嵌入式字符识别技术的研究与开发
|
摘要
随着工业生产的自动化程度越来越高,许多场合下需要对生产线上产品的标号或编码通过机器进行自动识别。然而工业现场的复杂环境,如光照不均匀、噪声等因素,给字符的准确识别带来较大的困难,对字符识别系统的硬件和软件的性能也提出了更高的要求。本文研究基于嵌入式智能相机硬件平台,以轴承压印字符为识别对象,在总结前人经验和成果基础上,提出了自己的解决方法,实现轴承压印字符的自动识别。论文所涉及的内容包括以下几个方面:
1)轴承图像的采集和预处理。在分析轴承压印字符的成像特点的基础上,设计了适用于轴承的图像采集系统。该系统基于嵌入式智能相机图像采集平台,并选用低角度LCD环形光源作为辅助光源,通过对轴承进行图像采集证实该系统能够获取质量较高的轴承图片。在图像预处理阶段,由于轴承是圆形结构且字符区域在图像中的位置不固定,因此需要对轴承字符区域进行定位和矫正,以便后续的处理和识别。为此,在使用大津法得到轴承的二值图像后,首先要对轴承圆心进行定位。针对随机Hough变换圆检测算法的不足,使用一种改进的随机圆检测算法用于轴承的圆心定位,在候选圆选取的过程中通过简单的判断降低了运算量,实验证实该圆心定位算法能够快速而准确定位出轴承圆心。随后,以定位出的圆心为极坐标原点,采用投影法确定轴承字符区域。最后,对轴承字符扇形区域进行矫正,若采用极坐标变换所得图像毛刺较多,因此本文采用基于仿射变换的字符矫正方法,实验表明该方法能使变换后的图像毛刺较少且速度上也能满足要求。
2)轴承字符的特征提取和分类器。本文详细描述了两种常用的特征提取方法:方向线素特征和轮廓层次特征,并在理论分析和实验的基础上,针对他们的不足分别提出了基于弹性网格的方向线素特征和基于小波变换的轮廓层次特征两种改进的特征提取方法。基于弹性网格的方向线素特征有效地弥补了均匀网格划分对字符形变的敏感性,特征的鲁棒性更强。基于小波变换的轮廓层次特征充分利用了小波多分辨率分析的特性,特征抗噪性更好且维数更低。关于轴承字符识别的分类器,本文讨论了BP神经网络和支持向量机分类器的原理,并分别设计了基于动量项与自适应学习速率的BP神经网络和基于LIBSVM的支持向量机网络。轴承字符中识别系统具体采用的特征提取方法和分类器方案是通过最后的识别实验确定的。
通过对实际拍摄的图片进行识别实验,验证了本文所述方法的有效性,并确定特征提取方法和分类器的选取。实验表明:本文采用的图像采集方案能够获取质量较高的轴承图像,预处理方法效果较好,根据试验结果最终选取改进的轮廓层次特征作为特征,使用支持向量机作为分类器。字符识别的准确率在96%以上,速度上也能满足实际需求。本文方法能够快速而准确地对轴承压印字符进行自动识别。
With the increasing degree of automation of production, the automatic recognition of theproduct label or code in production line through machine is needed.However, the complicatedindustrial environments, such as uneven illumination,noisy,etc.,bring greater difficulties toaccurately identify the characters.People also put forward higher requirements of thehardware and the software of character recognition system.In this paper,research is based onembedded intelligent camera hardware platform,and identify object is the pressed characterson bearing.Summarizing the predecessors' experience and work,the author puts forward hisown solution,and achieves the automatic recognition of the pressed characters onbearings.Paper involves the the following study content:
1) Bearing image capture and preprocessing.On the basis of the analysis of imagecharacteristics of pressed characters on bearing,image acquisition system which is suitable forbearing is designed.The system is based on embedded intelligent camera platform for imageacquisition,and low-angle LCD ring light source is chosen as auxiliary illuminant.It isconfirmed that the system can get high quality bearing image.In the image pre-processingstage,the structure ofbearing is a circle structure and the position of the character is notfixed,so it is needed to locate bearing character area and correct bearing character forsubsequent processing and recognition.Therefore,after getting bearing binary image by Otsumethod,the center of the bearing should be located firstly. Because of the deficiencies ofRandomized-Hough-Transformation for the circle detection algorithm,an improvedRandomized-Circles-Detection algorithm for the bearing center localization is proposed inthis paper.This method reduces the computational complexity through the simplest decisionsin the process of choosing a candidate circle.The experiment proves the circle centerlocalization algorithm proposed can locate the bearing circle quickly and accurately.Then,usethe center as the origin of polar coordinates and the bearing character area is determined byprojection method.Finally,in the process of correcting bearing character area,there would be alot of burrs in the result image if we use the polar coordinates transform method.Thus,thispaper proposes a character correction method based on affine transformation,the experimentalresults show that the method can transform the image less burr and the speed of thetransformation also can meet the requirements.
