视觉数据不变性特征研究
|
摘要
随着多媒体技术的发展，视觉数据呈爆炸式增长。视觉数据识别作为视觉数据智能化处理的关键一环，其效果在极大程度上依赖于视觉数据特征的质量。本文对视觉数据特征提取的一些关键问题进行研究，其中包括图像复原、图像轮廓特征提取、静态纹理以及动态纹理的描述。实际采集得到的视觉数据通常含有各种类型的退化，这将影响特征提取的稳定性和特征的不变性。为消除这种影响，本文首先研究图像复原算法。图像复原技术可将退化图像还原到与真实接近的版本，为特征提取提供可靠的数据。轮廓特征作为人类视觉中的一种重要特征，目前尚未在图像识别中被充分运用和刻画。相对于轮廓特征，静态纹理特征在当前研究中较为成熟。但当前的静态纹理特征提取方法的计算复杂度较高，难以在实际中应用。动态纹理是静态纹理从图像空间延伸至时域的结果，普遍存在于视频数据中。相比于静态纹理，动态纹理能为识别提供额外的线索，但这种线索在当前研究中尚未被充分利用。针对以上问题，本文分别进行了研究，提出了对轮廓、静态纹理和动态纹理这三种特征的提取方法，所提取的特征具有一定的不变性和较强的鲁棒性。本文的研究成果概括如下：
1.本文提出了一种数据驱动的非局部小波框架和小波紧框架构造方法。通过把所构造的非局部小波框架用于稀疏正则化，本文提出了一种通用有效的图像复原方法，该方法能同时利用图像的局部变化稀疏性先验以及非局部结构自相似先验，对处理图像的平滑区域和纹理区域都非常奏效，并在图像修复、去噪和去模糊实验中取得了一流的复原效果。
2.通过把物理力矩概念引入图像域，本文提出了一种有效的轮廓子块显著性度量，据此设计出一种有效的轮廓特征提取方法，其中包括一个新颖的轮廓子块检测子和一个鲁棒的轮廓子块描述子。通过积分图像技术，可实现该轮廓特征的加速计算。所提出的轮廓特征具有较好的区分性，并能与纹理特征相互补充，在物体分类中表现出色。
3.结合图像局部二值模式和全局分形分析，本文提出了一种纹理特征提取方法。相比于其他基于图像局部二值模式的方法，本文方法能很好地应用于复杂的随机纹理上；相对于其他基于分形分析的方法，本文方法在计算速度、特征紧凑性和分类精度上均具有优势。在四个公开纹理数据集上，本文方法取得了一流的分类结果。
4.本文引入一种时空多重分形分析方法提取动态纹理特征，其中包含体分析和切片分析两部分：体分析用于描述动态纹理的整体分形特性；切片分析用于捕捉动态纹理沿不同方向的局部分形行为。结合四种时空多重分形测度，该方法能全方位地分析动态纹理中的自相似结构，并在三个基准动态纹理数据集上取得了一流的分类结果。
With the development of multimedia technology, visual data are exploding. Visual datarecognition, as a key step in the intelligent processing of visual data, largely depends on thequality of the visual data features. In this paper, several key issues in the extraction of visualdata features have been studied, including image restoration, image contour feature extraction,and, the description on static texture as well as dynamic texture. The visual data collectedfrom the real world inevitably involves various types of degradation. Such degradation mightsignificantly affect the stability of the feature extraction process as well as the invariance ofthe extracted features. To remedy this problem, this paper starts with the study on imagerestoration algorithm, which is expected to recover the clear image from the degraded versionand to provide reliable data for image recognition. Contour, as one kind of visual feature thatplays an important role in human vision, has not been fully exploited in image recognition.Compared with contour features, texture features have been extensively studied in the past.However, the computational complexity of the current approaches is still a problem thatshould be treated in practical use. Often presented in the exploding video data, dynamictexture is one type of significant visual feature, resulted from the extension of static texturefrom image space to temporal domain. Compared with static texture, dynamic texture canprovide additional cues for recognition. Nevertheless, the statistical self-similarity of dynamictexture along temporal axis has not been fully exploited. Motivated by the problems above,this paper studies the contour feature, the static texture feature and the dynamic texture featurerespectively, with several effective and robust solutions proposed. The contributions of thispaper are concluded as follow:
1. A scheme for constructing a non-local wavelet frame as well as a wavelet tight frameis developed, based on which the sparsity regularization can simultaneously exploit both thesparse prior of local variations of image intensity and the non-local self-recursive prior ofimage structures over the image. Built upon the proposed construction scheme, a powerfulregularization-based method is developed for solving general image restoration problems. Theproposed method can perform well on both the cartoon-type region and the texture region.
2. By introducing the concept of physical torque into image space, a significance metricfor contour patch is proposed. Based on the torque-based metric, a powerful contour-relatedfeature is proposed with a novel contour patch detector and a robust contour patch descriptor.Integral image trick is used to accelerate the calculation process of the proposed feature. Theproposed contour-related feature can perform well in classifying complex objects, and is ableto provide complementary information to texture feature.
3. Combining local binary patterns coding with global fractal analysis, a powerful texturedescriptor is proposed and applied to texture classification. Compared with current localbinary pattern based approaches, the proposed approach can perform well in recognizingrandom textures from the real world. Compared to the state-of-the-art fractal-based methods,the proposed approach shows its advantages in speed, feature compactness and classificationaccuracy.
4. A spatio-temporal multi-fractal analysis scheme is introduced for extracting dynamictexture features, which consists of two sub-schemes: one is the volumetric analysis for globalcharacterization and the other is the multi-slice analysis for encoding the local fractalbehaviors of dynamic texture along different axes. Combined with four spatio-temporalmulti-fractal measures, the proposed approach can fully capture the self-similar structuresexisting in dynamic texture from different perspectives.
1.本文提出了一种数据驱动的非局部小波框架和小波紧框架构造方法。通过把所构造的非局部小波框架用于稀疏正则化，本文提出了一种通用有效的图像复原方法，该方法能同时利用图像的局部变化稀疏性先验以及非局部结构自相似先验，对处理图像的平滑区域和纹理区域都非常奏效，并在图像修复、去噪和去模糊实验中取得了一流的复原效果。
2.通过把物理力矩概念引入图像域，本文提出了一种有效的轮廓子块显著性度量，据此设计出一种有效的轮廓特征提取方法，其中包括一个新颖的轮廓子块检测子和一个鲁棒的轮廓子块描述子。通过积分图像技术，可实现该轮廓特征的加速计算。所提出的轮廓特征具有较好的区分性，并能与纹理特征相互补充，在物体分类中表现出色。
3.结合图像局部二值模式和全局分形分析，本文提出了一种纹理特征提取方法。相比于其他基于图像局部二值模式的方法，本文方法能很好地应用于复杂的随机纹理上；相对于其他基于分形分析的方法，本文方法在计算速度、特征紧凑性和分类精度上均具有优势。在四个公开纹理数据集上，本文方法取得了一流的分类结果。
4.本文引入一种时空多重分形分析方法提取动态纹理特征，其中包含体分析和切片分析两部分：体分析用于描述动态纹理的整体分形特性；切片分析用于捕捉动态纹理沿不同方向的局部分形行为。结合四种时空多重分形测度，该方法能全方位地分析动态纹理中的自相似结构，并在三个基准动态纹理数据集上取得了一流的分类结果。
With the development of multimedia technology, visual data are exploding. Visual datarecognition, as a key step in the intelligent processing of visual data, largely depends on thequality of the visual data features. In this paper, several key issues in the extraction of visualdata features have been studied, including image restoration, image contour feature extraction,and, the description on static texture as well as dynamic texture. The visual data collectedfrom the real world inevitably involves various types of degradation. Such degradation mightsignificantly affect the stability of the feature extraction process as well as the invariance ofthe extracted features. To remedy this problem, this paper starts with the study on imagerestoration algorithm, which is expected to recover the clear image from the degraded versionand to provide reliable data for image recognition. Contour, as one kind of visual feature thatplays an important role in human vision, has not been fully exploited in image recognition.Compared with contour features, texture features have been extensively studied in the past.However, the computational complexity of the current approaches is still a problem thatshould be treated in practical use. Often presented in the exploding video data, dynamictexture is one type of significant visual feature, resulted from the extension of static texturefrom image space to temporal domain. Compared with static texture, dynamic texture canprovide additional cues for recognition. Nevertheless, the statistical self-similarity of dynamictexture along temporal axis has not been fully exploited. Motivated by the problems above,this paper studies the contour feature, the static texture feature and the dynamic texture featurerespectively, with several effective and robust solutions proposed. The contributions of thispaper are concluded as follow:
1. A scheme for constructing a non-local wavelet frame as well as a wavelet tight frameis developed, based on which the sparsity regularization can simultaneously exploit both thesparse prior of local variations of image intensity and the non-local self-recursive prior ofimage structures over the image. Built upon the proposed construction scheme, a powerfulregularization-based method is developed for solving general image restoration problems. Theproposed method can perform well on both the cartoon-type region and the texture region.
