基于量子神经元的手写体识别方法研究
|
摘要
随着社会的不断发展,手写体字符识别技术被越来越多地应用于生产生活中。尽管研究已经过30多年的时间,但较为通用且识别正确率较高的手写体识别方法仍是人们目前研究的焦点问题。
本论文完成的主要工作及创新点体现在如下几个方面:
首先,本文针对手写体识别研究的背景、现状及方法、难点及应用前景等进行了一些分析研究。另外,本论文还针对手写体样本预处理的平滑去噪、二值化、图像细化、归一化等步骤的实现原理及方法等做了一定的分析研究。
然后,本文在针对手写体识别中常见的粗网格特征、笔划密度特征、投影信号特征和小波变换特征等四种特征提取方法进行分析研究的基础上,提出了两种新的特征提取方法。这两种方法分别为,将粗网格特征与四方向笔划密度特征结合而成的两特征结合特征提取法,以及先提取投影信号然后对其进行小波变换而产生的基于投影信号的小波变换特征提取法。
其次,本文在对量子神经网络(QNN)的相关原理及算法等内容进行分析研究的基础上,结合前面提出的两种特征提取方法,提出了两种新的手写体识别方法,其一为基于两特征结合特征提取法与QNN的识别方法,其二为基于投影信号的小波变换及QNN的识别方法。通过采用MNIST手写数字、金融大写汉字、手写英文等三种样本,对两方法进行了Matlab仿真验证,其结果也表明,两方法对于常见的手写体样本类型都能适用,而且识别正确率也比较高。另外,本论文还对两种新方法进行了分析比较。
在本论文的最后,对全文进行了分析总结与回顾,并对进一步的研究工作做了展望。
With the development of society, the ha n d wr i t t e n-character r e c o g n i t i o n technique has been widely applied to production and daily life. Although the research about the technique has went on 30 years, it is also focus on how to make the handwritten character recognition technique much more common and have higher recognition rate.
The innovative ideas and the main work in this paper are as follows.
At first, some contents of handwritten-character recognition are instructed, just as the research background, current state of research, research difficulty and application. And then, the principle and implementation of pretreatment processes of handwritten character swatch are presented in this paper. The processes include image noise reduction, binarization, thinning of image, normalizing method.
Second, four common methods of feature extraction: rough grid feature extraction, stroke-density feature extraction, the traditional projection characteristic feature extraction and wavelet muhiresolution analysis feature extraction are also researched in this paper. On the basis of these researches, two new methods are introduced. The one is the blend features extraction which is composed of rough grid feature and stroke-density feature extraction, and the other is also a blend features extraction which combines the traditional projection characteristic and wavelet muhiresolution analysis.
Third, based on the research of the basic principle and all kinds of learning algorithm of QNN, two new handwritten-character recognition methods are presented in this paper. The one is composed of QNN and the grid feature and stroke-density feature extraction, the other is composed of QNN and a blend features extraction, which combines the traditional projection characteristic and wavelet muhiresolution analysis feature extraction. The simulator results show that common and higher recognition rate for three swatch types include MNIST handwritten number, Chinese character and English letter. Also, two methods are compared and analysed in the paper.
At last, it makes the summary and review of the whole paper and the forward research aim.
本论文完成的主要工作及创新点体现在如下几个方面:
首先,本文针对手写体识别研究的背景、现状及方法、难点及应用前景等进行了一些分析研究。另外,本论文还针对手写体样本预处理的平滑去噪、二值化、图像细化、归一化等步骤的实现原理及方法等做了一定的分析研究。
然后,本文在针对手写体识别中常见的粗网格特征、笔划密度特征、投影信号特征和小波变换特征等四种特征提取方法进行分析研究的基础上,提出了两种新的特征提取方法。这两种方法分别为,将粗网格特征与四方向笔划密度特征结合而成的两特征结合特征提取法,以及先提取投影信号然后对其进行小波变换而产生的基于投影信号的小波变换特征提取法。
其次,本文在对量子神经网络(QNN)的相关原理及算法等内容进行分析研究的基础上,结合前面提出的两种特征提取方法,提出了两种新的手写体识别方法,其一为基于两特征结合特征提取法与QNN的识别方法,其二为基于投影信号的小波变换及QNN的识别方法。通过采用MNIST手写数字、金融大写汉字、手写英文等三种样本,对两方法进行了Matlab仿真验证,其结果也表明,两方法对于常见的手写体样本类型都能适用,而且识别正确率也比较高。另外,本论文还对两种新方法进行了分析比较。
在本论文的最后,对全文进行了分析总结与回顾,并对进一步的研究工作做了展望。
With the development of society, the ha n d wr i t t e n-character r e c o g n i t i o n technique has been widely applied to production and daily life. Although the research about the technique has went on 30 years, it is also focus on how to make the handwritten character recognition technique much more common and have higher recognition rate.
