古代壁画图像保护与智能修复技术研究
|
摘要
濒危古代壁画的保护具有紧迫性和复杂性,传统保护手段的低效率和保护人员的缺乏,制约了我国古代壁画保护事业的发展。因此,引入计算机技术特别是图像处理技术就显得很有必要。利用图像处理技术辅助古代壁画保护不仅可以降低古代壁画保护的难度、减少人为因素对壁画的损坏,也可以实现资源共享,提高工作效率。
本文对古代壁画图像保护与智能修复技术的研究主要用于解决古代壁画的线描图生成、病害识别、缺损区域分割以及缺损修复等问题。现有相关图像处理和修复技术没有紧密结合古代壁画图像的特征及其相关文化艺术信息,难以解决上述问题,其不足主要表现在：首先,古代壁画中线描笔划具有特定的艺术风格,现有用于生成线描图的图像处理技术没有考虑上述风格；其次,在进行古代壁画病害的特征提取时,没有针对古代壁画病害图像存在的亮度和角度不一致以及含有噪声等特点进行专门设计；再次,能用于古代壁画缺损区域分割的图像分割技术还无法有效综合底层线索和高层语义知识,古代壁画缺损的类别信息等高层语义知识没有得到很好利用；最后,能用于古代壁画缺损虚拟修复的图像缺损信息修复技术存在错误传递或未考虑结构信息等问题。
为了解决以上问题,本文对古代壁画图像保护与智能修复技术进行了深入的研究。主要研究内容如下：
1.提出了一种壁画线描图生成技术。首先根据古代壁画中线描具有的特殊颜色和狭长形体结构,提出了一种综合颜色和形状特征的线描提取算法,自动提取出壁画中残留的线描笔划得到不完整的线描图；在此基础上,提出了一种基于笔划模型的线描图交互绘制方法,通过定义基于骨架的笔划模型来模拟艺术家总结出的线描笔划风格并作为笔划风格模板,在交互绘制时利用边缘跟踪和笔划风格类比学习算法辅助线描图的交互绘制。该方法同时采用了艺术家的专业知识和用户交互信息,能够实现任意古代壁画的线描图绘制。
2.提出了一种基于纹理特征和支持向量机的壁画病害识别技术。首先针对古代壁画病害图像存在亮度和角度不一致以及含有噪声等情况,提出了一种基于小波局部二值模式的旋转无关和灰度尺度无关纹理特征提取方法,通过对图像进行小波变换并抑制部分高频信息,克服了原有局部二值模式纹理特征提取方法存在的对噪声敏感性和尺度受内存大小限制等缺点；然后,针对古代壁画病害识别属于多类分类问题的情况,采用了一种新的基于树结构的多类支持向量机,通过利用核空间的类间距度量,克服了传统方法中直接在低维特征空间上计算各类间的间距而无法真实反映类间距的问题。最后,利用上述小波局部二值模式纹理特征提取方法和多类支持向量机实现了古代壁画病害的识别。
3.提出了一种基于图割的壁画缺损区域同步检测与分割技术。通过把古代壁画缺损区域的检测和分割问题建模为条件随机场中的最大后验概率问题,进而转化为基于图割的能量函数最小化问题,并利用类别信息等高层语义知识和底层线索分别来定义似然能量函数和先验能量函数,有效地综合了自下往上和自上而下的分割算法思想,实现了古代壁画缺损区域的准确分割。
4.提出了基于离散优化的壁画图像缺损信息修复技术。为了克服现有图像缺损信息修复算法存在的错误传递或未考虑结构信息等不足并充分利用古代壁画图像中重复性图案比较多的特点,提出了两种基于离散优化的壁画图像缺损信息修复算法，其基本思想都是通过对图像缺损区域栅格化采样并建模,把缺损信息修复问题转化为定义在离散马尔科夫随机场的能量函数最小化问题,并设计了两种不同的能量函数,分别采用类EM和置信传播算法实现能量函数最小化的优化,从整体上考量缺损区域的修复状况,避免了传统贪婪修复算法存在的错误传递等问题；同时,通过在设计能量函数时综合利用纹理和结构信息来设置权值保证了周围已知像素比例大且结构信息强的缺损部分被优先修复。
The preservation of endangered ancient frescos is an urgent and complex task, however, the traditional methods are inefficient with a lack of ancient frescoes preservation personnel, which hinders the development of ancient frescoes preservation cause. As a result, the introduction of computer technology, especially image processing technology becomes very important, for the ancient fresco preservation assisted by image processing technology can not only reduces damages caused by human factor but also greatly improve efficiency.
In this paper, the research on intelligent image processing and inpainting technologies for the preservation of ancient fresco was used to solve the ancient fresco line drawings generation, ancient fresco disease recognition, ancient fresco damaged area segmentation and restoration issues. The existing image processing technology can hardly solve these problems for its low connection with the characteristics of ancient fresco and information of related art and culture. Its shortcomings mainly include:Firstly, the existing line drawings generation techniques don't take the specific style information existed in ancient frescos into account. Secondly, the existing feature extraction and recognition technology don't consider the inconsistencies of brightness and angle and noise characteristics of ancient fresco images. Thirdly, the existing image segmentation technology cannot effectively integrate high-level semantic knowledge with underlying clues. At last, the existing inpainting technology used for the virtual restoration of ancient frescos has problems of error propagation and accumulation or lack of considering structural information.
In order to solve the problems mentioned above, this dissertation focuses on key technologies of intelligent image processing and inpainting for ancient fresco preservation. The main research topics are as follows:
1. An ancient fresco line drawing generation method was proposed. As most of Chinese frescoes are traditional meticulous painting, which contains line drawing strokes, an ancient fresco line drawing extraction algorithm using color and shape information was presented, color and shape features were firstly used to extract the line drawing strokes, then a SVM classifier was trained and used to remove the cracks which might be misidentified as line drawing strokes. Then, an interactive line drawing generation algorithm was presented. The algorithm first got the contour of a fresco image which was composed of many connected curves, and then rendered the strokes by learning styles from examples. As both the expertise of the artist and user interaction information were used, the method could get line-drawings of any ancient frescoes.
2. An ancient fresco diseases recognition method via texture feature and support vector machine was proposed. Firstly, a multi-resolution gray-scale and rotation invariant texture feature extraction with wavlet local binary patterns was presented, which had advantages of computational simplicity and strong antinoise ability. Then, a new tree-structured support vector machine for multi-class classification was presented. The distances measured at the kernel space and fuzzy clustering were used to construct the tree-structured multi-class SVM, which had more classification accuracy comparable to some popular multi-class SVM approaches. At last, the improved feature exactor and classifier were used to implement the ancient fresco diseases recognition algorithm.
