基于朝向对比度的边界检测和图像分类研究
|
摘要
本文主要研究自然场景理解中的两个重要问题：图像边界检测和图像分类。边界检测算法的输出结果是图像的一种压缩表示,常作为高级视觉任务的预处理步骤。图像分类使用抽取的图像特征把一幅图像划分到特定的类别。尽管这两个图像任务看起来是弱相关的,我们认为图像的特征表示是连接这两个任务的关键因素。本文在分析了现有算法的优缺点之后,从图像特征表示的角度给出了更加有效的图像边界检测和图像分类算法。本文取得的主要研究成果如下：
(1)在计算机视觉和模式识别领域,边界检测问题已被广泛研究。最近,研究人员已经把这项任务归结为监督或无监督学习问题,利用机器学习方法,提高了检测精度。然而,对于边界检测问题中比较重要的纹理边缘抑制,并没有包含在此框架中。为了解决这个限制,也受到心理物理学和神经生理学研究结果的启发,我们提出了一个基于朝向对比度的边界检测模型,把机器学习技术和纹理边缘抑制统一在一个框架里。特别地,该模型尤其适合于检测被自然纹理环绕的对象的边界。在几个标准数据库上的实验都验证了该模型的边界检测性能有所改善。具体来说,在Rug数据集上,其检测精度比当前最好的无监督边界检测算法的性能提高了10%,在BSDS500数据集上,其性能至少能与以前的监督边界检测算法的性能相媲美或者更好。
(2)最近,基于稀疏编码的图像分类算法已经在几个常用的图像分类数据库上达到了较高的精度。然而,文献中很少有使用图象的空间信息来改善稀疏编码中的编码或池化操作。本文提出了一种新的空间约束编码方案,它采用局部特征在图像空间上的m-近邻来提高编码的一致性,这隐含的改善了图像的特征表示。具体地,使用这种编码策略,相似的图像特征将被相似的视觉单词进行编码,这降低了常规编码策略的随机性。我们使用当前主流的稀疏编码算法在UIUC体育事件数据库、15自然场景数据库和Caltech101对象数据库上进行了大量的实验,实验结果表明通过使用我们提出的空间约束编码方案,分类性能能够提高,验证了在图像分类问题上我们所提出的方法的通用性和实用性。
(3)我们研究了在使用稀疏编码算法进行图像分类时如何对视觉单词选择最佳池化区域的问题。我们指出,通过使用人脸检测领域众所周知的Viola-Jones算法,可以学习到稀疏编码算法中的池化区域。具体来说,我们使用Boosting技术学习池化区域。实验结果表明只使用低维的图像特征和较小规模的字典就能使图像分类的性能提升到当前主流算法的分类精度(UIUC体育事件数据库、15自然场景数据库和Caltech101对象数据库)。此外,可以显式的学到“显著池化区域”。
(4)最近利用图像中具有判别能力的图像块提取中层特征的方法,已经显示出其在图像分类问题中的威力。我们通过综合局部特征和中层特征来提高图像特征的表达能力。具体而言,我们首先使用SLIC超像素算法将图像过分割为若干超像素区域。然后在每个区域上,我们在落入该区域的局部特征集合上学习到一个子空间。通过一个子空间映射到点的算法把张成子空间的基向量对应为一个新的中层特征。为了合并这两种类型的特征,我们建立两个字典,一个用于对局部特征编码,另一个用于对中层特征编码。最终由局部特征和中层特征的串联构成图像的特征表示。在Caltech101和Caltech256对象数据库上,实验结果表明通过使用中层特征和局部特征,两个基于稀疏编码的图像分类算法的分类精度都显著提高,验证了融合中层特征对于图像分类的实用性。
In this dissertation, we focus on two important problems in natural scene under-standing:image boundary detection and image classification. Usually employed as a preprocessing step for high-level vision tasks, boundary detection algorithms output com-pressed representation for images. While in image classification, an image is classified to some predefined class using the extracted features. Although the two image processing tasks seem to be weakly related, we argue that feature representation is the key factor that links the above two tasks. After analyzing the advantages and disadvantages of the existing algorithms, we propose effective algorithms for image boundary detection and image classification from the feature perspective. Our main contributions are:
(1) The boundary detection task has been extensively studied in the field of computer vision and pattern recognition. Recently, researchers have formulated this task as supervised or unsupervised learning problems to leverage machine learning meth-ods to improve detection accuracy. However, texture suppression, which is impor-tant for boundary detection, is not incorporated in this framework. To address this limitation, and also motivated by psychophysical and neurophysiological findings, we propose an orientation contrast model for boundary detection, which combines machine learning technique and texture suppression in a unified framework. Thus, the model is especially suited for detecting object boundaries surrounded by natural textures. Extensive experiments on several benchmarks demonstrate the improved boundary detection performance of the model. Specifically, its detection accuracy was improved by10%on the Rug dataset compared with state-of-the-art unsuper-vised boundary detection algorithm. And its performance is also better or at least comparable with previous supervised boundary detection algorithms on BSDS500dataset.
(2) Recently, sparse coding-based algorithms have achieved high performance on sev-eral popular image classification benchmarks. However, few works have used the spatial information of local image descriptions to improve either coding or the pool-ing operation. This paper proposes a novel spatially constrained coding scheme, which employs the m-nearest neighbors of a local feature in the image space to im-prove the consistency of coding discriminant ability. Specifically, with this coding strategy, similar image features will be encoded with similar visual words, which reduced the stochasticity of conventional coding strategy. Extensive experiments on the UIUC sport event,15natural scenes and the Caltech101database using sev-eral popular algorithms suggests that the image classification performance can be ubiquitously improved by incorporating the proposed spatially constrained coding scheme, firmly suggesting the generality and usefulness of the proposed approach on image classification.
(3) We study the image feature representation problem in sparse coding algorithm which is how to select the optimal pooling regions for the codewords. We show that the Viola-Jones algorithm, which is well-known in face detection, can be tai-lored to learning pooling regions for the sparse coding algorithms. Specifically, using the boosting approach to learning pooling regions, image classification per-formance can be ubiquitously enhanced on several benchmarks (UIUC sport event,15natural scenes and the Caltech101dataset) to the state-of-the-art, using only low dimensional features and small codebook sizes. Furthermore, the "salient pooling regions" can be obtained explicitly.
(4) Recently, mid-level features extracted from discriminant patches have been demon-strated powerful in image classification problems. We combine local features and mid-level features to obtain a more powerful feature representation for image clas-sification. Specifically, we first segment an image into several coherent regions by SLIC superpixel method. Then, in each region, we learn a subspace from all the local features falling in that region. The basis vectors spanning that subspace are combined to generate a new mid-level feature by the subspace-to-point mapping algorithm. To merge the two types of features, we construct two dictionaries:one for local features and the other for mid-level features, and the two types of features are concatenated to form the final image representation. Extensive experiments on the Caltech101and the Caltech256databases using two popular algorithms sug-gest that by combining the two types of features, the image classification accuracy can be significantly improved, which demonstrates the usefulness of the proposed method for image classification.
(1)在计算机视觉和模式识别领域,边界检测问题已被广泛研究。最近,研究人员已经把这项任务归结为监督或无监督学习问题,利用机器学习方法,提高了检测精度。然而,对于边界检测问题中比较重要的纹理边缘抑制,并没有包含在此框架中。为了解决这个限制,也受到心理物理学和神经生理学研究结果的启发,我们提出了一个基于朝向对比度的边界检测模型,把机器学习技术和纹理边缘抑制统一在一个框架里。特别地,该模型尤其适合于检测被自然纹理环绕的对象的边界。在几个标准数据库上的实验都验证了该模型的边界检测性能有所改善。具体来说,在Rug数据集上,其检测精度比当前最好的无监督边界检测算法的性能提高了10%,在BSDS500数据集上,其性能至少能与以前的监督边界检测算法的性能相媲美或者更好。
(2)最近,基于稀疏编码的图像分类算法已经在几个常用的图像分类数据库上达到了较高的精度。然而,文献中很少有使用图象的空间信息来改善稀疏编码中的编码或池化操作。本文提出了一种新的空间约束编码方案,它采用局部特征在图像空间上的m-近邻来提高编码的一致性,这隐含的改善了图像的特征表示。具体地,使用这种编码策略,相似的图像特征将被相似的视觉单词进行编码,这降低了常规编码策略的随机性。我们使用当前主流的稀疏编码算法在UIUC体育事件数据库、15自然场景数据库和Caltech101对象数据库上进行了大量的实验,实验结果表明通过使用我们提出的空间约束编码方案,分类性能能够提高,验证了在图像分类问题上我们所提出的方法的通用性和实用性。
(3)我们研究了在使用稀疏编码算法进行图像分类时如何对视觉单词选择最佳池化区域的问题。我们指出,通过使用人脸检测领域众所周知的Viola-Jones算法,可以学习到稀疏编码算法中的池化区域。具体来说,我们使用Boosting技术学习池化区域。实验结果表明只使用低维的图像特征和较小规模的字典就能使图像分类的性能提升到当前主流算法的分类精度(UIUC体育事件数据库、15自然场景数据库和Caltech101对象数据库)。此外,可以显式的学到“显著池化区域”。
(4)最近利用图像中具有判别能力的图像块提取中层特征的方法,已经显示出其在图像分类问题中的威力。我们通过综合局部特征和中层特征来提高图像特征的表达能力。具体而言,我们首先使用SLIC超像素算法将图像过分割为若干超像素区域。然后在每个区域上,我们在落入该区域的局部特征集合上学习到一个子空间。通过一个子空间映射到点的算法把张成子空间的基向量对应为一个新的中层特征。为了合并这两种类型的特征,我们建立两个字典,一个用于对局部特征编码,另一个用于对中层特征编码。最终由局部特征和中层特征的串联构成图像的特征表示。在Caltech101和Caltech256对象数据库上,实验结果表明通过使用中层特征和局部特征,两个基于稀疏编码的图像分类算法的分类精度都显著提高,验证了融合中层特征对于图像分类的实用性。
In this dissertation, we focus on two important problems in natural scene under-standing:image boundary detection and image classification. Usually employed as a preprocessing step for high-level vision tasks, boundary detection algorithms output com-pressed representation for images. While in image classification, an image is classified to some predefined class using the extracted features. Although the two image processing tasks seem to be weakly related, we argue that feature representation is the key factor that links the above two tasks. After analyzing the advantages and disadvantages of the existing algorithms, we propose effective algorithms for image boundary detection and image classification from the feature perspective. Our main contributions are:
(1) The boundary detection task has been extensively studied in the field of computer vision and pattern recognition. Recently, researchers have formulated this task as supervised or unsupervised learning problems to leverage machine learning meth-ods to improve detection accuracy. However, texture suppression, which is impor-tant for boundary detection, is not incorporated in this framework. To address this limitation, and also motivated by psychophysical and neurophysiological findings, we propose an orientation contrast model for boundary detection, which combines machine learning technique and texture suppression in a unified framework. Thus, the model is especially suited for detecting object boundaries surrounded by natural textures. Extensive experiments on several benchmarks demonstrate the improved boundary detection performance of the model. Specifically, its detection accuracy was improved by10%on the Rug dataset compared with state-of-the-art unsuper-vised boundary detection algorithm. And its performance is also better or at least comparable with previous supervised boundary detection algorithms on BSDS500dataset.