The innovative ideas and the main work in this paper are as follows.
At first, some contents of handwritten-character recognition are instructed, just as the research background, current state of research, research difficulty and application. And then, the principle and implementation of pretreatment processes of handwritten character swatch are presented in this paper. The processes include image noise reduction, binarization, thinning of image, normalizing method.
Second, four common methods of feature extraction: rough grid feature extraction, stroke-density feature extraction, the traditional projection characteristic feature extraction and wavelet muhiresolution analysis feature extraction are also researched in this paper. On the basis of these researches, two new methods are introduced. The one is the blend features extraction which is composed of rough grid feature and stroke-density feature extraction, and the other is also a blend features extraction which combines the traditional projection characteristic and wavelet muhiresolution analysis.
Third, based on the research of the basic principle and all kinds of learning algorithm of QNN, two new handwritten-character recognition methods are presented in this paper. The one is composed of QNN and the grid feature and stroke-density feature extraction, the other is composed of QNN and a blend features extraction, which combines the traditional projection characteristic and wavelet muhiresolution analysis feature extraction. The simulator results show that common and higher recognition rate for three swatch types include MNIST handwritten number, Chinese character and English letter. Also, two methods are compared and analysed in the paper.
At last, it makes the summary and review of the whole paper and the forward research aim.
引文
[1]清风.文字的起源与发展. wyq550730.blog.sohu.com/28158962.html, 2007-01-03
[2]郭姝伶.中国文字的演变与视觉运用. www.yywzw.com,2007-01-12
[3]岳晓峰,焦圣喜,韩立强,等.模式识别中的光字符识别技术及应用综述.河北工业科技,2006, 23(5):312-316
[4]天下维客. OCR技术的发展历史. www.allwiki.com/wiki,2008-07-04
[5]丁慧东.脱机手写体汉字识别研究:[东北师范大学硕士学位论文].长春:东北师范大学,2005,9-45
[6]张猛,余仲秋,姚绍文.手写体数字识别中图像预处理的研究.微计算机信息,2006, 22(6-1): 256-258
[7]袁氢.基于特征融合与神经网络的手写体数字识别技术研究:[武汉科技大学硕士学位论文].武汉:武汉科技大学,2007, 6-36
[8]任丹,陈学峰.手写数字识别的原理及应用.计算机时代,2007,3:17-21
[9]温尚清,郝志峰,廖芹,等.基于贝叶斯网络的脱机手写体汉字智能识别.计算机辅助工程, 2006, 3:72-89
[10]王建雄,刘应龙.基于人工神经网络的数字识别系统的研究.计算机技术与发展,2006, 16(5): 26-30
[11]桂杰,李晓风,唐磊,等.多分类器组合及其应用于手写体数字识别.计算机工程与设计, 2007,28(11): 2633-2636
[12]赵锋,薛惠锋,王伟,等.采用多级分类器的手写数字识别技术研究.微电子学与计算机, 2006,23(12): 30-37
[13]洪留荣,王耀才.应用图论和基元方向信息的手写数字识别.计算机工程, 2006, 32(3): 34-36
[14]尚磊,刘风进.基于支持向量机的手写体数字识别.兵工自动化,2007, 26(3): 39-41
[15]刘接胜.BP神经网络改进及其在手写数字识别中的应用.福建电脑, 2007, 10: 96-97
[16]李望晨,张池平.改进BP神经网络在手写数字识别中的性能研究.信息技术与信息化,2006, 5: 104-106
[17]叶佩,江涛.基于BP特征筛选的模糊聚类手写体数字识别.武汉理工大学学报,2007, 29(6): 128-130
[18]李三平,岳振军.基于概率神经网络的手写数字识别系统的MATLAB实现.军事通信技术, 2005,26(1):54-57
