Hiromitsu Kumamoto. Random sampling approach to state estimation in switching environments [J]. Automatica,1977,13(4):429-434.
[65]Geweke John, Tanizaki Hisashi. On Markov chain Monte Carlo methods for nonlinear and non-Gaussian state-space models [J]. Communications in Statistics-Simulation and Computation, 1999,28(4):867-894.
[66]Geweke John, Tanizaki Hisashi. Note on the sampling distribution for the Metropolis-Hastings algorithm [J]. Communications in Statistics-Theory and Methods,2003,32(4):775-789.
[67]Geweke John, Tanizaki Hisashi. Bayesian estimation of state-space models using the Metropolis-Hastings algorithm within Gibbs sampling [J]. Computational statistics & data analysis,2001,37(2):151-170.
[68]Tanizaki Hisashi. Nonlinear and non-Gaussian state-space modeling with Monte Carlo techniques: A survey and comparative study [J]. Handbook of Statistics,2003,21:871-929.
[69]Smith Adrian FM, Gelfand Alan E. Bayesian statistics without tears:a sampling-resampling perspective [J]. The American Statistician,1992,46(2):84-88.
[70]Gordon Neil J, Salmond David J, Smith Adrian FM. Novel approach to nonlinear/non-Gaussian Bayesian state estimation [J]. lee Proceedings F Radar and Signal Processing,1993, 140(2):107-113.
[71]Doucet Arnaud, De Freitas Nando, Murphy Kevin, et al. Stuart Rao-Blackwellised particle filtering for dynamic Bayesian networks[C]. The Sixteenth conference on Uncertainty in artificial intelligence,2000,176-183.
[72]Su H-T, Wu T-P, Liu H-W, et al. Rao-Blackwellised particle filter based trackbefore-detect algorithm [J]. Signal Processing,2008,2(2):169-176.
[73]Branko Ristic, Sanjeev Arulampalm, Neil James Gordon. Beyond the Kalman filter:Particle filters for tracking applications [M]. Boston:Artech House,2004:35-62.
[74]Doucet Arnaud, Freitas Nando de, Gordon Neil. Sequential Monte Carlo Methods in Practice [G]. New York:Springer-Verlag,2001:17-73.
[75]Waqas Hassan, Nagachetan Bangalore, Philip Birch. An Adaptive sample count particles filter [J]. Computer Vision and Image Understanding,2012,116(12):1208-1222.
[76]Li Bai, Yan Wang. Road tracking using particle filters with partition sampling and auxiliary variables [J]. Computer Vision and Image Understanding,2011,115(10):1463-1471.
[77]Alberto Del Bimbo, Fabrizio Dini. Particle filter-based visual tracking with a first order dynamic model and uncertainty adaptation [J]. Computer Vision and Image Understanding,2011, 115(6):771-786.
[78]Mammen James P, Chaudhuri Subhasis, Agrawal Tushar. Dimensionality reduction using a Gaussian Process Annealed Particle Filter for tracking and classification of articulated body motions [J]. Computer Vision and Image Understanding,2011,115(4):503-519.
[79]Shimin Yin, Jin Hee Na, Jin Young Choi, et al. Hierarchical Kalman-particle filter with adaptation to motion changes for object tracking [J]. Computer Vision and Image Understanding,2011, 115(6):885-900.
[80]Ros German, del Rincon Jesus Martinez, Mateos Gines Garcia. Articulated particle filter for hand tracking[C]. The 21st International Conference on Pattern Recognition,2012,3581-3585.
[81]Yuan Quan, Thangali Ashwin, Ablavsky Vitaly, et al. Multiplicative Kernels:Object Detection, Segmentation and Pose Estimation[C]. IEEE Conference on Computer Vision and Pattern Recognition,2008:1-8.
[82]Marcel Sebastien, Bernier Olivier, Viallet J-E, et al. Hand gesture recognition using Input/Ouput Hidden Markov Models[C]. The Fourth IEEE International Conference on Automatic Face and Gesture Recognition,2000,456-461.
[83]Triesch Jochen, Von Der Malsburg Christoph. Robust Classification of Hand Postures against Complex Backgrounds[C]. The Second IEEE International Conference on Automatic Face and Gesture Recognition,1996,170-175.
[84]Triesch Jochen, Von Der Malsburg Christoph. A System for Person-Independent Hand Posture Recognition against Complex Backgrounds [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2001,23(12):1449-1453.
[85]Marcel Sebastien, Bernier Olivier. Hand posture recognition in a body-face centered space [J]. Gesture-Based Communication in Human-Computer Interaction,1999,97-100.
[86]顾立忠.基于表观的手势识别及人机交互研究[D].上海交通大学,2008.
[87]Mahmoud Othman Selim Mahmoud Elmezain. Hand Gesture Spotting and Recognition Using HMMs and CRFs in Color Image Sequences [D]. OTTO VON GUERICKE UNIVERSITAT MAGDEBURG,2010.
[88]于洋.基于手形特征的静态手势识别[D].河北工业大学,2007.