2. By introducing the concept of physical torque into image space, a significance metricfor contour patch is proposed. Based on the torque-based metric, a powerful contour-relatedfeature is proposed with a novel contour patch detector and a robust contour patch descriptor.Integral image trick is used to accelerate the calculation process of the proposed feature. Theproposed contour-related feature can perform well in classifying complex objects, and is ableto provide complementary information to texture feature.
3. Combining local binary patterns coding with global fractal analysis, a powerful texturedescriptor is proposed and applied to texture classification. Compared with current localbinary pattern based approaches, the proposed approach can perform well in recognizingrandom textures from the real world. Compared to the state-of-the-art fractal-based methods,the proposed approach shows its advantages in speed, feature compactness and classificationaccuracy.
4. A spatio-temporal multi-fractal analysis scheme is introduced for extracting dynamictexture features, which consists of two sub-schemes: one is the volumetric analysis for globalcharacterization and the other is the multi-slice analysis for encoding the local fractalbehaviors of dynamic texture along different axes. Combined with four spatio-temporalmulti-fractal measures, the proposed approach can fully capture the self-similar structuresexisting in dynamic texture from different perspectives.
引文
[1]章毓晋.图像工程(上,下册)[M].北京:清华大学出版社,2000
[2]程刚,王春恒.基于结构和纹理特征融合的场景图像分类[J].计算机工程,2011,37(5):227-9
[3] Moore G.E.. Progress in digital integrated electronics[A]. IEEE International Electron DevicesMeeting[C].1975:11-3
[4] Ji Hui, Liu Chaoqiang, Shen Zuowei, et al. Robust video denoising using low rank matrixcompletion[A]. IEEE Conference on Computer Vision and Pattern Recognition[C].2010:1791-8
[5] Ji Hui, Huang Sibin, Shen Zuowei, et al. Robust video restoration by joint sparse and low rank matrixapproximation[J]. SIAM Journal on Imaging Sciences,2011,4(4):1122-42
[6]刘宁钟,杨静宇.基于傅立叶变换的二维条码识别[J].中国图象图形学报,2003:877-82
[7]王凤鹏.模糊条码图像的正则化复原算法[J].光学技术,2006,32(6):932-5
[8]张煜东,吴乐南.单帧图像的超分辨率技术进展[J].光学技术,2008,34(z1):4
[9] Joachim Frank. Three-dimensional electron microscopy of macromolecular assemblies[M].Academic Press,1996
[10] Bhanu Bir. Automatic target recognition: state of the art survey[J]. IEEE Transactions onAerospace and Electronic Systems,1986,(4):364-79
[11]邓继忠,张泰岭,石江.机器视觉技术在农业机械中的应用[J].农机化研究,2001,2:91-3
[12]陈健美.基于密度聚类和多特征融合的医学图像识别研究[D]:江苏:江苏大学,2008
[13] Hirata Kyoji, Kato Toshikazu. Query by visual example[A].3rd International Conference onExtending Database Technology[C]. Springer,1992:56-71
[14] Smeulders A.W. M., Worring Marcel, Santini Simone, et al. Content-based image retrieval at theend of the early years[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(12):1349-80
[15] Tomasi Carlo, Manduchi Roberto. Bilateral filtering for gray and color images[A]. IEEEInternational Conference on Computer Vision[C].1998:839-46
[16] Donoho D.L, Johnstone I.M.. Adapting to unknown smoothness via wavelet shrinkage[J]. Journalof the american statistical association,1995,90(432):1200-24
[17] Daubechies Ingrid. Ten lectures on wavelets[M]. SIAM,1992
[18] Daubechies Ingrid, Han Bin, Ron Amos, et al. Framelets: MRA-based constructions of waveletframes[J]. Applied and Computational Harmonic Analysis,2003,14(1):1-46
[19] Mallat Stéphane, Peyré Gabriel. A review of bandlet methods for geometrical imagerepresentation[J]. Numerical Algorithms,2007,44(3):205-34
[20] Starck J.L, Candès E.J., Donoho D.L.. The curvelet transform for image denoising[J]. IEEETransactions on Image Processing,2002,11(6):670-84
[21] Buades Antoni, Coll Bartomeu, Morel J.M.. A non-local algorithm for image denoising[A]. IEEEConference on Computer Vision and Pattern Recognition[C].2005:60-5
[22] Lou Yifei, Zhang Xiaoqun, Osher Stanley, et al. Image recovery via nonlocal operators[J]. Journalof Scientific Computing,2010,42(2):185-97
[23] Chatterjee Priyam, Milanfar Peyman. Image denoising using locally learned dictionaries[A].Proceeding of SPIE-Computational Imaging VII[C]. International Society for Optics andPhotonics,2009:7246
[24] Danielyan Aram, Katkovnik Vladimir, Egiazarian Karen. BM3D frames and variational imagedeblurring[J]. IEEE Transactions on Image Processing,2012,21(4):1715-28
[25] Zhang Li, Vaddadi Sundeep, Jin Hailin, et al. Multiple view image denoising[A]. IEEE Conferenceon Computer Vision and Pattern Recognition[C].2009:1542-9
[26] Dabov Kostadin, Foi Alessandro, Egiazarian Karen. Video denoising by sparse3D transform-domaincollaborative filtering[A]. Procceding of15th European Signal Processing Conference[C].2007:7
[27] MAGGIONI Matteo, KATKOVNIK Vladimir, EGIAZARIAN Karen, et al. NonlocalTransform-Domain Filter for Volumetric Data Denoising and Reconstruction[J]. IEEE transactionson image processing,2013,22(1-2):119-33
[28] Szeliski Richard. Computer vision: algorithms and applications[M]. Springer,2010
[29] Xu Yong, Ji Hui, Fermüller Cornelia. Viewpoint invariant texture description using fractalanalysis[J]. International Journal of Computer Vision, Springer,2009,83(1):85-100
[30] Zhou Dongxiao. Texture analysis and synthesis using a generic Markov-Gibbs image model[D].Auckland: The University of Auckland,2006
[31] Taylor Richard, Micolich A.P., Jonas David. Fractal expressionism[J]. Physics World,1999,12(10):25-8
[32] Haralick R.M.. Statistical and structural approaches to texture[J]. the1979,67(5):786-804
[33] Ojala Timo, Pietik inen Matti, Harwood David. A comparative study of texture measures withclassification based on featured distributions[J]. Pattern recognition,1996,29(1):51-9
[34] He Dong-Chen, Wang Li. Texture features based on texture spectrum[J]. Pattern Recognition,1991,24(5):391-9
[35] Carlucci Luigia. A formal system for texture languages[J]. Pattern Recognition,1972,4(1):53-72
[36] Cross George R, Jain Anil K. Markov random field texture models[J]. IEEE Transactions onPattern Analysis and Machine Intelligence,1983,(1):25-39
[37] Laws K.I.. Rapid texture identification[A]. Procceding of24th Annual Technical Symposium[C].International Society for Optics and Photonics,1980:376-81
[38] Ojala Timo, Pietikainen Matti, Maenpaa Topi. Multiresolution gray-scale and rotation invarianttexture classification with local binary patterns[J]. IEEE Transactions on Pattern Analysis andMachine Intelligence,2002,24(7):971-87
[39] Lowe D.G. Distinctive image features from scale-invariant keypoints[J]. International journal ofcomputer vision,2004,60(2):91-110
[40] Schaffalitzky Frederik, Zisserman Andrew. Viewpoint invariant texture matching and wide baselinestereo[A]. Proccedings of IEEE International Conference on Computer Vision[C].2001:636-43
[41] Kervrann Charles, Heitz Fabrice. A Markov random field model-based approach to unsupervisedtexture segmentation using local and global spatial statistics[J]. IEEE Transactions on ImageProcessing,1995,4(6):856-62
[42] Xu Yong, Ji Hui, Fermuller Cornelia. A projective invariant for textures[A]. IEEE Conference onComputer Vision and Pattern Recognition[C].2006:1932-9
