2.793

2018影响因子

(CJCR)

  • 中文核心
  • EI
  • 中国科技核心
  • Scopus
  • CSCD
  • 英国科学文摘

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

图像纹理分类方法研究进展和展望

刘丽 赵凌君 郭承玉 王亮 汤俊

刘丽, 赵凌君, 郭承玉, 王亮, 汤俊. 图像纹理分类方法研究进展和展望. 自动化学报, 2018, 44(4): 584-607. doi: 10.16383/j.aas.2018.c160452
引用本文: 刘丽, 赵凌君, 郭承玉, 王亮, 汤俊. 图像纹理分类方法研究进展和展望. 自动化学报, 2018, 44(4): 584-607. doi: 10.16383/j.aas.2018.c160452
LIU Li, ZHAO Ling-Jun, GUO Cheng-Yu, WANG Liang, TANG Jun. Texture Classification: State-of-the-art Methods and Prospects. ACTA AUTOMATICA SINICA, 2018, 44(4): 584-607. doi: 10.16383/j.aas.2018.c160452
Citation: LIU Li, ZHAO Ling-Jun, GUO Cheng-Yu, WANG Liang, TANG Jun. Texture Classification: State-of-the-art Methods and Prospects. ACTA AUTOMATICA SINICA, 2018, 44(4): 584-607. doi: 10.16383/j.aas.2018.c160452

图像纹理分类方法研究进展和展望

doi: 10.16383/j.aas.2018.c160452
基金项目: 

湖南省自然科学基金杰出青年基金 2017JJ1007

详细信息
    作者简介:

    赵凌君  国防科学技术大学电子科学与工程学院副教授.主要研究方向为遥感信息处理, 合成孔径雷达目标自动识别.E-mail:nudtzlj@163.com

    郭承玉  国防科学技术大学信息系统与管理学院博士研究生.主要研究方向为图像理解, 计算机视觉, 模式识别.E-mail:sdlwgcy@126.com

    王亮  中国科学院自动化研究所模式识别国家重点实验室研究员.主要研究方向计算机视觉与模式识别.E-mail:wangliang@nlpr.ia.ac.cn

    汤俊  国防科学技术大学信息系统与管理学院信息系统工程国防科技重点实验室讲师.主要研究方向为智能交通系统, 航迹规划, 深度学习.E-mail:jun.tang@e-campus.uab.cat

    通讯作者:

    刘丽  国防科学技术大学信息系统与管理学院副教授.主要研究方向为图像理解, 计算机视觉, 模式识别.本文通信作者.E-mail:liuli_nudt@nudt.edu.cn

  • 本文责任编委 张长水

Texture Classification: State-of-the-art Methods and Prospects

Funds: 

The Hunan Provincial Natural Science Fund for Distinguished Young Scholars 2017JJ1007

More Information
    Author Bio:

     Associate professor at the School of Electronic Science and Engineering, National University of Defense Technology. Her research interest covers remote sensing information processing, and SAR automatic target recognition

     Ph. D. candidate at the College of Information System and Management, National University of Defense Technology. Her research interest covers image understanding, computer vision, and pattern recognition

     Professor at the National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences. His research interest covers computer vision and pattern recognition

     Lecturer at the Science and Technology on Information Systems Engineering Laboratory, College of Information System and Management, National University of Defense Technology. His research interest covers intelligent transportation systems, trajectory planning, and machine learning

    Corresponding author: LIU Li  Associate professor at the College of Information System and Management, National University of Defense Technology. Her research interest covers image understanding, computer vision, and pattern recognition. Corresponding author of this paper
  • 摘要: 纹理分类是计算机视觉和模式识别领域的一个重要的基本问题,也是图像分割、物体识别、场景理解等其他视觉任务的基础.本文从纹理分类问题的基本定义出发,首先,对纹理分类研究中存在的困难与挑战进行阐述;接下来,对纹理分类方面的典型数据库进行全面梳理和总结;然后,对近期的纹理特征提取方法的发展和现状进行归类总结,并对主流纹理特征提取方法进行了详细的阐述和评述;最后,对纹理分类发展方向进行思考和讨论.
    1)  本文责任编委 张长水
  • 图  1  纹理识别难点示例(实例层次: (a)光照变化带来的影响, 图片来自CUReT数据集第30类; (b)视角变化和局部非刚性形变带来的难点, 图片来自UIUC数据集第25类; (c)尺度变化带来的影响, 图片来自KTHTIPS2b数据集.类别层次: (d)同一类别的不同实例图像带来很大类内差异, 图片来自DTD数据集的braided类; (e)材质识别的难点, 图片来自FMD数据集, 正确答案为(从左往右):玻璃, 皮质, 塑料, 木质, 塑料, 金属, 木质, 金属和塑料)

    Fig.  1  Challenging examples of texture recognition ((a) Illumination variations, images are from the 30th category of the CUReT dataset; (b) View point and local non-rigid deformation, images are from the 25th category of the UIUC dataset; (c) Scale variations, images are from the KTHTIPS2b dataset; (d) Different instance appearance variations from the same category, images are from the braided category in the DTD dataset; (e) Material classification difficulties, images are from the FMD dataset, the category for these images are as follows (from left to right): glass, cortex, plastic, wood, plastic, metal, wood, metal, and plastic, (a), (b) and (c) belong to instance-level variations; (d) and (e) belong to category-level variations.)

