基于图像内容的成人图像检测
|
摘要
当前,互联网已经成为人们生活中密不可分的重要组成部分。但同时在互联网海量的图像中,出现了大量有害的成人图像。检测并过滤互联网上的成人图像,已经成为各国研究者日益关注的一个紧迫问题。其中,多数的研究者采取了分析图像内容的方法来识别成人图像。近些年来提出的识别算法大多都建立在各种低层图像特征的基础之上,例如颜色、纹理和肤色区域等方面的特征。这类方法会产生大量的误检,特别是当图片中包含了大面积类似肤色的区域,例如人物类图像被误判的情况就很普遍。于是本文展开了对图像内容的深入分析,试图减少对肤色检测结果的依赖,并降低误检率。
本文选择图像的局部特征为突破口。在系统中,将局部特征量化为视觉单词,据此可以高效地分析图像的上下文语义,并结合其它方面的低层特征,对图像的类别给出综合的判断。论文的具体研究内容如下:
首先对各种重要的低层特征展开了的研究,并进行了相应的改进。所考察的特征包括:颜色、肤色分布、局部特征、以及边缘线条特征。对于各种特征,都探讨了不同的方案在成人图像检测中的效果。并针对传统方法的不足,提出了有针对性的改进,主要包括:通过统计肤色块局部模式的出现规律,提出了一种新的描述肤色分布的特征;在局部特征方面,同时使用了局部的形态和纹理信息,并适度简化了局部特征点的采集算法;此外,对于局部特征无监督量化中所产生的随意性,通过调整和限制局部特征量化簇集的半径,提高了量化结果(即“视觉单词”)的质量;对图像中线条的分布情况,以局部短线段为基础,建立了旋转不变的描述。实验证明,上述特征产生了更好的识别能力。
然后以普通的视觉单词为基础,建立了对成人图像视觉单词上下文的多层描述体系。该体系总共分3个层次,除了普通的视觉单词,还包括:中间层的词组,以及更高层的兴趣区域(region of interest,ROI)话题。词组是视觉单词的局部相邻关系的描述模型,本文建立了一种简单而高效的局部词组生成算法。ROI话题则用于在更大的尺度上(ROI)描述成人图像中视觉单词的上下文关系。在实验中发现,高层的视觉单词降低了普通单词的歧义性,并提高了对成人图像的识别性能。此外,还提取了敏感单词分布特征,从而补充了对视觉单词的全局分布信息的描述。最后,将子空间学习的思想融入到算法中,通过向量映射,不但使图像特征向量得以显著降维,而且使图像的语义距离和空间距离更为协调。通过上述各项对视觉单词出现规律的多层次分析,有效地提高了成人图像的识别准确率。实验结果证明,相比于传统类型方法,基于视觉单词的方法不再从根本上依赖肤色检测,从而明显地降低了误检率,尤其是在人物类图像中效果更加明显。
基于上述的多层描述体系,提出了一种融合了视觉单词上下文的图像核函数。该核函数以单词和词组的多粒度直方图金字塔为基本框架,利用直方图的交运算来计算图像的相似性,并在其中融入了各个单词所处的上下文类别信息。实验结果显示,不论是在一般意义的图像识别中,或是在本文所讨论的成人图像识别中,均可以借助这种核函数来提高支持向量机(support vectormachine,SVM)的识别性能。
考虑到基于上述核函数的检测方法具有较高的计算复杂度,于是又提出一种将核函数与局部学习相结合的识别算法。该算法使特征空间中成人图像模式的分析变得尽可能局部化,从而可以只使用一幅图像邻近的训练数据来对其进行分类。首先利用一些普通的特征将图像分成若干组;而后在各组的训练数据中采集了部分有代表性的数据点作为代表点;继而在各代表点邻域内建立了子SVM分类器,并依据各个子SVM的识别性能对其赋以相应的权重;最终利用测试图像的k个近邻子SVM来共同判断图像的类别。在实验中证明,这种基于局部空间分析的策略不但有效地控制了计算复杂度,而且能够准确地识别散布于各个局部空间中的成人图像。
本文充分利用了成人图像中各种类型的信息,全面地分析了图像的语义,以视觉单词为基础,发展出了一套完整的识别策略。系统的检测性能明显地超越了传统类型的成人图像检测方法,在以往难以准确识别的图像中,错判大为减少。
Internet has been an important part of our life. However, in the sea of webimages, there are a large number of pornographic ones. The urgent task of detect-ing and filtering those harmful images attracts more and more attention of researchersthroughout the world. Most of the researchers try to find pornographic images throughanalyzing image content. Traditional approaches proposed in recent years are basedon simple, low-level visual features such as color, texture, skin regions, etc. Thosesystems generate many false positives when they detect benign images with large re-gions of skin-like colors, for example, human images. The dissertation aims to providea deeper understanding about image content and create detection systems which areless dependent on skin detection to generate much fewer false positives.
This dissertation analyzes pornographic images mainly based on local features.Local features can be coded as visual words by which the context of images can beconveniently expressed and analyzed. Images will be classified based on both visualwords and other low-level features. The detailed descriptions of the methods are asfollows.
First, a comprehensive research is done on different types of image features,including color, edge, skin region distribution, and local features. Discriminative fea-tures are selected or proposed for each feature type to re?ect the characteristics ofpornographic images. The dissertation proposes to represent the skin region distribu-tion with the occurrence statistics of local uniform patterns of skin blocks. For thevisual words, local appearances and textures are extracted as local features. The ex-traction of local features is simplified to speed up the computation. Moreover, therandomness of the construction of visual words is reduced by adjusting the clusters’radii in the unsupervised coding of local features. Finally, a group of rotation-invariantfeatures of edge distribution are developed based on short line segments. Experimen-tal results show that all of these features are more discriminative for pornographicimage detection.
Next, a multi-level image representation is constructed based on visual words.The model comprises three levels: word, phrase, and ROI (region of interest) topic. An effective method is proposed to construct phrases which code the co-occurrencepatterns of neighboring words. ROI topics reveal the context of words in a largerscale. It is proved in the experiments that the higher level representation can reducethe ambiguity of common words. Thus the pornographic images can be detected moreaccurately. To describe the global distribution of words, the author also developsthe distribution features of pornography-related words. At last, with the means ofsubspace learning, the multi-level representation is projected into a low dimensionalspace to bridge the gap between the semantic similarities and geometric distances ofimage pairs. After the multi-level analysis of visual words, results of skin detectionare no longer crucial in the detection. The proposed method outperforms traditionalmethods, especially in human images.
Based on the above multi-level representation of visual words, the dissertationproposes a novel kernel which fuses multi-level context of visual words. The authorconstructs multi-resolution histogram pyramids of words, phrases, and the classes ofthe ROIs in which they are located. Then the similarity of image pairs is evaluatedby the intersection of the histograms. Experimental results demonstrate that supportvector machines (SVM) using the kernel can perform better in not only pornographicimage detection but also general image-classification problems.
Considering the high computational cost of the image classification based on thenovel kernel, the author proposes to integrate the kernel into local learning. Then,the pattern analysis of pornographic images is limited to corresponding local featuresubspaces. In other words, an image can be classified only based on a small part oftraining images close to it. First, images are grouped according to low-level features.Second, in each group the algorithm selects one part of representative training dataaround each of which a local SVM is constructed. Then, these SVMs are weightedby their classification performances. Finally, a test image is classified by its k nearestSVMs jointly. It is shown in the experiments that the system has a lower compu-tational cost and accurately recognize pornographic images distributed in differentsubspaces.
In this dissertation the author makes use of various information in pornographicimages and gives a comprehensive semantic analysis. Based on visual words, a com-plete detection strategy is developed. Compared with baselines, the proposed systemshave better performance, particularly in the images which are difficult to be classified by traditional methods.
