红细胞图像自动识别的关键技术研究
|
摘要
红细胞分类计数是医学临床检验的一个重要项目,也是判断各种血液疾病和其他相关疾病的重要依据。随着计算机图像处理与分析在医学领域的应用越来越广泛,应用先进的图像处理技术和模式识别的方法检查血细胞总数及血细胞分类计数成为医学辅助诊断的一种重要方法。它能有效减少主观干扰,部分代替人的劳动,改进使用血细胞自动分析仪存在的不能用目视观察细胞形态,不能够保留每次测试样本,成本昂贵等问题,提供了一条医学诊断的技术途径。
本课题研究运用图像处理和模式识别技术实现不同形态红细胞的分类,以提高红细胞检验的准确度和精密度;研究了包括图像预处理、特征提取与分类识别等一整套基本算法;重点研究了红细胞的图像分割和特征提取,并将特征选择子集的结果用于红细胞的分类,取得了较好的结果。
1.在图像分割研究方面,通过对阈值分割、边缘检测、流域分割等分割方法的研究,提出了一种重叠粘连细胞的新的分割方法。该算法实现简单,效果理想,能较好地还原单个细胞的原始形状。
2.借鉴细胞医学目视分类的经验,借鉴在图像特征提取方面已有的研究成果,提取了对细胞的形状、大小等定量描述的细胞形态学参数;通过实验研究,增加了红细胞纹理特征的提取,构建了有效的特征集合。此外,还改进了圆形度的表达式以提高分类准确率。
3.研究和设计了多级支持向量机分类器对12类红细胞进行识别,能够在少量样本的情况下,得到较好的分类预测结果。
本课题是图像处理和模式识别在医学领域的一个应用性研究,本研究结果具有理论价值和实际应用意义。
The count and recognition of red blood cells plays an important role in modern clinical practice. At the same time, it is the key foundation for diagnosing kinds of blood diseases and other pertinent diseases. With the digital image processing and analysis has been widely applied in many medical areas, advanced image processing and pattern recognition technology, which is used in the sum and sort counting of blood corpuscles, is one of the important methods in medical-aided diagnosis. The technology effectively reduced subjective influence, partly replacing the labor works and improving the disadvantages of blood corpuscle analyzing apparatuses used currently in hospital, for example it can't observe the shape of the cells, can't save the swatch of the test, and the machine is very expensive, and so on.
The study use the technology of image processing and pattern recognition to classify the red blood cells in different shapes, in order to enhance the correctness and exactness; Bring forward a set of basic algorithms including pretreatment, feature extraction and classification; Most work has been focused on the image segmentation and feature extraction. Satisfying results have been reached by the selected feature parameters acting on erythrocytes classification.
1. Study classical image segmentation method such as threshold segmentation, edge detection, watershed and etc, design a new algorithm for automatically separating overlap cells images. The algorithm is simple and effective, it can obtain every cell's original shape preferably.
2. According to the eyeballing experience of erythrocytes classification, combining with the former work in feature extraction, quantification described morphology parameters, such as shape and size of cell area are extracted. Then extract texture feature and improve the expressions of round-grade on the basis of experiments, in order to improve classification accuracy. Finally form an effective feature subset.
3. Hierarchical support vector machine classifier is constructed for 12 species recognition. With a small quantity of samples, our proposed methods achieve a decent performance on erythrocytes classification.
The subject is an application research in the image processing and recognition field of medicine. The results of this study have both theoretical and practical values.