(2) Recently, sparse coding-based algorithms have achieved high performance on sev-eral popular image classification benchmarks. However, few works have used the spatial information of local image descriptions to improve either coding or the pool-ing operation. This paper proposes a novel spatially constrained coding scheme, which employs the m-nearest neighbors of a local feature in the image space to im-prove the consistency of coding discriminant ability. Specifically, with this coding strategy, similar image features will be encoded with similar visual words, which reduced the stochasticity of conventional coding strategy. Extensive experiments on the UIUC sport event,15natural scenes and the Caltech101database using sev-eral popular algorithms suggests that the image classification performance can be ubiquitously improved by incorporating the proposed spatially constrained coding scheme, firmly suggesting the generality and usefulness of the proposed approach on image classification.
(3) We study the image feature representation problem in sparse coding algorithm which is how to select the optimal pooling regions for the codewords. We show that the Viola-Jones algorithm, which is well-known in face detection, can be tai-lored to learning pooling regions for the sparse coding algorithms. Specifically, using the boosting approach to learning pooling regions, image classification per-formance can be ubiquitously enhanced on several benchmarks (UIUC sport event,15natural scenes and the Caltech101dataset) to the state-of-the-art, using only low dimensional features and small codebook sizes. Furthermore, the "salient pooling regions" can be obtained explicitly.
(4) Recently, mid-level features extracted from discriminant patches have been demon-strated powerful in image classification problems. We combine local features and mid-level features to obtain a more powerful feature representation for image clas-sification. Specifically, we first segment an image into several coherent regions by SLIC superpixel method. Then, in each region, we learn a subspace from all the local features falling in that region. The basis vectors spanning that subspace are combined to generate a new mid-level feature by the subspace-to-point mapping algorithm. To merge the two types of features, we construct two dictionaries:one for local features and the other for mid-level features, and the two types of features are concatenated to form the final image representation. Extensive experiments on the Caltech101and the Caltech256databases using two popular algorithms sug-gest that by combining the two types of features, the image classification accuracy can be significantly improved, which demonstrates the usefulness of the proposed method for image classification.
引文
[1]Elder J H, Zucker S W. Space Scale Localization, Blur, and Contour-Based Image Coding. Pro-ceedings of the 1996 Conference on Computer Vision and Pattern Recognition, Washington, DC, USA:IEEE Computer Society,1996.27-34.
[2]Freixenet J, Munoz X, Raba D, et al. Yet Another Survey on Image Segmentation:Region and Boundary Information Integration. Proceedings of the 7th European Conference on Computer Vision-Part Ⅲ, London, UK, UK:Springer-Verlag,2002.408-422.
[3]Roh M C, Kim T Y, Park J, et al. Accurate Object Contour Tracking Based on Boundary Edge Selection. Pattern Recogn.,2007,40(3):931-943.
[4]Roberts L G. Machine Perception of Three-Dimensional Solids. Outstanding Dissertations in the Computer Sciences, New York, USA:Garland Publishing,1963.
[5]Sobel I. Camera Models and Machine Perception. Stanford, CA, USA:UMI,1970.
[6]Prewitt J M S. Object enhancement and extraction. New York, USA,1970:75-149.
[7]Canny J. A Computational Approach to Edge Detection. IEEE Trans. Pattern Anal. Mach. Intell.,1986,8:679-698.
[8]Bergholm F. Edge focusing. IEEE Trans. Pattern Anal. Mach. Intell.,1987,9:726-741.
[9]Papari G, Petkov N. Edge and line oriented contour detection:State of the art. Image and Vision Computing,2011,29(2-3):79-103.
[10]Arbelaez P, Maire M, Fowlkes C, et al. Contour Detection and Hierarchical Image Segmenta-tion. IEEE Trans. Pattern Anal. Mach. Intell.,2011,33:898-916.
[11]Moore A P, Prince S J D, Warrell J. "Lattice Cut"-Constructing superpixels using layer constraints. Proceedings of CVPR,2010.2117-2124.
[12]Moore A P, Prince S J D, Warrell J, et al. Superpixel lattices.2008 IEEE Conference on Computer Vision and Pattern Recognition,2008,0:1-8.
[13]Csurka G, Dance C R, Fan L, et al. Visual categorization with bags of keypoints. Proceedings of ECCV Workshop on Statistical Learning in Computer Vision,2004.1-22.
[14]Liu Y, Zhang D, Lu G, et al. A Survey of Content-based Image Retrieval with High-level Semantics. Pattern Recogn.,2007,40(1):262-282.
[15]Lu D, Weng Q. A Survey of Image Classification Methods and Techniques for Improving Classification Performance. Int. J. Remote Sens.,2007,28(5):823-870.
[16]Pourghassem H, Ghassemian H. Content-based medical image classification using a new hi-erarchical merging scheme. Computerized Medical Imaging and Graphics,2008,32(8):651-661.
[17]Gibson J J. The Perception of the Visual World. Boston, MA:Houghton Mifflin,1950.
[18]Bennamoun M, Mamic G J. Object Recognition:Fundamentals and Case Studies. Advances in Pattern Recognition, Springer-Verlag London:Springer,2002:1-350.
[19]Rosenfeld A, Thurston M. Edge and Curve Detection for Visual Scene Analysis. IEEE Trans-actions on Computers,1971,20(5):562-569.
[20]Rosenfeld A, Thurston M, Yung-Han Lee. Edge and Curve Detection:Further Experiments. IEEE Transactions on Computers,1972,21(7):677-715.
[21]Davis L S. A survey of edge detection techniques. Computer Graphics and Image Processing, 1975,4(3):248-270.
[22]Marr D, Hildreth E. Theory of Edge Detection. Proceedings of the Royal Society of London Series B,1980,207:187-217.
[23]Haralick R M. Digital Step Edges from Zero Crossing of Second Directional Derivatives. IEEE Trans. Pattern Anal. Mach. Intell.,1984,6(1):58-68.
[24]Poggio T, Torre V, Koch C. Computational Vision and Regularization Theory. Nature,1985, 317(26):314-319.
[25]Torre V, Poggio T A. On Edge Detection. IEEE Trans. Pattern Anal. Mach. Intell.,1986, 8(2):147-163.
[26]Poggio T, Voorhees H, Yuille A. A regularized solution to edge detection. Journal of Com-plexity,1988,4(2):106-123.
[27]Canny J F. Finding Edges and Lines in Images[M]. Cambridge, MA, USA:Artificial Intelli-gence Laboratory, Massachusetts Institute of Technology,1983.
[28]Witkin A P. Scale-space Filtering. Proceedings of the Eighth International Joint Conference on Artificial Intelligence-Volume 2, San Francisco, CA, USA:Morgan Kaufmann Publishers Inc.,1983.1019-1022.
[29]Di Zenzo S. A Note on the Gradient of a Multi-image. Comput. Vision Graph. Image Process., 1986,33(1):116-125.
[30]Jacob M, Unser M. Design of Steerable Filters for Feature Detection Using Canny-like Criteria. IEEE Trans. Pattern Anal. Mach. Intell.,2004,26(8):1007-1019.
[31]Basu M. Gaussian-based Edge-detection Methods-a Survey. IEEE Trans. Sys. Man Cyber Part C,2002,32(3):252-260.
