带钢表面缺陷图像检测与分类方法研究
|
摘要
钢铁工业飞速发展,带钢生产线的生产速度逐渐提高,同时随着各领域对自身产品质量的要求提高,用户对上游钢铁企业供应的带钢等轧制品也提出了更高的表面质量要求。为此,带钢表面缺陷的在线检测过程对带钢的生产和质量控制显得尤为重要,然而表面缺陷检测的相关技术并未随着图像处理技术的发展而快速发展,其原因是在相关技术转化为生产力的过程中未能更多地结合实际生产的需要做出改进,也不能克服生产环境的变化给这些技术实现带来的障碍。为了进一步提高检测的科学性,为工业的标准化生产提供准确的数据信息,提高生产系统整体的自动化程度,最终突破制约产业转型升级的关键技术；为了提高带钢表面缺陷分类的一致性,保护设备不受缺陷影响,并降低返工成本;为了减少贸易纠纷,维护企业形象与信誉,保持企业核心竞争力,本文对以下内容进行了综述和说明：
(1)对国内外带钢表面缺陷检测技术的发展情况进行了综述,并分析了机器视觉带钢表面缺陷检测技术未来的发展趋势。
(2)根据不同的生产环节,阐述了适合多种生产环境下带钢表面图像采集的方式和方法,其中包括照明光源、CCD传感器和检测方式等内容。明确了不同工业生产中的多种带钢表面缺陷检测点位置与检测方式。
(3)以热轧和冷轧生产中对表面缺陷要求最高的钢种类型为基础,阐明了缺陷形貌、形成机理、位置分布等影响带钢表面缺陷检测与分类结果的主要因素。
并根据研究内容提出了三个问题：
(1)带钢图像灰度非均匀分布下边界检测的问题。灰度非均匀分布是带钢表面图像常见的状态之一,如果在该状态下边界检测结果的准确率较低,将严重影响带钢边界缺陷的识别率。
(2)无固定形态缺陷图像分类问题。多数伪缺陷形貌无固定形态,而且许多缺陷的内在属性也具有无固定形态的特征。如果不考虑缺陷的无固定形态特性,缺陷识别率将无法达到工业要求的结果,影响生产。
(3)带钢图像分类方法的实用性问题。分类算法的识别率、噪声型缺陷的过滤能力、分类结果与生产判定标准匹配关系等因素影响带钢图像分类方法的实用性。
围绕上述问题,在多种图像检测与分类方法上,做了以下几方面的深入研究工作：
(1)研究了带钢表面缺陷检测中典型的图像检测与分类方法以及这些方法适用的范围。
(2)研究出基于高斯模型的动态边界检测方法,该方法能够检测带钢背景与表面的灰度差异,动态地确定干扰的灰度范围,与传统带钢表面缺陷检测使用的的固定闽值法和对比度匹配法相比,它能更好的检测边界含重度干扰的边界图像,在其他两种算法准确度仅为4.6%和1.6%时,该算法可以达到62.8%,且实验条件下的检测速度为每千行1.82秒,满足工业要求。
(3)在缺陷分割阶段,研究出基于带钢图像灰度标准化的感兴趣区域搜索算法(Regions of Interest, ROI)和基于缺陷距离阈值的缺陷标记与合并方法。新感兴趣区域搜索方法结构简单,且可以通过判别阈值参数调整搜索结果；新的缺陷标记与合并方法可以通过控制4个参数的大小改变缺陷标记和合并区域。实验验证,该方法能对边缘分割后的纹理不连续性缺陷进行重新组合,实现纹理非连续性缺陷地完整分割,以及同一感兴趣区域不同缺陷的分离。在缺陷分类阶段,研究出一种以Isomap算法为基础,适合监督分类的dls-Isomap算法。该算法对roll-swiss数据建立邻域图时能够减少Isomap算法因k值设置不当引起的“短路边”问题,能够解决dbt-Isomap算法无法对多类roll-swiss数据建立完整邻域图的问题,能够用于多类数据的分类工作。实验表明,基于dls-Isomap的分类方法对冷轧带钢表面缺陷的整体识别率可以达到78%,针对热轧带钢的表面缺陷识别率可以达到93%。最重要的是,当缺陷图像中包含较多无固定形态缺陷时,dls-Isomap方法要明显优于其他方法。
(4)研究出一种新的图像分类系统,系统由一套图像类型主观评价机制、两组主分类器和一个三级图像分类构架组成。实验验证,噪声型缺陷的过滤错误量占总数量的比例低于1%,多卷带钢的整体识别率达到了90%以上。
研究成果已经成功应用于江苏沙钢集团有限公司1450热轧成品机组。经核算,研究应用新增约351.4万元／年的经济效益。
There are two points that making the online strip surface defect detection greatly important on steel production and quality control. One point is,with the high speed development of iron and steel industry, the strip production line speed is increasing; another is consumption enterprises on the strip also put forward higher surface quality requirements with their increasing quality requirements in many filed. But steel strip surface defect detection is slow development with the rapid development of image processing technology. The reason of this problem is failure to make more improvements of related technology for production needs and failure to change these technologies for overcome the obstacles form production environment.
The overview and research of this paper listed as follows are in order to further improve the scientific detection that including accurate data of Industrial production standardization, to improve the degree of automation, to classification accuracy which related rework cost and maintenance cost, to reduce the trade disputes and keep the enterprise reputation.
(1)The developments of domestic and foreign steel surface defect detection technology are reviewed, and analyzed the strip surface defect machine vision inspection technology future trends.
(2)Studied for strip surface image acquisition ways with a variety of production environments. The research topics include lighting, CCD sensors and detection methods. And then the Strip surface defect detection position and detection method in many different production environments have been identified.
(3)Studied for the main factors affecting the cold/hot rolling strip surface defect detection and classification results, which including morphology, formation mechanism, location distribution.
According to the research, three further questions are raised.
(1) The question of strip boundary detection under conditions of non-uniform distribution of gray in strip surface image. non-uniform distribution of gray is the common status of strip surface image. Therefore the accuracy of boundary detection results will seriously affect the boundary defect rate of the strip.
(2)The question of the classification with no-fixed shape defect images. Most pseudo-defects have no-fixed shape, and many features of defect image also have no-fixed shape. If not consider the non-fixed shape characteristics of defects, the defect rate will not adapt the industrial level.
(3)The issues of the strip image classification method have not enough capability in practice.
This paper has done the following in-depth research in many image detection and classification methods with these problem:
(1)Studied for the typical image detection and classification method in strip surface defect detection and classification.