[19]孙征,李宁.用专家乘积系统实现手写体数字识别.计算机仿真,2006, 23(5): 197-214
[20]李飞,郑宝玉,赵生妹.量子神经网络及其应用.电子与信息学报,2004, 26(8): 1332-1339
[21]吴成东,刘文涵,傅小菲,等.基于粗网格神经网络的车牌字符识别方法.沈阳建筑大学学报(自然科学版), 2007, 23(4): 693-697
[22]赵莉,杨莉,林晓.基于投影信号和小波分析的字符特征提取方法.山东建筑大学学报,2007, 22(3): 247-250
[23]陈北京,王蔚,宋加涛,等.一种融合二值边缘特征和灰度特征的人脸识别方法,电子学报, 2009, 6:1180-1184
[24]毛以芳,吴天爱.基于弹性网格和方向线素特征的脱机手写汉字识别.辽宁省交通高等专科学校学报, 2008, 1: 38-39
[25] Lee S W, Park J S. Nonlinear Shape Normalization Methods for theRecognition of Large-set Handwritten Characters. Pattern Recognition,1994,27 (7):895-902
[26]高学,金连文,尹俊勋.一种基于笔画密度的弹性网格特征提取方法.模式识别与人工智能, 2002, 15(3): 351-354
[27]王烁.小波变换与Fourier变换的比较.河北理工大学学报(自然科学版),2008,30(2): 23-26
[28]钟珞,饶文碧,邹承明.人工神经网络及其融合应用技术.北京:科学出版社,2007: 60-68
[29]卢湖川,张继霞,张明修.基于Hough变换头部检测与跟踪的方法研究.系统仿真学报,2008, 20(8): 2127-2132
[30]董冀媛,穆志纯,王瑜.基于力场收敛特征的多姿态人耳识别.计算机应用研究,2009, 6: 2370-2373
[31]武文辉,岳云天.基于Zernike矩和DCT变换的数字水印算法.计算机工程, 2009, 35(13): 174-176
[32]刘会金,吴玉蓉,熊玲玲.基于Daubechies小波的多分辨分解在电压闪变信号分析中的应用.继电器, 2004, 32(13):6-11
[33]黄海宁,李志舜.小波分析理论及其应用.鱼雷技术, 1997,5(3):1-6
[34] Parist R,et al. Car plate recognition by neural networks and image Processing. Proc.IEEE International Symposium on Circuit and Systems, USA.2000,5(3):31-37
[35]吴茹石,朱大奇,彭力.基于多层激励函数量子神经网络的字符识别算法.数据采集与处理, 2007, 22(4): 401-406
[36] Cheng-Lin Liu,Hiromichi Fujisawa. Classification and Learning for Character Recognition: Comparison of Methods and Remaining Problems. Proc. Int. Workshop on Neural Networks and Learning in Document Analysis and Recognition, Seoul, Korea, August, 2005
[37] M. Blumenstein, B. Verma ,H. Basli. A Novel Feature Extraction Technique for the Recognition of Segmented Handwritten Characters. In:Proceedings of the Seventh International Conference on Document Analysis and Recognition (ICDAR 2003) , Aug. 2003:137-141,vol.1
[38] M. Hanmandlu,M. Vamsi Krishna, P.Chaitanya Krishna. Some approaches to the recognition of handwritten numerals. National Conference on Document Analysis and Recognition,Mandya, India,2001, 13-14 July
[39] Alessandro L. Koerich, Robert Sabourin, Ching Y. Suen. Recognition and Verification of Unconstrained Handwritten Words. IEEE transactions on pattern analysis and machine intelligence ,2005, 27(10):1509-1522
[40]罗佳,王玲.基于凹凸特性笔顺编码的手写体数字识别方法.计算机工程与科学,2007, 29(5): 69-108
[41]解光军,庄镇泉.量子神经网络.计算机科学, 2001, 28(7): 1-6
[42]李飞,赵生妹,等.量子神经元特性研究.电路与系统学报,2004,9(4):76-80
[43]郑建国,覃朝勇.量子计算进展与展望.计算机应用研究, 2008,25(3):641-645
[44] Behrman E C,Niemel J,et al. A quantum dot neural network. In:Proc.of the 4th Workshop on Phys. of Comp, Boston, 1996:22-24
[45] Bob Ricks, Dan Ventura. Training a Quantum Neural Network. Neural Information processing systems,2003: 1019-1026
[46]邓铭辉,孙枫,张志.一种基于MATLAB的手写字母的神经网络识别方法.应用科技,2001, 28(10): 28-30
[47]张亮,方康玲,龚剑,等.基于MATLAB神经网络的工业现场数字字符识别.微计算机信息, 2007, 23(4-3): 299-301
[48] J.W. Turkey.Exploratory Data Analysis. Addison-Wesley, Reading, Mass., 1977
[49]周姗姗,柴金广.图像预处理的滤波算法研究.科学技术与工程,2009, 9(23):3830-3839