[32]Szeliski R. Computer Vision:Algorithms and Applications.1st ed., New York, NY, USA: Springer-Verlag New York, Inc.,2010.
[33]Grigorescu C, Petkov N, Westenberg M A. Contour detection based on nonclassical receptive field inhibition. IEEE Transactions on Image Processing,2003,12(7):729-739.
[34]Grigorescu C. Contour and boundary detection improved by surround suppression of texture edges. Image and Vision Computing,2004,22(8):609-622.
[35]Papari G, Petkov N. An improved model for surround suppression by steerable filters and multilevel inhibition with application to contour detection. Pattern Recogn.,2011,44:1999-2007.
[36]Freeman W T, Adelson E H. The Design and Use of Steerable Filters. IEEE Trans. Pattern Anal. Mach. Intell.,1991,13:891-906.
[37]Martin D, Fowlkes C, Tal D, et al. A Database of Human Segmented Natural Images and its Application to Evaluating Segmentation Algorithms and Measuring Ecological Statistics. Proceedings of Proc.8th Int'l Conf. Computer Vision, volume 2,2001.416-423.
[38]BSDS500. http://www.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/resources.html, 2011.
[39]Rug. http://www.cs.rug.nl/imaging/PR/,2011.
[40]Martin D R, Fowlkes C C, Malik J. Learning to Detect Natural Image Boundaries Using Local Brightness, Color, and Texture Cues. IEEE Trans. Pattern Anal. Mach. Intel].,2004,26:530-549.
[41]Dollar P, Tu Z, Belongie S. Supervised Learning of Edges and Object Boundaries. Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition-Volume 2, Washington, DC, USA:IEEE Computer Society,2006.1964-1971.
[42]Kokkinos I. Highly accurate boundary detection and grouping.2010 IEEE Conference on Computer Vision and Pattern Recognition,2010,0:2520-2527.
[43]Kokkinos I. Boundary Detection Using F-measure-, Filter-and Feature-(F3) Boost. Pro-ceedings of the 11th European Conference on Computer Vision:Part Ⅱ, Berlin, Heidelberg: Springer-Verlag,2010.650-663.
[44]Ren X, Fowlkes C C, Malik J. Learning Probabilistic Models for Contour Completion in Natural Images. Int. J. Comput. Vision,2008,77(1-3):47-63.
[45]Catanzaro B, Su B, Sundaram N, et al. Efficient, high-quality image contour detection. Pro-ceedings of In IEEE International Conference on Computer Vision,2009.2381-2388.
[46]Ming Y, Li H, He X. Connected contours:A new contour completion model that respects the closure effect. Proceedings of CVPR,2012.829-836.
[47]Ren X, Bo L. Discriminatively Trained Sparse Code Gradients for Contour Detection. Pro-ceedings of NIPS,2012.593-601.
[48]Dollar P, Zitnick C L. Structured Forests for Fast Edge Detection. Proceedings of ICCV,2013. 1841-1848.
[49]Lim J J, Zitnick C L, Dollar P. Sketch Tokens:A Learned Mid-level Representation for Contour and Object Detection.2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013,0:3158-3165.
[50]Zhang C, Li X, Ruan X, et al. Discriminative Generative Contour Detection. Proceedings of the British Machine Vision Conference. BMVA Press,2013.1-11.
[51]Itti L, Koch C, Niebur E. A Model of Saliency-Based Visual Attention for Rapid Scene Anal-ysis. IEEE Trans. Pattern Anal. Mach. Intell.,1998,20(11):1254-1259.
[52]Cheng M M, Zhang G X, Mitra N J, et al. Global Contrast based Salient Region Detection. Proceedings of IEEE CVPR,2011.409-416.
[53]Achanta R, Hemami S, Estrada F, et al. Frequency-tuned salient region detection.2009 IEEE Conference on Computer Vision and Pattern Recognition,2009,0:1597-1604.
[54]Liu T, Sun J, Zheng N N, et al. Learning to Detect A Salient Object. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2007.1-8.
[55]Feng S, Xu D, Yang X. Attention-driven salient edge(s) and region(s) extraction with applica-tion to CBIR. Signal Process.,2010,90(1):1-15.
[56]Hisashi S. A method for detecting boundary edges based on a local image-feature integration method. Information and communication studies,2011,44:15-40.
[57]Sun Y, Fisher R. Object-based visual attention for computer vision. Artif. Intel].,2003, 146(1):77-123.
[58]Zamperoni P. Model-Free Texture Segmentation Based on Distances between First-Order S-tatistics. Digital Signal Processing,1995,5(4):197-225.
[59]Jr E M D, Raudseps J G. Non-parametric unsupervised learning with applications to image classification. Pattern Recognition,1970,2(4):313-335.
[60]Haralick R, Shanmugam K, Dinstein I. Textural Features for Image Classification. IEEE Transactions on Systems, Man and Cybernetics,1973, SMC-3(6):610-621.
[61]Agnelli D, Bollini A, Lombardi L. Image classification:an evolutionary approach. Pattern Recognition Letters,2002,23(1-3):303-309.
[62]Shepherd B A. An appraisal of a decision tree approach to image classification. Proceedings of International Joint Conference on Artificial Intelligence,1983.473-475.
[63]Park S B, Lee J W, Kim S K. Content-based image classification using a neural network. Pattern Recognition Letters,2004,25(3):287-300.
[64]Warfield S. Fast k-NN classification for multichannel image data. Pattern Recognition Letters, 1996,17(7):713-721.
[65]Caelli T, Reye D. On the classification of image regions by colour, texture and shape. Pattern Recognition,1993,26(4):461-470.
[66]Cheng Y C, Chen S Y. Image classification using color, texture and regions. Image and Vision Computing,2003,21(9):759-776.
[67]Chapelle O, Haffner P, Vapnik V. Support vector machines for histogram-based image classifi-cation. IEEE Transactions on Neural Networks,1999,10(5):1055-1064.
[68]Joachims T. A Probabilistic Analysis of the Rocchio Algorithm with TFIDF for Text Catego-rization. Proceedings of the Fourteenth International Conference on Machine Learning, San Francisco, CA, USA:Morgan Kaufmann Publishers Inc.,1997.143-151.
[69]Sivic J, Zisserman A. Video Google:A Text Retrieval Approach to Object Matching in Videos. Proceedings of the Ninth IEEE International Conference on Computer Vision-Volume 2, Washington, DC, USA:IEEE Computer Society,2003.1470-1477.
[70]Li F F, Perona P. A Bayesian Hierarchical Model for Learning Natural Scene Categories. Proceedings of CVPR,2005.524-531.
[71]Lowe D G. Distinctive Image Features from Scale-Invariant Keypoints. Int. J. Comput. Vision, 2004,60(2):91-110.
[72]Lazebnik S, Schmid C, Ponce J. Beyond Bags of Features:Spatial Pyramid Matching for Recognizing Natural Scene Categories. Proceedings of CVPR,2006.2169-2178.
[73]Grauman K, Darrell T. The pyramid match kernel:Discriminative classification with sets of image features. Proceedings of In ICCV,2005.1458-1465.
[74]Cao Y, Wang C, Li Z, et al. Spatial-bag-of-features. Proceedings of 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2010.3352-3359.
[75]Wu Z, Ke Q, Isard M, et al. Bundling features for large scale partial-duplicate web image search. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2009. 25-32.
[76]Matas J, Chum O, Urban M, et al. Robust Wide Baseline Stereo from Maximally Stable Extremal Regions. Proceedings of BMVC,2002.1-10.
[77]Yang J, Yu K, Gong Y, et al. Linear spatial pyramid matching using sparse coding for image classification. Proceedings of CVPR,2009.1974-1801.
[78]Boureau Y, Bach F, LeCun Y, et al. Learning Mid-Level Features for Recognition. Proceedings of CVPR,2010.2559-2566.
[79]Wang J, Yang J, Yu K, et al. Locality-constrained linear coding for image classification. Pro-ceedings of CVPR,2010.3360-3367.
[80]Liu L, Wang L, Liu X. In defense of soft-assignment coding. Proceedings of ICCV,2011. 2486-2493.
[81]Huang Y, Huang K, Yu Y, et al. Salient coding for image classification. Proceedings of CVPR, 2011.1753-1760.
[82]Perronnin F, Dance C. Fisher Kernels on Visual Vocabularies for Image Categorization. Pro-ceedings of IEEE Conference on Computer Vision and Pattern Recognition,2007.1-8.
[83]Perronnin F, Sanchez J, Mensink T. Improving the Fisher Kernel for Large-scale Image Clas-sification. Proceedings of the 11th European Conference on Computer Vision:Part Ⅳ, Berlin, Heidelberg:Springer-Verlag,2010.143-156.
[84]Sanchez J, Perronnin F, Mensink T, et al. Image Classification with the Fisher Vector:Theory and Practice. International Journal of Computer Vision,2013,105(3):222-245.
[85]Huang Y, Wu Z, Wang L, et al. Feature Coding in Image Classification:A Comprehensive Study. IEEE Trans. Pattern Anal. Mach. Intell.,2014,36(3):493-506.
[86]Jia Y, Huang C, Darrell T. Beyond spatial pyramids:Receptive field learning for pooled image features. Proceedings of CVPR,2012.3370-3377.