本文选择图像的局部特征为突破口。在系统中,将局部特征量化为视觉单词,据此可以高效地分析图像的上下文语义,并结合其它方面的低层特征,对图像的类别给出综合的判断。论文的具体研究内容如下:
首先对各种重要的低层特征展开了的研究,并进行了相应的改进。所考察的特征包括:颜色、肤色分布、局部特征、以及边缘线条特征。对于各种特征,都探讨了不同的方案在成人图像检测中的效果。并针对传统方法的不足,提出了有针对性的改进,主要包括:通过统计肤色块局部模式的出现规律,提出了一种新的描述肤色分布的特征;在局部特征方面,同时使用了局部的形态和纹理信息,并适度简化了局部特征点的采集算法;此外,对于局部特征无监督量化中所产生的随意性,通过调整和限制局部特征量化簇集的半径,提高了量化结果(即“视觉单词”)的质量;对图像中线条的分布情况,以局部短线段为基础,建立了旋转不变的描述。实验证明,上述特征产生了更好的识别能力。
然后以普通的视觉单词为基础,建立了对成人图像视觉单词上下文的多层描述体系。该体系总共分3个层次,除了普通的视觉单词,还包括:中间层的词组,以及更高层的兴趣区域(region of interest,ROI)话题。词组是视觉单词的局部相邻关系的描述模型,本文建立了一种简单而高效的局部词组生成算法。ROI话题则用于在更大的尺度上(ROI)描述成人图像中视觉单词的上下文关系。在实验中发现,高层的视觉单词降低了普通单词的歧义性,并提高了对成人图像的识别性能。此外,还提取了敏感单词分布特征,从而补充了对视觉单词的全局分布信息的描述。最后,将子空间学习的思想融入到算法中,通过向量映射,不但使图像特征向量得以显著降维,而且使图像的语义距离和空间距离更为协调。通过上述各项对视觉单词出现规律的多层次分析,有效地提高了成人图像的识别准确率。实验结果证明,相比于传统类型方法,基于视觉单词的方法不再从根本上依赖肤色检测,从而明显地降低了误检率,尤其是在人物类图像中效果更加明显。
基于上述的多层描述体系,提出了一种融合了视觉单词上下文的图像核函数。该核函数以单词和词组的多粒度直方图金字塔为基本框架,利用直方图的交运算来计算图像的相似性,并在其中融入了各个单词所处的上下文类别信息。实验结果显示,不论是在一般意义的图像识别中,或是在本文所讨论的成人图像识别中,均可以借助这种核函数来提高支持向量机(support vectormachine,SVM)的识别性能。
考虑到基于上述核函数的检测方法具有较高的计算复杂度,于是又提出一种将核函数与局部学习相结合的识别算法。该算法使特征空间中成人图像模式的分析变得尽可能局部化,从而可以只使用一幅图像邻近的训练数据来对其进行分类。首先利用一些普通的特征将图像分成若干组;而后在各组的训练数据中采集了部分有代表性的数据点作为代表点;继而在各代表点邻域内建立了子SVM分类器,并依据各个子SVM的识别性能对其赋以相应的权重;最终利用测试图像的k个近邻子SVM来共同判断图像的类别。在实验中证明,这种基于局部空间分析的策略不但有效地控制了计算复杂度,而且能够准确地识别散布于各个局部空间中的成人图像。
本文充分利用了成人图像中各种类型的信息,全面地分析了图像的语义,以视觉单词为基础,发展出了一套完整的识别策略。系统的检测性能明显地超越了传统类型的成人图像检测方法,在以往难以准确识别的图像中,错判大为减少。
Internet has been an important part of our life. However, in the sea of webimages, there are a large number of pornographic ones. The urgent task of detect-ing and filtering those harmful images attracts more and more attention of researchersthroughout the world. Most of the researchers try to find pornographic images throughanalyzing image content. Traditional approaches proposed in recent years are basedon simple, low-level visual features such as color, texture, skin regions, etc. Thosesystems generate many false positives when they detect benign images with large re-gions of skin-like colors, for example, human images. The dissertation aims to providea deeper understanding about image content and create detection systems which areless dependent on skin detection to generate much fewer false positives.
This dissertation analyzes pornographic images mainly based on local features.Local features can be coded as visual words by which the context of images can beconveniently expressed and analyzed. Images will be classified based on both visualwords and other low-level features. The detailed descriptions of the methods are asfollows.
First, a comprehensive research is done on different types of image features,including color, edge, skin region distribution, and local features. Discriminative fea-tures are selected or proposed for each feature type to re?ect the characteristics ofpornographic images. The dissertation proposes to represent the skin region distribu-tion with the occurrence statistics of local uniform patterns of skin blocks. For thevisual words, local appearances and textures are extracted as local features. The ex-traction of local features is simplified to speed up the computation. Moreover, therandomness of the construction of visual words is reduced by adjusting the clusters’radii in the unsupervised coding of local features. Finally, a group of rotation-invariantfeatures of edge distribution are developed based on short line segments. Experimen-tal results show that all of these features are more discriminative for pornographicimage detection.
Next, a multi-level image representation is constructed based on visual words.The model comprises three levels: word, phrase, and ROI (region of interest) topic. An effective method is proposed to construct phrases which code the co-occurrencepatterns of neighboring words. ROI topics reveal the context of words in a largerscale. It is proved in the experiments that the higher level representation can reducethe ambiguity of common words. Thus the pornographic images can be detected moreaccurately. To describe the global distribution of words, the author also developsthe distribution features of pornography-related words. At last, with the means ofsubspace learning, the multi-level representation is projected into a low dimensionalspace to bridge the gap between the semantic similarities and geometric distances ofimage pairs. After the multi-level analysis of visual words, results of skin detectionare no longer crucial in the detection. The proposed method outperforms traditionalmethods, especially in human images.
Based on the above multi-level representation of visual words, the dissertationproposes a novel kernel which fuses multi-level context of visual words. The authorconstructs multi-resolution histogram pyramids of words, phrases, and the classes ofthe ROIs in which they are located. Then the similarity of image pairs is evaluatedby the intersection of the histograms. Experimental results demonstrate that supportvector machines (SVM) using the kernel can perform better in not only pornographicimage detection but also general image-classification problems.
Considering the high computational cost of the image classification based on thenovel kernel, the author proposes to integrate the kernel into local learning. Then,the pattern analysis of pornographic images is limited to corresponding local featuresubspaces. In other words, an image can be classified only based on a small part oftraining images close to it. First, images are grouped according to low-level features.Second, in each group the algorithm selects one part of representative training dataaround each of which a local SVM is constructed. Then, these SVMs are weightedby their classification performances. Finally, a test image is classified by its k nearestSVMs jointly. It is shown in the experiments that the system has a lower compu-tational cost and accurately recognize pornographic images distributed in differentsubspaces.
In this dissertation the author makes use of various information in pornographicimages and gives a comprehensive semantic analysis. Based on visual words, a com-plete detection strategy is developed. Compared with baselines, the proposed systemshave better performance, particularly in the images which are difficult to be classified by traditional methods.
引文
1 Internet Filter Learning Center. http://internet-filter-review.toptenreviews.com/internet-pornography-statistics.html
2 Statistics on Pornography, Sexual Addiction and Online Perpetrators. http://www.safefamilies.org/sfStats.php
3 Internet Pornography Statistics. http://www.mykidsbrowser.com/internet-pornography-statistics.php
4 Internet Filter Software Review. http://internet-filter-review.toptenreviews.com/
5 M. Fleck, D. Forsyth, C. Bregler. Finding Naked People. European Conferenceon Computer Vision. Cambridge, UK, 1996:593–602
6 D. Forsyth, M. Fleck. Automatic Detection of Human Nudes. Int’l J. ComputerVision. 1999, 32(1):63–77
7 J. Wang, G. Wiederhold, O.Firschein. System for Screening Objectionable Im-ages. Computer Communications. 1998, 21(15):1355–1360
8 J. Yang, Z. Fu, T. Tan, et al. A Novel Approach to Detecting Adult Images.Proceedings of the 17th International Conference on Pattern Recognition. Cam-bridge, UK, 2004:479–482
9杨金锋,傅周宇,谭铁牛,等.一种新型的基于内容的图像识别与过滤方法.通信学报. 2004, 25(7):93–106
10 W. Hu, O. Wu, Z. Chen, et al. Recognition of Pornographic Web Pages by Clas-sifying Texts and Images. IEEE Transactions on Pattern Analysis and MachineIntelligence. 2007, 29(6):1019–1034
11 X. Shen, W. Wei, Q. Qian. The Filtering of Internet Images Based on DetectingErotogenic-part. The Third International Conference on Natural Computation.Hainan, China, 2007:732–736
12 J. Wang, J. Li, G. Wiederhold, et al. Classifying Objectionable Websites Basedon Image Content. Proceedings of the 5th International Workshop on InteractiveDistributed Multimedia Systems and Telecommunication Services. 1998:113–124
