摘要
图像分类是计算机视觉领域的一个基本问题,近年来已吸引了大量的关注。目前的研究往往以结合空间金字塔匹配(Spatial Pyramid Matching,SPM)的词袋(Bag-of-Words, BoW)模型为基础展开。此方案为场景图像分类提供了一个有效的捕捉图像统计信息的方式。词袋模型最初应用于自然语言处理和信息检索,是一个简化的假设。在这个模型中,不考虑语法甚至语序,把文本(如一个句子或者一个文档)表示为一个无序的词的集合。计算机视觉的研究者们从此受到启发,把该理论扩展应用到图像表示中。假定图像是一个文本,从图像提取的局部关键点特征对应于文本中的“词”。BoW表示是进一步图像处理的基础,如目标识别。此方法首先学习一个视觉词汇表(vocabulary),然后量化每一个图像的关键点特征使其成为视觉词汇表中的的某个视觉词(visual word),最后用视觉词的频率直方图表示图像。视觉词汇表也称为码书或者码本(codebook),视觉词汇相对应的称为码字(codeword)。在此过程中,往往用聚类算法(k-means)生成码书。大量的研究和学习表明,BoW模型在目标识别领域取得了令人鼓舞的成果。因此,本文以BoW模型为研究背景,主要探讨和研究图像不变特征的表示方法和场景图像分类算法。
目前,码书通常是用训练集图像通过聚类方法得到。此外还有基于有监督的码书学习、核码书学习、稀疏编码等码书生成方法。利用这些方法生成的码书存在冗余的缺点。本文中,应用新近提出的激活力(Word Activation Forces, WAFs)来减少BoW模型中码书的冗余性。实验结果表明,基于WAFs的码书优化算法是有效的。通过码书的优化,图像特征表示得到改善。
此外,本文提出使用软阈值-倒排文档频率(soft-Inverse DocumentFrequency,soft-IDF)优化BoW特征。给定码书和数据集,每个视觉词(码字)在特定的图像中出现的次数不同,而且出现在不同数量的图像中。一些视觉词出现频率很高,相反一些视觉词罕见的出现在几幅图像中。基于Soft-IDF的BoW特征优化方法平衡了这种不均衡性。实验表明,所提出的方法在场景图像分类中取得了令人鼓舞的效果。
本文还提出基于参考比较(reference-based)的场景图像分类方法。该方法用一个参考集(reference-set)对图像进行表示,并利用该reference-set进行码书学习。联合reference-set的码书学习过程为：首先加权联合该reference-set到目标函数中,形成一个归一化的目标函数,然后用K-SVD算法优化求解,学习码书。码书生成以后,提取图像的局部限制的线性编码特征(Locality-constrained Linear Coding, LLC)表示图像。接下来,计算图像和reference-set的相似度矢量,以此矢量作为图像的最终特征。通过此过程,图像的特征空间维数显著降低。更重要的是,实验结果表明,reference-based算法实现了卓越的分类性能。
Reference-based场景图像分类算法成功引入一个reference-set到码书学习和图像特征表示过程,其reference-set是每类图像中随机选取若干图像组建而成,相似度度量方法也是应用简单的距离测量。本文中,作者对该算法主要从两方面进行了改进。首先,给定更有代表性的reference-set。为此,本文改进了k-means聚类方法,在特征空间选择了一个更有代表性的reference-set。另一方面,在图像分类过程中,把reference-set的每一类看作一个社会网络,用社会网络中的中介度中心性(betweenness centrality)度量图像和reference-set的相似性。因为考虑了查询图和reference-set的整体关联性,因此该度量方法更加准确。而且不同于以往只考虑图像与图像的相似度测量,betweenness centrality引入了图像到图像类的相似度测量。通过大量的实验证实,改进算法获得了更好的性能,改进算法也成功的将社会网络的理论应用到场景图像分类领域。
Image classification is a fundamental problem in computer vision and has attracted a lot of attention in recent years. Current research converges on leveraging bag-of-words (BoW) representation combined with spatial pyra-mid matching (SPM). Such scheme provides an effective way of capturing im-age statistics for natural scene classification and reports state-of-the-art perfor-mance. The bag-of-words (BoW) model is a simplifying assumption used in natural language processing and information retrieval. In this model, a text (such as a sentence or a document) is represented as an unordered collection of words, disregarding grammar and even word order. Computer vision re-searchers use a similar idea for image representation (Here an image may refer to a particular object, such as an image of a car). For example, an image can be treated as a document, and features extracted from the image are considered as the "words". The BoW representation serves as the basic element for further processing, such as object categorization. The key idea is to quantize each ex-tracted key point into one of visual words, and then represent each image by a histogram of the visual words (Visual codebook). For this purpose, a clustering algorithm (e.g., K-means), is generally used for generating the visual words. A number of studies have shown encouraging results of the bag-of-words rep-resentation for object categorization. Based on the BoW model, the research on representation of image invariant feature and scene image categorization method is presented in this thesis.