3. An efficient ancient fresco damaged area concurrent detection and segmentation algorithm based on graph cut was proposed. We cast the problem of damaged areas segmentation within a fresco image as that of estimating a probabilistic model which consisted of an object category model in addition to the grid CRF. While low-level cues provided bottom-up information, the damaged areas category model based on relevance vector machine incorporated top-down information about the color and texture of the damaged areas. In contrast to most existing algorithms which trained top-down and bottom-up modules separately, our method took into account both bottom-up and top-down cues simultaneously.
4. Two ancient fresco image inpainting algorithms via discrete optimization were proposed. As greedy synthesis based image inpainting algorithms might cause visual inconsistency, and some other global optimization based image inpainting algorithms might not consider structure information, two fast ancient fresco image inpainting algorithms via discrete optimization were proposed. The first algorithm formulated the image inpainting problem as minimization of a weighted energy function, which was optimized using an Expectation Maximization(EM)-like algorithm. The second algorithm formulated the image inpainting problem as a graph labeling problem, which was optimized using belief propagation algorithm, besides, a non-local mean based label candidates reduction was presented to improve the performance of belief propagation.
本文对古代壁画图像保护与智能修复技术的研究主要用于解决古代壁画的线描图生成、病害识别、缺损区域分割以及缺损修复等问题。现有相关图像处理和修复技术没有紧密结合古代壁画图像的特征及其相关文化艺术信息,难以解决上述问题,其不足主要表现在：首先,古代壁画中线描笔划具有特定的艺术风格,现有用于生成线描图的图像处理技术没有考虑上述风格；其次,在进行古代壁画病害的特征提取时,没有针对古代壁画病害图像存在的亮度和角度不一致以及含有噪声等特点进行专门设计；再次,能用于古代壁画缺损区域分割的图像分割技术还无法有效综合底层线索和高层语义知识,古代壁画缺损的类别信息等高层语义知识没有得到很好利用；最后,能用于古代壁画缺损虚拟修复的图像缺损信息修复技术存在错误传递或未考虑结构信息等问题。
为了解决以上问题,本文对古代壁画图像保护与智能修复技术进行了深入的研究。主要研究内容如下：
1.提出了一种壁画线描图生成技术。首先根据古代壁画中线描具有的特殊颜色和狭长形体结构,提出了一种综合颜色和形状特征的线描提取算法,自动提取出壁画中残留的线描笔划得到不完整的线描图；在此基础上,提出了一种基于笔划模型的线描图交互绘制方法,通过定义基于骨架的笔划模型来模拟艺术家总结出的线描笔划风格并作为笔划风格模板,在交互绘制时利用边缘跟踪和笔划风格类比学习算法辅助线描图的交互绘制。该方法同时采用了艺术家的专业知识和用户交互信息,能够实现任意古代壁画的线描图绘制。
2.提出了一种基于纹理特征和支持向量机的壁画病害识别技术。首先针对古代壁画病害图像存在亮度和角度不一致以及含有噪声等情况,提出了一种基于小波局部二值模式的旋转无关和灰度尺度无关纹理特征提取方法,通过对图像进行小波变换并抑制部分高频信息,克服了原有局部二值模式纹理特征提取方法存在的对噪声敏感性和尺度受内存大小限制等缺点；然后,针对古代壁画病害识别属于多类分类问题的情况,采用了一种新的基于树结构的多类支持向量机,通过利用核空间的类间距度量,克服了传统方法中直接在低维特征空间上计算各类间的间距而无法真实反映类间距的问题。最后,利用上述小波局部二值模式纹理特征提取方法和多类支持向量机实现了古代壁画病害的识别。
3.提出了一种基于图割的壁画缺损区域同步检测与分割技术。通过把古代壁画缺损区域的检测和分割问题建模为条件随机场中的最大后验概率问题,进而转化为基于图割的能量函数最小化问题,并利用类别信息等高层语义知识和底层线索分别来定义似然能量函数和先验能量函数,有效地综合了自下往上和自上而下的分割算法思想,实现了古代壁画缺损区域的准确分割。
4.提出了基于离散优化的壁画图像缺损信息修复技术。为了克服现有图像缺损信息修复算法存在的错误传递或未考虑结构信息等不足并充分利用古代壁画图像中重复性图案比较多的特点,提出了两种基于离散优化的壁画图像缺损信息修复算法，其基本思想都是通过对图像缺损区域栅格化采样并建模,把缺损信息修复问题转化为定义在离散马尔科夫随机场的能量函数最小化问题,并设计了两种不同的能量函数,分别采用类EM和置信传播算法实现能量函数最小化的优化,从整体上考量缺损区域的修复状况,避免了传统贪婪修复算法存在的错误传递等问题；同时,通过在设计能量函数时综合利用纹理和结构信息来设置权值保证了周围已知像素比例大且结构信息强的缺损部分被优先修复。
The preservation of endangered ancient frescos is an urgent and complex task, however, the traditional methods are inefficient with a lack of ancient frescoes preservation personnel, which hinders the development of ancient frescoes preservation cause. As a result, the introduction of computer technology, especially image processing technology becomes very important, for the ancient fresco preservation assisted by image processing technology can not only reduces damages caused by human factor but also greatly improve efficiency.
In this paper, the research on intelligent image processing and inpainting technologies for the preservation of ancient fresco was used to solve the ancient fresco line drawings generation, ancient fresco disease recognition, ancient fresco damaged area segmentation and restoration issues. The existing image processing technology can hardly solve these problems for its low connection with the characteristics of ancient fresco and information of related art and culture. Its shortcomings mainly include:Firstly, the existing line drawings generation techniques don't take the specific style information existed in ancient frescos into account. Secondly, the existing feature extraction and recognition technology don't consider the inconsistencies of brightness and angle and noise characteristics of ancient fresco images. Thirdly, the existing image segmentation technology cannot effectively integrate high-level semantic knowledge with underlying clues. At last, the existing inpainting technology used for the virtual restoration of ancient frescos has problems of error propagation and accumulation or lack of considering structural information.
In order to solve the problems mentioned above, this dissertation focuses on key technologies of intelligent image processing and inpainting for ancient fresco preservation. The main research topics are as follows:
1. An ancient fresco line drawing generation method was proposed. As most of Chinese frescoes are traditional meticulous painting, which contains line drawing strokes, an ancient fresco line drawing extraction algorithm using color and shape information was presented, color and shape features were firstly used to extract the line drawing strokes, then a SVM classifier was trained and used to remove the cracks which might be misidentified as line drawing strokes. Then, an interactive line drawing generation algorithm was presented. The algorithm first got the contour of a fresco image which was composed of many connected curves, and then rendered the strokes by learning styles from examples. As both the expertise of the artist and user interaction information were used, the method could get line-drawings of any ancient frescoes.
2. An ancient fresco diseases recognition method via texture feature and support vector machine was proposed. Firstly, a multi-resolution gray-scale and rotation invariant texture feature extraction with wavlet local binary patterns was presented, which had advantages of computational simplicity and strong antinoise ability. Then, a new tree-structured support vector machine for multi-class classification was presented. The distances measured at the kernel space and fuzzy clustering were used to construct the tree-structured multi-class SVM, which had more classification accuracy comparable to some popular multi-class SVM approaches. At last, the improved feature exactor and classifier were used to implement the ancient fresco diseases recognition algorithm.