13 L. Duan, G. Cui, W. Gao, et al. Adult Image Detection Method Base on SkinColor Model and Support Vector Machine. The Fifth Asian Conference onComputer Vision. Melbourne, Australia, 2002:797–800
14 A.Bosson, G. C. Cawley, Y. Chan, et al. Non-retrieval: Blocking PornographicImages. Proceedings of the International Conference on Image and Video Re-trieval. London, UK, 2002:50–60
15 M. Jones, J. Rehg. Statistical Color Models with Application to Skin Detection.International Journal of Computer Vision. 2002, 46(1):81–96
16 H. Zheng, M. Daoudi, B. Jedynak. Blocking Adult Images Based on StatisticalSkin Detection. Electronic Letters on Computer Vision and Image Analysis.2004, 4(2):1–14
17温泽逢,袁华.基于内容的图像过滤新方法.通信学报. 2006, 27(11):280–284
18 J. Lee, Y. Kuo, P. Chung, et al. Naked Image Detection Based on Adaptiveand Extensible Skin Color Model. Computer Vision and Image Understanding.2007, 40(8):2261–2270
19 Y. Xu, B. Li, X. Xue, et al. Region-based Pornographic Image Detection. IEEE7th Workshop on Multimedia Signal Processing. Shanghai, China, 2005:1–4
20 W. Zeng, W. Gao, T. Zhang, et al. Image Guarder: An Intelligent Detectorfor Adult Images. Asian Conference on Computer Vision. Jeju Island, Korea,2004:198–203
21曾炜,郑清芳,赵德斌.图片卫士:一个自动成人图像识别系统.高技术通讯. 2005, 15(3):11–16
22 Q. Zheng, W. Zeng, W. Gao, et al. Shape-based Adult Image Classification.The Third International Conference on Image and Graphics. Hong Kong, China,2004:150–153
23 Q. Zheng, M. Zhang, W. Wang. A Hybrid Approach to Detect Adult Web Im-ages. The 5th Pacific Rim Conference on Multimedia. Tokyo, Japan, 2004:609–616
24 R. Schettini, C. Brambilla, C. Cusano, et al. On the Detection of PornographicDigital Images. Visual Communications and Image Processing. Lugano,Switzerland, 2003:2105–2113
25 W. Arentz, B. Olstad. Classifying Offensive Sites Based on Image Content.Computer Vision and Image Understanding. 2004, 94(1–3):295–310
26 C. Y. Jeong, J. S. Kim, K. S. Hong. Appearance-based Nude Image Detec-tion. 17th International Conference on Pattern Recognition. Cambridge, UK,2004:467–470
27 C. Y. Jeong, S. W. Han, S. G. Choi, et al. An Objectionable Image DetectionSystem Based on Region of Interest. IEEE International Conference on ImageProcessing. Atlanta, Georgia, USA, 2006:1477–1480
28 J. Shih, C. Lee, C. Yang. An Adult Image Identification System EmployingImage Retrieval Technique. Pattern Recognition Letters. 2007, 28(16):2367–2374
29 H. A. Rowley, Y. Jing, S. Baluja. Large Scale Image-based Adult-content Fil-tering. International Conference on Computer Vision Theory and Applications.Setubal, Portugal, 2006:25–28
30 Y. Liu, W. Zeng, H. Yao. Online Learning Objectionable Image Filter Basedon SVM. The 5th Pacific Rim Conference on Multimedia. Tokyo, Japan,2004:304–311
31 H. Zhu, S. Zhou, J. Wang, et al. An Algorithm of Pornographic Image Detec-tion. Fourth International Conference on Image and Graphics. Chengdu, China,2007:801–804
32 Y. Wu, E. Y. Chang, K. Cheng, et al. Morf: A Distributed Multimodal Infor-mation Filtering System. Third IEEE Pacific Rim Conference on Multimedia.Hsinchu, Taiwan, China, 2002:279–286
33 L. Spyros, T. Georgios. Color and Texture Image Retrieval Using ChromaticityHistograms and Wavelet Frames. IEEE Transactions on Multimedia. 2004,6(5):676–686
34 T. Amin, M. Zeytinoglu, L. Guan. Application of Laplacian Mixture Modelto Image and Video Retrieval. IEEE Transactions on Multimedia. 2007,9(7):1416–1429
35 A. Vailaya, M. Figueiredo, A. Jain, et al. Image Classification for Content-basedIndexing. IEEE Transactions on Image Processing. 2001, 10(1):117–130
36 A. Oliva, A. Torralba. Modeling the Shape of the Scene: A Holistic Represen-tation of the Spatial Envelope. International Journal of Computer Vision. 2001,42(3):145–175
37 A. Kanaujia, C. Sminchisescu, D. Metaxas. Spectral Latent Variable Modelsfor Perceptual Inference. Eleventh IEEE International Conference on ComputerVision. Rio de Janeiro, Brazil, 2007:1–8
38 E. Hadjidemetriou, M. Grossberg, S. Nayar. Multiresolution Histograms andTheir Use for Recognition. IEEE Transactions on Pattern Analysis and MachineIntelligence. 2004, 26(7):831–847
39 C. Fredembach, M. Schroder, S. Susstrunk. Eigenregions for Image Classifica-tion. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2004,26(12):1645–1649
40 A. Torralba, K. P. Murphy, W. T. Freeman. Sharing Visual Features for Multi-class and Multiview Object Detection. IEEE Transactions on Pattern Analysisand Machine Intelligence. 2007, 29(5):854–869
41 S. Gangaputra, D. Geman. Spectral Latent Variable Models for Perceptual In-ference. IEEE Conference on Computer Vision and Pattern Recognition. NewYork, USA, 2006:1877–1884
42 R. O. Duda, P. E. Hart, D. G. Stork原著,李宏东,姚天翔译.模式分类.机械工业出版社, 2003:385–386
43 K. Tieu, P. Viola. Boosting Image Retrieval. International Journal of ComputerVision. 2004, 56(1-2):17–36
44 Y. Gao, J. Fan, X. Xue, et al. Automatic Image Annotation by IncorporatingFeature Hierarchy and Boosting to Scale-up SVM Classifier Training. 14thACM International Conference on Multimedia. Santa Barbara, USA, 2006:901–910
45 W. Jiang, G. Er, Q. Dai, et al. Similarity-based Online Feature Selection inContent-based Image Retrieval. IEEE Transactions on Image Processing. 2006,15(3):702–712
46 M. Naphade, T. Huang. A Probabilistic Framework for Semantic Video Index-ing, Filtering and Retrieval. IEEE Transaction on Multimedia. 2001, 3(1):141–
15147 N. Serrano, A. Savakis, J. Luo. A Computationally Efficient Approach to In-door/outdoor Scene Classification. Proceeding of International Conference onPattern Recognition. Quebec, Canada, 2002:146–149
48 J. Vogel, B. Schiele. Natural Scene Retrieval Based on a Semantic ModelingStep. Proceeding of International Conference on Image and Video Retrieval.Dublin, Ireland, 2004:207–215
49 L. Lu, K. Toyama, G. D. Hager. A Two Level Approach for Scene Recog-nition. IEEE Conference on Computer Vision and Pattern Recognition. SanDiego, USA, 2005:688–695
50 B. Epshtein, S. Ullman. Identifying Semantically Equivalent Object Fragments.IEEE Conference on Computer Vision and Pattern Recognition. San Diego,USA, 2005:2–9
51 B. Epshtein, S. Ullman. Feature Hierarchies for Object Classification. TenthIEEE International Conference on Computer Vision. Beijing, China, 2005:220–227
52 G. Bouchard, B. Triggs. Hierarchical Part-based Visual Object Categorization.IEEE Conference on Computer Vision and Pattern Recognition. San Diego,USA, 2005:710–715
53 S. Fidler, A. Leonardis. Towards Scalable Representations of Object Categories:Learning a Hierarchy of Parts. IEEE Conference on Computer Vision and Pat-tern Recognition. Minneapolis, USA, 2007:1–8
54 D. Zhang, S. Chang. A Generative-discriminative Hybrid Method for Multi-view Object Detection. IEEE Conference on Computer Vision and PatternRecognition. New York, USA, 2006:2017–2024
55 R. Fergus, P. Perona, A. Zisserman. Object Class Recognition by UnsupervisedScale Invariant Learning. IEEE Conference on Computer Vision and PatternRecognition. Madison, USA, 2003:264–271
56 G. Dorko, C. Schmid. Selection of Scale Invariant Parts for Object Class Recog-nition. Ninth IEEE International Conference on Computer Vision. Nice, France,2003:634–639
57 A. Bar-Hillel, T. Hertz, D. Weinshall. Object Class Recognition by Boosting aPart Based Model. IEEE Conference on Computer Vision and Pattern Recogni-tion. San Diego, USA, 2005:702–709
58 G. Carneiro, D. G. Lowe. Sparse Flexible Models of Local Features. 9th Euro-pean Conference on Computer Vision. Graz, Austria, 2006:29–43
59 Z. Zha, X. Hua, T. Mei, et al. Joint Multi-label Multi-instance Learning for Im-age Classification. IEEE Conference on Computer Vision and Pattern Recogni-tion. Anchorage, USA, 2008:1–8
60 O. Boiman, E. Shechtman, M. Irani. In Defense of Nearest-neighbor Based Im-age Classification. IEEE Conference on Computer Vision and Pattern Recogni-tion. Anchorage, USA, 2008:1–8
61 A. Bosch, A. Zisserman, X. Munoz. Scene Classification via Plsa. 9th EuropeanConference on Computer Vision. Graz, Austria, 2006:517–530