Currently, codebooks are typically created from a set of training images using a clustering algorithm. However, these codebooks are often functionally limited due to redundancy, we use the newly proposed statistics of word activa-tion forces (WAFs) to reduce the redundancy in the codebook used in the BoW model. The experimental results show that WAFs can remove the redundancy efficiently. In such a way, the representation of image features is improved.
In addition, we propose a method using inverse document frequency (IDF) to optimize BoW based image features, which is called Soft-IDF. Given visual words and the dataset, each visual word appears in different amount of images and also different times in each particular image. Some of the visual words appear rare in contrary to the frequent ones. The proposed method balances this case. Experiments show encouraging results in scene categorization by the proposed approach.
A reference-based algorithm for scene image categorization is presented in this paper. In addition to using a reference-set for images representation, we also associate the reference-set with training data in sparse codes during the dictionary learning process. The reference-set is combined with the recon-struction error to form a unified objective function. The optimal solution is efficiently obtained using the K-SVD algorithm. After dictionaries are con-structed, Locality-constrained Linear Coding (LLC) features of images are ex-tracted. Then, we represent each image feature vector using the similarities between the image and the reference-set, leading to a significant reduction of the dimensionality in the feature space. Experimental results demonstrate that the reference-based algorithm achieves outstanding performance.
Reference-based image classification approach introduces a reference-set for both image representation and dictionary learning. It significantly reduces the dimensionality of represented images and shows outstanding performance even with randomly selected reference images and simple distance measure. In this paper, we improve upon existing work with two major contributions. First, we show that a more representative reference-set contributes to better classification accuracy. To this end, we carefully adapt the K-means cluster-ing algorithm in the feature space to select a distinguished reference-set. Sec-ond, in the image classification process, we propose to represent each image by measuring its betweenness centrality in a social network composed of the representative reference-set in each class, leading to a more coherent distance measure that considers the overall connectivity between the probe image and the reference-set. Extensive experiment results demonstrate that our proposed scheme achieves better performance than existing methods.
引文
[1]Datta R, Li J, Wang J Z. Content-based image retrieval:approaches and trends of the new age [C]. In Proc. of the 7th ACM SIGMM international workshop on multimedia information retrieval,2005: 253-262.
[2]Smeulders A W M, Worring M, Santini S, et al. Content-based image retrieval at the end of the early years [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(12):1349-1380.
[3]Datta R, Joshi D, Li J, et al. Image retrieval:Ideas, influences, and trends of the new age [J]. ACM Comput. Surv. (CSUR),2008,40 (2):5:1-5:60.
[4]Choras R S. Image feature extraction techniques and their applications for CBIR and biometrics systems [J]. International Journal of Biology and Biomedical Engineering,2007,1 (1):6-16.
[5]Sivic J, Zisserman A. Video google:A text retrieval approach to object matching in videos [C]. In Proc. of International Conference on Computer Vision (ICCV),2003:1470-1477.
[6]Csurka G, Dance C R, Fan L, et al. Visual categorization with bags of keypoints [C]. In Workshop on Statistical Learning in Computer Vision, European Conference on Computer Vision (ECCVW), 2004:1-22.
[7]Guillaumin M, Verbeek J, Schmid C. Multimodal semi-supervised learning for image classification [C]. In Proc. of 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2010: 902-909.
[8]Nixon M, Aguado A S. Feature extraction & image processing [M]. Academic Press,2008.
[9]Yang X-M, Wu W, Qing L-B, et al. Image feature extraction and matching technology [J]. Optics and Precision Engineering,2009,9:33-33.
[10]Ojala T, Pietikainen M, Maenpaa T. Multiresolution gray-scale and rotation invariant texture classifi-cation with local binary patterns [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI),2002,24 (7):971-987.
[11]Tuytelaars T, Mikolajczyk K. Local invariant feature detectors:a survey [J]. Foundations and Trends? in Computer Graphics and Vision,2008,3 (3):177-280.
[12]Van De Weijer J, Schmid C. Coloring local feature extraction [C]. In Proc. of European Conference on Computer Vision (ECCV),2006:334-348.
[13]Haralick R M, Shanmugam K, Dinstein I H. Textural features for image classification [J]. IEEE Transactions on Systems, Man and Cybernetics,1973:610-621.
[14]Vailaya A, Member A, Figueiredo M A T, et al. Image classification for content-based indexing [J]. IEEE Transactions on Image Processing,2001,10:117-130.