[43] Xu Yong, Huang Si-Bin, Ji Hui, et al. Combining powerful local and global statistics for texturedescription[A]. IEEE Conference on Computer Vision and Pattern Recognition[C].2009:573-80
[44] Varma Manik, Zisserman Andrew. Classifying images of materials: Achieving viewpoint andillumination independence[A]. European Conference on Computer Vision[C]: Springer,2002:255-71
[45] Liu Li, Fieguth Paul, Kuang Gangyao, et al. Sorted Random Projections for robust textureclassification[A]. IEEE International Conference on Computer Vision[C].2011:391-8
[46] Lazebnik Svetlana. Local semi-local and global models for texture, object and scene recognition[D].Illinois: University of Illinois at Urbana-Champaign,2006:
[47] Zhang Jianguo, Marsza ek Marcin, Lazebnik Svetlana, et al. Local features and kernels forclassification of texture and object categories: A comprehensive study[J]. International Journal ofComputer Vision,2007,73(2):213-38
[48] Xu Yong, Yang Xiong, Ling Haibin, et al. A new texture descriptor using multifractal analysis inmulti-orientation wavelet pyramid[A]. IEEE Conference on Computer Vision and PatternRecognition[C].2010:161-8
[49] Mandelbrot B.B.. The fractal geometry of nature[M]. W. H. Freeman and Company,1983
[50]孙霞,吴自勤,黄均.分形原理及其应用[M].合肥:中国科学技术大学出版社,2006
[51]谢和平,薛秀谦.分形应用中的数学基础与方法[M].北京:科学出版社,1997
[52] Falconer K.J, Falconer K.J. Techniques in fractal geometry[M]. Wiley Chichester,1997
[53] Cai Jian-Feng, Dong Bin, Osher Stanley, et al. Image restoration: Total variation, wavelet frames,and beyond[J]. Journal of the American Mathematical Society,2012,25(4):1033-89
[54] Donoho D.L. Compressed sensing[J]. IEEE Transactions on Aerospace and Electronic Systems,2006,52(4):1289-306
[55] Cai Jian-Feng, Osher Stanley, Shen Zuowei. Split Bregman methods and frame based imagerestoration[J]. Multiscale modeling and simulation,2009,8(2):337-69
[56] Elad Michael, Milanfar Peyman, Rubinstein Ron. Analysis versus synthesis in signal priors[J].Inverse problems,2007,23(3):947
[57] Shen Zuowei. Wavelet frames and image restorations[A]. the International congress ofMathematicians[C]. World Scientific,2010:2834-63
[58] Goldstein Tom, Osher Stanley. The split Bregman method for L1-regularized problems[J]. SIAMJournal on Imaging Sciences,2009,2(2):323-43
[59] Mallat Stéphane. A wavelet tour of signal processing[M]. Academic press,1999
[60] Donoho David L. De-noising by soft-thresholding[J]. IEEE Transactions on Information Theory,1995,41(3):613-27
[61] Cai Jian-Feng, Ji Hui, Liu Chaoqiang, et al. High-quality curvelet-based motion deblurring from animage pair[A]. IEEE Conference on Computer Vision and Pattern Recognition[C].2009:1566-73
[62] Le Pennec Erwan, Mallat Stephane. Bandelet image approximation and compression[J]. MultiscaleModeling and Simulation,2005,4(3):992-1039
[63] Ron Amos, Shen Zuowei. Affine Systems in L2(Rd): The Analysis of the Analysis Operator[J].Journal of Functional Analysis,1997,148(2):408-47
[64] Cai Jian-Feng, Chan Raymond H, Shen Zuowei. A framelet-based image inpainting algorithm[J].Applied and Computational Harmonic Analysis,2008,24(2):131-49
[65] Cai Jian-Feng, Ji Hui, Liu Chaoqiang, et al. Framelet-based blind motion deblurring from a singleimage[J]. IEEE Transactions on Image Processing,2012,21(2):562-72
[66] Dong Bin, Ji Hui, Li Jia, et al. Wavelet frame based blind image inpainting[J]. Applied andComputational Harmonic Analysis,2012,32(2):268-79
[67] Elad Michael, Aharon Michal. Image denoising via sparse and redundant representations overlearned dictionaries[J]. IEEE Transactions on Image Processing,2006,15(12):3736-45
[68] Cai Jian-Feng, Huang Sibin, Ji Hui, et al. Data-driven tight frame construction and imagedenoising[R]. UCLA: UCLA Cam Report,2012
[69] Dabov Kostadin, Foi Alessandro, Katkovnik Vladimir, et al. Image denoising by sparse3-Dtransform-domain collaborative filtering[J]. IEEE Transactions on Image Processing,2007,16(8):2080-95
[70] Gilboa Guy, Osher Stanley. Nonlocal operators with applications to image processing[J].Multiscale Modeling and Simulation,2008,7(3):1005-28
[71] Peyré Gabriel, Bougleux Sébastien, Cohen Laurent. Non-local regularization of inverse problems[A].European Conference of Computer Vision[C]. Springer,2008:57-68
[72] Zhang Xiaoqun, Burger Martin, Bresson Xavier, et al. Bregmanized nonlocal regularization fordeconvolution and sparse reconstruction[J]. SIAM Journal on Imaging Sciences,2010,3(3):253-76
[73] Dabov Kostadin, Foi Alessandro, Katkovnik Vladimir, et al. Image restoration by sparse3Dtransform-domain collaborative filtering[M]. Electronic Imaging: International Society for Opticsand Photonics,2008:681207-12
[74] Mairal Julien, Bach Francis, Ponce Jean, et al. Non-local sparse models for image restoration[A].IEEE International Conference on Computer Vision[C].2009:2272-9
[75] Chai Anwei, Shen Zuowei. Deconvolution: A wavelet frame approach[J]. Numerische Mathematik,2007,106(4):529-87
[76] Cai Jian-Feng, Ji Hui, Liu Chaoqiang, et al. Blind motion deblurring from a single image usingsparse approximation[A]. IEEE Conference on Computer Vision and Pattern Recognition[C].2009:104-11
[77] Ponomarenko Nikolay, Battisti Federica, Egiazarian Karen, et al. Metrics performance comparisonfor color image database[A].4th International Workshop on Video Processing and Quality Metricsfor Consumer Electronics[C].2009:14-6
[78] Boiman Oren, Shechtman Eli, Irani Michal. In defense of nearest-neighbor based imageclassification[A]. IEEE Computer Society Conference on Computer Vision and PatternRecognition[C].2008:1-8
[79] van Gemert Jan C, Geusebroek Jan-Mark, Veenman Cor J, et al. Kernel codebooks for scenecategorization[A]. European Conference of Computer Vision[C]. Springer,2008:696-709
[80] Jain Prateek, Kulis Brian, Grauman Kristen. Fast image search for learned metrics[A]. IEEEConference on Computer Vision and Pattern Recognition[C].2008:1-8
[81] Lazebnik Svetlana, Schmid Cordelia, Ponce Jean. Beyond bags of features: Spatial pyramidmatching for recognizing natural scene categories[A]. IEEE Conference on Computer Vision andPattern Recognition[C].2006:2169-78
[82] Wang Jinjun, Yang Jianchao, Yu Kai, et al. Locality-constrained linear coding for imageclassification[A]. Proceedings ofIEEE Conference on Computer Vision and PatternRecognition[C].2010:3360-7
[83] Yang Jianchao, Yu Kai, Gong Yihong, et al. Linear spatial pyramid matching using sparse coding forimage classification[A]. Proceedings ofIEEE Conference on Computer Vision and PatternRecognition[C].2009:1794-801
[84] Zhang Hao, Berg Alexander C, Maire Michael, et al. SVM-KNN: Discriminative nearest neighborclassification for visual category recognition[A]. IEEE Computer Society Conference on ComputerVision and Pattern Recognition[C].2006:2126-36
[85] Fergus Robert, Perona Pietro, Zisserman Andrew. A visual category filter for google images[A].European Conference of Computer Vision[C]. Springer,2004:242-56
[86] Pawan Kumar M, Torr Philip, Zisserman Andrew. Extending Pictorial Structures for ObjectRecognition[J].2004:
[87] Mikolajczyk Krystian, Zisserman Andrew, Schmid Cordelia. Shape recognition with edge-basedfeatures[A].14th British Machine Vision Conference[C]. Britain: BMVA,2003:779-88
[88] Opelt Andreas, Pinz Axel, Zisserman Andrew. A boundary-fragment-model for object detection[A].European Conference of Computer Vision[C]. Springer,2006:575-88
[89] Shotton Jamie, Blake Andrew, Cipolla Roberto. Contour-based learning for object detection[A].IEEE International Conference on Computer Vision[C].2005:503-10
[90] Berg Alexander Christiansen, Berg Tamara L, Malik Jitendra. Shape matching and object recognitionusing low distortion correspondences[A]. IEEE Conference on Computer Vision and PatternRecognition[C].2005:26-33
[91] Belongie Serge, Malik Jitendra, Puzicha Jan. Shape context: A new descriptor for shape matchingand object recognition[J]. Advances in neural information processing systems,2001:831-7
[92] Mori Greg, Belongie Serge, Malik Jitendra. Efficient shape matching using shape contexts[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(11):1832-7
[93] Nelson Randal C, Selinger Andrea. A cubist approach to object recognition[A]. IEEE InternationalConference on Computer Vision[C].1998:614-21
[94] Jurie Frédéric, Schmid Cordelia. Scale-invariant shape features for recognition of objectcategories[A]. IEEE Conference on Computer Vision and Pattern Recognition[C].2004:II-90-II-6Vol.2
[95] Ferrari Vittorio, Fevrier Loic, Jurie Frederic, et al. Groups of adjacent contour segments for objectdetection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(1):36-51
[96] Zhu Qihui, Wang Liming, Wu Yang, et al. Contour context selection for object detection: A set-to-setcontour matching approach[A]. European Conference of Computer Vision[C]. Springer,2008:774-87
[97] Catanzaro Bryan, Su Bor-Yiing, Sundaram Narayanan, et al. Efficient, high-quality image contourdetection[A]. IEEE International Conference on Computer Vision[C].2009:2381-8
[98] Caltech-101[DB/OL]. http://www.vision.caltech.edu/Image_Datasets/Caltech101/
[99] Griffin Gregory, Holub Alex, Perona Pietro. Caltech-256object category dataset[DB/OL].http://authors.library.caltech.edu/7694/,2007:
[100] UMD texture dataset[DB/OL]. http://www.cfar.umd.edu/fer/High-resolution-data-base/
[101] Dana.J.K, Shree.K.N. Histogram model for3d textures[A]. IEEE Conference on Computer Visionand Pattern Recognition[C].1998:618-24
[102] Leung Thomas, Malik Jitendra. Representing and recognizing the visual appearance of materialsusing three-dimensional textons[J]. International Journal of Computer Vision,2001,43(1):29-44
[103] Manjunath B.S, Ohm J.R, Vasudevan V.V., et al. Color and texture descriptors[J]. IEEETransactions on Circuits and Systems for Video Technology,2001,11(6):703-15
[104] Wu Jiahua, Chantler Mike J. Combining gradient and albedo data for rotation invariantclassification of3d surface texture[A]. IEEE International Conference on Computer Vision[C].2003:848-55
[105] Hayman Eric, Caputo Barbara, Fritz Mario, et al. On the significance of real-world conditions formaterial classification[A]. European Conference of Computer Vision[C]. Springer,2004:253-66
[106] Mindru Florica, Tuytelaars Tinne, Gool L.V., et al. Moment invariants for recognition underchanging viewpoint and illumination[J]. Computer Vision and Image Understanding,2004,94(1):3-27
[107] Pietik inen M., Ojala T., Xu Z.. Rotation-invariant texture classification using featuredistributions[J]. Pattern Recognition,2000,33(1):43-52
[108] Liao Shu, Law M.W.K., Chung A.C.S. Dominant local binary patterns for texture classification[J].IEEE Transactions on Image Processing,2009,18(5):1107-18
[109] Guo Zhenhua, Zhang Lei, Zhang David. Rotation invariant texture classification using LBPvariance (LBPV) with global matching[J]. Pattern Recognition,2010,43(3):706-19
[110] Guo Zhenhua, Zhang Lei, Zhang David. A completed modeling of local binary pattern operator fortexture classification[J]. IEEE Transactions on Image Processing,2010,19(6):1657-63
[111] Zhao Guoying, Ahonen Timo, Matas Ji í, et al. Rotation-invariant image and video description withlocal binary pattern features[J]. IEEE Transactions on Image Processing,2012,21(4):1465-77
[112] Varma Manik, Garg Rahul. Locally invariant fractal features for statistical texture classification[A].IEEE International Conference on Computer Vision[C].2007:1-8
[113] Ji Hui, Yang Xiong, Ling Haibin, et al. Wavelet Domain Multi-fractal Analysis for Static andDynamic Texture Classification[J]. IEEE Transactions on Image Processing,2013:
[114] Xu Yong, Huang Sibin, Ji Hui, et al. Scale-space texture description on SIFT-like textons[J].Computer Vision and Image Understanding,2012:
[115] Caputo.B, Hayman.E, Fritz.M, etal, Classifying Materials in the Real World, Image and VisionComputing[J],2010;28(1),150-163,
[116] Lazebnik Svetlana, Schmid Cordelia, Ponce Jean. A discriminative framework for texture andobject recognition using local image features[A]. Toward Category-Level Object Recognition[C].Springer,2006:423-42
[117] Julesz Bela. Textons, the elements of texture perception, and their interactions[J]. Nature,1981:
[118] Malik Jitendra, Belongie Serge, Leung Thomas, et al. Contour and texture analysis for imagesegmentation[J]. International Journal of Computer Vision,2001,43(1):7-27
[119] Zhu S.C., Guo C.E., Wang Yizhou, et al. What are textons?[J]. International Journal of ComputerVision,2005,62(1-2):121-43
[120] Lazebnik Svetlana, Schmid Cordelia, Ponce Jean. A sparse texture representation usingaffine-invariant regions[A]. IEEE Conference on Computer Vision and Pattern Recognition[C].IEEE,2003: II-319-II-24Vol.2
[121] Liao Shu, Chung Albert CS. Texture classification by using advanced local binary patterns andspatial distribution of dominant patterns[A].32nd IEEE International Conference on Acoustics,Speech and Signal Processing[C].2007:1221-4
[122] Ahonen Timo, Matas Ji í, He Chu, et al. Rotation invariant image description with local binarypattern histogram fourier features[M]. Image Analysis. Springer,2009:61-70
[123] Levy V.J., Mignot Pascal, Berroir J.P.. Multifractals, texture, and image analysis[A]. IEEEConference on Computer Vision and Pattern Recognition[C].1992:661-4
[124] Kaplan L.M.. Extended fractal analysis for texture classification and segmentation[J]. IEEETransactions on Image Processing,1999,8(11):1572-85
[125] Deguy Sébastien, Debain Christophe, Benassi Albert. Classification of texture images usingmulti-scale statistical estimators of fractal parameters[A].11th British machine visionconference[C]. Britain: BMVA,2000:192-201
[126] Ojala Timo, Pietik inen Matti, M enp Topi. Gray-scale and rotation invariant textureclassification with local binary patterns[A]. European Conference of Computer Vision[C].Springer,2000:404-20
[127] M enp Topi. The Local Binary Pattern Approach to Texture Analysis: Extenxions andApplications[M]. Oulun yliopisto,2003
[128] UIUC texture dataset[DB/OL]. http://www-cvr.ai.uiuc.edu/ponce_grp/data/
[129] KTH-TIPS texture dataset[DB/OL]. http://www.nada.kth.se/cvap/databases/kth-tips
[130] ALOT texture dataset[DB/OL]. http://www.science.uva.nl/aloi/public_alot