62 A. Bosch, A. Zisserman, X. Muoz. Image Classification Using Random Forestsand Ferns. Eleventh IEEE International Conference on Computer Vision. Riode Janeiro, Brazil, 2007:1–8
63 D. G. Lowe. Distinctive Image Features from Scale-invariant Keypoints. Inter-national Journal of Computer Vision. 2004, 60(2):91–110
64 K. Mikolajczyk, B. Leibe, B. Schiele. Local Features for Object Class Recogni-tion. Tenth IEEE International Conference on Computer Vision. Beijing, China,2005:1792–1799
65 T. Kadir, A. Zisserman, M. Brady. An Affine Invariant Salient Region Detec-tor. 8th European Conference on Computer Vision. Prague, Czech Republic,2004:228–241
66 P. K. Bocher, K. R. McCloy. The Fundamentals of Average Local Variance -Part I: Detecting Regular Patterns. IEEE Transactions on Image Processing.2006, 15(2):300–310
67 L. Szumilas, R. Donner, G. Langs, et al. Local Structure Detection withOrientation-invariant Radial Configuration. IEEE Conference on Computer Vi-sion and Pattern Recognition. Minneapolis, USA, 2007:1–7
68 F. Jing, M. Li, H. Zhang, et al. An Efficient and Effective Region-based Im-age Retrieval Framework. IEEE Transactions on Image Processing. 2004,13(5):699–709
69 A. C. Berg, T. L. Berg, J. Malik. Shape Matching and Object Recognition UsingLow Distortion Correspondences. IEEE Conference on Computer Vision andPattern Recognition. San Diego, USA, 2005:26–33
70 A. Diplaros, T. Gevers, I. Patras. Combining Color and Shape Information forIllumination-viewpoint Invariant Object Recognition. IEEE Transactions onImage Processing. 2006, 15(1):1–11
71 H. Ling, D. W. Jacobs. Deformation Invariant Image Matching. Tenth IEEE In-ternational Conference on Computer Vision. Beijing, China, 2005:1466–1473
72 J. C. van Gemert, J. Geusebroek, C. J. Veenman, et al. Robust Scene Cat-egorization by Learning Image Statistics in Context. Proceedings of the 2006Conference on Computer Vision and Pattern Recognition Workshop. New York,USA, 2006:105–112
73 A. E. Abdel-Hakim, A. A. Farag. CSIFT: A SIFT Descriptor with Color Invari-ant Characteristics. IEEE Conference on Computer Vision and Pattern Recog-nition. New York, USA, 2006:1978–1983
74 C. A. Murthy, S. K. Naik. Distinct Multicolored Region Descriptors for ObjectRecognition. IEEE Transactions on Pattern Analysis and Machine Intelligence.2007, 29(7):1291–1296
75 B. Ommer, J. M. Buhmann. Learning Compositional Categorization Models.9th European Conference on Computer Vision. Graz, Austria, 2006:316–329
76 C. Schmid. Weakly Supervised Learning of Visual Models and its Applicationto Content-based Retrieval. International Journal of Computer Vision. 2004,56(1-2):7–16
77 B. Ommer, J. M. Buhmann. Object Categorization by Compositional GraphicalModels. The 5th International Workshop on Energy Minimization Methods inComputer Vision and Pattern Recognition. Augustine, USA, 2005:235–250
78 K. Mikolajczyk, B. Leibe, B. Schiele. Multiple Object Class Detection with aGenerative Model. IEEE Conference on Computer Vision and Pattern Recog-nition. New York, USA, 2006:26–36
79 B. Leibe, A. Leonardis, B. Schiele. Robust Object Detection with InterleavedCategorization and Segmentation. International Journal of Computer Vision.2008, 77(1-3):259–289
80 F. Perronnin, C. R. Dance, G. Csurka, et al. Adapted Vocabularies for GenericVisual Categorization. 9th European Conference on Computer Vision. Graz,Austria, 2006:464–475
81 S. Lazebnik, C. Schmid, J. Ponce. Affine-invariant Local Descriptors andNeighborhood Statistics for Texture Recognition. Ninth IEEE InternationalConference on Computer Vision. Nice, France, 2003:649–655
82 D. Nister, H. Stewenius. Scalable Recognition with a Vocabulary Tree. IEEEConference on Computer Vision and Pattern Recognition. New York, USA,2006:2161–2168
83 E. Nowak, F. Jurie. Learning Visual Similarity Measures for Comparing NeverSeen Objects. IEEE Conference on Computer Vision and Pattern Recognition.Minneapolis, USA, 2007:1–8
84 E. Nowak, F. Jurie, B. Triggs. Sampling Strategies for Bag-of-features ImageClassification. 9th European Conference on Computer Vision. Graz, Austria,2006:490–503
85 A. Opelt, M. Fussenegger, A. Pinz, et al. Weak Hypotheses and Boosting forGeneric Object Detection and Recognition. 8th European Conference on Com-puter Vision. Prague, Czech Republic, 2004:71–84
86 J. Winn, A. Criminisi, T. Minka. Object Categorization by Learned UniversalVisual Dictionary. Tenth IEEE International Conference on Computer Vision.Beijing, China, 2005:1800–1807
87 G. Csurka, C. R. Dance, L. Fan, et al. Visual Categorization with Bags of Key-points. Workshop on Statistical Learning in Computer Vision of 8th EuropeanConference on Computer Vision. Prague, Czech Republic, 2004:1–22
88 M. Marszaek, C. Schmid. Spatial Weighting for Bag-of-features. IEEEConference on Computer Vision and Pattern Recognition. New York, USA,2006:2118–2125
89 M. Marszalek, C. Schmid. Semantic Hierarchies for Visual Object Recognition.IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis,USA, 2007:1–7
90 W. Jiang, K. L. Chan, M. Li, et al. Mapping Low-level Features to High-levelSemantic Concepts in Region-based Image Retrieval. IEEE Conference onComputer Vision and Pattern Recognition. San Diego, USA, 2005:244–249
91 J. Sivic, B. C. Russell, A. A. Efros, et al. Discovering Objects and Their Lo-cation in Images. Tenth IEEE International Conference on Computer Vision.Beijing, China, 2005:370–377
92 T. Hofmann. Unsupervised Learning by Probabilistic Latent Semantic Analysis.Machine Learning. 2001, 42(1-2):177–196
93 P. Quelhas, F. Monay, J. M. Odobez, et al. A Thousand Words in Scene. IEEETransactions on Pattern Analysis and Machine Intelligence. 2007, 29(9):1575–1589
94 R. Zhang, Z. Zhang. Effective Image Retrieval Based on Hidden Concept Dis-covery in Image Database. IEEE Transactions on Image Processing. 2007,16(2):562–572
95 L. Fei-Fei, P. Perona. A Bayesian Hierarchical Model for Learning NaturalScene Categories. IEEE Conference on Computer Vision and Pattern Recogni-tion. San Diego, USA, 2005:524–531
96 D. Blei, A. Ng, M. Jordan. Latent Dirichlet Allocation. Journal of MachineLearning Research. 2003, 3(7):993–1022
97 L.-J. Li, L. Fei-Fei. What, Where and Who Classifying Events by Scene andObject Recognition. Eleventh IEEE International Conference on Computer Vi-sion. Rio de Janeiro, Brazil, 2007:1–8
98 G. Wang, Y. Zhang, L. Fei-Fei. Using Dependent Regions for Object Catego-rization in a Generative Framework. IEEE Conference on Computer Vision andPattern Recognition. New York, USA, 2006:1597–1604
99 L.-J. Li, G. Wang, L. Fei-Fei. OPTIMOL: Automatic Online Picture Collectionvia Incremental Model Learning. IEEE Conference on Computer Vision andPattern Recognition. Minneapolis, USA, 2007:1–8
100 N. Rasiwasia, N. Vasconcelos. Scene Classification with Low-dimensional Se-mantic Spaces and Weak Supervision. IEEE Conference on Computer Visionand Pattern Recognition. Anchorage, USA, 2008:1–6
101 S. Nowozin, K. Tsuda, T. Uno, et al. Weighted Substructure Mining for Im-age Analysis. IEEE Conference on Computer Vision and Pattern Recognition.Minneapolis, USA, 2007:1–8
102 S. Savarese, J. Winn, A. Criminisi. Discriminative Object Class Models ofAppearance and Shape by Correlations. IEEE Conference on Computer Visionand Pattern Recognition. New York, USA, 2006:2033–2040
103 J. Malik, S. Belongie, J. Shi, et al. Textons, Contours and Regions: Cue Integra-tion in Image Segmentation. 7th IEEE International Conference on ComputerVision. Kerkyra, Greece, 1999:918–925
104 W. Zhang, H. Deng, T. G. Dietterich, et al. A Hierarchical Object RecognitionSystem Based on Multi-scale Principal Curvature Regions. 18th InternationalConference on Pattern Recognition. Hong Kong, China, 2006:778–782
105 S. Agarwal, A. Awan, D. Roth. Learning to Detect Objects in Images via aSparse, Part-based Representation. IEEE Transactions on Pattern Analysis andMachine Intelligence. 2004, 26(11):1475–1490
106 D. Liu, G. Hua, P. Viola, et al. Integrated Feature Selection and Higher-orderSpatial Feature Extraction for Object Categorization. IEEE Conference onComputer Vision and Pattern Recognition. Anchorage, USA, 2008:1–8