[87]Yan S, Xu X, Xu D, et al. Beyond spatial pyramids:a new feature extraction framework with dense spatial sampling for image classification. Proceedings of the 12th European conference on Computer Vision-Volume Part IV, Berlin, Heidelberg:Springer-Verlag,2012.473-487.
[88]Russakovsky O, Lin Y, Yu K, et al. Object-Centric spatial pooling for image classification. Proceedings of the 12th European conference on Computer Vision-Volume Part Ⅱ, Berlin, Heidelberg:Springer-Verlag,2012.1-15.
[89]Ji Z, Wang J, Su Y, et al. Balance between object and background:Object-enhanced features for scene image classification. Neurocomputing,2013,120(0):15-23.
[90]Zhu J, Zou W, Yang X, et al. Image Classification by Hierarchical Spatial Pooling with Partial Least Squares Analysis. Proceedings of the British Machine Vision Conference. BMVA Press, 2012.1-11.
[91]Feng J, Ni B, Tian Q, et al. Geometric lp-norm feature pooling for image classification. Pro-ceedings of CVPR,2011.2697-2704.
[92]Xie L, Tian Q, Zhang B. Spatial Pooling of Heterogeneous Features for Image Applications. Proceedings of the 20th ACM International Conference on Multimedia, New York, NY, USA: ACM,2012.539-548.
[93]Cao L, Ji R, Gao Y, et al. Weakly supervised sparse coding with geometric consistency pooling. Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012.3578-3585.
[94]Doersch C, Singh S, Gupta A, et al. What Makes Paris Look Like Paris? ACM Trans. Graph., 2012,31(4):101:1-101:9.
[95]Singh S, Gupta A, Efros A A. Unsupervised Discovery of Mid-level Discriminative Patches. Proceedings of the 12th European Conference on Computer Vision-Volume Part II, Berlin, Heidelberg:Springer-Verlag,2012.73-86.
[96]Juneja M, Vedaldi A, Jawahar C V, et al. Blocks That Shout:Distinctive Parts for Scene Classification. Proceedings of CVPR,2013.923-930.
[97]Jain A, Gupta A, Rodriguez M, et al. Representing Videos Using Mid-level Discriminative Patches. Proceedings of CVPR,2013.2571-2578.
[98]Malisiewicz T, Gupta A, Efros A A. Ensemble of exemplar-SVMs for Object Detection and Beyond. Proceedings of the 2011 International Conference on Computer Vision, Washington, DC, USA:IEEE Computer Society,2011.89-96.
[99]Viola P, Jones M J. Robust Real-Time Face Detection. Int. J. Comput. Vision,2004,57(2):137-154.
[100]Li L, Fei-Fei L. What, where and who? classifying event by scene and object recognition. Proceedings of In IEEE International Conference on Computer Vision,2007.1-8.
[101]Oliva A, Torralba A. Modeling the Shape of the Scene:A Holistic Representation of the Spatial Envelope. Int. J. Comput. Vision,2001,42(3):145-175.
[102]Fei-Fei L, Fergus R, Perona P. Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. Proceedings of Workshop on Generative-Model Based Vision,2004.
[103]Griffin G, Holub A, Perona P. Caltech-256 Object Category Dataset. Technical Report 7694, California Institute of Technology,2007. http://authors.library.caltech.edu/7694.
[104]Najman L, Schmitt M. Geodesic Saliency of Watershed Contours and Hierarchical Segmenta-tion. IEEE Trans. Pattern Anal. Mach. Intell.,1996,18(12):1163-1173.
[105]Nitzberg M, Mumford D, Shiota T. Filtering, Segmentation, and Depth. Secaucus, NJ, USA: Springer-Verlag New York, Inc.,1993.
[106]Elder J H, Goldberg R M. Ecological statistics of Gestalt laws for the perceptual organization of contours. J Vis,2002,2(4):324-353.
[107]Papari G, Petkov N. Adaptive Pseudo Dilation for Gestalt Edge Grouping and Contour Detec-tion. IEEE Transactions on Image Processing,2008,17(10):1950-1962.
[108]Jermyn I H, Ishikawa H. Globally Optimal Regions and Boundaries As Minimum Ratio Weight Cycles. IEEE Trans. Pattern Anal. Mach. Intell.,2001,23(10):1075-1088.
[109]Liu T, Yuan Z, Sun J, et al. Learning to Detect a Salient Object. IEEE Trans. Pattern Anal. Mach. Intell.,2011,33(2):353-367.
[110]Deng Y,, SManjunath B. Unsupervised segmentation of color-texture regions in images and video. IEEE Trans. Pattern Anal. Mach. Intell.,2001,23(8):800-810.
[111]Feldman J, Singh M. Information along contours and object boundaries. Psychol Rev,2005, 112(1):243-252.
[112]Sirovich L, Kirby M. Low-dimensional procedure for the characterization of human faces. JOS A A,1987,4(3):519-524.
[113]Turk M, Pentland A. Eigenfaces for Recognition. J. Cognitive Neuroscience,1991,3(1):71-86.
[114]Dalal N, Triggs B. Histograms of Oriented Gradients for Human Detection. Proceedings of CVPR,2005.886-893.
[115]Ojala T, Pietikainen M, Harwood D. A comparative study of texture measures with classifica-tion based on featured distributions. Pattern Recognition,1996,29(1):51-59.
[116]Harris C, Stephens M. A Combined Corner and Edge Detector. Proceedings of the Alvey Vision Conference. Alvety Vision Club,1988.147-152.
[117]Mikolajczyk K, Schmid C. Scale & Amp; A ffine Invariant Interest Point Detectors. Int. J. Comput. Vision,2004,60(l):63-86.
[118]Tuytelaars T, Mikolajczyk K. Local Invariant Feature Detectors:A Survey. Hanover, MA, USA:Now Publishers Inc.,2008.
[119]Mikolajczyk K, Schmid C. A Performance Evaluation of Local Descriptors. IEEE Trans. Pattern Anal. Mach. Intell.,2005,27(10):1615-1630.
[120]Carson C, Belongie S, Greenspan H, et al. Blobworld:Image Segmentation Using Expectation-Maximization and Its Application to Image Querying. IEEE Trans. Pattern Anal. Mach. Intell., 2002,24(8):1026-1038.
[121]Wang J Z, Li J, Wiederhold G. SIMPLIcity:Semantics-Sensitive Integrated Matching for Picture LIbraries. IEEE Trans. Pattern Anal. Mach. Intell.,2001,23(9):947-963.
[122]Ren X, Malik J. Learning a classification model for segmentation. Proceedings of Ninth IEEE International Conference on Computer Vision, volume 1,2003.10-17.
[123]Vedaldi A, Soatto S. Quick Shift and Kernel Methods for Mode Seeking. Proceedings of ECCV (4),2008.705-718.
[124]Levinshtein A, Stere A, Kutulakos K N, et al. TurboPixels:Fast Superpixels Using Geometric Flows. IEEE Trans. Pattern Anal. Mach. Intell.,2009,31(12):2290-2297.
[125]Liu M Y, Tuzel O, Ramalingam S, et al. Entropy rate superpixel segmentation.2011 IEEE Conference on Computer Vision and Pattern Recognition,2011,0:2097-2104.
[126]Achanta R, Shaji A, Smith K, et al. SLIC Superpixels Compared to State-of-the-Art Superpixel Methods. IEEE Trans. Pattern Anal. Mach. Intell.,2012,34(11):2274-2282.
[127]Kaufhold J, Hoogs A. Learning to segment images using region-based perceptual features. Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, volume 2,2004.954-961.
[128]Kennedy R, Gallier J, Shi J. Contour cut:Identifying salient contours in images by solving a Hermitian eigenvalue problem. Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition, Washington, DC, USA:IEEE Computer Society,2011.2065-2072.
[129]Kovacs I, Julesz B. A Closed Curve Is Much More Than an Incomplete One:Effect of Closure in Figure-Ground Segmentation. Proceedings of the National Academy of Sciences, USA, 1993,90:7495-7497.
[130]Elder J H, Zucker S W. Computing Contour Closure. Proceedings of In Proc.4th European Conference on Computer Vision,1996.399-412.
[131]Hariharan B, Arbelaez P, Bourdev L, et al. Semantic contours from inverse detectors. IEEE International Conference on Computer Vision,2011,0:991-998.
[132]Landy M S, Graham N. Visual Perception of Texture. Proceedings of The Visual Neuro-sciences. MIT Press,2004. 1106-1118.
[133]Zhang H, Xie B, Yu J. An Improved Surround Suppression Model Based on Orientation Con-trast for Boundary Detection. Proceedings of 21th International Conference on Pattern Recog-nition,2012.3086-3089.
[134]Fan R E, Chang K W, Hsieh C J, et al. LIBLINEAR:A Library for Large Linear Classification. J. Mach. Learn. Res.,2008,9:1871-1874.
[135]Ng A Y, Jordan M I, Weiss Y. On Spectral Clustering:Analysis and an algorithm. Proceedings of Advances in neural information processing systems. MIT Press,2001.849-856.
[136]Torralba A, Efros A. Unbiased look at dataset bias. Proceedings of 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2011.1521-1528.
[137]Pascal VOC 2010. http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2010/,2010.
[138]Deng J, Dong W, Socher R, et al. ImageNet:A large-scale hierarchical image database. Pro-ceedings of IEEE Conference on Computer Vision and Pattern Recognition,2009.248-255.
