细胞图像的分割、纹理提取及识别方法研究
|
摘要
本文对细胞图像的分割、纹理提取及识别中的关键技术进行了深入研究，主要包括单细胞图像中细胞核与细胞质边缘的精确提取、细胞图像的纹理提取及细胞图像多特征融合分类。此外，本文还尝试改进极限学习机（Extreme LearningMachine，ELM）分类器处理细胞图像分类中常存在的不平衡数据问题。主要研究成果如下：
1.本文提出一种基于射线梯度的GVF Snake主动轮廓模型，用以从单细胞图像中精确定位细胞核与细胞质的边缘。GVF Snake主动轮廓模型是种应用广泛的目标边缘跟踪算法。在细胞图像中，细胞质与背景间的界限相对模糊、细胞核与细胞质边缘附近常分散有干扰性的血细胞及炎症细胞、染色浓度不均匀，这些都容易将GVF Snake轮廓吸附到错误的位置。为解决这些问题，本文结合细胞图像中染色浓度的分布特点，提出了如下改进：（1）充分利用梯度的方向性信息，提出了基于射线梯度的边缘图计算思路，相比传统梯度边缘图，能有效提取模糊边缘；（2）提出了基于栈的灰度差补偿算法，结合正灰度差抑制，能有效克服由噪声、血细胞及炎症细胞等引起的虚假梯度的影响。Herlev宫颈细胞数据集上的实验验证了这种方法的有效性。
2.本文提出一种基于Gabor系数分块统计的细胞图像纹理提取方法。纹理特征在细胞图像状态识别中发挥着重要作用。针对Gabor滤波后图像特征维数高、数据量大的问题，提出如下改进：将图像分成若干子块，计算各子块中特定尺度和方向Gabor系数的均值和方差，组成各块的特征矢量。按行列顺序将各块特征矢量拼接组成整幅图像的特征矢量。依据投票规则将多个两类分类器组合成多类分类器，并在两类分类器设计时自适应地挑选出最具分辨能力的最优特征子集。在Yale人脸数据库上进行实验并与其他方法进行比较，讨论了分块大小和最优特征子集维数对分类识别率的影响。HEp-2细胞染色型别分类实验验证了本方法的有效性。
3.本文提出一种基于局部最大熵多值模式的细胞图像纹理提取方法。局部多值模式（Local Multiple Pattern，LMP）是对局部二值模式（Local Binary Pattern，LBP）的改进，是种高效的图像纹理特征提取方法。但局部多值模式需手工设定多个阈值，且其特征维数过高。为解决这两个问题，提出如下改进：首先，统计每幅图像的灰度差直方图，依据最大熵原理在此直方图基础上自动计算各阈值，以保留最多的不确定性及分类信息。然后，使用平面切分组合编码机制取代原有的编码机制，将特征维度控制在多项式范围内。在Outex与KTH-TIPS纹理数据集上与局部二值模式及局部多值模式进行了全方位比较，验证了本方法的有效性。HEp-2细胞染色型别分类实验也取得了满意的效果。
4.本文提出一种基于后验概率的细胞图像多特征融合分类方法。在细胞图像分类中，需对不同方法提取的多种特征进行有效的融合。首先，使用每种特征训练一个后验概率分类器，将多个分类器的概率输出加权求和，构建集成分类器。其中，各分类器的权重根据其在训练集上的表现确定，在训练集上表现较好的分类器将获得较大的权重。而后，将集成分类器用作元分类器嵌入到AdaBoost.M1分类器集成框架中，提升分类效果。HEp-2细胞染色型别分类实验表明：该方法能有效融合多种图像特征，显著提升分类性能。
5.本文提出两种改进ELM分类器处理不平衡数据分类问题的方法。对临床数据分类时，受限于各种条件，常出现样本集分布不平衡的情况。使用标准分类方法对不平衡数据处理时常无法取得满意的结果。不平衡数据的分类问题已得到广泛的研究关注，但尚无相关研究围绕ELM分类器展开。本文提出如下改进：首先，将代价敏感信息引入ELM，为不同类样本赋予不同的错分权重，使用遗传算法搜索最优权重集合，提出代价敏感ELM；然后，将代价敏感ELM嵌入代价敏感AdaBoost.M1分类器集成框架，提出代价敏感组合ELM。在19个医学相关不平衡数据集上的实验验证了所提出的两种方法的有效性。
This thesis is focused on some issues related to segmentation,texture extraction andclassification of cell images. These issues mainly include a method to accurately extractboth the nucleus and cytoplasm, two new texture extraction methods, as well as a fusionmethod of different kinds of features. In addition, using ELM to deal with the imbalanceddataset classification problem, which is common in medical data, is also discussed in thisthesis. The main contributes can be exhibited by the following aspects:
1. A radiating GVF Snake (RGVF) model is proposed aiming at accurate extrac-tion of both the nucleus and cytoplasm from a single-cell image. GVF Snake model isa widely used contour tracking method in image processing. However, when used toextract the nuclei and cytoplasm from cell images, GVF Snake may be easily absorbedto wrong positions due to the fact that (1) the boundaries between the cytoplasm and thebackground are oftenquite obscure;(2) alot of inferences exist nearthe edgeof the nucleiand the cytoplasm, including inflammatory cells, blood cells and other noises. To solvethese problems, RGVF involves a new edge map computation method and a stack-basedrefinement, and is thus robust to contaminations and can effectively locate the obscureboundaries. The boundaries can also be correctly traced even if there are interferencesnear the cytoplasm and nucleus regions. Experiments performed on the Herlev dataset,which contains917images show the effectiveness of the proposed algorithm.
2. A novel texture extraction method based on Gabor filters is proposed. Texturefeatures play important roles in cell classifications. The cell image is first decomposedby convolving with multi-scale and multi-orientation Gabor filters, then separated intoseveral blocks. The Block Feature Vector (BFV) can be obtained through statistical tech-niques. The Total Feature Vector (TFV) of the whole image is then constructed by conju-gating the BFVs in row column order. In the classification stage, a robust classificationmethod which performs multi-class classification is built based on many two-class clas-sifiers using voting mechanism. Before each two-class classifier, a feature extractionmodule adaptively selects the most important features. The results compared with thepublished results on Yale face database verify the validity of the proposed method. Thestaining pattern classification results on HEp-2cell dataset also prove that the proposemethod is effective.
3. A novel texture extraction method named Maximum Entropy based Local Mul-tiple Pattern (MELMP) is proposed. Local multiple patterns(LMP) has been proved tobe an efficient and robust texture extraction method. However, the thresholds have to beset manually and the the feature dimension is quite high in LMP. To solve these prob-lems, a maximum entropy based thresholding scheme, which computes the thresholds bydividing the intensity difference histogram of an image equally, is adopted, and the split-concatenate encoding is used to form shorter and more effective feature vectors. Exper-imental results on four test suits with an SVM classifier show that the proposed methodachieves overall better performances than both LBP and LMP in texture classification.The staining pattern classification results on HEp-2cell dataset are also very satisfying.
4. A feature fusion framework based on posteriori probability classifier and Ad-aBoost.M1framework is introduced. How to fuse different features together is quiteimportant in achieving better cell image classification results. In this thesis:(1) withineach boosting round, several posterior probability classifiers are trained corresponding todifferent descriptors, and then combined to an integrated classifier;(2) AdaBoost.M1ismodifiedtoenhancetheperformanceoftheintegratedclassifiers. ExperimentalresultsonHEp-2cell dataset show the proposed method is effective and can significantly improvethe classification accuracy.
5. Two strategies to deal with imbalanced classification are proposed, namely cost-sensitive ELM (CS-ELM) and ELM based cost-sensitive AdaBoost (ELM-AdaCx). First,cost-sensitive information is introduced into the training process of ELM to form CS-ELM. A genetic algorithm (GA) is utilized to find the optimal weights. Second, the pro-posed CS-ELM is utilized as the meta classifier and embedded into a cost-sensitive Ad-aBoost.M1frameworktoformELM-AdaCx. Experimentalresultson19datasetsfromtheKEEL repository show that the proposed strategies could achieve more balanced resultsthan the basic ELM.
1.本文提出一种基于射线梯度的GVF Snake主动轮廓模型，用以从单细胞图像中精确定位细胞核与细胞质的边缘。GVF Snake主动轮廓模型是种应用广泛的目标边缘跟踪算法。在细胞图像中，细胞质与背景间的界限相对模糊、细胞核与细胞质边缘附近常分散有干扰性的血细胞及炎症细胞、染色浓度不均匀，这些都容易将GVF Snake轮廓吸附到错误的位置。为解决这些问题，本文结合细胞图像中染色浓度的分布特点，提出了如下改进：（1）充分利用梯度的方向性信息，提出了基于射线梯度的边缘图计算思路，相比传统梯度边缘图，能有效提取模糊边缘；（2）提出了基于栈的灰度差补偿算法，结合正灰度差抑制，能有效克服由噪声、血细胞及炎症细胞等引起的虚假梯度的影响。Herlev宫颈细胞数据集上的实验验证了这种方法的有效性。
2.本文提出一种基于Gabor系数分块统计的细胞图像纹理提取方法。纹理特征在细胞图像状态识别中发挥着重要作用。针对Gabor滤波后图像特征维数高、数据量大的问题，提出如下改进：将图像分成若干子块，计算各子块中特定尺度和方向Gabor系数的均值和方差，组成各块的特征矢量。按行列顺序将各块特征矢量拼接组成整幅图像的特征矢量。依据投票规则将多个两类分类器组合成多类分类器，并在两类分类器设计时自适应地挑选出最具分辨能力的最优特征子集。在Yale人脸数据库上进行实验并与其他方法进行比较，讨论了分块大小和最优特征子集维数对分类识别率的影响。HEp-2细胞染色型别分类实验验证了本方法的有效性。
3.本文提出一种基于局部最大熵多值模式的细胞图像纹理提取方法。局部多值模式（Local Multiple Pattern，LMP）是对局部二值模式（Local Binary Pattern，LBP）的改进，是种高效的图像纹理特征提取方法。但局部多值模式需手工设定多个阈值，且其特征维数过高。为解决这两个问题，提出如下改进：首先，统计每幅图像的灰度差直方图，依据最大熵原理在此直方图基础上自动计算各阈值，以保留最多的不确定性及分类信息。然后，使用平面切分组合编码机制取代原有的编码机制，将特征维度控制在多项式范围内。在Outex与KTH-TIPS纹理数据集上与局部二值模式及局部多值模式进行了全方位比较，验证了本方法的有效性。HEp-2细胞染色型别分类实验也取得了满意的效果。
4.本文提出一种基于后验概率的细胞图像多特征融合分类方法。在细胞图像分类中，需对不同方法提取的多种特征进行有效的融合。首先，使用每种特征训练一个后验概率分类器，将多个分类器的概率输出加权求和，构建集成分类器。其中，各分类器的权重根据其在训练集上的表现确定，在训练集上表现较好的分类器将获得较大的权重。而后，将集成分类器用作元分类器嵌入到AdaBoost.M1分类器集成框架中，提升分类效果。HEp-2细胞染色型别分类实验表明：该方法能有效融合多种图像特征，显著提升分类性能。
5.本文提出两种改进ELM分类器处理不平衡数据分类问题的方法。对临床数据分类时，受限于各种条件，常出现样本集分布不平衡的情况。使用标准分类方法对不平衡数据处理时常无法取得满意的结果。不平衡数据的分类问题已得到广泛的研究关注，但尚无相关研究围绕ELM分类器展开。本文提出如下改进：首先，将代价敏感信息引入ELM，为不同类样本赋予不同的错分权重，使用遗传算法搜索最优权重集合，提出代价敏感ELM；然后，将代价敏感ELM嵌入代价敏感AdaBoost.M1分类器集成框架，提出代价敏感组合ELM。在19个医学相关不平衡数据集上的实验验证了所提出的两种方法的有效性。
This thesis is focused on some issues related to segmentation,texture extraction andclassification of cell images. These issues mainly include a method to accurately extractboth the nucleus and cytoplasm, two new texture extraction methods, as well as a fusionmethod of different kinds of features. In addition, using ELM to deal with the imbalanceddataset classification problem, which is common in medical data, is also discussed in thisthesis. The main contributes can be exhibited by the following aspects:
1. A radiating GVF Snake (RGVF) model is proposed aiming at accurate extrac-tion of both the nucleus and cytoplasm from a single-cell image. GVF Snake model isa widely used contour tracking method in image processing. However, when used toextract the nuclei and cytoplasm from cell images, GVF Snake may be easily absorbedto wrong positions due to the fact that (1) the boundaries between the cytoplasm and thebackground are oftenquite obscure;(2) alot of inferences exist nearthe edgeof the nucleiand the cytoplasm, including inflammatory cells, blood cells and other noises. To solvethese problems, RGVF involves a new edge map computation method and a stack-basedrefinement, and is thus robust to contaminations and can effectively locate the obscureboundaries. The boundaries can also be correctly traced even if there are interferencesnear the cytoplasm and nucleus regions. Experiments performed on the Herlev dataset,which contains917images show the effectiveness of the proposed algorithm.
2. A novel texture extraction method based on Gabor filters is proposed. Texturefeatures play important roles in cell classifications. The cell image is first decomposedby convolving with multi-scale and multi-orientation Gabor filters, then separated intoseveral blocks. The Block Feature Vector (BFV) can be obtained through statistical tech-niques. The Total Feature Vector (TFV) of the whole image is then constructed by conju-gating the BFVs in row column order. In the classification stage, a robust classificationmethod which performs multi-class classification is built based on many two-class clas-sifiers using voting mechanism. Before each two-class classifier, a feature extractionmodule adaptively selects the most important features. The results compared with thepublished results on Yale face database verify the validity of the proposed method. Thestaining pattern classification results on HEp-2cell dataset also prove that the proposemethod is effective.
3. A novel texture extraction method named Maximum Entropy based Local Mul-tiple Pattern (MELMP) is proposed. Local multiple patterns(LMP) has been proved tobe an efficient and robust texture extraction method. However, the thresholds have to beset manually and the the feature dimension is quite high in LMP. To solve these prob-lems, a maximum entropy based thresholding scheme, which computes the thresholds bydividing the intensity difference histogram of an image equally, is adopted, and the split-concatenate encoding is used to form shorter and more effective feature vectors. Exper-imental results on four test suits with an SVM classifier show that the proposed methodachieves overall better performances than both LBP and LMP in texture classification.The staining pattern classification results on HEp-2cell dataset are also very satisfying.
4. A feature fusion framework based on posteriori probability classifier and Ad-aBoost.M1framework is introduced. How to fuse different features together is quiteimportant in achieving better cell image classification results. In this thesis:(1) withineach boosting round, several posterior probability classifiers are trained corresponding todifferent descriptors, and then combined to an integrated classifier;(2) AdaBoost.M1ismodifiedtoenhancetheperformanceoftheintegratedclassifiers. ExperimentalresultsonHEp-2cell dataset show the proposed method is effective and can significantly improvethe classification accuracy.
5. Two strategies to deal with imbalanced classification are proposed, namely cost-sensitive ELM (CS-ELM) and ELM based cost-sensitive AdaBoost (ELM-AdaCx). First,cost-sensitive information is introduced into the training process of ELM to form CS-ELM. A genetic algorithm (GA) is utilized to find the optimal weights. Second, the pro-posed CS-ELM is utilized as the meta classifier and embedded into a cost-sensitive Ad-aBoost.M1frameworktoformELM-AdaCx. Experimentalresultson19datasetsfromtheKEEL repository show that the proposed strategies could achieve more balanced resultsthan the basic ELM.
引文
[1] Papanicolaou G. A new procedure for staining vaginal smears [J]. Science.1942,95(2469):438.
[2] Yang-MaoS-F,ChanY-K,ChuY-P.Edgeenhancementnucleusandcytoplastcon-tour detector of cervical smear images [J]. IEEE Transactions on Systems, Man,and Cybernetics.2008,38(2):353–366.
[3] Rigon A, Soda P, Zennaro D, et al. Indirect immunofluorescence in autoimmunediseases: assessment of digital images for diagnostic purpose [J]. Cytometry PartB: Clinical Cytometry.2007,72(6):472–477.
[4]谢凤英,姜志国.基于最大方差的免疫细胞图像双阈值分割[J].中国体视学与图像分析.2007,12(1):59–61.
[5] Lin Z. The cell image segmentation based on the K-L transform and OtsuMethod [C]. In Proceedings of the International Conference on Multimedia andSignal Processing.2011:25–28.
[6] Sahoo P, Arora G. A thresholding method based on two-dimensional Renyi’s en-tropy [J]. Pattern Recognition.2004,37(6):1149–1161.
[7]魏伟一.基于最大区域互信息量的生物细胞图像分割[J].西北师范大学学报:自然科学版.2010,46(3):44–46.
[8] Bruzzese D, Giani U. Automatic multilevel thresholding based on a fuzzy entropymeasure [M]//Bruzzese D, Giani U. Classification and Multivariate Analysis forComplex Data Structures. Springer,2011:2011:125–133.
[9]王任挥.基于最大信息熵原理的显微细胞图像多阈值分割算法[J].内蒙古科技与经济.2010(18):58–60.
[10] EspinozaE,MartinezG,FrerichsJ,etal.Cellclustersegmentationbasedonglobaland local thresholding forin-situ microscopy [C]. In Proceedings of the3rd IEEEInternationalSymposiumonBiomedicalImaging:NanotoMacro.2006:542–545.
[11]马保国，乔玲玲，贾寅波．基于局部自适应闽值的细胞图像分割方法[J]．计算机应用研究．2009，26(2)：755–756．
[12] PlissitiM,NikouC,CharchantiA.AccuratelocalizationofcellnucleiinPapsmearimages using gradient vector flow deformable models [C]. In Proceedings of the3rdInternationalConferenceonBio-inspiredSignalsandSystems.2010:284–289.
[13] Harandi N, Sadri S, Moghaddam N, et al. An automated method for segmentationof epithelial cervical cells in images of ThinPrep [J]. Journal of Medical Systems.2010,34(6):1043–1058.
[14] Sauvola J, Pietik inen M. Adaptive document image binarization [J]. PatternRecognition.2000,33(2):225–236.
[15] Bradbury L, Wan J. A spectral k-means approach to bright-field cell image seg-mentation [C]. In Proceedings of the International Conference of the IEEE Engi-neering in Medicine and Biology Society.2010:4748–4751.
[16] Theera-UmponN.Whitebloodcellsegmentationandclassificationinmicroscopicbone marrow images [C]. In Proceedings of Fuzzy Systems and Knowledge Dis-covery.2005:787–796.
[17] Chaira T. A novel intuitionistic fuzzy c means color clustering on human cell im-ages [C]. In Proceedings of the World Congress on Nature&Biologically InspiredComputing.2009:736–741.
[18] KongH,GurcanM, Belkacem-BoussaidK.Partitioninghistopathologicalimages:an integrated framework for supervised color-texture segmentation and cell split-ting [J]. IEEE Transactions on Medical Imaging.2011,30(9):1661–1677.
[19] Yin Z, Bise R, Chen M, et al. Cell segmentation in microscopy imagery usinga bag of local Bayesian classifiers [C]. In Proceedings of the IEEE InternationalSymposium on Biomedical Imaging: From Nano to Macro.2010:125–128.
[20]窦智宙，平子良，冯文兵．多分类支持向量机分割彩色癌细胞图像[J]．计算机工程与应用．2009，45(20)：236–239．
[21] Orozco-Monteagudo M, Sahli H, Mihai C, et al. A hybrid approach for Pap-Smearcell nucleus extraction [M]//Orozco-Monteagudo M, Sahli H, Mihai C, et al.Pattern Recognition. Springer,2011:2011:174–183.
[22] Orozco-Monteagudo M, Miha C, Sahli H, et al. Combined hierarchical watershedsegmentation and SVM classification for Pap-Smear cell nucleus extraction [J].Computing and Systems.2012,16(2):133–145.
[23] DiF,MaoyongC,ChangzhiL,etal.Wall-adherentcellssegmentationbasedonBPneural network [C]. In Proceedings of the3rd International Conference on Bioin-formatics and Biomedical Engineering.2009:1–4.
[24] Pan C, Park D, Yang Y, et al. Leukocyte image segmentation by visual attentionand extreme learning machine [J]. Neural Computing&Applications.2011,21:1217–1227.
[25] Feng C, Chen P. Blood cell image localized segmentation combining mean-shiftand ELM [C]. In Proceedings of the International Conference on Mechatronic Sci-ence, Electric Engineering and Computer.2011:2078–2081.
[26] WangM,ZhouX,LiF,etal.NovelcellsegmentationandonlineSVMforcellcyclephase identification in automated microscopy [J]. Bioinformatics.2008,24(1):94–101.
[27]刘应乾,曹茂永.基于Gabor滤波与区域生长的细胞分割[J].山东科技大学学报:自然科学版.2012,31(2):99–103.
[28] Mustafa N, Isa N, Mashor M. Automated multicells segmentation of ThinPrepimage Using modified seed based region growing algorithm [J]. Biomedical SoftComputing and Human Sciences.2009,14(2):41–47.
[29] Kim K, Song D, Woo Y. Nucleus segmentation and recognition of uterine cervicalpap-smears [C]. In Proceedings of the11th International Conference on RoughSets, Fuzzy Sets, Data Mining and Granular Computing.2007:153–160.
[30] PlissitiM,NikouC,CharchantiA.AutomateddetectionofcellnucleiinPapsmearimages using morphological reconstruction and clustering [J]. IEEE Transactionson Information Technology in Biomedicine.2011,15(2):233–241.
[31] Vincent L, Soille P. Watersheds in igital spaces: an efficient algorithm based onimmersion simulations [J]. IEEE Transactions on Pattern Analysis and MachineIntelligence.1991,13(6):583–598.
[32] Jiang K, Liao Q, Xiong Y. A novel white blood cell segmentation scheme based onfeature space clustering [J]. Soft Computing-A Fusion of Foundations, Method-ologies and Applications.2006,10(1):12–19.
[33] Chen W, Zhang X. A new watershed algorithm for cellular image segmenta-tion based on mathematical morphology [C]. In Proceedings of the InternationalConference on Machine Vision and Human-Machine Interface (MVHI).2010:653–656.
[34] Plissiti M, Nikou C, Charchanti A. Watershed-based segmentation of cell nucleiboundariesinPapsmearimages[C].InProceedingsofthe10thIEEEInternationalConference on Information Technology and Applications in Biomedicine.2010:1–4.
[35] Wang Y, Sun Y, Lin C, et al. Nerve cell segmentation via multi-scale gradient wa-tershed hierarchies [C]. In Proceedings of the28th Annual International Confer-enceoftheIEEEEngineeringinMedicineandBiologySociety.2006:4310–4313.
[36] Gonzalez R, Woods R. Digital Image Processing, third ed.[M]. Prentice-Hall,2008.
[37]赵英红,乔双,董丽华. Canny算子与数学形态学算子相结合实现胸水细胞的边缘提取[J].东北师大学报:自然科学版.2008,40(3):42–45.
[38] Yang-Mao S, Chen Y, Chan Y, et al. Gradient direction edge enhancement basednucleus and cytoplasm contour detector of cervical smear images [C]. In Proceed-ings of the International Conference on Medical Biometrics.2007:290–297.
[39] Lin C-H, Chan Y-K, Chen C-C. Detection and segmentation of cervical cell cyto-plast and nucleus [J]. International Journal of Imaging Systems and Technology.2009,19(3):260–270.
[40]王可佳,平子良,海鹰, et al.用改进的随机Hough变换检测胸水图像中的细胞[J].光电子.激光.2008,19(3):420–422.
[41] Hukkanen J, Hategan A, Sabo E, et al. Segmentation of cell nuclei from histologi-cal images by ellipse fitting [C]. In Proceedings of the European Signal ProcessingConference.2010:1219–1223.
[42] Vromen J, McCane B. Red blood cell segmentation from SEM images [C]. InProceedings of the24th International Conference Image and Vision ComputingNew Zealand.2009:44–49.
[43] KassM,WitkinA,TerzopoulosD.Snakes:activecontourmodels[J].InternationalJournal of Computer Vision.1988,1(4):321–331.
[44] Bamford P, Lovell B. Unsupervised cell nucleus segmentation with active con-tours [J]. Signal Processing.1998,71(2):203–213.
[45] Xu C, Prince J. Snakes, shapes, and gradient vector flow [J]. IEEE Transactionson Image Processing.2002,7(3):359–369.
[46] Zamani F, Safabakhsh R. An unsupervised GVF snake approach for white bloodcell segmentation based on nucleus [C]. In Proceedings of the8th InternationalConference on Signal Processing.2006:1–4.
[47] Ma ka M, Daněk O, Ortiz-de Solórzano C, et al. A two-phase segmentation of cellnuclei using fast level set-like algorithms [C]. In Proceedings of the ScandinavianConference on Image Analysis.2009:390–399.
[48] Yu W, Lee H, Hariharan S, et al. Level set segmentation of cellular images basedon topological dependence [C]. In Proceedings of the International Symposium onVisual Computing.2008:540–551.
[49] Jing-Feng M, Kai H, Shang-Lian B, et al. A new level set model for cell imagesegmentation [J]. Chinese Physics B.2011,20(2):028701.
[50] Sobrevilla P, Montseny E, Lerma E. A fuzzy-based automated cells detectionsystem for color Pap Smear tests–FACSDS [M]//Sobrevilla P, Montseny E,LermaE.FuzzySetsandTheirExtensions:Representation,AggregationandMod-els. Springer,2008:2008:657–674.
[51] Vaschetto F, Montseny E, Sobrevilla P, et al. THREECOND: an automated andunsupervised three colour fuzzy-based algorithm for detecting nuclei in cervicalPap smear images [C]. In Proceedings of the9th International Conference on In-telligent Systems Design and Applications.2009:1359–1364.
[52] NaL,Jian-XinL. Automatic colorimage segmentationbasedonanisotropicdiffu-sion and the application in cancer cell segmentation [C]. In Proceedings of the1stInternational Conference on Bioinformatics and Biomedical Engineering.2007:992–994.
[53] Lassouaoui N, Hamami L. Genetic algorithms and multifractal segmentation ofcervical cell images [C]. In Proceedings of the7th International Symposium onSignal Processing and Its Applications.2003:1–4.
[54] Al-Kofahi Y, Lassoued W, Lee W, et al. Improved automatic detection andsegmentation of cell nuclei in histopathology images [J]. IEEE Transactions onBiomedical Engineering.2010,57(4):841–852.
[55] KeuperM.HierarchicalMarkovRandomFieldsformastcellsegmentationinelec-tron microscopic recordings [C]. In Proceedings of the IEEE International Sym-posium on Biomedical Imaging: From Nano to Macro.2011.
[56] Nandy K, Gudla P, Lockett S. Automatic segmentation of cell nuclei in2D usingdynamicprogramming[C].InProceedingsof2ndWorkshoponMicrosopicImageAnalysis with Applications in Biology.2007.
[57] Cheng J, Rajapakse J. Segmentation of clustered nuclei with shape markers andmarkingfunction[J].IEEETransactionsonBiomedicalEngineering.2009,56(3):741–748.
[58] Jung C, Kim C. Segmenting clustered nuclei using H-minima transform-basedmarker extraction and contour parameterization [J]. IEEE Transactions onBiomedical Engineering.2010,57(10):2600–2604.
[59]傅蓉.细胞重叠与融合性图像的分离与分割技术研究[D].[S. l.]:广州:南方医科大学,2007.
[60] Jantzen J, Norup J, Dounias G, et al. Pap-smear benchmark data for pattern classi-fication[J].Proceedingsofthe1stEuropeanSymposiumonNature-inspiredSmartInformation Systems.2005:1–9.
[61] Plissiti M, Nikou C. Cervical cell classification based exclusively on nucleus fea-tures [C]. In Proceedings of the International Conference on Image Analysis andRecognition.2012:483–490.
[62] Marinakis Y, Marinaki M, Dounias G, et al. Intelligent and nature inspired opti-mization methods in medicine: the Pap smear cell classification problem [J]. Ex-pert Systems.2009,26(5):433–457.
[63]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):622–635.
[64] Ojala T, Pietikainen M, Harwood D. A comparative study of texture measureswith classification based on featured distributions [J]. Pattern Recognition Letters.1996,29(1):51–59.
[65] Haralick R, Shanmugam K, Dinstein I. Textural features for image classifica-tion [J]. IEEE Transactions on Systems, Man and Cybernetics.1973,3(6):610–621.
[66] Li X, Hu W, Zhang Z, et al. Heat kernel based local binary pattern for face repre-sentation [J]. IEEE Signal Processing Letters.2010,17(3):308–311.
[67] Bur in K, Vasif N. Down syndrome recognition using local binary patterns andstatistical evaluation of the system [J]. Expert Systems with Applications.2011,38(7):8690–8695.
[68] HuangX,ZhaoG,ZhengW,etal.Spatiotemporallocalmonogenicbinarypatternsfor facial expression recognition [J]. IEEE Signal Processing Letters.2012,19(5):243–246.
[69] Shen L, Jia S, Ji Z, et al. Extracting local texture features for image-based coinrecognition [J]. IET Image Processing.2011,5(5):394–401.
[70] Janney P, Geers G. Texture classification using invariant features of local tex-tures [J]. IET Image Processing.2010,4(3):158–171.
[71] Materka A, Strzelecki M, et al. Texture analysis methods: a review [R].1998.
[72] Randen T, Husoy J. Filtering for texture classification: a comparative study [J].IEEE Transactions on Pattern Analysis and Machine Intelligence.1999,21(4):291–310.
[73] Lam E, Goodman J. A mathematical analysis of the DCT coefficient distributionsfor images [J]. IEEE Transactions on Image Processing.2000,9(10):1661–1666.
[74] Zhou F, Feng J, Shi Q. Texture feature based on local Fourier transform [C]. InProceedingsoftheInternationalConferenceonImageProcessing.2001:610–613.
[75]张志龙,李吉成,沈振康.基于局部沃尔什变换的纹理特征提取方法研究[J].信号处理.2005,21(6):589–596.
[76] Movellan J. Tutorial on gabor filters [R].2008.
[77] Wiskott L, Fellous J, Kuiger N, et al. Face recognition by elastic bunch graphmatching [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.1997,19(7):775–779.
[78] Liu C, Wechsler H. Gabor feature based classification using the enhanced fisherlinear discriminant model for face recognition [J]. IEEE Transactions on Imageprocessing.2002,11(4):467–476.
[79] Pavlidis T. Structural descriptions and graph grammars [C]. In Pictorial Informa-tion Systems.1980:86–103.
[80] Soille P. Morphological image analysis: principles and applications [M]. Springer-Verlag New York, Inc.,2003.
[81] Walker R, Jackway P, Lovell B, et al. Classification of cervical cell nuclei usingmorphological segmentation and textural feature extraction [C]. In Proceedings ofthe1994Second Australian and New Zealand Conference on Intelligent Informa-tion Systems.1994:297–301.
[82] Walker R, Jackway P, Lovell B. Cervical cell classification via co-occurrence andMarkov random field features [C]. In Proceedings of Digital Image Computing:Techniques and Applications.1995:294–299.
[83]张培培,陈德运,包振健.基于共生矩阵和分形的彩色骨髓细胞图像纹理[J].哈尔滨理工大学学报.2008,13(1):46–49.
[84]赵晖,鲍莉,梁光明, et al.基于综合灰度共生矩阵的显微细胞图像纹理研究[J].自动化技术与应用.2005,23(10):27–29.
[85] Nanni L, Lumini A, Brahnam S. Local binary patterns variants as texture descrip-torsformedicalimageanalysis[J].Artificialintelligenceinmedicine.2010,49(2):117–125.
[86] PlissitiM,NikouC,CharchantiA.Combiningshape,textureandintensityfeaturesfor cell nuclei extraction in Pap smear images [J]. Pattern Recognition Letters.2011,32(6):838–853.
[87] Xu S, Sun N, Cao M. Wall-pasted cell segmentation based on circular Gabor filterbank [C]. In Proceedings of the International Conference on Wavelet Analysis andPattern Recognition.2007:1735–1741.
[88] CHO S, KIM J. Combining multiple neural networks by fuzzy integral for robustclassification [J]. IEEE Transactions on Systems, Man, and Cybernetics.1995,25(2):380–384.
[89] Kittler J, Hatef M, Duin R, et al. On combining classifiers [J]. IEEE Transactionson Pattern Analysis and Machine Intelligence.1998,20(3):226–239.
[90] Kumar A, Kanhangad V, Zhang D. A new framework for adaptive multimodalbiometrics management [J]. IEEE Transactions on Information Forensics and Se-curity.2010,5(1):92–102.
[91] Chawla N V, Bowyer K W, Hall L O, et al. SMOTE: synthetic minority over-sampling technique [J]. Journal of Artificial Intelligence Research.2002,16:321–357.
[92] DrownD,KhoshgoftaarT,NarayananR.Usingevolutionarysamplingtomineim-balanced data [C]. In Proceedings of the6th International Conference on MachineLearning and Applications.2007:363–368.
[93] Yen S, Lee Y. Cluster-based under-sampling approaches for imbalanced data dis-tributions [J]. Expert Systems with Applications.2009,36(3):5718–5727.
[94] Pazzani M, Merz C, Murphy P, et al. Reducing misclassification costs [C]. InProceedings of the11th International Conference on Machine Learning.1994:217–225.
[95] Chen C, Liaw A, Breiman L. Using random forest to learn imbalanced data [R].2004.
[96] Chew H, Bogner R, Lim C. Dual-support vector machine with error rate andtraining size biasing [C]. In Proceedings of the IEEE International Conference onAcoustics, Speech, and Signal Processing.2001:1269–1272.
[97]谢纪刚,裘正定.非平衡数据集Fisher线性判别模型[J].北京交通大学学报:自然科学版.2006,30(5):15–18.
[98] Kotsiantis S, Pintelas P. Mixture of expert agents for handling imbalanced datasets[J].AnnalsofMathematics,Computing&Teleinformatics.2003,1(1):46–55.
[99] Chawla N, Lazarevic A, Hall L, et al. SMOTEBoost: improving prediction of theminority class in boosting [C]. In Proceedings of Principles of Data Mining andKnowledge Discovery.2003:107–119.
[100] Lee S. Noisy replication in skewed binary classification [J]. Computational Statis-tics&Data Analysis.2000,34(2):165–191.
[101] Wu H S, Gil J, Barba J. Optimal segmentation of cell images [J]. IEE Proceedingsof Vision, Image and Signal Processing.1998,145(1):50–56.
[102] Bamford P, Lovell B. A water immersion algorithm for cytological image seg-mentation [C]. In Proceedings of the APRS Image Segmentation Workshop.1996:75–79.
[103] Kale A, Aksoy S. Segmentation of cervical cell images [C]. In Proceedings of the20th IAPR International Conference on Pattern Recognition.2010:2399–2402.
[104] LinC-H,ChenC.Imagesegmentationbasedonedgedetectionandregiongrowingfor Thinprep cervical smear [J]. International Journal of Pattern Recognition andArtificial Intelligence.2010,24(7):1061–1089.
[105] Buades A, Coll B, Morel J. Self-similarity-based image denoising [J]. Communi-cations of the ACM.2011,54(5):109–117.
[106] Rubner Y, Tomasi C. Perceptual metrics for image database navigation [M].Springer,2000.
[107] Cheng H, Jiang X, Sun Y, et al. Color image segmentation: advances andprospects [J]. Pattern Recognition.2001,34(12):2259–2281.
[108] Yu J, Tan J, Wang Y. Ultrasound speckle reduction by a SUSAN-controlledanisotropic diffusion method [J]. Pattern Recognition.2010,43(9):3083–3092.
[109] Tomasi C, Manduchi R. Bilateral filtering for gray and color images [C]. In Pro-ceedings of the6th International Conference on Computer Vision.1998:839–846.
[110] Wang Z, Bovik A, Sheikh H, et al. Image quality assessment: from error visibilityto structural similarity [J]. IEEE Transactions on Image Processing.2004,13(4):600–612.
[111] Sezgin M, et al. Survey over image thresholding techniques and quantitative per-formance evaluation [J]. Journal of Electronic Imaging.2004,13(1):146–168.
[112] Zacharia E, Kostopoulou E, Maroulis D, et al. A spot segmentation approach for2D gel electrophoresis images based on2D histograms [C]. In Proceedings of the20th IAPR International Conference on Pattern Recognition.2010:2540–2543.
[113] Wang N, Li X, Chen X. Fast three-dimensional Otsu thresholding with shuffledfrog-leapingalgorithm[J].PatternRecognitionLetters.2010,31(13):1809–1815.
[114] Zijdenbos A, Dawant B, Margolin R, et al. Morphometric analysis of white matterlesions in MR images: method and validation [J]. IEEE Transactions on MedicalImaging.1994,13(4):716–724.
[115] LiuL,FieguthP.Textureclassificationfromrandomfeatures[J].IEEEtransactionson Pattern Analysis and Machine Intelligence.2012,34(3):574–586.
[116] JRouco, Mosquera A, Penedo M, et al. Texture description in local scale usingtexton histograms with quadrature filter universal dictionaries [J]. IET ComputerVision.2011,5(4):211–221.
[117] Zhu C, Wang R. Local multiple patterns based multiresolution gray-scale androtation invariant texture classification [J]. Information Sciences.2012,187(3):93–108.
[118] Huang X, Li S, Wang Y. Shape localization based on statistical method using ex-tended local binary pattern [C]. In Proceedings of the3rd International Conferenceon Image and Graphics.2004:184–187.
[119]冯贵玉.人脸与掌纹识别的子空间特征提取方法研究[D].[S. l.]:长沙:国防科学技术大学,2007.
[120] He X, Yan S, Hu Y, et al. Face recognition using laplacian faces [J]. IEEE Trans-actions on Pattern Analysis and Machine Intelligence.2005,27(3):328–340.
[121] Yang J, Zhang D, Frangi A, et al. Two-dimensional PCA: a new approach toappearance-based face representation and recognition [J]. IEEE Transactions onPattern Analysis and Machine Intelligence.2004,26(1):131–137.
[122] Ojala T, Pietikainen M, Maenpaa T. Multiresolution gray-scale and rotation in-variant texture classification with local binary patterns [J]. IEEE Transactions onPattern Analysis and Machine Intelligence.2002,24(7):971–987.
[123] Liao S, Chung A. Face recognition by using elongated local binary patterns withaverage maximum distance gradient magnitude [C]. In Proceedings of Asian Con-ference on Computer Vision.2007:672–679.
[124] M enp T, Pietik inen M. Multi-scale binary patterns for texture analysis [C]. InProceedings of the Scandinavian Conference on Image Analysis.2003:885–892.
[125] Tan X, Triggs B. Enhanced local texture feature sets for face recognition underdifficult lighting conditions [J]. IEEE Transactions on Image Processing.2010,19(6):1635–1650.
[126] Grinstead C, Snell J. Introduction to probability [M]. American Mathematical So-ciety,2006.
[127] Ojala T, M enp T, Pietik inen M, et al. Outex: new framework for empiricalevaluation of texture analysis algorithms [C]. In Proceedings of the16th Interna-tional Conference on Pattern Recognition.2002:701–706.
[128] Caputo B, Hayman E, Fritz M, et al. Classifying materials in the real world [J].Image and Vision Computing.2010,28(1):150–163.
[129] Chang C, Lin C. LIBSVM: a library for support vector machines [J]. ACM Trans-actions on Intelligent Systems and Technology.2011,2(3):1–39.
[130] Vapnik V. The nature of statistical learning theory [M]. springer,1999.
[131] Platt J, et al. Probabilistic outputs for support vector machines and comparisons toregularized likelihood methods [J]. Advances in Large Margin Classifiers.1999,10(3):61–74.
[132] Gonen M, Tanugur A, Alpaydm E. Multiclass posterior probability support vectormachines [J]. IEEE Transactions on Neural Networks.2008,19(1):130–139.
[133] Wu T, Lin C, Weng R. Probability estimates for multi-class classification by pair-wise coupling [J]. The Journal of Machine Learning Research.2004,5:975–1005.
[134] Huang G-B, Wang D-H, Lan Y. Extreme learning machines: a survey [J]. Interna-tional Journal of Machine Learning and Cybernetics.2011,2(2):107–122.
[135] Huang G-B, Zhu Q-Y, Siew C-K. Extreme learning machine: theory and applica-tions [J]. Neurocomputing.2006,70(1):489–501.
[136] Serre D. Matrices: Theory and applications [M]. Springer Verlag,2010.
[137] ChawlaNV.Dataminingforimbalanceddatasets:anoverview[M]//ChawlaNV.Data Mining and Knowledge Discovery Handbook. Springer,2010:2010:875–886.
[138] Weiss G M. Mining with rarity: a unifying framework [J]. ACM SIGKDD Explo-rations.2004,6(1):7–19.
[139] Kotsiantis S, Kanellopoulos D, Pintelas P. Handling imbalanced datasets: a re-view [J]. GESTS International Transactions on Computer Science and Engineer-ing.2006,30(1):25–36.
[140] Guo X-J, Yin Y-L, Dong C-L, et al. On the class imbalance problem [C]. InProceedings of the4th International Conference on Natural Computation.2008:192–201.
[141] He H-B, Garcia E A. Learning from imbalanced data [J]. IEEE Transactions onKnowledge and Data Enginerring.2009,21(9):1263–1284.
[142] KrishnaVeni C, Rani T. On the classification of imbalanced datasets [J]. Interna-tional Journal of Computer Science&Technology.2011,2(SP1):145–148.
[143] Wang S, Yao X. Multiclass imbalance problems: analysis and potential solu-tions[J].IEEEtransactionsonsystems,man,andcybernetics.PartB,Cybernetics.2012,42(4):1119–1130.
[144] Chawla N V. C4.5and imbalanced data sets: investigating the effect of samplingmethod, probabilistic estimate, and decision tree structure [C]. In Proceedings ofthe International Conference on Machine Learning (Workshop on Learning fromImbalanced Datasets II).2003.
[145] Cieslak D A, Chawla N V. Learning decision trees for unbalanced data [C]. In Pro-ceedings of Principles of Data Mining and Knowledge Discovery.2008:241–256.
[146] Burez J, Van den Poel D. Handling class imbalance in customer churn predic-tion [J]. Expert Systems with Applications.2009,36(3):4626–4636.
[147] ZhouZ-H,LiuX-Y.Trainingcost-sensitiveneuralnetworkswithmethodsaddress-ing the class imbalance problem [J]. IEEE Transactions on Knowledge and DataEngineering.2006,18(1):63–77.
[148] Alejo R, Garcia V, Sotoca J, et al. Improving the performance of the RBF neuralnetworks trained with imbalanced samples [C]. In Proceedings of the9th Interna-tional Conference on Artificial Neural Networks.2007:162–169.
[149] Mazurowski M A, Habas P A, Zurada J M, et al. Training Neural Network Classi-fiers for Medical Decision Making: the Effects of Imbalanced Datasets on Classi-fication Performance [J]. Neural Networks.2008,21(2):427–436.
[150] AlejoR,SotocaJ,CasanG.Anempiricalstudyforthemulti-classimbalanceprob-lem with neural networks [C]. In Proceedings of the13th Iberoamerican Congresson Pattern Recognition.2008:479–486.
[151] Alejo R, Sotoca J, Casan G. The multi-class imbalance problem: cost functionswith modular and non-modular neural networks [C]. In Proceedings of the6thInternational Symposium on Neural Networks.2009:421–431.
[152] Palodeto V, Terenzi H, Marques J L B. Training neural networks for protein sec-ondary structure prediction: the effects of imbalanced data set [C]. In Proceedingsof the International Conference on Intelligent Computing.2009:258–265.
[153] Khoshgoftaar T M, Van Hulse J, Napolitano A. Supervised neural network mod-eling: an empirical investigation into learning from imbalanced data with labelingerrors [J]. IEEE transactions on Neural Networks.2010,21(5):813–830.
[154] Alejo R, Sotoca J, Garcia V, et al. Back propagation with balanced MSE costfunction and nearest neighbor editing for handling class overlap and class imbal-ance [C]. In Proceedings of the11th International Work-Conference on ArtificialNeural Networks.2011:199–206.
[155] Oh S-H. Error back-propagation algorithm for classification of imbalanceddata [J]. Neurocomputing.2011,74(6):1058–1061.
[156] Hwang J P, Park S, Kim E. A new weighted approach to imbalanced data classifi-cation problem via support vector machine with quadratic cost function [J]. ExpertSystems with Applications.2011,38(7):8580–8585.
[157] Hsu C-C, Wang K-S, Chang S-H. Bayesian decision theory for support vector ma-chines: imbalance measurement and feature optimization [J]. Expert Systems withApplications.2011,38(5):4698–4704.
[158] Tang Y-C, Zhang Y-Q, Chawla N V, et al. SVMs modeling for highly imbalancedclassification [J]. IEEE Transactions on Systems, Man, and Cybernetics. Part B,Cybernetics.2009,39(1):281–288.
[159] Fernández A, del Jesus M J, Herrera F. On the2-tuples based genetic tuning per-formance for fuzzy rule based classification systems in imbalanced datasets [J].Information Sciences.2010,180(8):1268–1291.
[160] Fernández A, del Jesus M J, Herrera F. Multi-class imbalanced dataSets with lin-guistic fuzzy rule based classification systems based on pairwise learning [C]. InProceedings of Information Processing and Management of Uncertainty.2010:89–98.
[161] Huang G-B, Zhou H-M, Ding X-J, et al. Extreme learning machine for regressionand multiclass classification [J]. IEEE Transactions on Systems, Man, and Cyber-netics. Part B, Cybernetics.2012,42(2):513–529.
[162] Deng W-Y, Zheng Q-H, Chen L. Regularized extreme learning machine [C]. InProceedingsoftheIEEESymposiumonComputationalIntelligenceandDataMin-ing.2009:389–395.
[163] Chacko B P, Vimal Krishnan V R, Raju G, et al. Handwritten character recognitionusing wavelet energy and extreme learning machine [J]. International Journal ofMachine Learning and Cybernetics.2011,3(2):149–161.
[164] Savitha R, Suresh S, Sundararajan N. Fast learning circular complex-valued ex-treme learning machine (CC-ELM) for real-valued classification problems [J]. In-formation Sciences.2012,187(1):277–290.
[165] Huang G-B, Ding X-J, Zhou H-M. Optimization Method based extreme learningmachine for classification [J]. Neurocomputing.2010,74(1-3):155–163.
[166] Deb K, Member A, Pratap A, et al. A fast and elitist multiobjective genetic algo-rithm: NSGA-II [J]. IEEE Transaction on Evolutionary Computation.2002,6(2):182–197.
[167] Sun Y, Kamel M S, Wong A K, et al. Cost-sensitive boosting for classification ofimbalanced data [J]. Pattern Recognition.2007,40(12):3358–3378.
[168] Viktor H L, Guo H. Multiple classifier prediction improvements against im-balanced datasets through added synthetic examples [C]. In Proceedings of theInternational Workshop on Structural and Syntactic Pattern Recognition.2004:974–982.
[169] Gao M, Hong X, Chen S, et al. A Combined SMOTE and PSO based RBF Clas-sifier for two-class imbalanced problems [J]. Neurocomputing.2011,74(17):3456–3466.
[170] Liu X-Y, Wu J-X, Zhou Z-H. Exploratory undersampling for class-imbalancelearning [J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cy-bernetics.2009,39(2):539–550.
[171] Lin S-C, Chang Y-C I, Yang W-N. Meta-learning for imbalanced data and clas-sification ensemble in binary classification [J]. Neurocomputing.2009,73(3):484–494.
[172] Schapire R. The boosting approach to machine learning: an overview [C]. In Pro-ceedingsoftheMSRIWorkshoponNonlinearEstimationandClassification.2002:149–172.
[173] PratiR,BatistaG,MonardM.Learningwithclassskewsandsmalldisjuncts[C].InProceedingsoftheBrazilianSymposiumonArtificialIntelligence.2004:296–306.
[174] Wilson D. Asymptotic properties of nearest neighbor rules using edited data [J].IEEE Transactions on Systems, Man and Cybernetics.1972,2(3):408–421.
[2] Yang-MaoS-F,ChanY-K,ChuY-P.Edgeenhancementnucleusandcytoplastcon-tour detector of cervical smear images [J]. IEEE Transactions on Systems, Man,and Cybernetics.2008,38(2):353–366.
[3] Rigon A, Soda P, Zennaro D, et al. Indirect immunofluorescence in autoimmunediseases: assessment of digital images for diagnostic purpose [J]. Cytometry PartB: Clinical Cytometry.2007,72(6):472–477.
[4]谢凤英,姜志国.基于最大方差的免疫细胞图像双阈值分割[J].中国体视学与图像分析.2007,12(1):59–61.
[5] Lin Z. The cell image segmentation based on the K-L transform and OtsuMethod [C]. In Proceedings of the International Conference on Multimedia andSignal Processing.2011:25–28.
[6] Sahoo P, Arora G. A thresholding method based on two-dimensional Renyi’s en-tropy [J]. Pattern Recognition.2004,37(6):1149–1161.
[7]魏伟一.基于最大区域互信息量的生物细胞图像分割[J].西北师范大学学报:自然科学版.2010,46(3):44–46.
[8] Bruzzese D, Giani U. Automatic multilevel thresholding based on a fuzzy entropymeasure [M]//Bruzzese D, Giani U. Classification and Multivariate Analysis forComplex Data Structures. Springer,2011:2011:125–133.
[9]王任挥.基于最大信息熵原理的显微细胞图像多阈值分割算法[J].内蒙古科技与经济.2010(18):58–60.
[10] EspinozaE,MartinezG,FrerichsJ,etal.Cellclustersegmentationbasedonglobaland local thresholding forin-situ microscopy [C]. In Proceedings of the3rd IEEEInternationalSymposiumonBiomedicalImaging:NanotoMacro.2006:542–545.
[11]马保国，乔玲玲，贾寅波．基于局部自适应闽值的细胞图像分割方法[J]．计算机应用研究．2009，26(2)：755–756．
[12] PlissitiM,NikouC,CharchantiA.AccuratelocalizationofcellnucleiinPapsmearimages using gradient vector flow deformable models [C]. In Proceedings of the3rdInternationalConferenceonBio-inspiredSignalsandSystems.2010:284–289.
[13] Harandi N, Sadri S, Moghaddam N, et al. An automated method for segmentationof epithelial cervical cells in images of ThinPrep [J]. Journal of Medical Systems.2010,34(6):1043–1058.
[14] Sauvola J, Pietik inen M. Adaptive document image binarization [J]. PatternRecognition.2000,33(2):225–236.
[15] Bradbury L, Wan J. A spectral k-means approach to bright-field cell image seg-mentation [C]. In Proceedings of the International Conference of the IEEE Engi-neering in Medicine and Biology Society.2010:4748–4751.
[16] Theera-UmponN.Whitebloodcellsegmentationandclassificationinmicroscopicbone marrow images [C]. In Proceedings of Fuzzy Systems and Knowledge Dis-covery.2005:787–796.
[17] Chaira T. A novel intuitionistic fuzzy c means color clustering on human cell im-ages [C]. In Proceedings of the World Congress on Nature&Biologically InspiredComputing.2009:736–741.
[18] KongH,GurcanM, Belkacem-BoussaidK.Partitioninghistopathologicalimages:an integrated framework for supervised color-texture segmentation and cell split-ting [J]. IEEE Transactions on Medical Imaging.2011,30(9):1661–1677.
[19] Yin Z, Bise R, Chen M, et al. Cell segmentation in microscopy imagery usinga bag of local Bayesian classifiers [C]. In Proceedings of the IEEE InternationalSymposium on Biomedical Imaging: From Nano to Macro.2010:125–128.
[20]窦智宙，平子良，冯文兵．多分类支持向量机分割彩色癌细胞图像[J]．计算机工程与应用．2009，45(20)：236–239．
[21] Orozco-Monteagudo M, Sahli H, Mihai C, et al. A hybrid approach for Pap-Smearcell nucleus extraction [M]//Orozco-Monteagudo M, Sahli H, Mihai C, et al.Pattern Recognition. Springer,2011:2011:174–183.
[22] Orozco-Monteagudo M, Miha C, Sahli H, et al. Combined hierarchical watershedsegmentation and SVM classification for Pap-Smear cell nucleus extraction [J].Computing and Systems.2012,16(2):133–145.
[23] DiF,MaoyongC,ChangzhiL,etal.Wall-adherentcellssegmentationbasedonBPneural network [C]. In Proceedings of the3rd International Conference on Bioin-formatics and Biomedical Engineering.2009:1–4.
[24] Pan C, Park D, Yang Y, et al. Leukocyte image segmentation by visual attentionand extreme learning machine [J]. Neural Computing&Applications.2011,21:1217–1227.
[25] Feng C, Chen P. Blood cell image localized segmentation combining mean-shiftand ELM [C]. In Proceedings of the International Conference on Mechatronic Sci-ence, Electric Engineering and Computer.2011:2078–2081.
[26] WangM,ZhouX,LiF,etal.NovelcellsegmentationandonlineSVMforcellcyclephase identification in automated microscopy [J]. Bioinformatics.2008,24(1):94–101.
[27]刘应乾,曹茂永.基于Gabor滤波与区域生长的细胞分割[J].山东科技大学学报:自然科学版.2012,31(2):99–103.
[28] Mustafa N, Isa N, Mashor M. Automated multicells segmentation of ThinPrepimage Using modified seed based region growing algorithm [J]. Biomedical SoftComputing and Human Sciences.2009,14(2):41–47.
[29] Kim K, Song D, Woo Y. Nucleus segmentation and recognition of uterine cervicalpap-smears [C]. In Proceedings of the11th International Conference on RoughSets, Fuzzy Sets, Data Mining and Granular Computing.2007:153–160.
[30] PlissitiM,NikouC,CharchantiA.AutomateddetectionofcellnucleiinPapsmearimages using morphological reconstruction and clustering [J]. IEEE Transactionson Information Technology in Biomedicine.2011,15(2):233–241.
[31] Vincent L, Soille P. Watersheds in igital spaces: an efficient algorithm based onimmersion simulations [J]. IEEE Transactions on Pattern Analysis and MachineIntelligence.1991,13(6):583–598.
[32] Jiang K, Liao Q, Xiong Y. A novel white blood cell segmentation scheme based onfeature space clustering [J]. Soft Computing-A Fusion of Foundations, Method-ologies and Applications.2006,10(1):12–19.
[33] Chen W, Zhang X. A new watershed algorithm for cellular image segmenta-tion based on mathematical morphology [C]. In Proceedings of the InternationalConference on Machine Vision and Human-Machine Interface (MVHI).2010:653–656.
[34] Plissiti M, Nikou C, Charchanti A. Watershed-based segmentation of cell nucleiboundariesinPapsmearimages[C].InProceedingsofthe10thIEEEInternationalConference on Information Technology and Applications in Biomedicine.2010:1–4.
[35] Wang Y, Sun Y, Lin C, et al. Nerve cell segmentation via multi-scale gradient wa-tershed hierarchies [C]. In Proceedings of the28th Annual International Confer-enceoftheIEEEEngineeringinMedicineandBiologySociety.2006:4310–4313.
[36] Gonzalez R, Woods R. Digital Image Processing, third ed.[M]. Prentice-Hall,2008.
[37]赵英红,乔双,董丽华. Canny算子与数学形态学算子相结合实现胸水细胞的边缘提取[J].东北师大学报:自然科学版.2008,40(3):42–45.
[38] Yang-Mao S, Chen Y, Chan Y, et al. Gradient direction edge enhancement basednucleus and cytoplasm contour detector of cervical smear images [C]. In Proceed-ings of the International Conference on Medical Biometrics.2007:290–297.
[39] Lin C-H, Chan Y-K, Chen C-C. Detection and segmentation of cervical cell cyto-plast and nucleus [J]. International Journal of Imaging Systems and Technology.2009,19(3):260–270.
[40]王可佳,平子良,海鹰, et al.用改进的随机Hough变换检测胸水图像中的细胞[J].光电子.激光.2008,19(3):420–422.
[41] Hukkanen J, Hategan A, Sabo E, et al. Segmentation of cell nuclei from histologi-cal images by ellipse fitting [C]. In Proceedings of the European Signal ProcessingConference.2010:1219–1223.
[42] Vromen J, McCane B. Red blood cell segmentation from SEM images [C]. InProceedings of the24th International Conference Image and Vision ComputingNew Zealand.2009:44–49.
[43] KassM,WitkinA,TerzopoulosD.Snakes:activecontourmodels[J].InternationalJournal of Computer Vision.1988,1(4):321–331.
[44] Bamford P, Lovell B. Unsupervised cell nucleus segmentation with active con-tours [J]. Signal Processing.1998,71(2):203–213.
[45] Xu C, Prince J. Snakes, shapes, and gradient vector flow [J]. IEEE Transactionson Image Processing.2002,7(3):359–369.
[46] Zamani F, Safabakhsh R. An unsupervised GVF snake approach for white bloodcell segmentation based on nucleus [C]. In Proceedings of the8th InternationalConference on Signal Processing.2006:1–4.
[47] Ma ka M, Daněk O, Ortiz-de Solórzano C, et al. A two-phase segmentation of cellnuclei using fast level set-like algorithms [C]. In Proceedings of the ScandinavianConference on Image Analysis.2009:390–399.
[48] Yu W, Lee H, Hariharan S, et al. Level set segmentation of cellular images basedon topological dependence [C]. In Proceedings of the International Symposium onVisual Computing.2008:540–551.
[49] Jing-Feng M, Kai H, Shang-Lian B, et al. A new level set model for cell imagesegmentation [J]. Chinese Physics B.2011,20(2):028701.
[50] Sobrevilla P, Montseny E, Lerma E. A fuzzy-based automated cells detectionsystem for color Pap Smear tests–FACSDS [M]//Sobrevilla P, Montseny E,LermaE.FuzzySetsandTheirExtensions:Representation,AggregationandMod-els. Springer,2008:2008:657–674.
[51] Vaschetto F, Montseny E, Sobrevilla P, et al. THREECOND: an automated andunsupervised three colour fuzzy-based algorithm for detecting nuclei in cervicalPap smear images [C]. In Proceedings of the9th International Conference on In-telligent Systems Design and Applications.2009:1359–1364.
[52] NaL,Jian-XinL. Automatic colorimage segmentationbasedonanisotropicdiffu-sion and the application in cancer cell segmentation [C]. In Proceedings of the1stInternational Conference on Bioinformatics and Biomedical Engineering.2007:992–994.
[53] Lassouaoui N, Hamami L. Genetic algorithms and multifractal segmentation ofcervical cell images [C]. In Proceedings of the7th International Symposium onSignal Processing and Its Applications.2003:1–4.
[54] Al-Kofahi Y, Lassoued W, Lee W, et al. Improved automatic detection andsegmentation of cell nuclei in histopathology images [J]. IEEE Transactions onBiomedical Engineering.2010,57(4):841–852.
[55] KeuperM.HierarchicalMarkovRandomFieldsformastcellsegmentationinelec-tron microscopic recordings [C]. In Proceedings of the IEEE International Sym-posium on Biomedical Imaging: From Nano to Macro.2011.
[56] Nandy K, Gudla P, Lockett S. Automatic segmentation of cell nuclei in2D usingdynamicprogramming[C].InProceedingsof2ndWorkshoponMicrosopicImageAnalysis with Applications in Biology.2007.
[57] Cheng J, Rajapakse J. Segmentation of clustered nuclei with shape markers andmarkingfunction[J].IEEETransactionsonBiomedicalEngineering.2009,56(3):741–748.
[58] Jung C, Kim C. Segmenting clustered nuclei using H-minima transform-basedmarker extraction and contour parameterization [J]. IEEE Transactions onBiomedical Engineering.2010,57(10):2600–2604.
[59]傅蓉.细胞重叠与融合性图像的分离与分割技术研究[D].[S. l.]:广州:南方医科大学,2007.
[60] Jantzen J, Norup J, Dounias G, et al. Pap-smear benchmark data for pattern classi-fication[J].Proceedingsofthe1stEuropeanSymposiumonNature-inspiredSmartInformation Systems.2005:1–9.
[61] Plissiti M, Nikou C. Cervical cell classification based exclusively on nucleus fea-tures [C]. In Proceedings of the International Conference on Image Analysis andRecognition.2012:483–490.
[62] Marinakis Y, Marinaki M, Dounias G, et al. Intelligent and nature inspired opti-mization methods in medicine: the Pap smear cell classification problem [J]. Ex-pert Systems.2009,26(5):433–457.
[63]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):622–635.
[64] Ojala T, Pietikainen M, Harwood D. A comparative study of texture measureswith classification based on featured distributions [J]. Pattern Recognition Letters.1996,29(1):51–59.
[65] Haralick R, Shanmugam K, Dinstein I. Textural features for image classifica-tion [J]. IEEE Transactions on Systems, Man and Cybernetics.1973,3(6):610–621.
[66] Li X, Hu W, Zhang Z, et al. Heat kernel based local binary pattern for face repre-sentation [J]. IEEE Signal Processing Letters.2010,17(3):308–311.
[67] Bur in K, Vasif N. Down syndrome recognition using local binary patterns andstatistical evaluation of the system [J]. Expert Systems with Applications.2011,38(7):8690–8695.
[68] HuangX,ZhaoG,ZhengW,etal.Spatiotemporallocalmonogenicbinarypatternsfor facial expression recognition [J]. IEEE Signal Processing Letters.2012,19(5):243–246.
[69] Shen L, Jia S, Ji Z, et al. Extracting local texture features for image-based coinrecognition [J]. IET Image Processing.2011,5(5):394–401.
[70] Janney P, Geers G. Texture classification using invariant features of local tex-tures [J]. IET Image Processing.2010,4(3):158–171.
[71] Materka A, Strzelecki M, et al. Texture analysis methods: a review [R].1998.
[72] Randen T, Husoy J. Filtering for texture classification: a comparative study [J].IEEE Transactions on Pattern Analysis and Machine Intelligence.1999,21(4):291–310.
[73] Lam E, Goodman J. A mathematical analysis of the DCT coefficient distributionsfor images [J]. IEEE Transactions on Image Processing.2000,9(10):1661–1666.
[74] Zhou F, Feng J, Shi Q. Texture feature based on local Fourier transform [C]. InProceedingsoftheInternationalConferenceonImageProcessing.2001:610–613.
[75]张志龙,李吉成,沈振康.基于局部沃尔什变换的纹理特征提取方法研究[J].信号处理.2005,21(6):589–596.
[76] Movellan J. Tutorial on gabor filters [R].2008.
[77] Wiskott L, Fellous J, Kuiger N, et al. Face recognition by elastic bunch graphmatching [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.1997,19(7):775–779.
[78] Liu C, Wechsler H. Gabor feature based classification using the enhanced fisherlinear discriminant model for face recognition [J]. IEEE Transactions on Imageprocessing.2002,11(4):467–476.
[79] Pavlidis T. Structural descriptions and graph grammars [C]. In Pictorial Informa-tion Systems.1980:86–103.
[80] Soille P. Morphological image analysis: principles and applications [M]. Springer-Verlag New York, Inc.,2003.
[81] Walker R, Jackway P, Lovell B, et al. Classification of cervical cell nuclei usingmorphological segmentation and textural feature extraction [C]. In Proceedings ofthe1994Second Australian and New Zealand Conference on Intelligent Informa-tion Systems.1994:297–301.
[82] Walker R, Jackway P, Lovell B. Cervical cell classification via co-occurrence andMarkov random field features [C]. In Proceedings of Digital Image Computing:Techniques and Applications.1995:294–299.
[83]张培培,陈德运,包振健.基于共生矩阵和分形的彩色骨髓细胞图像纹理[J].哈尔滨理工大学学报.2008,13(1):46–49.
[84]赵晖,鲍莉,梁光明, et al.基于综合灰度共生矩阵的显微细胞图像纹理研究[J].自动化技术与应用.2005,23(10):27–29.
[85] Nanni L, Lumini A, Brahnam S. Local binary patterns variants as texture descrip-torsformedicalimageanalysis[J].Artificialintelligenceinmedicine.2010,49(2):117–125.
[86] PlissitiM,NikouC,CharchantiA.Combiningshape,textureandintensityfeaturesfor cell nuclei extraction in Pap smear images [J]. Pattern Recognition Letters.2011,32(6):838–853.
[87] Xu S, Sun N, Cao M. Wall-pasted cell segmentation based on circular Gabor filterbank [C]. In Proceedings of the International Conference on Wavelet Analysis andPattern Recognition.2007:1735–1741.
[88] CHO S, KIM J. Combining multiple neural networks by fuzzy integral for robustclassification [J]. IEEE Transactions on Systems, Man, and Cybernetics.1995,25(2):380–384.
[89] Kittler J, Hatef M, Duin R, et al. On combining classifiers [J]. IEEE Transactionson Pattern Analysis and Machine Intelligence.1998,20(3):226–239.
[90] Kumar A, Kanhangad V, Zhang D. A new framework for adaptive multimodalbiometrics management [J]. IEEE Transactions on Information Forensics and Se-curity.2010,5(1):92–102.
[91] Chawla N V, Bowyer K W, Hall L O, et al. SMOTE: synthetic minority over-sampling technique [J]. Journal of Artificial Intelligence Research.2002,16:321–357.
[92] DrownD,KhoshgoftaarT,NarayananR.Usingevolutionarysamplingtomineim-balanced data [C]. In Proceedings of the6th International Conference on MachineLearning and Applications.2007:363–368.
[93] Yen S, Lee Y. Cluster-based under-sampling approaches for imbalanced data dis-tributions [J]. Expert Systems with Applications.2009,36(3):5718–5727.
[94] Pazzani M, Merz C, Murphy P, et al. Reducing misclassification costs [C]. InProceedings of the11th International Conference on Machine Learning.1994:217–225.
[95] Chen C, Liaw A, Breiman L. Using random forest to learn imbalanced data [R].2004.
[96] Chew H, Bogner R, Lim C. Dual-support vector machine with error rate andtraining size biasing [C]. In Proceedings of the IEEE International Conference onAcoustics, Speech, and Signal Processing.2001:1269–1272.
[97]谢纪刚,裘正定.非平衡数据集Fisher线性判别模型[J].北京交通大学学报:自然科学版.2006,30(5):15–18.
[98] Kotsiantis S, Pintelas P. Mixture of expert agents for handling imbalanced datasets[J].AnnalsofMathematics,Computing&Teleinformatics.2003,1(1):46–55.
[99] Chawla N, Lazarevic A, Hall L, et al. SMOTEBoost: improving prediction of theminority class in boosting [C]. In Proceedings of Principles of Data Mining andKnowledge Discovery.2003:107–119.
[100] Lee S. Noisy replication in skewed binary classification [J]. Computational Statis-tics&Data Analysis.2000,34(2):165–191.
[101] Wu H S, Gil J, Barba J. Optimal segmentation of cell images [J]. IEE Proceedingsof Vision, Image and Signal Processing.1998,145(1):50–56.
[102] Bamford P, Lovell B. A water immersion algorithm for cytological image seg-mentation [C]. In Proceedings of the APRS Image Segmentation Workshop.1996:75–79.
[103] Kale A, Aksoy S. Segmentation of cervical cell images [C]. In Proceedings of the20th IAPR International Conference on Pattern Recognition.2010:2399–2402.
[104] LinC-H,ChenC.Imagesegmentationbasedonedgedetectionandregiongrowingfor Thinprep cervical smear [J]. International Journal of Pattern Recognition andArtificial Intelligence.2010,24(7):1061–1089.
[105] Buades A, Coll B, Morel J. Self-similarity-based image denoising [J]. Communi-cations of the ACM.2011,54(5):109–117.
[106] Rubner Y, Tomasi C. Perceptual metrics for image database navigation [M].Springer,2000.
[107] Cheng H, Jiang X, Sun Y, et al. Color image segmentation: advances andprospects [J]. Pattern Recognition.2001,34(12):2259–2281.
[108] Yu J, Tan J, Wang Y. Ultrasound speckle reduction by a SUSAN-controlledanisotropic diffusion method [J]. Pattern Recognition.2010,43(9):3083–3092.
[109] Tomasi C, Manduchi R. Bilateral filtering for gray and color images [C]. In Pro-ceedings of the6th International Conference on Computer Vision.1998:839–846.
[110] Wang Z, Bovik A, Sheikh H, et al. Image quality assessment: from error visibilityto structural similarity [J]. IEEE Transactions on Image Processing.2004,13(4):600–612.
[111] Sezgin M, et al. Survey over image thresholding techniques and quantitative per-formance evaluation [J]. Journal of Electronic Imaging.2004,13(1):146–168.
[112] Zacharia E, Kostopoulou E, Maroulis D, et al. A spot segmentation approach for2D gel electrophoresis images based on2D histograms [C]. In Proceedings of the20th IAPR International Conference on Pattern Recognition.2010:2540–2543.
[113] Wang N, Li X, Chen X. Fast three-dimensional Otsu thresholding with shuffledfrog-leapingalgorithm[J].PatternRecognitionLetters.2010,31(13):1809–1815.
[114] Zijdenbos A, Dawant B, Margolin R, et al. Morphometric analysis of white matterlesions in MR images: method and validation [J]. IEEE Transactions on MedicalImaging.1994,13(4):716–724.
[115] LiuL,FieguthP.Textureclassificationfromrandomfeatures[J].IEEEtransactionson Pattern Analysis and Machine Intelligence.2012,34(3):574–586.
[116] JRouco, Mosquera A, Penedo M, et al. Texture description in local scale usingtexton histograms with quadrature filter universal dictionaries [J]. IET ComputerVision.2011,5(4):211–221.
[117] Zhu C, Wang R. Local multiple patterns based multiresolution gray-scale androtation invariant texture classification [J]. Information Sciences.2012,187(3):93–108.
[118] Huang X, Li S, Wang Y. Shape localization based on statistical method using ex-tended local binary pattern [C]. In Proceedings of the3rd International Conferenceon Image and Graphics.2004:184–187.
[119]冯贵玉.人脸与掌纹识别的子空间特征提取方法研究[D].[S. l.]:长沙:国防科学技术大学,2007.
[120] He X, Yan S, Hu Y, et al. Face recognition using laplacian faces [J]. IEEE Trans-actions on Pattern Analysis and Machine Intelligence.2005,27(3):328–340.
[121] Yang J, Zhang D, Frangi A, et al. Two-dimensional PCA: a new approach toappearance-based face representation and recognition [J]. IEEE Transactions onPattern Analysis and Machine Intelligence.2004,26(1):131–137.
[122] Ojala T, Pietikainen M, Maenpaa T. Multiresolution gray-scale and rotation in-variant texture classification with local binary patterns [J]. IEEE Transactions onPattern Analysis and Machine Intelligence.2002,24(7):971–987.
[123] Liao S, Chung A. Face recognition by using elongated local binary patterns withaverage maximum distance gradient magnitude [C]. In Proceedings of Asian Con-ference on Computer Vision.2007:672–679.
[124] M enp T, Pietik inen M. Multi-scale binary patterns for texture analysis [C]. InProceedings of the Scandinavian Conference on Image Analysis.2003:885–892.
[125] Tan X, Triggs B. Enhanced local texture feature sets for face recognition underdifficult lighting conditions [J]. IEEE Transactions on Image Processing.2010,19(6):1635–1650.
[126] Grinstead C, Snell J. Introduction to probability [M]. American Mathematical So-ciety,2006.
[127] Ojala T, M enp T, Pietik inen M, et al. Outex: new framework for empiricalevaluation of texture analysis algorithms [C]. In Proceedings of the16th Interna-tional Conference on Pattern Recognition.2002:701–706.
[128] Caputo B, Hayman E, Fritz M, et al. Classifying materials in the real world [J].Image and Vision Computing.2010,28(1):150–163.
[129] Chang C, Lin C. LIBSVM: a library for support vector machines [J]. ACM Trans-actions on Intelligent Systems and Technology.2011,2(3):1–39.
[130] Vapnik V. The nature of statistical learning theory [M]. springer,1999.
[131] Platt J, et al. Probabilistic outputs for support vector machines and comparisons toregularized likelihood methods [J]. Advances in Large Margin Classifiers.1999,10(3):61–74.
[132] Gonen M, Tanugur A, Alpaydm E. Multiclass posterior probability support vectormachines [J]. IEEE Transactions on Neural Networks.2008,19(1):130–139.
[133] Wu T, Lin C, Weng R. Probability estimates for multi-class classification by pair-wise coupling [J]. The Journal of Machine Learning Research.2004,5:975–1005.
[134] Huang G-B, Wang D-H, Lan Y. Extreme learning machines: a survey [J]. Interna-tional Journal of Machine Learning and Cybernetics.2011,2(2):107–122.
[135] Huang G-B, Zhu Q-Y, Siew C-K. Extreme learning machine: theory and applica-tions [J]. Neurocomputing.2006,70(1):489–501.
[136] Serre D. Matrices: Theory and applications [M]. Springer Verlag,2010.
[137] ChawlaNV.Dataminingforimbalanceddatasets:anoverview[M]//ChawlaNV.Data Mining and Knowledge Discovery Handbook. Springer,2010:2010:875–886.
[138] Weiss G M. Mining with rarity: a unifying framework [J]. ACM SIGKDD Explo-rations.2004,6(1):7–19.
[139] Kotsiantis S, Kanellopoulos D, Pintelas P. Handling imbalanced datasets: a re-view [J]. GESTS International Transactions on Computer Science and Engineer-ing.2006,30(1):25–36.
[140] Guo X-J, Yin Y-L, Dong C-L, et al. On the class imbalance problem [C]. InProceedings of the4th International Conference on Natural Computation.2008:192–201.
[141] He H-B, Garcia E A. Learning from imbalanced data [J]. IEEE Transactions onKnowledge and Data Enginerring.2009,21(9):1263–1284.
[142] KrishnaVeni C, Rani T. On the classification of imbalanced datasets [J]. Interna-tional Journal of Computer Science&Technology.2011,2(SP1):145–148.
[143] Wang S, Yao X. Multiclass imbalance problems: analysis and potential solu-tions[J].IEEEtransactionsonsystems,man,andcybernetics.PartB,Cybernetics.2012,42(4):1119–1130.
[144] Chawla N V. C4.5and imbalanced data sets: investigating the effect of samplingmethod, probabilistic estimate, and decision tree structure [C]. In Proceedings ofthe International Conference on Machine Learning (Workshop on Learning fromImbalanced Datasets II).2003.
[145] Cieslak D A, Chawla N V. Learning decision trees for unbalanced data [C]. In Pro-ceedings of Principles of Data Mining and Knowledge Discovery.2008:241–256.
[146] Burez J, Van den Poel D. Handling class imbalance in customer churn predic-tion [J]. Expert Systems with Applications.2009,36(3):4626–4636.
[147] ZhouZ-H,LiuX-Y.Trainingcost-sensitiveneuralnetworkswithmethodsaddress-ing the class imbalance problem [J]. IEEE Transactions on Knowledge and DataEngineering.2006,18(1):63–77.
[148] Alejo R, Garcia V, Sotoca J, et al. Improving the performance of the RBF neuralnetworks trained with imbalanced samples [C]. In Proceedings of the9th Interna-tional Conference on Artificial Neural Networks.2007:162–169.
[149] Mazurowski M A, Habas P A, Zurada J M, et al. Training Neural Network Classi-fiers for Medical Decision Making: the Effects of Imbalanced Datasets on Classi-fication Performance [J]. Neural Networks.2008,21(2):427–436.
[150] AlejoR,SotocaJ,CasanG.Anempiricalstudyforthemulti-classimbalanceprob-lem with neural networks [C]. In Proceedings of the13th Iberoamerican Congresson Pattern Recognition.2008:479–486.
[151] Alejo R, Sotoca J, Casan G. The multi-class imbalance problem: cost functionswith modular and non-modular neural networks [C]. In Proceedings of the6thInternational Symposium on Neural Networks.2009:421–431.
[152] Palodeto V, Terenzi H, Marques J L B. Training neural networks for protein sec-ondary structure prediction: the effects of imbalanced data set [C]. In Proceedingsof the International Conference on Intelligent Computing.2009:258–265.
[153] Khoshgoftaar T M, Van Hulse J, Napolitano A. Supervised neural network mod-eling: an empirical investigation into learning from imbalanced data with labelingerrors [J]. IEEE transactions on Neural Networks.2010,21(5):813–830.
[154] Alejo R, Sotoca J, Garcia V, et al. Back propagation with balanced MSE costfunction and nearest neighbor editing for handling class overlap and class imbal-ance [C]. In Proceedings of the11th International Work-Conference on ArtificialNeural Networks.2011:199–206.
[155] Oh S-H. Error back-propagation algorithm for classification of imbalanceddata [J]. Neurocomputing.2011,74(6):1058–1061.
[156] Hwang J P, Park S, Kim E. A new weighted approach to imbalanced data classifi-cation problem via support vector machine with quadratic cost function [J]. ExpertSystems with Applications.2011,38(7):8580–8585.
[157] Hsu C-C, Wang K-S, Chang S-H. Bayesian decision theory for support vector ma-chines: imbalance measurement and feature optimization [J]. Expert Systems withApplications.2011,38(5):4698–4704.
[158] Tang Y-C, Zhang Y-Q, Chawla N V, et al. SVMs modeling for highly imbalancedclassification [J]. IEEE Transactions on Systems, Man, and Cybernetics. Part B,Cybernetics.2009,39(1):281–288.
[159] Fernández A, del Jesus M J, Herrera F. On the2-tuples based genetic tuning per-formance for fuzzy rule based classification systems in imbalanced datasets [J].Information Sciences.2010,180(8):1268–1291.
[160] Fernández A, del Jesus M J, Herrera F. Multi-class imbalanced dataSets with lin-guistic fuzzy rule based classification systems based on pairwise learning [C]. InProceedings of Information Processing and Management of Uncertainty.2010:89–98.
[161] Huang G-B, Zhou H-M, Ding X-J, et al. Extreme learning machine for regressionand multiclass classification [J]. IEEE Transactions on Systems, Man, and Cyber-netics. Part B, Cybernetics.2012,42(2):513–529.
[162] Deng W-Y, Zheng Q-H, Chen L. Regularized extreme learning machine [C]. InProceedingsoftheIEEESymposiumonComputationalIntelligenceandDataMin-ing.2009:389–395.
[163] Chacko B P, Vimal Krishnan V R, Raju G, et al. Handwritten character recognitionusing wavelet energy and extreme learning machine [J]. International Journal ofMachine Learning and Cybernetics.2011,3(2):149–161.
[164] Savitha R, Suresh S, Sundararajan N. Fast learning circular complex-valued ex-treme learning machine (CC-ELM) for real-valued classification problems [J]. In-formation Sciences.2012,187(1):277–290.
[165] Huang G-B, Ding X-J, Zhou H-M. Optimization Method based extreme learningmachine for classification [J]. Neurocomputing.2010,74(1-3):155–163.
[166] Deb K, Member A, Pratap A, et al. A fast and elitist multiobjective genetic algo-rithm: NSGA-II [J]. IEEE Transaction on Evolutionary Computation.2002,6(2):182–197.
[167] Sun Y, Kamel M S, Wong A K, et al. Cost-sensitive boosting for classification ofimbalanced data [J]. Pattern Recognition.2007,40(12):3358–3378.
[168] Viktor H L, Guo H. Multiple classifier prediction improvements against im-balanced datasets through added synthetic examples [C]. In Proceedings of theInternational Workshop on Structural and Syntactic Pattern Recognition.2004:974–982.
[169] Gao M, Hong X, Chen S, et al. A Combined SMOTE and PSO based RBF Clas-sifier for two-class imbalanced problems [J]. Neurocomputing.2011,74(17):3456–3466.
[170] Liu X-Y, Wu J-X, Zhou Z-H. Exploratory undersampling for class-imbalancelearning [J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cy-bernetics.2009,39(2):539–550.
[171] Lin S-C, Chang Y-C I, Yang W-N. Meta-learning for imbalanced data and clas-sification ensemble in binary classification [J]. Neurocomputing.2009,73(3):484–494.
[172] Schapire R. The boosting approach to machine learning: an overview [C]. In Pro-ceedingsoftheMSRIWorkshoponNonlinearEstimationandClassification.2002:149–172.
[173] PratiR,BatistaG,MonardM.Learningwithclassskewsandsmalldisjuncts[C].InProceedingsoftheBrazilianSymposiumonArtificialIntelligence.2004:296–306.
[174] Wilson D. Asymptotic properties of nearest neighbor rules using edited data [J].IEEE Transactions on Systems, Man and Cybernetics.1972,2(3):408–421.