(2)Developed an adaptive boundary detection method which based on Gaussian. This method can detection the gray differences with the surface and the background, can dynamically determine the interference range of gray. Compared to the traditional method of strip surface defect detection, this method can detect stripe boundary that contains the boundary interference. The accuracy of the method up to62.8%form4.6%and1.6%in the most severe case. Detection speed is every thousand lines of1.82seconds
(3)In the stage of defect segmentation, developed an Region of Interest algorithm that base on standard strip gray image. This algorithm has the advantages of simple structure, and through the discrimination threshold parameters can be adjusted for search results. Developed an defect image Connected Component marking and merging method by controlling the4parameters can be resized results.
In the stage of defect classification, developed double-limited and supervise-connect Isomap dimensionality reduction and classification method (dls-Isomap). Based on the dimensionality reduction technique from Isomap, the connection of neighborhood graph is limited by key parameters k-nn and ε-radius, and inter-class neighborhood points are connected extensionally with the supervision of class labels. According to multi-classes roll-swiss data experiments, all the points can be embedded in lower dimensions with the complete inter-class and intra-class geometric structure, and the "short circuit" in the Isomap can be solved by the dls-Isomap method. In addition, stripe surface defect images data experiments show that the new proposed classification method is suitable for the classification of stripe surface defects including more no-fixed shape defect images, with the recognition rate of78%for cold-roll strip images, and93%for hot-roll strip images with water.
(4)Developed a new image classification system, which including a set of image class subjective evaluation mechanism, two sets of the main classifier and a set of three image classification framework. The experiment result show that the filtering error amount of defects in the total number is less than1%. The overall recognition rate of all the experimental steel coil up to90%.
The research results have been successfully applied in Jiangsu Shagang Group Co. Ltd. in 1450Hot Rolling Product Unit. The economic benefits of these application about three million yuan per year.
(1)对国内外带钢表面缺陷检测技术的发展情况进行了综述,并分析了机器视觉带钢表面缺陷检测技术未来的发展趋势。
(2)根据不同的生产环节,阐述了适合多种生产环境下带钢表面图像采集的方式和方法,其中包括照明光源、CCD传感器和检测方式等内容。明确了不同工业生产中的多种带钢表面缺陷检测点位置与检测方式。
(3)以热轧和冷轧生产中对表面缺陷要求最高的钢种类型为基础,阐明了缺陷形貌、形成机理、位置分布等影响带钢表面缺陷检测与分类结果的主要因素。
并根据研究内容提出了三个问题：
(1)带钢图像灰度非均匀分布下边界检测的问题。灰度非均匀分布是带钢表面图像常见的状态之一,如果在该状态下边界检测结果的准确率较低,将严重影响带钢边界缺陷的识别率。
(2)无固定形态缺陷图像分类问题。多数伪缺陷形貌无固定形态,而且许多缺陷的内在属性也具有无固定形态的特征。如果不考虑缺陷的无固定形态特性,缺陷识别率将无法达到工业要求的结果,影响生产。
(3)带钢图像分类方法的实用性问题。分类算法的识别率、噪声型缺陷的过滤能力、分类结果与生产判定标准匹配关系等因素影响带钢图像分类方法的实用性。
围绕上述问题,在多种图像检测与分类方法上,做了以下几方面的深入研究工作：
(1)研究了带钢表面缺陷检测中典型的图像检测与分类方法以及这些方法适用的范围。
(2)研究出基于高斯模型的动态边界检测方法,该方法能够检测带钢背景与表面的灰度差异,动态地确定干扰的灰度范围,与传统带钢表面缺陷检测使用的的固定闽值法和对比度匹配法相比,它能更好的检测边界含重度干扰的边界图像,在其他两种算法准确度仅为4.6%和1.6%时,该算法可以达到62.8%,且实验条件下的检测速度为每千行1.82秒,满足工业要求。
(3)在缺陷分割阶段,研究出基于带钢图像灰度标准化的感兴趣区域搜索算法(Regions of Interest, ROI)和基于缺陷距离阈值的缺陷标记与合并方法。新感兴趣区域搜索方法结构简单,且可以通过判别阈值参数调整搜索结果；新的缺陷标记与合并方法可以通过控制4个参数的大小改变缺陷标记和合并区域。实验验证,该方法能对边缘分割后的纹理不连续性缺陷进行重新组合,实现纹理非连续性缺陷地完整分割,以及同一感兴趣区域不同缺陷的分离。在缺陷分类阶段,研究出一种以Isomap算法为基础,适合监督分类的dls-Isomap算法。该算法对roll-swiss数据建立邻域图时能够减少Isomap算法因k值设置不当引起的“短路边”问题,能够解决dbt-Isomap算法无法对多类roll-swiss数据建立完整邻域图的问题,能够用于多类数据的分类工作。实验表明,基于dls-Isomap的分类方法对冷轧带钢表面缺陷的整体识别率可以达到78%,针对热轧带钢的表面缺陷识别率可以达到93%。最重要的是,当缺陷图像中包含较多无固定形态缺陷时,dls-Isomap方法要明显优于其他方法。
(4)研究出一种新的图像分类系统,系统由一套图像类型主观评价机制、两组主分类器和一个三级图像分类构架组成。实验验证,噪声型缺陷的过滤错误量占总数量的比例低于1%,多卷带钢的整体识别率达到了90%以上。
研究成果已经成功应用于江苏沙钢集团有限公司1450热轧成品机组。经核算,研究应用新增约351.4万元／年的经济效益。
There are two points that making the online strip surface defect detection greatly important on steel production and quality control. One point is,with the high speed development of iron and steel industry, the strip production line speed is increasing; another is consumption enterprises on the strip also put forward higher surface quality requirements with their increasing quality requirements in many filed. But steel strip surface defect detection is slow development with the rapid development of image processing technology. The reason of this problem is failure to make more improvements of related technology for production needs and failure to change these technologies for overcome the obstacles form production environment.
The overview and research of this paper listed as follows are in order to further improve the scientific detection that including accurate data of Industrial production standardization, to improve the degree of automation, to classification accuracy which related rework cost and maintenance cost, to reduce the trade disputes and keep the enterprise reputation.
(1)The developments of domestic and foreign steel surface defect detection technology are reviewed, and analyzed the strip surface defect machine vision inspection technology future trends.
(2)Studied for strip surface image acquisition ways with a variety of production environments. The research topics include lighting, CCD sensors and detection methods. And then the Strip surface defect detection position and detection method in many different production environments have been identified.
