基于GPU并行计算的动态签名鉴别算法研究
|
摘要
本文的主要工作是对动态签名鉴别算法进行研究。在对动态签名特征进行稳定性分析的基础上,首次将新兴的基于GPU的并行计算技术应用于动态签名鉴别领域。并综合考虑动态签名的时域和频域特性,运用多分辨分析、动态规划、傅立叶变换和聚类分析等相关理论对动态签名鉴别技术进行深入研究。
具体研究内容和取得的成果如下:
一、系统地介绍了基于GPU通用计算的体系结构和并行机制,并在签名鉴别算法设计中率先引入了基于GPU的并行计算技术,显著地提高了相应算法的效率。
二、建立了基于时间序列分段的动态签名鉴别数学模型,提出了依签名主轴进行极坐标映射并按极值点进行分段的签名笔段划分方法。
三、针对动态签名鉴别问题中的小样本和特征时移等特点,提出了一种基于CREW PRAM模型的并行动态规划算法,依笔段的局部相关性进行动态匹配。
四、为进一步提高动态规划算法的性能,本文提出了运用多分辨分析进行特征提取和信息降维的方法。
五、提出了一种隐式分层聚类算法,利用签名Fourier变换后的频域特征对模板库进行聚类分析,并据此完成签名模板库的优化处理。
六、建立了一个可广泛用于签名鉴别算法测试的吉林大学动态签名数据库JLU-DHSDB2.0
Authentication is a mostly encountered basic matter in our daily life. With the development of the computer and network technology and the expansion of the physical and virtual space, so much more demands are put forward such as precision, security and practicability that the classical authentication methods are more and more limited in the various application areas. Some new authentication methods with more security and convenience need to be sought for. Under these circumstances, the biometric authentications were coming up and become quite popular.
Dynamic signature verification is a biometric authentication technology using person’s behavior characteristics in handwriting. To obtain the abundant patten information, the dynamic signature characteristics are widely adopted from the on-line collecting device. The special input device can provide manifold signature signals such as trajectory, pressure, obliquity et al, and these information compose the time sequence. Via the corresponding matching algorithm, the exterior features as trajectory and the interior features such as pressure, velocity, acceleration can be verified to supply references for authentication. Having the advantage of hard to forge, dynamic signature verification preserves the habit of ink-like signature behavior and has more acceptability in the application.
Based on the stability analysis about the features of dynamic signature, a novel parallel computing technology with GPU device is proposed in the study of signature verification. And the features both in frequency region and time region are integrated into the algorithm, so that the theories of Multi-resolution Analysis, Dynamic Programming, Fourier Transform and Clustering can be well applied to the research on the dynamic signature verification.
The main contents of the study and the contribution are listed in the following.
1. With the rapid development of computer technology and VLSI technology, the graphics processor (GPU) on today's commodity video cards has evolved into an extremely powerful and flexible processor. The latest graphics architectures provide tremendous memory bandwidth and computational horsepower, with fully programmable vertex and pixel processing units that support vector operations up to full IEEE floating point precision. Architecturally, since the G80 series GPUs have been highly parallel streaming processors optimized for vector operations, with both MIMD (vertex) and SIMD (pixel) pipelines. Researchers have found that exploiting the GPU can accelerate some problems by over an order of magnitude over the CPU. These processors are capable of general-purpose computation beyond the graphics applications for which they were designed.
CUDA is a parallel computing architecture and programming model developed by NVIDIA. The CUDA architecture includes an assembly language (PTX) and compilation technology that is the basis on which multiple parallel language and API interfaces are built on NVIDIA GPUs, including C (C++) for CUDA, OpenCL, Fortran, Matlab and DirectX Compute Shaders. C for CUDA uses the standard C language with extensions, and exposes hardware features to researchers for fully use of GPU resources. With the high level languages have emerged for graphics hardware, personal computer’s computational power are more accessible and make high performance computing on the desktop come to true.
2. A set of mathematical model is established in here according to the segments of dynamic signature sequences. A method is presented to create a polar coordinate system based on the mess centers of whole signature and the golden section under which we can extract the extrema from the feature of polar angle as signature segmenting-point sequence. Upon these special points, a signture can be splitted to segments with the relatively stable local features.
3. After the segments achieved, the GPDM (GPU based Parallel Dynamic Matching) algorithm of parallel dynamic matching is presented according to the CREW PRAM parallel model for matching the time sequences among the small capacity library with dynamic programming technology. Dynamic programming is a global optimization method to match the time sequences with variable length by the evaluating function. It has various implementing algorithm applied to the pattern recognition area and it is also a primary method in dynamic signature verification. Since there are specialities of the dynamic signature time sequence with well stability in global scale and variability between phases, the segment’s correlativity is much more important to the verification course rather than some special points’s matching result. To reduce the computing quantity, the GPGPU is adopted to accelerate the performance in dynamic matching algorithm. Evaluated using the JLU-DHSDB 2.0 signature database, The GPDM algorithm resulted in 4.10% EER.
4. A method for features extraction and dimension reducing was presented here based on MRA, to promote the performance of the dynamic programming algorithm furthermore. The wavelet transform is a synthesis of ideas that emerged over many years from different fields, such as mathematics and signal processing. Generally speaking, the wavelet transform is a tool that divides up data into different frequency components and then studies each component with a resolution matched to its scale.
Using wavelet decomposition, the approximate coefficients of signature at high scale can be applied to obtain the extrema based on the polar angle feature. As the result, the much more eligible stable segments can be obtained accordingly and then we can calculate the similarity at lower scale coefficients. By wavelet decomposition the dimension of signature sequence can be reduced more efficiently to save the quantity of computing operations ulteriorly in the following verification phase.
5. An algorithm of Iteration based Hidden Hierarchical Clustering (IHHC) was proposed. Clustering was performed based on the features extracted from frequency region with Fourier Transform, which can be used to optimize the signature template database. The signatures written by enrollee in a short period contain more redundancies which are not suit for the constructing the reference template effectively and that can induce the false rejection in next verification after a long period. Using the Clustering method can optimize the signature template on the one hand and on the other hand it can scout the trend of the man’s handwriting and trace the new feature which never occured before. Thus it can promote the performance more efficiently and increase the verification precision.
6. Evaluation databases used in this dissertation is JLU-DHSDB2.0 which has been established specially by the Dynamic Signature Verification Team of Jilin University. There are 127 categories in the database corresponding to 127 individual donor’s original dynamic handwritten signature data. In each category it contains at least 20 skilled genuine signatures, additionally some of the enrollee signed another 10 genuine signatures after 3 weeks. There are also 60 skilled forgeries and 10 counterdrawing forgeries in the every category. This database is used to evaluate the stabilities of signature and accuracy of the authentication algorithm widely.
具体研究内容和取得的成果如下:
一、系统地介绍了基于GPU通用计算的体系结构和并行机制,并在签名鉴别算法设计中率先引入了基于GPU的并行计算技术,显著地提高了相应算法的效率。
二、建立了基于时间序列分段的动态签名鉴别数学模型,提出了依签名主轴进行极坐标映射并按极值点进行分段的签名笔段划分方法。
三、针对动态签名鉴别问题中的小样本和特征时移等特点,提出了一种基于CREW PRAM模型的并行动态规划算法,依笔段的局部相关性进行动态匹配。
四、为进一步提高动态规划算法的性能,本文提出了运用多分辨分析进行特征提取和信息降维的方法。
五、提出了一种隐式分层聚类算法,利用签名Fourier变换后的频域特征对模板库进行聚类分析,并据此完成签名模板库的优化处理。
六、建立了一个可广泛用于签名鉴别算法测试的吉林大学动态签名数据库JLU-DHSDB2.0
Authentication is a mostly encountered basic matter in our daily life. With the development of the computer and network technology and the expansion of the physical and virtual space, so much more demands are put forward such as precision, security and practicability that the classical authentication methods are more and more limited in the various application areas. Some new authentication methods with more security and convenience need to be sought for. Under these circumstances, the biometric authentications were coming up and become quite popular.