[50]王俊芳,王正欢,王敏.常用图像去噪滤波方法分析.现代商贸工业,2009, 16:310-311
[51]李刚,宋文静.基于图像直方图的车牌图像二值化方法研究.交通运输系统工程与信息,2009, 9(1):113-116
[52]余松熠,周源华,张瑞.数字图像处理.上海:上海交通大学出版社,2007: 9-30
[53] A.Rosenfeld,A.C.Kak. Digital Picture Processing. Academic press,New York,1982, Vol.2
[54] R.M.Haralick, L.G.ShaPiry. Survey:Image Segmentation Techniques, Computer Vision Graphics and Image Processing,1985, Vol.29:100-132
[55] D.P.Panda,A.Rosenfeld. Image Segmentation by Pixel Classification in (Cray Level,Edge Value)Space,IEEE Transactions on Computers,1978, C-27:875-879
[56] C.J.Hiditch. Linear Skeletons From Square Cupboards. Machine Inte1ligence.(B.Meltzer and D.Michie.Eds).New York: Amer.Elsevier.1969, Vol.4: 403-420
[57] E.S.Deutsch. Thinning algorithms on rectangular,hexagonal,and triangular arrays. Communiactions of the ACM,1972, 15(9):827-837
[58] T.Y.Zhang,C.Y.Suen. A Fast Parallel Algorithm for Thinning Digital Patterns. Communications, ACM,1984,27(3):236-239
[59]厉旭,杨杰.基于神经网络的多识别器在字符识别中的应用.交通与计算机, 2001增刊,19(101): 89-92
[60]杨明,刘强,尹忠科,等.基于轮廓追踪的字符识别特征提取.计算机工程与应用, 2007,43(20): 207-209
[61]任春辉,魏平,肖先赐.改进的Morlet小波在信号特征提取中的应用.电波科学学报, 2003, 18(6):633-637
[62]闫传鹏.Y.Meyer型小波的构造现.浙江科技学院学报,2006,18(3):177-179
[63]高成.Matlab小波分析与应用(第2版).北京:国防工业出版社,2007: 6-28
[64]庄德文,周德龙,王宪保.基于Gabor变换的每类单个训练样本人脸识别研究.计算机应用研究,2009,6: 2379-2382
[65]孔凡辉.基于小波矩的印刷体英文字符识别研究.哈尔滨商业大学学报(自然科学版), 2007,23(6): 694-697
[66]张伟林.钢索检测信号降噪处理的小波分析.安徽建筑工业学院学报(自然科学版),2007, 15(1): 6-8
[67]苏清华,郭淑会.Haar小波基的多分辨分析生成.中国水运,2006,4(16):136-137
[68] Brito N S P, Souza B A,Pires F A C. Daubechies Wavelets in Quality of Electrical Power.In: The 1998 International Conference on Harmonics and Quality of Power. Athens (Greece),1998:511-515
[69]刘明贵,岳向红,杨永波,等.基于Sym小波和BP神经网络的基桩缺陷智能化识别.岩石力学与工程学报, 2007,z1: 3484-3488
[70]任春辉,魏平,肖先赐.改进的Morlet小波在信号特征提取中的应用.电波科学学报,2003, 18(6):633-637
[71]轩建平,史铁林,廖广兰,等.coiflet小波构造与设计.华中科技大学学报(自然科学版), 2006, 34(4): 73-75
[72] Marasovich J. Biorthogonal mutiwavelets Dissertation. Vanderbilt University, Nashville: TN,1996
[73]谷德军,王东晓,纪忠萍,等.墨西哥帽小波变换的影响域和计算方案新探讨.应用气象学报,2009, 20(1): 62-69
[74]任勋益,王汝传,祁正华.消失矩对小波分析求解自相似参数Hurst的影响研究.电子与信息学报,2007,29(9): 2257-2261
[75] Mallat, S. A theory for multiresolution signal decomposition:the wavelet representation. IEEE Trans. on Pattern Analysis and Machine Intelligence,1989,11(7): 674~693
[76]杜建卫,程乾生,刘乃强,等.基于小波变换与分形的中药指纹图谱的特征提取.信号处理, 2006, 22(5): 719-723
[77] EZHOV A,VENTURE D. Quantum neural networks. In:Kasabov N ed.Future Directions for Intelligent Systems and Information Sciences. Springer-Verlag, Heidelberg, 2000:213-234
[78] Benioff P A. Quantum mechanical Hamiltonian model of turning machine. J.Stat.Phys.,1982, 29(3):515-546
[79] Feynman R P. Simulating physics with computers. Int J Theor Phys, 1982, 21(6, 7): 467-488
[80] Deutsch D. Quantum theory,the Church-turing Principle and the universal quantum computer. Proc. of Roy.Soc.of London.A,1985, A400:97-117