[131] Rubner Yossi, Tomasi Carlo, Guibas L.J.. The earth mover's distance as a metric for imageretrieval[J]. International Journal of Computer Vision,2000,40(2):99-121
[132] Chetverikov Dmitry, Péteri Renaud. A brief survey of dynamic texture description andrecognition[A].4th International Conference on Computer Recognition Systems[C]. Springer,2005:17-26
[133] Doretto Gianfranco, Chiuso Alessandro, Wu Ying Nian, et al. Dynamic textures[J]. InternationalJournal of Computer Vision,2003,51(2):91-109
[134] Doretto Gianfranco, Cremers Daniel, Favaro Paolo, et al. Dynamic texture segmentation[A].IEEE International Conference on Computer Vision[C].2003:1236-42
[135] Ghanem B.S., Adviser-Ahuja Narendra. Dynamic textures: Models and applications[M]. IllinoisUniversity of Illinois at Urbana-Champaign,2010
[136] Smith John R, Lin Ching-Yung, Naphade Milind. Video texture indexing using spatio-temporalwavelets[A]. IEEE International Conference on Image Processing[C].2002: Vol.2:437-40
[137] Péteri Renaud, Fazekas Sándor, Huiskes.M.J.. DynTex: A comprehensive database of DynamicTextures[J]. Pattern Recognition Letters,2010,31(12):1627-32
[138] Billock V.A., de Guzman Gonzalo C, Scott Kelso JA. Fractal time and1/f spectra in dynamicimages and human vision[J]. Physica D: Nonlinear Phenomena,2001,148(1):136-46
[139] Dong D.W., Atick J.J.. Statistics of natural time-varying images[J]. Network: Computation inNeural Systems,1995,6(3):345-58
[140] Van H.J.H.. Processing of natural time series of intensities by the visual system of the blowfly[J].Vision research,1997,37(23):3407-16
[141] Chan A.B., Vasconcelos Nuno. Classifying video with kernel dynamic textures[A]. IEEEConference on Computer Vision and Pattern Recognition[C].2007:1-6
[142] Doretto Gianfranco, Jones Eagle, Soatto Stefano. Spatially homogeneous dynamic textures[A].European Conference of Computer Vision[C]. Springer,2004:591-602
[143] Ghanem Bernard, Ahuja Narendra. Phase based modelling of dynamic textures[A]. IEEEInternational Conference on Computer Vision[C].2007:1-8
[144] Ravichandran Avinash, Chaudhry Rizwan, Vidal René. View-invariant dynamic texture recognitionusing a bag of dynamical systems[A]. IEEE Conference on Computer Vision and PatternRecognition[C].2009:1651-7
[145] Saisan Payam, Doretto Gianfranco, Wu YingNian, et al. Dynamic texture recognition[A]. IEEEConference on Computer Vision and Pattern Recognition[C],2001: II-58-63
[146] Szummer Martin, Picard R.W.. Temporal texture modeling[A]. IEEE International Conference onImage Processing[C].1996:823-6
[147] Woolfe Franco, Fitzgibbon Andrew. Shift-invariant dynamic texture recognition[A]. EuropeanConference of Computer Vision[C]. Springer,2006:549-62
[148] Ghanem Bernard, Ahuja Narendra. Maximum margin distance learning for dynamic texturerecognition[A]. European Conference of Computer Vision[C]. Springer,2010:223-36
[149] Wildes R.P., Bergen J.R.. Qualitative spatiotemporal analysis using an oriented energyrepresentation[A]. European Conference of Computer Vision[C]. Springer,2000:768-84
[150] Zhao Guoying, Pietikainen Matti. Dynamic texture recognition using local binary patterns with anapplication to facial expressions[J]. IEEE Transactions on Pattern Analysis and MachineIntelligence,2007,29(6):915-28
[151] Zhao Guoying, Pietik inen Matti. Dynamic texture recognition using volume local binarypatterns[M]. Dynamical Vision: Springer,2007:165-77
[152] Polana Ramprasad, Nelson Randal. Temporal texture and activity recognition[M]. Springer,1997
[153] Lu Zongqing, Xie Weixin, Pei Jihong, et al. Dynamic texture recognition by spatio-temporalmultiresolution histograms[A]. IEEE Workshops on Application of Computer Vision[C].2005:241-6
[154] Fazekas Sándor, Chetverikov Dmitry. Normal versus complete flow in dynamic texture recognition:a comparative study[A]. International workshop on texture analysis and synthesis[C],2005:37-42
[155] Péteri Renaud, Chetverikov Dmitry. Dynamic texture recognition using normal flow and textureregularity[A]. Pattern Recognition and Image Analysis[C]. Springer,2005:223-30
[156] Derpanis Konstantinos G, Wildes Richard P. Dynamic texture recognition based on distributions ofspacetime oriented structure[A]. IEEE Conference on Computer Vision and Pattern Recognition[C].2010:191-8
[2]程刚,王春恒.基于结构和纹理特征融合的场景图像分类[J].计算机工程,2011,37(5):227-9
[3] Moore G.E.. Progress in digital integrated electronics[A]. IEEE International Electron DevicesMeeting[C].1975:11-3
[4] Ji Hui, Liu Chaoqiang, Shen Zuowei, et al. Robust video denoising using low rank matrixcompletion[A]. IEEE Conference on Computer Vision and Pattern Recognition[C].2010:1791-8
[5] Ji Hui, Huang Sibin, Shen Zuowei, et al. Robust video restoration by joint sparse and low rank matrixapproximation[J]. SIAM Journal on Imaging Sciences,2011,4(4):1122-42
[6]刘宁钟,杨静宇.基于傅立叶变换的二维条码识别[J].中国图象图形学报,2003:877-82
[7]王凤鹏.模糊条码图像的正则化复原算法[J].光学技术,2006,32(6):932-5
[8]张煜东,吴乐南.单帧图像的超分辨率技术进展[J].光学技术,2008,34(z1):4
[9] Joachim Frank. Three-dimensional electron microscopy of macromolecular assemblies[M].Academic Press,1996
[10] Bhanu Bir. Automatic target recognition: state of the art survey[J]. IEEE Transactions onAerospace and Electronic Systems,1986,(4):364-79
[11]邓继忠,张泰岭,石江.机器视觉技术在农业机械中的应用[J].农机化研究,2001,2:91-3
[12]陈健美.基于密度聚类和多特征融合的医学图像识别研究[D]:江苏:江苏大学,2008
[13] Hirata Kyoji, Kato Toshikazu. Query by visual example[A].3rd International Conference onExtending Database Technology[C]. Springer,1992:56-71
[14] Smeulders A.W. M., Worring Marcel, Santini Simone, et al. Content-based image retrieval at theend of the early years[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(12):1349-80
[15] Tomasi Carlo, Manduchi Roberto. Bilateral filtering for gray and color images[A]. IEEEInternational Conference on Computer Vision[C].1998:839-46
[16] Donoho D.L, Johnstone I.M.. Adapting to unknown smoothness via wavelet shrinkage[J]. Journalof the american statistical association,1995,90(432):1200-24
[17] Daubechies Ingrid. Ten lectures on wavelets[M]. SIAM,1992
[18] Daubechies Ingrid, Han Bin, Ron Amos, et al. Framelets: MRA-based constructions of waveletframes[J]. Applied and Computational Harmonic Analysis,2003,14(1):1-46
[19] Mallat Stéphane, Peyré Gabriel. A review of bandlet methods for geometrical imagerepresentation[J]. Numerical Algorithms,2007,44(3):205-34
[20] Starck J.L, Candès E.J., Donoho D.L.. The curvelet transform for image denoising[J]. IEEETransactions on Image Processing,2002,11(6):670-84
[21] Buades Antoni, Coll Bartomeu, Morel J.M.. A non-local algorithm for image denoising[A]. IEEEConference on Computer Vision and Pattern Recognition[C].2005:60-5
[22] Lou Yifei, Zhang Xiaoqun, Osher Stanley, et al. Image recovery via nonlocal operators[J]. Journalof Scientific Computing,2010,42(2):185-97
[23] Chatterjee Priyam, Milanfar Peyman. Image denoising using locally learned dictionaries[A].Proceeding of SPIE-Computational Imaging VII[C]. International Society for Optics andPhotonics,2009:7246
[24] Danielyan Aram, Katkovnik Vladimir, Egiazarian Karen. BM3D frames and variational imagedeblurring[J]. IEEE Transactions on Image Processing,2012,21(4):1715-28