2) Bearing character feature extraction and classifier.Two commonly used methods offeature extraction are describes in this paper:the direction line element feature extractionmethod and the contour feature extraction method.After analysing their deficiency,twoimproved feature extraction method are proposes in this paper:the direction line elementfeature extraction method based on elastic gird and the contour features extraction methodbased on wavelet analysis.The improved direction line element features make up for thesensitivity of uniform gird division of characters to character deformation which are morerobust.The improved contour features make full use of the characteristics of waveletdecomposition,which have better noise resistance and lower dimension.About the classifier ofbearing character recognition,this paper analyzes BP neural network and support vector machine classifier principle.BP neural network based on momentum term with adaptivelearning rate and SVM based on sequential minimal optimization are designed in thispaper.The effectiveness of the method proposed is confirmed by experiments on real bearingimage,and the method of feature extraction and classifier are determine by experiments results.Feature extraction method and classifier is determined by experiments.
Experiments show that the proposed scheme can obtain high quality bearing image,andthe effect of preprocessing methods is better, finally choose the improved contour features anduse support vector machine as classifier.Character recognition accuracy is 96% or more,andthe speed can meet the practical demands. The method proposed in this paper canautomatically recognize bearing characters quickly and accurately.
1)轴承图像的采集和预处理。在分析轴承压印字符的成像特点的基础上,设计了适用于轴承的图像采集系统。该系统基于嵌入式智能相机图像采集平台,并选用低角度LCD环形光源作为辅助光源,通过对轴承进行图像采集证实该系统能够获取质量较高的轴承图片。在图像预处理阶段,由于轴承是圆形结构且字符区域在图像中的位置不固定,因此需要对轴承字符区域进行定位和矫正,以便后续的处理和识别。为此,在使用大津法得到轴承的二值图像后,首先要对轴承圆心进行定位。针对随机Hough变换圆检测算法的不足,使用一种改进的随机圆检测算法用于轴承的圆心定位,在候选圆选取的过程中通过简单的判断降低了运算量,实验证实该圆心定位算法能够快速而准确定位出轴承圆心。随后,以定位出的圆心为极坐标原点,采用投影法确定轴承字符区域。最后,对轴承字符扇形区域进行矫正,若采用极坐标变换所得图像毛刺较多,因此本文采用基于仿射变换的字符矫正方法,实验表明该方法能使变换后的图像毛刺较少且速度上也能满足要求。
2)轴承字符的特征提取和分类器。本文详细描述了两种常用的特征提取方法:方向线素特征和轮廓层次特征,并在理论分析和实验的基础上,针对他们的不足分别提出了基于弹性网格的方向线素特征和基于小波变换的轮廓层次特征两种改进的特征提取方法。基于弹性网格的方向线素特征有效地弥补了均匀网格划分对字符形变的敏感性,特征的鲁棒性更强。基于小波变换的轮廓层次特征充分利用了小波多分辨率分析的特性,特征抗噪性更好且维数更低。关于轴承字符识别的分类器,本文讨论了BP神经网络和支持向量机分类器的原理,并分别设计了基于动量项与自适应学习速率的BP神经网络和基于LIBSVM的支持向量机网络。轴承字符中识别系统具体采用的特征提取方法和分类器方案是通过最后的识别实验确定的。
通过对实际拍摄的图片进行识别实验,验证了本文所述方法的有效性,并确定特征提取方法和分类器的选取。实验表明:本文采用的图像采集方案能够获取质量较高的轴承图像,预处理方法效果较好,根据试验结果最终选取改进的轮廓层次特征作为特征,使用支持向量机作为分类器。字符识别的准确率在96%以上,速度上也能满足实际需求。本文方法能够快速而准确地对轴承压印字符进行自动识别。
With the increasing degree of automation of production, the automatic recognition of theproduct label or code in production line through machine is needed.However, the complicatedindustrial environments, such as uneven illumination,noisy,etc.,bring greater difficulties toaccurately identify the characters.People also put forward higher requirements of thehardware and the software of character recognition system.In this paper,research is based onembedded intelligent camera hardware platform,and identify object is the pressed characterson bearing.Summarizing the predecessors' experience and work,the author puts forward hisown solution,and achieves the automatic recognition of the pressed characters onbearings.Paper involves the the following study content:
1) Bearing image capture and preprocessing.On the basis of the analysis of imagecharacteristics of pressed characters on bearing,image acquisition system which is suitable forbearing is designed.The system is based on embedded intelligent camera platform for imageacquisition,and low-angle LCD ring light source is chosen as auxiliary illuminant.It isconfirmed that the system can get high quality bearing image.In the image pre-processingstage,the structure ofbearing is a circle structure and the position of the character is notfixed,so it is needed to locate bearing character area and correct bearing character forsubsequent processing and recognition.Therefore,after getting bearing binary image by Otsumethod,the center of the bearing should be located firstly. Because of the deficiencies ofRandomized-Hough-Transformation for the circle detection algorithm,an improvedRandomized-Circles-Detection algorithm for the bearing center localization is proposed inthis paper.This method reduces the computational complexity through the simplest decisionsin the process of choosing a candidate circle.The experiment proves the circle centerlocalization algorithm proposed can locate the bearing circle quickly and accurately.Then,usethe center as the origin of polar coordinates and the bearing character area is determined byprojection method.Finally,in the process of correcting bearing character area,there would be alot of burrs in the result image if we use the polar coordinates transform method.Thus,thispaper proposes a character correction method based on affine transformation,the experimentalresults show that the method can transform the image less burr and the speed of thetransformation also can meet the requirements.
2) Bearing character feature extraction and classifier.Two commonly used methods offeature extraction are describes in this paper:the direction line element feature extractionmethod and the contour feature extraction method.After analysing their deficiency,twoimproved feature extraction method are proposes in this paper:the direction line elementfeature extraction method based on elastic gird and the contour features extraction methodbased on wavelet analysis.The improved direction line element features make up for thesensitivity of uniform gird division of characters to character deformation which are morerobust.The improved contour features make full use of the characteristics of waveletdecomposition,which have better noise resistance and lower dimension.About the classifier ofbearing character recognition,this paper analyzes BP neural network and support vector machine classifier principle.BP neural network based on momentum term with adaptivelearning rate and SVM based on sequential minimal optimization are designed in thispaper.The effectiveness of the method proposed is confirmed by experiments on real bearingimage,and the method of feature extraction and classifier are determine by experiments results.Feature extraction method and classifier is determined by experiments.
Experiments show that the proposed scheme can obtain high quality bearing image,andthe effect of preprocessing methods is better, finally choose the improved contour features anduse support vector machine as classifier.Character recognition accuracy is 96% or more,andthe speed can meet the practical demands. The method proposed in this paper canautomatically recognize bearing characters quickly and accurately.
引文
1.荆涛,王仲.光学字符识别技术与展望[J].计算机工程.2003,29(2):1-2,80.
2.李杜.字符识别技术研究及其在机器视觉测控中的应用[D]:[硕士学位论文].无锡:江南大学,2011.
3. Mori S.Historical Review of OCR Research and Development.Proceedings ofIEEE,1992,80(7):1029-1058.
4.张妍中.汉字识别技术[M].北京:清华大学出版社,1992.
5. Vuokko Vuori,Matti Aksela,Jorma Laaksonen.Adaptive Character recognizer for ahand-held Device:Implementation and Evaluation setup[J].Proeeedings of 7th InternationalWorkshoP on Frontiers in Handwriting Recognition.2000,13-22.
6. Lanra Walker Renninger,Jitendra Malik.When is scene identification just texturereeognition[J].Vision Research.2004,(44):2301-2311.
7. Brian Ball.Advances in Character Recognition Exand Proeessing Power[J].The Journal ofWork Process Improvement.2007,30(2).
8.朱峰.车牌汉字识别技术的研究与实现[D]:[硕士学位论文].镇江:江苏大学,2006.