    图  2  来自KTHTIPS2的某类图像的样本

    Fig.  2  Image examples from one category in KTHTIPS2

    图  3  来自MINC数据库中的图像样本(第一行为食物类别, 第二行为foliage类别)

    Fig.  3  Image samples from the MINC database (Example images in the first row are from the food category, while those in the second row are from the foliage category)

    图  4  基于词包模型的纹理分类示意图

    Fig.  4  Texture classification based on the BoW pipeline

    图  5  LM (Leung-Malik)滤波器组

    Fig.  5  LM (Leung-Malik) filters

    图  6  Leung和Malik提出的三维纹元字典学习流程示意图

    Fig.  6  Illustration for 3D texton dictionary learning with LMfilters proposed by Leung and Malik

    图  7  SRP描述子示意图

    Fig.  7  Illustration of SRP descriptors

    图  8  BIF局部特征提取过程示意图

    Fig.  8  Illustration of BIF feature extraction

    图  9  WLD描述子一阶邻域系统示意图

    Fig.  9  First order neighborhood in WLD

    图  10  传统基于滤波方法的纹理分类流程示意图

    Fig.  10  Illustration of traditional texture classification based on filtering methods

    图  11  ScatNet计算示意图(图示了三层散射结构. $x$为原始图像, $\psi$为多尺度多方向的Gabor小波(例如常用的4个尺度8个方向), 图中可以看成仅画出了4个尺度的卷积, 方向滤波器的卷积没有画出; $\psi$为随着层深度变化可改变的高斯低通滤波器, 等同于高斯加权平均特征汇聚的作用, 可以获得局部特征不变性; 白色圆点为小波卷积后取模, 用于下一层再次进行小波卷积并取模操作; 黑色圆点是在白色圆点基础上进行局部特征汇聚操作, 为最终输出的特征图)

    Fig.  11  Illustration of the 3-level scattering structure of ScatNet ($x$ is the original image, and $\psi$ is the multi-scale and multi-directional Gabor wavelet (e. g., the commonly used five scales and eight orientations). In this figure we only show the convolution in four scales and do not show the convolution in different orientations. $\psi$ is a low-pass Gaussian filter, which changes with the depth of layers, and is equivalent to the feature pooling of the Gaussian weighted average to locally obtain invariance. The white dot is to take modulus after convolution by wavelet, which is then used for the next layer and also take the modulus. The black dot represents feature pooling for the output from the white dot, and then is used as the final feature mapping.)

    图  12  Bilinear CNN模型结构示意图

    Fig.  12  Illustration of the Bilinear CNN architecture

    图  13  基于VGG-VD模型进行纹理合成示意

    Fig.  13  Texture synthesis based on VGG-VD model

    图  14  生活中常见的丰富纹理特征的物体(可以用纹理视觉属性进行描述:网状的、斑点的、条纹的、点状的、斑纹的)

    Fig.  14  Objects with rich textures in our daily life (We can use texture attributes to describe them: mesh, spotted, striated, spotted, striped.)

    表  1  主流纹理分类数据库, 下载地址为: Brodatz[13]、VisTex[14]、CUReT[15]、Outex[16]、KTHTIPS[17]、UIUC[18]、KTHTIPS2a[17]、KTHTIPS2b[17]、UMD[19]、ALOT[20]、FMD[21]、Drexel[22]、OS[23]、DTD[24]、MINC[25]

    Table  1  Widely used texture datasets and their download link: Brodatz[13], VisTex[14], CUReT[15], Outex[16], KTHTIPS[17], UIUC[18], KTHTIPS2a[17], KTHTIPS2b[17], UMD[19], ALOT[20], FMD[21], Drexel[22], OS[23], DTD[24], MINC[25]