107 J. Yuan, Y. Wu, M. Yang. Discovery of Collocation Patterns: From VisualWords to Visual Phrases. IEEE Conference on Computer Vision and PatternRecognition. Minneapolis, USA, 2007:1–8
108 Y. Zheng, M. Zhao, S. Neo, et al. Visual Synset: Towards a Higher-level VisualRepresentation. IEEE Conference on Computer Vision and Pattern Recognition.Anchorage, USA, 2008:1–8
109 Q. Zheng, W. Wang, W. Gao. Effective and Efficient Object-based Image Re-trieval Using Visual Phrases. 14th ACM International Conference on Multime-dia. Santa Barbara, USA, 2006:77–80
110 A. Agarwal, B. Triggs. Hyperfeatures: Multilevel Local Coding for VisualRecognition. 9th European Conference on Computer Vision. Graz, Austria,2006:30–43
111 B. Ommer, J. M. Buhmann. Learning the Compositional Nature of Visual Ob-jects. IEEE Conference on Computer Vision and Pattern Recognition. Min-neapolis, USA, 2007:1–8
112 O. Chum, A. Zisserman. An Exemplar Model for Learning Object Classes.IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis,USA, 2007:1–8
113 K. Grauman, T. Darrell. Approximate Correspondences in High Dimensions.The 20th Annual Conference on Neural Information Processing Systems. Van-couver, Canada, 2006:505–512
114 J. Shawe-Taylor and N. Cristianini. Kernel Methods for Pattern Analysis. Cam-bridge University Press, 2004:211–230, 63–66, 74–79
115 C. Wallraven, B. Caputo, A. Graf. Recognition with Local Features: The Ker-nel Recipe. Ninth IEEE International Conference on Computer Vision. Nice,France, 2003:257–264
116 S. Lyu. Mercer Kernels for Object Recognition with Local Features. IEEEConference on Computer Vision and Pattern Recognition. San Diego, USA,2005:223–229
117 H. Sahbi, J. Audibert. Context-dependent Kernel Design for Object Matchingand Recognition. IEEE Conference on Computer Vision and Pattern Recogni-tion. Anchorage, USA, 2008:1–8
118 L. Wolf, A. Shashua. Learning Over Sets Using Kernel Principal Angles. Jour-nal of Machine Learning Research. 2003, 4(10):913–931
119 R. Kondor, T. Jebara. A Kernel between Sets of Vectors. International Confer-ence on Machine Learning. Washington, D.C., USA, 2003:361–368
120 P. Moreno, P. Ho, N. Vasconcelos. A Kullback-leibler Divergence Based Ker-nel for SVM Classification in Multimedia Applications. The 17th AnnualConference on Neural Information Processing Systems. Vancouver, Canada,2003:1385–1392
121 Y. Liu, F. Perronnin. A Similarity Measure between Unordered Vector Sets withApplication to Image Categorization. IEEE Conference on Computer Visionand Pattern Recognition. Anchorage, USA, 2008:1–8
122 G. Qi, X. Hua, Y. Rui. A Joint Appearance-spatial Distance for Kernel-basedImage Categorization. IEEE Conference on Computer Vision and PatternRecognition. Anchorage, USA, 2008:1–8
123 K. Grauman, T. Darrell. The Pyramid Match Kernel: Efficient Learning withSets of Features. Journal of Machine Learning Research. 2007, 8(4):725–760
124 S. Lazebnik, C. Schmid, J. Ponce. Beyond Bags of Features: Spatial Pyra-mid Matching for Recognizing Natural Scene Categories. IEEE Conference onComputer Vision and Pattern Recognition. New York, USA, 2006:2169–2176
125 A. Kapoor, J. Winn. Located Hidden Random Fields: Learning Discrimina-tive Parts for Object Detection. 9th European Conference on Computer Vision.Graz, Austria, 2006:302–315
126 J. Yuan, J. Li, B. Zhang. Exploiting Spatial Context Constraints for AutomaticImage Region Annotation. 15th ACM International Conference on Multimedia.Augsburg, Germany, 2007:595–604
127 A. Rabinovich, A. Vedaldi, C. Galleguillos, et al. Objects in Context. EleventhIEEE International Conference on Computer Vision. Rio de Janeiro, Brazil,2007:1–8
128 P. Carbonetto, G. Dorko, C. Schmid, et al. Learning to Recognize Objectswith Little Supervision. International Journal of Computer Vision. 2008, 77(1-3):219–237
129 J. Yuan, J. Li, B. Zhang. Scene Understanding with Discriminative StructuredPrediction. IEEE Conference on Computer Vision and Pattern Recognition.Anchorage, USA, 2008:1–8
130 G. Pass, R. Zabih, J. Miller. Comparing Images Using Color Coherence Vec-tors. The Fourth ACM International Conference on Multimedia. Boston, USA,1996:65–73
131 P. Kakumanu, S. Makrogiannis, N. Bourbakis. A Survey of Skin-color Model-ing and Detection Methods. Pattern Recognition. 2007, 40(3):1106–1122
132 P. Viola, M. Jones. Rapid Object Detection Using a Boosted Cascade of Sim-ple Features. IEEE Conference on Computer Vision and Pattern Recognition.Kauai, USA, 2001:511–518
133 T. Ojala, M. Pietikainen, T. Maenpaa. Multiresolution Gray-scale and RotationInvariant Texture Classification with Local Binary Patterns. IEEE Transactionson Pattern Analysis and Machine Intelligence. 2002, 24(7):971–987
134 K. Mikolajczyk, C. Schmid. A Performance Evaluation of Local Descrip-tors. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2005,27(10):1615–1630
135 M. Sonka, V. Hlavac, R. Boyle原著,艾海舟,武勃译.图像处理、分析与机器视觉.人民邮电出版社, 2003:110–116
136 T. Deselaers, L. Pimenidis, H. Ney. Bag-of-visual-words Models for AdultImage Classification and Filtering. 19th International Conference on PatternRecognition. Tampa, USA, 2008:1–4
137 B. Liu, Y. Xia, P. S. Yu. Clustering Through Decision Tree Construction.The 9th International Conference on Information and Knowledge Management.McLean, USA, 2000:20–29
138 A. Webb. Statistical Pattern Recognition. 2nd edn. John Wiley and Sons Inc,2002:106–113
139 M. Figueiredo, A. Jain. Unsupervised Learning of Finite Mixture Models. IEEETransactions on Pattern Analysis and Machine Intelligence. 2002, 24(3):381–396
140 J. Yu, Q. Tian. Learning Image Manifolds by Semantic Subspace Projection.The 14th ACM International Conference on Multimedia. Santa Barbara, USA,2006:297–306
141 D. Swets, J. Weng. Using Discriminant Eigenfeatures for Image Retrieval. IEEETransactions on Pattern Analysis and Machine Intelligence. 1996, 18(8):831–836
142 I. H. Witten, E. Frank. Data Mining: Practical Machine Learning Tools andTechniques. 2nd edn. Morgan Kaufmann, 2005:291
143 H. Zhang, A. C. Berg, M. Maire, et al. SVM-KNN: Discriminative NearestNeighbor Classification for Visual Category Recognition. The 2006 IEEE Com-puter Society Conference on Computer Vision and Pattern Recognition. NewYork, USA, 2006:2126–2136
144 K. Grauman, T. Darrell. Approximate Correspondences in High Dimensions.The 20th Annual Conference on Neural Information Processing Systems. Van-couver, Canada, 2006:505–512
145 F. Odone, A. Barla, A. Verri. Building Kernels from Binary Strings for ImageMatching. IEEE Transaction on Image Processing. 2005, 14(2):169–180
146 C. Chang, C. Lin. LIBSVM : A Library for Support Vector Machines. http://www.csie.ntu.edu.tw/～cjlin/libsvm. 2001
147 F. Li, R. Fergus, P. Perona. Learning Generative Visual Models from Few Train-ing Examples: An Incremental Bayesian Approach Tested on 101 Object Cate-gories. Computer Vision and Image Understanding. 2007, 106(1):59–70
148 D. Jacobs, D. Weinshall, Y. Gdalyahu. Classification with Nonmetric Distances:Image Retrieval and Class Representation. IEEE Transactions on Pattern Anal-ysis and Machine Intelligence. 2000, 22(6):583–600– 114–
2 Statistics on Pornography, Sexual Addiction and Online Perpetrators. http://www.safefamilies.org/sfStats.php
3 Internet Pornography Statistics. http://www.mykidsbrowser.com/internet-pornography-statistics.php
4 Internet Filter Software Review. http://internet-filter-review.toptenreviews.com/
5 M. Fleck, D. Forsyth, C. Bregler. Finding Naked People. European Conferenceon Computer Vision. Cambridge, UK, 1996:593–602
6 D. Forsyth, M. Fleck. Automatic Detection of Human Nudes. Int’l J. ComputerVision. 1999, 32(1):63–77
7 J. Wang, G. Wiederhold, O.Firschein. System for Screening Objectionable Im-ages. Computer Communications. 1998, 21(15):1355–1360
8 J. Yang, Z. Fu, T. Tan, et al. A Novel Approach to Detecting Adult Images.Proceedings of the 17th International Conference on Pattern Recognition. Cam-bridge, UK, 2004:479–482