3. An efficient ancient fresco damaged area concurrent detection and segmentation algorithm based on graph cut was proposed. We cast the problem of damaged areas segmentation within a fresco image as that of estimating a probabilistic model which consisted of an object category model in addition to the grid CRF. While low-level cues provided bottom-up information, the damaged areas category model based on relevance vector machine incorporated top-down information about the color and texture of the damaged areas. In contrast to most existing algorithms which trained top-down and bottom-up modules separately, our method took into account both bottom-up and top-down cues simultaneously.
4. Two ancient fresco image inpainting algorithms via discrete optimization were proposed. As greedy synthesis based image inpainting algorithms might cause visual inconsistency, and some other global optimization based image inpainting algorithms might not consider structure information, two fast ancient fresco image inpainting algorithms via discrete optimization were proposed. The first algorithm formulated the image inpainting problem as minimization of a weighted energy function, which was optimized using an Expectation Maximization(EM)-like algorithm. The second algorithm formulated the image inpainting problem as a graph labeling problem, which was optimized using belief propagation algorithm, besides, a non-local mean based label candidates reduction was presented to improve the performance of belief propagation.
引文
[1]Barni M, Pelagotti A, Piva A. Image processing for the analysis and conservation of paintings:Opportunities and challenges[J]. IEEE Signal processing magazine,2005,22(5):141-144
[2]Koshimizu H, Tominaga M, Fujiwara T, et al. On KANSEI facial image processing for computerized facial caricaturing system PICASSO[C]. In: Proceeds of IEEE International Conference on Systems, Man, and Cybernetics, Tokyo, Japan,1999,6:294-299
[3]Li Y Z, Kobatake H. Extraction of facial sketch image based on morphological processing [C]. In:Proceeds of In:Proceeds of International Conference on Image Processing, Washington, DC, USA,1997,3:316-319
[4]陈洪,郑南宁,梁林等.基于样本学习的肖像画自动生成算法[J].计算机学报,2003,26(2)：147-152
[5]闵锋,桑农.一种基于与或图表示的多风格肖像画自动生成方法[J].计算机学报,2009,32(8)：1595-1602
[6]Yang Y, Zheng NN, Liu YH, et al. Interactive facial sketch expression generation using local constraints[C]. In:Proceeds of IEEE International Conference on Intelligent Computing and Intelligent Systems, Shanghai, China,2009,2:864-868
[7]Kang H W, He W, Chui C K, et al. Interactive sketch generation[J]. The Visual Computer,2005,21(8):821-830
[8]Kang H, Lee S, Chui C K. Coherent line drawing[C]. In:Proceedings of the 5th international symposium on Non-photorealistic animation and rendering, San Diego, California,2007:43-50
[9]Barni M, Bartolini F, Cappellini V. Image processing for virtual restoration of artworks[J]. IEEE Multimedia,2000:34-37
[10]Giakoumis I, Nikolaidis N, Pitas I. Digital image processing techniques for the detection and removal of cracks in digitized paintings[J]. IEEE Transactions on Image Processing,2006,15(1):178-188
[11]Hanbury A, Kammerer P, Zolda E. Painting crack elimination using viscous morphological reconstruction[C].In:Proceeds of 12th International Conference on Image Analysis and Processing, Mantova, Italy,2003: 226-231
[12]Abas F S. Analysis of craquelure patterns for content-based retrieval[D]. Southampton:University of Southampton,2004
[13]Classification of painting cracks for content-based analysis[C]. In:Proceeds of 14th International Conference on Digital Signal Processing, Santorini, Greece, 2003,1:111-114
[14]De Rosa A, Bonacchi A M, Cappellini V, et al. Image segmentation and region filling for virtual restoration of art-works[C]. In:Proceedings of IEEE International Conference on Image Processing, Thessaloniki, Greece,2001,1: 562-565
[15]Chang R C, Sie Y L, Chou S M; Shih, T.K. Photo defect detection for image inpainting[C]. In:Proceeds of Seventh IEEE International Symposium on Multimedia, Irvine, CA, USA,2005:1-5
[16]Nikolaidis N, Pitas I. Digital image processing in painting restoration and archiving[C]. In:Proceedings of IEEE International Conference on Image Processing, Thessaloniki, Greece,2001:586-589
[17]Pappas M, Pitas I. Digital color restoration of old paintings[J]. IEEE Transactions on image processing,2000,9(2):291-294
[18]Battiti R. First-and second-order methods for learning:between steepest descent and Newton's method[J]. Neural computation,1992,4(2):141-166
[19]Barni M, Bartolini F, Cappellini V. Image processing for virtual restoration of artworks[J]. IEEE Multimedia,2000:34-37
[20]潘云鹤,鲁东明.古代敦煌壁画的数字化保护与修复[J].系统仿真学报,2003,15(3)：310-314
[21]华忠,鲁东明.敦煌壁画虚拟复原及演变模拟模型研究[J].中国图象图形学报：A辑,2002,7(002)：181-186
[22]Li X, Lu D, Pan Y. Color restoration and image retrieval for Dunhuang fresco preservation[J]. IEEE Multimedia,2000:38-42
[23]Bertalmio M, Sapiro Q Caselles V, et al. Image inpainting[C]. In:Proceedings of the 27th annual conference on Computer graphics and interactive techniques, New Orleans, Louisiana,2000,417-424
[24]Chan T F, Shen J. Mathematical models for local nontexture inpaintings[J]. SIAM Journal on Applied Mathematics,2001:1019-1043
[25]Chan T F, Shen J. Non-texture inpainting by curvature-driven diffusions (CDD)[J]. J. Visual Comm. Image Rep,2001,12(4):436-449
[26]Esedoglu S, Shen J. Digital inpainting based on the Mumford-Shah-Euler image model[J]. European Journal of Applied Mathematics,2002,13(04): 353-370
[27]张红英,彭启琮.数字图像修复技术综述[J].中国图像图形学报,2007,12(1)：1-10
[28]Bertalmio M, Bertozzi A L, Sapiro G Navier-Stokes, fluid dynamics, and image and video inpainting[C]. In:Proceeds of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Hawaii, 2001,1:355-362
[29]Auclair-Fortier M F, Ziou D. A global approach for solving evolutive heat transfer for image denoising and inpainting [J]. IEEE Transactions on Image Processing,2006,15(9):2558-2574
[30]侯正信,何宇清,许微.一种快速的图像修复算法[J].中国图象图形学报,2007(10)：1909-1912
[31]张红英,彭启琮,吴亚东.数字破损图像的非线性各向异性扩散修补算法[J].计算机辅助设计与图形学学报,2006,18(010)：1541-1546
[32]Efros A A, Leung T K. Texture synthesis by non-parametric sampling[C]. In: Proceedings of the International Conference on Computer Vision, Washington, DC, USA,1999:1033-1038