(3)Studied for the main factors affecting the cold/hot rolling strip surface defect detection and classification results, which including morphology, formation mechanism, location distribution.
According to the research, three further questions are raised.
(1) The question of strip boundary detection under conditions of non-uniform distribution of gray in strip surface image. non-uniform distribution of gray is the common status of strip surface image. Therefore the accuracy of boundary detection results will seriously affect the boundary defect rate of the strip.
(2)The question of the classification with no-fixed shape defect images. Most pseudo-defects have no-fixed shape, and many features of defect image also have no-fixed shape. If not consider the non-fixed shape characteristics of defects, the defect rate will not adapt the industrial level.
(3)The issues of the strip image classification method have not enough capability in practice.
This paper has done the following in-depth research in many image detection and classification methods with these problem:
(1)Studied for the typical image detection and classification method in strip surface defect detection and classification.
(2)Developed an adaptive boundary detection method which based on Gaussian. This method can detection the gray differences with the surface and the background, can dynamically determine the interference range of gray. Compared to the traditional method of strip surface defect detection, this method can detect stripe boundary that contains the boundary interference. The accuracy of the method up to62.8%form4.6%and1.6%in the most severe case. Detection speed is every thousand lines of1.82seconds
(3)In the stage of defect segmentation, developed an Region of Interest algorithm that base on standard strip gray image. This algorithm has the advantages of simple structure, and through the discrimination threshold parameters can be adjusted for search results. Developed an defect image Connected Component marking and merging method by controlling the4parameters can be resized results.
In the stage of defect classification, developed double-limited and supervise-connect Isomap dimensionality reduction and classification method (dls-Isomap). Based on the dimensionality reduction technique from Isomap, the connection of neighborhood graph is limited by key parameters k-nn and ε-radius, and inter-class neighborhood points are connected extensionally with the supervision of class labels. According to multi-classes roll-swiss data experiments, all the points can be embedded in lower dimensions with the complete inter-class and intra-class geometric structure, and the "short circuit" in the Isomap can be solved by the dls-Isomap method. In addition, stripe surface defect images data experiments show that the new proposed classification method is suitable for the classification of stripe surface defects including more no-fixed shape defect images, with the recognition rate of78%for cold-roll strip images, and93%for hot-roll strip images with water.
(4)Developed a new image classification system, which including a set of image class subjective evaluation mechanism, two sets of the main classifier and a set of three image classification framework. The experiment result show that the filtering error amount of defects in the total number is less than1%. The overall recognition rate of all the experimental steel coil up to90%.
The research results have been successfully applied in Jiangsu Shagang Group Co. Ltd. in 1450Hot Rolling Product Unit. The economic benefits of these application about three million yuan per year.
引文
[1]中国钢铁行业分析报告(2010年4季度).中国经济信息网数据有限公司,2011.1-4；
[2]2011-2015年中国钢铁板材行业市场调查及发展现状分析报告.中商情报网,2011.57；
[3]何永辉；黄胜标.带钢表面质量检测技术研究与实践.中国仪器仪表学会2007学术年会智能检测控制技术及仪表装置发展研讨会论文集,2007,09：1-8；
[4]胡亮.线阵CCD实现钢板表面缺陷在线检测关键技术及其应用研究：[博士学位论文].天津：天津大学,2005;
[5]Goebbels K. and Ferrano G Automation of surface defect detection and evaluation.Memoires et etudes scientifiques de la Revue de metallurgie,1989,86:277-284;
[6]Ochin E F. and Chukreev D P. Analysis of the algorithm for the classification of surface defects of solids of revolution by the signals of scanning transducers. The Soviet journal of nondestructive testing,1989,25:47-51;
[7]Treiber F. On-line automatic defect detection and surface roughness measurement of steel strip. Iron and Steel Engineer,1989,66:26-33;
[8]Piironen T. and Strommer E, et al. Automated visual inspection system for rolled metal surfaces. Technical Paper-Society of Manufacturing Engineers,1989;
[9]Piironen T H. and Kantola P, et al. Design considerations for a metal strip surface inspection system. Proceedings of SPIE-The International Society for Optical Engineering,1994,2353: 422-429;