[15]Stockman G, Shapiro L G. Computer Vision [M].1st ed. Upper Saddle River, NJ, USA:Prentice Hall PTR,2001.
[16]Shapiro L. Computer vision and image processing [M]. Academic Press,1992.
[17]Jahne B, HauBeβcker H. Computer vision and applications:a guide for students and practitioners [M]. Academic Press,2000.
[18]Sonka M, Hlavac V, Boyle R. Image Processing, Analysis, and Machine Vision [M]. Thomson-Engineering,2007.
[19]Ponce J, Forsyth D, Willow E-p, et al. Computer vision:a modern approach [J]. Computer,2011, 16:11.
[20]Ballard D H, Brown C M. Computer Vision [M]. New Jersey, USA:Prentice Hall,1982.
[21]Gonzalez R C, Woods R E, Eddins S L. Digital image processing using MATLAB [M]. Upper Saddle River, NJ, USA:Prentice-Hall, Inc.,2003.
[22]常昌.图像特征提取方法研究及应用[D].武汉：华中科技大学,2009.
[23]Lin C-H, Chen R-T, Chan Y-K. A smart content-based image retrieval system based on color and texture feature [J]. Image Vision Comput.,2009,27 (6):658-665.
[24]Rui Y, Huang T S. Image retrieval:Current techniques, promising directions and open issues [J]. Journal of Visual Communication and Image Representation,1999,10:39-62.
[25]Marr D, Hildreth E. Theory of edge detection [J]. Proceedings of the Royal Society of London Series B,1980,207:187-217.
[26]Mikolajczyk K, Tuytelaars T, Schmid C, et al. A comparison of affine region detectors [J]. Int. J. Comput. Vision,2005,65 (1-2):43-72.
[27]Schmid C, Mohr R, Bauckhage C. Evaluation of interest point detectors [J]. Int. J. Comput. Vision, 2000,37(2):151-172.
[28]Forstner W. A framework for low level feature extraction [C]. In Proc. of European Conference on Computer Vision (ECCV),1994:383-394.
[29]黄志开.彩色图像特征提取与植物分类研究[D].合肥：中国科学技术大学研究院,2006.
[30]曾璞.面向语义提取的图像分类关键技术研究[D].长沙：国防科学技术大学,2009.
[31]Mehrotra R, Gary J E. Similar-shape retrieval in shape data management [J]. Computer,1995,28 (9):57-62.
[32]Jing F, Li M, Zhang L, et al. Learning in region-based image retrieval [M]//Jing F, Li M, Zhang L, et al. Image and Video Retrieval. Springer,2003:2003:206-215.
[33]Liu Y, Zhang D, Lu G, et al. A survey of content-based image retrieval with high-level semantics [J]. Pattern Recognition,2007,40 (1):262-282.
[34]Sethi I K, Coman I L, Stan D. Mining association rules between low-level image features and high-level concepts [J]. Proc. of the SPIE Data Mining and Knowledge Discovery,2001,3:279-290.
[35]Mojsilovic A, Rogowitz B. Capturing image semantics with low-level descriptors [C]. In Proc. of 2001 International Conference on Image Processing (ICIP),2001:18-21.
[36]Oliva A, Torralba A. Modeling the shape of the scene:A holistic representation of the spatial enve-lope [J]. International Journal of Computer Vision,2001,42:145-175.
[37]王君秋,查红彬.结合兴趣点和边缘的建筑物和物体识别方法[J].计算机辅助设计与图形学学报,2005,18(08)：1257-1263.
[38]聂青,战守义.基于区域特征的图像分类技术[J].北京理工大学学报,2008,28(10)：885—889.
[39]Jiang Y G, Ngo C W, Yang J. Towards optimal bag-of-features for object categorization and semantic video retrieval [C]. In Proceedings of the 6th ACM International Conference on Image and Video Retrieval,2007:494-501.
[40]Ulusoy I, Bishop C M. Generative versus discriminative methods for object recognition [C]. In Proc. of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR),2005: 258-265.
[41]Raina R, Shen Y, Ng A Y. et al. Classification with hybrid generative/discriminative models [J]. Advances in Neural Information Processing Systems,2003,16.
[42]Quelhas P, Monay F, Odobez J-M, et al. A thousand words in a scene [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI),2007,29 (9):1575-1589.
[43]Fei-Fei L, Perona P. A Bayesian hierarchical model for learning natural scene categories [C]. In Proc. of the International Conference on Computer Vision and Pattern Recognition (CVPR),2005: 524-531.
[44]Horster E, Lienhart R, Slaney M. Continuous visual vocabulary modelsfor pLSA-based scene recog-nition [C]. In Proc. of the 2008 international conference on Content-based image and video retrieval, New York, USA,2008:319-328.