9.王碧翠.电力设备图片中字符识别技术的研究[D]:[硕士学位论文].北京:华北电力大学,2006.
10.李了了.工业现场字符识别方法的研究[D]:[硕士学位论文].合肥:合肥工业大学,2003.
11.邬文俊.基于机器视觉技术的啤酒瓶字符自动识别系统的研究[D]:[硕士学位论文].武汉:湖北工业大学,2005.
12.李建美.标牌压印字符图像获取与处理中的关键技术研究[D]:[博士学位论文].济南:山东大学,2008.
13.李建美,路长厚,李学勇.一种基于图像分层的标牌压印字符分割方法[J].光电子激光.2008,19(6):818-822.
14.李学勇,路长厚,李建美.融合轮廓矩和Fourier描述子特征的压印字符识别[J].光电子激光.2007,18(10):1244-1247,1259.
15.曹建海,路长厚.基于小波变换和DCT的字符图像特征抽取新方法[J].光电子激光.2004,15(4):477-482.
16.曹建海,李龙,路长厚.基于RBF-NN的压印凹凸字符质量检测研究[J].光电子激光,2006,17(8):963-968.
17.李国平,路长厚,李健美.基于最小二乘支持向量机的压印字符识别方法[J].上海大学学报.2007,13(2):125-129.
18.杨基春,黄战华,朱猛,等.高噪声轮胎图像规格号提取方法研究[J].光电工程,2010,37(3):24-28.
19.杨基春,黄战华,蔡怀宇,等.大噪声图像的轮胎规格号识别技术[J].光电工程,2010,37(9):98-103.
20.白瑞林,史鹏飞,吉峰,等.基于Modbus/TCP的智能相机通信接口实现[J].控制工程,2011,18(4):618-622.
21.叶芗芸,戚飞虎,吴健渊.文本图像的快速二值化方法[J].红外与毫米波学报,1997,16(5):344-350.
22.李倩.文档图像的二值化算法综述[J].中国传媒大学学报自然科学版,2008,15(4):66-70.
23.李牧,闫继宏,朱延河,等.一种改进的大津法在机器视觉中的应用[J].吉林大学学报(工学版),2008,38(4):913-918.
24. Lei XU,Erkki OJA,Pekka KULTANEN.A new curve detection method:RandomizedHough transform RHT[J].Pattern Recognition Letters,1990,11(5):331-338.
25. ChenTehchuan,ChenKuoliang.AnEfficient Randomized Algorithmfor DetectingCircles[J].Computer Visionand Image Understanding,2001,83(2):172-191.
26.陈爱军,李金宗,李东东.一种改进的随机圆检测算法[J].光电工程,2006,33(12):91-95.
27.阮秋琦.数字图像处理学[M].北京:电子工业出版社,2007.
28.张剑,周少武,刘洁.一种基于字符分割与字符识别的LPR方法[J].计算技术与自动化,2007,26(2):111-114.
29.黄剑航.基于HALCON的圆环区域字符识别实现[J].现代计算机,2010,07:58-60.
30.刑博.车辆牌照字符识别算法的设计与实现[D]:[硕士学位论文].大连:大连海事大学,2005.
31.唐宏震.车牌识别系统中字符识别的研究与实现[D]:[硕士学位论文].西安:西北大学,2008.
32.高伟.车牌字符识别技术的研究[D]:[硕士学位论文].太原:山西大学,2005.
33.肖进.多神经网络在车牌字符识别中的应用[D]:[硕士学位论文].南京:东南大学,2004.
34.李庆昌.基于神经树的英文字符识别技术研究[D]:[硕士学位论文].济南:山东师范大学,2009.
35.丁胜.基于支持向量机的手写体字符识别[D]:[硕士学位论文].青岛:青岛大学,2006.
36.杜晶.基于支持向量机的车牌字符识别研究[D]:[硕士学位论文].邯郸:河北工程大学,2008.
37.何浩智,字符识别中笔段及特征提取方法的研究[D]:[硕士学位论文].长沙:湖南大学,2007.
38.高宏宾,陈军,陈丽平.一种基于低维特征的高精度手写数字识别算法[J].计算机应用,2009,29(5):1412-1425.
39. Ekenel H K and Sanker B.Multiresolution face recognition[J].Image and VisionComputing,2005, 23:469-477.
40.边威.小波基的选取与构造方法讨论[D]:[硕士学位论文].长春:东北师范大学,2007.