[33]Drori I, Cohen-Or D, Yeshurun H. Fragment-based image completion[J]. ACM Transactions on Graphics (TOG),2003,22(3):303-312
[34]Criminisi A, Perez P, Toyama K. Region filling and object removal by exemplar-based image inpainting[J]. IEEE Transactions on Image Processing, 2004,13(9):1200-1212
[35]Chen Q, Zhang Y, Liu Y. Image Inpainting with Improved Exemplar-Based Approach[C]. In:Proceeds of International Workshop on Multimedia Content Analysis and Mining, Weihai, China,2007,4577:242-251
[36]Reinhard E, Ashikhmin M, Gooch B, et al. Color transfer between images[J]. IEEE Computer Graphics and Applications,2001:34-41
[37]Wu J, Ruan Q. Object Removal By Cross Isophotes Exemplar-based Inpainting[C]. In:Proceedings of the 18th International Conference on Pattern Recognition, Hong Kong,2006,3:810-813
[38]Wong A, Orchard J. A nonlocal-means approach to exemplar-based inpainting[C]. In:Proceeding of 2008 IEEE International Conference on Image Processing, San Diego, California, USA,2008:2600-2603
[39]Shao XW, Liu ZK, Houqiang Li HQ. An image inpainting approach based on the Poisson equation[C]. In:Proceedings of the Second International Conference on Document Image Analysis for Libraries, Washington, DC, USA, 2006:368-372
[40]Hays J, Efros A A. Scene completion using millions of photographs [J]. ACM Transactions on Graphics,2007,26(3):4-es
[41]KOMODAKIS N, TZIRITAS G Image completion using efficient belief propagation via priority scheduling and dynamic pruning[J]. IEEE Transactions on Image Processing,2007,16(11):2649-2661
[42]Huang T, Chen S, Liu J, et al. Image Inpainting by Global Structure and Texture Propagation[C]. In:Proceedings of the 15th international conference on Multimedia. Augsburg, Germany,2007,901:517-520
[43]葛仕明,程义民,潘浩等.基于离散优化的图像修复[J].中国科学技术大学学报,2008,38(12)：1381-1385
[44]Kwatra V, Essa I, Bobick A, et al. Texture optimization for example-based synthesis[J]. ACM Transactions on Graphics (TOG),2005,24(3):795-802
[45]Sun J, Shum H Y. Image completion with structure propagation[J]. ACM Transactions on Graphics,2005,24(3):861-868
[46]Felzenszwalb P F, Huttenlocher. D P. Efficient belief propagation for early vision[J]. International Journal of Computer Vision,2006,70(1):41-54
[47]Bertalmio M, Vese L, Sapiro G, et al. Simultaneous structure and texture image inpainting[J]. IEEE Transactions on Image Processing,2003,12(8): 882-889
[48]J. H. Yamauchi, H. P. Seidel, Image Restoration Using Multiresolution Texture Synthesis and Image Inpainting[C].In:Proceeds of Computer Graphics International, Tokyo, Japan,2003:120-125
[49]Sonka M., Havac V., Boyle R.图像处理,分析与机器视觉[M].北京：人民邮电出版社,2002
[50]Zhang J, Tan T. Brief review of invariant texture analysis methods[J]. Pattern Recognition,2002,35(3):735-747
[51]Haralick R M, Dinstein I, Shanmugam K. Textural features for image classification[J]. IEEE Transactions on systems, man, and cybernetics,1973, 3(6):610-621
[52]Sarkar A, Sharma K, Sonak R V. A new approach for subset 2-D AR model identification for describing textures[J]. IEEE Transactions on Image Processing,1997,6(3):407-413
[53]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(7):971-987
[54]Chellappa R, Chatterjee S. Classification of texture using Gaussian Markov Random Fields[J]. IEEE Transactions on Acoustics, Speech, and Signal Processing,1985,33(4):959-963
[55]Krishnamachari S, Chellappa R. Muhiresolution Gauss—markov random field models for texture segmentation[J].IEEEE Transactions on Image Processing,1997,6(2):251-267
[56]Y Chitre, A.P. Dhawan, M-band wavelet discrimination of natural textures[J]. Pattern Recognition,1999,32:773-789
[57]A.C. Bovik, Analysis of multichannel narrow-band filters for image texture segmentation, IEEE Transactions on Signal Processing,1990,39:2025-2043
[58]Pavlidis T. Structural Descriptions and Graph Grammars[M]. Berlin, Germany: Springer Press,1980
[59]Soille P. Morphological Image Analysis:Principles and Application [M]. Berlin, Germany:Springer Press,2003
[60]Christopher J.C. A Tutorial on Support Vector Machines for Pattern Recognition[J]. Data Mining and Knowledge Discovery,2004:121-167
[61]Bahlmann C, Haasdonk B, Burkhardt H. On-line handwriting recognition with support vector machines—a kernel approach[C]. In:Proceeds of 8th International Workshop on Frontiers in Handwriting Recognition, Ontario, Canada,2002:49-54
[62]Gordan M, Kotropoulos C, Pitas I. Application of support vector machines classifiers to visual speech recognition[C]. In:Proceedings of 2002 International Conference on Image Processing, New York, USA,2002,3:129-132
[63]Guo Q Li S Z, Chan K. Face recognition by support vector machines[C]. In: Proceedings of Fourth IEEE International Conference on Automatic Face and Gesture Recognition, Grenoble, France,2000:196-201
[64]Veksler O. Efficient graph-based energy minimization methods in computer vision[D]. New York:Cornell University,1999
[65]Boykov Y, Kolmogorov V. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2004:1124-1137
[66]Freedman D, Turek M W. Illumination-invariant tracking via graph cuts[C]. In: Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, CA, USA,2005:265-274
[67]Kwatra V, Schodl A, Essa I, et al. Graphcut textures:Image and video synthesis using graph cuts[J]. ACM Transactions on Graphics,2003,22(3): 277-286
[68]Boykov Y, Kolmogorov V. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2004:1124-1137
[69]Kolmogorov V, Zabin R What energy functions can be minimized via graph cuts?[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004,26(2):147-159
[70]Felzenszwalb P F, Huttenlocher D P. Efficient belief propagation for early vision[J]. International Journal of Computer Vision,2006,70(1):41-54
[71]L. Ford and D. Fulkerson. Flows in Networks[M]. New Jersey, USA: Princeton University Press,1962
[72]Hanbury A. The morphological top-hat operator generalised to multi-channel images[C]. In:Proceeds of 17th International Conference on Pattern Recognition, Washington, DC,2004:672-675
[73]Pun T. Entropie thresholding:A new approach[J]. Computer, Graphics and image Process,1981,16:210-239
[74]Canny J. A computational approach to edge detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1986,6:679-698
[75]Hsu C W, Chang C C, Lin C J. A practical guide to support vector classification[R]. Taipei, National Taiwan University:Computer Science Department,2009
