摘要
基于颜色标记的图像着色具有广阔的应用背景。由于影响着色质量的诸多因素存在耦合,现有算法在描述着色失真的成因以及特定场景中的应用都存在不尽如人意之处,因此,在分析着色机理的基础上,研究更有效的着色方法具有重要的理论和实际意义。
本文通过对影响标记设置的关联因素解耦以降低设置难度,通过采用优化的扩散机制降低着色结果对颜色标记分布的敏感度,以抑制在弱边缘处和零碎分布区域的着色失真。主要研究工作与创新点如下：
建立优化式着色算法框架,并通过数学分析证明优化式着色算法的结果由各颜色标记混色而成,并给出混色权重的物理意义；另外构建了优化式着色算法的等效电路,从而可利用电路理论分析着色特性；利用该混色机制不仅对标记的颜色与位置可独立调整,而且还设计出与传统标记互补的阴性颜色标记,从而更直观、灵活地修改着色失真；而混色权重与首达概率的等价性为进一步分析着色失真的原因提供了理论依据。
分析了常用着色算法对颜色标记分布敏感,特别是在弱边缘区域容易失真的原因,提出了三种改进方法。首先基于对不平度的特性分析,设计了一种具有线性计算复杂度的不平度改进算法；第二种方法是基于其优化式着色算法混色机制,通过设置混色权重的调节系数控制过渡带宽度,从而得到更高质量的着色效果；最后还引入弱边缘标记来干预失真的修改。
分析了常用着色算法在零碎分布对象上着色失真的成因。针对现有的着色相似度函数由人为主观指定,难以准确反映图像复杂处像素关系的问题,提出基于自然彩色图像的特性建立相似度函数的方法。从自然彩色图像提取色度-灰度局部线性关系,作为先验知识建立相似度函数。而对于二次着色则提出采用两级协同扩散算法,将过度分割得到的小块区域与像素组成两级有权图,图中包含像素级近邻连接、区域级全连接,以及区域与其内部像素间连接,并设计色彩迭代过程对所有这些连接进行信息调配,从而能实现远距离扩散。该两级传播机制可以方便地用于图像分割。
针对现有算法在图像高光、暗影区着色结果不真实的问题,利用成像模型将光线颜色与物体本征颜色的作用解耦,并进一步构建一个在白色光线下像素色度-灰度关系模型,分析现有算法着色失真原因,提出基于色度修正的改进方法。由于每个颜色块的调整只需用户选择一个灰度参数即可实现,所以不仅可以设置默认值自动实现粗调,而且还可以人机实时交互进一步细调,避免了手工设置复杂层次颜色标记的问题。另外基于该模型还提出一种简便方法实现有色光线下着色。
为了提高着色速度,提出以超级像素作为基本单元的快速着色策略。根据着色要求拟定选择标准,从而挑选出最佳的超级像素生成算法实现快速着色,然后选择线性复杂度的引导型滤波器,在保持物体边缘的同时快速实现超级像素问颜色的光滑过渡。最后将快速算法和前面提出的改进算法相结合,设计了一个快速灵活的着色系统,用户可以根据着色结果在线实时调整颜色标记,以获得满意的着色结果。
Stroke-based colorization has been applied in many areas. Because many factors influence colorization quality and couple together, it is difficult for any existing algorithm to describe the reason for falsehood perfectly, and accordingly, these algorithms performs not good enough in particular scene. Hence, it is of theoretical and practical significance to develop technologies based on analysis to colorization mechanism.
This thesis focuses on researches on two key procedures in colorization, in particular, on relieving the difficulty in finding desirable stroke by decoupling relative factor, and on developing better diffusion method to reduce sensitivity of visual result to stroke distribution in order to improve visual effect over weak boundary and scattered areas. The main contents are shown as following:
A general frame for optimization-colorization is put forward, and it is proved that optimization-colorization is an exact process of chrominance blending, where individual chrominance blending weight is equivalent to the pixel's first-reach probability to relevant stroke. In addition, its equivalent circuit is established, which convert colorization process into determining voltage distribution of all node in this circuit, and thus provides different view, electrical theory, to address colorization. The above implicit blending mechanism not only make it available to modify stroke's color and position respectively, but also inspires developing negative label which, in contrast to traditional label, plays the role of disappear specific label, makes good the deficiencies of traditional one as well as extends flexibility in improvement for poor result. In addition, the equivalence between blending weight and first-reach probability prepares analytical tool to investigate the very reason for falsehood.