[81] Shor P W. Algorithms for quantum computation:Discrete logarithms and factoring. In: Proc of the 35th Annual Symp. on Foundations of Computer Science. New Mexico:IEEE Computer Society Press, 1994: 124-134
[82] Grover L K. A fast quantum mechanical algorithm for database search. In:Proc. Of the 28th Annual ACM Symposium the Theory of Computing, New York,1996: 212-219
[83] Chrisley R. Quantum learning. In:Pylkk?nen P. and Pylkk? P. Editors New Directions in Cognitive Science:Proc. of Int. Symp. on Finish Association of Artificial Intelligence,Lapland,1995:77-89
[84] Menneer T,Narayanan A. Quantum-inspired neural networks. Tech.Rep. R329, Univ.of Exeter,1995
[85] Menneer T. Quantum artificial neural networks: [Ph.D. thesis]. UK:The Univ. of Exeter, 1998
[86] Ventura D,Martinez T R.Quantum associative memory. Information Sciences,2000,124(1-4): 273-296
[87] Li Wei-gang. A study of parallel self-organizing map. xxx.lanl.gov/quant-ph/9808025,1998
[88] Li Wei-gang. Quantum neural computing study. www.cic.ubn.br/weigang/qc,1999
[89] Ventura D, Martinez T R. An artificial neuron with quantum mechanical Properties. In: Proc.of the Int. Conf.on Artificial Neural Networks and Genetic Algorithms, Norwich, 1997:482-485
[90] Chrisley R. Learning in non-superpositional quantum neurocomputer. Pylkk?nen P and Pylkk? P(Ed.),Brain,Mind,Physics,Amsterdam IOS Press,1997: 126-139
[91]解光军,周典,等.基于量子门组单元的神经网络及其应用.系统工程理论与实践, 2005,25(5): 113-117
[92]李士勇,李盼池.量子计算与量子优化算法.哈尔滨:哈尔滨工业大学出版社,2009: 21-29
[93]吴茹石,彭力,基于量子神经网络的手写体数字识别方法研究.计算机工程与设计, 2007, 28(18):4462-4465
[94]熊和金,陈德军.智能信息处理.北京:国防工业出版社,2006:257-278
[95] Hopfield J.J. Neural networks and physical systems with emergent collective computational properties.In:Proc.Nat.Acad.Sci(USA)1983,79: 2554-2558
[96] Penrose,Roger. The Road to reality,A complete guide to the laws of the universe. Random House Inc, 2005
[97]解光军.量子神经计算.合肥工业大学学报(自然科学版),2002,25(3):355-359
[98]庄镇泉,李斌,等.量子神经计算和量子遗传算法的理论分析和应用.高技术通讯, 2005, 15(7): 1-5
[99]吕强,俞金寿.量子神经元结构设计及其应用.控制与决策,2007,22(9):1022-1026
[100]周树德,王岩,等.量子神经网络.中国智能自动化会议CIAC 2003论文集(上册).香港:香港中文大学出版社, 2003, 163-168
[101] Karayiannis N B, Purushothaman G. Fuzzy pattern classification using feed forward neural networks with multilevel hidden neurons. IEEE Transaction on Neural Networks,1994, 5(2):127-132
[102]易文娟,郁梅,蒋刚毅.Contourlet:一种有效的方向多尺度变换分析方法.计算机应用研究, 2006, 9:18-22
[2]郭姝伶.中国文字的演变与视觉运用. www.yywzw.com,2007-01-12
[3]岳晓峰,焦圣喜,韩立强,等.模式识别中的光字符识别技术及应用综述.河北工业科技,2006, 23(5):312-316
[4]天下维客. OCR技术的发展历史. www.allwiki.com/wiki,2008-07-04
[5]丁慧东.脱机手写体汉字识别研究:[东北师范大学硕士学位论文].长春:东北师范大学,2005,9-45
[6]张猛,余仲秋,姚绍文.手写体数字识别中图像预处理的研究.微计算机信息,2006, 22(6-1): 256-258
[7]袁氢.基于特征融合与神经网络的手写体数字识别技术研究:[武汉科技大学硕士学位论文].武汉:武汉科技大学,2007, 6-36
[8]任丹,陈学峰.手写数字识别的原理及应用.计算机时代,2007,3:17-21
[9]温尚清,郝志峰,廖芹,等.基于贝叶斯网络的脱机手写体汉字智能识别.计算机辅助工程, 2006, 3:72-89
[10]王建雄,刘应龙.基于人工神经网络的数字识别系统的研究.计算机技术与发展,2006, 16(5): 26-30