[76]林生佑,潘瑞芳,杜辉,石教英.数字抠图技术综述[J].计算机辅助设计与图形学学报,2007,19(4)：473-479
[77]Kang H W, Shin S Y Enhanced lane:interactive image segmentation by incremental path map construction[J]. Graphical Models,2002,64(5): 282-303
[78]Falc O A X, Udupa J K, Samarasekera S, et al. User-steered image segmentation paradigms:Live wire and live lane[J]. Graphical Models and Image Processing,1998,60(4):233-260
[79]Schneider P J. An algorithm for automatically fitting digitized curves[J]. Graphics gems,1990,1:612-626
[80]Duda R O, Hart P E, Stork D G. Pattern classification,2rd ed[M]. New York:Wiley-Interscience,2001
[81]Davis L S., Johns S, Aggarwal J K. Texture Analysis Using Generalized Co-occurrence Matrices[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1979,3:251-259
[82]Mao J, Jain A K. Texture classification and segmentation using multiresolution simultaneous autoregressive models[J]. Pattern recognition,1992,25(2): 173-188
[83]Haley G M, Manjunath B S. Rotation-invariant texture classification using a complete space-frequency model [J]. IEEE Transactions on Image Processing, 1999,8(2):255-269
[84]Fountain S R, Tan T N. Efficient rotation invariant texture features for content-based image retrieval[J]. Pattern Recognition,1998,31(11): 1725-1732
[85]Manthalkar R, Biswas P K, Chatterji B N. Rotation and scale invariant texture features using discrete wavelet packet transform[J]. Pattern Recognition Letters,2003,24(14):2455-2462
[86]Pun C M, Lee M C. Log-polar wavelet energy signatures for rotation and scale invariant texture classification[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(5):590-603
[87]Ojala T, Pietik Inen M, M Enp T Multiresolution gray scale and rotation invariant texture analysis with local binary patterns [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7):971-987
[88]Chen J L, Kundu A. Rotation and gray scale transform invariant texture identification using wavelet decomposition and hidden markov model[J]. IEEE Transactions on pattern analysis and machine intelligence,1994,16(2): 208-214
[89]Takala V, Ahonen T, Pietikainen M. Block-based methods for image retrieval using local binary patterns[J]. Lecture Notes in Computer Science,2005, 3540:882-891
[90]Ahonen T, Hadid A, Pietikainen M. Face recognition with local binary patterns[C]. In:Proceeds of The 8th European Conference on Computer Vision, Prague, Czech Republic,2004,3021:469-481
[91]Hsu C W, Lin C J. A comparison of methods for multiclass support vector machines[J]. IEEE transactions on Neural Networks,2002,13(2):415-425
[92]Hao P Y, Chiang J H, Lin Y H. A new maximal-margin spherical-structured multi-class support vector machine[J]. Applied Intelligence,2009,30(2): 98-111
[93]Zhang Y, Chi Z X, Liu X D, et al. A novel fuzzy compensation multi-class support vector machine[J]. Applied Intelligence,2007,27(1):21-28
[94]Cheong S, Oh S H, Lee S Y Support vector machines with binary tree architecture for multi-class classification[J]. Neural Information Processing-Letters and Reviews,2004,2(3):47-51
[95]Cheng LL,Zhang JP,Yang J, Ma J. An Improved Hierarchical Multi-class Support Vector Machine with Binary Tree Architecture[C]. In:Proceeds of International Conference on Internet Computing in Science and Engineering, Harbin,2008:106-109
[96]高惠璇.实用统计方法与SAS系统[M].第一版,北京：北京大学出版社,2001
[97]Smits G F, Jordaan E M. Improved SVM regression using mixtures of kernels[C]. In:Proceedings of the 2002 International Joint Conference on Neural Networks, NY, USA,2002(3):2785-2790
[98]张冰,孔锐.一种支持向量机的组合核函数[J].计算机应用,2007,27(001)：44-46
[99]Phung S L, Bouzerdoum Sr A, Chai Sr D. Skin segmentation using color pixel classification:analysis and comparison[J]. IEEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(1):148-154
[100]Jones M J, Rehg J M. Statistical color models with application to skin detection[J]. International Journal of Computer Vision,2002,46(1):81-96
[101]Reynolds J, Murphy K. Figure-ground segmentation using a hierarchical conditional random field[C]. In:Proceedings of the Fourth Canadian Conference on Computer and Robot Vision, Washington, DC, USA,2007: 175-182
[102]Kumar M P, Ton P H S, Zisserman A. OBJ CUT[C]. In:Proceedings of the 2005 IEEE Computer Society'Conference on Computer Vision and Pattern Recognition, Beijing,2005:18-25
[103]Malik J, Belongie S, Leung T, et al. Contour and texture analysis for image segmentation [J]. International Journal of Computer Vision,2001,43(1):7-27
[104]Pal N R, Pal S K. A review on image segmentation techniques[J]. Pattern recognition,1993,26(9):1277-1294
[105]Winn J, Jojic N. Locus:Learning object classes with unsupervised segmentation[C]. In:Proceeds of IEEE International Conference on Computer Vision, Beijing, China,2005:756-763
[106]Leibe B, Leonardis A, Schiele B. Combined object categorization and segmentation with an implicit shape model[C]. In:Proceeds of The 8th European Conference on Computer Vision, Prague,Czech Republic,2004: 1-16
[107]Borenstein E, Ullman S. Class-specific, top-down segmentation[C]. In: Proceeds of The seventh European Conference on Computer Vision, Copenhagen,2002,2351:639-641
[108]Levin A, Weiss Y. Learning to combine bottom-up and top-down segmentation[J]. International Journal of Computer Vision,2009,81(1): 105-118
[109]Yu S, Shi J. Object-specific figure-ground segregation[C]. In:Proceeds of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Madison, USA,2003,2:39-45
[110]Lafferty J, Mccallum A, Pereira F. Conditional random fields:Probabilistic models for segmenting and labeling sequence data[C]. In:Proceeds of the Eighteenth International Conference on Machine Learning, USA,2001: 282-289
[111]Pawan Kumar M, Torr P, Zisserman A. Learning layered motion segmentations of video[J]. International Journal of Computer Vision,2008, 76(3):301-319
[112]Boykov Y, Jolly M P. Interactive graph cuts for optimal boundary and region segmentation of objects in ND images[C]. In:Proceedings of Internation Conference on Computer Vision, Vancouver, Canada,2001,1:105-112
[113]Comaniciu D, Meer P. Mean shift:A robust approach toward feature space analysis[J]. IEEE Transactions on pattern analysis and machine intelligence, 2002:603-619
[114]Tipping M. Relevance vector machine[Z]. Google Patents,2003