[10]Muehlemann M M. Standardizing defect detection for the surface inspection of wide flat rolled steel. AISE Steel Technology,2000,77:40-43;
[11]Anon. High speed surface defect detection on strip. Steel Times,1994,222:109-110;
[12]Wiltschi K. Pinz A. and Lindeberg T. Automatic assessment scheme for steel quality inspection. Machine Vision and Applications,2000,12:113-128;
[13]Dufour M L. and Samson M. On-line detection of surface defects on steel billets using multiple grazing-incidence light sources. Proceedings of SPIE-The International Society for Optical Engineering,1992,1614:35-44;
[14]Ntuen C A. and Park E H K. Experimental study of computer-vision reliability in production-line inspection. Proceedings of the Industrial Engineering Research Conference,1993: p 252-25;
[15]Simonis M. and Rinn R. Surface inspection for automatic detection and classification of defects on hot strip. Steel Times International,1998,22:2;
[16]Ceracki P. and Luecking F, et al. On-line detection of hot strip defects through automatic surface inspection. Stahl und Eisen,1999,119:77-82;
[17]GmbH V S. On-line detection, identification and visualization of surface defects. MPT Metallurgical Plant and Technology International,2005,28:24-26;
[18]Keesug C. and Kyungmo K, et al. Development of defect classification algorithm for POSCO rolling strip surface inspection system.2006 SICE-ICASE International Joint Conference,2006:2499-2502;
[19]Kumar A. and Pang G. Identification of surface defects in textured materials using wavelet packets. Conference Record-IAS Annual Meeting (IEEE Industry Applications Society),2001, 1:247-251;
[20]Tsai D M. and Lin C P. Fast defect detection in textured surfaces using 1D Gabor filters. International Journal of Advanced Manufacturing Technology,2002,20:664-675;
[21]Yu G and Kamarthi S V, et al. A new cluster-based feature extraction method for surface defect detection. Proceedings of the 2004 International Conference on Machine Learning and Applications,2004, ICMLA'04:93-98;
[22]Borselli A. and Colla V, et al. Surface defects classification in steel products:A comparison between different artificial intelligence-based approaches. Proceedings of the 11th IASTED International Conference on Artificial Intelligence and Applications,2011,129-134;
[23]Tolba A S. Fast defect detection in homogeneous flat surface products. Expert Systems with Applications,2011,38:12339-12347;
[24]Araki N. and Nishiuchi K, et al. Defect detection for mirror polished metal surface using independent component analysis. ICIC Express Letters,2011,5:3291-3295;
[25]Pernkopf F. and O'Leary P. Image acquisition techniques for automatic visual inspection of metallic surfaces. NDT & E International,2003,36(8):609-617;
[26]Morel O. and Stolz C, et al. Application of polarimetric imaging to 3D inspection of highly reflective metallic surface. Proceedings of SPIE-The International Society for Optical Engineering,2004,5606:p 82-89;
[27]Ren S. and Zhang Z, et al. Inspection of smooth metallic surface using complex discrete wavelet transform.3rd International Conference on Innovative Computing Information and Control,2008,61:69;
[28]Medina R. and Gayubo F, et al. Surface defects detection on rolled steel strips by Gabor filters.3rd International Conference on Computer Vision Theory and Applications,2008, 1:479-485;
[29]卢益民；翁虹；罗志勇.钢带表面缺陷检测信息实时处理方法的研究.华中理工大学学报,1994,22(11)：108-112；
[30]吕红军；罗志勇.冷轧钢板表面缺陷检测的信号处理.量子电子学报,1991,3(01)：61-64；
[31]卢益民；翁虹；罗志勇.冷轧钢带表面缺陷在线检测及系统的计算机接口.华中理工大学学报,1994,22(11)：102-107；
[32]罗志勇；刘栋玉；江涛等.新艰冷轧带钢表面缺陷在线检测系统.华中理工大学学报,1996,24(01)：75-78；
[33]王斌；罗志勇；刘栋玉等.带钢表面重皮缺陷在线图像识别算法研究.华中理工大学学 报,1996,24(08)：35-37；
[34]王斌；罗志勇；刘栋玉等.带钢边缘缺陷实时图象识别与宽度测量算法.无损检测,1997,19(07)：188-190；
[35]吴平川；路同浚；王炎.钢板表面缺陷的无损检测技术与应用.无损检测,1999,22(07)：311-315；
[36]吴平川；路同浚；王炎.机器视觉与钢板表面缺陷的无损检测.无损检测,2000,22(01)：13-16；
[37]吴平川；路同浚；王炎.带钢表面自动检测系统研究现状与展望.钢铁,2000,35(06)：70-75；
[38]徐科；徐金梧；陈雨来.冷轧带钢表面缺陷在线监测系统.北京科技大学学报,2002,24(03)：329-332；
[39]徐科；徐金梧；鹿守理等.冷轧带钢表面自动监测系统的研究.钢铁,2000,35(10)：63-66；
[40]徐科；徐金梧.基于图象处理的冷轧带钢表面缺陷在线检测技术.钢铁,2002.37(12)：61-64；
[41]徐科；徐金梧；班晓娟.冷轧带钢表面质量自动监测系统的模式识别方法研究.钢铁,2002,37(6)：28-31；
[42]徐科；徐金梧；梁治国等.冷轧带钢表面质量自动检测系统的在线应用研究.冶金自动化,2003,(01)：51-53；
[43]李文峰；徐科；杨朝霖.中厚板表面缺陷在线检测系统的分类器设计.钢铁,2006,41(04)：47-50；
[44]徐科；孙浩.形态滤波在中厚板表面裂纹在线检测中的应用.仪器仪表学报,2006,27(09)1008-1011；
[45]徐科；杨朝霖；周鹏.热轧带钢表面缺陷在线检测的方法与工业应用.机械工程学报,2009,45(04)：111-114；
[46]刘乃强；徐科.形态学梯度在带钢表面缺陷检测中的应用.2006全国炼钢连铸过程自动化技术交流会论文集：626-628;
[47]吴贵芳；徐科；徐金梧.基于LVQ神经网络的冷轧带钢表面缺陷分类方法,北京科技大学学报,2005,27(06)：732-735；
[49]吴秀永；徐科；徐金梧.基于Gabor小波和核保局投影算法的表面缺陷自动识别方法.自动化学报,2010,36(3)：438-.441；
[50]甘胜丰；孙林.多级图像分类系统在硅钢冷轧表面缺陷检测中的应用.冶金自动化,2009,33(02)：63-65；
[51]段志娟；周新星.基于独立成分分析的冷轧带钢表面缺陷识别.钢铁研究学报,2011,23(10)：63-66；
[52]刘钟；吴杰；张华.热轧带钢表面质量检测系统的工程设计与实践.宝钢技术,2005,(06)：57-61；
[53]艾矫健；李飞.一种基于线扫描技术的带钢表面检测系统.2007中国钢铁年会论文集；
[54]陈应耀；谢向群；夏晓明.梅山1422mm热连轧机组的现代化改造.轧钢,2004,21(06)：59-62；