It is determined analytically that common algorithms are sensitive to distribution of stroke and tend to perform poorly over weak boundary areas, and three improvement methods are proposed. The first one employs the idea of evenness, but optimizes its implementation, which leads to better robustness and high speed. The second one employs blending mechanism discussed in the last chapter, can control width of chrominance transit area via bending-weight-factor, and provides better quality result. The last one introduces a new label to indicate weak boundary and provide relevant treatment.
It is proved that common colorization methods are inevitable to perform badly in scattered object. Existing function is assigned artificially as one of some kernel functions, hard to capture the affinity accurately between pixels in complicated texture area. Aiming at this problem, a feature of natural color images is employed in modeling weight function. Firstly, a local linear chrominance-luminance relation was extracted from the distribution of pixels in color images, and then served as prior assumption, generalized to the whole image and finally provides a novel chrominance weight function model. To recolorization, a two-layers propagation algorithm incorporated with regions cues is put forward. Firstly, Regions by over-segmentation are combined with pixels to construct a two layer weight graph. In contrast to previous works which only employ connection between neighboring pixels, both full-connections in region layer and inter-connections between the pixels and their corresponding regions are introduced into this graph additionally. Then all these connections are integrated in a chrominance iteration formulation, not only facilitates propagation of local grouping cues across larger image areas but partly enforces color edit consistency inside each region. Because updating is performed in the case of membership of all pixels to every label, thereby the method can be extended to segmentation via comparison to resulting membership.
Existing colorization algorithms can hardly provide pleasant visual effect in highlight or shadow areas. Motivated by the general imaging principle of natural color images, a realism improvement approach based on post-process correction in chrominance is proposed. First, an imaging model is built where influence of both light and objective on resulting image is decoupled. Then, a further chrominance-luminance relation model for any pixel imaged in white light is established and employed to identify the very reason for falsehood resulted from existing colorization methods and inspires a realism improvement strategy based on chrominance correction. Since only a grey parameter is to be set, two convenient operation modes are available-automatic coarse adjustment based on default values, and fine tuning by user's intervention. In addition, this decupling model makes it easy to extend colorization to case of color light. This proposed method could provide a general platform to improve realism of colorization result.
In order to speed colorization, a novel colorization strategy characterized as superpixel instead of basic pixel during colorization is put forward. Based on analysis to shortage of existing method, the reasonable criterion is formulated according to discussion of characteristics of colorization and facilitate selecting appropriate superpixel which lead to colorization in high speed with edges preserved. And then a guided filter is used to smooth out the result based on superpixel. Combining with improvement in colorization discussed in earlier chapter, we build a fast and flexible colorization system as this algorithm's another application. User can modifies scribbles in real-time according to visual result thanks to short runtime (below one second) until get pleasant visual result.
引文
[1]Ruderman D L, Cronin T W, Chiao C C. Statistics of cone responses to natural images:implications for visual coding[J]. Journal of the Optical Society of America,1998,15(8):2036-2045
[2]贾云涛,胡事民.基于图切分的交互式图像染色算法[J].计算机学报,2006,29(3)：508-513.
[3]Boykov Y, Jolly M P. Interactive graph cuts for optimal boundary and region segmentation of objects in N-D images[C]. Proceedings of International Conference on Image Processing (ICCV), Vancouver, Canada:IEEE,2001: 105-112
[4]Liu X, Liu J, Feng Z. Colorization using segmentation with random walk[C]. Proceedings of International Conference on Computer Analysis of Images and Patterns, Munster, Germany:Springer-Verlag,2009:468-475.
[5]Jacob V G, Gupta S. Colorization of grayscale images and videos using a semi-automatic approach[C]. Proceedings of 16th IEEE International Conference on Image Processing (ICIP2009), Cairo, Egypt,2009:1653-1656.
[6]Horiuchi T. Estimation of color for gray-level image by probabilistic relaxation[C]. Proceedings of the 16 the International Conference on Pattern Recognition, Quebec, Canada:IEEE,2002:867-870.