[25] Zhang Li, Vaddadi Sundeep, Jin Hailin, et al. Multiple view image denoising[A]. IEEE Conferenceon Computer Vision and Pattern Recognition[C].2009:1542-9
[26] Dabov Kostadin, Foi Alessandro, Egiazarian Karen. Video denoising by sparse3D transform-domaincollaborative filtering[A]. Procceding of15th European Signal Processing Conference[C].2007:7
[27] MAGGIONI Matteo, KATKOVNIK Vladimir, EGIAZARIAN Karen, et al. NonlocalTransform-Domain Filter for Volumetric Data Denoising and Reconstruction[J]. IEEE transactionson image processing,2013,22(1-2):119-33
[28] Szeliski Richard. Computer vision: algorithms and applications[M]. Springer,2010
[29] Xu Yong, Ji Hui, Fermüller Cornelia. Viewpoint invariant texture description using fractalanalysis[J]. International Journal of Computer Vision, Springer,2009,83(1):85-100
[30] Zhou Dongxiao. Texture analysis and synthesis using a generic Markov-Gibbs image model[D].Auckland: The University of Auckland,2006
[31] Taylor Richard, Micolich A.P., Jonas David. Fractal expressionism[J]. Physics World,1999,12(10):25-8
[32] Haralick R.M.. Statistical and structural approaches to texture[J]. the1979,67(5):786-804
[33] Ojala Timo, Pietik inen Matti, Harwood David. A comparative study of texture measures withclassification based on featured distributions[J]. Pattern recognition,1996,29(1):51-9
[34] He Dong-Chen, Wang Li. Texture features based on texture spectrum[J]. Pattern Recognition,1991,24(5):391-9
[35] Carlucci Luigia. A formal system for texture languages[J]. Pattern Recognition,1972,4(1):53-72
[36] Cross George R, Jain Anil K. Markov random field texture models[J]. IEEE Transactions onPattern Analysis and Machine Intelligence,1983,(1):25-39
[37] Laws K.I.. Rapid texture identification[A]. Procceding of24th Annual Technical Symposium[C].International Society for Optics and Photonics,1980:376-81
[38] Ojala Timo, Pietikainen Matti, Maenpaa Topi. Multiresolution gray-scale and rotation invarianttexture classification with local binary patterns[J]. IEEE Transactions on Pattern Analysis andMachine Intelligence,2002,24(7):971-87
[39] Lowe D.G. Distinctive image features from scale-invariant keypoints[J]. International journal ofcomputer vision,2004,60(2):91-110
[40] Schaffalitzky Frederik, Zisserman Andrew. Viewpoint invariant texture matching and wide baselinestereo[A]. Proccedings of IEEE International Conference on Computer Vision[C].2001:636-43
[41] Kervrann Charles, Heitz Fabrice. A Markov random field model-based approach to unsupervisedtexture segmentation using local and global spatial statistics[J]. IEEE Transactions on ImageProcessing,1995,4(6):856-62
[42] Xu Yong, Ji Hui, Fermuller Cornelia. A projective invariant for textures[A]. IEEE Conference onComputer Vision and Pattern Recognition[C].2006:1932-9
[43] Xu Yong, Huang Si-Bin, Ji Hui, et al. Combining powerful local and global statistics for texturedescription[A]. IEEE Conference on Computer Vision and Pattern Recognition[C].2009:573-80
[44] Varma Manik, Zisserman Andrew. Classifying images of materials: Achieving viewpoint andillumination independence[A]. European Conference on Computer Vision[C]: Springer,2002:255-71
[45] Liu Li, Fieguth Paul, Kuang Gangyao, et al. Sorted Random Projections for robust textureclassification[A]. IEEE International Conference on Computer Vision[C].2011:391-8
[46] Lazebnik Svetlana. Local semi-local and global models for texture, object and scene recognition[D].Illinois: University of Illinois at Urbana-Champaign,2006:
[47] Zhang Jianguo, Marsza ek Marcin, Lazebnik Svetlana, et al. Local features and kernels forclassification of texture and object categories: A comprehensive study[J]. International Journal ofComputer Vision,2007,73(2):213-38
[48] Xu Yong, Yang Xiong, Ling Haibin, et al. A new texture descriptor using multifractal analysis inmulti-orientation wavelet pyramid[A]. IEEE Conference on Computer Vision and PatternRecognition[C].2010:161-8
[49] Mandelbrot B.B.. The fractal geometry of nature[M]. W. H. Freeman and Company,1983
[50]孙霞,吴自勤,黄均.分形原理及其应用[M].合肥:中国科学技术大学出版社,2006
[51]谢和平,薛秀谦.分形应用中的数学基础与方法[M].北京:科学出版社,1997
[52] Falconer K.J, Falconer K.J. Techniques in fractal geometry[M]. Wiley Chichester,1997
[53] Cai Jian-Feng, Dong Bin, Osher Stanley, et al. Image restoration: Total variation, wavelet frames,and beyond[J]. Journal of the American Mathematical Society,2012,25(4):1033-89
[54] Donoho D.L. Compressed sensing[J]. IEEE Transactions on Aerospace and Electronic Systems,2006,52(4):1289-306
[55] Cai Jian-Feng, Osher Stanley, Shen Zuowei. Split Bregman methods and frame based imagerestoration[J]. Multiscale modeling and simulation,2009,8(2):337-69
[56] Elad Michael, Milanfar Peyman, Rubinstein Ron. Analysis versus synthesis in signal priors[J].Inverse problems,2007,23(3):947
[57] Shen Zuowei. Wavelet frames and image restorations[A]. the International congress ofMathematicians[C]. World Scientific,2010:2834-63
[58] Goldstein Tom, Osher Stanley. The split Bregman method for L1-regularized problems[J]. SIAMJournal on Imaging Sciences,2009,2(2):323-43
[59] Mallat Stéphane. A wavelet tour of signal processing[M]. Academic press,1999
[60] Donoho David L. De-noising by soft-thresholding[J]. IEEE Transactions on Information Theory,1995,41(3):613-27
[61] Cai Jian-Feng, Ji Hui, Liu Chaoqiang, et al. High-quality curvelet-based motion deblurring from animage pair[A]. IEEE Conference on Computer Vision and Pattern Recognition[C].2009:1566-73
[62] Le Pennec Erwan, Mallat Stephane. Bandelet image approximation and compression[J]. MultiscaleModeling and Simulation,2005,4(3):992-1039
[63] Ron Amos, Shen Zuowei. Affine Systems in L2(Rd): The Analysis of the Analysis Operator[J].Journal of Functional Analysis,1997,148(2):408-47
[64] Cai Jian-Feng, Chan Raymond H, Shen Zuowei. A framelet-based image inpainting algorithm[J].Applied and Computational Harmonic Analysis,2008,24(2):131-49
[65] Cai Jian-Feng, Ji Hui, Liu Chaoqiang, et al. Framelet-based blind motion deblurring from a singleimage[J]. IEEE Transactions on Image Processing,2012,21(2):562-72
[66] Dong Bin, Ji Hui, Li Jia, et al. Wavelet frame based blind image inpainting[J]. Applied andComputational Harmonic Analysis,2012,32(2):268-79
[67] Elad Michael, Aharon Michal. Image denoising via sparse and redundant representations overlearned dictionaries[J]. IEEE Transactions on Image Processing,2006,15(12):3736-45
[68] Cai Jian-Feng, Huang Sibin, Ji Hui, et al. Data-driven tight frame construction and imagedenoising[R]. UCLA: UCLA Cam Report,2012
[69] Dabov Kostadin, Foi Alessandro, Katkovnik Vladimir, et al. Image denoising by sparse3-Dtransform-domain collaborative filtering[J]. IEEE Transactions on Image Processing,2007,16(8):2080-95
[70] Gilboa Guy, Osher Stanley. Nonlocal operators with applications to image processing[J].Multiscale Modeling and Simulation,2008,7(3):1005-28
[71] Peyré Gabriel, Bougleux Sébastien, Cohen Laurent. Non-local regularization of inverse problems[A].European Conference of Computer Vision[C]. Springer,2008:57-68