[115]Goldberg A V, Tarjan R E. A new approach to the maximum-flow problem[J]. Journal of the Association for Computing Machinery,1988,35(4):921-940
[116]Jones M J, Rehg J M. Statistical color models with application to skin detection[J]. International Journal of Computer Vision,2002,46(1):81-96
[117]Yang M H, Ahuja N. Gaussian mixture model for human skin color and its application in image and video databases[C]. In:Proceeds of SPIE:Storage and Retrieval for Image and Video Databases VII,1999,3656:458-466
[118]J. A. Bilmes. A gentle tutorial of the em algorithm and its application to parameter estimation for gaussian mixture and hidden markov models[R]. USA, U C Berkeley:EECS Department,1998
[119]Buades A, Coll B, Morel J M. A non-local algorithm for image denoising[C]. In:Proceeds of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, USA,2005,2:60-65
[2]Koshimizu H, Tominaga M, Fujiwara T, et al. On KANSEI facial image processing for computerized facial caricaturing system PICASSO[C]. In: Proceeds of IEEE International Conference on Systems, Man, and Cybernetics, Tokyo, Japan,1999,6:294-299
[3]Li Y Z, Kobatake H. Extraction of facial sketch image based on morphological processing [C]. In:Proceeds of In:Proceeds of International Conference on Image Processing, Washington, DC, USA,1997,3:316-319
[4]陈洪,郑南宁,梁林等.基于样本学习的肖像画自动生成算法[J].计算机学报,2003,26(2)：147-152
[5]闵锋,桑农.一种基于与或图表示的多风格肖像画自动生成方法[J].计算机学报,2009,32(8)：1595-1602
[6]Yang Y, Zheng NN, Liu YH, et al. Interactive facial sketch expression generation using local constraints[C]. In:Proceeds of IEEE International Conference on Intelligent Computing and Intelligent Systems, Shanghai, China,2009,2:864-868
[7]Kang H W, He W, Chui C K, et al. Interactive sketch generation[J]. The Visual Computer,2005,21(8):821-830
[8]Kang H, Lee S, Chui C K. Coherent line drawing[C]. In:Proceedings of the 5th international symposium on Non-photorealistic animation and rendering, San Diego, California,2007:43-50
[9]Barni M, Bartolini F, Cappellini V. Image processing for virtual restoration of artworks[J]. IEEE Multimedia,2000:34-37
[10]Giakoumis I, Nikolaidis N, Pitas I. Digital image processing techniques for the detection and removal of cracks in digitized paintings[J]. IEEE Transactions on Image Processing,2006,15(1):178-188
[11]Hanbury A, Kammerer P, Zolda E. Painting crack elimination using viscous morphological reconstruction[C].In:Proceeds of 12th International Conference on Image Analysis and Processing, Mantova, Italy,2003: 226-231
[12]Abas F S. Analysis of craquelure patterns for content-based retrieval[D]. Southampton:University of Southampton,2004
[13]Classification of painting cracks for content-based analysis[C]. In:Proceeds of 14th International Conference on Digital Signal Processing, Santorini, Greece, 2003,1:111-114
[14]De Rosa A, Bonacchi A M, Cappellini V, et al. Image segmentation and region filling for virtual restoration of art-works[C]. In:Proceedings of IEEE International Conference on Image Processing, Thessaloniki, Greece,2001,1: 562-565
[15]Chang R C, Sie Y L, Chou S M; Shih, T.K. Photo defect detection for image inpainting[C]. In:Proceeds of Seventh IEEE International Symposium on Multimedia, Irvine, CA, USA,2005:1-5
[16]Nikolaidis N, Pitas I. Digital image processing in painting restoration and archiving[C]. In:Proceedings of IEEE International Conference on Image Processing, Thessaloniki, Greece,2001:586-589
[17]Pappas M, Pitas I. Digital color restoration of old paintings[J]. IEEE Transactions on image processing,2000,9(2):291-294
[18]Battiti R. First-and second-order methods for learning:between steepest descent and Newton's method[J]. Neural computation,1992,4(2):141-166
[19]Barni M, Bartolini F, Cappellini V. Image processing for virtual restoration of artworks[J]. IEEE Multimedia,2000:34-37
[20]潘云鹤,鲁东明.古代敦煌壁画的数字化保护与修复[J].系统仿真学报,2003,15(3)：310-314
[21]华忠,鲁东明.敦煌壁画虚拟复原及演变模拟模型研究[J].中国图象图形学报：A辑,2002,7(002)：181-186
[22]Li X, Lu D, Pan Y. Color restoration and image retrieval for Dunhuang fresco preservation[J]. IEEE Multimedia,2000:38-42
[23]Bertalmio M, Sapiro Q Caselles V, et al. Image inpainting[C]. In:Proceedings of the 27th annual conference on Computer graphics and interactive techniques, New Orleans, Louisiana,2000,417-424
[24]Chan T F, Shen J. Mathematical models for local nontexture inpaintings[J]. SIAM Journal on Applied Mathematics,2001:1019-1043
[25]Chan T F, Shen J. Non-texture inpainting by curvature-driven diffusions (CDD)[J]. J. Visual Comm. Image Rep,2001,12(4):436-449
[26]Esedoglu S, Shen J. Digital inpainting based on the Mumford-Shah-Euler image model[J]. European Journal of Applied Mathematics,2002,13(04): 353-370
[27]张红英,彭启琮.数字图像修复技术综述[J].中国图像图形学报,2007,12(1)：1-10
[28]Bertalmio M, Bertozzi A L, Sapiro G Navier-Stokes, fluid dynamics, and image and video inpainting[C]. In:Proceeds of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Hawaii, 2001,1:355-362
[29]Auclair-Fortier M F, Ziou D. A global approach for solving evolutive heat transfer for image denoising and inpainting [J]. IEEE Transactions on Image Processing,2006,15(9):2558-2574
[30]侯正信,何宇清,许微.一种快速的图像修复算法[J].中国图象图形学报,2007(10)：1909-1912
[31]张红英,彭启琮,吴亚东.数字破损图像的非线性各向异性扩散修补算法[J].计算机辅助设计与图形学学报,2006,18(010)：1541-1546
[32]Efros A A, Leung T K. Texture synthesis by non-parametric sampling[C]. In: Proceedings of the International Conference on Computer Vision, Washington, DC, USA,1999:1033-1038
[33]Drori I, Cohen-Or D, Yeshurun H. Fragment-based image completion[J]. ACM Transactions on Graphics (TOG),2003,22(3):303-312
[34]Criminisi A, Perez P, Toyama K. Region filling and object removal by exemplar-based image inpainting[J]. IEEE Transactions on Image Processing, 2004,13(9):1200-1212
[35]Chen Q, Zhang Y, Liu Y. Image Inpainting with Improved Exemplar-Based Approach[C]. In:Proceeds of International Workshop on Multimedia Content Analysis and Mining, Weihai, China,2007,4577:242-251
[36]Reinhard E, Ashikhmin M, Gooch B, et al. Color transfer between images[J]. IEEE Computer Graphics and Applications,2001:34-41
[37]Wu J, Ruan Q. Object Removal By Cross Isophotes Exemplar-based Inpainting[C]. In:Proceedings of the 18th International Conference on Pattern Recognition, Hong Kong,2006,3:810-813