[7]Horiuchi T. Colorization algorithm using probabilistic relaxation[J]. Image and Vision Computing,2004,22(3):197-202
[8]Horiuchi T, Hirano S. Colorization algorithm for grayscale image by propagating seed pixels [C]. Proceedings of 2003 IEEE International Conference on Image Processing, Barcelona, Spain:IEEE,2003:457-460.
[9]Horiuchi T, Kotera H. Colorization for monochrome image with texture[C]. Proceedings of 13th Color Imaging Conference, Scottsdale, USA:IEEE,2005: 245-250.
[10]Chen T, Wang Y, Schillings V, et al. Grayscale image matting and colorization[C].Proceedings of 2004 Asian Conference on Computer Vision, Korea:ACM,2004:1164-1169.
[11]Chuang, Y Y. Curless B. Salesin D, et al. A bayesian approach to digital matting[C]. Proceedings of 2001 Computer Vision and Pattern Recognition, Kauai,USA:IEEE,2001,264-271.
[12]Dalmau C O, Rivera M, and Mayorga P P. Computing the a-channel with probabilistic segmentation for image colorization[C]. Proceedings of 2007 IEEE International Conference on Computer Vision, Rio de Janeiro, Brazil:IEEE,2007:1-7.
[13]Rother C, Kolmogorov V, Blake A. Grabcut-Interactive foreground extraction using iterated graph cuts[J]. ACM SIGGRAPH,2004,23(3):309-314.
[14]Grady L, Schiwietz, S. Aharon, and Westermann R. Random walks for interactive alpha-matting[C]. Proceedings of 2005 International Conference on Visualization, Imaging and Image Processing, Benidorm, Spain:ACTA Press,2005:423-429.
[15]Wang J, Cohen M F. An iterative optimization approach for unified image segmentation and matting[C]. Proceedings of IEEE International Conference on Computer Vision, Beijing, China:IEEE,2005:936-943.
[16]Guan Y, Chen W, Liang X, etal. Easy matting:a stroke based approach for continuous image matting[J]. Eurographics,2006:567-576.
[17]Wang J, Cohen M F. Optimized color sampling for robust matting[C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, USA:IEEE,2007:1-8.
[18]Xiang S M, Nie F P, Zhang C S. Semi-supervised classification via local spline regression[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010,32(11):2039-2053
[19]Wang J, Agrawala M, Cohen M F. Soft scissors:An interactive tool for real time high quality matting[J]. ACM SIGGRAPH,2007,26(3):9-16.
[20]Levin A, Lischinski A, Weiss Y. A closed form solution to natural image matting[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008,30(2):228-242.
[21]Levin A, Rav-Acha A, Lischinski D. Spectral matting[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(10):1699-1712.
[22]Rhemann C, Rother C, Rav-Acha A, et al. High resolution matting via interactive trimap segmentation[C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, USA:IEEE,2008:1-8.
[23]Singaraju D, Rother C, Rhemann C. New appearance models for image matting [C]. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Miami, USA:IEEE,2009:659-666.
[24]Konushin V, Vezhnevets V. Interactive image colorization and recoloring based on coupled map lattices[C]. Proceedings of Graphicon,2006:231-234.
[25]Vezhnevets V, Konouchine V. Grow cut-interactive multi-label N-D image segmentation[C]. Proceedings of Graphicon.2005:150-156.
[26]Heu J H, Hyun D Y, Kim C S, et al. Image and video colorization based on prioritized source propagation[C]. Proceedings of the 16th International Conference of Image Processing, Cairo, Egypt:IEEE,2009:465-468
[27]Bertalmio M, Sapiro G, Gaselles V, et al. Image inpainting[C]. Proceedings of ACM SIGGRAPH, New York:ACM,2000:417-424.
[28]赵文华.偏微分方程在图像处理中的几种应用[D].杭州：浙江大学,2004.
[29]秦川.图像修复和图像编辑的偏微分方程模型及其求解[D],上海：上海大学,2008.
[30]滕升华,谌安军,邹谋炎.一种基于拉普拉斯方程的图像彩色化方法[J].中国图象图形学报,2006(4)：45-48.
[31]彭宏京,顾佳玲,段江.扩散张量加权梯度域图像彩色化方法[J].计算机辅助设计与图形学学报,2007,19(9)：1114-1118
[32]王泽文,张小明.基于p-Laplace方程的图像彩色化方法[J].工程图学学报,2010,31(6)：62-67
[33]Lezoray O, Vinh T T, Elmoataz A. Nonlocal graph regularization for image colorization [C]. Proceedings of 19th International Conference on Pattern Recognition, Anchorage, USA:IEEE,2008,11-14.