[72] Zhang Xiaoqun, Burger Martin, Bresson Xavier, et al. Bregmanized nonlocal regularization fordeconvolution and sparse reconstruction[J]. SIAM Journal on Imaging Sciences,2010,3(3):253-76
[73] Dabov Kostadin, Foi Alessandro, Katkovnik Vladimir, et al. Image restoration by sparse3Dtransform-domain collaborative filtering[M]. Electronic Imaging: International Society for Opticsand Photonics,2008:681207-12
[74] Mairal Julien, Bach Francis, Ponce Jean, et al. Non-local sparse models for image restoration[A].IEEE International Conference on Computer Vision[C].2009:2272-9
[75] Chai Anwei, Shen Zuowei. Deconvolution: A wavelet frame approach[J]. Numerische Mathematik,2007,106(4):529-87
[76] Cai Jian-Feng, Ji Hui, Liu Chaoqiang, et al. Blind motion deblurring from a single image usingsparse approximation[A]. IEEE Conference on Computer Vision and Pattern Recognition[C].2009:104-11
[77] Ponomarenko Nikolay, Battisti Federica, Egiazarian Karen, et al. Metrics performance comparisonfor color image database[A].4th International Workshop on Video Processing and Quality Metricsfor Consumer Electronics[C].2009:14-6
[78] Boiman Oren, Shechtman Eli, Irani Michal. In defense of nearest-neighbor based imageclassification[A]. IEEE Computer Society Conference on Computer Vision and PatternRecognition[C].2008:1-8
[79] van Gemert Jan C, Geusebroek Jan-Mark, Veenman Cor J, et al. Kernel codebooks for scenecategorization[A]. European Conference of Computer Vision[C]. Springer,2008:696-709
[80] Jain Prateek, Kulis Brian, Grauman Kristen. Fast image search for learned metrics[A]. IEEEConference on Computer Vision and Pattern Recognition[C].2008:1-8
[81] Lazebnik Svetlana, Schmid Cordelia, Ponce Jean. Beyond bags of features: Spatial pyramidmatching for recognizing natural scene categories[A]. IEEE Conference on Computer Vision andPattern Recognition[C].2006:2169-78
[82] Wang Jinjun, Yang Jianchao, Yu Kai, et al. Locality-constrained linear coding for imageclassification[A]. Proceedings ofIEEE Conference on Computer Vision and PatternRecognition[C].2010:3360-7
[83] Yang Jianchao, Yu Kai, Gong Yihong, et al. Linear spatial pyramid matching using sparse coding forimage classification[A]. Proceedings ofIEEE Conference on Computer Vision and PatternRecognition[C].2009:1794-801
[84] Zhang Hao, Berg Alexander C, Maire Michael, et al. SVM-KNN: Discriminative nearest neighborclassification for visual category recognition[A]. IEEE Computer Society Conference on ComputerVision and Pattern Recognition[C].2006:2126-36
[85] Fergus Robert, Perona Pietro, Zisserman Andrew. A visual category filter for google images[A].European Conference of Computer Vision[C]. Springer,2004:242-56
[86] Pawan Kumar M, Torr Philip, Zisserman Andrew. Extending Pictorial Structures for ObjectRecognition[J].2004:
[87] Mikolajczyk Krystian, Zisserman Andrew, Schmid Cordelia. Shape recognition with edge-basedfeatures[A].14th British Machine Vision Conference[C]. Britain: BMVA,2003:779-88
[88] Opelt Andreas, Pinz Axel, Zisserman Andrew. A boundary-fragment-model for object detection[A].European Conference of Computer Vision[C]. Springer,2006:575-88
[89] Shotton Jamie, Blake Andrew, Cipolla Roberto. Contour-based learning for object detection[A].IEEE International Conference on Computer Vision[C].2005:503-10
[90] Berg Alexander Christiansen, Berg Tamara L, Malik Jitendra. Shape matching and object recognitionusing low distortion correspondences[A]. IEEE Conference on Computer Vision and PatternRecognition[C].2005:26-33
[91] Belongie Serge, Malik Jitendra, Puzicha Jan. Shape context: A new descriptor for shape matchingand object recognition[J]. Advances in neural information processing systems,2001:831-7
[92] Mori Greg, Belongie Serge, Malik Jitendra. Efficient shape matching using shape contexts[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(11):1832-7
[93] Nelson Randal C, Selinger Andrea. A cubist approach to object recognition[A]. IEEE InternationalConference on Computer Vision[C].1998:614-21
[94] Jurie Frédéric, Schmid Cordelia. Scale-invariant shape features for recognition of objectcategories[A]. IEEE Conference on Computer Vision and Pattern Recognition[C].2004:II-90-II-6Vol.2
[95] Ferrari Vittorio, Fevrier Loic, Jurie Frederic, et al. Groups of adjacent contour segments for objectdetection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(1):36-51
[96] Zhu Qihui, Wang Liming, Wu Yang, et al. Contour context selection for object detection: A set-to-setcontour matching approach[A]. European Conference of Computer Vision[C]. Springer,2008:774-87
[97] Catanzaro Bryan, Su Bor-Yiing, Sundaram Narayanan, et al. Efficient, high-quality image contourdetection[A]. IEEE International Conference on Computer Vision[C].2009:2381-8
[98] Caltech-101[DB/OL]. http://www.vision.caltech.edu/Image_Datasets/Caltech101/
[99] Griffin Gregory, Holub Alex, Perona Pietro. Caltech-256object category dataset[DB/OL].http://authors.library.caltech.edu/7694/,2007:
[100] UMD texture dataset[DB/OL]. http://www.cfar.umd.edu/fer/High-resolution-data-base/
[101] Dana.J.K, Shree.K.N. Histogram model for3d textures[A]. IEEE Conference on Computer Visionand Pattern Recognition[C].1998:618-24
[102] Leung Thomas, Malik Jitendra. Representing and recognizing the visual appearance of materialsusing three-dimensional textons[J]. International Journal of Computer Vision,2001,43(1):29-44
[103] Manjunath B.S, Ohm J.R, Vasudevan V.V., et al. Color and texture descriptors[J]. IEEETransactions on Circuits and Systems for Video Technology,2001,11(6):703-15
[104] Wu Jiahua, Chantler Mike J. Combining gradient and albedo data for rotation invariantclassification of3d surface texture[A]. IEEE International Conference on Computer Vision[C].2003:848-55
[105] Hayman Eric, Caputo Barbara, Fritz Mario, et al. On the significance of real-world conditions formaterial classification[A]. European Conference of Computer Vision[C]. Springer,2004:253-66
[106] Mindru Florica, Tuytelaars Tinne, Gool L.V., et al. Moment invariants for recognition underchanging viewpoint and illumination[J]. Computer Vision and Image Understanding,2004,94(1):3-27
[107] Pietik inen M., Ojala T., Xu Z.. Rotation-invariant texture classification using featuredistributions[J]. Pattern Recognition,2000,33(1):43-52
[108] Liao Shu, Law M.W.K., Chung A.C.S. Dominant local binary patterns for texture classification[J].IEEE Transactions on Image Processing,2009,18(5):1107-18
[109] Guo Zhenhua, Zhang Lei, Zhang David. Rotation invariant texture classification using LBPvariance (LBPV) with global matching[J]. Pattern Recognition,2010,43(3):706-19
[110] Guo Zhenhua, Zhang Lei, Zhang David. A completed modeling of local binary pattern operator fortexture classification[J]. IEEE Transactions on Image Processing,2010,19(6):1657-63
[111] Zhao Guoying, Ahonen Timo, Matas Ji í, et al. Rotation-invariant image and video description withlocal binary pattern features[J]. IEEE Transactions on Image Processing,2012,21(4):1465-77
[112] Varma Manik, Garg Rahul. Locally invariant fractal features for statistical texture classification[A].IEEE International Conference on Computer Vision[C].2007:1-8