[38]Wong A, Orchard J. A nonlocal-means approach to exemplar-based inpainting[C]. In:Proceeding of 2008 IEEE International Conference on Image Processing, San Diego, California, USA,2008:2600-2603
[39]Shao XW, Liu ZK, Houqiang Li HQ. An image inpainting approach based on the Poisson equation[C]. In:Proceedings of the Second International Conference on Document Image Analysis for Libraries, Washington, DC, USA, 2006:368-372
[40]Hays J, Efros A A. Scene completion using millions of photographs [J]. ACM Transactions on Graphics,2007,26(3):4-es
[41]KOMODAKIS N, TZIRITAS G Image completion using efficient belief propagation via priority scheduling and dynamic pruning[J]. IEEE Transactions on Image Processing,2007,16(11):2649-2661
[42]Huang T, Chen S, Liu J, et al. Image Inpainting by Global Structure and Texture Propagation[C]. In:Proceedings of the 15th international conference on Multimedia. Augsburg, Germany,2007,901:517-520
[43]葛仕明,程义民,潘浩等.基于离散优化的图像修复[J].中国科学技术大学学报,2008,38(12)：1381-1385
[44]Kwatra V, Essa I, Bobick A, et al. Texture optimization for example-based synthesis[J]. ACM Transactions on Graphics (TOG),2005,24(3):795-802
[45]Sun J, Shum H Y. Image completion with structure propagation[J]. ACM Transactions on Graphics,2005,24(3):861-868
[46]Felzenszwalb P F, Huttenlocher. D P. Efficient belief propagation for early vision[J]. International Journal of Computer Vision,2006,70(1):41-54
[47]Bertalmio M, Vese L, Sapiro G, et al. Simultaneous structure and texture image inpainting[J]. IEEE Transactions on Image Processing,2003,12(8): 882-889
[48]J. H. Yamauchi, H. P. Seidel, Image Restoration Using Multiresolution Texture Synthesis and Image Inpainting[C].In:Proceeds of Computer Graphics International, Tokyo, Japan,2003:120-125
[49]Sonka M., Havac V., Boyle R.图像处理,分析与机器视觉[M].北京：人民邮电出版社,2002
[50]Zhang J, Tan T. Brief review of invariant texture analysis methods[J]. Pattern Recognition,2002,35(3):735-747
[51]Haralick R M, Dinstein I, Shanmugam K. Textural features for image classification[J]. IEEE Transactions on systems, man, and cybernetics,1973, 3(6):610-621
[52]Sarkar A, Sharma K, Sonak R V. A new approach for subset 2-D AR model identification for describing textures[J]. IEEE Transactions on Image Processing,1997,6(3):407-413
[53]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(7):971-987
[54]Chellappa R, Chatterjee S. Classification of texture using Gaussian Markov Random Fields[J]. IEEE Transactions on Acoustics, Speech, and Signal Processing,1985,33(4):959-963
[55]Krishnamachari S, Chellappa R. Muhiresolution Gauss—markov random field models for texture segmentation[J].IEEEE Transactions on Image Processing,1997,6(2):251-267
[56]Y Chitre, A.P. Dhawan, M-band wavelet discrimination of natural textures[J]. Pattern Recognition,1999,32:773-789
[57]A.C. Bovik, Analysis of multichannel narrow-band filters for image texture segmentation, IEEE Transactions on Signal Processing,1990,39:2025-2043
[58]Pavlidis T. Structural Descriptions and Graph Grammars[M]. Berlin, Germany: Springer Press,1980
[59]Soille P. Morphological Image Analysis:Principles and Application [M]. Berlin, Germany:Springer Press,2003
[60]Christopher J.C. A Tutorial on Support Vector Machines for Pattern Recognition[J]. Data Mining and Knowledge Discovery,2004:121-167
[61]Bahlmann C, Haasdonk B, Burkhardt H. On-line handwriting recognition with support vector machines—a kernel approach[C]. In:Proceeds of 8th International Workshop on Frontiers in Handwriting Recognition, Ontario, Canada,2002:49-54
[62]Gordan M, Kotropoulos C, Pitas I. Application of support vector machines classifiers to visual speech recognition[C]. In:Proceedings of 2002 International Conference on Image Processing, New York, USA,2002,3:129-132
[63]Guo Q Li S Z, Chan K. Face recognition by support vector machines[C]. In: Proceedings of Fourth IEEE International Conference on Automatic Face and Gesture Recognition, Grenoble, France,2000:196-201
[64]Veksler O. Efficient graph-based energy minimization methods in computer vision[D]. New York:Cornell University,1999
[65]Boykov Y, Kolmogorov V. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2004:1124-1137
[66]Freedman D, Turek M W. Illumination-invariant tracking via graph cuts[C]. In: Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, CA, USA,2005:265-274
[67]Kwatra V, Schodl A, Essa I, et al. Graphcut textures:Image and video synthesis using graph cuts[J]. ACM Transactions on Graphics,2003,22(3): 277-286
[68]Boykov Y, Kolmogorov V. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2004:1124-1137
[69]Kolmogorov V, Zabin R What energy functions can be minimized via graph cuts?[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004,26(2):147-159
[70]Felzenszwalb P F, Huttenlocher D P. Efficient belief propagation for early vision[J]. International Journal of Computer Vision,2006,70(1):41-54
[71]L. Ford and D. Fulkerson. Flows in Networks[M]. New Jersey, USA: Princeton University Press,1962
[72]Hanbury A. The morphological top-hat operator generalised to multi-channel images[C]. In:Proceeds of 17th International Conference on Pattern Recognition, Washington, DC,2004:672-675
[73]Pun T. Entropie thresholding:A new approach[J]. Computer, Graphics and image Process,1981,16:210-239
[74]Canny J. A computational approach to edge detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1986,6:679-698
[75]Hsu C W, Chang C C, Lin C J. A practical guide to support vector classification[R]. Taipei, National Taiwan University:Computer Science Department,2009
[76]林生佑,潘瑞芳,杜辉,石教英.数字抠图技术综述[J].计算机辅助设计与图形学学报,2007,19(4)：473-479
[77]Kang H W, Shin S Y Enhanced lane:interactive image segmentation by incremental path map construction[J]. Graphical Models,2002,64(5): 282-303
[78]Falc O A X, Udupa J K, Samarasekera S, et al. User-steered image segmentation paradigms:Live wire and live lane[J]. Graphical Models and Image Processing,1998,60(4):233-260
[79]Schneider P J. An algorithm for automatically fitting digitized curves[J]. Graphics gems,1990,1:612-626
[80]Duda R O, Hart P E, Stork D G. Pattern classification,2rd ed[M]. New York:Wiley-Interscience,2001
[81]Davis L S., Johns S, Aggarwal J K. Texture Analysis Using Generalized Co-occurrence Matrices[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1979,3:251-259