9杨金锋,傅周宇,谭铁牛,等.一种新型的基于内容的图像识别与过滤方法.通信学报. 2004, 25(7):93–106
10 W. Hu, O. Wu, Z. Chen, et al. Recognition of Pornographic Web Pages by Clas-sifying Texts and Images. IEEE Transactions on Pattern Analysis and MachineIntelligence. 2007, 29(6):1019–1034
11 X. Shen, W. Wei, Q. Qian. The Filtering of Internet Images Based on DetectingErotogenic-part. The Third International Conference on Natural Computation.Hainan, China, 2007:732–736
12 J. Wang, J. Li, G. Wiederhold, et al. Classifying Objectionable Websites Basedon Image Content. Proceedings of the 5th International Workshop on InteractiveDistributed Multimedia Systems and Telecommunication Services. 1998:113–124
13 L. Duan, G. Cui, W. Gao, et al. Adult Image Detection Method Base on SkinColor Model and Support Vector Machine. The Fifth Asian Conference onComputer Vision. Melbourne, Australia, 2002:797–800
14 A.Bosson, G. C. Cawley, Y. Chan, et al. Non-retrieval: Blocking PornographicImages. Proceedings of the International Conference on Image and Video Re-trieval. London, UK, 2002:50–60
15 M. Jones, J. Rehg. Statistical Color Models with Application to Skin Detection.International Journal of Computer Vision. 2002, 46(1):81–96
16 H. Zheng, M. Daoudi, B. Jedynak. Blocking Adult Images Based on StatisticalSkin Detection. Electronic Letters on Computer Vision and Image Analysis.2004, 4(2):1–14
17温泽逢,袁华.基于内容的图像过滤新方法.通信学报. 2006, 27(11):280–284
18 J. Lee, Y. Kuo, P. Chung, et al. Naked Image Detection Based on Adaptiveand Extensible Skin Color Model. Computer Vision and Image Understanding.2007, 40(8):2261–2270
19 Y. Xu, B. Li, X. Xue, et al. Region-based Pornographic Image Detection. IEEE7th Workshop on Multimedia Signal Processing. Shanghai, China, 2005:1–4
20 W. Zeng, W. Gao, T. Zhang, et al. Image Guarder: An Intelligent Detectorfor Adult Images. Asian Conference on Computer Vision. Jeju Island, Korea,2004:198–203
21曾炜,郑清芳,赵德斌.图片卫士:一个自动成人图像识别系统.高技术通讯. 2005, 15(3):11–16
22 Q. Zheng, W. Zeng, W. Gao, et al. Shape-based Adult Image Classification.The Third International Conference on Image and Graphics. Hong Kong, China,2004:150–153
23 Q. Zheng, M. Zhang, W. Wang. A Hybrid Approach to Detect Adult Web Im-ages. The 5th Pacific Rim Conference on Multimedia. Tokyo, Japan, 2004:609–616
24 R. Schettini, C. Brambilla, C. Cusano, et al. On the Detection of PornographicDigital Images. Visual Communications and Image Processing. Lugano,Switzerland, 2003:2105–2113
25 W. Arentz, B. Olstad. Classifying Offensive Sites Based on Image Content.Computer Vision and Image Understanding. 2004, 94(1–3):295–310
26 C. Y. Jeong, J. S. Kim, K. S. Hong. Appearance-based Nude Image Detec-tion. 17th International Conference on Pattern Recognition. Cambridge, UK,2004:467–470
27 C. Y. Jeong, S. W. Han, S. G. Choi, et al. An Objectionable Image DetectionSystem Based on Region of Interest. IEEE International Conference on ImageProcessing. Atlanta, Georgia, USA, 2006:1477–1480
28 J. Shih, C. Lee, C. Yang. An Adult Image Identification System EmployingImage Retrieval Technique. Pattern Recognition Letters. 2007, 28(16):2367–2374
29 H. A. Rowley, Y. Jing, S. Baluja. Large Scale Image-based Adult-content Fil-tering. International Conference on Computer Vision Theory and Applications.Setubal, Portugal, 2006:25–28
30 Y. Liu, W. Zeng, H. Yao. Online Learning Objectionable Image Filter Basedon SVM. The 5th Pacific Rim Conference on Multimedia. Tokyo, Japan,2004:304–311
31 H. Zhu, S. Zhou, J. Wang, et al. An Algorithm of Pornographic Image Detec-tion. Fourth International Conference on Image and Graphics. Chengdu, China,2007:801–804
32 Y. Wu, E. Y. Chang, K. Cheng, et al. Morf: A Distributed Multimodal Infor-mation Filtering System. Third IEEE Pacific Rim Conference on Multimedia.Hsinchu, Taiwan, China, 2002:279–286
33 L. Spyros, T. Georgios. Color and Texture Image Retrieval Using ChromaticityHistograms and Wavelet Frames. IEEE Transactions on Multimedia. 2004,6(5):676–686
34 T. Amin, M. Zeytinoglu, L. Guan. Application of Laplacian Mixture Modelto Image and Video Retrieval. IEEE Transactions on Multimedia. 2007,9(7):1416–1429
35 A. Vailaya, M. Figueiredo, A. Jain, et al. Image Classification for Content-basedIndexing. IEEE Transactions on Image Processing. 2001, 10(1):117–130
36 A. Oliva, A. Torralba. Modeling the Shape of the Scene: A Holistic Represen-tation of the Spatial Envelope. International Journal of Computer Vision. 2001,42(3):145–175
37 A. Kanaujia, C. Sminchisescu, D. Metaxas. Spectral Latent Variable Modelsfor Perceptual Inference. Eleventh IEEE International Conference on ComputerVision. Rio de Janeiro, Brazil, 2007:1–8
38 E. Hadjidemetriou, M. Grossberg, S. Nayar. Multiresolution Histograms andTheir Use for Recognition. IEEE Transactions on Pattern Analysis and MachineIntelligence. 2004, 26(7):831–847
39 C. Fredembach, M. Schroder, S. Susstrunk. Eigenregions for Image Classifica-tion. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2004,26(12):1645–1649
40 A. Torralba, K. P. Murphy, W. T. Freeman. Sharing Visual Features for Multi-class and Multiview Object Detection. IEEE Transactions on Pattern Analysisand Machine Intelligence. 2007, 29(5):854–869
41 S. Gangaputra, D. Geman. Spectral Latent Variable Models for Perceptual In-ference. IEEE Conference on Computer Vision and Pattern Recognition. NewYork, USA, 2006:1877–1884
42 R. O. Duda, P. E. Hart, D. G. Stork原著,李宏东,姚天翔译.模式分类.机械工业出版社, 2003:385–386
43 K. Tieu, P. Viola. Boosting Image Retrieval. International Journal of ComputerVision. 2004, 56(1-2):17–36
44 Y. Gao, J. Fan, X. Xue, et al. Automatic Image Annotation by IncorporatingFeature Hierarchy and Boosting to Scale-up SVM Classifier Training. 14thACM International Conference on Multimedia. Santa Barbara, USA, 2006:901–910
45 W. Jiang, G. Er, Q. Dai, et al. Similarity-based Online Feature Selection inContent-based Image Retrieval. IEEE Transactions on Image Processing. 2006,15(3):702–712
46 M. Naphade, T. Huang. A Probabilistic Framework for Semantic Video Index-ing, Filtering and Retrieval. IEEE Transaction on Multimedia. 2001, 3(1):141–
15147 N. Serrano, A. Savakis, J. Luo. A Computationally Efficient Approach to In-door/outdoor Scene Classification. Proceeding of International Conference onPattern Recognition. Quebec, Canada, 2002:146–149
48 J. Vogel, B. Schiele. Natural Scene Retrieval Based on a Semantic ModelingStep. Proceeding of International Conference on Image and Video Retrieval.Dublin, Ireland, 2004:207–215
49 L. Lu, K. Toyama, G. D. Hager. A Two Level Approach for Scene Recog-nition. IEEE Conference on Computer Vision and Pattern Recognition. SanDiego, USA, 2005:688–695
50 B. Epshtein, S. Ullman. Identifying Semantically Equivalent Object Fragments.IEEE Conference on Computer Vision and Pattern Recognition. San Diego,USA, 2005:2–9
51 B. Epshtein, S. Ullman. Feature Hierarchies for Object Classification. TenthIEEE International Conference on Computer Vision. Beijing, China, 2005:220–227
52 G. Bouchard, B. Triggs. Hierarchical Part-based Visual Object Categorization.IEEE Conference on Computer Vision and Pattern Recognition. San Diego,USA, 2005:710–715
53 S. Fidler, A. Leonardis. Towards Scalable Representations of Object Categories:Learning a Hierarchy of Parts. IEEE Conference on Computer Vision and Pat-tern Recognition. Minneapolis, USA, 2007:1–8
54 D. Zhang, S. Chang. A Generative-discriminative Hybrid Method for Multi-view Object Detection. IEEE Conference on Computer Vision and PatternRecognition. New York, USA, 2006:2017–2024
55 R. Fergus, P. Perona, A. Zisserman. Object Class Recognition by UnsupervisedScale Invariant Learning. IEEE Conference on Computer Vision and PatternRecognition. Madison, USA, 2003:264–271
56 G. Dorko, C. Schmid. Selection of Scale Invariant Parts for Object Class Recog-nition. Ninth IEEE International Conference on Computer Vision. Nice, France,2003:634–639