[55]王军.梅钢1422热轧在线检测技术的应用金属材料与冶金工程,2010,38(04)：50-52；
[56]胡亮；段发阶.带钢表面缺陷计算机视觉在线检测系统的设计.无损检测,2003,25(06)：287-290；
[57]胡亮；段发阶.钢板表面缺陷计算机视觉在线检测系统的研制.钢铁,2005,40(02)：59-61；
[58]郑健峰.带钢表面缺陷检测方法研究：[硕十学位论文].西安：西安建筑科技大学,2005；
[59]汤勃；孔建益.基于数学形态学的带钢表面缺陷检测研究.钢铁研究学报,2010,22(10)：56-59；
[60]王路；陈黎；徐朝阳.基于局部信息熵迭代的带钢表面缺陷分.微计算机信息,2011,27(06)：208-210；
[61]许道峰；邸小娟.基于LVQ的带钢表面缺陷分类研究.中国仪器仪表,2004,(02)：5-7；
[62]刘红冰；康戈文.基于神经网络的冷轧带钢表面缺陷检测.中国图象图形学报,2005,(10)10：1310-1311；
[63]费江华；何永辉；孙晨.一种基于特征选择的组合分类器在带钢表面缺陷分类中的应用.冶金自动化,2010,34(02)：19-23；
[64]朱向华；苏宏立.一种基于支持向量机的带钢表面缺陷识别方法.浙江商职业技术学院学报.2011,10(04)：92-96；
[65]汤勃；孔建益；王兴东.基于遗传算法的带钢表面缺陷特征降维优化选择.钢铁研究学报,2011,23(09)：59-62；
[66]张洪涛.钢板表面缺陷在线视觉检测系统关键技术研究：[博十学位论文].天津：天津大学,2008；
[67]徐晓星.光纤照明的原理与应用.灯与照明,2002,26(5)：29-30；
[68]周鸿；赵宏.基于线阵CCD阵列的在线检测方法.半导体技术,2001,26(11)：1-4；
[69]Arutyunov V A. and Sorokin O V. Performance improvement of CCD image sensor arrays. Russian Microelectronics,2000,29(5):303-306;
[70]Zheng H. and Kong X L, et al. Automatic inspection of metallic surface defects using genetic algorithms. Journal of Materials Processing Technology,2002,125-126:427-433;
[71]Yazdchi M. and Yazdi M, et al. Steel surface defect detection using texture segmentation based on multifractal dimension.2009 International Conference on Digital Image Processing: 346-350;
[72]林竹君；杨飒.CCD非接触检测技术在工业生产中的实际应用.河北工业科技,2009,25(5)：335-344；
[73]Tretjakov V. and Baryshev V, et al. Automatic surface inspection at the NLMK hot strip mill. MPT Metallurgical Plant and Technology International,2005,28:54-60;
[74]Iivarinen J. and Heikkinen, et al. Defect detection scheme for web surface inspection. International Journal of Pattern Recognition and Artificial Intelligence,2000,14:735-755;
[75]王军.梅钢1422热轧在线检测技术的应用.金属材料与冶金工程,2010,38(04)：50-52；
[76]Raus M. and Kotthoff N, et al. New developments in surface inspection of galvanized strip. MPT Metallurgical Plant and Technology International,2011,24:94-97;
[77]冈萨雷斯.数字图像处理.第二版中文版.电子工业出版社,2004,175-189；
[78]朱红高.图像边缘检测技术研究现状.制造业自动化,2010,32(1)：45-47；
[79]Chen P C. and Pavlidis T. Segementation by Texture using a Co-occurrence Matrix and a split-and-merge Algorithm. Comput.Graphics Image Process,1979,10:172-182;
[80]陈燕平；张德富；沈平.基于局部操作的一种有效标记算法.计算机学 报,1993,16(10)：744-749；
[81]Iivarinen J. Surface defect detection with histogram-based texture features. Proceedings of SPIE-The International Society for Optical Engineering,2000,4197:140-145;
[82]韩国强.基于小样本的线性降维算法与应用研究：[硕十学位论文].广州：华南理工大学,2010；
[83]徐蓉；姜峰；姚鸿勋.流形学习概述.智能系统学报,2006,1(1)：44-51；
[84]沈庭芝；闫雪梅.数字图像处理及模式识别.第二版.北京理工大学出版社,2007.162-203；
[85]周家齐.热轧钢板表面缺陷浅析.重钢技术,1991,34(2)：32-35；
[86]李峰；叶学卫；姜正连.冷轧带钢表面缺陷识别与控制.冶金设备,2010,(1)：65-69；
[87]李成良；周成宏；刘东升.SPHC冷轧基板常见表面缺陷及其原因.上海金属,2013,35(1)：4-45；
[88]朱浩；郭德福；熊文涛.热轧带钢麻点原因及控制措施.金属热处理,2013,38(3)：127-129；
[89]Tolba A S. A novel multiscale-multidirectional autocorrelation approach for defect detection in homogeneous flat surfaces. Machine Vision and Applications,2011,10:1-12;
[90]翟青涌；黄建国；程玉华.基于梯度算子的线阵CCD图像边缘检测方法研究.电子质量.2009(10)：1-2；
[91]Burns J B;Hanson A R; Riseman E M. Extracting straight lines. Pattern Analysis and Machine Intelligence,1986, PAMI-8(4),425-455;
[92]Hull R. and Osgood R M. Image Processing of Edge and Surface Defects. Springer Series in Materials Science, Springer-Verlag Berlin Heidelberg,2009,32-50;
[93]Naidu D K, Fisher R B, A comparison of algorithms for sub-pixel peak detection, Department of Artifical Intelligence, DAI Research Paper No.553,1991;
[93]Mohajeri M H. and Manning P J. ARIA:an Perating system of Pavement distress diagnosis by image Proeessing. Trans Portation Research Record,1991,1311:120-130.
[94]Wu W Y. and Hou C C. Automated metal surface inspection through machine vision. Imaging Science Journal,2003,51:79-88;
[95]徐科.基于图像处理的冷轧带钢表面监测系统的研究与实现：[博士学位论文].北京：北京科技大学,2000
[96]Mohajeri M H. and Manning P J. ARIA:an Perating system of Pavement distress diagnosis by image Proeessing. Trans Portation Research Record,1991,1311:120-130.
[97]Roweis S T; Saul L K. Nonlinear dimensionality reduction by locally linear embedding. Science,2000,290:2323-2326;
[98]Jianjun W. Improved Genetic Algorithm Based 2-D Maximum Entropy Image Segmentation Algorithm. Advances in Computer Science and Information Engineering,2012,(169):529-534;
[99]王文渊；王芳梅.改进的最大熵算法在图像分割中的应用.计算机仿真,2011,28(8)：291-294；
[100]Palenichka R M. Defect Detection on Imaging Surfaces by Using Multi-Scale Image Analysis. International Conference on Digital Printing Technologies,2000,373-376;
[101]Rallo M. and Millan M S, et al. Unsupervised local defect segmentation in textures using Gabor filters:application to industrial inspection. Proceedings of SPIE-The International Society for Optical Engineering,2009,7443;
[102]韩国强.基于小样本的线性降维算法与应用研究：[硕土学位论文].广州：华南理工大学,2010：
[103]Tenenbaum J B; Silva V; Langford JC. A global geometric framework for onlinear dimensionality reduction. Science,2000,290,2319-2323;