[82]Mao J, Jain A K. Texture classification and segmentation using multiresolution simultaneous autoregressive models[J]. Pattern recognition,1992,25(2): 173-188
[83]Haley G M, Manjunath B S. Rotation-invariant texture classification using a complete space-frequency model [J]. IEEE Transactions on Image Processing, 1999,8(2):255-269
[84]Fountain S R, Tan T N. Efficient rotation invariant texture features for content-based image retrieval[J]. Pattern Recognition,1998,31(11): 1725-1732
[85]Manthalkar R, Biswas P K, Chatterji B N. Rotation and scale invariant texture features using discrete wavelet packet transform[J]. Pattern Recognition Letters,2003,24(14):2455-2462
[86]Pun C M, Lee M C. Log-polar wavelet energy signatures for rotation and scale invariant texture classification[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(5):590-603
[87]Ojala T, Pietik Inen M, M Enp T Multiresolution gray scale and rotation invariant texture analysis with local binary patterns [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7):971-987
[88]Chen J L, Kundu A. Rotation and gray scale transform invariant texture identification using wavelet decomposition and hidden markov model[J]. IEEE Transactions on pattern analysis and machine intelligence,1994,16(2): 208-214
[89]Takala V, Ahonen T, Pietikainen M. Block-based methods for image retrieval using local binary patterns[J]. Lecture Notes in Computer Science,2005, 3540:882-891
[90]Ahonen T, Hadid A, Pietikainen M. Face recognition with local binary patterns[C]. In:Proceeds of The 8th European Conference on Computer Vision, Prague, Czech Republic,2004,3021:469-481
[91]Hsu C W, Lin C J. A comparison of methods for multiclass support vector machines[J]. IEEE transactions on Neural Networks,2002,13(2):415-425
[92]Hao P Y, Chiang J H, Lin Y H. A new maximal-margin spherical-structured multi-class support vector machine[J]. Applied Intelligence,2009,30(2): 98-111
[93]Zhang Y, Chi Z X, Liu X D, et al. A novel fuzzy compensation multi-class support vector machine[J]. Applied Intelligence,2007,27(1):21-28
[94]Cheong S, Oh S H, Lee S Y Support vector machines with binary tree architecture for multi-class classification[J]. Neural Information Processing-Letters and Reviews,2004,2(3):47-51
[95]Cheng LL,Zhang JP,Yang J, Ma J. An Improved Hierarchical Multi-class Support Vector Machine with Binary Tree Architecture[C]. In:Proceeds of International Conference on Internet Computing in Science and Engineering, Harbin,2008:106-109
[96]高惠璇.实用统计方法与SAS系统[M].第一版,北京：北京大学出版社,2001
[97]Smits G F, Jordaan E M. Improved SVM regression using mixtures of kernels[C]. In:Proceedings of the 2002 International Joint Conference on Neural Networks, NY, USA,2002(3):2785-2790
[98]张冰,孔锐.一种支持向量机的组合核函数[J].计算机应用,2007,27(001)：44-46
[99]Phung S L, Bouzerdoum Sr A, Chai Sr D. Skin segmentation using color pixel classification:analysis and comparison[J]. IEEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(1):148-154
[100]Jones M J, Rehg J M. Statistical color models with application to skin detection[J]. International Journal of Computer Vision,2002,46(1):81-96
[101]Reynolds J, Murphy K. Figure-ground segmentation using a hierarchical conditional random field[C]. In:Proceedings of the Fourth Canadian Conference on Computer and Robot Vision, Washington, DC, USA,2007: 175-182
[102]Kumar M P, Ton P H S, Zisserman A. OBJ CUT[C]. In:Proceedings of the 2005 IEEE Computer Society'Conference on Computer Vision and Pattern Recognition, Beijing,2005:18-25
[103]Malik J, Belongie S, Leung T, et al. Contour and texture analysis for image segmentation [J]. International Journal of Computer Vision,2001,43(1):7-27
[104]Pal N R, Pal S K. A review on image segmentation techniques[J]. Pattern recognition,1993,26(9):1277-1294
[105]Winn J, Jojic N. Locus:Learning object classes with unsupervised segmentation[C]. In:Proceeds of IEEE International Conference on Computer Vision, Beijing, China,2005:756-763
[106]Leibe B, Leonardis A, Schiele B. Combined object categorization and segmentation with an implicit shape model[C]. In:Proceeds of The 8th European Conference on Computer Vision, Prague,Czech Republic,2004: 1-16
[107]Borenstein E, Ullman S. Class-specific, top-down segmentation[C]. In: Proceeds of The seventh European Conference on Computer Vision, Copenhagen,2002,2351:639-641
[108]Levin A, Weiss Y. Learning to combine bottom-up and top-down segmentation[J]. International Journal of Computer Vision,2009,81(1): 105-118
[109]Yu S, Shi J. Object-specific figure-ground segregation[C]. In:Proceeds of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Madison, USA,2003,2:39-45
[110]Lafferty J, Mccallum A, Pereira F. Conditional random fields:Probabilistic models for segmenting and labeling sequence data[C]. In:Proceeds of the Eighteenth International Conference on Machine Learning, USA,2001: 282-289
[111]Pawan Kumar M, Torr P, Zisserman A. Learning layered motion segmentations of video[J]. International Journal of Computer Vision,2008, 76(3):301-319
[112]Boykov Y, Jolly M P. Interactive graph cuts for optimal boundary and region segmentation of objects in ND images[C]. In:Proceedings of Internation Conference on Computer Vision, Vancouver, Canada,2001,1:105-112
[113]Comaniciu D, Meer P. Mean shift:A robust approach toward feature space analysis[J]. IEEE Transactions on pattern analysis and machine intelligence, 2002:603-619
[114]Tipping M. Relevance vector machine[Z]. Google Patents,2003
[115]Goldberg A V, Tarjan R E. A new approach to the maximum-flow problem[J]. Journal of the Association for Computing Machinery,1988,35(4):921-940
[116]Jones M J, Rehg J M. Statistical color models with application to skin detection[J]. International Journal of Computer Vision,2002,46(1):81-96
[117]Yang M H, Ahuja N. Gaussian mixture model for human skin color and its application in image and video databases[C]. In:Proceeds of SPIE:Storage and Retrieval for Image and Video Databases VII,1999,3656:458-466
[118]J. A. Bilmes. A gentle tutorial of the em algorithm and its application to parameter estimation for gaussian mixture and hidden markov models[R]. USA, U C Berkeley:EECS Department,1998
[119]Buades A, Coll B, Morel J M. A non-local algorithm for image denoising[C]. In:Proceeds of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, USA,2005,2:60-65