57 A. Bar-Hillel, T. Hertz, D. Weinshall. Object Class Recognition by Boosting aPart Based Model. IEEE Conference on Computer Vision and Pattern Recogni-tion. San Diego, USA, 2005:702–709
58 G. Carneiro, D. G. Lowe. Sparse Flexible Models of Local Features. 9th Euro-pean Conference on Computer Vision. Graz, Austria, 2006:29–43
59 Z. Zha, X. Hua, T. Mei, et al. Joint Multi-label Multi-instance Learning for Im-age Classification. IEEE Conference on Computer Vision and Pattern Recogni-tion. Anchorage, USA, 2008:1–8
60 O. Boiman, E. Shechtman, M. Irani. In Defense of Nearest-neighbor Based Im-age Classification. IEEE Conference on Computer Vision and Pattern Recogni-tion. Anchorage, USA, 2008:1–8
61 A. Bosch, A. Zisserman, X. Munoz. Scene Classification via Plsa. 9th EuropeanConference on Computer Vision. Graz, Austria, 2006:517–530
62 A. Bosch, A. Zisserman, X. Muoz. Image Classification Using Random Forestsand Ferns. Eleventh IEEE International Conference on Computer Vision. Riode Janeiro, Brazil, 2007:1–8
63 D. G. Lowe. Distinctive Image Features from Scale-invariant Keypoints. Inter-national Journal of Computer Vision. 2004, 60(2):91–110
64 K. Mikolajczyk, B. Leibe, B. Schiele. Local Features for Object Class Recogni-tion. Tenth IEEE International Conference on Computer Vision. Beijing, China,2005:1792–1799
65 T. Kadir, A. Zisserman, M. Brady. An Affine Invariant Salient Region Detec-tor. 8th European Conference on Computer Vision. Prague, Czech Republic,2004:228–241
66 P. K. Bocher, K. R. McCloy. The Fundamentals of Average Local Variance -Part I: Detecting Regular Patterns. IEEE Transactions on Image Processing.2006, 15(2):300–310
67 L. Szumilas, R. Donner, G. Langs, et al. Local Structure Detection withOrientation-invariant Radial Configuration. IEEE Conference on Computer Vi-sion and Pattern Recognition. Minneapolis, USA, 2007:1–7
68 F. Jing, M. Li, H. Zhang, et al. An Efficient and Effective Region-based Im-age Retrieval Framework. IEEE Transactions on Image Processing. 2004,13(5):699–709
69 A. C. Berg, T. L. Berg, J. Malik. Shape Matching and Object Recognition UsingLow Distortion Correspondences. IEEE Conference on Computer Vision andPattern Recognition. San Diego, USA, 2005:26–33
70 A. Diplaros, T. Gevers, I. Patras. Combining Color and Shape Information forIllumination-viewpoint Invariant Object Recognition. IEEE Transactions onImage Processing. 2006, 15(1):1–11
71 H. Ling, D. W. Jacobs. Deformation Invariant Image Matching. Tenth IEEE In-ternational Conference on Computer Vision. Beijing, China, 2005:1466–1473
72 J. C. van Gemert, J. Geusebroek, C. J. Veenman, et al. Robust Scene Cat-egorization by Learning Image Statistics in Context. Proceedings of the 2006Conference on Computer Vision and Pattern Recognition Workshop. New York,USA, 2006:105–112
73 A. E. Abdel-Hakim, A. A. Farag. CSIFT: A SIFT Descriptor with Color Invari-ant Characteristics. IEEE Conference on Computer Vision and Pattern Recog-nition. New York, USA, 2006:1978–1983
74 C. A. Murthy, S. K. Naik. Distinct Multicolored Region Descriptors for ObjectRecognition. IEEE Transactions on Pattern Analysis and Machine Intelligence.2007, 29(7):1291–1296
75 B. Ommer, J. M. Buhmann. Learning Compositional Categorization Models.9th European Conference on Computer Vision. Graz, Austria, 2006:316–329
76 C. Schmid. Weakly Supervised Learning of Visual Models and its Applicationto Content-based Retrieval. International Journal of Computer Vision. 2004,56(1-2):7–16
77 B. Ommer, J. M. Buhmann. Object Categorization by Compositional GraphicalModels. The 5th International Workshop on Energy Minimization Methods inComputer Vision and Pattern Recognition. Augustine, USA, 2005:235–250
78 K. Mikolajczyk, B. Leibe, B. Schiele. Multiple Object Class Detection with aGenerative Model. IEEE Conference on Computer Vision and Pattern Recog-nition. New York, USA, 2006:26–36
79 B. Leibe, A. Leonardis, B. Schiele. Robust Object Detection with InterleavedCategorization and Segmentation. International Journal of Computer Vision.2008, 77(1-3):259–289
80 F. Perronnin, C. R. Dance, G. Csurka, et al. Adapted Vocabularies for GenericVisual Categorization. 9th European Conference on Computer Vision. Graz,Austria, 2006:464–475
81 S. Lazebnik, C. Schmid, J. Ponce. Affine-invariant Local Descriptors andNeighborhood Statistics for Texture Recognition. Ninth IEEE InternationalConference on Computer Vision. Nice, France, 2003:649–655
82 D. Nister, H. Stewenius. Scalable Recognition with a Vocabulary Tree. IEEEConference on Computer Vision and Pattern Recognition. New York, USA,2006:2161–2168
83 E. Nowak, F. Jurie. Learning Visual Similarity Measures for Comparing NeverSeen Objects. IEEE Conference on Computer Vision and Pattern Recognition.Minneapolis, USA, 2007:1–8
84 E. Nowak, F. Jurie, B. Triggs. Sampling Strategies for Bag-of-features ImageClassification. 9th European Conference on Computer Vision. Graz, Austria,2006:490–503
85 A. Opelt, M. Fussenegger, A. Pinz, et al. Weak Hypotheses and Boosting forGeneric Object Detection and Recognition. 8th European Conference on Com-puter Vision. Prague, Czech Republic, 2004:71–84
86 J. Winn, A. Criminisi, T. Minka. Object Categorization by Learned UniversalVisual Dictionary. Tenth IEEE International Conference on Computer Vision.Beijing, China, 2005:1800–1807
87 G. Csurka, C. R. Dance, L. Fan, et al. Visual Categorization with Bags of Key-points. Workshop on Statistical Learning in Computer Vision of 8th EuropeanConference on Computer Vision. Prague, Czech Republic, 2004:1–22
88 M. Marszaek, C. Schmid. Spatial Weighting for Bag-of-features. IEEEConference on Computer Vision and Pattern Recognition. New York, USA,2006:2118–2125
89 M. Marszalek, C. Schmid. Semantic Hierarchies for Visual Object Recognition.IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis,USA, 2007:1–7
90 W. Jiang, K. L. Chan, M. Li, et al. Mapping Low-level Features to High-levelSemantic Concepts in Region-based Image Retrieval. IEEE Conference onComputer Vision and Pattern Recognition. San Diego, USA, 2005:244–249
91 J. Sivic, B. C. Russell, A. A. Efros, et al. Discovering Objects and Their Lo-cation in Images. Tenth IEEE International Conference on Computer Vision.Beijing, China, 2005:370–377
92 T. Hofmann. Unsupervised Learning by Probabilistic Latent Semantic Analysis.Machine Learning. 2001, 42(1-2):177–196
93 P. Quelhas, F. Monay, J. M. Odobez, et al. A Thousand Words in Scene. IEEETransactions on Pattern Analysis and Machine Intelligence. 2007, 29(9):1575–1589
94 R. Zhang, Z. Zhang. Effective Image Retrieval Based on Hidden Concept Dis-covery in Image Database. IEEE Transactions on Image Processing. 2007,16(2):562–572
95 L. Fei-Fei, P. Perona. A Bayesian Hierarchical Model for Learning NaturalScene Categories. IEEE Conference on Computer Vision and Pattern Recogni-tion. San Diego, USA, 2005:524–531
96 D. Blei, A. Ng, M. Jordan. Latent Dirichlet Allocation. Journal of MachineLearning Research. 2003, 3(7):993–1022
97 L.-J. Li, L. Fei-Fei. What, Where and Who Classifying Events by Scene andObject Recognition. Eleventh IEEE International Conference on Computer Vi-sion. Rio de Janeiro, Brazil, 2007:1–8
98 G. Wang, Y. Zhang, L. Fei-Fei. Using Dependent Regions for Object Catego-rization in a Generative Framework. IEEE Conference on Computer Vision andPattern Recognition. New York, USA, 2006:1597–1604
99 L.-J. Li, G. Wang, L. Fei-Fei. OPTIMOL: Automatic Online Picture Collectionvia Incremental Model Learning. IEEE Conference on Computer Vision andPattern Recognition. Minneapolis, USA, 2007:1–8
100 N. Rasiwasia, N. Vasconcelos. Scene Classification with Low-dimensional Se-mantic Spaces and Weak Supervision. IEEE Conference on Computer Visionand Pattern Recognition. Anchorage, USA, 2008:1–6
101 S. Nowozin, K. Tsuda, T. Uno, et al. Weighted Substructure Mining for Im-age Analysis. IEEE Conference on Computer Vision and Pattern Recognition.Minneapolis, USA, 2007:1–8
102 S. Savarese, J. Winn, A. Criminisi. Discriminative Object Class Models ofAppearance and Shape by Correlations. IEEE Conference on Computer Visionand Pattern Recognition. New York, USA, 2006:2033–2040