[104]阳建宏；杨德斌；徐科等.非线性降维在冷轧带钢表面缺陷分类中的应用.钢铁,2005,40(12)：37-40
[105]Belkin M; Niyogi P. Laplacian eigenmaps for dimensionality reduction and data representation. Neural Comput.2003,15:1373-1396;
[106]Liu C; Sun W; Wang R. Nonlinear Dimensionality Reduction via the ENH-LTSA Method for Hyperspectral Image Classification. Selected Topics in Applied Earth Observations and Remote Sensing,2013,99, PP:1-14;
[107]李波.基于流形学习的特征提取方法及其应用研究：[博士学位论文].合肥：中国科学技术大学,2008;
[108]Geng X; Zhan D C; Zhou Z H. Supervised Nonlinear Dimensionality Reduction for Visualization and Classification. IEEE Transactions on Systems Man and Cybernetics Pan B— Cybernetics,2005,35(6):1098-1107;
[109]Orsemogo C; Vercellis C. An effective double-bouned tree-connected Isomap algorithm for microarray data classification, Pattern Recognition Letters,2012,33:9-16;
[110]Cox T F; Cox M A A. Multidimensional Scaling. Chapman & Hall, London,1994;
[111]夏静；基于广义回归神经网络的工业过程优化建模,2009,哈尔滨理工大学,硕十学位论文;
[112]Krasser S; Yuchun T; Gould J. Identifying Image Spam based on Header and File Properties using C4.5 Decision Trees and Support Vector Machine Learning. Information Assurance and Security Workshop,2007. IAW'07. IEEE SMC,2007.255-261
[113]王志瑞；闫彩良.图像特征提取方法的综述.吉首大学学报(自然科学版)2011,32(05)：43-47；
[114]Andalo F A.; Miranda P A V, and Torres R. Shape feature extraction and description based on tensor scale. Pattern Recognition,2010,43:26-36;
[115]Chengjun L. New Color Features for Pattern Recognition. Cross Disciplinary Biometric Systems,2012,37:15-34;
[116]Mingqiang Y; Kidiyo K; Joseph R. A survey of shape feature extraction techniques. Pattern Recognition Techniques, Technology and Applications,2008,978-953;
[117]沈文武.因果图推理算法及专家系统应用研究：[博十学位论文].重庆：重庆大学,2005；
[118]李航.统计学习方法.第一版.北京：清华大学出版社,2012.95-100；
[2]2011-2015年中国钢铁板材行业市场调查及发展现状分析报告.中商情报网,2011.57；
[3]何永辉；黄胜标.带钢表面质量检测技术研究与实践.中国仪器仪表学会2007学术年会智能检测控制技术及仪表装置发展研讨会论文集,2007,09：1-8；
[4]胡亮.线阵CCD实现钢板表面缺陷在线检测关键技术及其应用研究：[博士学位论文].天津：天津大学,2005;
[5]Goebbels K. and Ferrano G Automation of surface defect detection and evaluation.Memoires et etudes scientifiques de la Revue de metallurgie,1989,86:277-284;
[6]Ochin E F. and Chukreev D P. Analysis of the algorithm for the classification of surface defects of solids of revolution by the signals of scanning transducers. The Soviet journal of nondestructive testing,1989,25:47-51;
[7]Treiber F. On-line automatic defect detection and surface roughness measurement of steel strip. Iron and Steel Engineer,1989,66:26-33;
[8]Piironen T. and Strommer E, et al. Automated visual inspection system for rolled metal surfaces. Technical Paper-Society of Manufacturing Engineers,1989;
[9]Piironen T H. and Kantola P, et al. Design considerations for a metal strip surface inspection system. Proceedings of SPIE-The International Society for Optical Engineering,1994,2353: 422-429;
[10]Muehlemann M M. Standardizing defect detection for the surface inspection of wide flat rolled steel. AISE Steel Technology,2000,77:40-43;
[11]Anon. High speed surface defect detection on strip. Steel Times,1994,222:109-110;
[12]Wiltschi K. Pinz A. and Lindeberg T. Automatic assessment scheme for steel quality inspection. Machine Vision and Applications,2000,12:113-128;
[13]Dufour M L. and Samson M. On-line detection of surface defects on steel billets using multiple grazing-incidence light sources. Proceedings of SPIE-The International Society for Optical Engineering,1992,1614:35-44;
[14]Ntuen C A. and Park E H K. Experimental study of computer-vision reliability in production-line inspection. Proceedings of the Industrial Engineering Research Conference,1993: p 252-25;
[15]Simonis M. and Rinn R. Surface inspection for automatic detection and classification of defects on hot strip. Steel Times International,1998,22:2;
[16]Ceracki P. and Luecking F, et al. On-line detection of hot strip defects through automatic surface inspection. Stahl und Eisen,1999,119:77-82;
[17]GmbH V S. On-line detection, identification and visualization of surface defects. MPT Metallurgical Plant and Technology International,2005,28:24-26;
[18]Keesug C. and Kyungmo K, et al. Development of defect classification algorithm for POSCO rolling strip surface inspection system.2006 SICE-ICASE International Joint Conference,2006:2499-2502;
[19]Kumar A. and Pang G. Identification of surface defects in textured materials using wavelet packets. Conference Record-IAS Annual Meeting (IEEE Industry Applications Society),2001, 1:247-251;
[20]Tsai D M. and Lin C P. Fast defect detection in textured surfaces using 1D Gabor filters. International Journal of Advanced Manufacturing Technology,2002,20:664-675;
[21]Yu G and Kamarthi S V, et al. A new cluster-based feature extraction method for surface defect detection. Proceedings of the 2004 International Conference on Machine Learning and Applications,2004, ICMLA'04:93-98;