[113] Ji Hui, Yang Xiong, Ling Haibin, et al. Wavelet Domain Multi-fractal Analysis for Static andDynamic Texture Classification[J]. IEEE Transactions on Image Processing,2013:
[114] Xu Yong, Huang Sibin, Ji Hui, et al. Scale-space texture description on SIFT-like textons[J].Computer Vision and Image Understanding,2012:
[115] Caputo.B, Hayman.E, Fritz.M, etal, Classifying Materials in the Real World, Image and VisionComputing[J],2010;28(1),150-163,
[116] Lazebnik Svetlana, Schmid Cordelia, Ponce Jean. A discriminative framework for texture andobject recognition using local image features[A]. Toward Category-Level Object Recognition[C].Springer,2006:423-42
[117] Julesz Bela. Textons, the elements of texture perception, and their interactions[J]. Nature,1981:
[118] Malik Jitendra, Belongie Serge, Leung Thomas, et al. Contour and texture analysis for imagesegmentation[J]. International Journal of Computer Vision,2001,43(1):7-27
[119] Zhu S.C., Guo C.E., Wang Yizhou, et al. What are textons?[J]. International Journal of ComputerVision,2005,62(1-2):121-43
[120] Lazebnik Svetlana, Schmid Cordelia, Ponce Jean. A sparse texture representation usingaffine-invariant regions[A]. IEEE Conference on Computer Vision and Pattern Recognition[C].IEEE,2003: II-319-II-24Vol.2
[121] Liao Shu, Chung Albert CS. Texture classification by using advanced local binary patterns andspatial distribution of dominant patterns[A].32nd IEEE International Conference on Acoustics,Speech and Signal Processing[C].2007:1221-4
[122] Ahonen Timo, Matas Ji í, He Chu, et al. Rotation invariant image description with local binarypattern histogram fourier features[M]. Image Analysis. Springer,2009:61-70
[123] Levy V.J., Mignot Pascal, Berroir J.P.. Multifractals, texture, and image analysis[A]. IEEEConference on Computer Vision and Pattern Recognition[C].1992:661-4
[124] Kaplan L.M.. Extended fractal analysis for texture classification and segmentation[J]. IEEETransactions on Image Processing,1999,8(11):1572-85
[125] Deguy Sébastien, Debain Christophe, Benassi Albert. Classification of texture images usingmulti-scale statistical estimators of fractal parameters[A].11th British machine visionconference[C]. Britain: BMVA,2000:192-201
[126] Ojala Timo, Pietik inen Matti, M enp Topi. Gray-scale and rotation invariant textureclassification with local binary patterns[A]. European Conference of Computer Vision[C].Springer,2000:404-20
[127] M enp Topi. The Local Binary Pattern Approach to Texture Analysis: Extenxions andApplications[M]. Oulun yliopisto,2003
[128] UIUC texture dataset[DB/OL]. http://www-cvr.ai.uiuc.edu/ponce_grp/data/
[129] KTH-TIPS texture dataset[DB/OL]. http://www.nada.kth.se/cvap/databases/kth-tips
[130] ALOT texture dataset[DB/OL]. http://www.science.uva.nl/aloi/public_alot
[131] Rubner Yossi, Tomasi Carlo, Guibas L.J.. The earth mover's distance as a metric for imageretrieval[J]. International Journal of Computer Vision,2000,40(2):99-121
[132] Chetverikov Dmitry, Péteri Renaud. A brief survey of dynamic texture description andrecognition[A].4th International Conference on Computer Recognition Systems[C]. Springer,2005:17-26
[133] Doretto Gianfranco, Chiuso Alessandro, Wu Ying Nian, et al. Dynamic textures[J]. InternationalJournal of Computer Vision,2003,51(2):91-109
[134] Doretto Gianfranco, Cremers Daniel, Favaro Paolo, et al. Dynamic texture segmentation[A].IEEE International Conference on Computer Vision[C].2003:1236-42
[135] Ghanem B.S., Adviser-Ahuja Narendra. Dynamic textures: Models and applications[M]. IllinoisUniversity of Illinois at Urbana-Champaign,2010
[136] Smith John R, Lin Ching-Yung, Naphade Milind. Video texture indexing using spatio-temporalwavelets[A]. IEEE International Conference on Image Processing[C].2002: Vol.2:437-40
[137] Péteri Renaud, Fazekas Sándor, Huiskes.M.J.. DynTex: A comprehensive database of DynamicTextures[J]. Pattern Recognition Letters,2010,31(12):1627-32
[138] Billock V.A., de Guzman Gonzalo C, Scott Kelso JA. Fractal time and1/f spectra in dynamicimages and human vision[J]. Physica D: Nonlinear Phenomena,2001,148(1):136-46
[139] Dong D.W., Atick J.J.. Statistics of natural time-varying images[J]. Network: Computation inNeural Systems,1995,6(3):345-58
[140] Van H.J.H.. Processing of natural time series of intensities by the visual system of the blowfly[J].Vision research,1997,37(23):3407-16
[141] Chan A.B., Vasconcelos Nuno. Classifying video with kernel dynamic textures[A]. IEEEConference on Computer Vision and Pattern Recognition[C].2007:1-6
[142] Doretto Gianfranco, Jones Eagle, Soatto Stefano. Spatially homogeneous dynamic textures[A].European Conference of Computer Vision[C]. Springer,2004:591-602
[143] Ghanem Bernard, Ahuja Narendra. Phase based modelling of dynamic textures[A]. IEEEInternational Conference on Computer Vision[C].2007:1-8
[144] Ravichandran Avinash, Chaudhry Rizwan, Vidal René. View-invariant dynamic texture recognitionusing a bag of dynamical systems[A]. IEEE Conference on Computer Vision and PatternRecognition[C].2009:1651-7
[145] Saisan Payam, Doretto Gianfranco, Wu YingNian, et al. Dynamic texture recognition[A]. IEEEConference on Computer Vision and Pattern Recognition[C],2001: II-58-63
[146] Szummer Martin, Picard R.W.. Temporal texture modeling[A]. IEEE International Conference onImage Processing[C].1996:823-6
[147] Woolfe Franco, Fitzgibbon Andrew. Shift-invariant dynamic texture recognition[A]. EuropeanConference of Computer Vision[C]. Springer,2006:549-62
[148] Ghanem Bernard, Ahuja Narendra. Maximum margin distance learning for dynamic texturerecognition[A]. European Conference of Computer Vision[C]. Springer,2010:223-36
[149] Wildes R.P., Bergen J.R.. Qualitative spatiotemporal analysis using an oriented energyrepresentation[A]. European Conference of Computer Vision[C]. Springer,2000:768-84
[150] Zhao Guoying, Pietikainen Matti. Dynamic texture recognition using local binary patterns with anapplication to facial expressions[J]. IEEE Transactions on Pattern Analysis and MachineIntelligence,2007,29(6):915-28
[151] Zhao Guoying, Pietik inen Matti. Dynamic texture recognition using volume local binarypatterns[M]. Dynamical Vision: Springer,2007:165-77
[152] Polana Ramprasad, Nelson Randal. Temporal texture and activity recognition[M]. Springer,1997
[153] Lu Zongqing, Xie Weixin, Pei Jihong, et al. Dynamic texture recognition by spatio-temporalmultiresolution histograms[A]. IEEE Workshops on Application of Computer Vision[C].2005:241-6
[154] Fazekas Sándor, Chetverikov Dmitry. Normal versus complete flow in dynamic texture recognition:a comparative study[A]. International workshop on texture analysis and synthesis[C],2005:37-42
[155] Péteri Renaud, Chetverikov Dmitry. Dynamic texture recognition using normal flow and textureregularity[A]. Pattern Recognition and Image Analysis[C]. Springer,2005:223-30
[156] Derpanis Konstantinos G, Wildes Richard P. Dynamic texture recognition based on distributions ofspacetime oriented structure[A]. IEEE Conference on Computer Vision and Pattern Recognition[C].2010:191-8