本课题研究运用图像处理和模式识别技术实现不同形态红细胞的分类,以提高红细胞检验的准确度和精密度;研究了包括图像预处理、特征提取与分类识别等一整套基本算法;重点研究了红细胞的图像分割和特征提取,并将特征选择子集的结果用于红细胞的分类,取得了较好的结果。
1.在图像分割研究方面,通过对阈值分割、边缘检测、流域分割等分割方法的研究,提出了一种重叠粘连细胞的新的分割方法。该算法实现简单,效果理想,能较好地还原单个细胞的原始形状。
2.借鉴细胞医学目视分类的经验,借鉴在图像特征提取方面已有的研究成果,提取了对细胞的形状、大小等定量描述的细胞形态学参数;通过实验研究,增加了红细胞纹理特征的提取,构建了有效的特征集合。此外,还改进了圆形度的表达式以提高分类准确率。
3.研究和设计了多级支持向量机分类器对12类红细胞进行识别,能够在少量样本的情况下,得到较好的分类预测结果。
本课题是图像处理和模式识别在医学领域的一个应用性研究,本研究结果具有理论价值和实际应用意义。
The count and recognition of red blood cells plays an important role in modern clinical practice. At the same time, it is the key foundation for diagnosing kinds of blood diseases and other pertinent diseases. With the digital image processing and analysis has been widely applied in many medical areas, advanced image processing and pattern recognition technology, which is used in the sum and sort counting of blood corpuscles, is one of the important methods in medical-aided diagnosis. The technology effectively reduced subjective influence, partly replacing the labor works and improving the disadvantages of blood corpuscle analyzing apparatuses used currently in hospital, for example it can't observe the shape of the cells, can't save the swatch of the test, and the machine is very expensive, and so on.
The study use the technology of image processing and pattern recognition to classify the red blood cells in different shapes, in order to enhance the correctness and exactness; Bring forward a set of basic algorithms including pretreatment, feature extraction and classification; Most work has been focused on the image segmentation and feature extraction. Satisfying results have been reached by the selected feature parameters acting on erythrocytes classification.
1. Study classical image segmentation method such as threshold segmentation, edge detection, watershed and etc, design a new algorithm for automatically separating overlap cells images. The algorithm is simple and effective, it can obtain every cell's original shape preferably.
2. According to the eyeballing experience of erythrocytes classification, combining with the former work in feature extraction, quantification described morphology parameters, such as shape and size of cell area are extracted. Then extract texture feature and improve the expressions of round-grade on the basis of experiments, in order to improve classification accuracy. Finally form an effective feature subset.
3. Hierarchical support vector machine classifier is constructed for 12 species recognition. With a small quantity of samples, our proposed methods achieve a decent performance on erythrocytes classification.
The subject is an application research in the image processing and recognition field of medicine. The results of this study have both theoretical and practical values.
引文
1.Jeffcoat MK,Reddy MS.Advances in measurements of periodontal bone and attachment loss[J].Monogr Oral Sci,2000:1756-1772.
2.田娅,饶妮妮,蒲立新.国内医学图像处理技术的最新动态[J].电子科技大学学报,2002,31(5):485-489.
3.Duncan J.S.,Ayache N.Medical image analysis:progress over two decades and the challenges ahead[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(1):85-106.
4.尧德中,李永杰,周山宏.生物医学中的信息技术[J].电子科技大学学报社科版,2001,3(2):3-9.
5.曾明,孟庆浩,张建勋,鲍菁丹.基于形态特征和SVM的血液细胞核自动分析[J].计算机工程,2008,34(2):14-19.
6.许志伟,吴太虎,徐和福 等.血细饱计数技术最新研究进展[J].医疗卫生装备,2004:24-28.
7.Kan Jiang,Qing-Min Liao,Yuan Xiong.A novel white blood cell segmentation scheme based on feature space clustering.Soft Comput,2006,10:12-19.
8.Ugur Halici,Kemal Leblebicioglu,Guclu Ongun,Meral Beksac,Sinan Beksae.An automated differential blood count system using microscopic smear images[A].Middle east technical univ ankara(Turkey)computer and neural networks research center[C],2001.
9.J.Kendall Preston.High-resolution leukocyte analyzers:retrospective and prospective[J].Appl.1987,26(16):3258-3265.
10.周颖颖.彩色白细胞图像的特征选择与分类识别[D].南京:东南大学,2006.
11.SeigneurinD,Gauvain C,Brugal G.A quantitative analysis of the human bone marrow granulocytic cell lineage using the SAMBA 200 cell image processor[J].Analytical and Quantitative Cytology.1984,6(3):168-178.
12.毛维玉,徐勇,霍梅 等.Coulter Gen.s System 2血液分析仪的使用评价[J].2003,21(3):184-184.
13.Fares AK.Performance evaluation of two haematology analyzers:the Sysmex KX-21 and the Beckman Coulter Ac.T diff[J].Sysmex J International,2001,11:27-31.