[11]桂杰,李晓风,唐磊,等.多分类器组合及其应用于手写体数字识别.计算机工程与设计, 2007,28(11): 2633-2636
[12]赵锋,薛惠锋,王伟,等.采用多级分类器的手写数字识别技术研究.微电子学与计算机, 2006,23(12): 30-37
[13]洪留荣,王耀才.应用图论和基元方向信息的手写数字识别.计算机工程, 2006, 32(3): 34-36
[14]尚磊,刘风进.基于支持向量机的手写体数字识别.兵工自动化,2007, 26(3): 39-41
[15]刘接胜.BP神经网络改进及其在手写数字识别中的应用.福建电脑, 2007, 10: 96-97
[16]李望晨,张池平.改进BP神经网络在手写数字识别中的性能研究.信息技术与信息化,2006, 5: 104-106
[17]叶佩,江涛.基于BP特征筛选的模糊聚类手写体数字识别.武汉理工大学学报,2007, 29(6): 128-130
[18]李三平,岳振军.基于概率神经网络的手写数字识别系统的MATLAB实现.军事通信技术, 2005,26(1):54-57
[19]孙征,李宁.用专家乘积系统实现手写体数字识别.计算机仿真,2006, 23(5): 197-214
[20]李飞,郑宝玉,赵生妹.量子神经网络及其应用.电子与信息学报,2004, 26(8): 1332-1339
[21]吴成东,刘文涵,傅小菲,等.基于粗网格神经网络的车牌字符识别方法.沈阳建筑大学学报(自然科学版), 2007, 23(4): 693-697
[22]赵莉,杨莉,林晓.基于投影信号和小波分析的字符特征提取方法.山东建筑大学学报,2007, 22(3): 247-250
[23]陈北京,王蔚,宋加涛,等.一种融合二值边缘特征和灰度特征的人脸识别方法,电子学报, 2009, 6:1180-1184
[24]毛以芳,吴天爱.基于弹性网格和方向线素特征的脱机手写汉字识别.辽宁省交通高等专科学校学报, 2008, 1: 38-39
[25] Lee S W, Park J S. Nonlinear Shape Normalization Methods for theRecognition of Large-set Handwritten Characters. Pattern Recognition,1994,27 (7):895-902
[26]高学,金连文,尹俊勋.一种基于笔画密度的弹性网格特征提取方法.模式识别与人工智能, 2002, 15(3): 351-354
[27]王烁.小波变换与Fourier变换的比较.河北理工大学学报(自然科学版),2008,30(2): 23-26
[28]钟珞,饶文碧,邹承明.人工神经网络及其融合应用技术.北京:科学出版社,2007: 60-68
[29]卢湖川,张继霞,张明修.基于Hough变换头部检测与跟踪的方法研究.系统仿真学报,2008, 20(8): 2127-2132
[30]董冀媛,穆志纯,王瑜.基于力场收敛特征的多姿态人耳识别.计算机应用研究,2009, 6: 2370-2373
[31]武文辉,岳云天.基于Zernike矩和DCT变换的数字水印算法.计算机工程, 2009, 35(13): 174-176
[32]刘会金,吴玉蓉,熊玲玲.基于Daubechies小波的多分辨分解在电压闪变信号分析中的应用.继电器, 2004, 32(13):6-11
[33]黄海宁,李志舜.小波分析理论及其应用.鱼雷技术, 1997,5(3):1-6
[34] Parist R,et al. Car plate recognition by neural networks and image Processing. Proc.IEEE International Symposium on Circuit and Systems, USA.2000,5(3):31-37
[35]吴茹石,朱大奇,彭力.基于多层激励函数量子神经网络的字符识别算法.数据采集与处理, 2007, 22(4): 401-406
[36] Cheng-Lin Liu,Hiromichi Fujisawa. Classification and Learning for Character Recognition: Comparison of Methods and Remaining Problems. Proc. Int. Workshop on Neural Networks and Learning in Document Analysis and Recognition, Seoul, Korea, August, 2005
[37] M. Blumenstein, B. Verma ,H. Basli. A Novel Feature Extraction Technique for the Recognition of Segmented Handwritten Characters. In:Proceedings of the Seventh International Conference on Document Analysis and Recognition (ICDAR 2003) , Aug. 2003:137-141,vol.1
[38] M. Hanmandlu,M. Vamsi Krishna, P.Chaitanya Krishna. Some approaches to the recognition of handwritten numerals. National Conference on Document Analysis and Recognition,Mandya, India,2001, 13-14 July
[39] Alessandro L. Koerich, Robert Sabourin, Ching Y. Suen. Recognition and Verification of Unconstrained Handwritten Words. IEEE transactions on pattern analysis and machine intelligence ,2005, 27(10):1509-1522
[40]罗佳,王玲.基于凹凸特性笔顺编码的手写体数字识别方法.计算机工程与科学,2007, 29(5): 69-108
[41]解光军,庄镇泉.量子神经网络.计算机科学, 2001, 28(7): 1-6
[42]李飞,赵生妹,等.量子神经元特性研究.电路与系统学报,2004,9(4):76-80
[43]郑建国,覃朝勇.量子计算进展与展望.计算机应用研究, 2008,25(3):641-645