[45]Fergus R, Fei-Fei L, Perona P, et al. Learning object categories from Google's image search [C]. In Proc. of International Conference on Computer Vision (ICCV),2005:1816-1823.
[46]Li Y, Wang W, Gao W. A robust approach for object recognition [C]. In Proc. of 7th Pacific Rim Conference on Multimedia(PCM),2006:262-269.
[47]Liu D, Chen T. Unsupervised image categorization and object localization using topic models and correspondences between images [J]. Proc. of International Conference on Computer Vision (ICCV), 2007:1-7.
[48]Sivic J, Russell B C, Efros A A, et al. Discovering object categories in image collections [C], In Proc. of the International Conference on Computer Vision (CVPR),2005.
[49]Wang G, Zhang Y, Fei-fei L. Using dependent regions for object categorization in a generative framework [C]. In Pro. of International Conference on Computer Vision and Pattern Recognition (CVPR),2006:1597-1604.
[50]Teh Y W, Jordan M I, Beal M J, et al. Hierarchical dirichlet processes [J]. Journal of the American Statistical Association,2006,101 (476):1566-1581.
[51]Wu L, Li M, Li Z, et al. Visual language modeling for image classification [C]. In Proc. of the international Conference on Multimedia Information Retrieval Workshop(MIR), New York, USA, 2007:115-124.
[52]Tirilly P, Claveau V, Gros P. Language modeling for bag-of-visual words image categorization [C]. In Proc. of ACM International Conference on Image and Video Retrieval(CIVR),2008:249-258.
[53]Crandall D J, Felzenszwalb P F, Huttenlocher D P. Spatial priors for part-based recognition using statistical models [C]. In Proc. of International Conference on Computer Vision and Pattern Recog-nition (CVPR),2005:10-17.
[54]Bouchard G. Hierarchical part-based visual object categorization [C]. In Proc. of International Con-ference on Computer Vision and Pattern Recognition (CVPR),2005:710-715.
[55]Fergus R, Perona P, Zisserman A. Weakly supervised scale-invariant learning of models for visual recognition [J]. International Journal of Computer Vision,2007,71 (3):273-303.
[56]Carneiro G, Lowe D. Sparse flexible models of local features [C]. In Proc. of European Conference on Computer Vision (ECCV),2006:29-43.
[57]Fergus R, Perona P, Zisserman A. A sparse object category model for efficient learning and exhaus-tive recognition [C]. In Proc. of International Conference on Computer Vision and Pattern Recogni-tion (CVPR),2005:380-387.
[58]Felzenszwalb P F, Huttenlocher D P. Pictorial structures for object recognition [J]. International Journal of Computer Vision (IJCV),2005,61 (1):55-79.
[59]Cortes C, Vapnik V. Support-vector networks [J]. Machine learning,1995,20 (3):273-297.
[60]Vapnik V N. The Nature of Statistical Learning Theory [M]. Springer,1995.
[61]Boser B E, et al. A training algorithm for optimal margin classifiers [C]. In Proc. of the 5th Annual ACM Workshop on Computational Learning Theory,1992:144-152.
[62]Goh K S, Chang E Y, Li B. Using one-class and two-class svms for multiclass image annotation [J]. IEEE Transactions on Knowledge and Data Engineering,2005,17 (10):1333-1346.
[63]Wolf L, Shashua A. Learning over sets using kernel principal angles [J]. The Journal of Machine Learning Research,2003,4:913-931.
[64]Boughorbel S, Tarel J-P, Fleuret F. Non-Mercer kernels for SVM object recognition [C]. In Proc. of British Machine Vision Conference (BMVC),2004:137-146.
[65]Kondor R, Jebara T. A kernel between sets of vectors [C]. In Proc. of International Conference on Machine Learning (ICML),2003.
[66]Lyu S. Mercer kernels for object recognition with local features [C]. In Proc. of International Con-ference on Computer Vision and Pattern Recognition (CVPR),2005:223-229.
[67]Grauman K, Darrell T. The pyramid match kernel:Discriminative classification with sets of image features [C], In Proc. of International Conference on Computer Vision (ICCV),2005:1458-1465.
[68]Grauman K, Darrell T. Approximate correspondences in high dimensions [C]. In Proc. of Annual Conference on Neural Information Processing Systems (NIPS),2006.
[69]Lazebnik S, Schmid C, Ponce J. Beyond bags of features:Spatial pyramid matching for recognizing natural scene categories [C]. In Proc. of International Conference on Computer Vision and Pattern Recognition (CVPR),2006:2169-2178.