[89]甘志杰.基于Hu矩和支持向量机的静态手势识别及应用[D].青岛科技大学,2008.
[90]程小鹏.基于特征提取的手势识别技术研究[D].武汉理工大学,2012.
[91]Przemyslaw Glomb, Michal Romaszewski, Sebastian Opozda, et al.Choosing and Modeling the Hand Gesture Database for a Natural User Interface[J]. Gesture and Sign Language in Human-Computer Interaction and Embodied Communication,2012,7206:24-35.
[92]Vladimir N Vapnik. An overview of statistical learning theory [J]. IEEE Transactions on Neural Networks,1999,10(5):988-999.
[93]朱美琳,刘向东,陈世福..用球结构的支持向量机解决多分类问题[J].南京大学学报：自然科学版,2003,39(2)：153-158.
[94]周绍磊,秦亮,史贤俊等.基于模糊机会约束的超球支持向量机[J].华中科技大学学报(自然科学版),2012,40(7)：29-33.
[951 吴石,林连冬,肖飞等.基于多类超球支持向量机的铣削颤振预测方法[J].仪器仪表学报,2012,33(11)：2415-2421.
[96]艾青,赵骥,秦玉平.基于最大间隔最小体积超球支持向量机的多主题分类算法[J].计算机科学,2012,39(8)：237-238.
[97]Iain E. G. Richardson. H.264 and MPEG-4 Video Compression, Video Coding for Next-generation Multimedia [M]. Aberdeen:Wiley,2003:9-24.
[98]Fukunaga Keinosuke, Hostetler Larry. The Estimation of the Gradient of a Density Function, with Applications in Pattern Recognition [J]. IEEE Transactions on Information Theory,1975, 21(1):32-40.
[99]冈萨雷斯.数字图像处理[M].第二版中文版.北京：电子工业出版社,2003：59-112.
[100]Everingham Mark, Van Gool Luc, Williams Christopher K.I, et al. The pascal visual object classes (voc) challenge [J]. International journal of computer vision,2010,88(2):303-338.
[101]Juan Pablo Wachs, Mathias Kolsch, Helman Stern, et al. Vision-based hand-gesture applications [J]. Communication of ACM,2011,54(2):60-71.
[102]Mahmoud Elmezain, Ayoub Al-Hamadi, Appenrodt, Jorg, et al. A Hidden Markov Model-Based Continuous Gesture Recognition System for Hand Motion Trajectory[C]. The 19th International Conference on Pattern Recognition,2008:1-4.
[103]李文生,解梅,姚琼.基于Laguerre正交基神经网络的动态手势识别[J].南京大学学报：自然科学版,2011,47(5)：515-523.
[104]Thangali, A., Nash, J.P., Sclaroff, S., et al. Exploiting phonological constraints for handshape inference in ASL video[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2011:521-528.
[105]Oikonomidis, I., Kyriazis, N., Argyros, A. Full dof tracking of a hand interacting with an object by modeling occlusions and physical constraints[C]. The 13th International Conference on Computer Vision,2011,2088-2095.
[106]Kong WW, Ranganath S. Automatic Hand Trajectory Segmentation and Phoneme Transcription for Sign Language[C]. IEEE International Conference on Automatic Face & Gesture Recognition, 2008,1-6.
[107]Scherr, R.E.Gesture analysis for physics education researchers [J]. Physical Review Special Topics-Physics Education Research,2008,4(1):101-115.
[108]Batmaz, F., Stone, R.G. Using Hand Gestures to Capture Students'Design Rationale[C]. Computers and Advanced Technology in Education,2011,12-20.
[109]Kelly Spencer D, Manning Sarah M, Rodak Sabrina. Gesture gives a hand to language and learning:Perspectives from cognitive neuroscience, developmental psychology and education [J]. Language and Linguistics Compass,2008,2(4):569-588.
[110]Jan Flusser. On the Independence of Rotation Moment Invariants [J]. Pattern Recognition,2000, 33(9):1405-1410.
[111]Jan Flusser, Tomas Suk. Rotation Moment Invariants for Recognition of Symmetric Objects [J]. IEEE Transactions on Image Processing,2006,15(12):3784-3790.
[112]Bourennane S, Fossati C. Comparison of shape descriptors for hand posture recognition in video [J]. Signal, image and video processing,2012,6(1):147-157.
[113]3D moment forms:their construction and application to object identification and positioning [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1989,11(10):1053-1064.
[114]朱继玉,王西颖,王威信等.基于结构分析的手势识别[J].计算机学报,2006,29(12)2130-2137.
[115]Ming-Kuei Hu. Visual pattern recognition by moment invariants [J]. IRE Transactions on Information Theory,1962,8(2):179-187.
[116]Jun Cheng, Can Xie, Wei Bian, et al. DachengFeature fusion for 3D hand gesture recognition by learning a shared hidden space [J]. Pattern Recognition Letters,2012,33(4):476-484.
[117]Yoon Ho-Sub, Soh Jung, Bae Younglae J, et al. Hand Gesture Recognition Using Combined Features of Location [J]. Pattern Recognition,2001,34(7):1491-1501.