Dynamic signature verification is a biometric authentication technology using person’s behavior characteristics in handwriting. To obtain the abundant patten information, the dynamic signature characteristics are widely adopted from the on-line collecting device. The special input device can provide manifold signature signals such as trajectory, pressure, obliquity et al, and these information compose the time sequence. Via the corresponding matching algorithm, the exterior features as trajectory and the interior features such as pressure, velocity, acceleration can be verified to supply references for authentication. Having the advantage of hard to forge, dynamic signature verification preserves the habit of ink-like signature behavior and has more acceptability in the application.
Based on the stability analysis about the features of dynamic signature, a novel parallel computing technology with GPU device is proposed in the study of signature verification. And the features both in frequency region and time region are integrated into the algorithm, so that the theories of Multi-resolution Analysis, Dynamic Programming, Fourier Transform and Clustering can be well applied to the research on the dynamic signature verification.
The main contents of the study and the contribution are listed in the following.
1. With the rapid development of computer technology and VLSI technology, the graphics processor (GPU) on today's commodity video cards has evolved into an extremely powerful and flexible processor. The latest graphics architectures provide tremendous memory bandwidth and computational horsepower, with fully programmable vertex and pixel processing units that support vector operations up to full IEEE floating point precision. Architecturally, since the G80 series GPUs have been highly parallel streaming processors optimized for vector operations, with both MIMD (vertex) and SIMD (pixel) pipelines. Researchers have found that exploiting the GPU can accelerate some problems by over an order of magnitude over the CPU. These processors are capable of general-purpose computation beyond the graphics applications for which they were designed.
CUDA is a parallel computing architecture and programming model developed by NVIDIA. The CUDA architecture includes an assembly language (PTX) and compilation technology that is the basis on which multiple parallel language and API interfaces are built on NVIDIA GPUs, including C (C++) for CUDA, OpenCL, Fortran, Matlab and DirectX Compute Shaders. C for CUDA uses the standard C language with extensions, and exposes hardware features to researchers for fully use of GPU resources. With the high level languages have emerged for graphics hardware, personal computer’s computational power are more accessible and make high performance computing on the desktop come to true.
2. A set of mathematical model is established in here according to the segments of dynamic signature sequences. A method is presented to create a polar coordinate system based on the mess centers of whole signature and the golden section under which we can extract the extrema from the feature of polar angle as signature segmenting-point sequence. Upon these special points, a signture can be splitted to segments with the relatively stable local features.
3. After the segments achieved, the GPDM (GPU based Parallel Dynamic Matching) algorithm of parallel dynamic matching is presented according to the CREW PRAM parallel model for matching the time sequences among the small capacity library with dynamic programming technology. Dynamic programming is a global optimization method to match the time sequences with variable length by the evaluating function. It has various implementing algorithm applied to the pattern recognition area and it is also a primary method in dynamic signature verification. Since there are specialities of the dynamic signature time sequence with well stability in global scale and variability between phases, the segment’s correlativity is much more important to the verification course rather than some special points’s matching result. To reduce the computing quantity, the GPGPU is adopted to accelerate the performance in dynamic matching algorithm. Evaluated using the JLU-DHSDB 2.0 signature database, The GPDM algorithm resulted in 4.10% EER.
4. A method for features extraction and dimension reducing was presented here based on MRA, to promote the performance of the dynamic programming algorithm furthermore. The wavelet transform is a synthesis of ideas that emerged over many years from different fields, such as mathematics and signal processing. Generally speaking, the wavelet transform is a tool that divides up data into different frequency components and then studies each component with a resolution matched to its scale.
Using wavelet decomposition, the approximate coefficients of signature at high scale can be applied to obtain the extrema based on the polar angle feature. As the result, the much more eligible stable segments can be obtained accordingly and then we can calculate the similarity at lower scale coefficients. By wavelet decomposition the dimension of signature sequence can be reduced more efficiently to save the quantity of computing operations ulteriorly in the following verification phase.
5. An algorithm of Iteration based Hidden Hierarchical Clustering (IHHC) was proposed. Clustering was performed based on the features extracted from frequency region with Fourier Transform, which can be used to optimize the signature template database. The signatures written by enrollee in a short period contain more redundancies which are not suit for the constructing the reference template effectively and that can induce the false rejection in next verification after a long period. Using the Clustering method can optimize the signature template on the one hand and on the other hand it can scout the trend of the man’s handwriting and trace the new feature which never occured before. Thus it can promote the performance more efficiently and increase the verification precision.
6. Evaluation databases used in this dissertation is JLU-DHSDB2.0 which has been established specially by the Dynamic Signature Verification Team of Jilin University. There are 127 categories in the database corresponding to 127 individual donor’s original dynamic handwritten signature data. In each category it contains at least 20 skilled genuine signatures, additionally some of the enrollee signed another 10 genuine signatures after 3 weeks. There are also 60 skilled forgeries and 10 counterdrawing forgeries in the every category. This database is used to evaluate the stabilities of signature and accuracy of the authentication algorithm widely.
引文
[1]卢官明,李海波,刘莉.生物特征识别综述[J].南京邮电大学学报(自然科学版), 2007,27(1):81-88.
[2] M. Kawagoe, A.Tojo. Fingerprint pattern classification[J]. Pattern Recog- nition, 1984, 17(3):295-303.
[3]刘小华,王燕生.指纹识别技术的发展[J].光学技术, 1998,4:78-80.
[4] Tsai-Yang Jea, and Venu Govindaraju. A minutia-based partial fingerprint recognition system[J].Pattern Recognition, 2005, 38 (10) :1672-1684.
[5] A. Kumar, D.Zhang. Personal recognition usinghand shape and texture [J]. IEEE Tran on Image Processing, 2006, 15(8):2454-2461.
[6]束为,荣钢,边肇祺等.利用掌纹进行身份自动鉴别方法的研究[J].清华大学学报(自然科学版), 1999, 39(1):95-97.
[7] N. Duta, A.K.Jain, K.V. Mardia. Matching of palmprint[J]. Pattern Recog- nition Letters, 2002, 23(4):477-485.
[8] E. Hjelmas, B. K. Low. Face Detection: A Survey[J]. Computer Vision and Image Understanding, 2001, 83(3): 236-274.
[9] L. Hock Koh, S. Ranganath, Y. V. Venkatesh. An integrated automatic face detection and recognition system[J]. Pattern Recognition, 2002, 35(6): 1259-1273.
[10]常卫东,刘完芳,鄢喜爱.虹膜识别的研究现状与发展趋势[J].中国科技信息, 2007,1:246-247.
[11] John Daugman, Recognizing people by their iris patterns[J]. Information Security Technical Report, 1998, 3(1):33-39.