    数据库 图像数目 类别数目 图像尺寸 灰度/颜色 成像条件 光照变化 旋转变化 视点变化 尺度变化 图像内容 实例类别 建立年度
    Brodatz 112 112 640 $\times$ 640 灰度 实验可控 物体表面 实例 1966
    VisTex 167 167 786 $\times$ 512 颜色 户外 $\surd$ 物体表面 实例 1995
    CUReT 5 612 92 200 $\times$ 200 颜色 实验可控 $\surd$ $\surd$ 材料表面 实例 1999
    Outex 8 640 320 746 $\times$ 538 颜色 实验可控 $\surd$ $\surd$ $\surd$ 材质/物体 实例 2002
    KTHTIPS 810 10 200 $\times$ 200 颜色 实验可控 $\surd$ $\surd$ 材料表面 实例 2004
    UIUC 1 000 25 640 $\times$ 480 灰度 户外可控 $\surd$ $\surd$ $\surd$ $\surd$ 材料表面 实例 2005
    KTHTIPS2a 4 608 11 200 $\times$ 200 颜色 实验可控 $\surd$ $\surd$ 材料表面 类别 2006
    KTHTIPS2b 4 752 11 200 $\times$ 200 颜色 实验可控 $\surd$ $\surd$ 材料表面 类别 2006
    UMD 1 000 25 1 280 $\times$ 960 灰度 户外可控 $\surd$ $\surd$ $\surd$ 物体表面 实例 2009
    ALOT 25 000 250 768 $\times$ 512 颜色 实验可控 $\surd$ $\surd$ $\surd$ 材料表面 实例 2009
    FMD 1 000 10 512 $\times$ 384 颜色 不可控 $\surd$ $\surd$ $\surd$ $\surd$ 材料表面 类别 2009
    Drexel 40 000 20 200 $\times$ 200 颜色 实验可控 $\surd$ $\surd$ $\surd$ 材料表面 实例 2012
    OS 10 422 22 不固定 颜色 不可控 $\surd$ $\surd$ $\surd$ $\surd$ 材料表面 杂波 2013
    DTD 5 640 47 不固定 颜色 不可控 $\surd$ $\surd$ $\surd$ 纹理属性 类别 2014
    MINC 2 996 674 23 不固定 颜色 不可控 $\surd$ $\surd$ $\surd$ $\surd$ 材料表面 杂波 2015
    MINC2500 57 500 23 362 $\times$ 362 颜色 不可控 $\surd$ $\surd$ $\surd$ $\surd$ 材料表面 杂波 2015
    下载: 导出CSV

    表  2  近期主流分类方法报道的纹理分类性能总结(数据都是原文报道的结果, 带*标记的数据是引自近期综述性论文[6])

    Table  2  Performance summary of recent dominant classification methods on texture classification (All results are quoted directly from original papers, except for those marked with *, which are from a recent review paper[6].)

    Method Dataset Outex_TC10 Outex_TC12 Brodatz CUReT KTHTIPS UIUC UMD KTHTIPS2 ALOT FMD DTD
    LBP[30] TPAMI2002 96.1 97.2
    MRS[27] IJCV2005 97.4
    Lazebnik et al.[33] TPAMI2005 88.2 72.5* 91.3* 96.0
    Zhang et al.[6] IJCV2007 95.4 95.3 95.5 98.7
    Mellor et al.[110] TPAMI2008 89.7
    MFS[34] IJCV2009 92.7 93.9
    OTF[85] CVPR2009 97.4 98.5
    WMFS[86] CVPR2010 98.6 98.7
    Patch[67] TPAMI2009 92.9* 98.0 92.4* 97.8
    WLD[84] TPAMI2009 64.7
    BIF[80] IJCV2010 98.6 98.5 98.8
    RP[74] TPAMI2012 98.5
    SRP[77] PR2012 96.3 98.5 97.7 96.3 99.1
    Timofte et al.[83] BMVC2012 97.3 99.4 99.4 99.0 99.5 55.8
    Ce Liu[37] IJCV2013 55.6
    ScatNet[93] CVPR2013 98.8 99.8 99.4 99.4 99.7
    SRP-RCA[79] TCSVT2015 96.8 99.4 99.1 98.6 99.3 53.2
    PCANet[95] TIP2015 99.6
    MRELBP[69] TIP2016 99.8 99.6 99.0 99.4 77.9 99.1
    AlexNet+FV[40] IJCV2016 98.5 99.2 99.7 77.9 99.1 67.2 62.9
    VGG-M+FV[40] IJCV2016 98.7 99.6 99.9 79.9 99.4 73.5 66.8
    VGG-VD+FV[40] IJCV2016 99.0 99.9 99.9 88.2 99.5 79.8 72.3
    BCNN[98] CVPR2016 77.9 81.6 72.9
    下载: 导出CSV
  • [1] Julesz B. Visual pattern discrimination. IRE Transactions on Information Theory, 1962, 8(2):84-92 doi: 10.1109/TIT.1962.1057698
    [2] Tuceryan M, Jain A K. Texture analysis. Handbook of Pattern Recognition and Computer Vision. Singapore:World Scientiflc, 1993. 235-276
    [3] Reed T R, Dubuf J M H. A review of recent texture segmentation and feature extraction techniques. CVGIP:Image Understanding, 1993, 57(3):359-372 doi: 10.1006/ciun.1993.1024
    [4] Randen T, Husoy J H. Filtering for texture classiflcation:a comparative study. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1999, 21(4):291-310 doi: 10.1109/34.761261
    [5] Zhang J G, Tan T N. Brief review of invariant texture analysis methods. Pattern Recognition, 2002, 35(3):735-747 doi: 10.1016/S0031-3203(01)00074-7
    [6] Zhang J G, Marszalek M, Lazebnik S, Schmid C. Local features and kernels for classiflcation of texture and object categories:a comprehensive study. International Journal of Computer Vision, 2007, 73(2):213-238 doi: 10.1007/s11263-006-9794-4
    [7] Xie X H, Mirmehdi M. A galaxy of texture features. Handbook of Texture Analysis. London:Imperial College Press, 2008. 375-406
    [8] 刘丽, 匡纲要.图像纹理特征提取方法综述.中国图象图形学报, 2009, 14(4):622-635 doi: 10.11834/jig.20090409