[34]Levin A, Lischinski D, Weiss Y, Colorization using optimization, ACM Transaction on Graph.,2004,23(3):689-694.
[35]Qiu G, Guan J. Color by linear neighborhood embedding[C]. Proceedings of IEEE International Conference on Image Processing, Genoa, Italy:IEEE,2005: 988-991.
[36]Liu B B, Liu M, Wang G L. Colorization based on image manifold learning [C]. IEEE Region Conference on TENCON, HongKong, China:IEEE,2006:1-3
[37]Roweis S T, Saul L K. Nonlinear dimensionality by locally linear embedding[J]. Science,2000,290:2323-2326
[38]Wang H J, Gan Z L, Zhang Y B, et al. Novel colorization method based on correlation neighborhood similarity pixels priori[C]. Proceedings of 11th International Conference on Signal Processing, Beijing, China:IEEE,2012: 885-888
[39]Huang Y C, Tung Y S. Chen J C, et al. An adaptive edge detection based colorization algorithm and its applications[C]. Proceedings of 13th annual ACM international conference on Multimedia, New Jersey, USA:ACM,2005:351-354.
[40]Nie D D, Ma D L, Xiao S, et al. Grey-scale image colorization by local correlation based optimization algorithm[C].Proceedings of Visual Information and Information Systems, Berlin, Germany:Springer-Verlag,,2005:13-23.
[41]滕升华,谌安军,袁建华,等.一种改进的基于过度分割的图像彩色化方法[J].电子与信息学报,2006(7)：60-64.
[42]Nie D D, Ma Q Y, Ma L Z, et al. Optimization based grayscale image Colorization[J]. Pattern Recognition Letters,2007,(28):1445-1451.
[43]胡伟,秦开怀.高分辨率灰度图像的快速多分辨率着色[J].计算机学报,2009(5)：62-69.
[44]Liu B B, Lu Z M. Image colourisation using graph-based semi-supervised learning[J]. IET Image Process,2009,3 (3):115-120
[45]Yatziv L, Sapiro G, Fast image and video colorization using chrominance blending[J]. IEEE Transactions on Image Processing,2006,15(5):1120-1129.
[46]Sethian J A. A fast marching level-set method for monotonically advancing fronts [J]. Proceedings of National Academic Science,1996,93(4):1591-1595.
[47]Dijkstra E. A note on two problems in connection with graphs [C]. Numerische Mathematik,1959,1:269-271.
[48]Yao L, MA L Z, WU D. Fast colorization using edge and gradient constraints[C]. Proceedings of 15th International Conference of Central Europe Computing Graphics, Visualization,2007,309-316
[49]Kim T, Kyoung M. Lee, S. Lee. Edge-preserving colorization using data-driven random walks with restart[C]. Proceedings of the 16th IEEE International Conference on Image Processing, Cairo, Egypt:IEEE,2009:1661-1664
[50]Canny J F. A computational approach to edge detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1986,8(6):679-698
[51]Lagodzinski P, Smilka P. On the application of distance transformation in digital image colorization [C]. Proceedings of International Conference on Computer Recognition Systems, Wrocaw, Poland:Springer,2008,45(2):108-116.
[52]Lagodzinski P, Smilka B. Fast digital image colorization technique [J]. IEEE International Symposium on Signal Processing and Information Technology, 2007(12):813-818.
[53]Lagodzinski P, Smolka B. Digital image colorization based on probabilistic distance transform[J]. Lecture Notes in Computer Science, Berlin Germany: Springer-Verlag,2008:626-634.
[54]Madeira J S, Stork A, Grob M H. An approach to computer supported cartooning[J]. The Visual Computer,1996(12):1-17.
[55]崔会卿.基于聚类和距离变换的数字图像彩色化技术[D],河北：河北师范大学,2009.
[56]Kawulok M, Smolka B. Competitive image colorization[C]. Proceedings of 2010 IEEE 17th International Conference on Image Processing[C], HongKong,China:IEEE,2010:405-408
[57]Kawulok M, Smolka B. Texture-adaptive image colorization framework[J]. EURASIP Journal on Advances in Signal Processing,2011,99(1):1-15
[58]李志永,滕升华,杜坤,等.基于不平度颜色混合的图像彩色化方法[J].电子与信息学报,2008(3)：514-517.