[22]Borselli A. and Colla V, et al. Surface defects classification in steel products:A comparison between different artificial intelligence-based approaches. Proceedings of the 11th IASTED International Conference on Artificial Intelligence and Applications,2011,129-134;
[23]Tolba A S. Fast defect detection in homogeneous flat surface products. Expert Systems with Applications,2011,38:12339-12347;
[24]Araki N. and Nishiuchi K, et al. Defect detection for mirror polished metal surface using independent component analysis. ICIC Express Letters,2011,5:3291-3295;
[25]Pernkopf F. and O'Leary P. Image acquisition techniques for automatic visual inspection of metallic surfaces. NDT & E International,2003,36(8):609-617;
[26]Morel O. and Stolz C, et al. Application of polarimetric imaging to 3D inspection of highly reflective metallic surface. Proceedings of SPIE-The International Society for Optical Engineering,2004,5606:p 82-89;
[27]Ren S. and Zhang Z, et al. Inspection of smooth metallic surface using complex discrete wavelet transform.3rd International Conference on Innovative Computing Information and Control,2008,61:69;
[28]Medina R. and Gayubo F, et al. Surface defects detection on rolled steel strips by Gabor filters.3rd International Conference on Computer Vision Theory and Applications,2008, 1:479-485;
[29]卢益民；翁虹；罗志勇.钢带表面缺陷检测信息实时处理方法的研究.华中理工大学学报,1994,22(11)：108-112；
[30]吕红军；罗志勇.冷轧钢板表面缺陷检测的信号处理.量子电子学报,1991,3(01)：61-64；
[31]卢益民；翁虹；罗志勇.冷轧钢带表面缺陷在线检测及系统的计算机接口.华中理工大学学报,1994,22(11)：102-107；
[32]罗志勇；刘栋玉；江涛等.新艰冷轧带钢表面缺陷在线检测系统.华中理工大学学报,1996,24(01)：75-78；
[33]王斌；罗志勇；刘栋玉等.带钢表面重皮缺陷在线图像识别算法研究.华中理工大学学 报,1996,24(08)：35-37；
[34]王斌；罗志勇；刘栋玉等.带钢边缘缺陷实时图象识别与宽度测量算法.无损检测,1997,19(07)：188-190；
[35]吴平川；路同浚；王炎.钢板表面缺陷的无损检测技术与应用.无损检测,1999,22(07)：311-315；
[36]吴平川；路同浚；王炎.机器视觉与钢板表面缺陷的无损检测.无损检测,2000,22(01)：13-16；
[37]吴平川；路同浚；王炎.带钢表面自动检测系统研究现状与展望.钢铁,2000,35(06)：70-75；
[38]徐科；徐金梧；陈雨来.冷轧带钢表面缺陷在线监测系统.北京科技大学学报,2002,24(03)：329-332；
[39]徐科；徐金梧；鹿守理等.冷轧带钢表面自动监测系统的研究.钢铁,2000,35(10)：63-66；
[40]徐科；徐金梧.基于图象处理的冷轧带钢表面缺陷在线检测技术.钢铁,2002.37(12)：61-64；
[41]徐科；徐金梧；班晓娟.冷轧带钢表面质量自动监测系统的模式识别方法研究.钢铁,2002,37(6)：28-31；
[42]徐科；徐金梧；梁治国等.冷轧带钢表面质量自动检测系统的在线应用研究.冶金自动化,2003,(01)：51-53；
[43]李文峰；徐科；杨朝霖.中厚板表面缺陷在线检测系统的分类器设计.钢铁,2006,41(04)：47-50；
[44]徐科；孙浩.形态滤波在中厚板表面裂纹在线检测中的应用.仪器仪表学报,2006,27(09)1008-1011；
[45]徐科；杨朝霖；周鹏.热轧带钢表面缺陷在线检测的方法与工业应用.机械工程学报,2009,45(04)：111-114；
[46]刘乃强；徐科.形态学梯度在带钢表面缺陷检测中的应用.2006全国炼钢连铸过程自动化技术交流会论文集：626-628;
[47]吴贵芳；徐科；徐金梧.基于LVQ神经网络的冷轧带钢表面缺陷分类方法,北京科技大学学报,2005,27(06)：732-735；
[49]吴秀永；徐科；徐金梧.基于Gabor小波和核保局投影算法的表面缺陷自动识别方法.自动化学报,2010,36(3)：438-.441；
[50]甘胜丰；孙林.多级图像分类系统在硅钢冷轧表面缺陷检测中的应用.冶金自动化,2009,33(02)：63-65；
[51]段志娟；周新星.基于独立成分分析的冷轧带钢表面缺陷识别.钢铁研究学报,2011,23(10)：63-66；
[52]刘钟；吴杰；张华.热轧带钢表面质量检测系统的工程设计与实践.宝钢技术,2005,(06)：57-61；
[53]艾矫健；李飞.一种基于线扫描技术的带钢表面检测系统.2007中国钢铁年会论文集；
[54]陈应耀；谢向群；夏晓明.梅山1422mm热连轧机组的现代化改造.轧钢,2004,21(06)：59-62；
[55]王军.梅钢1422热轧在线检测技术的应用金属材料与冶金工程,2010,38(04)：50-52；
[56]胡亮；段发阶.带钢表面缺陷计算机视觉在线检测系统的设计.无损检测,2003,25(06)：287-290；
[57]胡亮；段发阶.钢板表面缺陷计算机视觉在线检测系统的研制.钢铁,2005,40(02)：59-61；
[58]郑健峰.带钢表面缺陷检测方法研究：[硕十学位论文].西安：西安建筑科技大学,2005；
[59]汤勃；孔建益.基于数学形态学的带钢表面缺陷检测研究.钢铁研究学报,2010,22(10)：56-59；
[60]王路；陈黎；徐朝阳.基于局部信息熵迭代的带钢表面缺陷分.微计算机信息,2011,27(06)：208-210；
[61]许道峰；邸小娟.基于LVQ的带钢表面缺陷分类研究.中国仪器仪表,2004,(02)：5-7；
[62]刘红冰；康戈文.基于神经网络的冷轧带钢表面缺陷检测.中国图象图形学报,2005,(10)10：1310-1311；
[63]费江华；何永辉；孙晨.一种基于特征选择的组合分类器在带钢表面缺陷分类中的应用.冶金自动化,2010,34(02)：19-23；
[64]朱向华；苏宏立.一种基于支持向量机的带钢表面缺陷识别方法.浙江商职业技术学院学报.2011,10(04)：92-96；
[65]汤勃；孔建益；王兴东.基于遗传算法的带钢表面缺陷特征降维优化选择.钢铁研究学报,2011,23(09)：59-62；
[66]张洪涛.钢板表面缺陷在线视觉检测系统关键技术研究：[博十学位论文].天津：天津大学,2008；
[67]徐晓星.光纤照明的原理与应用.灯与照明,2002,26(5)：29-30；
[68]周鸿；赵宏.基于线阵CCD阵列的在线检测方法.半导体技术,2001,26(11)：1-4；
[69]Arutyunov V A. and Sorokin O V. Performance improvement of CCD image sensor arrays. Russian Microelectronics,2000,29(5):303-306;
[70]Zheng H. and Kong X L, et al. Automatic inspection of metallic surface defects using genetic algorithms. Journal of Materials Processing Technology,2002,125-126:427-433;
[71]Yazdchi M. and Yazdi M, et al. Steel surface defect detection using texture segmentation based on multifractal dimension.2009 International Conference on Digital Image Processing: 346-350;
[72]林竹君；杨飒.CCD非接触检测技术在工业生产中的实际应用.河北工业科技,2009,25(5)：335-344；
[73]Tretjakov V. and Baryshev V, et al. Automatic surface inspection at the NLMK hot strip mill. MPT Metallurgical Plant and Technology International,2005,28:54-60;
[74]Iivarinen J. and Heikkinen, et al. Defect detection scheme for web surface inspection. International Journal of Pattern Recognition and Artificial Intelligence,2000,14:735-755;
[75]王军.梅钢1422热轧在线检测技术的应用.金属材料与冶金工程,2010,38(04)：50-52；
[76]Raus M. and Kotthoff N, et al. New developments in surface inspection of galvanized strip. MPT Metallurgical Plant and Technology International,2011,24:94-97;