    Liu Li, Kuang Gang-Yao. Overview of image textural feature extraction methods. Journal of Image and Graphics, 2009, 14(4):622-635 doi: 10.11834/jig.20090409
    [9] Pietikäinen M, Zhao G Y. Two decades of local binary patterns: a survey. Advances in Independent Component Analysis and Learning Machines. Amsterdam, The Netherlands: Elsevier, 2015.
    [10] 宋克臣, 颜云辉, 陈文辉, 张旭.局部二值模式方法研究与展望.自动化学报, 2013, 39(6):730-744 http://www.aas.net.cn/CN/abstract/abstract18099.shtml

    Song Ke-Chen, Yan Yun-Hui, Chen Wen-Hui, Zhang Xu. Research and perspective on local binary pattern. Acta Automatica Sinica, 2013, 39(6):730-744 http://www.aas.net.cn/CN/abstract/abstract18099.shtml
    [11] Liu L, Fieguth P, Guo Y L, Wang X G, Pietikäinen M. Local binary features for texture classiflcation:taxonomy and experimental study. Pattern Recognition, 2017, 62:135-160 doi: 10.1016/j.patcog.2016.08.032
    [12] Brodatz P. Textures:A Photographic Album for Artists and Designers. New York:Dover, 1966.
    [13] Brodatz textures[Online], available: http://www.ux.uis.no/tranden/brodatz.html, April 18, 2018
    [14] Vision texture[Online], available: http://vismod.media.mit.edu/vismod/imagery/VisionTexture/, April 18, 2018
    [15] CURRET: columbia-Utrecht reflectance and texture database[Online], available: http://www.cs.columbia.edu/CAVE/software/curet/html/about.php, April 18, 2018
    [16] Outex texture database[Online], available: http://www.outex.oulu.fl/index.php?page=outexhome, April 18, 2018
    [17] The KTH-TIPS and KTH-TIPS2: image databases[Online], available: http://www.nada.kth.se/cvap/databases/kth-tips/download.html, April 18, 2018
    [18] UIUC Database[Online], available: http://wwwcvr.ai.uiuc.edu/poncegrp/data/, April 18, 2018
    [19] Viewpoint invariant texture description[Online], available: http://www.cfar.umd.edu/fer/website-texture/texture.htm, April 18, 2018
    [20] ALOT Database[Online], available: http://aloi.science.uva.nl/publicalot/, April 18, 2018
    [21] Flickr material database (FMD)[Online], available: http://people.csail.mit.edu/celiu/CVPR2010/FMD/, April 18, 2018
    [22] DRexel Database[Online], available: https://www.cs.drexel.edu/kon/texture/, April 18, 2018
    [23] Bell S, Upchurch P, Snavely N, Bala K. OpenSurfaces[Online], available: http://opensurfaces.cs.cornell.edu/, April 18, 2018
    [24] Describable textures dataset (DTD)[Online], available: http://www.robots.ox.ac.uk/vgg/data/dtd/, April 18, 2018
    [25] Bell S, Upchurch P, Snavely N, Bala K. Material recognition in the wild with the materials in context database[Online], available: http://opensurfaces.cs.cornell.edu/publications/minc/, April 18, 2018
    [26] Dana K J, Van Ginneken B, Nayar S K, Koenderink J J. Reflectance and texture of real-world surfaces. ACM Transactions on Graphics, 1999, 18(1):1-34 doi: 10.1145/300776.300778
    [27] Varma M, Zisserman A. A statistical approach to texture classiflcation from single images. International Journal of Computer Vision, 2005, 62(1-2):61-81 doi: 10.1007/s11263-005-4635-4
    [28] Hayman E, Caputo B, Fritz M, Eklundh J O. On the significance of real-world conditions for material classiflcation. In: Proceedings of the 8th European Conference on Computer Vision. Prague, Czech: Springer, 2004. 253-266
    [29] Ojala T, Mäenpää T, Pietikäinen M, Viertola J, Kyllönen J, Huovinen S. Outex-new framework for empirical evaluation of texture analysis algorithms. In: Proceedings of the 16th International Conference on Pattern Recognition. Quebec City, Canada: IEEE, 2002. 701-706
    [30] Ojala T, Pietikäinen M, Mäenpää T. Multiresolution grayscale and rotation invariant texture classiflcation with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(7):971-987 doi: 10.1109/TPAMI.2002.1017623
    [31] Matthews T, Nixon M S, Niranjan M. Enriching texture analysis with semantic data. In: Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Portland, USA: IEEE, 2013. 1248-1255
    [32] Lazebnik S, Schmid C, Ponce J. A sparse texture representation using a-ne-invariant regions. In: Proceedings of the 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). Madison, Wisconsin, USA: IEEE, 2003. Ⅱ-319-Ⅱ-324
    [33] Lazebnik S, Schmid C, Ponce J. A sparse texture representation using local a-ne regions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(8):1265-1278 doi: 10.1109/TPAMI.2005.151