[12] Ke Chen. Speaker Modeling with Various Speech Representations[C]. Biometric Authentication: First International Conference, ICBA 2004, Hong Kong, China, July,2004, 592-599
[13]王亮,胡卫明,谭铁牛.基于步态的身份识别[J].计算机学报, 2003, 26(3): 353-360.
[14]王蕴红,谭铁牛.现代身份鉴别新技术——生物特征识别技术[J].中国基础科学, 2000,(9):4-10.
[15]张公正.关于摹仿笔迹鉴定之探索.公安大学学报(自然科学版), 2002, 27(1): 5-7.
[16] A. K. Jain, F. D. Griess, and S. D. Connell. On-line Signature Verification [J]. Pattern Recognition, 2002, 35(12):2963-2972.
[17] J. G. A. Dolfing, E. H. L. Aarts, and J. J. G. M. Van Oosterhout. On-line signature verification with hidden Markov models[C]. in Proceedings of the International Conference on Pattern Recognition. Brisbane Australia, 1998, 1309–1312.
[18] A. Kholmatov and B. Yanikoglu. Identity authentication using improved online signature verification method[J]. Pattern Recognition Letters, 2005, 26(15):2400–2408.
[19] J. Richiardi and A. Drygajlo. Gaussian mixture models for on-line signature verification[C]. Proceedings of the ACM SIGMM Workshop on Multimedia Biometrics Methods and Applications (WBMA '03). Berkley, Calif, USA, 2003,115–122.
[20] R. Plamondon, G. Lorette. Automatic Signature Verification and Writer Identification—The State of the Art[J]. Pattern Recognition, 1989, 22(2): 107-131.
[21] J. P. Drouhard, R. Sabourin, M. Godbout. A Neural Network Approach to Off-line Signautre Verification Using Directional PDF[J]. Pattern Recognition, 1996, 29(3):415-424.
[22] R. Sabourin, G. Genest, F. J. Preteux. Off-Line Signautre Verification by Local Granulometric Size Distributions[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(9):976-988.
[23]朱勇,谭铁牛,王蕴红.基于笔迹的身份鉴别[J].自动化学报, 2001, 27(2): 229-234.
[24] M. Hanmandlu, M.H.M. Yusof, V. K. Madasu. Off-line signature verification and forgrey detection using fuzzy modeling[J]. Pattern Recognition, 2005, 38(3):341-356.
[25] B. Fang, C.H.Leung, YYTang, et al. Off-line Signature Verification by the Tracking of Feature and Stroke Positions[J]. PatternRecognition, 2003, 36(1):91-101.
[26] K. Huang and H. Yan, Off-line signature verification based on geometric feature extraction and neural network classification [J], Pattern Recognition, 1997, 30(1):9–17.
[27] M.A. Ferrer, J.B. Alonso and C.M. Travieso, Offline geometric parameters for automatic signature verification using fixed-point arithmetic[J], IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(6): 993–997.
[28]沈峰,杨飞,袁余良等.动态手写签名验证技术概述[J].计算机科学, 2003, 30(3):92-95.
[29] R. Plamondon. A Kinematic Theory of rapid Human Movements: Part I. Movement representation and generation[J]. Biological Cybernetics, 1995, 72(4): 295-307.
[30] N.M.Herbst, C.N.Liu. Automatic Signature Verification Based on Accelerometry[J]. IBM Journal Research and Development, 1977, 21(3): 245-253.
[31] W. Nelson and E. Kishon. Use of dynamic features for signature verification[C]. Proceedings of the IEEE. Int. Conf. on Syst., Man, Cybern, Charlottesville, VA, 1991,(1):201–205.
[32] F. Leclerc, R. Plamondon. Automatic signature verification: the state of the art-1989–1993[J]. International Journal of Pattern Recognition and Artificial Intelligence (IJPRAI) , 1994, 8 (3):643–660.
[33] V. S. Nalwa. Automatic on-line signature verification[J]. Proceedings of the IEEE, 1997, 85(2):215–239.
[34] G.K. Gupta and A. McCabe. A review of dynamic handwritten signature verification[R], Technical Report, Department of Computer Science, James Cook University, Townsville, Australia, 1997.
[35] SVC2004[DB/OL]. http://www.cs.ust.hk/SVC2004/index.html, 2004
[36] BMEC2007[DB/OL]. http://biometrics.it-sudparis.eu/BMEC2007/, 2007
[37] BSEC2009[DB/OL]. http://biometrics.it-sudparis.eu/BSEC2009/downloads/BS EC2009_results.pdf, 2009
[38] Y.Qi, B.R.Hunt. Signature Verification Using Global and Grid Features[J]. Pattern Recognition, 1994,27(12):1621-1629.
[39] G.V.Kiran, R.Srinivasa, Rao Kunte, Sudhaker Samuel. On-Line Signature Verification System Using Probabilistic Feature Modelling[J]. International Symposium on Signal Processing and its Applications, 2001,355-358.
[40] G.K.Gupta, R.C.Joyce. A Study of Some Pen Motion Features In Dynamic Handwritten Signature Verification[R].Technical Report, Department of Computer Science, James Cook University, Townsville, Australia,1997.
[41] Y.T.Yuan, C.M.L.Ernest. New Method for Feature Extraction Based on Fractal Behavior[J]. Pergamon Pattern Recognition, 2002, 35:1071-1081.
[42] T.Rhee, S.Cho, J.Kim. On-Line Signature Verification Using Model-Guided Segmentation and Discriminative Feature Selection for Skilled Forgeries [C]. In the 6th Int. Conf. on Document Analysis and Recognition (ICDAR) , 2001.
[43] L.Yang, B.K.Widjaja, R.Prasad. Application of Hidden Markov Models for Signature Verification[J]. Pattern Recognition, 1995, 28(2):161-170.
[44] H.S.Yoon, J.Y.Lee, H.S.Yang. An On-line Signature Verification System Using Hidden Markov Model In Polar Space[C]. Proc. of the Eighth International Workshop on Frontiers in Handwriting Recognition, 2002,329-333.
[45] Daigo Muramatsu, Takashi Matsumoto. An HMM On-line Signature Verification Algorithm[C]. AVBPA 2003, LNCS-2688:233-241.
[46]程开东,栾方军,马驷良.一种基于隐马尔可夫模型的在线手写签名认证算法[J].吉林大学学报(理学版),2008, 46(5):940-943
[47] J.Droughord, R.Plamondon, M.Godbout.A Neural Network Approach to Off-line Signature Verification Using Directional PDF[J]. Pattern Recognition, 1996, 29:415-424.
[48] C. Santos, E.J.R.Justino, F.Bortolozzi, et al. An Off-Line Signature Verification Method based on the Questioned Document Expert's Approach and a Neural Network Classifier [C]. Proceedings of the 9th International Workshop on Frontiers in Handwriting Recognition (IWFHR-9 2004).IEEE, 2004, 498-502.
[49] L. Y. Tseng, T. H. Huang. An online Chinese signature verification scheme based on the ART1 neural network[C]. International Joint Conference on Neural Networks (IJCNN 1992), 1992, 3:624-630.
[50]金涌,柳健.手写签名的概率神经网络识判模型[J].华中理工大学学报, 1999, 27(5):11-13.
[51] P. Mautner, O. Rohlik, V. Matousek, et al. Signature verification using ART-2 neural network[C]. Proceedings of the 9th International Conference on Neural Information Processing (ICONIP '02), 2002, 2:636-639.
[52]李媛,袁余良,沈峰等.一种基于神经网络的动态手写签名验证模型[J].计算机科学, 2005, 32(5):181-184.