[139]Savitzky A, Golay M J E. Smoothing and Differentiation of Data by Simplified Least Squares Procedures. Analytical Chemistry,1964,36(8):1627-1639.
[140]Pratt W K. Digital Image Processing:PIKS Inside.3rd ed., New York, NY, USA:John Wiley & Sons, Inc.,2001.
[141]Esakkirajan S, Veerakumar T, Subramanyam A N, et al. Removal of High Density Salt and Pepper Noise Through Modified Decision Based Unsymmetric Trimmed Median Filter. IEEE Signal Process. Lett.,2011,18(5):287-290.
[142]Olshausen B, Field D. Emergence of Simple-Cell Receptive Field Properties by Learning a Sparse Code for Natural Images. Nature,1996,381.607-609.
[143]Olshausen B A, Fieldt D J. Sparse coding with an overcomplete basis set:a strategy employed by V1. Vision Research,1997,37:3311-3325.
[144]Gao S, Tsang I W H, Chia L T, et al. Local features are not lonely-Laplacian sparse coding for image classification. Proceedings of CVPR,2010.3555-3561.
[145]Shabou A, Borgne H L. Locality-constrained and spatially regularized coding for scene cate-gorization. Proceedings of CVPR,2012.3618-3625.
[146]Boureau Y L, Le Roux N, Bach F, et al. Ask the locals:Multi-way local pooling for image recognition. Proceedings of the 2011 International Conference on Computer Vision, Washing-ton, DC, USA:IEEE Computer Society,2011.2651-2658.
[147]Hyvarinen A, Hoyer P O. A two-layer sparse coding model learns simple and complex cell receptive fields and topography from natural images. Vision Research,2001,41(18):2413-2423.
[148]Schapire R E, Singer Y. Improved Boosting Algorithms Using Confidence-rated Predictions. Mach. Learn.,1999,37(3):297-336.
[149]Freund Y, Schapire R E. A decision-theoretic generalization of on-line learning and an applica-tion to boosting. Proceedings of the Second European Conference on Computational Learning Theory, London, UK, UK:Springer-Verlag,1995.23-37.
[150]Benbouzid D, Busa-Fekete R, Casagrande N, et al. MULTIBOOST:A Multi-purpose Boosting Package. J. Mach. Learn. Res.,2012,13:549-553.
[151]Busa-Fekete R, Kegl B. Fast boosting using adversarial bandits. Proceedings of ICML,2010. 143-150.
[152]Wang Z, Feng J, Yan S, et al. Image Classification via Object-Aware Holistic Superpixel Selection. IEEE Transactions on Image Processing,2013,22(11):4341-4352.
[153]Huang R, Sang N, Luo D, et al. Image Segmentation via Coherent Clustering in L*a*B* Color Space. Pattern Recogn. Lett.,2011,32(7):891-902.
[154]Xiang D, Tang T, Zhao L, et al. Superpixel Generating Algorithm Based on Pixel Intensity and Location Similarity for SAR Image Classification. Geoscience and Remote Sensing Letters, IEEE,2013,10(6):1414-1418.
[155]Fu K, Gong C, Yang J, et al. Superpixel based color contrast and color distribution driven salient object detection. Signal Processing:Image Communication,2013,28(10):1448-1463.
[156]Lu H, Feng X, Li X, et al. Superpixel level object recognition under local learning framework. Neurocomputing,2013,120:203-213.
[157]Yuan Y, Fang J, Wang Q. Robust Superpixel Tracking via Depth Fusion. IEEE Transactions on Circuits and Systems for Video Technology,2014,24(1):15-26.
[158]Vincent L, Soille P. Watersheds in Digital Spaces:An Efficient Algorithm Based on Immersion Simulations. IEEE Trans. Pattern Anal. Mach. Intell.,1991,13(6):583-598.
[159]Comaniciu D, Meer P. Mean Shift:A Robust Approach Toward Feature Space Analysis. IEEE Trans. Pattern Anal. Mach. Intell.,2002,24(5):603-619.
[160]Shi J, Malik J. Normalized Cuts and Image Segmentation. IEEE Trans. Pattern Anal. Mach. Intell.,2000,22(8):888-905.
[161]Felzenszwalb P F, Huttenlocher D P. Efficient Graph-Based Image Segmentation. Int. J. Com-put. Vision,2004,59(2):167-181.
[162]Endres I, Hoiem D. Category Independent Object Proposals. Proceedings of the 11th European Conference on Computer Vision:Part V, Berlin, Heidelberg:Springer-Verlag,2010.575-588.
[163]Endres I, Hoiem D. Category-Independent Object Proposals with Diverse Ranking. IEEE Trans. Pattern Anal. Mach. Intell.,2014,36(2):222-234.
[164]Cheng M M, Zhang Z, Lin W Y, et al. BING:Binarized Normed Gradients for Objectness Estimation at 300fps. Proceedings of IEEE CVPR,2014.
[165]Tuzel O, Porikli F, Meer P. Region Covariance:A Fast Descriptor for Detection and Classi-fication. Proceedings of the 9th European Conference on Computer Vision-Volume Part II, Berlin, Heidelberg:Springer-Verlag,2006.589-600.
[166]Forstner W, Moonen B. A Metric for Covariance Matrices. In:Krumm F, Schwarze V S, (eds.). Proceedings of Festschrift for Erik W. Grafarend on the occasion of his 60th birthday,1999. 113-128.
[167]Cherian A, Sra S, Banerjee A, et al. Efficient similarity search for covariance matrices via the Jensen-Bregman LogDet Divergence. Proceedings of 2011 IEEE International Conference on Computer Vision (ICCV),2011.2399-2406.
[168]Cherian A, Sra S, Banerjee A, et al. Jensen-Bregman LogDet Divergence with Application to Efficient Similarity Search for Covariance Matrices. IEEE Trans. Pattern Anal. Mach. Intell., 2013,35(9):2161-2174.
[169]Hassner T,Mayzels V,Zelnik-Manor L. On SIFTs and their scales. Proceedings of 2012 IEEE Conference on Computer "Vision and Pattern Recognition (CVPR),2012.1522-1528.
[170]Basri R, Hassner T, Zelnik-Manor L. Approximate Nearest Subspace Search with Applications to Pattern Recognition. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Los Alamitos, CA, USA:IEEE Computer Society,2007.1-8.
[171]Basri R, Hassner T, Zelnik-Manor L. Approximate Nearest Subspace Search. IEEE Trans. Pattern Anal. Mach. Intell.,2011,33(2):266-278.
[172]Vedaldi A, Fulkerson B. Vlfeat:An Open and Portable Library of Computer Vision Algorithm-s. Proceedings of the International Conference on Multimedia, New York, NY, USA:ACM, 2010.1469-1472.
[173]Elder J, Zucker S. A measure of closure. Vision Research,1994,34(24):3361-3369.
[2]Freixenet J, Munoz X, Raba D, et al. Yet Another Survey on Image Segmentation:Region and Boundary Information Integration. Proceedings of the 7th European Conference on Computer Vision-Part Ⅲ, London, UK, UK:Springer-Verlag,2002.408-422.
[3]Roh M C, Kim T Y, Park J, et al. Accurate Object Contour Tracking Based on Boundary Edge Selection. Pattern Recogn.,2007,40(3):931-943.
[4]Roberts L G. Machine Perception of Three-Dimensional Solids. Outstanding Dissertations in the Computer Sciences, New York, USA:Garland Publishing,1963.
[5]Sobel I. Camera Models and Machine Perception. Stanford, CA, USA:UMI,1970.
[6]Prewitt J M S. Object enhancement and extraction. New York, USA,1970:75-149.
[7]Canny J. A Computational Approach to Edge Detection. IEEE Trans. Pattern Anal. Mach. Intell.,1986,8:679-698.
[8]Bergholm F. Edge focusing. IEEE Trans. Pattern Anal. Mach. Intell.,1987,9:726-741.
[9]Papari G, Petkov N. Edge and line oriented contour detection:State of the art. Image and Vision Computing,2011,29(2-3):79-103.
[10]Arbelaez P, Maire M, Fowlkes C, et al. Contour Detection and Hierarchical Image Segmenta-tion. IEEE Trans. Pattern Anal. Mach. Intell.,2011,33:898-916.
[11]Moore A P, Prince S J D, Warrell J. "Lattice Cut"-Constructing superpixels using layer constraints. Proceedings of CVPR,2010.2117-2124.
[12]Moore A P, Prince S J D, Warrell J, et al. Superpixel lattices.2008 IEEE Conference on Computer Vision and Pattern Recognition,2008,0:1-8.
[13]Csurka G, Dance C R, Fan L, et al. Visual categorization with bags of keypoints. Proceedings of ECCV Workshop on Statistical Learning in Computer Vision,2004.1-22.
[14]Liu Y, Zhang D, Lu G, et al. A Survey of Content-based Image Retrieval with High-level Semantics. Pattern Recogn.,2007,40(1):262-282.
[15]Lu D, Weng Q. A Survey of Image Classification Methods and Techniques for Improving Classification Performance. Int. J. Remote Sens.,2007,28(5):823-870.
[16]Pourghassem H, Ghassemian H. Content-based medical image classification using a new hi-erarchical merging scheme. Computerized Medical Imaging and Graphics,2008,32(8):651-661.