    [34] Xu Y, Ji H, Fermüller C. Viewpoint invariant texture description using fractal analysis. International Journal of Computer Vision, 2009, 83(1):85-100 doi: 10.1007/s11263-009-0220-6
    [35] Burghouts G J, Geusebroek J M. Material-speciflc adaptation of color invariant features. Pattern Recognition Letters, 2009, 30(3):306-313 doi: 10.1016/j.patrec.2008.10.005
    [36] Oxholm G, Bariya P, Nishino K. The scale of geometric texture. In: Proceedings of the 12th European Conference on Computer Vision (ECCV). Florence, Italy: Springer, 2012. 58-71
    [37] Sharan L, Liu C, Rosenholtz R, Adelson E H. Recognizing materials using perceptually inspired features. International Journal of Computer Vision, 2013, 103(3):348-371 doi: 10.1007/s11263-013-0609-0
    [38] Sharan L, Rosenholtz R, Adelson E H. Accuracy and speed of material categorization in real-world images. Journal of Vision, 2014, 14(9):Article No. 12 doi: 10.1167/14.9.12
    [39] Cimpoi M, Maji S, Vedaldi A. Deep fllter banks for texture recognition and segmentation. In: Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston, Massachusetts, USA: IEEE, 2015. 3828-3836
    [40] Cimpoi M, Maji S, Kokkinos I, Vedaldi A. Deep fllter banks for texture recognition, description, and segmentation. International Journal of Computer Vision, 2016, 118(1):65-94 doi: 10.1007/s11263-015-0872-3
    [41] Farhadi A, Endres I, Hoiem D, Forsyth D. Describing objects by their attributes. In: Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Miami, Florida, USA: IEEE, 2009. 1778-1785
    [42] Patterson G, Xu C, Su H, Hays J. The SUN attribute database:beyond categories for deeper scene understanding. International Journal of Computer Vision, 2014, 108(1-2):59-81 doi: 10.1007/s11263-013-0695-z
    [43] Parikh D, Grauman K. Relative attributes. In: Proceedings of the 2011 IEEE International Conference on Computer Vision (ICCV). Barcelona, Spain: IEEE, 2011. 503-510
    [44] Kumar N, Berg A, Belhumeur P N, Nayar S. Describable visual attributes for face veriflcation and image search. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(10):1962-1977 doi: 10.1109/TPAMI.2011.48
    [45] Cimpoi M, Maji S, Kokkinos I, Mohamed S, Vedaldi A. Describing textures in the wild. In: Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Columbus, OH, USA: IEEE, 2014. 3606-3613
    [46] Bell S, Upchurch P, Snavely N, Bala K. Material recognition in the wild with the materials in context database. In: Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston, Massachusetts, USA: IEEE, 2015. 3479-3487
    [47] Bell S, Upchurch P, Snavely N, Bala K. OpenSurfaces:a richly annotated catalog of surface appearance. ACM Transactions on Graphics, 2013, 32(4):Article No. 111 http://opensurfaces.cs.cornell.edu
    [48] Hossain S, Serikawa S. Texture databases——a comprehensive survey. Pattern Recognition Letters, 2013, 34(15):2007-2022 doi: 10.1016/j.patrec.2013.02.009
    [49] Julesz B. Textons, the elements of texture perception, and their interactions. Nature, 1981, 290(5802):91-97 doi: 10.1038/290091a0
    [50] Csurka G, Dance C, Fan L, Willamowski J, Bray C. Visual categorization with bags of keypoints. In: Proceedings of the 2004 Workshop on Statistical Learning in Computer Vision. Prague, Czech: ECCV, 2004. 1-22
    [51] Leung T, Malik J. Representing and recognizing the visual appearance of materials using three-dimensional textons. International Journal of Computer Vision, 2001, 43(1):29-44 doi: 10.1023/A:1011126920638
    [52] Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks. Science, 2006, 313(5786):504-507 doi: 10.1126/science.1127647
    [53] Krizhevsky A, Sutskever I, Hinton G E. ImageNet classiflcation with deep convolutional neural networks. In: Proceedings of the 25th International Conference on Neural Information Processing Systems (NIPS). Lake Tahoe, Nevada, USA: ACM, 2012. 1097-1105
    [54] LeCun Y, Bottou L, Bengio Y, Hafiner P. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 1998, 86(11):2278-2324 doi: 10.1109/5.726791
    [55] 黄凯奇, 任伟强, 谭铁牛.图像物体分类与检测算法综述.计算机学报, 2014, 36(6):1225-1240 http://kns.cnki.net/KCMS/detail/detail.aspx?filename=jsjx201406001&dbname=CJFD&dbcode=CJFQ