[53]刁在筠,刘桂真,宿洁等.运筹学(第三版)[M].北京:高等教育出版社, 2007.
[54]李胜春,丁晓青,陈彦.基于加权动态匹配方法的联机签名鉴别[J].清华大学学报(自然科学版) , 1999,39(9):61-64.
[55]胡航,语音信号处理[M].哈尔滨:哈尔滨工业大学出版社, 2005.
[56]唐降龙,孙广玲,刘家锋等.一种笔段序列匹配联机汉字识别方法[J].计算机研究与发展, 1999,36(12):1472-1476.
[57]柯晶,乔谊正,赵宏.联机自动签名鉴定系统的设计与实现[J].计算机与现代化, 1998,54(2):6-9(48).
[58] M.Parizeau, R.Plamondon. A comparative analysis of regional correlation, dynamical time warping and skeletal tree matching for signature verification [J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1990, 12(7):710- 717.
[59] B.Wirtz. Stroke-based time warping for signature verification[C]. Int. Conf. on Document Analysis and Recognition, 1995,179-182.
[60]金涌,柳健.基于空间曲线弹性匹配的在线手写签名鉴别[J].华中理工大学学报, 1999, 27(5):14-16.
[61] Isao Nakanishi, et al. Optimal User Weighting Fusion in DTW Domain On-Line Signature Verification[C]. AVBPA 2005, LNCS 3546: 758-766.
[62] A. Kholmatov, B. Yanikoglu. Identity authentication using improved online signature verification method[J]. Pattern Recognition Letters, 2005, 26(15): 2400-2408.
[63]郑建彬,徐陶神,朱光喜.基于DTW的在线手写签名验证算法[J].武汉理工大学学报, 2006,30(2):212-215.
[64] David Tarditi, Sidd Puri, Jose Oglesby. Accelerator: using data parallelism to program GPUs for general-purpose uses, Proceedings of the 12thinternational conference on Architectural support for programming languages and operating systems, October 21-25, 2006[C], San Jose, California, 2006.
[65]苏畅,付忠良,谭雨辰.一种在GPU上高精度大型矩阵快速运算的实现[J].计算机应用, 2009, 29(4):1177-1179(1192).
[66]吴恩华.图形处理器用于通用计算的技术、现状及其挑战[J].软件学报, 2004, 15(10):1493-1504.
[67]钱悦.图形处理器CUDA编程模型的应用研究[J].计算机与数字工程, 2008, 36(12):177-180.
[68] Nvidia Offcial Site[DB/OL]. http://www.nvidia.com/
[69] Erik Lindholm, M.J. Kligard, Henry Moreton, A user-programmable vertex engine[C]. Proceedings of the 28th annual conference on Computer graphics and interactive techniques, 2001, 149-158.
[70] Ian Buck, Tim Foley, Daniel Horn, et al. Brook for GPUs: stream computing on graphics hardware[C]. ACM SIGGRAPH 2004 Papers, Los Angeles, California, 2004,777-786.
[71] Mark J. Harris, Greg Coombe,et al. Physically-based visual simulation on graphics hardware[C]. Proceedings of the ACM conference on Graphics hardware, Saarbrucken, 2002,109-118.
[72] Jens Krüger, Rüdiger Westermann. Linear algebra operators for GPU implementation of numerical algorithms[C]. ACM SIGGRAPH 2003 Papers, July 27-31, 2003, San Diego, California, 2003, 22(3): 908-916.
[73] Jens Krüger. Linear algebra on GPUs[R]. ACM SIGGRAPH 2005 Courses, July 31-August 04, 2005, Los Angeles, California, 2005.
[74] Jeff Bolz, Ian Farmer, Eitan Grinspun, et al. Sparse matrix solvers on the GPU: Conjugate gradients and multigrid[C]. ACM SIGGRAPH 2003 Papers, July 27-31, 2003, San Diego, California, 2003, 22(3):917-924.
[75] Nolan Goodnight, Cliff Woolley, Gregory Lewin, et al. A multigrid solver for boundary value problems using programmable graphics hardware[C], Proceedings of the ACM conference on Graphics hardware, July 26-27, 2003, San Diego, California, 2003,102-111.
[76] Karl E. Hillesland, Sergey Molinov, Radek Grzeszczuk. Nonlinear optimization framework for image-based modeling on programmable graphicshardware. ACM SIGGRAPH 2003 Papers, July 27-31, 2003, San Diego, California, 2003, 22(3):925-934.
[77] Timothy J. Purcell, Ian Buck, William R. Mark, et al. Ray tracing on programmable graphics hardware[J]. ACM Transactions on Graphics, 2002, 21(3):703-712.
[78] N.A. Carr, J.D. Hall, J.C. Hart. The ray engine[C]. Proceedings of Graphics Hardware, Saarbrucken, 2002, 37-46 .
[79] Greg Coombe, Mark J. Harris, Anselmo Lastra. Radiosity on graphics hardware[C]. Proceedings of Graphics Interface 2004. London, Ontario, 2004, 161-168.
[80] Kun Zhou, Xin Huang, Weiwei Xu,et al. Direct manipulation of subdivision surfaces on GPUs[C]. Proceedings of ACM SIGGRAPH 2007. San Diego, California,2007, 26(3):91.
[81] Matthias Hopf, Thomas Ertl. Hardware accelerated wavelet transformations [C]. Proceedings of EG/IEEE TCVG Symposium on Visualization. VisSym, Netherlands, 2000, 93-103.
[82] Kenneth Moreland, Edward Angel. The FFT on a GPU[C]. Proceedings of the ACM SIGGRAPH/EUROGRAPHICS conference on Graphics hardware, July 26-27, 2003, San Diego, California, 2003, 112-119.
[83] Martin Rumpf, Robert Strzodka. Using graphics cards for quantized FEM computations[C]. Proceedings of VIIP, Marbella, 2001, 98-107.
[84] E. S. Larsen, M. David. Fast matrix multiplies using graphics hardware[C]. Proceedings of Super Coumputing, Denver, 2001, 55-60.
[85] C.J. Thompson, S. Hahn, M. Oskin, Using modern graphics architectures for general-purpose cumputing: A framework and analysis[C]. Proceedings of International Symposium on Microarchitecture, Istanbul, 2002, 306-317.
[86] Li Wei, Wei Xiaoming, Kaufman Arie. Implementing lattice Boltzmann computation on graphics hardware[J]. The Visual Computer, 2003, (19):44-46.
[87] A.E. Lefohn, J.M. Kniss, C.D. Hansen, et al. Interactive deformation and visualization of level set sufaces using graphics hardware[C]. Proceedings of 14th IEEE Visualization 2003(VIS'03), Seattle, 2003, 75-82.
[88] A.E. Lefohn, J. M. Kniss, C. D. Hansen, et al. A streaming narrow-bandalgorithm: interactive computation and visualization of level sets[C]. ACM SIGGRAPH 2005 Courses, July 31-August 04, 2005, Los Angeles, California, 2005, 243-257.
[89] E.Elsen, P. LeGresley, E. Darve. Large calculation of the flow over a hypersonic vehicle using a GPU[J]. Journal of Computational Physics. 2008, 227(24):10148-10161.
[90] W. Liu, B.Schmidt, G.Voss,et al. Streaming Algorithms for Biological Sequence Alignment on GPUs[J]. IEEE Transactions on Parallel and Distributed Systems. 2007,18(9):1270-1281.