[17]Gibson J J. The Perception of the Visual World. Boston, MA:Houghton Mifflin,1950.
[18]Bennamoun M, Mamic G J. Object Recognition:Fundamentals and Case Studies. Advances in Pattern Recognition, Springer-Verlag London:Springer,2002:1-350.
[19]Rosenfeld A, Thurston M. Edge and Curve Detection for Visual Scene Analysis. IEEE Trans-actions on Computers,1971,20(5):562-569.
[20]Rosenfeld A, Thurston M, Yung-Han Lee. Edge and Curve Detection:Further Experiments. IEEE Transactions on Computers,1972,21(7):677-715.
[21]Davis L S. A survey of edge detection techniques. Computer Graphics and Image Processing, 1975,4(3):248-270.
[22]Marr D, Hildreth E. Theory of Edge Detection. Proceedings of the Royal Society of London Series B,1980,207:187-217.
[23]Haralick R M. Digital Step Edges from Zero Crossing of Second Directional Derivatives. IEEE Trans. Pattern Anal. Mach. Intell.,1984,6(1):58-68.
[24]Poggio T, Torre V, Koch C. Computational Vision and Regularization Theory. Nature,1985, 317(26):314-319.
[25]Torre V, Poggio T A. On Edge Detection. IEEE Trans. Pattern Anal. Mach. Intell.,1986, 8(2):147-163.
[26]Poggio T, Voorhees H, Yuille A. A regularized solution to edge detection. Journal of Com-plexity,1988,4(2):106-123.
[27]Canny J F. Finding Edges and Lines in Images[M]. Cambridge, MA, USA:Artificial Intelli-gence Laboratory, Massachusetts Institute of Technology,1983.
[28]Witkin A P. Scale-space Filtering. Proceedings of the Eighth International Joint Conference on Artificial Intelligence-Volume 2, San Francisco, CA, USA:Morgan Kaufmann Publishers Inc.,1983.1019-1022.
[29]Di Zenzo S. A Note on the Gradient of a Multi-image. Comput. Vision Graph. Image Process., 1986,33(1):116-125.
[30]Jacob M, Unser M. Design of Steerable Filters for Feature Detection Using Canny-like Criteria. IEEE Trans. Pattern Anal. Mach. Intell.,2004,26(8):1007-1019.
[31]Basu M. Gaussian-based Edge-detection Methods-a Survey. IEEE Trans. Sys. Man Cyber Part C,2002,32(3):252-260.
[32]Szeliski R. Computer Vision:Algorithms and Applications.1st ed., New York, NY, USA: Springer-Verlag New York, Inc.,2010.
[33]Grigorescu C, Petkov N, Westenberg M A. Contour detection based on nonclassical receptive field inhibition. IEEE Transactions on Image Processing,2003,12(7):729-739.
[34]Grigorescu C. Contour and boundary detection improved by surround suppression of texture edges. Image and Vision Computing,2004,22(8):609-622.
[35]Papari G, Petkov N. An improved model for surround suppression by steerable filters and multilevel inhibition with application to contour detection. Pattern Recogn.,2011,44:1999-2007.
[36]Freeman W T, Adelson E H. The Design and Use of Steerable Filters. IEEE Trans. Pattern Anal. Mach. Intell.,1991,13:891-906.
[37]Martin D, Fowlkes C, Tal D, et al. A Database of Human Segmented Natural Images and its Application to Evaluating Segmentation Algorithms and Measuring Ecological Statistics. Proceedings of Proc.8th Int'l Conf. Computer Vision, volume 2,2001.416-423.
[38]BSDS500. http://www.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/resources.html, 2011.
[39]Rug. http://www.cs.rug.nl/imaging/PR/,2011.
[40]Martin D R, Fowlkes C C, Malik J. Learning to Detect Natural Image Boundaries Using Local Brightness, Color, and Texture Cues. IEEE Trans. Pattern Anal. Mach. Intel].,2004,26:530-549.
[41]Dollar P, Tu Z, Belongie S. Supervised Learning of Edges and Object Boundaries. Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition-Volume 2, Washington, DC, USA:IEEE Computer Society,2006.1964-1971.
[42]Kokkinos I. Highly accurate boundary detection and grouping.2010 IEEE Conference on Computer Vision and Pattern Recognition,2010,0:2520-2527.
[43]Kokkinos I. Boundary Detection Using F-measure-, Filter-and Feature-(F3) Boost. Pro-ceedings of the 11th European Conference on Computer Vision:Part Ⅱ, Berlin, Heidelberg: Springer-Verlag,2010.650-663.
[44]Ren X, Fowlkes C C, Malik J. Learning Probabilistic Models for Contour Completion in Natural Images. Int. J. Comput. Vision,2008,77(1-3):47-63.
[45]Catanzaro B, Su B, Sundaram N, et al. Efficient, high-quality image contour detection. Pro-ceedings of In IEEE International Conference on Computer Vision,2009.2381-2388.
[46]Ming Y, Li H, He X. Connected contours:A new contour completion model that respects the closure effect. Proceedings of CVPR,2012.829-836.
[47]Ren X, Bo L. Discriminatively Trained Sparse Code Gradients for Contour Detection. Pro-ceedings of NIPS,2012.593-601.
[48]Dollar P, Zitnick C L. Structured Forests for Fast Edge Detection. Proceedings of ICCV,2013. 1841-1848.
[49]Lim J J, Zitnick C L, Dollar P. Sketch Tokens:A Learned Mid-level Representation for Contour and Object Detection.2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013,0:3158-3165.
[50]Zhang C, Li X, Ruan X, et al. Discriminative Generative Contour Detection. Proceedings of the British Machine Vision Conference. BMVA Press,2013.1-11.
[51]Itti L, Koch C, Niebur E. A Model of Saliency-Based Visual Attention for Rapid Scene Anal-ysis. IEEE Trans. Pattern Anal. Mach. Intell.,1998,20(11):1254-1259.
[52]Cheng M M, Zhang G X, Mitra N J, et al. Global Contrast based Salient Region Detection. Proceedings of IEEE CVPR,2011.409-416.
[53]Achanta R, Hemami S, Estrada F, et al. Frequency-tuned salient region detection.2009 IEEE Conference on Computer Vision and Pattern Recognition,2009,0:1597-1604.
[54]Liu T, Sun J, Zheng N N, et al. Learning to Detect A Salient Object. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2007.1-8.
[55]Feng S, Xu D, Yang X. Attention-driven salient edge(s) and region(s) extraction with applica-tion to CBIR. Signal Process.,2010,90(1):1-15.
[56]Hisashi S. A method for detecting boundary edges based on a local image-feature integration method. Information and communication studies,2011,44:15-40.
[57]Sun Y, Fisher R. Object-based visual attention for computer vision. Artif. Intel].,2003, 146(1):77-123.
[58]Zamperoni P. Model-Free Texture Segmentation Based on Distances between First-Order S-tatistics. Digital Signal Processing,1995,5(4):197-225.
[59]Jr E M D, Raudseps J G. Non-parametric unsupervised learning with applications to image classification. Pattern Recognition,1970,2(4):313-335.
[60]Haralick R, Shanmugam K, Dinstein I. Textural Features for Image Classification. IEEE Transactions on Systems, Man and Cybernetics,1973, SMC-3(6):610-621.
[61]Agnelli D, Bollini A, Lombardi L. Image classification:an evolutionary approach. Pattern Recognition Letters,2002,23(1-3):303-309.
[62]Shepherd B A. An appraisal of a decision tree approach to image classification. Proceedings of International Joint Conference on Artificial Intelligence,1983.473-475.
[63]Park S B, Lee J W, Kim S K. Content-based image classification using a neural network. Pattern Recognition Letters,2004,25(3):287-300.
[64]Warfield S. Fast k-NN classification for multichannel image data. Pattern Recognition Letters, 1996,17(7):713-721.
[65]Caelli T, Reye D. On the classification of image regions by colour, texture and shape. Pattern Recognition,1993,26(4):461-470.
[66]Cheng Y C, Chen S Y. Image classification using color, texture and regions. Image and Vision Computing,2003,21(9):759-776.
[67]Chapelle O, Haffner P, Vapnik V. Support vector machines for histogram-based image classifi-cation. IEEE Transactions on Neural Networks,1999,10(5):1055-1064.
[68]Joachims T. A Probabilistic Analysis of the Rocchio Algorithm with TFIDF for Text Catego-rization. Proceedings of the Fourteenth International Conference on Machine Learning, San Francisco, CA, USA:Morgan Kaufmann Publishers Inc.,1997.143-151.
[69]Sivic J, Zisserman A. Video Google:A Text Retrieval Approach to Object Matching in Videos. Proceedings of the Ninth IEEE International Conference on Computer Vision-Volume 2, Washington, DC, USA:IEEE Computer Society,2003.1470-1477.
[70]Li F F, Perona P. A Bayesian Hierarchical Model for Learning Natural Scene Categories. Proceedings of CVPR,2005.524-531.
[71]Lowe D G. Distinctive Image Features from Scale-Invariant Keypoints. Int. J. Comput. Vision, 2004,60(2):91-110.
[72]Lazebnik S, Schmid C, Ponce J. Beyond Bags of Features:Spatial Pyramid Matching for Recognizing Natural Scene Categories. Proceedings of CVPR,2006.2169-2178.