    Huang Kai-Qi, Ren Wei-Qiang, Tan Tie-Niu. A review on image object classiflcation and detection. Chinese Journal of Computers, 2014, 36(6):1225-1240 http://kns.cnki.net/KCMS/detail/detail.aspx?filename=jsjx201406001&dbname=CJFD&dbcode=CJFQ
    [56] Mikolajczyk K, Tuytelaars T, Schmid C, Zisserman A, Matas J, Schafialitzky F, et al. A comparison of affine region detectors. International Journal of Computer Vision, 2005, 65(1-2):43-72 doi: 10.1007/s11263-005-3848-x
    [57] Tuytelaars T, Mikolajczyk K. Local invariant feature detectors:a survey. Foundations and Trendsr in Computer Graphics and Vision, 2008, 3(3):177-280 http://dl.acm.org/citation.cfm?id=1481563&preflayout=flat
    [58] Mikolajczyk K, Schmid C. A performance evaluation of local descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10):1615-1630 doi: 10.1109/TPAMI.2005.188
    [59] Huang Y Z, Wu Z F, Wang L, Tan T N. Feature coding in image classiflcation:a comprehensive study. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(3):493-506 doi: 10.1109/TPAMI.2013.113
    [60] Perronnin F, Larlus D. Fisher vectors meet neural networks: a hybrid classiflcation architecture. In: Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston, USA: IEEE, 2015. 3743-3752
    [61] Sánchez J, Perronnin F, Mensink T, Verbeek J. Image classiflcation with the flsher vector:theory and practice. International Journal of Computer Vision, 2013, 105(3):222-245 doi: 10.1007/s11263-013-0636-x
    [62] Aharon M, Elad M, Bruckstein A. K-SVD:an algorithm for designing overcomplete dictionaries for sparse representation. IEEE Transactions on Signal Processing, 2006, 54(11):4311-4322 doi: 10.1109/TSP.2006.881199
    [63] Mairal J, Bach F, Ponce J, Sapiro G, Zisserman A. Discriminative learned dictionaries for local image analysis. In: Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Anchorage, Alaska, USA: IEEE, 2008. 1-8
    [64] Lazebnik S, Schmid C, Ponce J. Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). New York, USA: IEEE, 2006. 2169-2178
    [65] Lowe D G. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 2004, 60(2):91-110 doi: 10.1023/B:VISI.0000029664.99615.94
    [66] Cula O G, Dana K J. 3D texture recognition using bidirectional feature histograms. International Journal of Computer Vision, 2004, 59(1):33-60 doi: 10.1023/B:VISI.0000020670.05764.55
    [67] Varma M, Zisserman A. A statistical approach to material classiflcation using image patch exemplars. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(11):2032-2047 doi: 10.1109/TPAMI.2008.182
    [68] Ojala T, Pietikäinen M, Harwood D. A comparative study of texture measures with classiflcation based on featured distributions. Pattern Recognition, 1996, 29(1):51-59 doi: 10.1016/0031-3203(95)00067-4
    [69] Liu L, Lao S Y, Fieguth P W, Guo Y L, Wang X G, Pietikainen M. Median robust extended local binary pattern for texture classiflcation. IEEE Transactions on Image Processing, 2016, 25(3):1368-1381 doi: 10.1109/TIP.2016.2522378
    [70] Guo Z H, Wang X Z, Zhou J, You J N. Robust texture image representation by scale selective local binary patterns. IEEE Transactions on Image Processing, 2016, 25(2):687-699 doi: 10.1109/TIP.2015.2507408
    [71] Sulc M, Matas J. Fast features invariant to rotation and scale of texture. In: Proceedings of the 2014 European Conference on Computer Vision (ECCV). Zurich, Switzerland: Springer, 2014. 47-62
    [72] Ryu J, Hong S, Yang H S. Sorted consecutive local binary pattern for texture classiflcation. IEEE Transactions on Image Processing, 2015, 24(7):2254-2265 doi: 10.1109/TIP.2015.2419081
    [73] Sharma G, Juriea F. Local higher-order statistics (LHS) describing images with statistics of local non-binarized pixel patterns. Computer Vision and Image Understanding, 2016, 142:13-22 doi: 10.1016/j.cviu.2015.09.007
    [74] Liu L, Fieguth P. Texture classiflcation from random features. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(3):574-586 doi: 10.1109/TPAMI.2011.145
