带钢表面缺陷图像检测理论及识别算法研究
|
摘要
轧制钢板是工业生产中的重要材料，钢板的质量直接影响到终端产品的质量。钢板的表面缺陷是影响钢板质量的重要因素，除了通过改进轧制工艺，以减少缺陷发生外，及时检测出钢板的表面缺陷也非常重要。本文深入研究了轧制钢板表面缺陷图像检测理论和识别算法，主要包括如下几方面内容：
基于缺陷检测和分类识别分步进行的思想，提出采用图像复杂度快速检测钢板表面缺陷的方法，从提高检测可靠性和节约检测时间出发，对四种图像复杂度描述参数的缺陷图像检测结果进行对比，根据检测结果，以图像的像素变化率作为图像复杂度描述参数进行缺陷图像检测，通过现场图像仿真，该方法能够正确检测出图像中的缺陷并且耗时较少，可以满足在线检测要求。
针对带钢表面背景区域纹理对分割产生的影响，提出采用图像局部复杂度和局部方差相结合的方法对背景纹理进行弱化，并采用基于Gaussian高频滤波方法对缺陷图像进行同态滤波，以去除图像亮斑、增强对比度，选用PSNR、MSE和Q值三个参数对滤波后图像进行评价，通过与常用的直方图均衡增强方法进行对比发现，其视觉和参数表现均更好。
基于视觉注意机制的缺陷图像分割，提出早期视觉特征选择方法，通过对缺陷图像的分析，选取灰度图像的亮度特征、稀少性特征、局部复杂度特征作为生成特征显著度图的早期特征，并给出计算表达式，以此为基础生成各特征显著度图，并采用Gaussian滤波获取全局特征显著度图。
提出改进的视觉特征显著度图融合方法，采用归一化特征显著度图的复杂度和熵值作为参数进行融合以得到综合显著度图，能够体现不同特征显著度图对综合显著度图的贡献差异；采用最大熵法对综合显著度图缺陷分割，通过与聚类分割法和区域增长分割法比较发现，改进后的视觉注意分割法能够获得更好的分割效果。
分析图像各种特征的适应性，提出缺陷图像的特征选取方法，充分考虑分割前后图像包含的不同信息，提取反映缺陷图像全局特征的纹理特征值、反映分割后缺陷形状特征的不变矩特征值和反映缺陷分布情况的离散度特征值，并将上述特征值作为缺陷图像的分类依据。
将可拓理论引入缺陷图像分类中，讨论了可拓理论用于缺陷图像分类的可行性；提出改进的关联度计算方法，给出了计算表达式，并进行了有效性论证。以待分物元的实际特征值与不同类别经典域的距的绝对值和各距绝对值之和的商来计算关联度加权系数，强化了待分类缺陷自身特征值对最终关联度值的影响，分类结果显示较原有的关联度计算方法有更好的效果。
通过统计分析获取缺陷类别特征值的经典域和节域，选取七类缺陷进行分类仿真，采用改进后的关联度计算方法获取待分类缺陷相对于各类缺陷的综合关联度，以最大关联度判断待分类缺陷所属缺陷类别，分类正确率接近90%，有效提高了分类正确率。
Rolled steel strips are important materials in industrial productions, so the quality of steelstrips will have serious influence on that of end products.Surface defects on steel strips aresignificant factors in evaluating quality of them. Except improving rolling technology todecrease defects,Detecting defects in time to avoide application of defects’ strip in endproducts is also very important.Algorithms and theories of defects detecting on rolled steelstrip surfaces by images are researched in this article.The research topics are as follows：
Quick defects detecting method is brought forward based on the principal that defectsdetecting and classification carried out in stages.Image complexity is introduced to quicklydetect defects on steel strip surfaces.Proceeding from reliability and time saving, four imagecomplexity describling parameters are compared to each other in detecting results, finallyRPVC is selected to detect defects on strip surfaces. Simulation shows that RPVC can detectdefects correctly using shorter time and realize detecting in time.
Defects images preprocessing is also researched in this article, in view of the influenceon defect segmentation by textures on images’ background, combination of local complexityand local variance is applied to weaken background textures and Gaussian high frequencyfilter is used to homomorphicly filter defects’ images to wipe of bright spot and enhancecontrast. Three parameters are selected to evaluate the quality of filtered images andcompared to the results of histogram enhancing, all shows better effects.
Visual features selection method is put forward to segment defect images by visualattention mechanism. After analysis of defect images, brightness, rareness and localcomplexity are selected to be features to generate salient images, expressions of them areprovided. Gaussian filter is used to get global salient images.
Improved salient images fused method is brought forward. We modified the weightcoefficients of feature salient images fusion computering method, Normalized complexity andentropy values of salient images are used as weight to generate comprehensive salient image,this can reflect the differences of different salient images’ contribution to comprehensivesalient image. Maximum entropy is used to segment comprehensive salient images,compare with results of K-means method and region-growing method, the improvedsegmentation method based on visual attention model has better effect.
For the purpose of defects classification, defect images’ features selecting method isprovided after analyzing the adaptability of different characters of them. In view of differentinformations included in unsegmented and segmented images, texture features, invariant moment features and dispersion are selected to be classification features.
Extenics theory is introduced into images classification.Feasibility of extenics theory inimages classification is discussed. Weight coefficients of defects images unspecifided topre-selected types of defects images in computering relevancy values are improved and theexpression is provided, the effectiveness of the improved computering method is alsodemonstrated. The quotients of distance between feature values and classical domain andsum of these distances are used as weight coffecients in computering comprehensiverelevancy values.This computering method enhances the influences of defects’ self featurevalues on comprehensive relevancy..
Classical domain and joint domain are key parameters in application of extenics theory,they are gotten by statistics analysis of a number of defects images.Seven defects types areselected to simulate the method, maximum relevancy value is used to group the unspecifieddefect image in one of preselected defect types, classification accuracy is close to90%,comparing to primary weight coefficient computering method, the improved theory is moreeffective in defects images classification.
基于缺陷检测和分类识别分步进行的思想，提出采用图像复杂度快速检测钢板表面缺陷的方法，从提高检测可靠性和节约检测时间出发，对四种图像复杂度描述参数的缺陷图像检测结果进行对比，根据检测结果，以图像的像素变化率作为图像复杂度描述参数进行缺陷图像检测，通过现场图像仿真，该方法能够正确检测出图像中的缺陷并且耗时较少，可以满足在线检测要求。
针对带钢表面背景区域纹理对分割产生的影响，提出采用图像局部复杂度和局部方差相结合的方法对背景纹理进行弱化，并采用基于Gaussian高频滤波方法对缺陷图像进行同态滤波，以去除图像亮斑、增强对比度，选用PSNR、MSE和Q值三个参数对滤波后图像进行评价，通过与常用的直方图均衡增强方法进行对比发现，其视觉和参数表现均更好。
基于视觉注意机制的缺陷图像分割，提出早期视觉特征选择方法，通过对缺陷图像的分析，选取灰度图像的亮度特征、稀少性特征、局部复杂度特征作为生成特征显著度图的早期特征，并给出计算表达式，以此为基础生成各特征显著度图，并采用Gaussian滤波获取全局特征显著度图。
提出改进的视觉特征显著度图融合方法，采用归一化特征显著度图的复杂度和熵值作为参数进行融合以得到综合显著度图，能够体现不同特征显著度图对综合显著度图的贡献差异；采用最大熵法对综合显著度图缺陷分割，通过与聚类分割法和区域增长分割法比较发现，改进后的视觉注意分割法能够获得更好的分割效果。
分析图像各种特征的适应性，提出缺陷图像的特征选取方法，充分考虑分割前后图像包含的不同信息，提取反映缺陷图像全局特征的纹理特征值、反映分割后缺陷形状特征的不变矩特征值和反映缺陷分布情况的离散度特征值，并将上述特征值作为缺陷图像的分类依据。
将可拓理论引入缺陷图像分类中，讨论了可拓理论用于缺陷图像分类的可行性；提出改进的关联度计算方法，给出了计算表达式，并进行了有效性论证。以待分物元的实际特征值与不同类别经典域的距的绝对值和各距绝对值之和的商来计算关联度加权系数，强化了待分类缺陷自身特征值对最终关联度值的影响，分类结果显示较原有的关联度计算方法有更好的效果。
通过统计分析获取缺陷类别特征值的经典域和节域，选取七类缺陷进行分类仿真，采用改进后的关联度计算方法获取待分类缺陷相对于各类缺陷的综合关联度，以最大关联度判断待分类缺陷所属缺陷类别，分类正确率接近90%，有效提高了分类正确率。
Rolled steel strips are important materials in industrial productions, so the quality of steelstrips will have serious influence on that of end products.Surface defects on steel strips aresignificant factors in evaluating quality of them. Except improving rolling technology todecrease defects,Detecting defects in time to avoide application of defects’ strip in endproducts is also very important.Algorithms and theories of defects detecting on rolled steelstrip surfaces by images are researched in this article.The research topics are as follows：
Quick defects detecting method is brought forward based on the principal that defectsdetecting and classification carried out in stages.Image complexity is introduced to quicklydetect defects on steel strip surfaces.Proceeding from reliability and time saving, four imagecomplexity describling parameters are compared to each other in detecting results, finallyRPVC is selected to detect defects on strip surfaces. Simulation shows that RPVC can detectdefects correctly using shorter time and realize detecting in time.
Defects images preprocessing is also researched in this article, in view of the influenceon defect segmentation by textures on images’ background, combination of local complexityand local variance is applied to weaken background textures and Gaussian high frequencyfilter is used to homomorphicly filter defects’ images to wipe of bright spot and enhancecontrast. Three parameters are selected to evaluate the quality of filtered images andcompared to the results of histogram enhancing, all shows better effects.
Visual features selection method is put forward to segment defect images by visualattention mechanism. After analysis of defect images, brightness, rareness and localcomplexity are selected to be features to generate salient images, expressions of them areprovided. Gaussian filter is used to get global salient images.
Improved salient images fused method is brought forward. We modified the weightcoefficients of feature salient images fusion computering method, Normalized complexity andentropy values of salient images are used as weight to generate comprehensive salient image,this can reflect the differences of different salient images’ contribution to comprehensivesalient image. Maximum entropy is used to segment comprehensive salient images,compare with results of K-means method and region-growing method, the improvedsegmentation method based on visual attention model has better effect.
For the purpose of defects classification, defect images’ features selecting method isprovided after analyzing the adaptability of different characters of them. In view of differentinformations included in unsegmented and segmented images, texture features, invariant moment features and dispersion are selected to be classification features.
Extenics theory is introduced into images classification.Feasibility of extenics theory inimages classification is discussed. Weight coefficients of defects images unspecifided topre-selected types of defects images in computering relevancy values are improved and theexpression is provided, the effectiveness of the improved computering method is alsodemonstrated. The quotients of distance between feature values and classical domain andsum of these distances are used as weight coffecients in computering comprehensiverelevancy values.This computering method enhances the influences of defects’ self featurevalues on comprehensive relevancy..
Classical domain and joint domain are key parameters in application of extenics theory,they are gotten by statistics analysis of a number of defects images.Seven defects types areselected to simulate the method, maximum relevancy value is used to group the unspecifieddefect image in one of preselected defect types, classification accuracy is close to90%,comparing to primary weight coefficient computering method, the improved theory is moreeffective in defects images classification.
引文
[1] S. W. Lee, W. J. Park, J. I. Joo, J. Y. Jung, J. H. Lee,and C. H. Park..Development of SurfaceInspection System for Steel Plate [C], The4th Rolling Symposium,Pohang, Korea,2001.
[2] Mohammad Reza Yazdchi, Arash Golibagh Mahyari, Ali Nazeri.Detection and Classificationof Surface Defects of Cold Rolling Mill Steel Using Morphology and NeuralNetwork[C].CIMCA2008, IAWTIC2008, and ISE2008.
[3] Keesug Choi,Kyungmo Koo, Jin S. Lee.Development of Defect Classification Algorithm forPOSCO Rolling Strip Surface Inspection System[C].SICE-ICASE International JointConference2006,2006：18-21.
[4] Ge-Wen Kang, Hong-Bing Liu.Surface defects inspection of cold rolled strips based on neuralnetwork[C].Machine Learning and Cybernetics.2005.2005International Conference onProceedings of.18-21Aug.2005(8)：5034-5037.
[5]胡亮，段发阶，丁克勤等.带钢表面缺陷计算机视觉在线检测系统的设计[J].无损检测，2003，25(6)：287-290.
[6]李炜，黄心汉，王敏等.基于机器视觉的带钢表面缺陷检测系统[J].华中科技大学学报(自然科学版)，2003，31(2)：72-74.
[7]王成明，颜云辉，韩英莉等.一种新的冷轧带钢表面缺陷图像模式识别方法[J].计算机工程与应用，2007，43(13)：207-209.
[8]韩英莉，颜云辉，韩英慧.基于Matlab的RBF网络的带钢表面缺陷的识别与分类研究[J].机械制造，2007(45)：24-25.
[9] Sugimoto, T., Kawaguchi, T.Development of a surface defect inspection system using radiantlight from steel products in a hot rolling line [J].Instrumentation and Measurement,1998(47)：409-416.
[10] Wu Xiu-yong, Xu Ke, Xu Jin-wu.Application of Undecimated Wavelet Transform to SurfaceDefect Detection of Hot Rolled Steel Plates [C].2008Congress on Image and SignalProcessing,2008(4)：528-532.
[11]Caleb, P.,Steuer, M. Classification of surface defects on hot rolled steel using adaptivelearning methods[C].Fourth International Conference on Knowledge-Based IntelligentEngineering Systems and Allied Technologies,2000(1)：103-108.
[12]汤勃，孔建益.带钢表面缺陷图像的小波阈值降噪研究[J].武汉科技大学学报：自然科学版.2010，33(1)：38-42.
[13]徐科，杨朝霖.热轧带钢表面缺陷在线检测的方法与工业应用[J].机械工程学报.2009，45(4)：111-115.
[14]王宏，朱德生.一种基于灰度投影的带钢表面缺陷检测算法[J].东北大学学报：自然科学版.2008，29(3)：375-377.
[15]王成明，颜云辉.基于改进支持向量机的冷轧带钢表面缺陷分类识别[J].东北大学学报：自然科学版.2007，28(3)：410-413.
[16]Zhao Jiuliang,Liu Weiwei,Yan Feng,Li Jun,Zhang Yao,Yan Yunhui.Research on SurfaceQuality Evaluation System of Steel Strip Based on Computer Vision [C]. Third InternationalSymposium on Intelligent Information Technology Application.2009(1)：32-35.
[17]Shui-Shan Yang,Yong-Hui He,Zhen-Long Wang,Wan-Sheng Zhao.A method of steel stripimage segmentation based on local gray information [C]. IEEE International Conference onIndustrial Technology.2008：1-4.
[18]赵向阳.基于神经网络的钢板表面缺陷识别若干问题的研究[D].大连：大连理工大学.2006.
[19]M. Sharifzadeh,S. Alirezaee,R. Amirfattahi,S. Sadri.Detection of Steel Defect Using theImage Processing Algorithms[C].Proceedings of the12th IEEE International MultitopicConference.2008：125-127.
[20]Kazuhito Kenmochi,Ikuo Yarita,Hideo Abe.Effect of micro-defects on the surface brightnessof cold-rolled stainless-steel strip[J].Journal of Materials Processing Technology.1997(69)：106-111.
[21] R. Ahmed, M.P.F. Sutcliffe. Identification of surface features on cold-rolled stainless steelstrip[J].Wear.2000(244)：60–70.
[22]Mohammadreza Yazdchi,Mehran Yazdi,Arash Golibagh Mahyari.Steel Surface DefectDetection Using Texture Segmentation Based on Multifractal Dimension[C].IEEEInternational Conference on Digital Image Processing.2009：346-350.
[23]Hu Qinghe,Xu Jiazhuo,Chen Weidong,Yang Dalei.Application of Artificial Neural Networksto Strip Steel Surface Defect Diagnosis[C].Chinese Control and Decision Conference.2009：2476-2479.
[24]Fred Treiber.带钢表面缺陷和光洁度在线自动检测[J].国外钢铁.1990(6)：43-50.
[25]TANG Bo,KONG Jian-yi,WANG Xing-dong,Chen Li.Surface Inspection System of Stee lStrip Based on Machine Vision[C].First International Workshop on Database Technology andApplications.2009：359-362.
[26]PENG Kai-xiang,ZHANG Xu-li.Classification Technology for Automatic Surface DefectsDetection of Steel Strip Based on Improved BP Algorithm[C].2009Fifth InternationalConference on Natural Computation.2009：110-114.
[27] Guifang Wu,Ke Xu,Jinwu Xu.Application of a new feature extraction and optimizationmethod to surface defect recognition of cold rolled strips[J].Journal of University of Scienceand Technology Beijing.2007，14(5)：437-442.
[28]Pai-Hui Hsu.Feature extraction of hyperspectral images using wavelet and matchingpursuit[J].ISPRS Journal of Photogrammetry&Remote Sensing.2007(62)：78-92.
[29]Stephen Moir,John Preston.Surface Defects-evolution and behaviour form cast slab to coatedstrip[J].Journal of Materials Processing Technology.2002：720-724.
[30]韩英莉，颜云辉.一种带钢表面缺陷识别与分类的研究-基于混合加权特征和RBF网络的方法[J].计算机工程与应用.2007，43(14)：207-209.
[31]Maurizio Cardaci,VitoDiGesù,MariaPetrou.A fuzzy approach to the evaluation of imagecomplexity[J].Fuzzy Sets and Systems,2009(160)：1474-1484.
[32]乔立永，徐立新，高敏.红外目标识别图像复杂度度量方法综述[J].红外技术，2013，35(2)：88-95.
[33]高振宇，杨晓梅，龚剑明.图像复杂度描述方法研究[J].中国图像图形学报，2010，15(1)：129-135.
[34]钟桦，杨晓鸣，焦李成.基于多分辨共生矩阵的纹理图像分类[J].计算机研究与发展.2011，48(11)：1991-1999.
[35]丁绪星，朱日宏，李建欣.一种静止图像质量评价指标[J].南京理工大学学报.2004，28(5)：507-509.
[36]Delon J., Desolneux A.,Lisani, J. L. etc. A Nonparametric Approach for HistogramSegmentation[J].Image Processing.2007，16(1)：253-261.
[37]Cheuk Yiu Ip,Varshney,A.,JaJa, J.Hierarchical Exploration of Volumes Using MultilevelSegmentation of the Intensity-Gradient Histograms[J].Visualization and Computer Graphics.2012，18(12)：2355-2363.
[38]Jehan-Besson, S.,Barlaud, M.,Aubert,G.Shape gradients for histogram segmentation usingactive contours[C].Ninth IEEE International Conference on Computer Vision.2003(1)：408-415.
[39]Huini Du,Burr, K.An algorithm for automatic flood histogram segmentation for a PETdetector[C].Nuclear Science Symposium and Medical Imaging Conference.2012：3488-3492.
[40]Jianping Jia,Hongli Li,Zhujun Jia.Image Segmentation of the Underwater WeldingV-seam Image Based on Improved Two-dimensionalOstu Algorithm[C].Sixth InternationalConference on Fuzzy Systems and Knowledge Discovery.2009(5)：397-400.
[41]Shuhong Jiao,Xueguang Li,Xin Lu.An Improved Ostu Methodfor Image Segmentation[C].8th International Conference on Signal Processing.2006(2)：1250-1256.
[42]Su Heng qiang,Wen Changji.A new algorithm based on super-green features forostu's methodusing image segmentation[C].World Automation Congress.2012：1-4.
[43]Liping Zheng,Guangyao Li,Yun Bao.Improvement of grayscale image2D maximumentropy threshold segmentation method[C].International Conference on Logistics Systemsand Intelligent Management.2010(1)：324-328.
[44]Wang Feng-chao.An Improved2-D Maximum Entropy ThresholdSegmentation Method Based on PSO[C].2nd International Congress on Image and SignalProcessing.2009：1-5.
[45]Wong, Andrew K.C.,Sahoo, P.K. A gray-level threshold selection method based onmaximum entropy principle[J].Systems, Man and Cybernetics.1989，19(4)：866-871.
[46]Ghosal, S.,Mehrotra,R.Detection of composite edges[J].Image Processing.1994，3(1)：14-25.
[47]Canny, John. A Computational Approach to Edge Detection[J].Pattern Analysis and MachineIntelligence.1986，8(6)：679-698.
[48]Perona, P.,Malik, J.Scale-space and edge detection using anisotropic diffusion[J].PatternAnalysis and Machine Intelligence.1990，12(7)：629-639.
[49] Meer,P.,Georgescu,B.Edge detection with embedded confidence[J].Pattern Analysis andMachine Intelligence.2001，23(12)：1351-1365.
[50]Torre, V.,Poggio,Tomaso A.On Edge Detection[J].Pattern Analysis and MachineIntelligence.1986，8(2)：147-163.
[51]Siddique, J.I.,Barner, K.E.Wavelet-based multi resolution edge detection utilizing graylevel edge maps[C].International Conference on Image Processing.1998(2)：550-554.
[52] Cheolha Pedro Lee.Robust Image Segmentation using Active Contours: Level SetApproaches [D]. North Carolina State University.2005.
[53]David Hoy Nabors.A boundary Based Image Segmentation and Representation Method forBinary Images[D].the University of Alabama in Huntsville.2000.
[54]JingRan Sun.Edge Detection, Image Segmentation and Their Applications in MicroarrayImage Analysis[D].University of Minnesota.2005.
[55]Derek C.Stanford.Fast Automatic Unsupervised Image Segmentation and Curve Detection inSpatial Point Pattern[D].University of Washington.1999.
[56]Dongxiang Xu.Image Segmentation and Its Application on MR Image Analysis[D].Universityof Washington.2001.
[57]Joseph H.Bosworth.Morphological Local Monotonicity for Multiscale ImageSegmentation[D].University of Virginia.2002.
[58]Chunghui Kuo.Image Segmentation and Classification[D].University of Minnesota.2001.
[59]Song Gao.A New Image Segmentation and Smoothing Method Based on the Mumford-ShahVariational Model[D].Concordia University.2003.
[60]Yu, P.,Qin,A.K.,Clausi,D.A.Unsupervised Polarimetric SAR Image Segmentation andClassification Using Region Growing With Edge Penalty[J].Geoscience and RemoteSensing.2012，50(4)：1302-1317.
[61]Preetha,M.M.S.J.,Suresh,L.P.,Bosco,M.J.Image segmentation usingseeded region growing[C].International Conference on Computing, Electronics and ElectricalTechnologies.2012：576-583.
[62]Tilton, J.C.,Tarabalka,Y.,Montesano,P.M.etc. Best Merge Region-Growing Segmentation WithIntegrated Nonadjacent Region Object Aggregation[J].Geoscience and RemoteSensing.2012，50(11)：4454-4467.
[63]Rodriguez-Cuenca, B.,Malpica, J.A.,Alonso,M.C. Region-growing segmentation ofmultispectral high-resolution space images with open software[C].Geoscience and RemoteSensing Symposium.2012：4311-4314.
[64]Jun Pang,Zhong-ying Bai,Jun-chen Lai.Automatic segmentation of crop leaf spot diseaseimages by integrating local threshold and seededregion growing[C].International Conferenceon Image Analysis and Signal Processing.2011：590-594.
[65]Song Lixin, Lv Yanan,Yang Bin.Segmentation of breast masses usingadaptiveregion growing[C].8th International Forum on Strategic Technology.2013(2)：77-81.
[66] Hong Yao, Qingling Duan, Daoliang Li,etc.An improved-means clustering algorithm forfish image segmentation [J].Mathematical and Computer Modelling.2013，58(34).790-798.
[67]Pei Rui Bai, Qing Yi Liu, Lei Li,etc.A novel region-based level set method initialized withmean shift clustering for automated medical image segmentation[J].Computers in Biology andMedicine.2013，43(11)：1827-1832.
[68]Zhimin Wang, Qing Song, Yeng Chai Soh,etc.An adaptive spatial information-theoreticfuzzy clustering algorithm for image segmentation[J].Computer Visionand Image Understanding.2013，117(10)：1412-1420.
[69]Girolamo Fornarelli, Antonio Giaquinto.An unsupervised multi-swarm clustering techniquefor image segmentation[J].Swarm and Evolutionary Computation.2013(11)：31-45.
[70] Hanqiang Liu, Feng Zhao, Licheng Jiao. Fuzzy spectral clustering with robust spatialinformation for image segmentation[J].Applied Soft Computing.2012，12(11)：3636-3647.
[71]Feng Zhao.Fuzzy clustering algorithms with self-tuning non-local spatial informationfor image segmentation [J].Neurocomputing.2013，106(15)：115-125.
[72]A.N. Benaichouche, H. Oulhadj, P. Siarry.Improved spatial fuzzyc-means clustering for image segmentation using PSO initialization, Mahalanobis distanceand post-segmentation correction[J]. Digital Signal Processing.2013，23(5)：1390-1400.
[73]Lijun Wang, Ming Dong.Multi-level Low-rank Approximation-basedSpectral Clustering for image segmentation[J].Pattern Recognition Letters.2012，33(16)：2206-2215.
[74]Feng Zhao,Licheng Jiao,Hanqiang Liu.Kernel generalized fuzzy c-means clustering withspatial information for image segmentation[J].Digital Signal Processing.2013，23(1)：184-199.
[75] Zexuan Ji, Yong Xia, Qiang Chen,etc.Fuzzy c-means clustering with weighted image patchfor image segmentation[J].Applied Soft Computing.2012，12(6)：1659-1667.
[76]Dante Mújica-Vargas, Francisco J. Gallegos-Funes, Alberto J. Rosales-Silva. Afuzzy clustering algorithm with spatial robust estimation constraint for noisy color imagesegmentation [J].Pattern Recognition Letters.2013，34(4)：400-413.
[77]Ping Sun, Lei Deng.An image fusion method based on regionsegmentation and wavelet transform[C].20th International Conference onGeoinformatics.2012：1-5.
[78]Xiaorong Xue,Hongfu Wang,Fang Xiang.A new method of SAR Image Segmentation Basedon FCM and wavelet transform[C].5th International Congress on Image and SignalProcessing.2012：621-624.
[79]Hyeokho Choi; Baraniuk, R.G. Multiscale image segmentation using wavelet-domain hiddenMarkov models[J].Image Processing.2001，10(9):13：09-1321.
[80]Dima, A.,Scholz, M.,Obermayer, K.Automatic segmentation and skeletonization of neuronsfrom confocal microscopy images based on the3-D wavelet transform[J].ImageProcessing.2002，11(7)：790-801.
[81]Acharyya, M., Kundu, M.K. Document image segmentation using wavelet scale-spacefeatures[J].Circuits and Systems for Video Technology.2002，12(12)：1117-1127.
[82]Bianchi, T.,Argenti, F.,Alparone, L.Segmentation-Based MAP Despeckling of SAR Images inthe Undecimated Wavelet Domain[J].Geoscience and Remote Sensing.2008，46(9)：2728-2742.
[83]Kumar, S.,Gupta, R.,Khanna, N.,etc.Text Extraction and Document Image SegmentationUsingMatched Wavelets and MRF Model[J].Image Processing.2007，16(8)：2117-2128.
[84]Liew, A.W.C.,Hong Yan.An adaptive spatial fuzzy clustering algorithm for3-DMR image segmentation[J].Medical Imaging.2003，22(9)：1063-1075.
[85]Tobias, Orlando J.,Seara, R.Image segmentation by histogram thresholdingusing fuzzy sets[J].Image Processing.2002，11(12)：1457-1465.
[86]Udupa, J.K.,Saha, P.K.,Lotufo, R.A.Disclaimer: Relative fuzzy connectedness and objectdefinition: theory, algorithms, and applications in image segmentation[J].Pattern Analysis andMachine Intelligence.2002，24(11)：1494-1500.
[87]Boskovitz, V.,Guterman, H.An adaptive neuro-fuzzy system forautomaticimage segmentation and edge detection[J].Fuzzy Systems.2002，10(2)：247-262.
[88]Liew, A.W.-C.,Shu Hung Leung,Wing Hong Lau.Segmentation of color lip images byspatial fuzzyclustering[J].Fuzzy Systems.2003，11(4)：542-549.
[89]Chatzis, S.P.,Varvarigou,T.A. A Fuzzy Clustering Approach Toward Hidden Markov RandomField Models for Enhanced Spatially Constrained Image Segmentation[J].FuzzySystems.2008，16(5)：1351-1361.
[90]Huiyu Zhou,Schaefer,G.,Sadka,A.H.etc.Anisotropic Mean Shift Based Fuzzy C-MeansSegmentation of Dermoscopy Images[J].Selected Topics in Signal Processing.2009，3(1)：26-34.
[91] Mouelhi, A., Sayadi, M.,Fnaiech, F. A supervised segmentation scheme based on multilayerneural network and color active contour model for breast cancer nuclei detection
[C].International Conference on Electrical Engineering and Software Applications.2013：1-6.
[92] Chuan-Yu Chang,Pau-Choo Chung,Yong-Cheng Hong. A Neural Network for ThyroidSegmentation and Volume Estimation in CT Images[J].Computational IntelligenceMagazine.2011，6(4)：43-55.
[93] Qing-sheng Wang,Yue-qin Zhang,Bin Hu. Improved genetic neural network for imagesegmentation [C].IEEE18Th International Conference on Industrial Engineering andEngineering Management.2011(3)：1694-1698.
[94]Tao Song,Jamshidi, M.M.,Lee, R.R.A Modified Probabilistic Neural Network for PartialVolume Segmentation in Brain MR Image[J].Neural Networks.2007，18(5)：1424-1432.
[95]Awad, M.,Chehdi, K.,Nasri, A.Multicomponent Image Segmentation Using a GeneticAlgorithm and Artificial Neural Network[J].Geoscience and Remote Sensing Letters.2007，4(4)：571-575.
[96]Hualiang Zhuang,Kay-Soon Low,Wei-Yun Yau.Multichannel Pulse Coupled Neural NetworkBased Color Image Segmentation for Object Detection [J].Industrial Electronics.2012，59(8)：3299-3308.
[97]Wen Guo,Changshen Xu,Songde Ma.Visual attention based small object segmentation innatual images[C].17th IEEE International Conference on Image Processing.2010：1565-1568.
[98]Gao Lining,Bi Fukun,Yang Jian.Visual attention based model for target detection in large-fieldimages[J].Systems Engineering and Electronics.2011，22(1)：150-156.
[99]Farias, M.C.Q.,Akamine,W.Y.L.On performance of image quality metrics enhancedwith visual attention computational models[J].Electronics Letters.2012，48(11)：631-633.
[100]Hou Biao,Yang Wei,Wang Shuang.A new visual attention-based method for water detectionin SAR images[C].3rd International Asia-Pacific Conference on Synthetic ApertureRadar.2011：1-2.
[101]Tao Gao,Ping Wang,Chengshan Wang.Visual attention mechanism based image shadowdefect detection[C].International Conference on Electrical and Control Engineering.2011：2808-2811.
[102]Liu, H.,Heynderickx, I.Visual Attention in Objective Image Quality Assessment: Based onEye-Tracking Data[J].Circuits and Systems for Video Technology.2011，21(7)：971-982.
[103]ChuanLong Li,Ying Li,XueRui Wu.Novel Fuzzy C-means Segmentation Algorithm forImage with the Spatial Neighborhoods[C].2nd International Conference on RemoteSensing.2012：1-4.
[104]Muqing Lin.Development of Segmentation and Registration Methods for Analysis ofMagnetic Resonance Images in Clinical Applications[D].University of California.2012.
[105]Unoma Ndili.A Coding Theoretic Approach to Image Segmentation[D].RiceUniversity.2001.
[106]Romeil S. Sandhu.Statistical Methods for2D Image Segmentation and3D PoseEstimation[D].Georgia Institute of Technology.2010.
[107]LeenKiat Soh.A Data Investigation Model and SAR Sea Ice Application[D].University ofKansas.1998.
[108]Eun Sang Bak.Statistical Analysis for Image Segmentation,Feature Classfication and ItsApplication in Medical Imaging and Gene Analysis[D].The University of NorthCarolina.2004.
[109]Tarundeep Singh Dhot.GPIS: Genetic Programming based Image Segmentation withApplications to Biomedical Object Detection[D].Concordia University.2009.
[110]Ming Zhang.Novel Approaches to Image Segmentation Based on NeutrosophicLogic[D].Utah State University.2010.
[111]Maryam Hasanzadeh,Shoreh Kasaei, Mohseni, Hadis.A New Fuzzy Connectedness Relationfor Image Segmentation[C].3rd International Conference on Information and CommunicationTechnologies.2008：1-6.
[112]张巧荣，景丽，肖会敏等.利用视觉显著性的图像分割方法[J].中国图象图形学报.2011，16(5)：767-772.
[113]程聪，戴朝辉.基于视觉注意的图像感兴趣区域分割算法[J].郑州轻工业学院学报(自然科学版).2011，26(2)：111-115.
[114]Cong Jiahui, Yan Yunhui. Application of Human Visual Attention Mechanism in Surface Defect Inspection of Steel Strip[J].中国机械工程.2011，22(10)：1189-1192.
[115]Braun, F.N.; Yokoyama, H. Fluctuations at the domain edges of nematic liquid crystals intwo dimensions[J].European Physical Journal B.1999，9(3)：377-379.
[116]Treisman, Anne. Pre-attentive processing in vision [J].Computer Vision, Graphics, andImage Processing.1985，31(2)：156-177.
[117]Posner M,l,CohenY,RafalRD.Neural systems control of spatial orienting[J].Philos Trans RSoc Lond BiolSci.1982，298(1089)：187-198.
[118]Koch C,Ullman S. Shifts in SelectiveVisual Attention:towards the Underlying NeuralCircuitry[J].Human Neurobiology.1985，4(4)：219-227.
[119]Laurent Itti. Automatic Foveation for Video Compression Usinga Neurobiological Model of Visual Attention[J].Image processing.2004，13(10)：1304-1318.
[120]Itti L.Models of Bottom-up and Top-down visual Attention [D].USA,California Institute ofTechnology.2000.
[121]田明辉.视觉注意机制建模及其应用研究[D].中国科学技术大学.2010.
[122]Yasnoff, William A., Mui, Jack K., Bacus, James W. Error Measures for Scene Segmentation[J].Pattern Recognition.1977，9(4)：217-231.
[123]Canny, John.Computational Approach to Edge Detection [J].Pattern Analysis and MachineIntelligence.1986，8(6)：679-698.
[124]Chalana, Vikram. Methodology for evaluation of boundary detection algorithms on medicalimages[J].IEEE Transactions on Medical Imaging.1997，16(5)：642-652.
[125]Ortiz de Solorzano, C., Chin, K., Chou, W.S.,etc. Measurement of genetic instability inbreast cancer by confocal microscopy and3D image analysis[C].Annual InternationalConference of the IEEE Engineering in Medicine and Biology.1999(2)：822-826.
[126]Zhixin Shi,Venu Govindaraju.A chaincode based scheme for fingerprint featureextraction[J].Pattern Recognition Letters.2006(27)：462-468.
[127]刘丽，匡纲要.图像纹理特征提取方法综述[J].中国图象图形学报.2009，14(4)：622-627.
[128]Yu Tao,Ernest C.M.Lam,Yuan Y.Tang.Feature Extraction Using Wavelet and Fractal[J].Pattern Recognition Letters.2001(22)：271-287.
[129]Frank Y.Shih,Chao-Fa Chuang.Automatic extraction of head and face boundaries and facialfeatures[J].Information Sciences.2004(158)：117-130.
[130]Nojun Kwak.Feature extraction for classification problems and its application to facerecognition [J]. Pattern Recognition.2008(41)：1701-1717.
[131]Pai-Hui Hsu Feature extraction of hyperspectral images using wavelet and matchingpursuit[J].ISPRS Journal of Photogrammetry&Remote Sensing.2007(62)：78-92.
[132]王成明，颜云辉，李骏，焦志刚.一种新的冷轧带钢典型表面缺陷特征提取方法[J].计算机工程与应用.2006(27)：184-186.
[133]Abdullah Bal.Image feature extraction by dynamic neural filtering and phase-only jointtransform correlation[J].Optics&Laser Technology.2007(39)：2-7.
[134]H. Zhang,C.M. Cartwright, M.S. Ding,W.A.Gillespie.Image feature extraction with variouswavelet functions in a photorefractive joint transform correlator[J].OpticsCommunications.2000(185)：277-284.
[135]Engin Avci,Abdulkadir Sengur,Davut Hanbay.An optimum feature extraction method fortexture classification[J].Expert Systems with Applications.2009(36)：6036-6043.
[136]Gang Yu,SagarV.Kamarthi.A cluster-based wavelet feature extraction method and itsapplication[J].Engineering Applications of Artificial Intelligence.2010(23)：196-202.
[137]Yannick Maret,Fre′de′ric Dufaux,Touradj Ebrahimi.Adaptive image replica detection basedon support vector classifiers[J].Signal Processing: Image Communication.2006(21)：688-703.
[138]M.Mirmehdi,P.L.Palmer, J.Kittler.Genetic optimisation of the image feature extractionprocess[J].Pattern Recognition Letters.1997(18)：355-365.
[139]Oivind Due Trier,Anil K.Jain,Torfinn Taxt.Feature Extraction Methods for CharacterRecognition-A Survey[J].Pattern Recognition.1996，29(4)：641-662.
[140]Vapnik V.The nature of statistical learning theory[M].New York：Springer Verlag.2000.
[141]Cristianini N.,Shawe T J.An introduction to support vector machine[M].New York：Cambridge University Press.2000.
[142]Zhao Hui.Study on Support Vector Machines Classification methods and their Application inText Categorization[D].Dalian University of Technology.2005.
[143]Doumpos M,Zopounidis C.Additive support vector machines for patternclassification[J].Systerms,Man,and Cybernetics：Part B.2007，37(3)：540-550.
[144]Jayadeva,Khemchandani R,Chandra S.Twin support vector machines for patternclassification[J].Pattern Analysis and Machine Intelligence.2007，29(5)：905-910.
[145]黄勇，郑春颖.多类支持向量机算法综述[J].计算技术与自动化.2005，24(4)：61-63.
[146]胡学坤，李金霞.基于粗糙集与模糊支持向量机的模式分类方法研究[R].科技通报.2010，26(2)：250-252.
[147]Lin Chun-Fu,Wang Sheng De.Fuzzy Support Vector Machines[J].Networks.2002，13(2)：464-471.
[148]陈方林，刘彦.基于支持向量机的X射线焊缝缺陷检测[J].机械工程与自动化.2010(2)：122-124.
[149]张晓光，肖兴明.基于广义加权支持向量机的焊接缺陷分类方法[J].华东理工大学学报：自然科学版.2005，31(5)：645-648.
[150]黎维娟，卢振泰.基于支持向量机的脑部MR图像细分类[J].电路与系统学报.2010，15(1)：5-9.
[151]Jordi Inglada.Automatic recognition of man-made objects in high resolution optical remotesensing images by SVM classification of geometric image features[J].ISPRS Journal ofPhotogrammetry and Remote Sensing.2007，62(3)：236-248.
[152]Georgios C.Anagnostopoulos. SVM-based target recognition from synthetic aperture radarimages using target region outline descriptors[J].Nonlinear Analysis:Theory,Methods&Applications.2009，71(12)：e2934-e2939.
[153]J. Mitéran,S.Bouillant,E.Bourennane.SVM approximation for real-time image segmentationby using an improved hyperrectangles-based method[J].Real-Time Imaging.2003，9(3)：179-188.
[154]蔡文.可拓集合和不相容问题[J].科学探索学报.1983(1)：83-97.
[155]Cai Wen.Extension theory and its applications[R].Chinese Science Bulletin.1999，44(17)：153-154.
[156]杨春燕，蔡文.可拓工程[M].北京：科学出版社.2007.
[157]陈文伟.挖掘变化知识的可拓数据挖掘研究[J].中国工程科学.2006，8(11)：70-73.
[158]Yu Yong-quan,PENG Hal-xia.The principle of extension detecting with extensionsets[C].Proc of International Conference on Computer:Communication and ControlTechnologies,Informatics＆Systemics.2003：113-118.
[159]Wang M H,Tseng Y F.A novel clustering algorithm based on the extension theory and geneticalgorithm[J].Expert Systems with Applications.2009，36(4)：8269-8276.
[160]Wang M H.Application of extension theory to PD pattern recognition in high-voltage currenttransformers[J].Power Delivery.2005，20(3)：1939-1946.
[161]Ye Jun.Application of extension theory in misfire fault diagnosis of gasolineengines[J].Expert Systems with Applications.2009，36(2)：1217-1221.
[162]刘海，朱小平.一种基于可拓理论的图像检索方法[J].计算机系统应用.2009(3)：54-56.
[163]Ye Dan,Yu Yong-quan,Zeng Bi.Research of Classification Based on Extenics[C].Conferenceon Computational Intelligence and Multimedia Applications.2007(1)：129-132.
[164]Jung-Chi Su,Chuin-Mu Wang,Sheng-Chih Yang,Gia-Hao Chang.An Extenics Approach toMRI Classification[C].IEEE International Conference on Systems,Man andCybernetics.2006(1)：562-567.
[165]Wang Shiyun,Wang Zhijun,Li Yunjie,etc.Study on the Application of Extenics in DataMining [C].International Forum on Computer Science-Technology andApplications.2009(2)：109-112.
[166]Shu Hong-chun,Hu Ze-jiang,Sun Shi-yun,etc.The fault diagnosis algorithm for transformerbased on Extenics and rough set theory[C].Third International Conference on Electric UtilityDeregulation and Restructuring and Power Technologies.2008：1269-1272.
[2] Mohammad Reza Yazdchi, Arash Golibagh Mahyari, Ali Nazeri.Detection and Classificationof Surface Defects of Cold Rolling Mill Steel Using Morphology and NeuralNetwork[C].CIMCA2008, IAWTIC2008, and ISE2008.
[3] Keesug Choi,Kyungmo Koo, Jin S. Lee.Development of Defect Classification Algorithm forPOSCO Rolling Strip Surface Inspection System[C].SICE-ICASE International JointConference2006,2006：18-21.
[4] Ge-Wen Kang, Hong-Bing Liu.Surface defects inspection of cold rolled strips based on neuralnetwork[C].Machine Learning and Cybernetics.2005.2005International Conference onProceedings of.18-21Aug.2005(8)：5034-5037.
[5]胡亮，段发阶，丁克勤等.带钢表面缺陷计算机视觉在线检测系统的设计[J].无损检测，2003，25(6)：287-290.
[6]李炜，黄心汉，王敏等.基于机器视觉的带钢表面缺陷检测系统[J].华中科技大学学报(自然科学版)，2003，31(2)：72-74.
[7]王成明，颜云辉，韩英莉等.一种新的冷轧带钢表面缺陷图像模式识别方法[J].计算机工程与应用，2007，43(13)：207-209.
[8]韩英莉，颜云辉，韩英慧.基于Matlab的RBF网络的带钢表面缺陷的识别与分类研究[J].机械制造，2007(45)：24-25.
[9] Sugimoto, T., Kawaguchi, T.Development of a surface defect inspection system using radiantlight from steel products in a hot rolling line [J].Instrumentation and Measurement,1998(47)：409-416.
[10] Wu Xiu-yong, Xu Ke, Xu Jin-wu.Application of Undecimated Wavelet Transform to SurfaceDefect Detection of Hot Rolled Steel Plates [C].2008Congress on Image and SignalProcessing,2008(4)：528-532.
[11]Caleb, P.,Steuer, M. Classification of surface defects on hot rolled steel using adaptivelearning methods[C].Fourth International Conference on Knowledge-Based IntelligentEngineering Systems and Allied Technologies,2000(1)：103-108.
[12]汤勃，孔建益.带钢表面缺陷图像的小波阈值降噪研究[J].武汉科技大学学报：自然科学版.2010，33(1)：38-42.
[13]徐科，杨朝霖.热轧带钢表面缺陷在线检测的方法与工业应用[J].机械工程学报.2009，45(4)：111-115.
[14]王宏，朱德生.一种基于灰度投影的带钢表面缺陷检测算法[J].东北大学学报：自然科学版.2008，29(3)：375-377.
[15]王成明，颜云辉.基于改进支持向量机的冷轧带钢表面缺陷分类识别[J].东北大学学报：自然科学版.2007，28(3)：410-413.
[16]Zhao Jiuliang,Liu Weiwei,Yan Feng,Li Jun,Zhang Yao,Yan Yunhui.Research on SurfaceQuality Evaluation System of Steel Strip Based on Computer Vision [C]. Third InternationalSymposium on Intelligent Information Technology Application.2009(1)：32-35.
[17]Shui-Shan Yang,Yong-Hui He,Zhen-Long Wang,Wan-Sheng Zhao.A method of steel stripimage segmentation based on local gray information [C]. IEEE International Conference onIndustrial Technology.2008：1-4.
[18]赵向阳.基于神经网络的钢板表面缺陷识别若干问题的研究[D].大连：大连理工大学.2006.
[19]M. Sharifzadeh,S. Alirezaee,R. Amirfattahi,S. Sadri.Detection of Steel Defect Using theImage Processing Algorithms[C].Proceedings of the12th IEEE International MultitopicConference.2008：125-127.
[20]Kazuhito Kenmochi,Ikuo Yarita,Hideo Abe.Effect of micro-defects on the surface brightnessof cold-rolled stainless-steel strip[J].Journal of Materials Processing Technology.1997(69)：106-111.
[21] R. Ahmed, M.P.F. Sutcliffe. Identification of surface features on cold-rolled stainless steelstrip[J].Wear.2000(244)：60–70.
[22]Mohammadreza Yazdchi,Mehran Yazdi,Arash Golibagh Mahyari.Steel Surface DefectDetection Using Texture Segmentation Based on Multifractal Dimension[C].IEEEInternational Conference on Digital Image Processing.2009：346-350.
[23]Hu Qinghe,Xu Jiazhuo,Chen Weidong,Yang Dalei.Application of Artificial Neural Networksto Strip Steel Surface Defect Diagnosis[C].Chinese Control and Decision Conference.2009：2476-2479.
[24]Fred Treiber.带钢表面缺陷和光洁度在线自动检测[J].国外钢铁.1990(6)：43-50.
[25]TANG Bo,KONG Jian-yi,WANG Xing-dong,Chen Li.Surface Inspection System of Stee lStrip Based on Machine Vision[C].First International Workshop on Database Technology andApplications.2009：359-362.
[26]PENG Kai-xiang,ZHANG Xu-li.Classification Technology for Automatic Surface DefectsDetection of Steel Strip Based on Improved BP Algorithm[C].2009Fifth InternationalConference on Natural Computation.2009：110-114.
[27] Guifang Wu,Ke Xu,Jinwu Xu.Application of a new feature extraction and optimizationmethod to surface defect recognition of cold rolled strips[J].Journal of University of Scienceand Technology Beijing.2007，14(5)：437-442.
[28]Pai-Hui Hsu.Feature extraction of hyperspectral images using wavelet and matchingpursuit[J].ISPRS Journal of Photogrammetry&Remote Sensing.2007(62)：78-92.
[29]Stephen Moir,John Preston.Surface Defects-evolution and behaviour form cast slab to coatedstrip[J].Journal of Materials Processing Technology.2002：720-724.
[30]韩英莉，颜云辉.一种带钢表面缺陷识别与分类的研究-基于混合加权特征和RBF网络的方法[J].计算机工程与应用.2007，43(14)：207-209.
[31]Maurizio Cardaci,VitoDiGesù,MariaPetrou.A fuzzy approach to the evaluation of imagecomplexity[J].Fuzzy Sets and Systems,2009(160)：1474-1484.
[32]乔立永，徐立新，高敏.红外目标识别图像复杂度度量方法综述[J].红外技术，2013，35(2)：88-95.
[33]高振宇，杨晓梅，龚剑明.图像复杂度描述方法研究[J].中国图像图形学报，2010，15(1)：129-135.
[34]钟桦，杨晓鸣，焦李成.基于多分辨共生矩阵的纹理图像分类[J].计算机研究与发展.2011，48(11)：1991-1999.
[35]丁绪星，朱日宏，李建欣.一种静止图像质量评价指标[J].南京理工大学学报.2004，28(5)：507-509.
[36]Delon J., Desolneux A.,Lisani, J. L. etc. A Nonparametric Approach for HistogramSegmentation[J].Image Processing.2007，16(1)：253-261.
[37]Cheuk Yiu Ip,Varshney,A.,JaJa, J.Hierarchical Exploration of Volumes Using MultilevelSegmentation of the Intensity-Gradient Histograms[J].Visualization and Computer Graphics.2012，18(12)：2355-2363.
[38]Jehan-Besson, S.,Barlaud, M.,Aubert,G.Shape gradients for histogram segmentation usingactive contours[C].Ninth IEEE International Conference on Computer Vision.2003(1)：408-415.
[39]Huini Du,Burr, K.An algorithm for automatic flood histogram segmentation for a PETdetector[C].Nuclear Science Symposium and Medical Imaging Conference.2012：3488-3492.
[40]Jianping Jia,Hongli Li,Zhujun Jia.Image Segmentation of the Underwater WeldingV-seam Image Based on Improved Two-dimensionalOstu Algorithm[C].Sixth InternationalConference on Fuzzy Systems and Knowledge Discovery.2009(5)：397-400.
[41]Shuhong Jiao,Xueguang Li,Xin Lu.An Improved Ostu Methodfor Image Segmentation[C].8th International Conference on Signal Processing.2006(2)：1250-1256.
[42]Su Heng qiang,Wen Changji.A new algorithm based on super-green features forostu's methodusing image segmentation[C].World Automation Congress.2012：1-4.
[43]Liping Zheng,Guangyao Li,Yun Bao.Improvement of grayscale image2D maximumentropy threshold segmentation method[C].International Conference on Logistics Systemsand Intelligent Management.2010(1)：324-328.
[44]Wang Feng-chao.An Improved2-D Maximum Entropy ThresholdSegmentation Method Based on PSO[C].2nd International Congress on Image and SignalProcessing.2009：1-5.
[45]Wong, Andrew K.C.,Sahoo, P.K. A gray-level threshold selection method based onmaximum entropy principle[J].Systems, Man and Cybernetics.1989，19(4)：866-871.
[46]Ghosal, S.,Mehrotra,R.Detection of composite edges[J].Image Processing.1994，3(1)：14-25.
[47]Canny, John. A Computational Approach to Edge Detection[J].Pattern Analysis and MachineIntelligence.1986，8(6)：679-698.
[48]Perona, P.,Malik, J.Scale-space and edge detection using anisotropic diffusion[J].PatternAnalysis and Machine Intelligence.1990，12(7)：629-639.
[49] Meer,P.,Georgescu,B.Edge detection with embedded confidence[J].Pattern Analysis andMachine Intelligence.2001，23(12)：1351-1365.
[50]Torre, V.,Poggio,Tomaso A.On Edge Detection[J].Pattern Analysis and MachineIntelligence.1986，8(2)：147-163.
[51]Siddique, J.I.,Barner, K.E.Wavelet-based multi resolution edge detection utilizing graylevel edge maps[C].International Conference on Image Processing.1998(2)：550-554.
[52] Cheolha Pedro Lee.Robust Image Segmentation using Active Contours: Level SetApproaches [D]. North Carolina State University.2005.
[53]David Hoy Nabors.A boundary Based Image Segmentation and Representation Method forBinary Images[D].the University of Alabama in Huntsville.2000.
[54]JingRan Sun.Edge Detection, Image Segmentation and Their Applications in MicroarrayImage Analysis[D].University of Minnesota.2005.
[55]Derek C.Stanford.Fast Automatic Unsupervised Image Segmentation and Curve Detection inSpatial Point Pattern[D].University of Washington.1999.
[56]Dongxiang Xu.Image Segmentation and Its Application on MR Image Analysis[D].Universityof Washington.2001.
[57]Joseph H.Bosworth.Morphological Local Monotonicity for Multiscale ImageSegmentation[D].University of Virginia.2002.
[58]Chunghui Kuo.Image Segmentation and Classification[D].University of Minnesota.2001.
[59]Song Gao.A New Image Segmentation and Smoothing Method Based on the Mumford-ShahVariational Model[D].Concordia University.2003.
[60]Yu, P.,Qin,A.K.,Clausi,D.A.Unsupervised Polarimetric SAR Image Segmentation andClassification Using Region Growing With Edge Penalty[J].Geoscience and RemoteSensing.2012，50(4)：1302-1317.
[61]Preetha,M.M.S.J.,Suresh,L.P.,Bosco,M.J.Image segmentation usingseeded region growing[C].International Conference on Computing, Electronics and ElectricalTechnologies.2012：576-583.
[62]Tilton, J.C.,Tarabalka,Y.,Montesano,P.M.etc. Best Merge Region-Growing Segmentation WithIntegrated Nonadjacent Region Object Aggregation[J].Geoscience and RemoteSensing.2012，50(11)：4454-4467.
[63]Rodriguez-Cuenca, B.,Malpica, J.A.,Alonso,M.C. Region-growing segmentation ofmultispectral high-resolution space images with open software[C].Geoscience and RemoteSensing Symposium.2012：4311-4314.
[64]Jun Pang,Zhong-ying Bai,Jun-chen Lai.Automatic segmentation of crop leaf spot diseaseimages by integrating local threshold and seededregion growing[C].International Conferenceon Image Analysis and Signal Processing.2011：590-594.
[65]Song Lixin, Lv Yanan,Yang Bin.Segmentation of breast masses usingadaptiveregion growing[C].8th International Forum on Strategic Technology.2013(2)：77-81.
[66] Hong Yao, Qingling Duan, Daoliang Li,etc.An improved-means clustering algorithm forfish image segmentation [J].Mathematical and Computer Modelling.2013，58(34).790-798.
[67]Pei Rui Bai, Qing Yi Liu, Lei Li,etc.A novel region-based level set method initialized withmean shift clustering for automated medical image segmentation[J].Computers in Biology andMedicine.2013，43(11)：1827-1832.
[68]Zhimin Wang, Qing Song, Yeng Chai Soh,etc.An adaptive spatial information-theoreticfuzzy clustering algorithm for image segmentation[J].Computer Visionand Image Understanding.2013，117(10)：1412-1420.
[69]Girolamo Fornarelli, Antonio Giaquinto.An unsupervised multi-swarm clustering techniquefor image segmentation[J].Swarm and Evolutionary Computation.2013(11)：31-45.
[70] Hanqiang Liu, Feng Zhao, Licheng Jiao. Fuzzy spectral clustering with robust spatialinformation for image segmentation[J].Applied Soft Computing.2012，12(11)：3636-3647.
[71]Feng Zhao.Fuzzy clustering algorithms with self-tuning non-local spatial informationfor image segmentation [J].Neurocomputing.2013，106(15)：115-125.
[72]A.N. Benaichouche, H. Oulhadj, P. Siarry.Improved spatial fuzzyc-means clustering for image segmentation using PSO initialization, Mahalanobis distanceand post-segmentation correction[J]. Digital Signal Processing.2013，23(5)：1390-1400.
[73]Lijun Wang, Ming Dong.Multi-level Low-rank Approximation-basedSpectral Clustering for image segmentation[J].Pattern Recognition Letters.2012，33(16)：2206-2215.
[74]Feng Zhao,Licheng Jiao,Hanqiang Liu.Kernel generalized fuzzy c-means clustering withspatial information for image segmentation[J].Digital Signal Processing.2013，23(1)：184-199.
[75] Zexuan Ji, Yong Xia, Qiang Chen,etc.Fuzzy c-means clustering with weighted image patchfor image segmentation[J].Applied Soft Computing.2012，12(6)：1659-1667.
[76]Dante Mújica-Vargas, Francisco J. Gallegos-Funes, Alberto J. Rosales-Silva. Afuzzy clustering algorithm with spatial robust estimation constraint for noisy color imagesegmentation [J].Pattern Recognition Letters.2013，34(4)：400-413.
[77]Ping Sun, Lei Deng.An image fusion method based on regionsegmentation and wavelet transform[C].20th International Conference onGeoinformatics.2012：1-5.
[78]Xiaorong Xue,Hongfu Wang,Fang Xiang.A new method of SAR Image Segmentation Basedon FCM and wavelet transform[C].5th International Congress on Image and SignalProcessing.2012：621-624.
[79]Hyeokho Choi; Baraniuk, R.G. Multiscale image segmentation using wavelet-domain hiddenMarkov models[J].Image Processing.2001，10(9):13：09-1321.
[80]Dima, A.,Scholz, M.,Obermayer, K.Automatic segmentation and skeletonization of neuronsfrom confocal microscopy images based on the3-D wavelet transform[J].ImageProcessing.2002，11(7)：790-801.
[81]Acharyya, M., Kundu, M.K. Document image segmentation using wavelet scale-spacefeatures[J].Circuits and Systems for Video Technology.2002，12(12)：1117-1127.
[82]Bianchi, T.,Argenti, F.,Alparone, L.Segmentation-Based MAP Despeckling of SAR Images inthe Undecimated Wavelet Domain[J].Geoscience and Remote Sensing.2008，46(9)：2728-2742.
[83]Kumar, S.,Gupta, R.,Khanna, N.,etc.Text Extraction and Document Image SegmentationUsingMatched Wavelets and MRF Model[J].Image Processing.2007，16(8)：2117-2128.
[84]Liew, A.W.C.,Hong Yan.An adaptive spatial fuzzy clustering algorithm for3-DMR image segmentation[J].Medical Imaging.2003，22(9)：1063-1075.
[85]Tobias, Orlando J.,Seara, R.Image segmentation by histogram thresholdingusing fuzzy sets[J].Image Processing.2002，11(12)：1457-1465.
[86]Udupa, J.K.,Saha, P.K.,Lotufo, R.A.Disclaimer: Relative fuzzy connectedness and objectdefinition: theory, algorithms, and applications in image segmentation[J].Pattern Analysis andMachine Intelligence.2002，24(11)：1494-1500.
[87]Boskovitz, V.,Guterman, H.An adaptive neuro-fuzzy system forautomaticimage segmentation and edge detection[J].Fuzzy Systems.2002，10(2)：247-262.
[88]Liew, A.W.-C.,Shu Hung Leung,Wing Hong Lau.Segmentation of color lip images byspatial fuzzyclustering[J].Fuzzy Systems.2003，11(4)：542-549.
[89]Chatzis, S.P.,Varvarigou,T.A. A Fuzzy Clustering Approach Toward Hidden Markov RandomField Models for Enhanced Spatially Constrained Image Segmentation[J].FuzzySystems.2008，16(5)：1351-1361.
[90]Huiyu Zhou,Schaefer,G.,Sadka,A.H.etc.Anisotropic Mean Shift Based Fuzzy C-MeansSegmentation of Dermoscopy Images[J].Selected Topics in Signal Processing.2009，3(1)：26-34.
[91] Mouelhi, A., Sayadi, M.,Fnaiech, F. A supervised segmentation scheme based on multilayerneural network and color active contour model for breast cancer nuclei detection
[C].International Conference on Electrical Engineering and Software Applications.2013：1-6.
[92] Chuan-Yu Chang,Pau-Choo Chung,Yong-Cheng Hong. A Neural Network for ThyroidSegmentation and Volume Estimation in CT Images[J].Computational IntelligenceMagazine.2011，6(4)：43-55.
[93] Qing-sheng Wang,Yue-qin Zhang,Bin Hu. Improved genetic neural network for imagesegmentation [C].IEEE18Th International Conference on Industrial Engineering andEngineering Management.2011(3)：1694-1698.
[94]Tao Song,Jamshidi, M.M.,Lee, R.R.A Modified Probabilistic Neural Network for PartialVolume Segmentation in Brain MR Image[J].Neural Networks.2007，18(5)：1424-1432.
[95]Awad, M.,Chehdi, K.,Nasri, A.Multicomponent Image Segmentation Using a GeneticAlgorithm and Artificial Neural Network[J].Geoscience and Remote Sensing Letters.2007，4(4)：571-575.
[96]Hualiang Zhuang,Kay-Soon Low,Wei-Yun Yau.Multichannel Pulse Coupled Neural NetworkBased Color Image Segmentation for Object Detection [J].Industrial Electronics.2012，59(8)：3299-3308.
[97]Wen Guo,Changshen Xu,Songde Ma.Visual attention based small object segmentation innatual images[C].17th IEEE International Conference on Image Processing.2010：1565-1568.
[98]Gao Lining,Bi Fukun,Yang Jian.Visual attention based model for target detection in large-fieldimages[J].Systems Engineering and Electronics.2011，22(1)：150-156.
[99]Farias, M.C.Q.,Akamine,W.Y.L.On performance of image quality metrics enhancedwith visual attention computational models[J].Electronics Letters.2012，48(11)：631-633.
[100]Hou Biao,Yang Wei,Wang Shuang.A new visual attention-based method for water detectionin SAR images[C].3rd International Asia-Pacific Conference on Synthetic ApertureRadar.2011：1-2.
[101]Tao Gao,Ping Wang,Chengshan Wang.Visual attention mechanism based image shadowdefect detection[C].International Conference on Electrical and Control Engineering.2011：2808-2811.
[102]Liu, H.,Heynderickx, I.Visual Attention in Objective Image Quality Assessment: Based onEye-Tracking Data[J].Circuits and Systems for Video Technology.2011，21(7)：971-982.
[103]ChuanLong Li,Ying Li,XueRui Wu.Novel Fuzzy C-means Segmentation Algorithm forImage with the Spatial Neighborhoods[C].2nd International Conference on RemoteSensing.2012：1-4.
[104]Muqing Lin.Development of Segmentation and Registration Methods for Analysis ofMagnetic Resonance Images in Clinical Applications[D].University of California.2012.
[105]Unoma Ndili.A Coding Theoretic Approach to Image Segmentation[D].RiceUniversity.2001.
[106]Romeil S. Sandhu.Statistical Methods for2D Image Segmentation and3D PoseEstimation[D].Georgia Institute of Technology.2010.
[107]LeenKiat Soh.A Data Investigation Model and SAR Sea Ice Application[D].University ofKansas.1998.
[108]Eun Sang Bak.Statistical Analysis for Image Segmentation,Feature Classfication and ItsApplication in Medical Imaging and Gene Analysis[D].The University of NorthCarolina.2004.
[109]Tarundeep Singh Dhot.GPIS: Genetic Programming based Image Segmentation withApplications to Biomedical Object Detection[D].Concordia University.2009.
[110]Ming Zhang.Novel Approaches to Image Segmentation Based on NeutrosophicLogic[D].Utah State University.2010.
[111]Maryam Hasanzadeh,Shoreh Kasaei, Mohseni, Hadis.A New Fuzzy Connectedness Relationfor Image Segmentation[C].3rd International Conference on Information and CommunicationTechnologies.2008：1-6.
[112]张巧荣，景丽，肖会敏等.利用视觉显著性的图像分割方法[J].中国图象图形学报.2011，16(5)：767-772.
[113]程聪，戴朝辉.基于视觉注意的图像感兴趣区域分割算法[J].郑州轻工业学院学报(自然科学版).2011，26(2)：111-115.
[114]Cong Jiahui, Yan Yunhui. Application of Human Visual Attention Mechanism in Surface Defect Inspection of Steel Strip[J].中国机械工程.2011，22(10)：1189-1192.
[115]Braun, F.N.; Yokoyama, H. Fluctuations at the domain edges of nematic liquid crystals intwo dimensions[J].European Physical Journal B.1999，9(3)：377-379.
[116]Treisman, Anne. Pre-attentive processing in vision [J].Computer Vision, Graphics, andImage Processing.1985，31(2)：156-177.
[117]Posner M,l,CohenY,RafalRD.Neural systems control of spatial orienting[J].Philos Trans RSoc Lond BiolSci.1982，298(1089)：187-198.
[118]Koch C,Ullman S. Shifts in SelectiveVisual Attention:towards the Underlying NeuralCircuitry[J].Human Neurobiology.1985，4(4)：219-227.
[119]Laurent Itti. Automatic Foveation for Video Compression Usinga Neurobiological Model of Visual Attention[J].Image processing.2004，13(10)：1304-1318.
[120]Itti L.Models of Bottom-up and Top-down visual Attention [D].USA,California Institute ofTechnology.2000.
[121]田明辉.视觉注意机制建模及其应用研究[D].中国科学技术大学.2010.
[122]Yasnoff, William A., Mui, Jack K., Bacus, James W. Error Measures for Scene Segmentation[J].Pattern Recognition.1977，9(4)：217-231.
[123]Canny, John.Computational Approach to Edge Detection [J].Pattern Analysis and MachineIntelligence.1986，8(6)：679-698.
[124]Chalana, Vikram. Methodology for evaluation of boundary detection algorithms on medicalimages[J].IEEE Transactions on Medical Imaging.1997，16(5)：642-652.
[125]Ortiz de Solorzano, C., Chin, K., Chou, W.S.,etc. Measurement of genetic instability inbreast cancer by confocal microscopy and3D image analysis[C].Annual InternationalConference of the IEEE Engineering in Medicine and Biology.1999(2)：822-826.
[126]Zhixin Shi,Venu Govindaraju.A chaincode based scheme for fingerprint featureextraction[J].Pattern Recognition Letters.2006(27)：462-468.
[127]刘丽，匡纲要.图像纹理特征提取方法综述[J].中国图象图形学报.2009，14(4)：622-627.
[128]Yu Tao,Ernest C.M.Lam,Yuan Y.Tang.Feature Extraction Using Wavelet and Fractal[J].Pattern Recognition Letters.2001(22)：271-287.
[129]Frank Y.Shih,Chao-Fa Chuang.Automatic extraction of head and face boundaries and facialfeatures[J].Information Sciences.2004(158)：117-130.
[130]Nojun Kwak.Feature extraction for classification problems and its application to facerecognition [J]. Pattern Recognition.2008(41)：1701-1717.
[131]Pai-Hui Hsu Feature extraction of hyperspectral images using wavelet and matchingpursuit[J].ISPRS Journal of Photogrammetry&Remote Sensing.2007(62)：78-92.
[132]王成明，颜云辉，李骏，焦志刚.一种新的冷轧带钢典型表面缺陷特征提取方法[J].计算机工程与应用.2006(27)：184-186.
[133]Abdullah Bal.Image feature extraction by dynamic neural filtering and phase-only jointtransform correlation[J].Optics&Laser Technology.2007(39)：2-7.
[134]H. Zhang,C.M. Cartwright, M.S. Ding,W.A.Gillespie.Image feature extraction with variouswavelet functions in a photorefractive joint transform correlator[J].OpticsCommunications.2000(185)：277-284.
[135]Engin Avci,Abdulkadir Sengur,Davut Hanbay.An optimum feature extraction method fortexture classification[J].Expert Systems with Applications.2009(36)：6036-6043.
[136]Gang Yu,SagarV.Kamarthi.A cluster-based wavelet feature extraction method and itsapplication[J].Engineering Applications of Artificial Intelligence.2010(23)：196-202.
[137]Yannick Maret,Fre′de′ric Dufaux,Touradj Ebrahimi.Adaptive image replica detection basedon support vector classifiers[J].Signal Processing: Image Communication.2006(21)：688-703.
[138]M.Mirmehdi,P.L.Palmer, J.Kittler.Genetic optimisation of the image feature extractionprocess[J].Pattern Recognition Letters.1997(18)：355-365.
[139]Oivind Due Trier,Anil K.Jain,Torfinn Taxt.Feature Extraction Methods for CharacterRecognition-A Survey[J].Pattern Recognition.1996，29(4)：641-662.
[140]Vapnik V.The nature of statistical learning theory[M].New York：Springer Verlag.2000.
[141]Cristianini N.,Shawe T J.An introduction to support vector machine[M].New York：Cambridge University Press.2000.
[142]Zhao Hui.Study on Support Vector Machines Classification methods and their Application inText Categorization[D].Dalian University of Technology.2005.
[143]Doumpos M,Zopounidis C.Additive support vector machines for patternclassification[J].Systerms,Man,and Cybernetics：Part B.2007，37(3)：540-550.
[144]Jayadeva,Khemchandani R,Chandra S.Twin support vector machines for patternclassification[J].Pattern Analysis and Machine Intelligence.2007，29(5)：905-910.
[145]黄勇，郑春颖.多类支持向量机算法综述[J].计算技术与自动化.2005，24(4)：61-63.
[146]胡学坤，李金霞.基于粗糙集与模糊支持向量机的模式分类方法研究[R].科技通报.2010，26(2)：250-252.
[147]Lin Chun-Fu,Wang Sheng De.Fuzzy Support Vector Machines[J].Networks.2002，13(2)：464-471.
[148]陈方林，刘彦.基于支持向量机的X射线焊缝缺陷检测[J].机械工程与自动化.2010(2)：122-124.
[149]张晓光，肖兴明.基于广义加权支持向量机的焊接缺陷分类方法[J].华东理工大学学报：自然科学版.2005，31(5)：645-648.
[150]黎维娟，卢振泰.基于支持向量机的脑部MR图像细分类[J].电路与系统学报.2010，15(1)：5-9.
[151]Jordi Inglada.Automatic recognition of man-made objects in high resolution optical remotesensing images by SVM classification of geometric image features[J].ISPRS Journal ofPhotogrammetry and Remote Sensing.2007，62(3)：236-248.
[152]Georgios C.Anagnostopoulos. SVM-based target recognition from synthetic aperture radarimages using target region outline descriptors[J].Nonlinear Analysis:Theory,Methods&Applications.2009，71(12)：e2934-e2939.
[153]J. Mitéran,S.Bouillant,E.Bourennane.SVM approximation for real-time image segmentationby using an improved hyperrectangles-based method[J].Real-Time Imaging.2003，9(3)：179-188.
[154]蔡文.可拓集合和不相容问题[J].科学探索学报.1983(1)：83-97.
[155]Cai Wen.Extension theory and its applications[R].Chinese Science Bulletin.1999，44(17)：153-154.
[156]杨春燕，蔡文.可拓工程[M].北京：科学出版社.2007.
[157]陈文伟.挖掘变化知识的可拓数据挖掘研究[J].中国工程科学.2006，8(11)：70-73.
[158]Yu Yong-quan,PENG Hal-xia.The principle of extension detecting with extensionsets[C].Proc of International Conference on Computer:Communication and ControlTechnologies,Informatics＆Systemics.2003：113-118.
[159]Wang M H,Tseng Y F.A novel clustering algorithm based on the extension theory and geneticalgorithm[J].Expert Systems with Applications.2009，36(4)：8269-8276.
[160]Wang M H.Application of extension theory to PD pattern recognition in high-voltage currenttransformers[J].Power Delivery.2005，20(3)：1939-1946.
[161]Ye Jun.Application of extension theory in misfire fault diagnosis of gasolineengines[J].Expert Systems with Applications.2009，36(2)：1217-1221.
[162]刘海，朱小平.一种基于可拓理论的图像检索方法[J].计算机系统应用.2009(3)：54-56.
[163]Ye Dan,Yu Yong-quan,Zeng Bi.Research of Classification Based on Extenics[C].Conferenceon Computational Intelligence and Multimedia Applications.2007(1)：129-132.
[164]Jung-Chi Su,Chuin-Mu Wang,Sheng-Chih Yang,Gia-Hao Chang.An Extenics Approach toMRI Classification[C].IEEE International Conference on Systems,Man andCybernetics.2006(1)：562-567.
[165]Wang Shiyun,Wang Zhijun,Li Yunjie,etc.Study on the Application of Extenics in DataMining [C].International Forum on Computer Science-Technology andApplications.2009(2)：109-112.
[166]Shu Hong-chun,Hu Ze-jiang,Sun Shi-yun,etc.The fault diagnosis algorithm for transformerbased on Extenics and rough set theory[C].Third International Conference on Electric UtilityDeregulation and Restructuring and Power Technologies.2008：1269-1272.
© 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 |