14.邱君凤,叶跃红,石姜.XT-2000i全自动血细胞分析仪测定网织红细胞的评价[J].国际检验医学杂志,2006,27(4):305-314.
15.Wang FS,Itose Y,Tsuji T,et al.Development and clinical application of nucleated red blood cell counting and staging on the automated hematology analyzer XE-2100.Clin Lab Haem,2003,25:17-23.
16.蹇启政,李惠,罗红英.CELL-DYN3700血细胞分析仪应用及评价[J].实用医院临床杂志.2005,2(1):86-87.
17.郑丽华,颜箫,李南华 等.采用国家标准对TEK5000血细胞分析仪性能评价[J].实验与检验医学,2008,26(3):238-241.
18.王松霞,韦涌涛,刘程 等.BC-5500型全自动血液分析仪使用与评价[J].医学检验与临床,2008,19(2):105-105.
19.陈方平.临床检验血液学[M].高等教育出版社,2006.
20.Stoltz JF.Red blood cell microrheology,Ric.Clin.Lab.1983,13(3):53-70.
21.Chien S,Dormsndy J,Ernst E and Matrai A(eds).Clinical Haemorheology.Dordrecht:Martinus Nijihoff,1987:1-60.
22.何为,邵阳,陈秀珍 等.外周血细胞形态学检测的临床价值[J].实用医技杂志,2008,15(6):702-704.
23.检验医学网上资源库[EB/OL],http://www.clinet.com.cn/edu/resource/graphic/hemo.htm
24.常见血液学图谱[EB/OL],http://www.39kf.com/cooperate/tu/yx/haematology-graphic/
25.医网[EB/OL],http://www.ewsos.com/html/disease/html/1134.htm
26.王浩军.彩色血液细胞图像的自动分割方法研究[J].生物医学工程学杂志2002,19(2):251-255.
27.A Garrido,N Perez,de la Blanca.Applying deformable templates for cell image segmentation[J].Pattern Recognition,2000,33:821-832.
28.Cuclu Ongun,Ugur Hahci,Kemai Leblebicioglu,et al.Automated contour detection in blood cell images by an efficient snake algorithm[J].Nonlinear Analysis.2001,47:5839-5847.
29.PJH Bronkorsta,MJT Reinders,EA Hendriks,et al.Online detection of red blood cell shape using deformable templates[J].Pattern Recognition Letters,2000,21:413-424.
30.Andre Bleau,L Joshua Leon.Watershed-Based Segmentation and Region Merging[J].Computer Vision and Image Understanding,2000,77:317-370.
31.马东.多信息融合的彩色细胞图像分割方法[J].北京生物医学工程,2000,19(1):33-38.
32.Jon-Bae Kim,Hang-Joon Kim.Multiresolution-based watersheds for efficient image segmentation[J].Pattern Recognition Letters,2003,24:473-488.
33.周浩.基于数学形态学的血液细胞图像边缘提取[J].北京生物医学工程2002,21(2):89-91.
34.陆振晔,范影乐,庞全.基于数学形态学的重叠细胞分离方法及比较研究[J].计算机工程与应用,2004.6,57-59.
35.Brusseau E,de Korte CL,Mastik F,et al.Fully automatic luminal contour segmentation in intracoronary ultrasound imaging-A statistical approach[J].IEEE Trans Medical Imaging,2004.23(5).
36.Plissiti ME,Fotiadis DI,Michalis LK,et al.An automated method for lumen and media-adventitia border detection in a sequence of IVUS frames[J].IEEE Trans Information Technology in Biomedicine,2004,8(2):131-141.
37.傅蓉,申洪,陈浩.基于凹点搜寻的重叠细胞图像自动分离的算法研究[J].计算机工程与应用,2007.43(17):21-28.
38.尤育赛,于慧敏.一种重叠红细胞图像的分离方法[J].中国图象图形学报,2005,10(6):736-740.
39.胡小峰,赵辉.Visual C++/MATLAB图像处理与识别实用案例精选[M].北京:人民邮电出版社,2004.
40.T.Markiewicz,S.Osowski.Data mining techniques for feature selection in blood cell recognition[C].Bruges:ESANN'2006 proceedings-European Symposium on Artificial Neural Networks,2006:26-28.