    [75] Candes E J, Tao T. Near-optimal signal recovery from random projections:universal encoding strategies? IEEE Transactions on Information Theory, 2006, 52(12):5406-5425 doi: 10.1109/TIT.2006.885507
    [76] Donoho D L. Compressed sensing. IEEE Transactions on Information Theory, 2006, 52(4):1289-1306 doi: 10.1109/TIT.2006.871582
    [77] Liu L, Fieguth P, Clausi D, Kuang G Y. Sorted random projections for robust rotation-invariant texture classiflcation. Pattern Recognition, 2012, 45(6):2405-2418 doi: 10.1016/j.patcog.2011.10.027
    [78] Liu L, Fieguth P, Kuang G Y, Zha H B. Sorted random projections for robust texture classiflcation. In: Proceedings of the 2011 IEEE International Conference on Computer Vision (ICCV). Barcelona, Spain: IEEE, 2011. 391-398
    [79] Liu L, Fieguth P W, Hu D W, Wei Y M, Kuang G Y. Fusing sorted random projections for robust texture and material classiflcation. IEEE Transactions on Circuits and Systems for Video Technology, 2015, 25(3):482-496 doi: 10.1109/TCSVT.2014.2359098
    [80] Crosier M, Griffin L D. Using basic image features for texture classiflcation. International Journal of Computer Vision, 2010, 88(3):447-460 doi: 10.1007/s11263-009-0315-0
    [81] Griffin L D, Lillholm M. Symmetry sensitivities of derivative-of-Gaussian fllters. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(6):1072-1083 doi: 10.1109/TPAMI.2009.91
    [82] Griffin L D, Lillholm M, Crosier M, Van Sande J. Basic image features (BIFs) arising from approximate symmetry type. In: Proceedings of the 2nd International Conference on Scale Space and Variational Methods in Computer Vision (SSVM). Voss, Norway: Springer, 2009. 343-355
    [83] Timofte R, Van Gool L. A training-free classiflcation framework for textures, writers, and materials. In: Proceedings of the 23rd British Machine Vision Conference (BMVC). Surrey, Guildford, UK: BMVA, 2012.
    [84] Chen J, Shan S G, He C, Zhao G Y, Pietikainen M, Chen X L, et al. WLD:a robust local image descriptor. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(9):1705-1720 doi: 10.1109/TPAMI.2009.155
    [85] Xu Y, Huang S B, Ji H, Fermüller C. Combining powerful local and global statistics for texture description. In: Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Miami, FL, USA: IEEE, 2009. 573-580
    [86] Xu Y, Yang X, Ling H B, Ji H. A new texture descriptor using multifractal analysis in multi-orientation wavelet pyramid. In: Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). San Francisco, California, USA: IEEE, 2010. 161-168
    [87] Quan Y H, Xu Y, Sun Y P, Luo Y. Lacunarity analysis on image patterns for texture classiflcation. In: Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Columbus, Ohio, USA: IEEE, 2014. 160-167
    [88] Jain A K, Duin R P W, Mao J C. Statistical pattern recognition:a review. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(1):4-37 doi: 10.1109/34.824819
    [89] Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S A, et al. ImageNet large scale visual recognition challenge. International Journal of Computer Vision, 2015, 115(3):211-252 doi: 10.1007/s11263-015-0816-y
    [90] Bengio Y, Courville A, Vincent P. Representation learning:a review and new perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(8):1798-1828 doi: 10.1109/TPAMI.2013.50
    [91] LeCun Y, Bengio Y, Hinton G. Deep learning. Nature, 2015, 521(7553):436-444 doi: 10.1038/nature14539
    [92] Bruna J, Mallat S. Invariant scattering convolution networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(8):1872-1886 doi: 10.1109/TPAMI.2012.230
    [93] Sifre L, Mallat S. Rotation, scaling and deformation invariant scattering for texture discrimination. In: Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Portland, Oregon, USA: IEEE, 2013. 1233-1240
    [94] Sifre L, Mallat S. Rigid-motion scattering for texture classiflcation. International Journal of Computer Vision, 2014. http://arxiv.org/abs/1403.1687