[59]李志永,滕升华,杜坤,等.基于不平度的快速图像彩色化方法[J].中国科学院研究生院学报,2008(2)：233-237.
[60]李志永.黑白影像的彩色化研究[D].北京：中国科学院电子所,2007
[61]Luan Q, Wen F, Cohen-or D, et al. Natural image colorization[C]. Proceedings of Eurographics Symposium on Rendering, Grenoble, France:ACM,2007: 309-320.
[62]栾青.色彩与结构在图像编辑和风格化中的应用[D].安徽：中国科学技术大学,2009.
[63]Qu Y, Wong T, Heng P. Manga colorization[J]. ACM Transactions on Graphics, 2006,25(3):1214-1220.
[64]Sykora, D, Burianek J, Zara J. Unsupervised colorization of black-and-white cartoons[C]. Proceedings of the 3rd international symposium on Non-photorealistic animation and rendering, Annecy, France:ACM,2004:121-127.
[65]Sykora D, Dingliana J, Collins S. Lazybrush:flexible painting tool for hand-drawn cartoons[J]. Computer Graphics Forum,2009,28 (2):599-608.
[66]Reinhard E, Ashikhmin M, Gooch B, et al. Color transfer between images[J]. IEEE Computer Graphics Application,2001,21(5):34-41.
[67]Welsh T, Ashikhmin M, Mueller K. Transferring color to greyscale images, ACM Transactions on Graph.,2002,21(3):277-280.
[68]李建明,叶飞,于守秋,等.一种快速灰度图像彩色化算法[J].中国图象图形学报,2007,12(3)：537-540.
[69]Chen T, Wang Y, Schillings V, et al. Grayscale image matting and colorization[C]. Proceedings of Asian Conference of Computer Vision, Korea, 2004:1164-1169.
[70]Chuang Y Y, Curless B, Salesin D, et al. A bayesian approach to digital matting [C]. Proceedings of Computer Vision and Pattern Recognition,2001,264-271.
[71]Morimoto Y, Taguchi Y, Naemura T. Automatic colorization of grayscale images using multiple images on the web[C]. Proceedings of SIGGRAPH 2009, New Orleans, Louisiana:ACM,2009:1-9.
[72]Hays J, Efros A A. Scene completion using millions of Photographs[J]. ACM Transactions of Graph,2007,26(3):87-94.
[73]Liu X, Wan L, Qu Yet al., Intrinsic colorization[C]. Proceedings of ACM SIGGRAPH Asia 2008, Singapore:ACM,2008,1-9.
[74]Bousseau A, Paris S, Fret al. User-assisted intrinsic images[C]. Proceedings of ACM SIGGRAPH Asia 2009, Yokohama, Japan:ACM,2009:1-10.
[75]Grosse R, Johnson M K, Adelson E H, et al. Ground truth dataset and baseline evaluations for intrinsic image algorithms[C]. Proceedings of IEEE 12th International Conference on Computer Vision, Kyoto, Japan:IEEE,2009: 2335-2342.
[76]赵国英,向世明,李华.高阶矩在颜色传输中的应用[J].计算机辅助设计与图形学学报,2004(1)：2-66.
[77]Greenfield G R, House D H. Image recoloring induced by palette color associations[J]. Journal of WSCG,2003(11):189-196.
[78]Sykora D, Burianek J, Zara J. Unsupervised colorization of black-and-white cartoons[C]. Proceedings of the 3rd International Symposium on Non-Photorealistic Animation and Rendering, Annecy, France:ACM,2004:121-127.
[79]Pitie F, Kokaram A C, Dahyot R. N-dimensional probability density function transfer and its application to color transfer[C]. Proceedings of the 10th IEEE International Conference on Computer Vision, Beijing, China:IEEE,2005: 1434-1439.
[80]Pitie F, Kokaram A C. The linear monge-kantorovitch colour mapping for example-based colour transfer[C]. Proceedings of 4th European Conference on Visual Media Production,2007:1-9.
[81]Pitie F, Kokaram A. Dahyot R. Automated color grading using colour distribution transfer[J]. Computer Vision and Image Understanding,2007, 107(1):123-137.