[70]Ling H, Soatto S. Proximity Distribution Kernels for Geometric Context in Category Recognition [C]. In Proc. of International Conference on Computer Vision (ICCV),2007:1-8.
[71]Liu X, Wang D, Li J, et al. The feature and spatial covariant kernel:adding implicit spatial con-straints to histogram [C]. In Proc. of ACM International Conference on Image and Video Retrieval (CIVR),2007:565-572.
[72]Vedaldi A, Soatto S. Relaxed matching kernels for robust image comparison. [C]. In Proc. of Inter-national Conference on Computer Vision and Pattern Recognition (CVPR),2008.
[73]陈海林,吴秀清,胡俊华.基于局部特征空间相关核的图像目标分类[J].光电工程,2009,36(3)：33-38.
[74]Opelt A, Pinz A, Fussenegger M, et al. Generic object recognition with boosting [J]. IEEE Transac-tions on Pattern Analysis and Machine Intelligence (TPAMI),2006,28 (3):416-431.
[75]Frome A, Singer Y, Malik J. Image retrieval and classification using local distance functions [C]. In Proc. of Annual Conference on Neural Information Processing Systems (NIPS),2007:417-424.
[76]Boiman O, Shechtman E, Irani M. In defense of Nearest-Neighbor based image classification [C]. In Proc. of International Conference on Computer Vision and Pattern Recognition (CVPR),2008: 1-8.
[77]Maron O, Ratan A L. Multiple-instance learning for natural scene classification [C]. In The Fifteenth International Conference on Machine Learning,1998:341-349.
[78]Zhang Q, Goldman S A. EM-DD:An improved multiple-instance learning technique [C]. In Ad-vances in Neural Information Processing Systems,2001:1073-1080.
[79]Chen Y, Wang J Z, Geman D. Image categorization by learning and reasoning with regions [J]. Journal of Machine Learning Research,2004,5:913-939.
[80]Chen Y, Bi J, Wang J Z. MILES:Multiple-instance learning via embedded instance selection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI),2006,28 (12):1931-1947.
[81]Holub A D, Perona P. A discriminative framework for modeling object class [C]. In Proc. of Inter-national Conference on Computer Vision and Pattern Recognition (CVPR),2005:664-671.
[82]Perronnin F, Dance C R. Fisher kernels on visual vocabularies for image categorization [C]. In Proc. of International Conference on Computer Vision and Pattern Recognition (CVPR),2007:1-8.
[83]Bosch A, Zisserman A, Munoz X. Scene classification using a hybrid generative/discriminative approach [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI),2008,30 (4):712-727.
[84]Bouguila N. Hybrid generative/discriminative approaches for proportional data modeling and clas-sification [J]. IEEE Transactions on Knowledge and Data Engineering,2012,24 (12):2184-2202.
[85]Lowe D G. Object recognition from local scale-invariant features [C]. In Proc. of the Seventh IEEE International Conference on Computer Vision (ICCV),1999:1150-1157.
[86]Lowe D G. Distinctive image features from scale-invariant keypoints [J]. International Journal of Computer Vision,2004,60:91-110.
[87]Mikolajczyk K, Schmid C. A performance evaluation of local descriptors [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI),2005,27 (10):1615-1630.
[88]Koenderink J. The structure of images [J]. Biological Cybernetics,1984,50:363-396.
[89]Lindeberg T. Detecting salient blob-like image structures and their scales with a scale-space primal sketch:A method for focus-of-attention [J]. International Journal of Computer Vision,1993,11: 283-318.
[90]Brown M, Lowe D. Invariant features from interest point groups [C]. In Proc. of British Machine Vision Conference,2002:656-665.
[91]Joachims T. Text categorization with support vector machines:learning with many relevant features [C]. In Proc. of 10th European Conference on Machine Learning (ECML), Heidelberg et al.,1998: 137-142.
[92]McCallumzy A, Nigamy K. Text classification by bootstrapping with keywords, em and shrinkage [C]. In Proc. of ACL99-Workshop for Unsupervised Learning in Natural Language Processing, 1999:52-58.
[93]Nowak E, Jurie F, Triggs B. Sampling strategies for bag-of-features image classification [C]. In Proc. of the European Conference on Computer Vision (ECCV),2006:490-503.
[94]Winn J, Criminisi A, Minka T. Object categorization by learned universal visual dictionary [C]. In Proc. of International Conference on Computer Vision (ICCV),2005:1800-1807.
[95]Sivic J, Zisserman A. Video Google:A text retrieval approach to object matching in videos [C]. In Proc. of International Conference on Computer Vision (ICCV),2003:1470-1477.
[96]Nowak E, Jurie F, Triggs B. Sampling strategies for bag-of-features image classification [C]. In Proc. of European Conference on Computer Vision (ECCV),2006:490-503.