41.Stanislaw Osowski,Tomasz Markiewicz,Bozena Marianska,Leszek Moszczynski Feature generation for the cell image recognition of myelogenous leukemia[C].Vienna:IEEE Int.Conf.EUSIPCO,2004:753-756.
42.毕峰.血细胞显微图像的特征提取[J].辽东学院学报,2006,13(2):25-28.
43.蒋勇,刘飞雷,鲍红光.显微图象的数字图象处理及其在血细胞形态分析中的应用[J].中国图象图形学报,2001,6(11):1079-1083.
44.任洪娥,徐海涛 细胞特征参数计算机的提取理论[J].林业科学,2007,43(9):68-73.
45.刘斌,曾立波,刘生浩.血液细胞图像自动识别系统的研究[J].计算机工程,2003,29(1):174-175.
46.毕峰.基于单输出型神经网络的血细胞分类研究[J].计算机应用,2007,27(6):1497-1499.
47.Vapnik V N.The Nature of Statistical Learning Theory[M].New York;Springer-Verlag,2000.
48.刘向东,朱美琳,陈兆乾,陈世福.支持向量机及其在模式识别中的应用[J].计算机科学,2003,30(6):113-117.
49.Amari S,Wu S.Improving support vector machine classifiers by modifying kernel functions[J].Neural Networks,1999,12:783-789.
50.Barzilay O,Brailovsky V L.On domain knowledge and feature selection using a support vector machine [J].Pattern Recognition Letters,1999,20(5):475-484.
51.Brailovsky V L,Barzilay O,Shahave R.On glogal,local,mixed and neighborhood kernels for support vector machines[J].Pattern Recognition Letters,1999,20:1183-1190.
52.Liu Xiang-dong,Luo Bin,Chen Zhao-qian.Optimal model selection for support vector machines[J].Journal of Computer Research and Development,2005,42(4):576-581.
53.Scholkopf B,Burges C,Vapnik V.Incorporating invariances in support vector learning machines[A].In:Artificial Neural Networks ICANN'96.Springer Lecture Notes in Computer Science,1996,1112:47-52.
54.Burges C J C,Scholkopf B.Improving the accuracy and speed of support vector learning machines[C].Advances in Neural Information Processing Systems.MIT Press,1997:375-381.
55.Burges C J C.Simplified support vector decision rules[A].In.Proc.13~(th) International Conference on Machine Learning[C],San Mateo,CA,1996:71-77.
56.Cortes C,Vapnik V.Support vector networks[J].Machine Learning,1995(20):273-297.
57.Osuna E,Freund R,Girosi F.An improved training algorithm for support vector machines[C].In:Principe J,Gile L,Morgan N,Wilson eds,Poceedings of the 1997 IEEE Workshop on Neural Networks for Signal Proceeding,New York:IEEE,1997:276-285.
58.Platt J.Fast training of support vector machines using sequential minimal optimization[A].In:Advances in Kernel Methods-Support Vector Learning,B.Schoelkopf,C.J.C.Burges,A.J.Smola,eds.Cambridge,MA,MIT Press,1999,185-208.
59.Keerthi S,Gilbert E.Convergence of a generalization SMO algorithm for SVM classifier design[J].Machine Learning,2002:46(1/3).
60.Arenas Garcia J,Perez Gruz F.Multi-class Support Vector Machines:A New Approach[A].Proe of the IEEE Int Conf on Acoustics,Speech and Signal Processing[C].New York,2003,2:781-784.
61.余辉,赵晖.支持向量机多类分类算法新研究[J].计算机工程与应用,2008,44(7):185-189.
62.Knerr S,Personnaz L,Dreyfus G.Single-layer learning revisited:a stepwise procedure for building and training a neural network[A].Neurocomputing:Algorithms,Architectures and Applications[C].NATO ASL Springer,1990.
63.Piatt J.Large Margin DAGs for Multiclass Classification[A],Advances in Neural Information Processing Systems[C].Massachusetts:MIT Press,2000:547-553.
64.Weston J,Watkins C.Multiclass Support Vector Machines.TR CSDTR 9804[Z],Department of Computer Science Egham,Survey TW 20 0EX,England,1998.