[91] Trapnell C, Schatz MC. Optimizing data intensive GPGPU computations for DNA sequence alignment[J]. Parallel Computing. 2009,35(8-9):429-440.
[92] Trapnell C, Schatz MC[DB/OL].http://sourceforge.net/projects/mummergpu/
[93]吴恩华,柳有权.基于图形处理器(GPU)的通用计算[J].计算机辅助设计与图形学学报, 2004, 16(5):609-612.
[94] Buck I, Foley T, Horn D, Sugerman J, Fatahalian K, Houston M, Hanrahan P. Brook for GPUs: stream computing on graphics hardware[C]. In: ACM SIGGRAPH 2004 Papers, Los Angeles, California. ACM, 2004, 777-786
[95] Hou Q, Zhou K, Guo B. BSGP: bulk-synchronous GPU programming[C]. In: ACM SIGGRAPH 2008 papers, Los Angeles, California. ACM, 2008,p. 19.
[96] Lenovo Offcial Site[DB/OL]. http://appserver.lenovo.com.cn/ product_ detail.aspx ?gdsId=A0500009756#,2009
[97] Dawning Offcial Site[DB/OL]. http://www.dawning.com.cn/Product /detail. aspx?id=166,2009
[98] David Tarditi, Sidd Puri, Jose Oglesby. Accelerator: using data parallelism to program GPUs for general-purpose uses[C]. Proceedings of the 2006 ASPLOS Conference, 2006, 34(5): 325-335.
[99] David Luebke. Introduction. In SIGGRAPH 2004 GPGPU Course [R/OL]. http://gpgpu.org/s2004,2004
[100] Nvidia Offcial Site[DB/OL]. http://developer.download.nvidia.com/ compute/cuda/2_3/toolkit/docs/NVIDIA_CUDA_Programming_Guide_2.3.pdf, 2009
[101] Cyril Zeller. NVIDIA CUDA Performance. In SIGGRAPH 2007 GPGPU Course[R/OL].http://gpgpu.org/s2007,2007
[102] Ian Buck, Parallel Programming with CUDA. In SUPERCOMPUTING 2008 Tutorial [R/OL]. http://gpgpu.org/sc2008,2008
[103] Paulius Micikevicius. Optimizing CUDA. In SUPERCOMPUTING 2008 Tutorial [R/OL]. http://gpgpu.org/sc2008,2008
[104] K.W. Yue, W.S. Wijesoma. Improved segmentation and segment association for on-line signature verification[C] , 2000 IEEE International Conference on Systems, Man, and Cybernetics, 2000,(4):2752-2756.
[105] R.S. Kashi, J. Hu, W.L. Nelson, et al. On-line Handwritten Signature Verification Using Hidden Markov Model Features[C]. In Proceedings of the 4th International conference on Document Analysis and Recognition(ICDAR '97), 1997,253-257.
[106] W.S. Wijesima, Mingming Ma, K.W. Yue. On-line Signature Verification Using a Computational Intelligence Approach[J]. Fuzzy Days, 2001,LNCS-2206: 699-711.
[107] F.R. Rioja, M.N. Miyatake, et al. Dynamics Features Extraction for on-Line Signature Verification[C]. Proceedings of the 14th International Conference on Electronics, Communications and Computers (CONIELECOMP’04), 2004, 156-161.
[108] F.A. Julian, et al. An On-Line Signature Verification System Based on Fusion of Local and Global Information[C]. AVBPA 2005, 2005, LNCS-3546: 523-532.
[109]梁循.数据挖掘算法与应用[M].北京:北京大学出版社,2006
[110] J. Lee, H. Yoon, J. soh, et al. Using Geometric Extrema for Segment-to-segment Characteristics Comparison in Online Signature Verification[J]. Pattern Recognition, 2004, 37 (1):93-103.
[111] L.R.B. Schomaker, R. Plamondon. The Relation between Axial Pen Force and Pen-point Kinematics in Handwriting[J]. Biological Cybernecics, 1990, 63(4):277-289.
[112] K.Huang, H. Yan. On-Line Signature Verification Based on Dynamic Segmentation and Global and Local Matching[J]. Optical Engineering, 1995, 34(12):57-59.
[113] K. Zhang, E. Nyssen, H. Sahli. A Multi-stage Online Signature Verification System[J]. Pattern Analysis & Applications, 2002, 5(3): 288-295.
[114] W. Lee, N. Minakrishnan, M.J. Paulik. Improved Segmentation through Dynamic Time Warping for Signature Verification Using Neural Network Classifier[C]. International Conference on Image Processing, 1998, 2(4): 929-933.
[115]金涌,柳健,姜向东.改善手写签名动态特征稳定性的局部相关分析[J].华中理工大学学报, 1998, 26(12):71-73.
[116] J. Brault, R. Plamondon. Segmenting Handwritten Signatures at Their Perceptually Important Points[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1993, 15(9): 953-957.
[117] J.Brault , R. Plamondon. A Complexity Measure of Handwritten Curves: Modeling of Dynamic Signature Forgery[J]. IEEE Transaction on Systems Man and Cybernetics, 1993, 23(2): 400-413.
[118]程开东,董险峰,马驷良.基于极角特征匹配的动态签名鉴别算法[J].吉林大学学报(理学版),2009, 47(5):1006-1012
[119]陈宝林.最优化理论与算法[M].北京:清华大学出版社,2005.
[120]唐远炎,王玲.小波分析与文本文字识别[M].北京:科学出版社, 2004.
[121]关履泰.小波方法与应用[M].北京:高等教育出版社, 2007.
[122] S. Mallat. A Theory of Multiresolution Signal Decomposition: The Wavelet Representation[J]. IEEE Trans. On Pattern Analysis and Machine Intelligence, 1989, 11:674-693.
[123] I. Daubechies. Orthonormal Bases of Compactly Supported Wavelets[J]. Comm. On Pure & Applied Mathematics, 1988, 41(7): 909-996.
[124]程正兴.小波分析算法与应用[M].西安:西安交通大学出版社, 1998.
[125]杨福生.小波变换的工程分析与应用[M].北京:科学出版社,1999.
[126] A. V. Oppenheim, R. W. Schafer, J. R. Buck著,刘树棠,黄建国译. Discrete-Time Signal Processing[M].西安:西安交通大学出版社, 2001.
[127]飞思科技产品研发中心. MATLAB7辅助信号处理技术与应用[M].北京:电子工业出版社,2005
[128] M.J. Quinn,陈文光,武永卫. MPI与OpenMP并行程序设计[M].北京:清华大学出版社,2004
[2] M. Kawagoe, A.Tojo. Fingerprint pattern classification[J]. Pattern Recog- nition, 1984, 17(3):295-303.
[3]刘小华,王燕生.指纹识别技术的发展[J].光学技术, 1998,4:78-80.
[4] Tsai-Yang Jea, and Venu Govindaraju. A minutia-based partial fingerprint recognition system[J].Pattern Recognition, 2005, 38 (10) :1672-1684.
[5] A. Kumar, D.Zhang. Personal recognition usinghand shape and texture [J]. IEEE Tran on Image Processing, 2006, 15(8):2454-2461.
[6]束为,荣钢,边肇祺等.利用掌纹进行身份自动鉴别方法的研究[J].清华大学学报(自然科学版), 1999, 39(1):95-97.