[73]Grauman K, Darrell T. The pyramid match kernel:Discriminative classification with sets of image features. Proceedings of In ICCV,2005.1458-1465.
[74]Cao Y, Wang C, Li Z, et al. Spatial-bag-of-features. Proceedings of 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2010.3352-3359.
[75]Wu Z, Ke Q, Isard M, et al. Bundling features for large scale partial-duplicate web image search. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2009. 25-32.
[76]Matas J, Chum O, Urban M, et al. Robust Wide Baseline Stereo from Maximally Stable Extremal Regions. Proceedings of BMVC,2002.1-10.
[77]Yang J, Yu K, Gong Y, et al. Linear spatial pyramid matching using sparse coding for image classification. Proceedings of CVPR,2009.1974-1801.
[78]Boureau Y, Bach F, LeCun Y, et al. Learning Mid-Level Features for Recognition. Proceedings of CVPR,2010.2559-2566.
[79]Wang J, Yang J, Yu K, et al. Locality-constrained linear coding for image classification. Pro-ceedings of CVPR,2010.3360-3367.
[80]Liu L, Wang L, Liu X. In defense of soft-assignment coding. Proceedings of ICCV,2011. 2486-2493.
[81]Huang Y, Huang K, Yu Y, et al. Salient coding for image classification. Proceedings of CVPR, 2011.1753-1760.
[82]Perronnin F, Dance C. Fisher Kernels on Visual Vocabularies for Image Categorization. Pro-ceedings of IEEE Conference on Computer Vision and Pattern Recognition,2007.1-8.
[83]Perronnin F, Sanchez J, Mensink T. Improving the Fisher Kernel for Large-scale Image Clas-sification. Proceedings of the 11th European Conference on Computer Vision:Part Ⅳ, Berlin, Heidelberg:Springer-Verlag,2010.143-156.
[84]Sanchez J, Perronnin F, Mensink T, et al. Image Classification with the Fisher Vector:Theory and Practice. International Journal of Computer Vision,2013,105(3):222-245.
[85]Huang Y, Wu Z, Wang L, et al. Feature Coding in Image Classification:A Comprehensive Study. IEEE Trans. Pattern Anal. Mach. Intell.,2014,36(3):493-506.
[86]Jia Y, Huang C, Darrell T. Beyond spatial pyramids:Receptive field learning for pooled image features. Proceedings of CVPR,2012.3370-3377.
[87]Yan S, Xu X, Xu D, et al. Beyond spatial pyramids:a new feature extraction framework with dense spatial sampling for image classification. Proceedings of the 12th European conference on Computer Vision-Volume Part IV, Berlin, Heidelberg:Springer-Verlag,2012.473-487.
[88]Russakovsky O, Lin Y, Yu K, et al. Object-Centric spatial pooling for image classification. Proceedings of the 12th European conference on Computer Vision-Volume Part Ⅱ, Berlin, Heidelberg:Springer-Verlag,2012.1-15.
[89]Ji Z, Wang J, Su Y, et al. Balance between object and background:Object-enhanced features for scene image classification. Neurocomputing,2013,120(0):15-23.
[90]Zhu J, Zou W, Yang X, et al. Image Classification by Hierarchical Spatial Pooling with Partial Least Squares Analysis. Proceedings of the British Machine Vision Conference. BMVA Press, 2012.1-11.
[91]Feng J, Ni B, Tian Q, et al. Geometric lp-norm feature pooling for image classification. Pro-ceedings of CVPR,2011.2697-2704.
[92]Xie L, Tian Q, Zhang B. Spatial Pooling of Heterogeneous Features for Image Applications. Proceedings of the 20th ACM International Conference on Multimedia, New York, NY, USA: ACM,2012.539-548.
[93]Cao L, Ji R, Gao Y, et al. Weakly supervised sparse coding with geometric consistency pooling. Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012.3578-3585.
[94]Doersch C, Singh S, Gupta A, et al. What Makes Paris Look Like Paris? ACM Trans. Graph., 2012,31(4):101:1-101:9.
[95]Singh S, Gupta A, Efros A A. Unsupervised Discovery of Mid-level Discriminative Patches. Proceedings of the 12th European Conference on Computer Vision-Volume Part II, Berlin, Heidelberg:Springer-Verlag,2012.73-86.
[96]Juneja M, Vedaldi A, Jawahar C V, et al. Blocks That Shout:Distinctive Parts for Scene Classification. Proceedings of CVPR,2013.923-930.
[97]Jain A, Gupta A, Rodriguez M, et al. Representing Videos Using Mid-level Discriminative Patches. Proceedings of CVPR,2013.2571-2578.
[98]Malisiewicz T, Gupta A, Efros A A. Ensemble of exemplar-SVMs for Object Detection and Beyond. Proceedings of the 2011 International Conference on Computer Vision, Washington, DC, USA:IEEE Computer Society,2011.89-96.
[99]Viola P, Jones M J. Robust Real-Time Face Detection. Int. J. Comput. Vision,2004,57(2):137-154.
[100]Li L, Fei-Fei L. What, where and who? classifying event by scene and object recognition. Proceedings of In IEEE International Conference on Computer Vision,2007.1-8.
[101]Oliva A, Torralba A. Modeling the Shape of the Scene:A Holistic Representation of the Spatial Envelope. Int. J. Comput. Vision,2001,42(3):145-175.
[102]Fei-Fei L, Fergus R, Perona P. Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. Proceedings of Workshop on Generative-Model Based Vision,2004.
[103]Griffin G, Holub A, Perona P. Caltech-256 Object Category Dataset. Technical Report 7694, California Institute of Technology,2007. http://authors.library.caltech.edu/7694.
[104]Najman L, Schmitt M. Geodesic Saliency of Watershed Contours and Hierarchical Segmenta-tion. IEEE Trans. Pattern Anal. Mach. Intell.,1996,18(12):1163-1173.
[105]Nitzberg M, Mumford D, Shiota T. Filtering, Segmentation, and Depth. Secaucus, NJ, USA: Springer-Verlag New York, Inc.,1993.
[106]Elder J H, Goldberg R M. Ecological statistics of Gestalt laws for the perceptual organization of contours. J Vis,2002,2(4):324-353.
[107]Papari G, Petkov N. Adaptive Pseudo Dilation for Gestalt Edge Grouping and Contour Detec-tion. IEEE Transactions on Image Processing,2008,17(10):1950-1962.
[108]Jermyn I H, Ishikawa H. Globally Optimal Regions and Boundaries As Minimum Ratio Weight Cycles. IEEE Trans. Pattern Anal. Mach. Intell.,2001,23(10):1075-1088.
[109]Liu T, Yuan Z, Sun J, et al. Learning to Detect a Salient Object. IEEE Trans. Pattern Anal. Mach. Intell.,2011,33(2):353-367.
[110]Deng Y,, SManjunath B. Unsupervised segmentation of color-texture regions in images and video. IEEE Trans. Pattern Anal. Mach. Intell.,2001,23(8):800-810.
[111]Feldman J, Singh M. Information along contours and object boundaries. Psychol Rev,2005, 112(1):243-252.
[112]Sirovich L, Kirby M. Low-dimensional procedure for the characterization of human faces. JOS A A,1987,4(3):519-524.
[113]Turk M, Pentland A. Eigenfaces for Recognition. J. Cognitive Neuroscience,1991,3(1):71-86.
[114]Dalal N, Triggs B. Histograms of Oriented Gradients for Human Detection. Proceedings of CVPR,2005.886-893.
[115]Ojala T, Pietikainen M, Harwood D. A comparative study of texture measures with classifica-tion based on featured distributions. Pattern Recognition,1996,29(1):51-59.
[116]Harris C, Stephens M. A Combined Corner and Edge Detector. Proceedings of the Alvey Vision Conference. Alvety Vision Club,1988.147-152.
[117]Mikolajczyk K, Schmid C. Scale & Amp; A ffine Invariant Interest Point Detectors. Int. J. Comput. Vision,2004,60(l):63-86.
[118]Tuytelaars T, Mikolajczyk K. Local Invariant Feature Detectors:A Survey. Hanover, MA, USA:Now Publishers Inc.,2008.
[119]Mikolajczyk K, Schmid C. A Performance Evaluation of Local Descriptors. IEEE Trans. Pattern Anal. Mach. Intell.,2005,27(10):1615-1630.
[120]Carson C, Belongie S, Greenspan H, et al. Blobworld:Image Segmentation Using Expectation-Maximization and Its Application to Image Querying. IEEE Trans. Pattern Anal. Mach. Intell., 2002,24(8):1026-1038.
[121]Wang J Z, Li J, Wiederhold G. SIMPLIcity:Semantics-Sensitive Integrated Matching for Picture LIbraries. IEEE Trans. Pattern Anal. Mach. Intell.,2001,23(9):947-963.
[122]Ren X, Malik J. Learning a classification model for segmentation. Proceedings of Ninth IEEE International Conference on Computer Vision, volume 1,2003.10-17.
[123]Vedaldi A, Soatto S. Quick Shift and Kernel Methods for Mode Seeking. Proceedings of ECCV (4),2008.705-718.
[124]Levinshtein A, Stere A, Kutulakos K N, et al. TurboPixels:Fast Superpixels Using Geometric Flows. IEEE Trans. Pattern Anal. Mach. Intell.,2009,31(12):2290-2297.