[97]Jurie F, Triggs B. Creating efficient codebooks for visual recognition [C]. In Proc. of the Interna-tional Conference on Computer Vision (ICCV),2005:604-610.
[98]Raginsky M, Lazebnik S. Locality-sensitive binary codes from shift-invariant kernels. [C]. In Proc. of Annual Conference on Neural Information Processing Systems (NIPS),2009:1509-1517.
[99]Moosmann F, Triggs B, Jurie F. Fast discriminative visual codebooks using randomized clustering forests [C]. In Proc. of Annual Conference on Neural Information Processing Systems (NIPS),2007: 985-992.
[100]Nister D, Stewenius H. Scalable recognition with a vocabulary tree [C]. In Proc. of International Conference on Computer Vision and Pattern Recognition (CVPR),2006:2161-2168.
[101]Philbin J, Isard M, Sivic J, et al. Lost in quantization:Improving particular object retrieval in large scale image databases [C]. In Proc. of the International Conference on Computer Vision and Pattern Recognition (CVPR),2008.
[102]Tuytelaars T. Vector quantizing feature space with a regular lattice [C]. In Proc. of International Conference on Computer Vision (ICCV),2007:1-8.
[103]Tong S, Koller D. Support vector machine active learning with applications to text classification [C]. In Journal of Machine Learning Research,2001:999-1006.
[104]Lodhi H, Saunders C, Shawe-Taylor J,et al. Text classification using string kernels [J]. Journal of Machine Learning Research,2002,2:563-569.
[105]Cristianini N, Shawe-Taylor J, Lodhi H. Latent semantic kernels [J]. Journal of Intelligent Infor-mation Systems,2002,18(2-3):127-152.
[106]Swain M J, Ballard D H. Color indexing [J].International Journal of Computer Vision (IJCV), 1991,7:11-32.
[107]Quelhas P, Monay F, m Odobez J, et al. Modeling scenes with local descriptors and latent aspects [C]. In Proc. of International Conference on Computer Vision (ICCV),2005:883-890.
[108]Fei-Fei L, Fergus R, Perona P. Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categories [J]. Computer Vision and Image Understanding,2007,106(1):59-70.
[109]Blei D M, Ng A Y, Jordan M I, et al. Latent dirichlet allocation [J]. Journal of Machine Learning Research,2003,3:2003.
[110]Berg A C, Berg T L, Malik J. Shape matching and object recognition using low distortion corre-spondence [C]. In Proc. of International Conference on Computer Vision and Pattern Recognition (CVPR),2005:26-33.
[111]Opelt A, Fussenegger M, Pinz A, et al. Weak hypotheses and boosting for generic object detection and recognition [C]. In Proc. of European Conference on Computer Vision (ECCV),2004:71-84.
[112]Oliva A, Torralba A. Modeling the shape of the scene:A holistic representation of the spatial envelope [J]. International Journal of Computer Vision,2001,42 (3):145-175.
[113]Sivic J, Russell B C, Efros A A, et al.Discovering objects and their location in images [C].2005: 370-377.
[114]Willamowski J, Arregui D, Csurka G, et al. Categorizing nine visual classes using local appearance descriptors [C]. In Workshop on Learning for Adaptable Visual Systems, International Conference on Pattern Recognition (ICPRW),2004:21-24.
[115]Oliva A, Torralba A, et al. Building the gist of a scene:The role of global image features in recognition [J]. Progress in brain research,2006,155:23-23.
[116]Yang J, Yu K, Gong Y, et al. Linear spatial pyramid matching using sparse coding for image clas-sification [C]. In Proc. of International Conference on Computer Vision and Pattern Recognition (CVPR),2009:1794-1801.
[117]Yu K, Zhang T, Gong Y. Nonlinear learning using local coordinate coding [C]. In Proc. of Annual Conference on Neural Information Processing Systems (NIPS),2009:2223-2231.
[118]Wang J, Yang J, Yu K, et al. Locality-constrained linear coding for image classification [C]. In Proc. of International Conference on Computer Vision and Pattern Recognition (CVPR),2010:3360-3367.
[119]周明全,耿国华,韦娜.基于内容图像检索技术[M].北京：清华大学出版社,2007.
[120]Griffin G, Holub A, Perona P. Caltech-256 Object Category Dataset,7694 [R/OL].2007. http: //authors.library.caltech.edu/7694.
[121]Everingham M, Van Gool L, Williams C K I, et al. The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Results.2007.www.pascal-network.org/challenges/VOC/ voc2007/workshop/.
[122]Torralba A, Fergus R, freeman W T.80 million tiny images:a large dataset for non-parametric object and scene recognition.2008. http://horatio.cs.nyu.edu/mit/tiny/data/ index.html.