[7] N. Duta, A.K.Jain, K.V. Mardia. Matching of palmprint[J]. Pattern Recog- nition Letters, 2002, 23(4):477-485.
[8] E. Hjelmas, B. K. Low. Face Detection: A Survey[J]. Computer Vision and Image Understanding, 2001, 83(3): 236-274.
[9] L. Hock Koh, S. Ranganath, Y. V. Venkatesh. An integrated automatic face detection and recognition system[J]. Pattern Recognition, 2002, 35(6): 1259-1273.
[10]常卫东,刘完芳,鄢喜爱.虹膜识别的研究现状与发展趋势[J].中国科技信息, 2007,1:246-247.
[11] John Daugman, Recognizing people by their iris patterns[J]. Information Security Technical Report, 1998, 3(1):33-39.
[12] Ke Chen. Speaker Modeling with Various Speech Representations[C]. Biometric Authentication: First International Conference, ICBA 2004, Hong Kong, China, July,2004, 592-599
[13]王亮,胡卫明,谭铁牛.基于步态的身份识别[J].计算机学报, 2003, 26(3): 353-360.
[14]王蕴红,谭铁牛.现代身份鉴别新技术——生物特征识别技术[J].中国基础科学, 2000,(9):4-10.
[15]张公正.关于摹仿笔迹鉴定之探索.公安大学学报(自然科学版), 2002, 27(1): 5-7.
[16] A. K. Jain, F. D. Griess, and S. D. Connell. On-line Signature Verification [J]. Pattern Recognition, 2002, 35(12):2963-2972.
[17] J. G. A. Dolfing, E. H. L. Aarts, and J. J. G. M. Van Oosterhout. On-line signature verification with hidden Markov models[C]. in Proceedings of the International Conference on Pattern Recognition. Brisbane Australia, 1998, 1309–1312.
[18] A. Kholmatov and B. Yanikoglu. Identity authentication using improved online signature verification method[J]. Pattern Recognition Letters, 2005, 26(15):2400–2408.
[19] J. Richiardi and A. Drygajlo. Gaussian mixture models for on-line signature verification[C]. Proceedings of the ACM SIGMM Workshop on Multimedia Biometrics Methods and Applications (WBMA '03). Berkley, Calif, USA, 2003,115–122.
[20] R. Plamondon, G. Lorette. Automatic Signature Verification and Writer Identification—The State of the Art[J]. Pattern Recognition, 1989, 22(2): 107-131.
[21] J. P. Drouhard, R. Sabourin, M. Godbout. A Neural Network Approach to Off-line Signautre Verification Using Directional PDF[J]. Pattern Recognition, 1996, 29(3):415-424.
[22] R. Sabourin, G. Genest, F. J. Preteux. Off-Line Signautre Verification by Local Granulometric Size Distributions[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(9):976-988.
[23]朱勇,谭铁牛,王蕴红.基于笔迹的身份鉴别[J].自动化学报, 2001, 27(2): 229-234.
[24] M. Hanmandlu, M.H.M. Yusof, V. K. Madasu. Off-line signature verification and forgrey detection using fuzzy modeling[J]. Pattern Recognition, 2005, 38(3):341-356.
[25] B. Fang, C.H.Leung, YYTang, et al. Off-line Signature Verification by the Tracking of Feature and Stroke Positions[J]. PatternRecognition, 2003, 36(1):91-101.
[26] K. Huang and H. Yan, Off-line signature verification based on geometric feature extraction and neural network classification [J], Pattern Recognition, 1997, 30(1):9–17.
[27] M.A. Ferrer, J.B. Alonso and C.M. Travieso, Offline geometric parameters for automatic signature verification using fixed-point arithmetic[J], IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(6): 993–997.
[28]沈峰,杨飞,袁余良等.动态手写签名验证技术概述[J].计算机科学, 2003, 30(3):92-95.
[29] R. Plamondon. A Kinematic Theory of rapid Human Movements: Part I. Movement representation and generation[J]. Biological Cybernetics, 1995, 72(4): 295-307.
[30] N.M.Herbst, C.N.Liu. Automatic Signature Verification Based on Accelerometry[J]. IBM Journal Research and Development, 1977, 21(3): 245-253.
[31] W. Nelson and E. Kishon. Use of dynamic features for signature verification[C]. Proceedings of the IEEE. Int. Conf. on Syst., Man, Cybern, Charlottesville, VA, 1991,(1):201–205.
[32] F. Leclerc, R. Plamondon. Automatic signature verification: the state of the art-1989–1993[J]. International Journal of Pattern Recognition and Artificial Intelligence (IJPRAI) , 1994, 8 (3):643–660.
[33] V. S. Nalwa. Automatic on-line signature verification[J]. Proceedings of the IEEE, 1997, 85(2):215–239.
[34] G.K. Gupta and A. McCabe. A review of dynamic handwritten signature verification[R], Technical Report, Department of Computer Science, James Cook University, Townsville, Australia, 1997.
[35] SVC2004[DB/OL]. http://www.cs.ust.hk/SVC2004/index.html, 2004
[36] BMEC2007[DB/OL]. http://biometrics.it-sudparis.eu/BMEC2007/, 2007
[37] BSEC2009[DB/OL]. http://biometrics.it-sudparis.eu/BSEC2009/downloads/BS EC2009_results.pdf, 2009
[38] Y.Qi, B.R.Hunt. Signature Verification Using Global and Grid Features[J]. Pattern Recognition, 1994,27(12):1621-1629.
[39] G.V.Kiran, R.Srinivasa, Rao Kunte, Sudhaker Samuel. On-Line Signature Verification System Using Probabilistic Feature Modelling[J]. International Symposium on Signal Processing and its Applications, 2001,355-358.
[40] G.K.Gupta, R.C.Joyce. A Study of Some Pen Motion Features In Dynamic Handwritten Signature Verification[R].Technical Report, Department of Computer Science, James Cook University, Townsville, Australia,1997.
[41] Y.T.Yuan, C.M.L.Ernest. New Method for Feature Extraction Based on Fractal Behavior[J]. Pergamon Pattern Recognition, 2002, 35:1071-1081.
[42] T.Rhee, S.Cho, J.Kim. On-Line Signature Verification Using Model-Guided Segmentation and Discriminative Feature Selection for Skilled Forgeries [C]. In the 6th Int. Conf. on Document Analysis and Recognition (ICDAR) , 2001.
[43] L.Yang, B.K.Widjaja, R.Prasad. Application of Hidden Markov Models for Signature Verification[J]. Pattern Recognition, 1995, 28(2):161-170.
[44] H.S.Yoon, J.Y.Lee, H.S.Yang. An On-line Signature Verification System Using Hidden Markov Model In Polar Space[C]. Proc. of the Eighth International Workshop on Frontiers in Handwriting Recognition, 2002,329-333.
[45] Daigo Muramatsu, Takashi Matsumoto. An HMM On-line Signature Verification Algorithm[C]. AVBPA 2003, LNCS-2688:233-241.
[46]程开东,栾方军,马驷良.一种基于隐马尔可夫模型的在线手写签名认证算法[J].吉林大学学报(理学版),2008, 46(5):940-943
[47] J.Droughord, R.Plamondon, M.Godbout.A Neural Network Approach to Off-line Signature Verification Using Directional PDF[J]. Pattern Recognition, 1996, 29:415-424.