103 J. Malik, S. Belongie, J. Shi, et al. Textons, Contours and Regions: Cue Integra-tion in Image Segmentation. 7th IEEE International Conference on ComputerVision. Kerkyra, Greece, 1999:918–925
104 W. Zhang, H. Deng, T. G. Dietterich, et al. A Hierarchical Object RecognitionSystem Based on Multi-scale Principal Curvature Regions. 18th InternationalConference on Pattern Recognition. Hong Kong, China, 2006:778–782
105 S. Agarwal, A. Awan, D. Roth. Learning to Detect Objects in Images via aSparse, Part-based Representation. IEEE Transactions on Pattern Analysis andMachine Intelligence. 2004, 26(11):1475–1490
106 D. Liu, G. Hua, P. Viola, et al. Integrated Feature Selection and Higher-orderSpatial Feature Extraction for Object Categorization. IEEE Conference onComputer Vision and Pattern Recognition. Anchorage, USA, 2008:1–8
107 J. Yuan, Y. Wu, M. Yang. Discovery of Collocation Patterns: From VisualWords to Visual Phrases. IEEE Conference on Computer Vision and PatternRecognition. Minneapolis, USA, 2007:1–8
108 Y. Zheng, M. Zhao, S. Neo, et al. Visual Synset: Towards a Higher-level VisualRepresentation. IEEE Conference on Computer Vision and Pattern Recognition.Anchorage, USA, 2008:1–8
109 Q. Zheng, W. Wang, W. Gao. Effective and Efficient Object-based Image Re-trieval Using Visual Phrases. 14th ACM International Conference on Multime-dia. Santa Barbara, USA, 2006:77–80
110 A. Agarwal, B. Triggs. Hyperfeatures: Multilevel Local Coding for VisualRecognition. 9th European Conference on Computer Vision. Graz, Austria,2006:30–43
111 B. Ommer, J. M. Buhmann. Learning the Compositional Nature of Visual Ob-jects. IEEE Conference on Computer Vision and Pattern Recognition. Min-neapolis, USA, 2007:1–8
112 O. Chum, A. Zisserman. An Exemplar Model for Learning Object Classes.IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis,USA, 2007:1–8
113 K. Grauman, T. Darrell. Approximate Correspondences in High Dimensions.The 20th Annual Conference on Neural Information Processing Systems. Van-couver, Canada, 2006:505–512
114 J. Shawe-Taylor and N. Cristianini. Kernel Methods for Pattern Analysis. Cam-bridge University Press, 2004:211–230, 63–66, 74–79
115 C. Wallraven, B. Caputo, A. Graf. Recognition with Local Features: The Ker-nel Recipe. Ninth IEEE International Conference on Computer Vision. Nice,France, 2003:257–264
116 S. Lyu. Mercer Kernels for Object Recognition with Local Features. IEEEConference on Computer Vision and Pattern Recognition. San Diego, USA,2005:223–229
117 H. Sahbi, J. Audibert. Context-dependent Kernel Design for Object Matchingand Recognition. IEEE Conference on Computer Vision and Pattern Recogni-tion. Anchorage, USA, 2008:1–8
118 L. Wolf, A. Shashua. Learning Over Sets Using Kernel Principal Angles. Jour-nal of Machine Learning Research. 2003, 4(10):913–931
119 R. Kondor, T. Jebara. A Kernel between Sets of Vectors. International Confer-ence on Machine Learning. Washington, D.C., USA, 2003:361–368
120 P. Moreno, P. Ho, N. Vasconcelos. A Kullback-leibler Divergence Based Ker-nel for SVM Classification in Multimedia Applications. The 17th AnnualConference on Neural Information Processing Systems. Vancouver, Canada,2003:1385–1392
121 Y. Liu, F. Perronnin. A Similarity Measure between Unordered Vector Sets withApplication to Image Categorization. IEEE Conference on Computer Visionand Pattern Recognition. Anchorage, USA, 2008:1–8
122 G. Qi, X. Hua, Y. Rui. A Joint Appearance-spatial Distance for Kernel-basedImage Categorization. IEEE Conference on Computer Vision and PatternRecognition. Anchorage, USA, 2008:1–8
123 K. Grauman, T. Darrell. The Pyramid Match Kernel: Efficient Learning withSets of Features. Journal of Machine Learning Research. 2007, 8(4):725–760
124 S. Lazebnik, C. Schmid, J. Ponce. Beyond Bags of Features: Spatial Pyra-mid Matching for Recognizing Natural Scene Categories. IEEE Conference onComputer Vision and Pattern Recognition. New York, USA, 2006:2169–2176
125 A. Kapoor, J. Winn. Located Hidden Random Fields: Learning Discrimina-tive Parts for Object Detection. 9th European Conference on Computer Vision.Graz, Austria, 2006:302–315
126 J. Yuan, J. Li, B. Zhang. Exploiting Spatial Context Constraints for AutomaticImage Region Annotation. 15th ACM International Conference on Multimedia.Augsburg, Germany, 2007:595–604
127 A. Rabinovich, A. Vedaldi, C. Galleguillos, et al. Objects in Context. EleventhIEEE International Conference on Computer Vision. Rio de Janeiro, Brazil,2007:1–8
128 P. Carbonetto, G. Dorko, C. Schmid, et al. Learning to Recognize Objectswith Little Supervision. International Journal of Computer Vision. 2008, 77(1-3):219–237
129 J. Yuan, J. Li, B. Zhang. Scene Understanding with Discriminative StructuredPrediction. IEEE Conference on Computer Vision and Pattern Recognition.Anchorage, USA, 2008:1–8
130 G. Pass, R. Zabih, J. Miller. Comparing Images Using Color Coherence Vec-tors. The Fourth ACM International Conference on Multimedia. Boston, USA,1996:65–73
131 P. Kakumanu, S. Makrogiannis, N. Bourbakis. A Survey of Skin-color Model-ing and Detection Methods. Pattern Recognition. 2007, 40(3):1106–1122
132 P. Viola, M. Jones. Rapid Object Detection Using a Boosted Cascade of Sim-ple Features. IEEE Conference on Computer Vision and Pattern Recognition.Kauai, USA, 2001:511–518
133 T. Ojala, M. Pietikainen, T. Maenpaa. Multiresolution Gray-scale and RotationInvariant Texture Classification with Local Binary Patterns. IEEE Transactionson Pattern Analysis and Machine Intelligence. 2002, 24(7):971–987
134 K. Mikolajczyk, C. Schmid. A Performance Evaluation of Local Descrip-tors. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2005,27(10):1615–1630
135 M. Sonka, V. Hlavac, R. Boyle原著,艾海舟,武勃译.图像处理、分析与机器视觉.人民邮电出版社, 2003:110–116
136 T. Deselaers, L. Pimenidis, H. Ney. Bag-of-visual-words Models for AdultImage Classification and Filtering. 19th International Conference on PatternRecognition. Tampa, USA, 2008:1–4
137 B. Liu, Y. Xia, P. S. Yu. Clustering Through Decision Tree Construction.The 9th International Conference on Information and Knowledge Management.McLean, USA, 2000:20–29
138 A. Webb. Statistical Pattern Recognition. 2nd edn. John Wiley and Sons Inc,2002:106–113
139 M. Figueiredo, A. Jain. Unsupervised Learning of Finite Mixture Models. IEEETransactions on Pattern Analysis and Machine Intelligence. 2002, 24(3):381–396
140 J. Yu, Q. Tian. Learning Image Manifolds by Semantic Subspace Projection.The 14th ACM International Conference on Multimedia. Santa Barbara, USA,2006:297–306
141 D. Swets, J. Weng. Using Discriminant Eigenfeatures for Image Retrieval. IEEETransactions on Pattern Analysis and Machine Intelligence. 1996, 18(8):831–836
142 I. H. Witten, E. Frank. Data Mining: Practical Machine Learning Tools andTechniques. 2nd edn. Morgan Kaufmann, 2005:291
143 H. Zhang, A. C. Berg, M. Maire, et al. SVM-KNN: Discriminative NearestNeighbor Classification for Visual Category Recognition. The 2006 IEEE Com-puter Society Conference on Computer Vision and Pattern Recognition. NewYork, USA, 2006:2126–2136
144 K. Grauman, T. Darrell. Approximate Correspondences in High Dimensions.The 20th Annual Conference on Neural Information Processing Systems. Van-couver, Canada, 2006:505–512
145 F. Odone, A. Barla, A. Verri. Building Kernels from Binary Strings for ImageMatching. IEEE Transaction on Image Processing. 2005, 14(2):169–180
146 C. Chang, C. Lin. LIBSVM : A Library for Support Vector Machines. http://www.csie.ntu.edu.tw/～cjlin/libsvm. 2001
147 F. Li, R. Fergus, P. Perona. Learning Generative Visual Models from Few Train-ing Examples: An Incremental Bayesian Approach Tested on 101 Object Cate-gories. Computer Vision and Image Understanding. 2007, 106(1):59–70
148 D. Jacobs, D. Weinshall, Y. Gdalyahu. Classification with Nonmetric Distances:Image Retrieval and Class Representation. IEEE Transactions on Pattern Anal-ysis and Machine Intelligence. 2000, 22(6):583–600– 114–