[125]Liu M Y, Tuzel O, Ramalingam S, et al. Entropy rate superpixel segmentation.2011 IEEE Conference on Computer Vision and Pattern Recognition,2011,0:2097-2104.
[126]Achanta R, Shaji A, Smith K, et al. SLIC Superpixels Compared to State-of-the-Art Superpixel Methods. IEEE Trans. Pattern Anal. Mach. Intell.,2012,34(11):2274-2282.
[127]Kaufhold J, Hoogs A. Learning to segment images using region-based perceptual features. Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, volume 2,2004.954-961.
[128]Kennedy R, Gallier J, Shi J. Contour cut:Identifying salient contours in images by solving a Hermitian eigenvalue problem. Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition, Washington, DC, USA:IEEE Computer Society,2011.2065-2072.
[129]Kovacs I, Julesz B. A Closed Curve Is Much More Than an Incomplete One:Effect of Closure in Figure-Ground Segmentation. Proceedings of the National Academy of Sciences, USA, 1993,90:7495-7497.
[130]Elder J H, Zucker S W. Computing Contour Closure. Proceedings of In Proc.4th European Conference on Computer Vision,1996.399-412.
[131]Hariharan B, Arbelaez P, Bourdev L, et al. Semantic contours from inverse detectors. IEEE International Conference on Computer Vision,2011,0:991-998.
[132]Landy M S, Graham N. Visual Perception of Texture. Proceedings of The Visual Neuro-sciences. MIT Press,2004. 1106-1118.
[133]Zhang H, Xie B, Yu J. An Improved Surround Suppression Model Based on Orientation Con-trast for Boundary Detection. Proceedings of 21th International Conference on Pattern Recog-nition,2012.3086-3089.
[134]Fan R E, Chang K W, Hsieh C J, et al. LIBLINEAR:A Library for Large Linear Classification. J. Mach. Learn. Res.,2008,9:1871-1874.
[135]Ng A Y, Jordan M I, Weiss Y. On Spectral Clustering:Analysis and an algorithm. Proceedings of Advances in neural information processing systems. MIT Press,2001.849-856.
[136]Torralba A, Efros A. Unbiased look at dataset bias. Proceedings of 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2011.1521-1528.
[137]Pascal VOC 2010. http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2010/,2010.
[138]Deng J, Dong W, Socher R, et al. ImageNet:A large-scale hierarchical image database. Pro-ceedings of IEEE Conference on Computer Vision and Pattern Recognition,2009.248-255.
[139]Savitzky A, Golay M J E. Smoothing and Differentiation of Data by Simplified Least Squares Procedures. Analytical Chemistry,1964,36(8):1627-1639.
[140]Pratt W K. Digital Image Processing:PIKS Inside.3rd ed., New York, NY, USA:John Wiley & Sons, Inc.,2001.
[141]Esakkirajan S, Veerakumar T, Subramanyam A N, et al. Removal of High Density Salt and Pepper Noise Through Modified Decision Based Unsymmetric Trimmed Median Filter. IEEE Signal Process. Lett.,2011,18(5):287-290.
[142]Olshausen B, Field D. Emergence of Simple-Cell Receptive Field Properties by Learning a Sparse Code for Natural Images. Nature,1996,381.607-609.
[143]Olshausen B A, Fieldt D J. Sparse coding with an overcomplete basis set:a strategy employed by V1. Vision Research,1997,37:3311-3325.
[144]Gao S, Tsang I W H, Chia L T, et al. Local features are not lonely-Laplacian sparse coding for image classification. Proceedings of CVPR,2010.3555-3561.
[145]Shabou A, Borgne H L. Locality-constrained and spatially regularized coding for scene cate-gorization. Proceedings of CVPR,2012.3618-3625.
[146]Boureau Y L, Le Roux N, Bach F, et al. Ask the locals:Multi-way local pooling for image recognition. Proceedings of the 2011 International Conference on Computer Vision, Washing-ton, DC, USA:IEEE Computer Society,2011.2651-2658.
[147]Hyvarinen A, Hoyer P O. A two-layer sparse coding model learns simple and complex cell receptive fields and topography from natural images. Vision Research,2001,41(18):2413-2423.
[148]Schapire R E, Singer Y. Improved Boosting Algorithms Using Confidence-rated Predictions. Mach. Learn.,1999,37(3):297-336.
[149]Freund Y, Schapire R E. A decision-theoretic generalization of on-line learning and an applica-tion to boosting. Proceedings of the Second European Conference on Computational Learning Theory, London, UK, UK:Springer-Verlag,1995.23-37.
[150]Benbouzid D, Busa-Fekete R, Casagrande N, et al. MULTIBOOST:A Multi-purpose Boosting Package. J. Mach. Learn. Res.,2012,13:549-553.
[151]Busa-Fekete R, Kegl B. Fast boosting using adversarial bandits. Proceedings of ICML,2010. 143-150.
[152]Wang Z, Feng J, Yan S, et al. Image Classification via Object-Aware Holistic Superpixel Selection. IEEE Transactions on Image Processing,2013,22(11):4341-4352.
[153]Huang R, Sang N, Luo D, et al. Image Segmentation via Coherent Clustering in L*a*B* Color Space. Pattern Recogn. Lett.,2011,32(7):891-902.
[154]Xiang D, Tang T, Zhao L, et al. Superpixel Generating Algorithm Based on Pixel Intensity and Location Similarity for SAR Image Classification. Geoscience and Remote Sensing Letters, IEEE,2013,10(6):1414-1418.
[155]Fu K, Gong C, Yang J, et al. Superpixel based color contrast and color distribution driven salient object detection. Signal Processing:Image Communication,2013,28(10):1448-1463.
[156]Lu H, Feng X, Li X, et al. Superpixel level object recognition under local learning framework. Neurocomputing,2013,120:203-213.
[157]Yuan Y, Fang J, Wang Q. Robust Superpixel Tracking via Depth Fusion. IEEE Transactions on Circuits and Systems for Video Technology,2014,24(1):15-26.
[158]Vincent L, Soille P. Watersheds in Digital Spaces:An Efficient Algorithm Based on Immersion Simulations. IEEE Trans. Pattern Anal. Mach. Intell.,1991,13(6):583-598.
[159]Comaniciu D, Meer P. Mean Shift:A Robust Approach Toward Feature Space Analysis. IEEE Trans. Pattern Anal. Mach. Intell.,2002,24(5):603-619.
[160]Shi J, Malik J. Normalized Cuts and Image Segmentation. IEEE Trans. Pattern Anal. Mach. Intell.,2000,22(8):888-905.
[161]Felzenszwalb P F, Huttenlocher D P. Efficient Graph-Based Image Segmentation. Int. J. Com-put. Vision,2004,59(2):167-181.
[162]Endres I, Hoiem D. Category Independent Object Proposals. Proceedings of the 11th European Conference on Computer Vision:Part V, Berlin, Heidelberg:Springer-Verlag,2010.575-588.
[163]Endres I, Hoiem D. Category-Independent Object Proposals with Diverse Ranking. IEEE Trans. Pattern Anal. Mach. Intell.,2014,36(2):222-234.
[164]Cheng M M, Zhang Z, Lin W Y, et al. BING:Binarized Normed Gradients for Objectness Estimation at 300fps. Proceedings of IEEE CVPR,2014.
[165]Tuzel O, Porikli F, Meer P. Region Covariance:A Fast Descriptor for Detection and Classi-fication. Proceedings of the 9th European Conference on Computer Vision-Volume Part II, Berlin, Heidelberg:Springer-Verlag,2006.589-600.
[166]Forstner W, Moonen B. A Metric for Covariance Matrices. In:Krumm F, Schwarze V S, (eds.). Proceedings of Festschrift for Erik W. Grafarend on the occasion of his 60th birthday,1999. 113-128.
[167]Cherian A, Sra S, Banerjee A, et al. Efficient similarity search for covariance matrices via the Jensen-Bregman LogDet Divergence. Proceedings of 2011 IEEE International Conference on Computer Vision (ICCV),2011.2399-2406.
[168]Cherian A, Sra S, Banerjee A, et al. Jensen-Bregman LogDet Divergence with Application to Efficient Similarity Search for Covariance Matrices. IEEE Trans. Pattern Anal. Mach. Intell., 2013,35(9):2161-2174.
[169]Hassner T,Mayzels V,Zelnik-Manor L. On SIFTs and their scales. Proceedings of 2012 IEEE Conference on Computer "Vision and Pattern Recognition (CVPR),2012.1522-1528.
[170]Basri R, Hassner T, Zelnik-Manor L. Approximate Nearest Subspace Search with Applications to Pattern Recognition. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Los Alamitos, CA, USA:IEEE Computer Society,2007.1-8.
[171]Basri R, Hassner T, Zelnik-Manor L. Approximate Nearest Subspace Search. IEEE Trans. Pattern Anal. Mach. Intell.,2011,33(2):266-278.
[172]Vedaldi A, Fulkerson B. Vlfeat:An Open and Portable Library of Computer Vision Algorithm-s. Proceedings of the International Conference on Multimedia, New York, NY, USA:ACM, 2010.1469-1472.
[173]Elder J, Zucker S. A measure of closure. Vision Research,1994,34(24):3361-3369.