    [95] Chan T H, Jia K, Gao S H, Lu J W, Zeng Z N, Ma Y. PCANet:a simple deep learning baseline for image classiflcation? IEEE Transactions on Image Processing, 2015, 24(12):5017-5032 doi: 10.1109/TIP.2015.2475625
    [96] Gatys L A, Ecker A S, Bethge M. Texture synthesis using convolutional neural networks. In: Proceedings of the 28th International Conference on Neural Information Processing Systems (NIPS). Montreal, Canada: MIT Press, 2015. 262-270
    [97] Lin T Y, RoyChowdhury A, Maji S. Bilinear CNN models for flne-grained visual recognition. In: Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV). Santiago, Chile: IEEE, 2015. 1449-1457
    [98] Lin T Y, Maji S. Visualizing and understanding deep texture representations. In: Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, USA: IEEE, 2016. 2791-2799
    [99] Zhou B L, Lapedriza A, Xiao J X, Torralba A, Oliva A. Learning deep features for scene recognition using places database. In: Proceedings of the 2014 Advances in Neural Information Processing Systems (NIPS). Montreal, Canada: Neural Information Processing Systems, 2014.
    [100] Razavian A S, Azizpour H, Sullivan J, Carlsson S. CNN features ofi-the-shelf: an astounding baseline for recognition. In: Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPR). Columbus, Ohio, USA: IEEE, 2014. 512-519
    [101] Girshick R, Donahue J, Darrell T, Malik J. Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Columbus, Ohio, USA: IEEE, 2014. 580-587
    [102] Sermanet P, Eigen D, Zhang X, Mathieu M, Fergus R, LeCun Y. OverFeat: integrated recognition, localization and detection using convolutional networks. In: Proceedings of the 2014 International Conference on Learning Representation (ICLR). Banfi, Canada: ICLR, 2014.
    [103] Chatfleld K, Simonyan K, Vedaldi A, Zisserman A. Return of the devil in the details: delving deep into convolutional nets. In: Proceedings of the 2014 British Machine Vision Conference (BMVC). Nottingham, UK: BMVA, 2014.
    [104] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In: Proceedings of the 2015 International Conference on Learning Representations (ICLR). San Diego, CA, USA: ICLR, 2015.
    [105] Portilla J, Simoncelli E P. A parametric texture model based on joint statistics of complex wavelet coefficients. International Journal of Computer Vision, 2000, 40(1):49-70 doi: 10.1023/A:1026553619983
    [106] Krishna R, Zhu Y K, Groth O, Johnson J, Hata K, Kravitz J, et al. Visual genome:connecting language and vision using crowdsourced dense image annotations. International Journal of Computer Vision, 2017, 123(1):32-73 doi: 10.1007/s11263-016-0981-7
    [107] Tamura H, Mori S, Yamawaki T. Textural features corresponding to visual perception. IEEE Transactions on Systems, Man, and Cybernetics, 1978, 8(6):460-473 doi: 10.1109/TSMC.1978.4309999
    [108] Bhushan N, Rao A R, Lohse G L. The texture lexicon:understanding the categorization of visual texture terms and their relationship to texture images. Cognitive Science, 1997, 21(2):219-246 doi: 10.1207/s15516709cog2102_4
    [109] Liu L, Fieguth P, Wang X G, Pietikäinen M, Hu D W. Evaluation of LBP and deep texture descriptors with a new robustness benchmark. In: Proceedings of the 14th European Conference on Computer Vision (ECCV). Amsterdam, The Netherlands: Springer, 2016. 69-86
    [110] Mellor M, Hong B W, Brady M. Locally rotation, contrast, and scale invariant descriptors for texture analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(1):52-61 doi: 10.1109/TPAMI.2007.1161
    [111] Hubara I, Courbariaux M, Soudry D, El-Yaniv R, Bengio Y. Binarized neural networks, Advances in neural information processing systems, 2016. 4107-4115
  • 加载中
图(14) / 表(2)
计量
  • 文章访问数:  4350
  • HTML全文浏览量:  871
  • PDF下载量:  1822
  • 被引次数: 0
出版历程
  • 收稿日期:  2016-06-08
  • 录用日期:  2017-05-06
  • 刊出日期:  2018-04-20

目录

    /

    返回文章
    返回