[48] C. Santos, E.J.R.Justino, F.Bortolozzi, et al. An Off-Line Signature Verification Method based on the Questioned Document Expert's Approach and a Neural Network Classifier [C]. Proceedings of the 9th International Workshop on Frontiers in Handwriting Recognition (IWFHR-9 2004).IEEE, 2004, 498-502.
[49] L. Y. Tseng, T. H. Huang. An online Chinese signature verification scheme based on the ART1 neural network[C]. International Joint Conference on Neural Networks (IJCNN 1992), 1992, 3:624-630.
[50]金涌,柳健.手写签名的概率神经网络识判模型[J].华中理工大学学报, 1999, 27(5):11-13.
[51] P. Mautner, O. Rohlik, V. Matousek, et al. Signature verification using ART-2 neural network[C]. Proceedings of the 9th International Conference on Neural Information Processing (ICONIP '02), 2002, 2:636-639.
[52]李媛,袁余良,沈峰等.一种基于神经网络的动态手写签名验证模型[J].计算机科学, 2005, 32(5):181-184.
[53]刁在筠,刘桂真,宿洁等.运筹学(第三版)[M].北京:高等教育出版社, 2007.
[54]李胜春,丁晓青,陈彦.基于加权动态匹配方法的联机签名鉴别[J].清华大学学报(自然科学版) , 1999,39(9):61-64.
[55]胡航,语音信号处理[M].哈尔滨:哈尔滨工业大学出版社, 2005.
[56]唐降龙,孙广玲,刘家锋等.一种笔段序列匹配联机汉字识别方法[J].计算机研究与发展, 1999,36(12):1472-1476.
[57]柯晶,乔谊正,赵宏.联机自动签名鉴定系统的设计与实现[J].计算机与现代化, 1998,54(2):6-9(48).
[58] M.Parizeau, R.Plamondon. A comparative analysis of regional correlation, dynamical time warping and skeletal tree matching for signature verification [J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1990, 12(7):710- 717.
[59] B.Wirtz. Stroke-based time warping for signature verification[C]. Int. Conf. on Document Analysis and Recognition, 1995,179-182.
[60]金涌,柳健.基于空间曲线弹性匹配的在线手写签名鉴别[J].华中理工大学学报, 1999, 27(5):14-16.
[61] Isao Nakanishi, et al. Optimal User Weighting Fusion in DTW Domain On-Line Signature Verification[C]. AVBPA 2005, LNCS 3546: 758-766.
[62] A. Kholmatov, B. Yanikoglu. Identity authentication using improved online signature verification method[J]. Pattern Recognition Letters, 2005, 26(15): 2400-2408.
[63]郑建彬,徐陶神,朱光喜.基于DTW的在线手写签名验证算法[J].武汉理工大学学报, 2006,30(2):212-215.
[64] David Tarditi, Sidd Puri, Jose Oglesby. Accelerator: using data parallelism to program GPUs for general-purpose uses, Proceedings of the 12thinternational conference on Architectural support for programming languages and operating systems, October 21-25, 2006[C], San Jose, California, 2006.
[65]苏畅,付忠良,谭雨辰.一种在GPU上高精度大型矩阵快速运算的实现[J].计算机应用, 2009, 29(4):1177-1179(1192).
[66]吴恩华.图形处理器用于通用计算的技术、现状及其挑战[J].软件学报, 2004, 15(10):1493-1504.
[67]钱悦.图形处理器CUDA编程模型的应用研究[J].计算机与数字工程, 2008, 36(12):177-180.
[68] Nvidia Offcial Site[DB/OL]. http://www.nvidia.com/
[69] Erik Lindholm, M.J. Kligard, Henry Moreton, A user-programmable vertex engine[C]. Proceedings of the 28th annual conference on Computer graphics and interactive techniques, 2001, 149-158.
[70] Ian Buck, Tim Foley, Daniel Horn, et al. Brook for GPUs: stream computing on graphics hardware[C]. ACM SIGGRAPH 2004 Papers, Los Angeles, California, 2004,777-786.
[71] Mark J. Harris, Greg Coombe,et al. Physically-based visual simulation on graphics hardware[C]. Proceedings of the ACM conference on Graphics hardware, Saarbrucken, 2002,109-118.
[72] Jens Krüger, Rüdiger Westermann. Linear algebra operators for GPU implementation of numerical algorithms[C]. ACM SIGGRAPH 2003 Papers, July 27-31, 2003, San Diego, California, 2003, 22(3): 908-916.
[73] Jens Krüger. Linear algebra on GPUs[R]. ACM SIGGRAPH 2005 Courses, July 31-August 04, 2005, Los Angeles, California, 2005.
[74] Jeff Bolz, Ian Farmer, Eitan Grinspun, et al. Sparse matrix solvers on the GPU: Conjugate gradients and multigrid[C]. ACM SIGGRAPH 2003 Papers, July 27-31, 2003, San Diego, California, 2003, 22(3):917-924.
[75] Nolan Goodnight, Cliff Woolley, Gregory Lewin, et al. A multigrid solver for boundary value problems using programmable graphics hardware[C], Proceedings of the ACM conference on Graphics hardware, July 26-27, 2003, San Diego, California, 2003,102-111.
[76] Karl E. Hillesland, Sergey Molinov, Radek Grzeszczuk. Nonlinear optimization framework for image-based modeling on programmable graphicshardware. ACM SIGGRAPH 2003 Papers, July 27-31, 2003, San Diego, California, 2003, 22(3):925-934.
[77] Timothy J. Purcell, Ian Buck, William R. Mark, et al. Ray tracing on programmable graphics hardware[J]. ACM Transactions on Graphics, 2002, 21(3):703-712.
[78] N.A. Carr, J.D. Hall, J.C. Hart. The ray engine[C]. Proceedings of Graphics Hardware, Saarbrucken, 2002, 37-46 .
[79] Greg Coombe, Mark J. Harris, Anselmo Lastra. Radiosity on graphics hardware[C]. Proceedings of Graphics Interface 2004. London, Ontario, 2004, 161-168.
[80] Kun Zhou, Xin Huang, Weiwei Xu,et al. Direct manipulation of subdivision surfaces on GPUs[C]. Proceedings of ACM SIGGRAPH 2007. San Diego, California,2007, 26(3):91.
[81] Matthias Hopf, Thomas Ertl. Hardware accelerated wavelet transformations [C]. Proceedings of EG/IEEE TCVG Symposium on Visualization. VisSym, Netherlands, 2000, 93-103.
[82] Kenneth Moreland, Edward Angel. The FFT on a GPU[C]. Proceedings of the ACM SIGGRAPH/EUROGRAPHICS conference on Graphics hardware, July 26-27, 2003, San Diego, California, 2003, 112-119.
[83] Martin Rumpf, Robert Strzodka. Using graphics cards for quantized FEM computations[C]. Proceedings of VIIP, Marbella, 2001, 98-107.
[84] E. S. Larsen, M. David. Fast matrix multiplies using graphics hardware[C]. Proceedings of Super Coumputing, Denver, 2001, 55-60.
[85] C.J. Thompson, S. Hahn, M. Oskin, Using modern graphics architectures for general-purpose cumputing: A framework and analysis[C]. Proceedings of International Symposium on Microarchitecture, Istanbul, 2002, 306-317.
[86] Li Wei, Wei Xiaoming, Kaufman Arie. Implementing lattice Boltzmann computation on graphics hardware[J]. The Visual Computer, 2003, (19):44-46.