41. Mallat S.A Wavelet Tour of Signal Processing[M].Beijing:China Machine Press,2009.
42.韩九强.机器视觉技术及应用[M].北京:高等教育出版社,2009.
43.孙娓娓.BP神经网络的算法改进及应用研究[D]:[硕士学位论文].重庆:重庆大学,2009.
44.朱大奇.人工神经网络原理及应用[M].北京:科学出版社,2006.
45. Nello Cristianini, John Shawe-Taylor.An Introduction to Support Vector Machines andOther Kernel-based Learning Methods[M].Beijing:China Machine Press,2005.
46.孟凡栋.基于主动学习SVM的字符识别方法研究[D]:[硕士学位论文].南京:南京理工大学,2008.
47.徐铭杰.基于支持向量机的字符识别系统的研究与实现[D]:[硕士学位论文].杭州:浙江工业大学,2007.
48.刘瑞祯,于仕琪.OpenCV教程基础篇[M].北京:北京航空航天出版社,2007.
49.从爽.面向MATLAB工具箱的神经网络理论与应用[M].合肥:中国科学技术出版社.2009.
50. Chang Chihchung,Lin Chinjen.LIBSVM:A Library for Support VectorMachines[EB/OL].(2007-09-15).http://www.csie.ntu.edu.tw/~cjlin/libsvm.
51.张宏烈.支持向量机在字符识别中的应用研究[J].微计算机信息,2006,22(42):245-247.
52.王晓云.SVM算法分析与研究[J].渝西学院学报(自然科学版),2005,4(3):15-18.
2.李杜.字符识别技术研究及其在机器视觉测控中的应用[D]:[硕士学位论文].无锡:江南大学,2011.
3. Mori S.Historical Review of OCR Research and Development.Proceedings ofIEEE,1992,80(7):1029-1058.
4.张妍中.汉字识别技术[M].北京:清华大学出版社,1992.
5. Vuokko Vuori,Matti Aksela,Jorma Laaksonen.Adaptive Character recognizer for ahand-held Device:Implementation and Evaluation setup[J].Proeeedings of 7th InternationalWorkshoP on Frontiers in Handwriting Recognition.2000,13-22.
6. Lanra Walker Renninger,Jitendra Malik.When is scene identification just texturereeognition[J].Vision Research.2004,(44):2301-2311.
7. Brian Ball.Advances in Character Recognition Exand Proeessing Power[J].The Journal ofWork Process Improvement.2007,30(2).
8.朱峰.车牌汉字识别技术的研究与实现[D]:[硕士学位论文].镇江:江苏大学,2006.
9.王碧翠.电力设备图片中字符识别技术的研究[D]:[硕士学位论文].北京:华北电力大学,2006.
10.李了了.工业现场字符识别方法的研究[D]:[硕士学位论文].合肥:合肥工业大学,2003.
11.邬文俊.基于机器视觉技术的啤酒瓶字符自动识别系统的研究[D]:[硕士学位论文].武汉:湖北工业大学,2005.
12.李建美.标牌压印字符图像获取与处理中的关键技术研究[D]:[博士学位论文].济南:山东大学,2008.
13.李建美,路长厚,李学勇.一种基于图像分层的标牌压印字符分割方法[J].光电子激光.2008,19(6):818-822.
14.李学勇,路长厚,李建美.融合轮廓矩和Fourier描述子特征的压印字符识别[J].光电子激光.2007,18(10):1244-1247,1259.
15.曹建海,路长厚.基于小波变换和DCT的字符图像特征抽取新方法[J].光电子激光.2004,15(4):477-482.
16.曹建海,李龙,路长厚.基于RBF-NN的压印凹凸字符质量检测研究[J].光电子激光,2006,17(8):963-968.
17.李国平,路长厚,李健美.基于最小二乘支持向量机的压印字符识别方法[J].上海大学学报.2007,13(2):125-129.
18.杨基春,黄战华,朱猛,等.高噪声轮胎图像规格号提取方法研究[J].光电工程,2010,37(3):24-28.
19.杨基春,黄战华,蔡怀宇,等.大噪声图像的轮胎规格号识别技术[J].光电工程,2010,37(9):98-103.