[44] Behrman E C,Niemel J,et al. A quantum dot neural network. In:Proc.of the 4th Workshop on Phys. of Comp, Boston, 1996:22-24
[45] Bob Ricks, Dan Ventura. Training a Quantum Neural Network. Neural Information processing systems,2003: 1019-1026
[46]邓铭辉,孙枫,张志.一种基于MATLAB的手写字母的神经网络识别方法.应用科技,2001, 28(10): 28-30
[47]张亮,方康玲,龚剑,等.基于MATLAB神经网络的工业现场数字字符识别.微计算机信息, 2007, 23(4-3): 299-301
[48] J.W. Turkey.Exploratory Data Analysis. Addison-Wesley, Reading, Mass., 1977
[49]周姗姗,柴金广.图像预处理的滤波算法研究.科学技术与工程,2009, 9(23):3830-3839
[50]王俊芳,王正欢,王敏.常用图像去噪滤波方法分析.现代商贸工业,2009, 16:310-311
[51]李刚,宋文静.基于图像直方图的车牌图像二值化方法研究.交通运输系统工程与信息,2009, 9(1):113-116
[52]余松熠,周源华,张瑞.数字图像处理.上海:上海交通大学出版社,2007: 9-30
[53] A.Rosenfeld,A.C.Kak. Digital Picture Processing. Academic press,New York,1982, Vol.2
[54] R.M.Haralick, L.G.ShaPiry. Survey:Image Segmentation Techniques, Computer Vision Graphics and Image Processing,1985, Vol.29:100-132
[55] D.P.Panda,A.Rosenfeld. Image Segmentation by Pixel Classification in (Cray Level,Edge Value)Space,IEEE Transactions on Computers,1978, C-27:875-879
[56] C.J.Hiditch. Linear Skeletons From Square Cupboards. Machine Inte1ligence.(B.Meltzer and D.Michie.Eds).New York: Amer.Elsevier.1969, Vol.4: 403-420
[57] E.S.Deutsch. Thinning algorithms on rectangular,hexagonal,and triangular arrays. Communiactions of the ACM,1972, 15(9):827-837
[58] T.Y.Zhang,C.Y.Suen. A Fast Parallel Algorithm for Thinning Digital Patterns. Communications, ACM,1984,27(3):236-239
[59]厉旭,杨杰.基于神经网络的多识别器在字符识别中的应用.交通与计算机, 2001增刊,19(101): 89-92
[60]杨明,刘强,尹忠科,等.基于轮廓追踪的字符识别特征提取.计算机工程与应用, 2007,43(20): 207-209
[61]任春辉,魏平,肖先赐.改进的Morlet小波在信号特征提取中的应用.电波科学学报, 2003, 18(6):633-637
[62]闫传鹏.Y.Meyer型小波的构造现.浙江科技学院学报,2006,18(3):177-179
[63]高成.Matlab小波分析与应用(第2版).北京:国防工业出版社,2007: 6-28
[64]庄德文,周德龙,王宪保.基于Gabor变换的每类单个训练样本人脸识别研究.计算机应用研究,2009,6: 2379-2382
[65]孔凡辉.基于小波矩的印刷体英文字符识别研究.哈尔滨商业大学学报(自然科学版), 2007,23(6): 694-697
[66]张伟林.钢索检测信号降噪处理的小波分析.安徽建筑工业学院学报(自然科学版),2007, 15(1): 6-8
[67]苏清华,郭淑会.Haar小波基的多分辨分析生成.中国水运,2006,4(16):136-137
[68] Brito N S P, Souza B A,Pires F A C. Daubechies Wavelets in Quality of Electrical Power.In: The 1998 International Conference on Harmonics and Quality of Power. Athens (Greece),1998:511-515
[69]刘明贵,岳向红,杨永波,等.基于Sym小波和BP神经网络的基桩缺陷智能化识别.岩石力学与工程学报, 2007,z1: 3484-3488
[70]任春辉,魏平,肖先赐.改进的Morlet小波在信号特征提取中的应用.电波科学学报,2003, 18(6):633-637
[71]轩建平,史铁林,廖广兰,等.coiflet小波构造与设计.华中科技大学学报(自然科学版), 2006, 34(4): 73-75
[72] Marasovich J. Biorthogonal mutiwavelets Dissertation. Vanderbilt University, Nashville: TN,1996
[73]谷德军,王东晓,纪忠萍,等.墨西哥帽小波变换的影响域和计算方案新探讨.应用气象学报,2009, 20(1): 62-69
[74]任勋益,王汝传,祁正华.消失矩对小波分析求解自相似参数Hurst的影响研究.电子与信息学报,2007,29(9): 2257-2261
[75] Mallat, S. A theory for multiresolution signal decomposition:the wavelet representation. IEEE Trans. on Pattern Analysis and Machine Intelligence,1989,11(7): 674~693
[76]杜建卫,程乾生,刘乃强,等.基于小波变换与分形的中药指纹图谱的特征提取.信号处理, 2006, 22(5): 719-723