[123]Deng J, Dong W, Socher R, et al. ImageNet:A large-scale hierarchical image database [C]. In Proc. of the International Conference on Computer Vision and Pattern Recognition (CVPR),2009: 248-255.
[124]Gemert J C V, Geusebroek J M, Veenman C J, et al. Kernel codebooks for scene categorization [C]. In Proc. of European Conference on Computer Vision (ECCV),2008:696-709.
[125]Mairal J, Bach F. Supervised dictionary learning [C]. In Proc. of Annual Conference on Neural Information Processing Systems (NIPS),2008:1033-1040.
[126]Guo J, Guo H, Wang Z. An activation force-based affinity measure for analyzing com-plex networks [J/OL]. Scientific reports,2011,1.http://www.biomedsearch.com/nih/ Activation-Force-based-Affinity-Measure/22355630.html.
[127]MacQueen J B. Some methods for classification and analysis of multivariate observations [C]. In Proc. of the fifth Berkeley Symposium on Mathematical Statistics and Probability,1967:281-297.
[128]Steinhaus H. Sur la division des corps materiels en parties [J]. Bull. Acad. Pol. Sci.,Cl.Ⅲ,1957, 4:801-804.
[129]Lloyd S P. Least squares quantization in PCM [J]. IEEE Transactions on Information Theory,1982: 128-137.
[130]Forgy E. Cluster analysis of multivariate data:efficiency versus interpretability of classifications [J]. Biometrics,1965,21:768-780.
[131]Hartigan J, Wong M. Algorithm AS 136:A K-means clustering algorithm [J]. Applied Statistics, 1979:100-108.
[132]MacKay D J C. Information Theory, Inference, and Learning Algorithms [M]. Copyright Cam-bridge University Press,2003.
[133]Hamerly G, Elkan C. Alternatives to the k-means algorithm that find better clusterings [C]. In Proc. of the Eleventh International Conference on Information and knowledge Management (CIKM), New York, NY, USA,2002:600-607.
[134]Palla G, Derenyi I, Farkas I, et al. Uncovering the overlapping community structure of complex networks in nature and society [J]. Nature,2005,435 (7043):814-818.
[135]Ahn Y Y, Bagrow J P, Lehmann S. Link communities reveal multiscale complexity in networks [J]. Nature,2010,466:761-764.
[136]Roweis S T, Saul L K. Nonlinear dimensionality reduction by locally linear embedding [J]. SCI-ENCE,2000,290:2323-2326.
[137]Crutch S J, Warrington E K. The semantic organisation of proper nouns:the case of people and brand names. [J]. Neuropsychologia,2004,42 (5):584-96.
[138]Szathmary E, Szamado S. Being human:language:a social history of words [J]. Nature,2008, 456(7218):40-41.
[139]Turkeltaub P E, Gareau L, Flowers D L, et al. Development of neural mechanisms for reading [J]. Nature Neuroscience,2003,6 (7):767-773.
[140]Nelson D L, McEvoy, L C, et al. The University of South Florida word association, rhyme, and word fragment norms [EB/OL].1998. http://w3.usf.edu/FreeAssociation/.
[141]Fellbaum C. Wordnet an electronic lexical database [M/OL]. Cambridge, MA;London:The MIT Press,1998. http://mitpress.mit.edu/catalog/item/default.asp?ttype= 2&tid=8106.
[142]Kutas M, Hillyard S A. Brain potentials during reading reflect word expectancy and semantic association [J]. Nature,1984,307 (January 12):161-163.
[143]Henson R, Shallice T, Dolan R. Neuroimaging evidence for dissociable forms of repetition priming [J]. Science,2000,287 (5456):1269-1272.
[144]Crinion J, Turner R, Grogan A. Language control in the bilingual brain [J]. Science,2006, 312(5779):1537-1540.
[145]Gennari S P, MacDonald M C, Postle B R, et al. Context-dependent interpretation of words:evi-dence for interactive neural processes. [J]. Neuroimage,2007,35 (3):1278-1286.
[146]Hoeks J C, Stowe L A, Doedens G. Seeing words in context:the interaction of lexical and sentence level information during reading [J]. Cognitive Brain Research,2004,19(1):59-73.
[147]Zhang J, Lazebnik S, Schmid C. Local features and kernels for classification of texture and object categories:a comprehensive study [J]. International Journal of Computer Vision (IJCV),2007,73 (2):213-238.
[148]Zhang H, Berg A C, Maire M, et al. SVM-KNN:Discriminative nearest neighbor classification for visual category recognition [C]. In Proc. of International Conference on Computer Vision and Pattern Recognition (CVPR),2006:2126-2136.