65.Ghani R.Using error-correcting codes for text classification[C].Proc of the 17~(th) International Conference on Machine Learning,2002.
66.Sahbi Hichem,Geman Donald,Perona Pietro.A hierarchy of support vector machines for pattern detection[J].J of Machine Learning Research,2006,7(10):2087-2123.
67.Hsu C W,Lin C J.A comparison of methods for multi-class support vector machines[J].IEEE Transactions on Neural Network,2002,13(2):415-425.
68.Wang X D,Shi Z W,Wu C M,et al.An improved algorithm for deision-tree-based SVM[C].Proc of the 6~(th) World Congress on Intelligent Control and Automation.Dalian,2006:4234-4237.
69.Zhu Meilin,Wang Yue,Chen Shifu,et al.Sphere-structured support vector machines for multi-class pattern recognition[J].Lecture Notes in Artificial Intelligence(S0302-9743),RSFDGrc 2003,LNAI 2639,2003:589-593.
70.顾磊,吴慧中,肖亮.基于新的决策规则的球形支持向量机分类算法[J].系统仿真学报,2008,20(11):2901-2904.
2.田娅,饶妮妮,蒲立新.国内医学图像处理技术的最新动态[J].电子科技大学学报,2002,31(5):485-489.
3.Duncan J.S.,Ayache N.Medical image analysis:progress over two decades and the challenges ahead[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(1):85-106.
4.尧德中,李永杰,周山宏.生物医学中的信息技术[J].电子科技大学学报社科版,2001,3(2):3-9.
5.曾明,孟庆浩,张建勋,鲍菁丹.基于形态特征和SVM的血液细胞核自动分析[J].计算机工程,2008,34(2):14-19.
6.许志伟,吴太虎,徐和福 等.血细饱计数技术最新研究进展[J].医疗卫生装备,2004:24-28.
7.Kan Jiang,Qing-Min Liao,Yuan Xiong.A novel white blood cell segmentation scheme based on feature space clustering.Soft Comput,2006,10:12-19.
8.Ugur Halici,Kemal Leblebicioglu,Guclu Ongun,Meral Beksac,Sinan Beksae.An automated differential blood count system using microscopic smear images[A].Middle east technical univ ankara(Turkey)computer and neural networks research center[C],2001.
9.J.Kendall Preston.High-resolution leukocyte analyzers:retrospective and prospective[J].Appl.1987,26(16):3258-3265.
10.周颖颖.彩色白细胞图像的特征选择与分类识别[D].南京:东南大学,2006.
11.SeigneurinD,Gauvain C,Brugal G.A quantitative analysis of the human bone marrow granulocytic cell lineage using the SAMBA 200 cell image processor[J].Analytical and Quantitative Cytology.1984,6(3):168-178.
12.毛维玉,徐勇,霍梅 等.Coulter Gen.s System 2血液分析仪的使用评价[J].2003,21(3):184-184.
13.Fares AK.Performance evaluation of two haematology analyzers:the Sysmex KX-21 and the Beckman Coulter Ac.T diff[J].Sysmex J International,2001,11:27-31.
14.邱君凤,叶跃红,石姜.XT-2000i全自动血细胞分析仪测定网织红细胞的评价[J].国际检验医学杂志,2006,27(4):305-314.
15.Wang FS,Itose Y,Tsuji T,et al.Development and clinical application of nucleated red blood cell counting and staging on the automated hematology analyzer XE-2100.Clin Lab Haem,2003,25:17-23.
16.蹇启政,李惠,罗红英.CELL-DYN3700血细胞分析仪应用及评价[J].实用医院临床杂志.2005,2(1):86-87.
17.郑丽华,颜箫,李南华 等.采用国家标准对TEK5000血细胞分析仪性能评价[J].实验与检验医学,2008,26(3):238-241.
18.王松霞,韦涌涛,刘程 等.BC-5500型全自动血液分析仪使用与评价[J].医学检验与临床,2008,19(2):105-105.
19.陈方平.临床检验血液学[M].高等教育出版社,2006.
20.Stoltz JF.Red blood cell microrheology,Ric.Clin.Lab.1983,13(3):53-70.