[87] A.E. Lefohn, J.M. Kniss, C.D. Hansen, et al. Interactive deformation and visualization of level set sufaces using graphics hardware[C]. Proceedings of 14th IEEE Visualization 2003(VIS'03), Seattle, 2003, 75-82.
[88] A.E. Lefohn, J. M. Kniss, C. D. Hansen, et al. A streaming narrow-bandalgorithm: interactive computation and visualization of level sets[C]. ACM SIGGRAPH 2005 Courses, July 31-August 04, 2005, Los Angeles, California, 2005, 243-257.
[89] E.Elsen, P. LeGresley, E. Darve. Large calculation of the flow over a hypersonic vehicle using a GPU[J]. Journal of Computational Physics. 2008, 227(24):10148-10161.
[90] W. Liu, B.Schmidt, G.Voss,et al. Streaming Algorithms for Biological Sequence Alignment on GPUs[J]. IEEE Transactions on Parallel and Distributed Systems. 2007,18(9):1270-1281.
[91] Trapnell C, Schatz MC. Optimizing data intensive GPGPU computations for DNA sequence alignment[J]. Parallel Computing. 2009,35(8-9):429-440.
[92] Trapnell C, Schatz MC[DB/OL].http://sourceforge.net/projects/mummergpu/
[93]吴恩华,柳有权.基于图形处理器(GPU)的通用计算[J].计算机辅助设计与图形学学报, 2004, 16(5):609-612.
[94] Buck I, Foley T, Horn D, Sugerman J, Fatahalian K, Houston M, Hanrahan P. Brook for GPUs: stream computing on graphics hardware[C]. In: ACM SIGGRAPH 2004 Papers, Los Angeles, California. ACM, 2004, 777-786
[95] Hou Q, Zhou K, Guo B. BSGP: bulk-synchronous GPU programming[C]. In: ACM SIGGRAPH 2008 papers, Los Angeles, California. ACM, 2008,p. 19.
[96] Lenovo Offcial Site[DB/OL]. http://appserver.lenovo.com.cn/ product_ detail.aspx ?gdsId=A0500009756#,2009
[97] Dawning Offcial Site[DB/OL]. http://www.dawning.com.cn/Product /detail. aspx?id=166,2009
[98] David Tarditi, Sidd Puri, Jose Oglesby. Accelerator: using data parallelism to program GPUs for general-purpose uses[C]. Proceedings of the 2006 ASPLOS Conference, 2006, 34(5): 325-335.
[99] David Luebke. Introduction. In SIGGRAPH 2004 GPGPU Course [R/OL]. http://gpgpu.org/s2004,2004
[100] Nvidia Offcial Site[DB/OL]. http://developer.download.nvidia.com/ compute/cuda/2_3/toolkit/docs/NVIDIA_CUDA_Programming_Guide_2.3.pdf, 2009
[101] Cyril Zeller. NVIDIA CUDA Performance. In SIGGRAPH 2007 GPGPU Course[R/OL].http://gpgpu.org/s2007,2007
[102] Ian Buck, Parallel Programming with CUDA. In SUPERCOMPUTING 2008 Tutorial [R/OL]. http://gpgpu.org/sc2008,2008
[103] Paulius Micikevicius. Optimizing CUDA. In SUPERCOMPUTING 2008 Tutorial [R/OL]. http://gpgpu.org/sc2008,2008
[104] K.W. Yue, W.S. Wijesoma. Improved segmentation and segment association for on-line signature verification[C] , 2000 IEEE International Conference on Systems, Man, and Cybernetics, 2000,(4):2752-2756.
[105] R.S. Kashi, J. Hu, W.L. Nelson, et al. On-line Handwritten Signature Verification Using Hidden Markov Model Features[C]. In Proceedings of the 4th International conference on Document Analysis and Recognition(ICDAR '97), 1997,253-257.
[106] W.S. Wijesima, Mingming Ma, K.W. Yue. On-line Signature Verification Using a Computational Intelligence Approach[J]. Fuzzy Days, 2001,LNCS-2206: 699-711.
[107] F.R. Rioja, M.N. Miyatake, et al. Dynamics Features Extraction for on-Line Signature Verification[C]. Proceedings of the 14th International Conference on Electronics, Communications and Computers (CONIELECOMP’04), 2004, 156-161.
[108] F.A. Julian, et al. An On-Line Signature Verification System Based on Fusion of Local and Global Information[C]. AVBPA 2005, 2005, LNCS-3546: 523-532.
[109]梁循.数据挖掘算法与应用[M].北京:北京大学出版社,2006
[110] J. Lee, H. Yoon, J. soh, et al. Using Geometric Extrema for Segment-to-segment Characteristics Comparison in Online Signature Verification[J]. Pattern Recognition, 2004, 37 (1):93-103.
[111] L.R.B. Schomaker, R. Plamondon. The Relation between Axial Pen Force and Pen-point Kinematics in Handwriting[J]. Biological Cybernecics, 1990, 63(4):277-289.
[112] K.Huang, H. Yan. On-Line Signature Verification Based on Dynamic Segmentation and Global and Local Matching[J]. Optical Engineering, 1995, 34(12):57-59.
[113] K. Zhang, E. Nyssen, H. Sahli. A Multi-stage Online Signature Verification System[J]. Pattern Analysis & Applications, 2002, 5(3): 288-295.
[114] W. Lee, N. Minakrishnan, M.J. Paulik. Improved Segmentation through Dynamic Time Warping for Signature Verification Using Neural Network Classifier[C]. International Conference on Image Processing, 1998, 2(4): 929-933.
[115]金涌,柳健,姜向东.改善手写签名动态特征稳定性的局部相关分析[J].华中理工大学学报, 1998, 26(12):71-73.
[116] J. Brault, R. Plamondon. Segmenting Handwritten Signatures at Their Perceptually Important Points[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1993, 15(9): 953-957.
[117] J.Brault , R. Plamondon. A Complexity Measure of Handwritten Curves: Modeling of Dynamic Signature Forgery[J]. IEEE Transaction on Systems Man and Cybernetics, 1993, 23(2): 400-413.
[118]程开东,董险峰,马驷良.基于极角特征匹配的动态签名鉴别算法[J].吉林大学学报(理学版),2009, 47(5):1006-1012
[119]陈宝林.最优化理论与算法[M].北京:清华大学出版社,2005.
[120]唐远炎,王玲.小波分析与文本文字识别[M].北京:科学出版社, 2004.
[121]关履泰.小波方法与应用[M].北京:高等教育出版社, 2007.
[122] S. Mallat. A Theory of Multiresolution Signal Decomposition: The Wavelet Representation[J]. IEEE Trans. On Pattern Analysis and Machine Intelligence, 1989, 11:674-693.
[123] I. Daubechies. Orthonormal Bases of Compactly Supported Wavelets[J]. Comm. On Pure & Applied Mathematics, 1988, 41(7): 909-996.
[124]程正兴.小波分析算法与应用[M].西安:西安交通大学出版社, 1998.
[125]杨福生.小波变换的工程分析与应用[M].北京:科学出版社,1999.
[126] A. V. Oppenheim, R. W. Schafer, J. R. Buck著,刘树棠,黄建国译. Discrete-Time Signal Processing[M].西安:西安交通大学出版社, 2001.
[127]飞思科技产品研发中心. MATLAB7辅助信号处理技术与应用[M].北京:电子工业出版社,2005
[128] M.J. Quinn,陈文光,武永卫. MPI与OpenMP并行程序设计[M].北京:清华大学出版社,2004