[149]Wu H C, Luk R W P, Wong K F, et al. Interpreting tf-idf term weights as making relevance decisions [J]. ACM Transactions on Information Systems (TOIS),2008,26 (3):1-37.
[150]Zhou X, Cui N, Li Z, et al. Hierarchical Gaussianization for image classification. [C]. In Proc. of International Conference on Computer Vision (ICCV),2009:1971-1977.
[151]Wright J, Yang A Y, Ganesh A, et al. Robust face recognition via sparse representation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI),2009,31 (2):210-227.
[152]Mairal J, Bach F, Ponce J. Online learning for matrix factorization and sparse coding [J]. Jour-nal of Machine Learning Research,2010,11(1):19-60.
[153]Mairal J, Bach F, Ponce J, et al. Discriminative learned dictionaries for local image analysis [C]. In Proc. of International Conference on Computer Vision and Pattern Recognition (CVPR),2008:1-8.
[154]Aharon M, Elad M, Bruckstein A. K-SVD:Design of dictionaries for sparse representation [C]. In Proc. of SPARS,2005:9-12.
[155]Zhang Q, Li B. Discriminative K-SVD for dictionary learning in face recognition [C]. In Proc. of International Conference on Computer Vision and Pattern Recognition (CVPR),2010:2691-2698.
[156]Jiang Z, Lin Z, Davis L S. Learning a discriminative dictionary for sparse coding via label consis-tent K-SVD. [C]. In Proc. of International Conference on Computer Vision and Pattern Recognition (CVPR),2011:1697-1704.
[157]Kumar N, Berg A C, Belhumeur P N, et al. Attribute and simile classifiers for face verification [C]. In Proc. of IEEE 12th International Conference on Computer Vision (ECCV),2009:365-372.
[158]Wu Z, Ke Q, Sun J, et al. Scalable face image retrieval with identity-based quantization and multi-reference re-ranking [C]. In Proc. of 2010 IEEE Conference on Computer Vision and Pattern Recog-nition (CVPR),2010:3469-3476.
[159]Fei-Fei L, Fergus R, Perona P. Learning generative visual models from few training exam-ples:an incremental Bayesian approach tested on 101 object categories [C]. In Workshop on Generative-Model Based Vision, International Conference on Computer Vision and Pattern Recog-nition (CVPRW),2004:178-178.
[160]Gao S, Tsang I W-H, Chia L-T, et al. Local features are not lonely-Laplacian sparse coding for im-age classification. [C]. In Proc. of International Conference on Computer Vision and Pattern Recog-nition (CVPR),2010:3555-3561.
[161]Zhang C, Liu J, Tian Q, et al. Image classification by non-negative sparse coding, low-rank and sparse decomposition. [C]. In Proc. of International Conference on Computer Vision and Pattern Recognition (CVPR),2011:1673-1680.
[162]KencfO618. Data visualization of Facebook relationships by the third-party app MyFnetwork. 2011. http://en.wikipedia.org/wiki/Social_network_analysis.
[163]Pinheiro C. Social Network Analysis in Telecommunications [M]. Wiley,2011.
[164]Hummon N, Doreian P. Computational social network analysis [J]. Computer Communications, 2010,12 (4):2-25.
[165]Freeman L C. The development of social network analysis [M]. Empirical Press,2004.
[166]Anheier H, Gerhards J, FP R. Forms of capital and social structure of fields:examining Bourdieu's social topography [M].1995.
[167]de Nooy W. Fields and networks:correspondence analysis and social network analysis in the framework of field theory [J]. Poetics,2003,31 (5):305-327.
[168]Smith M A, Shneiderman B, Milic-Frayling N, et al. Analyzing (social media) networks with NodeXL [C]. In Proc. of the Fourth International Conference on Communities and Technologies, 2009:255-264.
[169]Liu B. Web Data Mining:Exploring Hyperlinks, Contents, and Usage Data [M]. Springer,2007.
[170]Tsvetovat M, Kouznetsov A. Social Network Analysis for Startups:Finding connections on the social web [M]. O'Reilly Media,2011.
[171]Krebs V. The social life of routers:applying knowledge of human networks to the design of com-puter networks [J]. Internet Protocol Journal,2000,3 (4):14-25.
[172]Opsahl T, Agneessens F, Skvoretz J. Node centrality in weighted networks:Generalizing degree and shortest paths [J]. Social Networks,2010 (3):245-251.
[173]Mantrach A, et al. The sum-over-paths covariance kernel:a novel covariance measure between nodes of a directed graph [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI),2010,32 (6):1112-1126.
[174]Rocchini C. Hue scale representing node betweenness on a graph.2007. http://en. wikipedia.org/wiki/Centrality#Betweenness_centrality.