21.Chien S,Dormsndy J,Ernst E and Matrai A(eds).Clinical Haemorheology.Dordrecht:Martinus Nijihoff,1987:1-60.
22.何为,邵阳,陈秀珍 等.外周血细胞形态学检测的临床价值[J].实用医技杂志,2008,15(6):702-704.
23.检验医学网上资源库[EB/OL],http://www.clinet.com.cn/edu/resource/graphic/hemo.htm
24.常见血液学图谱[EB/OL],http://www.39kf.com/cooperate/tu/yx/haematology-graphic/
25.医网[EB/OL],http://www.ewsos.com/html/disease/html/1134.htm
26.王浩军.彩色血液细胞图像的自动分割方法研究[J].生物医学工程学杂志2002,19(2):251-255.
27.A Garrido,N Perez,de la Blanca.Applying deformable templates for cell image segmentation[J].Pattern Recognition,2000,33:821-832.
28.Cuclu Ongun,Ugur Hahci,Kemai Leblebicioglu,et al.Automated contour detection in blood cell images by an efficient snake algorithm[J].Nonlinear Analysis.2001,47:5839-5847.
29.PJH Bronkorsta,MJT Reinders,EA Hendriks,et al.Online detection of red blood cell shape using deformable templates[J].Pattern Recognition Letters,2000,21:413-424.
30.Andre Bleau,L Joshua Leon.Watershed-Based Segmentation and Region Merging[J].Computer Vision and Image Understanding,2000,77:317-370.
31.马东.多信息融合的彩色细胞图像分割方法[J].北京生物医学工程,2000,19(1):33-38.
32.Jon-Bae Kim,Hang-Joon Kim.Multiresolution-based watersheds for efficient image segmentation[J].Pattern Recognition Letters,2003,24:473-488.
33.周浩.基于数学形态学的血液细胞图像边缘提取[J].北京生物医学工程2002,21(2):89-91.
34.陆振晔,范影乐,庞全.基于数学形态学的重叠细胞分离方法及比较研究[J].计算机工程与应用,2004.6,57-59.
35.Brusseau E,de Korte CL,Mastik F,et al.Fully automatic luminal contour segmentation in intracoronary ultrasound imaging-A statistical approach[J].IEEE Trans Medical Imaging,2004.23(5).
36.Plissiti ME,Fotiadis DI,Michalis LK,et al.An automated method for lumen and media-adventitia border detection in a sequence of IVUS frames[J].IEEE Trans Information Technology in Biomedicine,2004,8(2):131-141.
37.傅蓉,申洪,陈浩.基于凹点搜寻的重叠细胞图像自动分离的算法研究[J].计算机工程与应用,2007.43(17):21-28.
38.尤育赛,于慧敏.一种重叠红细胞图像的分离方法[J].中国图象图形学报,2005,10(6):736-740.
39.胡小峰,赵辉.Visual C++/MATLAB图像处理与识别实用案例精选[M].北京:人民邮电出版社,2004.
40.T.Markiewicz,S.Osowski.Data mining techniques for feature selection in blood cell recognition[C].Bruges:ESANN'2006 proceedings-European Symposium on Artificial Neural Networks,2006:26-28.
41.Stanislaw Osowski,Tomasz Markiewicz,Bozena Marianska,Leszek Moszczynski Feature generation for the cell image recognition of myelogenous leukemia[C].Vienna:IEEE Int.Conf.EUSIPCO,2004:753-756.
42.毕峰.血细胞显微图像的特征提取[J].辽东学院学报,2006,13(2):25-28.
43.蒋勇,刘飞雷,鲍红光.显微图象的数字图象处理及其在血细胞形态分析中的应用[J].中国图象图形学报,2001,6(11):1079-1083.
44.任洪娥,徐海涛 细胞特征参数计算机的提取理论[J].林业科学,2007,43(9):68-73.
45.刘斌,曾立波,刘生浩.血液细胞图像自动识别系统的研究[J].计算机工程,2003,29(1):174-175.
46.毕峰.基于单输出型神经网络的血细胞分类研究[J].计算机应用,2007,27(6):1497-1499.
47.Vapnik V N.The Nature of Statistical Learning Theory[M].New York;Springer-Verlag,2000.