[82]Tai Y, Jia J, Tang C. Local color transfer via probabilistic segmentation by expectation-maximization[C]. Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, USA: IEEE,2005:747-754.
[83]Xiang Y, Zou B J, Wang H. Multi-source color transfer for natural images[C]. Proceedings of The lsth IEEE International Conference on Image Processing, SanDiego, USA:IEEE,2008:469-472
[84]Xiang Y, Zou B J, Li H. Selective color transfer with multi-source images[J]. Pattern Reeognition Letters,2009,7(30):682-689
[85]钱小燕,肖亮,吴慧中.模糊颜色聚类在颜色传输中的应用[J].计算机辅助设计与图形学学报,2006,18(9)：1332-1336.
[86]汪世刚,吕东辉.基于最优聚类数和直方图匹配的图像彩色化方法[J].计算机应用,2010(2)：35 1-353.
[87]Irony R, Cohen D, Lischinski D. Colorization by example[C]. In:Proceedings of Eurographics Symposium on Rendering, Konstanz Germany:ACM,2005: 201-210
[88]朱黎博,孙韶媛,王冬.基于图像分割和色彩扩展的灰度图像彩色化方法[J],微型电脑应用,2009(5)：4-6.
[89]朱黎博,孙韶媛,谷小婧等.基于色彩传递与扩展的图像着色算法[J],中国图象图形学报,2010,15(2)：200-205.
[90]孟敏,刘利刚.勾画式局部颜色迁移[J].计算机辅助设计与图形学学报,2008,20(7)：838-842
[91]Luan Q, Wen F, Xu Y Q. Color transfer brush[C]. Proceedings of the 15th Pacific Conference on Computer Graphics and Applications, Hawaii, USA: IEEE,2007:465-468.
[92]An X, Pellacini F. User-controllable color transfer [J]. Computer Graphics Forum,2010,29(2):263-271.
[93]An X, Pellacini F. AppProp:all-pairs appearance-space edit propagation[C]. Proceedings of ACM SIGGRAPH, Los Angeles, USA:ACM,2008:1-9.
[94]Chen Y, Yao H, Zhao Y. Image Colorization with diffusion tensor and edge enhancing[J]. Journal of Information & Computational Science,2011,8(14): 3329-3336
[95]Yao C, Yang X K, Wang J, et al. Patch-driven colorization[J]. Optical Engineering,2010,49(1):1-5.
[96]Sheng B, Sun H Q, Chen S B, et al. Colorization using the rotation-invariant feature space[J]. IEEE Computer Graphics and Applications,2011,31(2):24-35
[97]Yang W X, Cai J F, Zheng J M,et al. User-friendly interactive image segmentation through unified combinatorial user inputs[J]. IEEE Transactions on Image Processing,2010,19(9):2470-2479
[98]Omer I, Werman M. Color lines:image specific color representation[C]. Proceedings of IEEE Computer Vision and Pattern Recognition, New York, USA:IEEE,2004:946-953.
[99]Omer I, Werman M. Image specific feature similarities[C]. Proceedings of European Conference on Computer Vision, Graz:Springer,2006:321-333.
[100]Grady L, Schwartz E L. Faster graph-theoretic image processing via small-world and quadtree topologies[C].Proceedings of IEEE Computer Vision and Pattern Recognition, New York,USA:IEEE,2004:360-365.
[101]Boykov Y, Veksler O, Zabih R. Fast approximate energy minimization via graph cuts[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2001, 23(11):1222-1239.
[102]Rother C, Kolmogorov V, Blake A. Grabcut-interactive foreground segmentation using iterated graph cuts[J]. ACM Transactions on Graphics,2004, 23(3):309-314.
[103]刘嘉,王宏琦.一种基于图割的交互式图像分割方法[J].电子与信息学报,2008,30(8)：1973-1976
[104]Grady L. Random walks for image segmentation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(11):1768-1783.