20.白瑞林,史鹏飞,吉峰,等.基于Modbus/TCP的智能相机通信接口实现[J].控制工程,2011,18(4):618-622.
21.叶芗芸,戚飞虎,吴健渊.文本图像的快速二值化方法[J].红外与毫米波学报,1997,16(5):344-350.
22.李倩.文档图像的二值化算法综述[J].中国传媒大学学报自然科学版,2008,15(4):66-70.
23.李牧,闫继宏,朱延河,等.一种改进的大津法在机器视觉中的应用[J].吉林大学学报(工学版),2008,38(4):913-918.
24. Lei XU,Erkki OJA,Pekka KULTANEN.A new curve detection method:RandomizedHough transform RHT[J].Pattern Recognition Letters,1990,11(5):331-338.
25. ChenTehchuan,ChenKuoliang.AnEfficient Randomized Algorithmfor DetectingCircles[J].Computer Visionand Image Understanding,2001,83(2):172-191.
26.陈爱军,李金宗,李东东.一种改进的随机圆检测算法[J].光电工程,2006,33(12):91-95.
27.阮秋琦.数字图像处理学[M].北京:电子工业出版社,2007.
28.张剑,周少武,刘洁.一种基于字符分割与字符识别的LPR方法[J].计算技术与自动化,2007,26(2):111-114.
29.黄剑航.基于HALCON的圆环区域字符识别实现[J].现代计算机,2010,07:58-60.
30.刑博.车辆牌照字符识别算法的设计与实现[D]:[硕士学位论文].大连:大连海事大学,2005.
31.唐宏震.车牌识别系统中字符识别的研究与实现[D]:[硕士学位论文].西安:西北大学,2008.
32.高伟.车牌字符识别技术的研究[D]:[硕士学位论文].太原:山西大学,2005.
33.肖进.多神经网络在车牌字符识别中的应用[D]:[硕士学位论文].南京:东南大学,2004.
34.李庆昌.基于神经树的英文字符识别技术研究[D]:[硕士学位论文].济南:山东师范大学,2009.
35.丁胜.基于支持向量机的手写体字符识别[D]:[硕士学位论文].青岛:青岛大学,2006.
36.杜晶.基于支持向量机的车牌字符识别研究[D]:[硕士学位论文].邯郸:河北工程大学,2008.
37.何浩智,字符识别中笔段及特征提取方法的研究[D]:[硕士学位论文].长沙:湖南大学,2007.
38.高宏宾,陈军,陈丽平.一种基于低维特征的高精度手写数字识别算法[J].计算机应用,2009,29(5):1412-1425.
39. Ekenel H K and Sanker B.Multiresolution face recognition[J].Image and VisionComputing,2005, 23:469-477.
40.边威.小波基的选取与构造方法讨论[D]:[硕士学位论文].长春:东北师范大学,2007.
41. Mallat S.A Wavelet Tour of Signal Processing[M].Beijing:China Machine Press,2009.
42.韩九强.机器视觉技术及应用[M].北京:高等教育出版社,2009.
43.孙娓娓.BP神经网络的算法改进及应用研究[D]:[硕士学位论文].重庆:重庆大学,2009.
44.朱大奇.人工神经网络原理及应用[M].北京:科学出版社,2006.
45. Nello Cristianini, John Shawe-Taylor.An Introduction to Support Vector Machines andOther Kernel-based Learning Methods[M].Beijing:China Machine Press,2005.
46.孟凡栋.基于主动学习SVM的字符识别方法研究[D]:[硕士学位论文].南京:南京理工大学,2008.
47.徐铭杰.基于支持向量机的字符识别系统的研究与实现[D]:[硕士学位论文].杭州:浙江工业大学,2007.
48.刘瑞祯,于仕琪.OpenCV教程基础篇[M].北京:北京航空航天出版社,2007.
49.从爽.面向MATLAB工具箱的神经网络理论与应用[M].合肥:中国科学技术出版社.2009.
50. Chang Chihchung,Lin Chinjen.LIBSVM:A Library for Support VectorMachines[EB/OL].(2007-09-15).http://www.csie.ntu.edu.tw/~cjlin/libsvm.
51.张宏烈.支持向量机在字符识别中的应用研究[J].微计算机信息,2006,22(42):245-247.
52.王晓云.SVM算法分析与研究[J].渝西学院学报(自然科学版),2005,4(3):15-18.