48.刘向东,朱美琳,陈兆乾,陈世福.支持向量机及其在模式识别中的应用[J].计算机科学,2003,30(6):113-117.
49.Amari S,Wu S.Improving support vector machine classifiers by modifying kernel functions[J].Neural Networks,1999,12:783-789.
50.Barzilay O,Brailovsky V L.On domain knowledge and feature selection using a support vector machine [J].Pattern Recognition Letters,1999,20(5):475-484.
51.Brailovsky V L,Barzilay O,Shahave R.On glogal,local,mixed and neighborhood kernels for support vector machines[J].Pattern Recognition Letters,1999,20:1183-1190.
52.Liu Xiang-dong,Luo Bin,Chen Zhao-qian.Optimal model selection for support vector machines[J].Journal of Computer Research and Development,2005,42(4):576-581.
53.Scholkopf B,Burges C,Vapnik V.Incorporating invariances in support vector learning machines[A].In:Artificial Neural Networks ICANN'96.Springer Lecture Notes in Computer Science,1996,1112:47-52.
54.Burges C J C,Scholkopf B.Improving the accuracy and speed of support vector learning machines[C].Advances in Neural Information Processing Systems.MIT Press,1997:375-381.
55.Burges C J C.Simplified support vector decision rules[A].In.Proc.13~(th) International Conference on Machine Learning[C],San Mateo,CA,1996:71-77.
56.Cortes C,Vapnik V.Support vector networks[J].Machine Learning,1995(20):273-297.
57.Osuna E,Freund R,Girosi F.An improved training algorithm for support vector machines[C].In:Principe J,Gile L,Morgan N,Wilson eds,Poceedings of the 1997 IEEE Workshop on Neural Networks for Signal Proceeding,New York:IEEE,1997:276-285.
58.Platt J.Fast training of support vector machines using sequential minimal optimization[A].In:Advances in Kernel Methods-Support Vector Learning,B.Schoelkopf,C.J.C.Burges,A.J.Smola,eds.Cambridge,MA,MIT Press,1999,185-208.
59.Keerthi S,Gilbert E.Convergence of a generalization SMO algorithm for SVM classifier design[J].Machine Learning,2002:46(1/3).
60.Arenas Garcia J,Perez Gruz F.Multi-class Support Vector Machines:A New Approach[A].Proe of the IEEE Int Conf on Acoustics,Speech and Signal Processing[C].New York,2003,2:781-784.
61.余辉,赵晖.支持向量机多类分类算法新研究[J].计算机工程与应用,2008,44(7):185-189.
62.Knerr S,Personnaz L,Dreyfus G.Single-layer learning revisited:a stepwise procedure for building and training a neural network[A].Neurocomputing:Algorithms,Architectures and Applications[C].NATO ASL Springer,1990.
63.Piatt J.Large Margin DAGs for Multiclass Classification[A],Advances in Neural Information Processing Systems[C].Massachusetts:MIT Press,2000:547-553.
64.Weston J,Watkins C.Multiclass Support Vector Machines.TR CSDTR 9804[Z],Department of Computer Science Egham,Survey TW 20 0EX,England,1998.
65.Ghani R.Using error-correcting codes for text classification[C].Proc of the 17~(th) International Conference on Machine Learning,2002.
66.Sahbi Hichem,Geman Donald,Perona Pietro.A hierarchy of support vector machines for pattern detection[J].J of Machine Learning Research,2006,7(10):2087-2123.
67.Hsu C W,Lin C J.A comparison of methods for multi-class support vector machines[J].IEEE Transactions on Neural Network,2002,13(2):415-425.
68.Wang X D,Shi Z W,Wu C M,et al.An improved algorithm for deision-tree-based SVM[C].Proc of the 6~(th) World Congress on Intelligent Control and Automation.Dalian,2006:4234-4237.
69.Zhu Meilin,Wang Yue,Chen Shifu,et al.Sphere-structured support vector machines for multi-class pattern recognition[J].Lecture Notes in Artificial Intelligence(S0302-9743),RSFDGrc 2003,LNAI 2639,2003:589-593.
70.顾磊,吴慧中,肖亮.基于新的决策规则的球形支持向量机分类算法[J].系统仿真学报,2008,20(11):2901-2904.