[105]Kim T H, Lee K M, Lee S U. Generative image segmentation using random walks with restart[C]. Proceedings of the 9th European Conference on Computer Vision, Berlin, Germany:Springer,2008:264-275
[106]徐海霞,田铮,丁明涛,等.基于图上随机游走过程的SAR图像图谱分割方法[J].光电子激光,2009,20(7)：967-971
[107]Bai Xue, Sapiro G. Distancecut:interactive segmentation and matting of images and videos[C]. Proceedings of 2007 IEEE International Conference on Image Processing, Texas, USA:IEEE,2007(2):249-252
[108]Criminisi A, Sharp T, Blake A. GeoS:geodesic image segmentation [C]. Proceedings of the 9th European Conference on Computer Vision, Marseille, France:Springer,2008:99-112
[109]Couprie C, Grady L, Najman L et al. Power watersheds:a unifying graph-based optimization framework[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(7):1384-1399.
[110]Sinop A K, Grady L. A seeded image segmentation framework unifying graph cuts and random walker which yields a new algorithm[J]. Proceedings of the 11th International Conference on Computer Vision, Rio de Janeiro, Brazil: IEEE,2007:1-8.
[111]白向峰,李艾华,李喜来,等.基于颜色和梯度差估计器的运动阴影检测[J].光电子激光,2011,22(9)：1390-1394.
[112]刘尚平,陈骥.荧光视网膜图像的照度均衡及自适应血管增强算法[J].光电子激光,2011,22(5)：793-797.
[113]侯明正,冯子亮,刘艳丽等.光照变动条件下基于图切割算法的运动目标跟踪[J].光电子激光,2012,23(5)：986-992.
[114]Klinker G J, Shafer S A, Kanade T. A physical approach to color image understanding [J]. International Journal of Computer Vision,1990,4(l):7-38.
[115]Vazquez E, Baldrich R, Weijer J, et al. Describing reflectance for colour segmentation robust to shadows, highlights and textures[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,2011,33(5):917-930
[116]Shi J, Malik J. Normalized cuts and image segmentation[J]. IEEE Transactions of Pattern Analysis and Machine Intelligence,2000,22(8):888-905
[117]Felzenszwalb P, Huttenlocher D. Efficient Graph-based image segmentatiodn[J]. International Journal of Computer Vision,2004,29(2):167-181
[118]Moore A, Prince S, Warrell J, et al. Super-pixel lattices[C]. Proceedings of IEEE Conference of Computer Vision and Pattern Recognition, Cairo, Egypt:IEEE, 2008:1-8
[119]Vincent L, Soille P. Watersheds in digital spaces:an efficient algorithm based on immersion simulations[J], IEEE Transactions on Pattern Analysis and Machine Intelligence,1991,13(6):583-598
[120]Comaniciu, Meer P. Mean shift:A robust approach toward significantly reduce the complexity of the graph, making the feature space analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5): 603-619
[121]Vedaldi A,Soatto S. Quick shift and kernel methods for mode seeking[C]. Proceedings of European Conference of Computer Vision, Marseille, France: Springer,2008:705-718
[122]Levinshtein A, Stere A, Kiriakos N, et al. TurboPixels:fast superpixels using geometric flows[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(12):2290-2297
[123]Achanta A, Shaji A, Lucci A, et al. SLIC:superpixels compared to state-of-the-art superpixel methods[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(11)-.2274-2281
[124]Perona P, Malik J.Scale-space and edge detection using anisotropic diffusion[J]. IEEE Transactions of Pattern Analysis and Intelligence,1990, 12(7):629-639
[125]Farbman Z,Fattal R,Lischinski D,et al. Edge-preserving decompositions multi-scale tone and detail manipulation[C]. Proceedings of ACM Siggraph,2008.
[126]He Kaiming, Sun Jian, Tang Xiaoou.Single image haze removal using dark channel prior[J]. IEEE Transactions of Pattern Analysis and Intelligence,2011, 32(11):2341-2353
[127]Aurich V, Weule J. Non-linear gaussian filters performing edge preserving diffusion[J]. Mustererkennung,1995,17:538-545
[128]Smith S M, Brady J M. Susan-a new approach to low level image processing[J]. International Journal of Computer Vision,1995,23:45-7
[129]Weiss B. Fast median and bilateral filtering[J]. ACM Transactions of Graphics, 2006,25(3):519-526
[130]Yang Q, Tan K H, Ahuja N. Real-time O(1) bilateral filtering[C]. Proceedings of IEEE Conference of Computer Vision and Pattern Recognition,2009,557-564
[131]He Kaiming, Sun Jian, Tang Xiaoou. Guided image filtering[J]. IEEE Transactions of Pattern Analysis and Intelligence,2013,35(6):1397-1409