[77] EZHOV A,VENTURE D. Quantum neural networks. In:Kasabov N ed.Future Directions for Intelligent Systems and Information Sciences. Springer-Verlag, Heidelberg, 2000:213-234
[78] Benioff P A. Quantum mechanical Hamiltonian model of turning machine. J.Stat.Phys.,1982, 29(3):515-546
[79] Feynman R P. Simulating physics with computers. Int J Theor Phys, 1982, 21(6, 7): 467-488
[80] Deutsch D. Quantum theory,the Church-turing Principle and the universal quantum computer. Proc. of Roy.Soc.of London.A,1985, A400:97-117
[81] Shor P W. Algorithms for quantum computation:Discrete logarithms and factoring. In: Proc of the 35th Annual Symp. on Foundations of Computer Science. New Mexico:IEEE Computer Society Press, 1994: 124-134
[82] Grover L K. A fast quantum mechanical algorithm for database search. In:Proc. Of the 28th Annual ACM Symposium the Theory of Computing, New York,1996: 212-219
[83] Chrisley R. Quantum learning. In:Pylkk?nen P. and Pylkk? P. Editors New Directions in Cognitive Science:Proc. of Int. Symp. on Finish Association of Artificial Intelligence,Lapland,1995:77-89
[84] Menneer T,Narayanan A. Quantum-inspired neural networks. Tech.Rep. R329, Univ.of Exeter,1995
[85] Menneer T. Quantum artificial neural networks: [Ph.D. thesis]. UK:The Univ. of Exeter, 1998
[86] Ventura D,Martinez T R.Quantum associative memory. Information Sciences,2000,124(1-4): 273-296
[87] Li Wei-gang. A study of parallel self-organizing map. xxx.lanl.gov/quant-ph/9808025,1998
[88] Li Wei-gang. Quantum neural computing study. www.cic.ubn.br/weigang/qc,1999
[89] Ventura D, Martinez T R. An artificial neuron with quantum mechanical Properties. In: Proc.of the Int. Conf.on Artificial Neural Networks and Genetic Algorithms, Norwich, 1997:482-485
[90] Chrisley R. Learning in non-superpositional quantum neurocomputer. Pylkk?nen P and Pylkk? P(Ed.),Brain,Mind,Physics,Amsterdam IOS Press,1997: 126-139
[91]解光军,周典,等.基于量子门组单元的神经网络及其应用.系统工程理论与实践, 2005,25(5): 113-117
[92]李士勇,李盼池.量子计算与量子优化算法.哈尔滨:哈尔滨工业大学出版社,2009: 21-29
[93]吴茹石,彭力,基于量子神经网络的手写体数字识别方法研究.计算机工程与设计, 2007, 28(18):4462-4465
[94]熊和金,陈德军.智能信息处理.北京:国防工业出版社,2006:257-278
[95] Hopfield J.J. Neural networks and physical systems with emergent collective computational properties.In:Proc.Nat.Acad.Sci(USA)1983,79: 2554-2558
[96] Penrose,Roger. The Road to reality,A complete guide to the laws of the universe. Random House Inc, 2005
[97]解光军.量子神经计算.合肥工业大学学报(自然科学版),2002,25(3):355-359
[98]庄镇泉,李斌,等.量子神经计算和量子遗传算法的理论分析和应用.高技术通讯, 2005, 15(7): 1-5
[99]吕强,俞金寿.量子神经元结构设计及其应用.控制与决策,2007,22(9):1022-1026
[100]周树德,王岩,等.量子神经网络.中国智能自动化会议CIAC 2003论文集(上册).香港:香港中文大学出版社, 2003, 163-168
[101] Karayiannis N B, Purushothaman G. Fuzzy pattern classification using feed forward neural networks with multilevel hidden neurons. IEEE Transaction on Neural Networks,1994, 5(2):127-132
[102]易文娟,郁梅,蒋刚毅.Contourlet:一种有效的方向多尺度变换分析方法.计算机应用研究, 2006, 9:18-22