[77]冈萨雷斯.数字图像处理.第二版中文版.电子工业出版社,2004,175-189；
[78]朱红高.图像边缘检测技术研究现状.制造业自动化,2010,32(1)：45-47；
[79]Chen P C. and Pavlidis T. Segementation by Texture using a Co-occurrence Matrix and a split-and-merge Algorithm. Comput.Graphics Image Process,1979,10:172-182;
[80]陈燕平；张德富；沈平.基于局部操作的一种有效标记算法.计算机学 报,1993,16(10)：744-749；
[81]Iivarinen J. Surface defect detection with histogram-based texture features. Proceedings of SPIE-The International Society for Optical Engineering,2000,4197:140-145;
[82]韩国强.基于小样本的线性降维算法与应用研究：[硕十学位论文].广州：华南理工大学,2010；
[83]徐蓉；姜峰；姚鸿勋.流形学习概述.智能系统学报,2006,1(1)：44-51；
[84]沈庭芝；闫雪梅.数字图像处理及模式识别.第二版.北京理工大学出版社,2007.162-203；
[85]周家齐.热轧钢板表面缺陷浅析.重钢技术,1991,34(2)：32-35；
[86]李峰；叶学卫；姜正连.冷轧带钢表面缺陷识别与控制.冶金设备,2010,(1)：65-69；
[87]李成良；周成宏；刘东升.SPHC冷轧基板常见表面缺陷及其原因.上海金属,2013,35(1)：4-45；
[88]朱浩；郭德福；熊文涛.热轧带钢麻点原因及控制措施.金属热处理,2013,38(3)：127-129；
[89]Tolba A S. A novel multiscale-multidirectional autocorrelation approach for defect detection in homogeneous flat surfaces. Machine Vision and Applications,2011,10:1-12;
[90]翟青涌；黄建国；程玉华.基于梯度算子的线阵CCD图像边缘检测方法研究.电子质量.2009(10)：1-2；
[91]Burns J B;Hanson A R; Riseman E M. Extracting straight lines. Pattern Analysis and Machine Intelligence,1986, PAMI-8(4),425-455;
[92]Hull R. and Osgood R M. Image Processing of Edge and Surface Defects. Springer Series in Materials Science, Springer-Verlag Berlin Heidelberg,2009,32-50;
[93]Naidu D K, Fisher R B, A comparison of algorithms for sub-pixel peak detection, Department of Artifical Intelligence, DAI Research Paper No.553,1991;
[93]Mohajeri M H. and Manning P J. ARIA:an Perating system of Pavement distress diagnosis by image Proeessing. Trans Portation Research Record,1991,1311:120-130.
[94]Wu W Y. and Hou C C. Automated metal surface inspection through machine vision. Imaging Science Journal,2003,51:79-88;
[95]徐科.基于图像处理的冷轧带钢表面监测系统的研究与实现：[博士学位论文].北京：北京科技大学,2000
[96]Mohajeri M H. and Manning P J. ARIA:an Perating system of Pavement distress diagnosis by image Proeessing. Trans Portation Research Record,1991,1311:120-130.
[97]Roweis S T; Saul L K. Nonlinear dimensionality reduction by locally linear embedding. Science,2000,290:2323-2326;
[98]Jianjun W. Improved Genetic Algorithm Based 2-D Maximum Entropy Image Segmentation Algorithm. Advances in Computer Science and Information Engineering,2012,(169):529-534;
[99]王文渊；王芳梅.改进的最大熵算法在图像分割中的应用.计算机仿真,2011,28(8)：291-294；
[100]Palenichka R M. Defect Detection on Imaging Surfaces by Using Multi-Scale Image Analysis. International Conference on Digital Printing Technologies,2000,373-376;
[101]Rallo M. and Millan M S, et al. Unsupervised local defect segmentation in textures using Gabor filters:application to industrial inspection. Proceedings of SPIE-The International Society for Optical Engineering,2009,7443;
[102]韩国强.基于小样本的线性降维算法与应用研究：[硕土学位论文].广州：华南理工大学,2010：
[103]Tenenbaum J B; Silva V; Langford JC. A global geometric framework for onlinear dimensionality reduction. Science,2000,290,2319-2323;
[104]阳建宏；杨德斌；徐科等.非线性降维在冷轧带钢表面缺陷分类中的应用.钢铁,2005,40(12)：37-40
[105]Belkin M; Niyogi P. Laplacian eigenmaps for dimensionality reduction and data representation. Neural Comput.2003,15:1373-1396;
[106]Liu C; Sun W; Wang R. Nonlinear Dimensionality Reduction via the ENH-LTSA Method for Hyperspectral Image Classification. Selected Topics in Applied Earth Observations and Remote Sensing,2013,99, PP:1-14;
[107]李波.基于流形学习的特征提取方法及其应用研究：[博士学位论文].合肥：中国科学技术大学,2008;
[108]Geng X; Zhan D C; Zhou Z H. Supervised Nonlinear Dimensionality Reduction for Visualization and Classification. IEEE Transactions on Systems Man and Cybernetics Pan B— Cybernetics,2005,35(6):1098-1107;
[109]Orsemogo C; Vercellis C. An effective double-bouned tree-connected Isomap algorithm for microarray data classification, Pattern Recognition Letters,2012,33:9-16;
[110]Cox T F; Cox M A A. Multidimensional Scaling. Chapman & Hall, London,1994;
[111]夏静；基于广义回归神经网络的工业过程优化建模,2009,哈尔滨理工大学,硕十学位论文;
[112]Krasser S; Yuchun T; Gould J. Identifying Image Spam based on Header and File Properties using C4.5 Decision Trees and Support Vector Machine Learning. Information Assurance and Security Workshop,2007. IAW'07. IEEE SMC,2007.255-261
[113]王志瑞；闫彩良.图像特征提取方法的综述.吉首大学学报(自然科学版)2011,32(05)：43-47；
[114]Andalo F A.; Miranda P A V, and Torres R. Shape feature extraction and description based on tensor scale. Pattern Recognition,2010,43:26-36;
[115]Chengjun L. New Color Features for Pattern Recognition. Cross Disciplinary Biometric Systems,2012,37:15-34;
[116]Mingqiang Y; Kidiyo K; Joseph R. A survey of shape feature extraction techniques. Pattern Recognition Techniques, Technology and Applications,2008,978-953;
[117]沈文武.因果图推理算法及专家系统应用研究：[博十学位论文].重庆：重庆大学,2005；
[118]李航.统计学习方法.第一版.北京：清华大学出版社,2012.95-100；
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |