基于变化方向光源的压印立体字符分割方法的研究
|
摘要
在工业应用中,有些物体表面的字符是依靠表面的变形作为标记。这些立体字符不是通过色差成像,而是通过字符区域同背景区域对光线的反射不同成像。由于压印立体字符具有三维特征,因此很难实现照明、分割以及后续的检测识别。随着自动视觉检测技术的发展,对这些字符识别的准确性提出了更高的要求,其中的关键之一则是将其从背景图像中分割出来。在对如何利用压印立体字符的三维特征实现分割的研究中,国外有些学者提出了一些分割方法,而国内的研究大都还集中在基于二维灰度图像的分割基础上基于此问题,本文在变化方向光源的条件下,根据字符的立体特征提出了三种不同的分割方法,具体的研究工作如下：
首先,针对压印立体字符在不同方向光源照射下表现出不同状态的特点,在建立光照空间模型的指导下,基于散射光源与方向光源条件下采集图像的清晰度比对,指出了单一方向光源采集三维物体表面的二维灰度图像时包含深度信息不充分的局限性,提出利用变化方向光源照射下采集到的物体表面二维灰度图像彼此间的关系提取表面法向量特征以进行后续分割的方案。经过对光源方向的优化,确定了光照偏角的分布(分别为0°、90°、180°和270°)和最佳倾角的数值(63.43°),设计了以照明光源、图像采集设备和四方向光源同步照明采集电路为核心的图像采集系统。
在此基础上利用二阶多项式拟合平面消除了背景光不均匀性,采用直方图规定化的方法使图像的灰度等级一致,增强了序列图像的对比度,从而提高了法向量计算的精确性,为后续压印立体字符分割方法的研究奠定了条件和基础。
接下来基于四光源光照采集系统,提出了三种不同的分割压印立体字符的方法：
在基于表面纹理的分割方法中,针对压印字符表面的立体特征,首次提出了基于表面法向量的纹理特征的概念；在LBP算子的基础上引入了模糊集合的理论,提出了基于模糊化表面法向量LBP (Fuzzy-SNLBP)算子纹理特征的分割方法,并对Fuzzy-SNLBP算子中的各项参数对分割结果的影响进行了分析。通过比较实验发现：Fuzzy SNLBP比SNLBP具有更大的信息量；模糊化可有效改善SNLBP计算时的抗噪性；Fuzzy SNLBP比使用灰度值的LBP方法以及固定阈值的SNLBP方法具有更好的纹理分辨能力。
在基于表面法向量和图论聚类的图像分割方法研究中,将表面三维特征引入了图论的分割方法中,构建了基于表面法向量特征的图,提出了简单可行的图论聚类的分割算法。在具体分割过程中,又将反馈控制的思想引入了图像分割系数的优化过程：将二值图像的二维信息熵作为分割质量的检测评价标准并引入反馈来调节分割系数,得到了最优的分割结果(分割系数k=64时,二值图像二维信息熵S=2.0681为最小值)；
在基于PCNN和四方向光源图像融合技术的压印立体字符分割方法的研究中,提出了不需要对原始图像进行光照强度一致化处理的简单的分割方法：首先使用脉冲耦合神经网络(PCNN)提取出压印立体字符在四方向光源条件下获取的二维灰度图像中的高亮区域；然后通过图像融合的方式,得到分割完整的二值图像进行后续识别。研究中还建立了分割字符的评价标准,并以此来动态调节PCNN模型的参数,通过实验确定了最佳的分割参数。
最后采用了受试者工作特征曲线(ROC)和字符的识别率,分别对三种分割算法的字符分割效果进行了评价。评价结果表明：基于四光源的图像分割技术的三种分割算法,其识别率都高于基于单独光源的图像分割方法,可见四光源的图像分割较单一光源的图像分割更具优势。三种分割方法中,基于图论聚类的分割方法识别率最高,但执行时间也最长；基于PCNN的方法识别率最低,但执行时间最短；基于纹理的分割方法执行时间和识别率居中。在实际应用中可根据需要加以选择。
In the process of industrial applications, there is a great variety of identification marks on different materials to be detected.The work pieces, representing surface deformations, are required in many production processes as durable markings.These embossed characters is recorded not by colour difference, but through the different reflection of light between character region and background region.Because of their three-dimensional structure, characters created this way are often difficult to illuminate, to segment and, consequently, to detect. With the development of automatic vision inspection, it has put forward higher requirements for the accuracy of the character recognition.The segmentation of embossed characters from the background image plays an important role in the recognition system. In the study of how to make use of the3D feature of embossed characters to achieve segmentation, some overseas scholars have presented some new segmentation methods, while the domestic research is still concentrated in the segmentation based on two-dimensional gray-scale image.Three different segmentation methods is proposed in this paper according to the three-dimensional feature of character segmentation, based on variable illumination direction.The main research is as follows:
Firstly, in the Illumination space, by clarity comparison of image acquired in diffuse illumination and directional illumination, directional illumination is more appropriate to inspect3D embossed characters. However, this kind of3D embossed characters presents a different appearance under different illumination directions. So the depth information is inadequate with2D gray image in single direction acquisition for3D object surface. The scheme is proposed that extract surface normal vector feature using the relationship between two-dimensional surface gray image in variable illumination direction for subsequent segmentation.After optimization of the direction of the light source, the light azimuth angle distribution (0°,90°,180°and270°) and the optimum elevation angle (63.43degrees) is determined.The image acquisition system is designed with lighting, image acquisition device and the four direction of light source synchronous lighting acquisition circuit.
The background lighting difference is removed using polynomial regression planes, and gray level uniform between images is eliminated with histogram equalization.It improves the precision of surface vector calculation,laid a foundation for subsequent embossed characters segmentation.
Then, three different embossed stereo character segmentation methods are proposed based on four variable illumination direction systems.
In the segmentation method based on surface texture, the concept of texture features based on the surface normal vector is proposed.The fuzzy set theory is introduced to LBP operator, and Fuzzy-SNLBP operator segmentation method is proposed based on texture features.The influence of various parameters in Fuzzy-SNLBP to the segmentation results is analyzed. According to the comparison experiment:Fuzzy-SNLBP has more information than the SNLBP, fuzzy can effectively reduce the SNLBP calculation noise; Fuzzy-SNLBP is better in texture resolution than LBP method using the gray value and SNLBP with fixed threshold.
The segmentation method based on surface normal vector and the graph clustering is proposed.The graph is created based on surface normal and graph clustering segmentation algorithm is was executed.In the segmentation process, the feedback control theory is introduced to optimize image segmentation coefficient.The2D entropy of binary image as the segmentation quality evaluation criterion,the segmentation coefficient is adjust by the feedback control.The optimal segmentation result (segmentation coefficient k=64, when2D information entropy S=2.0681is the minimum value);
A simple segmentation method without illumination consistency processing for the original image is proposed based on pulse coupled neural network(PCNN) and image fusion.After extract the highlight of two-dimensional gray image acquired in variable illumination direction, through the image fusion method, get the segmentation of the complete binary image, its framework for subsequent recognition. The segmentation evaluation criterion for embossed stereo character are builded in this research, and the parameters of PCNN model are dynamic adjusted.Through the experiment determined the optimal segmentation parameters.
Finally, using the receiver operating characteristic curve (ROC) and the character recognition rate, each of the three segmentation algorithm for character segmentation results is evaluated. The evaluation results show that:three segmentation algorithm of3D embossed characters based on four variable illumination direction have more advantages than single light source.Their recognition rate is higher than other methods of image segmentation based on single light source.The character recognition rate based on graph theory clustering segmentation method is the highest, but the execution time is also the longest; identification method based on PCNN was the lowest, but the implementation of the shortest time; texture segmentation method execution time and recognition rate is centered on.It can be selected according to the need in practical application.
首先,针对压印立体字符在不同方向光源照射下表现出不同状态的特点,在建立光照空间模型的指导下,基于散射光源与方向光源条件下采集图像的清晰度比对,指出了单一方向光源采集三维物体表面的二维灰度图像时包含深度信息不充分的局限性,提出利用变化方向光源照射下采集到的物体表面二维灰度图像彼此间的关系提取表面法向量特征以进行后续分割的方案。经过对光源方向的优化,确定了光照偏角的分布(分别为0°、90°、180°和270°)和最佳倾角的数值(63.43°),设计了以照明光源、图像采集设备和四方向光源同步照明采集电路为核心的图像采集系统。
在此基础上利用二阶多项式拟合平面消除了背景光不均匀性,采用直方图规定化的方法使图像的灰度等级一致,增强了序列图像的对比度,从而提高了法向量计算的精确性,为后续压印立体字符分割方法的研究奠定了条件和基础。
接下来基于四光源光照采集系统,提出了三种不同的分割压印立体字符的方法：
在基于表面纹理的分割方法中,针对压印字符表面的立体特征,首次提出了基于表面法向量的纹理特征的概念；在LBP算子的基础上引入了模糊集合的理论,提出了基于模糊化表面法向量LBP (Fuzzy-SNLBP)算子纹理特征的分割方法,并对Fuzzy-SNLBP算子中的各项参数对分割结果的影响进行了分析。通过比较实验发现：Fuzzy SNLBP比SNLBP具有更大的信息量；模糊化可有效改善SNLBP计算时的抗噪性；Fuzzy SNLBP比使用灰度值的LBP方法以及固定阈值的SNLBP方法具有更好的纹理分辨能力。
在基于表面法向量和图论聚类的图像分割方法研究中,将表面三维特征引入了图论的分割方法中,构建了基于表面法向量特征的图,提出了简单可行的图论聚类的分割算法。在具体分割过程中,又将反馈控制的思想引入了图像分割系数的优化过程：将二值图像的二维信息熵作为分割质量的检测评价标准并引入反馈来调节分割系数,得到了最优的分割结果(分割系数k=64时,二值图像二维信息熵S=2.0681为最小值)；
在基于PCNN和四方向光源图像融合技术的压印立体字符分割方法的研究中,提出了不需要对原始图像进行光照强度一致化处理的简单的分割方法：首先使用脉冲耦合神经网络(PCNN)提取出压印立体字符在四方向光源条件下获取的二维灰度图像中的高亮区域；然后通过图像融合的方式,得到分割完整的二值图像进行后续识别。研究中还建立了分割字符的评价标准,并以此来动态调节PCNN模型的参数,通过实验确定了最佳的分割参数。
最后采用了受试者工作特征曲线(ROC)和字符的识别率,分别对三种分割算法的字符分割效果进行了评价。评价结果表明：基于四光源的图像分割技术的三种分割算法,其识别率都高于基于单独光源的图像分割方法,可见四光源的图像分割较单一光源的图像分割更具优势。三种分割方法中,基于图论聚类的分割方法识别率最高,但执行时间也最长；基于PCNN的方法识别率最低,但执行时间最短；基于纹理的分割方法执行时间和识别率居中。在实际应用中可根据需要加以选择。
In the process of industrial applications, there is a great variety of identification marks on different materials to be detected.The work pieces, representing surface deformations, are required in many production processes as durable markings.These embossed characters is recorded not by colour difference, but through the different reflection of light between character region and background region.Because of their three-dimensional structure, characters created this way are often difficult to illuminate, to segment and, consequently, to detect. With the development of automatic vision inspection, it has put forward higher requirements for the accuracy of the character recognition.The segmentation of embossed characters from the background image plays an important role in the recognition system. In the study of how to make use of the3D feature of embossed characters to achieve segmentation, some overseas scholars have presented some new segmentation methods, while the domestic research is still concentrated in the segmentation based on two-dimensional gray-scale image.Three different segmentation methods is proposed in this paper according to the three-dimensional feature of character segmentation, based on variable illumination direction.The main research is as follows:
Firstly, in the Illumination space, by clarity comparison of image acquired in diffuse illumination and directional illumination, directional illumination is more appropriate to inspect3D embossed characters. However, this kind of3D embossed characters presents a different appearance under different illumination directions. So the depth information is inadequate with2D gray image in single direction acquisition for3D object surface. The scheme is proposed that extract surface normal vector feature using the relationship between two-dimensional surface gray image in variable illumination direction for subsequent segmentation.After optimization of the direction of the light source, the light azimuth angle distribution (0°,90°,180°and270°) and the optimum elevation angle (63.43degrees) is determined.The image acquisition system is designed with lighting, image acquisition device and the four direction of light source synchronous lighting acquisition circuit.
The background lighting difference is removed using polynomial regression planes, and gray level uniform between images is eliminated with histogram equalization.It improves the precision of surface vector calculation,laid a foundation for subsequent embossed characters segmentation.
Then, three different embossed stereo character segmentation methods are proposed based on four variable illumination direction systems.
In the segmentation method based on surface texture, the concept of texture features based on the surface normal vector is proposed.The fuzzy set theory is introduced to LBP operator, and Fuzzy-SNLBP operator segmentation method is proposed based on texture features.The influence of various parameters in Fuzzy-SNLBP to the segmentation results is analyzed. According to the comparison experiment:Fuzzy-SNLBP has more information than the SNLBP, fuzzy can effectively reduce the SNLBP calculation noise; Fuzzy-SNLBP is better in texture resolution than LBP method using the gray value and SNLBP with fixed threshold.
The segmentation method based on surface normal vector and the graph clustering is proposed.The graph is created based on surface normal and graph clustering segmentation algorithm is was executed.In the segmentation process, the feedback control theory is introduced to optimize image segmentation coefficient.The2D entropy of binary image as the segmentation quality evaluation criterion,the segmentation coefficient is adjust by the feedback control.The optimal segmentation result (segmentation coefficient k=64, when2D information entropy S=2.0681is the minimum value);
A simple segmentation method without illumination consistency processing for the original image is proposed based on pulse coupled neural network(PCNN) and image fusion.After extract the highlight of two-dimensional gray image acquired in variable illumination direction, through the image fusion method, get the segmentation of the complete binary image, its framework for subsequent recognition. The segmentation evaluation criterion for embossed stereo character are builded in this research, and the parameters of PCNN model are dynamic adjusted.Through the experiment determined the optimal segmentation parameters.
Finally, using the receiver operating characteristic curve (ROC) and the character recognition rate, each of the three segmentation algorithm for character segmentation results is evaluated. The evaluation results show that:three segmentation algorithm of3D embossed characters based on four variable illumination direction have more advantages than single light source.Their recognition rate is higher than other methods of image segmentation based on single light source.The character recognition rate based on graph theory clustering segmentation method is the highest, but the execution time is also the longest; identification method based on PCNN was the lowest, but the implementation of the shortest time; texture segmentation method execution time and recognition rate is centered on.It can be selected according to the need in practical application.
引文
[1]蔡晋辉.实时自动视觉检测系统相关算法及应用研究[D].浙江大学博士论文,2005：6.
[2]贾云得.机器视觉[M].北京：科学出版社,2000.
[3]R.G.Casey,E.Lecolinent.A Survey of Methods and Strategies in Character Segmentation[J].IEEE trans.PAMI,1996,18(7):690-709.
[4]孙广玲.手写字符识别中关键技术研究[D].哈尔滨工业大学博士论文,2005:8.
[5]李建美,路长厚,李国平.基于Gabor变换的凹凸字符图像特征抽取新方法[J].系统仿真学报,2008,20(4):2133-2136.
[6]曹建海,路长厚,李磊.基于灰度图像的压印凸凹字符质量检测研究[J].光电子激光,2007(1),90-92.
[7]Christoph Lindner, Fernando Puente Leon.Model-Based Segmentation of Surfaces Using Illumination Series[J]. IEEE T. Instrumentation and Measurement,2007, 56(4):1340-1346.
[8]F. Puente Leon, C. Lindner, D. van Gorkom.Surface Segmentation by Variable Illumination[J].CIRP Annals-Manufacturing Technology,2007,56(1):549-552.
[9]Perez Grassi, Fernando Puente Leon.Translation and Rotation Invariant Histogram Features for Series of Images[J].GI Jahrestagung,2007,(1):38-43.
[10]Perez Grassi,Vadim Frolov,Fernando Puente Leon.Information fusion to detect and classify pedestrians using invariant features[J].Information Fusion.2011,12(4): 284-292.
[11]许新征,丁世飞,史忠植,贾伟宽.图像分割的新理论和新方法[J].电子学报.2010,2(2A)：76-81.
[12]何俊,葛红,王玉峰.图像分割算法研究综述[J].计算机工程与科学,2009,(12):58-61.
[13]章毓晋.图像分割[M].北京：科学出版社,2001.
[14]Serra J.,Mathematical Morphology [M].London,UK:Academic Press,1982.
[15]Victor O R,Juan I G L,Nicolas S L,Pedro G V.An improved watershed algorithm based on efficient computation of shortest paths[J].Pattern Recognition,2007,40(3): 1078-1090.
[16]E.Backer and A.Jain.A clustering Performance measure based on fuzzy set decomposition.[J].IEEE. Trans.Pattern Anal.Mach.Intel.,1981.3(1):66-75.
[17]Kanungo Tapas,Mount D.M.,Netanyahu N.S.,Piatko C.D.,Silverman, R.Wu A.Y..An efficient k-means clustering algorithm:analysis and implementation[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2002,24(7): 881-892.
[18]F.Hoppner,Klawonn,R.Kruse. Fuzzy cluster analysis:methods for classification, data analysis,and image recognition[M].1999:New York:wiley.
[19]R.Sharan and R.Shamir.CLICK.A clustering algorithm with applications to gene expression analysis[C].in 8th lnt.Conf.Intelligent. Systems for Molecular Biology.2000:307-316.
[20]A.Ben Hur,et al..A support vector clustering method[C].In 15th International Conference on Pattern Recognition, 2000,2:724-727.
[21]T.Kohonen.The self-organizing map[J].In Proceedings of the Institute of Electrical and Electronics Engineers.1990,78(9):1464-1480.
[22]I.Bloch. Information combination operators for data fusion:a comparative review with classification[J].IEEE Trans,on SMC,1996,26(1):52-67.
[23]S Fu,Q Ruan,W Wang.A feature-dependent fuzzy bidirectional flow for adaptive image sharpening[J].Neurocomputing,2007,70(4):883-895.
[24]Moghaddamzadeh A,Bourbakis N.,A Fuzzy Region Growing Approach for Segmentation of Color Images[J].Pattern Recognition,1997,30(6):867-881.
[25]张玲,基于模糊理论及其扩展的图像分割研究及应用[D].山东大学博士论文,2012：4.
[26]孙慧贤.基于纹理分析的视觉检测方法与应用研究[D].国防科大博士论文,2010：4.
[27]Tsai I,Lin C,Lin J.Applying an artificial neural network to pattern recognition[J]. Textile Research Journal,1995,65(3):123-130.
[28]Bodnarova A,Williams J,Bennamoun M,et al.Optimal textural features for flaw detection in textile materials[C].Proceedings of IEEE on Speech and Image Technologies for Computing and Telecommunications, Brishane, Australia, 1997,1:307-310.
[29]ShaPir L.G.,Stoekman G.C.,Computer vision[M].Pearson Education Inc.,2001: 235-247.
[30]Ojala T,Pietikainen M,Maenpaa T..Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J].IEEE.Transactions on Pattern Analysis and Machine Intelligence,2002,24(17):971-987.
[31]Monadjemi A..Towards Efficient Texture Classification and Abnormality Detection[D].United Kingdom:University of Bristol,2004:88-129.
[32]M. Niskanen, O. Silvenand H. Kauppinen.Color and texture based wood inspection with unsupervised clustering[C].Proceedings of the 12th Scandinavian Conference on Image Analysis,Bergen,Norway,2001:336-342.
[33]Maenpaa T,Turtinen M,Pietikainen M..Real-time surface in section by texture[J]. Real-Time Imaging,2003,9(5):289-296.
[34]M. Niskanen, H. Kauppinen and O. Silven.Real-time Aspects of SOM-based Visual Surface Inspection[C]. Proc. SPIE 4664,Machine Vision Applications in Industrial Inspection X,2002,123-134.
[35]Kauppinen, H.,Silven, O..The effect of illumination variations on color-based wood defect classification[J]. Pattern Recognition,1996,3:828-832.
[36]Chen C H,Pau L F,Wang P S P. Handbook of Pattern Recognition and Computer Vision(2nd edition)[M].Singapore:World Scientific,1999:207-248.
[37]CrossG C,Jain A K.Markov Random Field Texture Models[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 1983,5(1):25-39.
[38]Chellappa R,Chatterjee S.Classification of Textures Using Gaussian Markov Random Fields[J].IEEE Transactions on Acoustic,Speech and Signal Processing,1985,33(4):959-963.
[39]Krishnamachari S,Chellappa R.Multiresolution Gauss-Markov Random Field Models for Texture Segmentation[J].IEEE Transactions on Image Processing, 1997,6(2):251-267.
[40]Bharati M H,Liu J.J,Mac Gregor J F.Image texture analysis:methods and comparisons[J].Chemometrics and Intelligent Laboratory Systems,2004,2(1):57-71.
[41]Arof H,DeraviF.Circular neighbour hood and 1-D DFT features for texture classification and segmentation[J].IEEE Proceedings Vision, Image and Signal Processing,1998,145(3):167-172.
[42]Grigorescu S E,Petkov N.Kruizinga P.Comparison of Texture Features Based on Gabor Filters[J].IEEE Transactions on Image Processing,2002,11(10):1160-1167.
[43]Muneeswaran K.,Ganesan,Arumugam S.,et.al.Texture image segmentation using combined features from spatial and spectral distribution[J].Pattern Recognition Letters,2006,27(7):755-764.
[44]C. Julia, R.Moreno, D. Puig, M.A. Garcia.Image segmentation through graph-based clustering from surface normals estimated by photometric stereo[J].Electronics Letters,2010:64(2):134-135.
[45]Yuri Y. Boykov Marie-Pierre Jolly, Interactive graph cuts for optimal boundary& region segmentation of objects in N-D images[C]. Proceedings of International Conference on Computer Vision,2001:105-112.
[46]Moreno R.,Garcia M.A., Puig, D.,Graph-based perceptual segmentation of stereo vision 3D images at multiple abstraction levels[C].In proceeding of: Graph-Based Representations in Pattern Recognition,2007:148-157.
[47]Y. Boykov and V. Kolmogorov.An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision[J]. International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition,2001:359-374.
[48]V. Kolmogorov,R. Zabih.Computing visual correspondence with occlusions using graph cuts[C]. in International Conference on Computer Vision,2002,2:508-515.
[49]Y. Boykov, O. Veksler, and R. Zabih.Fast approximate energy minimization via graph cuts[J].Transactions on Pattern Analysis and Machine Intelligence,2001, 23(11):1222-1239.
[50]C.Zahn.Graph Theoretical Methods for Detecting and Describing Gestalt Clusters[J].IEEE Transactions on Computation.1971,20:68-86.
[51]Felzenszwalb P.,Huttenlocher D.Efficient graph-based image segmentation[J]. International Journal of Computer Vision.2004,59(2):167-181.
[52]Wu Z.,Leahy R..An optimal graph theoretic approach to data clustering:Theory and its application to image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1993,15(11):1101-1113.
[53]J.Shi and J.Malik.Normalized Cuts and Image Segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence.2000,22(8):888-905.
[54]Ding C.H.,Xiaofeng He, Hongyuan Zha,Ming Gu,Simon, H.D.A.. min-max cut algorithm for graph partitioning and data clustering[C]. Proceedings IEEE International Conference on Data Mining,2001:107-114.
[55]Wenbing Tao,Hai Jin,Yimin Zhang.Color Image Segmentation Based on Mean Shift and Normalized Cuts[J].Systems, Man, and Cybernetics,Part B:Cybernetics, IEEE Transactions on,2007,37(5):1382-1389.
[56]Vekslre O.Image segmentation by nested cuts [C].Proceedings of the IEEE on Conference Computer Vision and Pattern Recognition,2000,2:508-515.
[57]Wang S., Siskind J..Image segmentation with ratio cut[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(6):675-69.
[58]Grady L,Schwartz E. ISO perimetric graph partitioning for image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(3):469-475.
[59]Rout S.,Srivastava S.,Majumdar J.. Multi-model image segmentation using a modified hopfield neural network[J]. Patten Recognition,1998,31(6),743-750.
[60]Dekruger D.,Hunt B.R..Image processing and neural networks for recognition of cartographic area feature[J].Patten Recognition,1994,27(4):461-483.
[61]Wang D. L,Terman D..Image segmentation based on oscillatory correlation[J]. Normal Computation,1997,9:805-836.
[62]Vilarino D. L.,Brea V. M.,Cabello D..Discrete Time CNN for Image segmentation by active contours[J].Patten Recognition Letters,1998,19(8):721-734.
[63]Wang Y.,Adaii T.,Kung S. Y..Quantification and segmentation of rain tissues from MR images a probabilistic neural networks approach[J]. IEEE Transactions on Image Processing,1998,7(8):1-12.
[64]Coktepe M.,Yaiabik N.,Atalay V..Unsupervised segmentation of gray level Markov model textures with hierarchical self organizing map[C].Proceedings of the 13th International Conference on Pattern Recognition.USA:Institute of Electric and Electronic Engineer.1996:90-94.
[65]Kuntimad G,Ranganath H S.Perfect image segmentation using pulse coupled neural networks[J].IEEE Transactions on Neural Networks,1999,10(3):591-598.
[66]周俊武,孙传尧,王福利.径向基函数(RBF)网络的研究及实现[J].矿冶,2001,04：71-75.
[67]Kaski S., Kangas J.,Kohonen T.. Bibliography of self-organizing map (SOM) papers[J]. Neural Computing Surveys,1997,1:102-350.
[68]ZHANG Junying,FAN Xiuju,DONG Jiyang,SHI Meihon.Image segmentation based on modified pulse-coupled neural networks[J]. Chinese Journal of Electronics,2007,16(1):119-122.
[69]H.Berg,R.Olsson,T.Lindblad et al..Automatic design of pulse coupled neurons for image segmentation[J]. Neurocomputing, 2008,71(6):1980-1993.
[70]Zhu Shan,Ma Kaikuang. A New Diamond Search Algorithm for Fast Block Matching Motion Estimation[J].IEEE Trans, on Image Processing,2000, 9(2):287-290.
[71]Hsieh S L,Wang Hsing-Chih.Feature Extraction for Audio Finger printing Using Wavelet Transformation[J].Proc. of National Computer Symposium,2005:15-16.
[72]张明,毕笃彦.自适应可变模式搜索算法[J].计算机工程,2008,34(7):26-28.
[73]段青青,宋学瑞.一种H.264/AVC中的快速运动估计算法[J].计算机工程,2008,34(16)：244-246.
[74]Ghosal S etc.Range Surface Characterization and Segmentation Using Neural Networks[J].Pattern Recognition.1995,28(5):711-727.
[75]P.J.Besl and R.C.Jain.Segmentation through Variable Order Surface Fitting[D].IEEE Trans.Pattern Anal.Mach Intel.,1988, PAMI-10(2):167-192.
[76]R.Hoffman and A.K.Jain.Segmentation and Classification of Range lmages[D].IEEE Trans.Pattern Anal.Mach.Intel.,1987, PAMI-9(5):609-620.
[77]A.K.Jain and S.G.Nadabar. MRF Model-based Segmentation of Range Images[C].Proc of 3'd Int.Conf.On Computer Vision,1990:667-671.
[78]唐四春,袁保宗.基于拓扑图及三维特征的三维物体识别方法[J].通信学报,1993,14(2)：35-39.
[79]Benlamri R.Curved Shapes Construction for Object Recognition[J].IEEE Transactions on Theory and Applications,2002,10(3):167-172.
[80]T.J.Fan.Describing and Recognizing 3D Objects Using Surface Properties[M]. New York:Springer-Verlag,NewYork Inc.,1990.
[81]Bilge Gunsel,Anil K.Jain,Erdal Panayirei.Reconstruction and Boundary Detection of Range and Intensity Images Using Multiscale MRF Representations[J].Computer Vision and Image Understanding,1996,33(2):353-366.
[82]Olga R.P.,Bellon,Luciano Silva. New Improvements to Range Image Segmentation by Edge Detection[J].IEEE Transactions on signal processing letters,2002,9(2):43-45.
[83]薛琴,陈玮,罗俊奇.基于梯度算子的蚁群图像分割算法研究[J].计算机工程与设计,2007,(23):5660-5663.
[84]Jianyu Chen,Li, J.,Delu Pan,Qiankun Zhu.Zhihua Mao.Edge-Guided Multiscale Segmentation of Satellite Multispectral Imagery.Geoscience and Remote Sensing, IEEE Transactions on,2012,50(11):4513-4520.
[85]Sundaresan, A., Chellappa R..Model Driven Segmentation of Articulating Humans in Laplacian Eigenspace.Pattern Analysis and Machine Intelligence, IEEE Transactions on,2008,30(10):1771-1785.
[86]李翔,吴国威.一种适用于H.264的基于自适应搜索范围的快速运动估计算法[J].中国图象图形学报,2004,9(4):471-476.
[87]范剑英等.基于法向分量边缘融合的深度图像分割[J].计算机工程.2010,36(17)：221-223.
[88]邹宁,李庆,柳健.基于神经网络的深度图像分割方法.[J].红外与激光工程,2000,29(1)：22-25.
[89]曹建海.金属标牌压印凹凸字符的检测与识别研究[D].山东大学博士论文,2004：5.
[90]李国平.基于莫尔技术的标牌凹凸字符图像获取与识别研究[D].山东大学博士 论文,2007:3.
[91]李学勇.金属标牌压印凹凸字符的特征提取和识别方法研究[D].山东大学博士论文,2008:5.
[92]李建美.标牌压印字符图像获取与处理中的关键技术研究[D].山东大学博士论文,2008：9.
[93]R.J.Woodham.Photometric method for determining surface orientation from multiple images[J].Optical Engineering,1980,19(1):139-144.
[94]Tagare, Hemant D. and Rui J. P. deFigueiredo.A theory of photometric stereo for a class of diffuse non-lambertian surfaces[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1991,13(2):133-152.
[95]Nayar, Shree K., Katsushi Ikeuchi, and Takeo Kanade.Determining shape and reflectance of hybrid surfaces by photometric sampling[J]. IEEE Transactions on Robotics and Automation,1990,6(4):418-431.
[96]Georghiades, Athinodoros S.. Incorporating the Torrance and Sparrow model of reflectance in uncalibrated photometric stereo[C].In Proceedings of the ninth IEEE international conference on computer vision,2003,2:816-823.
[97]Heizmann, Michael and Jurgen Beyerer.Sampling the parameter domain of image series[J].The International Society for Optical Engineering,2005,5672:23-33.
[98]Fernando Puente Leon,Jurgen Beyerer. Datenfusion zur Gewinnung hochwertiger Bilder in der automatischen Sichtprufung. Automatisierungstechnik[J].Oldenbourg, 1997,45(10):480-489.
[99]Racky, J.,Pandit, M.. Active illumination for the segmentation of surface deformations[J]. Image Processing,1999,1:41-45.
[100]Pfeifer T.,L. Wiegers.Verfahren zur wissensunabhangigen automatischen Bildoptimierung in der technischen Sichtprufung[C].VDI Berichte,2000:37-42.
[101]Wiegers, L.. Image and illumination optimization for automated measurement of wear on cutting tools[D].RWTH Aachen University,Dissertation, Shaker Verlag, 2001,:116-123+142-145.
[102]Xianghua Xie and Majid Mirmehdi.Texture Exemplars for Defect Detection on Random Textured Surfaces[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(8):1454-1464.
[103]Chantler Michael J..The effect of variation in illumination direction on texture classification[D]. PhD thesis, Department of Computing and Electrical Engineering, Heriot-Watt University, Edinburgh,1994.
[104]Wu Jiahua.Rotation Invariant Classification of 3D Surface Texture using Photometric Stereo[D]. PhD thesis, School of Mathematical and Computer Sciences, Heriot-Watt University, Edinburgh,2003.
[105]Chantler Mike J.,Jiahua Wu.Rotation invariant classification of 3d surface textures using photometric stereo and surface magnitude spectra[C]. In Proceedings of British Machine Vision Association,2000.
[106]Ana Perez Grassi, Fernando Puente Leon.Invariant Features for Classification of Defects Based on Illumination Series[J]. Technisches Messen 2008,75(7-8): 455-463.
[107]Perez Grassi Ana, Miguel Angel Abian Perez, Fernando Puente Leon. Detection of circular defects on varnished or painted surfaces by image fusion[C].In Proceedings of the IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems,2006:255-260.
[108]Perez Grassi, Ana, Gianni Monti und Fernando Puente Leon:Matched-Filter im Beleuchtungsraum zur Detektion kraterformiger Defekte auf lackierten Holzoberflachen[J]. In:Sensoren und Messsysteme 2006,13:349-352.
[109]Perez Grassi Ana, Fernando Puente Leon.Klassifikation von Defekten auf asthetischen Oberflachen mittels variabler Beleuchtung und invarianter Merkmale[J]. In:Bildverarbeitung in der Mess und Automatisierungstechnik, Seiten 13-22, Dusseldorf, 2007.
[110]Perez Grassi, Ana und Fernando Puente Leon. Invariante Merkmale zur Klassifikation von Defekten aus Beleuchtungsserien[J]. Technisches Messen, 75(7-8),2008.
[111]Puente Leon, Fernando.Determination of the coverage of shot peened surfaces[J]. In Brebbia, Carlos A. (editor):Surface Treatment V,2001:323-332.
[112]Puente Leon, Fernando:Model-based inspection of shot peened surfaces using fusion techniques[C]. Proc. SPIE 4189, Machine Vision and Three-Dimensional Imaging Systems for Inspection and Metrology, 2001,41:41-52.
[113]McGunnigle, Ged and Mike J. Chantler.Segmentation of rough surfaces using reflectance[J]. In BMVC,2001.
[114]Hertzmann, Aaron and Steven M. Seitz.Shape and materials by example:A photometric stereo approach[C].IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2003,01:533-540.
[115]Dan B Goldman, Brian Curless, Aaron Hertzmann, Steven M Seitz.Shape and spatially-varying BRDFs from photometric stereo[J].In IEEE transactions on pattern analysis and machine intelligence,2010:32 (6):1060-1071.
[116]Brein, Christoph:Segmentation of Cartridge Cases Based on Illumination and Focus Series[C]. Proc. SPIE.5685, Image and Video Communications and Processing,2005:228-238.
[117]Lindner christoph.Segmentierung von Obeflachen mittels variabler Beleuchtung[D].PhD thesis,Technische Universitat Munchen.Shaker Verlag, Aachen,2009.
[118]Sun, J. Examining the uncertainty of the recovered surface normal in three light photometric stereo[J].Image and Vision Computing,2007,25(7):1073-1079.
[119]Ian Ashdown, P. Eng.Near-Field photometry:measuring and modeling complex 3-D light sources[J]. ACM SIGGRAPH 95 Course Notes-Realistic Input for Realistic Images,1995:1-15.
[120]Jiuai Sun, Melvyn Smith, Lyndon Smith, Abdul Farooq.Sampling Light Field for Photometric Stereo[J].International Journal of Computer Theory and Engineering,2013,5(1):14-18.
[121]LANDY MICHAEL.Computational models of visual processing[M]. MIT Press, Cambridge,1991.
[122]蒋刚毅,黄大江,王旭,郁梅.图像质量评价方法研究进展[J].电子与信息学报,2010,(01)：219-226.
[123]赵文哲.秦世引.图像质量评价的研究进展和若干问题的解决途径[J].激光与光电子学进展,2010,(04):46-54.
[124]周景超,戴汝为,肖柏华.图像质量评价研究综述[J].计算机科学,2008,(07)：1-4+8.
[125]刘书琴,毋立芳,宫玉,刘兴胜.图像质量评价综述[J].中国科技论文在线,2011,(07)：501-506+523.
[126]黄君.图像质量评价的研究[D].浙江理工大学硕士论文,2012:4.
[127]Hyung-ju Park,Dong-Hwan Har.Subjective image quality assessment based on objective image quality measurement factors[J]. IEEE Transactions on Consumer Electronics,2011,57(3):1176-1184.
[128]Lin Ma,Weisi Lin,Chenwei Deng,King Ngi Ngan.Image Retargeting Quality Assessment:A Study of Subjective Scores and Objective Metrics[J].Selected Topics in Signal Processing.2012,6(6):626-639.
[129]李俊,机器视觉照明光源关键技术研究[D].天津理工大学硕士论文.2006:12.
[130]Puente Leon, Fernando.Automatische Identifikation von SchuBwaffen[J], Band 787 der Reihe Fortschritt-Berichte VDI, Reihe 8. VDI Verlag, Diisseldorf, 1999.
[131]Barsky Svetlana,Maria Petrou.Surface texture using photometric stereo data: classification and direction of illumination detection[J]. Journal of Mathematical Imaging and Vision,2007,29:185-204.
[132]Chantler, Michael J., M. SCHMIDT, M. Petrou, G. Mcgunnigle. The effect of illuminant rotation on texture filters:Lissajous's ellipses[C].In Proceedings of the 7th European Conference on Computer Vision-Part III,2002:289-303.
[133]Ho Yun-Xian, Michael Landy,Laurence Maloney.How direction of illumination affects visually perceived surface roughness[J]. Journal of Vision,2006,6:634-648.
[134]Spence, A.D. and Chantler, M.J..Optimal illumination for three-image photometric stereo using sensitivity analysis[J].IEEE Proceedings in Vision, Image and Signal Processing,2006,153(2):149-159.
[135]Gullon C.. Height recovery of rough surfaces from intensity images[D]. PhD thesis, Heriot-Watt University, Edinburgh, Scotland,2003.
[136]Drbohlav O., Chantler M.. On Optimal Light Configurations in Photometric Stereo[C]. in ICCV 2005:Proceedings of the 10th IEEE International Conference on Computer Vision, vol. Ⅱ, Beijing, China, 2005:1707-1712.
[137]El Gendy A, Shalaby A.. Improved Specularity Detection relying on a Photometric Stereo Technique[C]. in Graphics, Vision, and Image Processing, GVIP, The International Congress for Global Science and Technology, (ICGST),2007, 6(4).
[138]McGunnigle, G..The Classification of Textured Surfaces Under Varying Illuminant Direction[D].PhD thesis, Heriot-Watt University, Edinburgh, Scotland, 1998.
[139]B.Phong.Ilumination for computer generated pictures[J]. Communications of the ACM,1975,18(6):449-455.
[140]J. Blin.Models of light reflection for computer synthesized pictures[J]. ACM SIGGRAPH,1997,11:192-198.
[141]K.E.Torrance,E.M.Sparrow.Theory for off-specular reflection from roughened surfaces[J]. Optical Society of America,1967,57:1305-1114.
[142]R.L.Cook,K.E.Torrance.A reflectance model for computer graphics[J]. In Computer Graphics,1981:307-316.
[143]WardG.J.. Measuring and modeling anisotropic reflection[J]. Comput. Graph. ACM,1992,26(2):265-272.
[144]Coleman E.N.,Jr.Jain R.. Obtaining 3-Dimensional Shape of Textured and Specular Surface Using Four-Source Photometry[J].Computer Graphics and Image Processing,1982,18:309-328.
[145]Ruggero Pintus, Simona Podda, Massimo Vanzi.An Automatic Alignment Procedure for a Four-Source Photometric Stereo Technique Applied to Scanning Electron Microscopy[J].IEEE Transactions on instrumentation and measurement,2008,57(5):989-996.
[146]Barsk S., Petrou M.. The 4-source photometric stereo technique for three-dimensional surfaces in the presence of highlights and shadows[J]. IEEE Trans. Patt. Anal. Mach. Intell.,2003,25(10):1239-1252.
[147]El Gendy Amin.Characterization of pavement surface texture using photometric stereo techniques[D], University of manitoba,2009.
[148]Pietikainen M.Image analysis with local binary patterns[C].Pros.14th Scandinavian Conference on Image Analysis,Joensuu,Finland,2005:115-118.
[149]Jin H,Liu Q,Lu H,et al.. Face detection using improved LBP under Bayesian framework[C].Proc.Third International Conference on Image and Graphics,ong Kong,China,2004:306-309.
[150]S. Liao, Max W. K. Law,Albert C. S. Chung.Dominant local binary patterns for texture classification[J].IEEE Transactions on Image Processing,2009, 18(5):1107-1118.
[151]Zhenhua Guo, Lei Zhang, David Zhang.Rotation invariant texture classification using LBP variance(LBPV) with global matching[J]. Pattern Recognition, 2010,43(3):706-719.
[152]Xu Qing,Yang Jie, Ding Siyi.Texture Segmentation using LBP embedded Region Competition[J].EI. Letters on Comp. Vision and Image Anal.,2005,5(1):41-47.
[153]K.H. Zhang, L. Zhang, H.H. Song, W. Zhou.Active contours with selective local or global segmentation:a new formulation and level set method[J].Image and Vision Computing,2010,28(4):668-676.
[154]C. Sagiv, N.A. Sochen, Y. Zeevi.Integrated Active Contours for Texture Segmentation[J].IEEE Trans. Image Processing,2004,1 (1):1-19.
[155]B.Wang, X. Gao, D. Tao, X. Li.A unified tensor level set for image segmentation[J].IEEE Transactions on Systems, Man, and Cybernetics, Part B,2010,40(3):857-867.
[156]Y. Yuan, Y. Pang, J. Pan, X. Li.Scene segmentation based on IPCA for visual surveillance[J].Neuro computing,2009,72(10-12):2450-2454.
[157]Gonzalez, Rafael C. und Richard E. Woods.Digital Image Processing[M]. Addison-Wesley Longman Publishing Co., Inc., Boston, MA, USA,2001.
[158]Ojala,T.andM.Pietikainen,Unsupervised texture segmentation using feature distributions[J].Pattern Recognition,1999,32(3):477-486.
[159]Saad,N.M.,Abu-Bakar,S.A.R,Muda,S.,Mokji,M..Automated segmentation of brain lesion based on diffusion-weighted MRI using a split and merge approach[C].Biomedical Engineering and Sciences(IECBES),2010 IEEE EMBS Conference on,2010:475-480.
[160]闫成新,桑农,张天序.基于图论的图像分割研究进展[J].计算机工程与应用,2006,(05)：11-14.
[161]曹建农,方丹霞.基于图论的图像分割方法及其局限性研究[J].测绘技术装备,2006,(02)：12-15+5
[162]朱友勇.基于图论的图像分割方法的研究与应用[D].江南大学硕士,2009.
[163]侯叶.基于图论的图像分割技术研究[D].西安电子科技大学博士论文,2011.
[164]P.Y.Yin.A fast scheme for optimal thresholding using genetic algorithm[J].Signal Process.1999(72):85-89.
[165]J. Scanlon, N. Florida.Graph theoretic algorithms for image segmentation[J]. Proc. of the IEEE International Symposium on Circuits and Systems, Florida,USA,1999,6:141-144.
[166]S. S arkar,K. L. Hoyer.Quantitative measures of change based on feature organization:eigen values and eigenvectors[J].Computer Vision and Pattern Recognition,1996:478-483.
[167]Ristic, D., Vuppala, S.K., Graser, A.. Feedback Control for Improvement of Image Processing: An Application of Recognition of Characters on Metallic Surfaces[C]. Computer Vision Systems,2006 ICVS'06. IEEE International Conference on,2006:04-07,39.
[168]Ristic-Durrant, D.,Graser, A.. Performance Measure as Feedback Variable in Image Processing[J].EURASIP Journal on Advances in Signal Processing, 2006:1-12.
[169]Grigorescu, S. M., Ristic-Durrant, D., Vupalla, S. K., Graser, A.. Closed-Loop Control in Image Processing for Improvement of Object Recognition[C]. In Proceedings of the 17th IFAC World Congress,2008,17(1):5335-5340.
[170]Xu D.,Tang X. D.. Multi-threshold image segmentation based on two-dimensional Tsallis[C].Proceedings of 3nd IEEE International Conference on Computer Science and Information Technology,2010:1-5.
[171]Cheng Zh.,Zhang T. X., Yan L X.. Thresholding using two-dimensional histogram based on local entropy[C].Proceedings of 2nd International Asia Conference on Informatics in Control, Automation and Robotics,2010:357-360.
[172]龙钧宇,金连文.一种基于全值均值和局部方差的图像二值化方法.[J].计算机工程,2004,30(2),70-72.
[173]吕俊哲.图像二值化算法研究及其实现.[J].科技情报开发与经济,2004,14(12),266-267.
[174]马义德等,脉冲耦合神经网络与数字图像处理[M].科学出版社.2008.
[175]Eckhorn R, Reitboeck H J, Arndt M et al. Feature linking via synchronization among distributed assemblies:Simulation of results from cat cortex[J]. Neural Comput.,1990,2(3):293-307
[176]Spackman.Signal Detection Theory:Valuable tools for evaluating inductive learning[J]. In Proceedings of the Sixth International Workshop on Machine Learning.1989.
[177]N. Lachiche,P.A. Flach.Improving accuracy and cost of two-class and multi-class probabilistic classifiers using ROC curves[C]. Proc.20th International Conference on Machine Learning (ICML'03),2003:416-423.
[178]Hand, D. J.,& Till, R. J. A Simple Generalization of the Area Under the ROC Curve to Multiple Class Classification Problems [J]. Machine Learning,2001,45 (2): 171-186.
[179]韦修喜,周永权.基于ROC曲线的两类分类问题性能评估方法[J].计算机技术与发展,2010,(11):47-50.
[180]孙长亮,何峻,肖怀铁.基于ROC曲线的目标识别性能评估方法[J].雷达科学与技术,2007,(01):17-21.
[181]方学立,梁甸农,董臻.目标检测性能的定量评估方法[J].系统工程与电子技术,2005,(12)：1991-1993+2106.
[2]贾云得.机器视觉[M].北京：科学出版社,2000.
[3]R.G.Casey,E.Lecolinent.A Survey of Methods and Strategies in Character Segmentation[J].IEEE trans.PAMI,1996,18(7):690-709.
[4]孙广玲.手写字符识别中关键技术研究[D].哈尔滨工业大学博士论文,2005:8.
[5]李建美,路长厚,李国平.基于Gabor变换的凹凸字符图像特征抽取新方法[J].系统仿真学报,2008,20(4):2133-2136.
[6]曹建海,路长厚,李磊.基于灰度图像的压印凸凹字符质量检测研究[J].光电子激光,2007(1),90-92.
[7]Christoph Lindner, Fernando Puente Leon.Model-Based Segmentation of Surfaces Using Illumination Series[J]. IEEE T. Instrumentation and Measurement,2007, 56(4):1340-1346.
[8]F. Puente Leon, C. Lindner, D. van Gorkom.Surface Segmentation by Variable Illumination[J].CIRP Annals-Manufacturing Technology,2007,56(1):549-552.
[9]Perez Grassi, Fernando Puente Leon.Translation and Rotation Invariant Histogram Features for Series of Images[J].GI Jahrestagung,2007,(1):38-43.
[10]Perez Grassi,Vadim Frolov,Fernando Puente Leon.Information fusion to detect and classify pedestrians using invariant features[J].Information Fusion.2011,12(4): 284-292.
[11]许新征,丁世飞,史忠植,贾伟宽.图像分割的新理论和新方法[J].电子学报.2010,2(2A)：76-81.
[12]何俊,葛红,王玉峰.图像分割算法研究综述[J].计算机工程与科学,2009,(12):58-61.
[13]章毓晋.图像分割[M].北京：科学出版社,2001.
[14]Serra J.,Mathematical Morphology [M].London,UK:Academic Press,1982.
[15]Victor O R,Juan I G L,Nicolas S L,Pedro G V.An improved watershed algorithm based on efficient computation of shortest paths[J].Pattern Recognition,2007,40(3): 1078-1090.
[16]E.Backer and A.Jain.A clustering Performance measure based on fuzzy set decomposition.[J].IEEE. Trans.Pattern Anal.Mach.Intel.,1981.3(1):66-75.
[17]Kanungo Tapas,Mount D.M.,Netanyahu N.S.,Piatko C.D.,Silverman, R.Wu A.Y..An efficient k-means clustering algorithm:analysis and implementation[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2002,24(7): 881-892.
[18]F.Hoppner,Klawonn,R.Kruse. Fuzzy cluster analysis:methods for classification, data analysis,and image recognition[M].1999:New York:wiley.
[19]R.Sharan and R.Shamir.CLICK.A clustering algorithm with applications to gene expression analysis[C].in 8th lnt.Conf.Intelligent. Systems for Molecular Biology.2000:307-316.
[20]A.Ben Hur,et al..A support vector clustering method[C].In 15th International Conference on Pattern Recognition, 2000,2:724-727.
[21]T.Kohonen.The self-organizing map[J].In Proceedings of the Institute of Electrical and Electronics Engineers.1990,78(9):1464-1480.
[22]I.Bloch. Information combination operators for data fusion:a comparative review with classification[J].IEEE Trans,on SMC,1996,26(1):52-67.
[23]S Fu,Q Ruan,W Wang.A feature-dependent fuzzy bidirectional flow for adaptive image sharpening[J].Neurocomputing,2007,70(4):883-895.
[24]Moghaddamzadeh A,Bourbakis N.,A Fuzzy Region Growing Approach for Segmentation of Color Images[J].Pattern Recognition,1997,30(6):867-881.
[25]张玲,基于模糊理论及其扩展的图像分割研究及应用[D].山东大学博士论文,2012：4.
[26]孙慧贤.基于纹理分析的视觉检测方法与应用研究[D].国防科大博士论文,2010：4.
[27]Tsai I,Lin C,Lin J.Applying an artificial neural network to pattern recognition[J]. Textile Research Journal,1995,65(3):123-130.
[28]Bodnarova A,Williams J,Bennamoun M,et al.Optimal textural features for flaw detection in textile materials[C].Proceedings of IEEE on Speech and Image Technologies for Computing and Telecommunications, Brishane, Australia, 1997,1:307-310.
[29]ShaPir L.G.,Stoekman G.C.,Computer vision[M].Pearson Education Inc.,2001: 235-247.
[30]Ojala T,Pietikainen M,Maenpaa T..Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J].IEEE.Transactions on Pattern Analysis and Machine Intelligence,2002,24(17):971-987.
[31]Monadjemi A..Towards Efficient Texture Classification and Abnormality Detection[D].United Kingdom:University of Bristol,2004:88-129.
[32]M. Niskanen, O. Silvenand H. Kauppinen.Color and texture based wood inspection with unsupervised clustering[C].Proceedings of the 12th Scandinavian Conference on Image Analysis,Bergen,Norway,2001:336-342.
[33]Maenpaa T,Turtinen M,Pietikainen M..Real-time surface in section by texture[J]. Real-Time Imaging,2003,9(5):289-296.
[34]M. Niskanen, H. Kauppinen and O. Silven.Real-time Aspects of SOM-based Visual Surface Inspection[C]. Proc. SPIE 4664,Machine Vision Applications in Industrial Inspection X,2002,123-134.
[35]Kauppinen, H.,Silven, O..The effect of illumination variations on color-based wood defect classification[J]. Pattern Recognition,1996,3:828-832.
[36]Chen C H,Pau L F,Wang P S P. Handbook of Pattern Recognition and Computer Vision(2nd edition)[M].Singapore:World Scientific,1999:207-248.
[37]CrossG C,Jain A K.Markov Random Field Texture Models[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 1983,5(1):25-39.
[38]Chellappa R,Chatterjee S.Classification of Textures Using Gaussian Markov Random Fields[J].IEEE Transactions on Acoustic,Speech and Signal Processing,1985,33(4):959-963.
[39]Krishnamachari S,Chellappa R.Multiresolution Gauss-Markov Random Field Models for Texture Segmentation[J].IEEE Transactions on Image Processing, 1997,6(2):251-267.
[40]Bharati M H,Liu J.J,Mac Gregor J F.Image texture analysis:methods and comparisons[J].Chemometrics and Intelligent Laboratory Systems,2004,2(1):57-71.
[41]Arof H,DeraviF.Circular neighbour hood and 1-D DFT features for texture classification and segmentation[J].IEEE Proceedings Vision, Image and Signal Processing,1998,145(3):167-172.
[42]Grigorescu S E,Petkov N.Kruizinga P.Comparison of Texture Features Based on Gabor Filters[J].IEEE Transactions on Image Processing,2002,11(10):1160-1167.
[43]Muneeswaran K.,Ganesan,Arumugam S.,et.al.Texture image segmentation using combined features from spatial and spectral distribution[J].Pattern Recognition Letters,2006,27(7):755-764.
[44]C. Julia, R.Moreno, D. Puig, M.A. Garcia.Image segmentation through graph-based clustering from surface normals estimated by photometric stereo[J].Electronics Letters,2010:64(2):134-135.
[45]Yuri Y. Boykov Marie-Pierre Jolly, Interactive graph cuts for optimal boundary& region segmentation of objects in N-D images[C]. Proceedings of International Conference on Computer Vision,2001:105-112.
[46]Moreno R.,Garcia M.A., Puig, D.,Graph-based perceptual segmentation of stereo vision 3D images at multiple abstraction levels[C].In proceeding of: Graph-Based Representations in Pattern Recognition,2007:148-157.
[47]Y. Boykov and V. Kolmogorov.An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision[J]. International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition,2001:359-374.
[48]V. Kolmogorov,R. Zabih.Computing visual correspondence with occlusions using graph cuts[C]. in International Conference on Computer Vision,2002,2:508-515.
[49]Y. Boykov, O. Veksler, and R. Zabih.Fast approximate energy minimization via graph cuts[J].Transactions on Pattern Analysis and Machine Intelligence,2001, 23(11):1222-1239.
[50]C.Zahn.Graph Theoretical Methods for Detecting and Describing Gestalt Clusters[J].IEEE Transactions on Computation.1971,20:68-86.
[51]Felzenszwalb P.,Huttenlocher D.Efficient graph-based image segmentation[J]. International Journal of Computer Vision.2004,59(2):167-181.
[52]Wu Z.,Leahy R..An optimal graph theoretic approach to data clustering:Theory and its application to image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1993,15(11):1101-1113.
[53]J.Shi and J.Malik.Normalized Cuts and Image Segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence.2000,22(8):888-905.
[54]Ding C.H.,Xiaofeng He, Hongyuan Zha,Ming Gu,Simon, H.D.A.. min-max cut algorithm for graph partitioning and data clustering[C]. Proceedings IEEE International Conference on Data Mining,2001:107-114.
[55]Wenbing Tao,Hai Jin,Yimin Zhang.Color Image Segmentation Based on Mean Shift and Normalized Cuts[J].Systems, Man, and Cybernetics,Part B:Cybernetics, IEEE Transactions on,2007,37(5):1382-1389.
[56]Vekslre O.Image segmentation by nested cuts [C].Proceedings of the IEEE on Conference Computer Vision and Pattern Recognition,2000,2:508-515.
[57]Wang S., Siskind J..Image segmentation with ratio cut[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(6):675-69.
[58]Grady L,Schwartz E. ISO perimetric graph partitioning for image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(3):469-475.
[59]Rout S.,Srivastava S.,Majumdar J.. Multi-model image segmentation using a modified hopfield neural network[J]. Patten Recognition,1998,31(6),743-750.
[60]Dekruger D.,Hunt B.R..Image processing and neural networks for recognition of cartographic area feature[J].Patten Recognition,1994,27(4):461-483.
[61]Wang D. L,Terman D..Image segmentation based on oscillatory correlation[J]. Normal Computation,1997,9:805-836.
[62]Vilarino D. L.,Brea V. M.,Cabello D..Discrete Time CNN for Image segmentation by active contours[J].Patten Recognition Letters,1998,19(8):721-734.
[63]Wang Y.,Adaii T.,Kung S. Y..Quantification and segmentation of rain tissues from MR images a probabilistic neural networks approach[J]. IEEE Transactions on Image Processing,1998,7(8):1-12.
[64]Coktepe M.,Yaiabik N.,Atalay V..Unsupervised segmentation of gray level Markov model textures with hierarchical self organizing map[C].Proceedings of the 13th International Conference on Pattern Recognition.USA:Institute of Electric and Electronic Engineer.1996:90-94.
[65]Kuntimad G,Ranganath H S.Perfect image segmentation using pulse coupled neural networks[J].IEEE Transactions on Neural Networks,1999,10(3):591-598.
[66]周俊武,孙传尧,王福利.径向基函数(RBF)网络的研究及实现[J].矿冶,2001,04：71-75.
[67]Kaski S., Kangas J.,Kohonen T.. Bibliography of self-organizing map (SOM) papers[J]. Neural Computing Surveys,1997,1:102-350.
[68]ZHANG Junying,FAN Xiuju,DONG Jiyang,SHI Meihon.Image segmentation based on modified pulse-coupled neural networks[J]. Chinese Journal of Electronics,2007,16(1):119-122.
[69]H.Berg,R.Olsson,T.Lindblad et al..Automatic design of pulse coupled neurons for image segmentation[J]. Neurocomputing, 2008,71(6):1980-1993.
[70]Zhu Shan,Ma Kaikuang. A New Diamond Search Algorithm for Fast Block Matching Motion Estimation[J].IEEE Trans, on Image Processing,2000, 9(2):287-290.
[71]Hsieh S L,Wang Hsing-Chih.Feature Extraction for Audio Finger printing Using Wavelet Transformation[J].Proc. of National Computer Symposium,2005:15-16.
[72]张明,毕笃彦.自适应可变模式搜索算法[J].计算机工程,2008,34(7):26-28.
[73]段青青,宋学瑞.一种H.264/AVC中的快速运动估计算法[J].计算机工程,2008,34(16)：244-246.
[74]Ghosal S etc.Range Surface Characterization and Segmentation Using Neural Networks[J].Pattern Recognition.1995,28(5):711-727.
[75]P.J.Besl and R.C.Jain.Segmentation through Variable Order Surface Fitting[D].IEEE Trans.Pattern Anal.Mach Intel.,1988, PAMI-10(2):167-192.
[76]R.Hoffman and A.K.Jain.Segmentation and Classification of Range lmages[D].IEEE Trans.Pattern Anal.Mach.Intel.,1987, PAMI-9(5):609-620.
[77]A.K.Jain and S.G.Nadabar. MRF Model-based Segmentation of Range Images[C].Proc of 3'd Int.Conf.On Computer Vision,1990:667-671.
[78]唐四春,袁保宗.基于拓扑图及三维特征的三维物体识别方法[J].通信学报,1993,14(2)：35-39.
[79]Benlamri R.Curved Shapes Construction for Object Recognition[J].IEEE Transactions on Theory and Applications,2002,10(3):167-172.
[80]T.J.Fan.Describing and Recognizing 3D Objects Using Surface Properties[M]. New York:Springer-Verlag,NewYork Inc.,1990.
[81]Bilge Gunsel,Anil K.Jain,Erdal Panayirei.Reconstruction and Boundary Detection of Range and Intensity Images Using Multiscale MRF Representations[J].Computer Vision and Image Understanding,1996,33(2):353-366.
[82]Olga R.P.,Bellon,Luciano Silva. New Improvements to Range Image Segmentation by Edge Detection[J].IEEE Transactions on signal processing letters,2002,9(2):43-45.
[83]薛琴,陈玮,罗俊奇.基于梯度算子的蚁群图像分割算法研究[J].计算机工程与设计,2007,(23):5660-5663.
[84]Jianyu Chen,Li, J.,Delu Pan,Qiankun Zhu.Zhihua Mao.Edge-Guided Multiscale Segmentation of Satellite Multispectral Imagery.Geoscience and Remote Sensing, IEEE Transactions on,2012,50(11):4513-4520.
[85]Sundaresan, A., Chellappa R..Model Driven Segmentation of Articulating Humans in Laplacian Eigenspace.Pattern Analysis and Machine Intelligence, IEEE Transactions on,2008,30(10):1771-1785.
[86]李翔,吴国威.一种适用于H.264的基于自适应搜索范围的快速运动估计算法[J].中国图象图形学报,2004,9(4):471-476.
[87]范剑英等.基于法向分量边缘融合的深度图像分割[J].计算机工程.2010,36(17)：221-223.
[88]邹宁,李庆,柳健.基于神经网络的深度图像分割方法.[J].红外与激光工程,2000,29(1)：22-25.
[89]曹建海.金属标牌压印凹凸字符的检测与识别研究[D].山东大学博士论文,2004：5.
[90]李国平.基于莫尔技术的标牌凹凸字符图像获取与识别研究[D].山东大学博士 论文,2007:3.
[91]李学勇.金属标牌压印凹凸字符的特征提取和识别方法研究[D].山东大学博士论文,2008:5.
[92]李建美.标牌压印字符图像获取与处理中的关键技术研究[D].山东大学博士论文,2008：9.
[93]R.J.Woodham.Photometric method for determining surface orientation from multiple images[J].Optical Engineering,1980,19(1):139-144.
[94]Tagare, Hemant D. and Rui J. P. deFigueiredo.A theory of photometric stereo for a class of diffuse non-lambertian surfaces[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1991,13(2):133-152.
[95]Nayar, Shree K., Katsushi Ikeuchi, and Takeo Kanade.Determining shape and reflectance of hybrid surfaces by photometric sampling[J]. IEEE Transactions on Robotics and Automation,1990,6(4):418-431.
[96]Georghiades, Athinodoros S.. Incorporating the Torrance and Sparrow model of reflectance in uncalibrated photometric stereo[C].In Proceedings of the ninth IEEE international conference on computer vision,2003,2:816-823.
[97]Heizmann, Michael and Jurgen Beyerer.Sampling the parameter domain of image series[J].The International Society for Optical Engineering,2005,5672:23-33.
[98]Fernando Puente Leon,Jurgen Beyerer. Datenfusion zur Gewinnung hochwertiger Bilder in der automatischen Sichtprufung. Automatisierungstechnik[J].Oldenbourg, 1997,45(10):480-489.
[99]Racky, J.,Pandit, M.. Active illumination for the segmentation of surface deformations[J]. Image Processing,1999,1:41-45.
[100]Pfeifer T.,L. Wiegers.Verfahren zur wissensunabhangigen automatischen Bildoptimierung in der technischen Sichtprufung[C].VDI Berichte,2000:37-42.
[101]Wiegers, L.. Image and illumination optimization for automated measurement of wear on cutting tools[D].RWTH Aachen University,Dissertation, Shaker Verlag, 2001,:116-123+142-145.
[102]Xianghua Xie and Majid Mirmehdi.Texture Exemplars for Defect Detection on Random Textured Surfaces[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(8):1454-1464.
[103]Chantler Michael J..The effect of variation in illumination direction on texture classification[D]. PhD thesis, Department of Computing and Electrical Engineering, Heriot-Watt University, Edinburgh,1994.
[104]Wu Jiahua.Rotation Invariant Classification of 3D Surface Texture using Photometric Stereo[D]. PhD thesis, School of Mathematical and Computer Sciences, Heriot-Watt University, Edinburgh,2003.
[105]Chantler Mike J.,Jiahua Wu.Rotation invariant classification of 3d surface textures using photometric stereo and surface magnitude spectra[C]. In Proceedings of British Machine Vision Association,2000.
[106]Ana Perez Grassi, Fernando Puente Leon.Invariant Features for Classification of Defects Based on Illumination Series[J]. Technisches Messen 2008,75(7-8): 455-463.
[107]Perez Grassi Ana, Miguel Angel Abian Perez, Fernando Puente Leon. Detection of circular defects on varnished or painted surfaces by image fusion[C].In Proceedings of the IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems,2006:255-260.
[108]Perez Grassi, Ana, Gianni Monti und Fernando Puente Leon:Matched-Filter im Beleuchtungsraum zur Detektion kraterformiger Defekte auf lackierten Holzoberflachen[J]. In:Sensoren und Messsysteme 2006,13:349-352.
[109]Perez Grassi Ana, Fernando Puente Leon.Klassifikation von Defekten auf asthetischen Oberflachen mittels variabler Beleuchtung und invarianter Merkmale[J]. In:Bildverarbeitung in der Mess und Automatisierungstechnik, Seiten 13-22, Dusseldorf, 2007.
[110]Perez Grassi, Ana und Fernando Puente Leon. Invariante Merkmale zur Klassifikation von Defekten aus Beleuchtungsserien[J]. Technisches Messen, 75(7-8),2008.
[111]Puente Leon, Fernando.Determination of the coverage of shot peened surfaces[J]. In Brebbia, Carlos A. (editor):Surface Treatment V,2001:323-332.
[112]Puente Leon, Fernando:Model-based inspection of shot peened surfaces using fusion techniques[C]. Proc. SPIE 4189, Machine Vision and Three-Dimensional Imaging Systems for Inspection and Metrology, 2001,41:41-52.
[113]McGunnigle, Ged and Mike J. Chantler.Segmentation of rough surfaces using reflectance[J]. In BMVC,2001.
[114]Hertzmann, Aaron and Steven M. Seitz.Shape and materials by example:A photometric stereo approach[C].IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2003,01:533-540.
[115]Dan B Goldman, Brian Curless, Aaron Hertzmann, Steven M Seitz.Shape and spatially-varying BRDFs from photometric stereo[J].In IEEE transactions on pattern analysis and machine intelligence,2010:32 (6):1060-1071.
[116]Brein, Christoph:Segmentation of Cartridge Cases Based on Illumination and Focus Series[C]. Proc. SPIE.5685, Image and Video Communications and Processing,2005:228-238.
[117]Lindner christoph.Segmentierung von Obeflachen mittels variabler Beleuchtung[D].PhD thesis,Technische Universitat Munchen.Shaker Verlag, Aachen,2009.
[118]Sun, J. Examining the uncertainty of the recovered surface normal in three light photometric stereo[J].Image and Vision Computing,2007,25(7):1073-1079.
[119]Ian Ashdown, P. Eng.Near-Field photometry:measuring and modeling complex 3-D light sources[J]. ACM SIGGRAPH 95 Course Notes-Realistic Input for Realistic Images,1995:1-15.
[120]Jiuai Sun, Melvyn Smith, Lyndon Smith, Abdul Farooq.Sampling Light Field for Photometric Stereo[J].International Journal of Computer Theory and Engineering,2013,5(1):14-18.
[121]LANDY MICHAEL.Computational models of visual processing[M]. MIT Press, Cambridge,1991.
[122]蒋刚毅,黄大江,王旭,郁梅.图像质量评价方法研究进展[J].电子与信息学报,2010,(01)：219-226.
[123]赵文哲.秦世引.图像质量评价的研究进展和若干问题的解决途径[J].激光与光电子学进展,2010,(04):46-54.
[124]周景超,戴汝为,肖柏华.图像质量评价研究综述[J].计算机科学,2008,(07)：1-4+8.
[125]刘书琴,毋立芳,宫玉,刘兴胜.图像质量评价综述[J].中国科技论文在线,2011,(07)：501-506+523.
[126]黄君.图像质量评价的研究[D].浙江理工大学硕士论文,2012:4.
[127]Hyung-ju Park,Dong-Hwan Har.Subjective image quality assessment based on objective image quality measurement factors[J]. IEEE Transactions on Consumer Electronics,2011,57(3):1176-1184.
[128]Lin Ma,Weisi Lin,Chenwei Deng,King Ngi Ngan.Image Retargeting Quality Assessment:A Study of Subjective Scores and Objective Metrics[J].Selected Topics in Signal Processing.2012,6(6):626-639.
[129]李俊,机器视觉照明光源关键技术研究[D].天津理工大学硕士论文.2006:12.
[130]Puente Leon, Fernando.Automatische Identifikation von SchuBwaffen[J], Band 787 der Reihe Fortschritt-Berichte VDI, Reihe 8. VDI Verlag, Diisseldorf, 1999.
[131]Barsky Svetlana,Maria Petrou.Surface texture using photometric stereo data: classification and direction of illumination detection[J]. Journal of Mathematical Imaging and Vision,2007,29:185-204.
[132]Chantler, Michael J., M. SCHMIDT, M. Petrou, G. Mcgunnigle. The effect of illuminant rotation on texture filters:Lissajous's ellipses[C].In Proceedings of the 7th European Conference on Computer Vision-Part III,2002:289-303.
[133]Ho Yun-Xian, Michael Landy,Laurence Maloney.How direction of illumination affects visually perceived surface roughness[J]. Journal of Vision,2006,6:634-648.
[134]Spence, A.D. and Chantler, M.J..Optimal illumination for three-image photometric stereo using sensitivity analysis[J].IEEE Proceedings in Vision, Image and Signal Processing,2006,153(2):149-159.
[135]Gullon C.. Height recovery of rough surfaces from intensity images[D]. PhD thesis, Heriot-Watt University, Edinburgh, Scotland,2003.
[136]Drbohlav O., Chantler M.. On Optimal Light Configurations in Photometric Stereo[C]. in ICCV 2005:Proceedings of the 10th IEEE International Conference on Computer Vision, vol. Ⅱ, Beijing, China, 2005:1707-1712.
[137]El Gendy A, Shalaby A.. Improved Specularity Detection relying on a Photometric Stereo Technique[C]. in Graphics, Vision, and Image Processing, GVIP, The International Congress for Global Science and Technology, (ICGST),2007, 6(4).
[138]McGunnigle, G..The Classification of Textured Surfaces Under Varying Illuminant Direction[D].PhD thesis, Heriot-Watt University, Edinburgh, Scotland, 1998.
[139]B.Phong.Ilumination for computer generated pictures[J]. Communications of the ACM,1975,18(6):449-455.
[140]J. Blin.Models of light reflection for computer synthesized pictures[J]. ACM SIGGRAPH,1997,11:192-198.
[141]K.E.Torrance,E.M.Sparrow.Theory for off-specular reflection from roughened surfaces[J]. Optical Society of America,1967,57:1305-1114.
[142]R.L.Cook,K.E.Torrance.A reflectance model for computer graphics[J]. In Computer Graphics,1981:307-316.
[143]WardG.J.. Measuring and modeling anisotropic reflection[J]. Comput. Graph. ACM,1992,26(2):265-272.
[144]Coleman E.N.,Jr.Jain R.. Obtaining 3-Dimensional Shape of Textured and Specular Surface Using Four-Source Photometry[J].Computer Graphics and Image Processing,1982,18:309-328.
[145]Ruggero Pintus, Simona Podda, Massimo Vanzi.An Automatic Alignment Procedure for a Four-Source Photometric Stereo Technique Applied to Scanning Electron Microscopy[J].IEEE Transactions on instrumentation and measurement,2008,57(5):989-996.
[146]Barsk S., Petrou M.. The 4-source photometric stereo technique for three-dimensional surfaces in the presence of highlights and shadows[J]. IEEE Trans. Patt. Anal. Mach. Intell.,2003,25(10):1239-1252.
[147]El Gendy Amin.Characterization of pavement surface texture using photometric stereo techniques[D], University of manitoba,2009.
[148]Pietikainen M.Image analysis with local binary patterns[C].Pros.14th Scandinavian Conference on Image Analysis,Joensuu,Finland,2005:115-118.
[149]Jin H,Liu Q,Lu H,et al.. Face detection using improved LBP under Bayesian framework[C].Proc.Third International Conference on Image and Graphics,ong Kong,China,2004:306-309.
[150]S. Liao, Max W. K. Law,Albert C. S. Chung.Dominant local binary patterns for texture classification[J].IEEE Transactions on Image Processing,2009, 18(5):1107-1118.
[151]Zhenhua Guo, Lei Zhang, David Zhang.Rotation invariant texture classification using LBP variance(LBPV) with global matching[J]. Pattern Recognition, 2010,43(3):706-719.
[152]Xu Qing,Yang Jie, Ding Siyi.Texture Segmentation using LBP embedded Region Competition[J].EI. Letters on Comp. Vision and Image Anal.,2005,5(1):41-47.
[153]K.H. Zhang, L. Zhang, H.H. Song, W. Zhou.Active contours with selective local or global segmentation:a new formulation and level set method[J].Image and Vision Computing,2010,28(4):668-676.
[154]C. Sagiv, N.A. Sochen, Y. Zeevi.Integrated Active Contours for Texture Segmentation[J].IEEE Trans. Image Processing,2004,1 (1):1-19.
[155]B.Wang, X. Gao, D. Tao, X. Li.A unified tensor level set for image segmentation[J].IEEE Transactions on Systems, Man, and Cybernetics, Part B,2010,40(3):857-867.
[156]Y. Yuan, Y. Pang, J. Pan, X. Li.Scene segmentation based on IPCA for visual surveillance[J].Neuro computing,2009,72(10-12):2450-2454.
[157]Gonzalez, Rafael C. und Richard E. Woods.Digital Image Processing[M]. Addison-Wesley Longman Publishing Co., Inc., Boston, MA, USA,2001.
[158]Ojala,T.andM.Pietikainen,Unsupervised texture segmentation using feature distributions[J].Pattern Recognition,1999,32(3):477-486.
[159]Saad,N.M.,Abu-Bakar,S.A.R,Muda,S.,Mokji,M..Automated segmentation of brain lesion based on diffusion-weighted MRI using a split and merge approach[C].Biomedical Engineering and Sciences(IECBES),2010 IEEE EMBS Conference on,2010:475-480.
[160]闫成新,桑农,张天序.基于图论的图像分割研究进展[J].计算机工程与应用,2006,(05)：11-14.
[161]曹建农,方丹霞.基于图论的图像分割方法及其局限性研究[J].测绘技术装备,2006,(02)：12-15+5
[162]朱友勇.基于图论的图像分割方法的研究与应用[D].江南大学硕士,2009.
[163]侯叶.基于图论的图像分割技术研究[D].西安电子科技大学博士论文,2011.
[164]P.Y.Yin.A fast scheme for optimal thresholding using genetic algorithm[J].Signal Process.1999(72):85-89.
[165]J. Scanlon, N. Florida.Graph theoretic algorithms for image segmentation[J]. Proc. of the IEEE International Symposium on Circuits and Systems, Florida,USA,1999,6:141-144.
[166]S. S arkar,K. L. Hoyer.Quantitative measures of change based on feature organization:eigen values and eigenvectors[J].Computer Vision and Pattern Recognition,1996:478-483.
[167]Ristic, D., Vuppala, S.K., Graser, A.. Feedback Control for Improvement of Image Processing: An Application of Recognition of Characters on Metallic Surfaces[C]. Computer Vision Systems,2006 ICVS'06. IEEE International Conference on,2006:04-07,39.
[168]Ristic-Durrant, D.,Graser, A.. Performance Measure as Feedback Variable in Image Processing[J].EURASIP Journal on Advances in Signal Processing, 2006:1-12.
[169]Grigorescu, S. M., Ristic-Durrant, D., Vupalla, S. K., Graser, A.. Closed-Loop Control in Image Processing for Improvement of Object Recognition[C]. In Proceedings of the 17th IFAC World Congress,2008,17(1):5335-5340.
[170]Xu D.,Tang X. D.. Multi-threshold image segmentation based on two-dimensional Tsallis[C].Proceedings of 3nd IEEE International Conference on Computer Science and Information Technology,2010:1-5.
[171]Cheng Zh.,Zhang T. X., Yan L X.. Thresholding using two-dimensional histogram based on local entropy[C].Proceedings of 2nd International Asia Conference on Informatics in Control, Automation and Robotics,2010:357-360.
[172]龙钧宇,金连文.一种基于全值均值和局部方差的图像二值化方法.[J].计算机工程,2004,30(2),70-72.
[173]吕俊哲.图像二值化算法研究及其实现.[J].科技情报开发与经济,2004,14(12),266-267.
[174]马义德等,脉冲耦合神经网络与数字图像处理[M].科学出版社.2008.
[175]Eckhorn R, Reitboeck H J, Arndt M et al. Feature linking via synchronization among distributed assemblies:Simulation of results from cat cortex[J]. Neural Comput.,1990,2(3):293-307
[176]Spackman.Signal Detection Theory:Valuable tools for evaluating inductive learning[J]. In Proceedings of the Sixth International Workshop on Machine Learning.1989.
[177]N. Lachiche,P.A. Flach.Improving accuracy and cost of two-class and multi-class probabilistic classifiers using ROC curves[C]. Proc.20th International Conference on Machine Learning (ICML'03),2003:416-423.
[178]Hand, D. J.,& Till, R. J. A Simple Generalization of the Area Under the ROC Curve to Multiple Class Classification Problems [J]. Machine Learning,2001,45 (2): 171-186.
[179]韦修喜,周永权.基于ROC曲线的两类分类问题性能评估方法[J].计算机技术与发展,2010,(11):47-50.
[180]孙长亮,何峻,肖怀铁.基于ROC曲线的目标识别性能评估方法[J].雷达科学与技术,2007,(01):17-21.
[181]方学立,梁甸农,董臻.目标检测性能的定量评估方法[J].系统工程与电子技术,2005,(12)：1991-1993+2106.