摘要
图像含有比文本更为丰富的信息，在人们日常生活中发挥着重要作用。近年来由于因特网技术的发展及各种消费型电子产品的普及，每天都有巨量的数字图像产生和发布。在多媒体数据库中快速、有效地寻找所需要的图像是一个非常有意义的课题。目前工业界的许多图像搜索引擎(如Google~(TM)和百度~(TM))在搜索图像时并没有按照图像内容本身来搜索，而是根据与图像相关联的文字信息来完成搜索任务。导致搜索结果不尽如人意。基于内容的图像检索是有望解决这一问题的关键技术。本文对这一技术中的几个问题进行了研究，取得了如下结果：
纹理特征是图像检索中广泛使用的重要底层视觉特征。本文将图像纹理视为非线性动力系统产生的信号，使用2种非线性信号分析方法-复杂性方法和希尔伯特-黄变换(HHT)方法来提取图像的纹理特征并将之用于纹理图像检索。得出的结果有：(1)将时间序列复杂性方法用于图像纹理分析与检索。所做的工作和得到的结论是：比较了8种时间序列复杂性方法用于图像检索时的性能，发现基于符号动力学和基于熵的方法不适于图像检索；基于频谱分析的CO复杂性特征适于图像检索，该特征的检索性能与二维图像一维化的扫描方法有关；实验表明采用Hilbert扫描方式的CO复杂性特征在Brodatz纹理库上取得了和Gabor特征极为接近的检索结果，计算特征所需要的时间比Gabor特征少了一个数量级；由图像阈值化算法得到启发，提出了一个新的一维时间序列粗粒化框架；提出了多种基于二维CO复杂性测度的纹理特征：复杂度直方图和多尺度复杂度直方图、复杂度共生矩阵、复杂度纹理谱和多尺度复杂性特征；实验表明基于金字塔分解的多尺度复杂性特征在不同的实验图像库上检索性能稳定，是一种较好的纹理特征；(2)将希尔伯特-黄变换方法用于图像纹理分析与检索，所做的工作和得到的结论是：提出了一种新的基于聚类的边界处理算法以改善经验模式分解(EMD)方法所产生的边界效应问题；使用二维Hilbert变换计算了内禀模态函数(IMF)的幅值作为检索用的图像纹理特征。实验表明，提出的HHT特征可以取得和Gabor特征较为接近的图像检索结果。
图像的显著性区域是表达图像语义的主要部分。本文尝试使用一个基于视觉生理和心理物理实验基础的选择性视觉注意计算模型用于自然图像检索的研究。所做的工作和得到的结果是：(1)使用视觉注意计算模型计算了图像中的兴趣点并提取兴趣点周围的局部特征用于图像检索。提出的检索特征有图像的显著性直方图特征、图像的显著性标签和注意焦点(FOA)空间关系直方图特征。实验结果表明显著性标签和FOA空间关系混合编码的直方图特征可以取得比全局直方图特征更好的检索结果；在采用视觉注意计算模型计算得到的图像显著性区域上提取的一些区域特征可以取得比全局特征更好的检索结果；(2)提出了将潜在语义标引方法和视觉注意计算模型结合起来用于自然图像检索的方法；(3)提出了在多示例学习框架下基于视觉注意计算模型和JSEG图像分割算法的包生成器方法，并将其用于自然图像检索。图像检索实验表明基于JSEG分割算法的包生成器取得了比一些文献中提出的包生成器更好的实验结果。
本文提出了“图像语义阈值”的新概念及其度量方法。通过计算机实验和心理物理学实验初步得到如下结论：在自然图像认知或理解时存在一个语义阈值；可以通过图像的图像熵和图像分维数及类似Weber律的方法来度量该阈值；差别阈限图像及其原始图像的度量值的比值与图像语义内容无关，而和色彩模式(彩色或灰度)及图像的变换方法相关。
本文作者还设计与开发成功了一个图像检索实验平台。使用该平台方便了研究者进行图像检索实验研究，提高了工作效率，便于他们之间进行学术交流。这项工作具有一定的应用价值。
A picture is worth a thousand words. Images play a very important role in human daily activities. Recently with the development of the Internet technology and popularization of the consumer electronic devices(such as mobile phone, digital camera, etc.), enormous digital images are created, distributed and shared everyday. It is a challengable task to search images rapidly and efficiently in all kinds of multimedia image databases. However, most of current image search engines(such as Google~(TM) and Baidu~(TM)) search images not by images' contents, but by texts related to them(for example, texts related to images in a web page), which leads to the poor retrieval accuracy. Content-based image retdeval(CBIR) is the key technique to solve the problem that is how to retrieve useful information within enormous amount of digital images. In this paper, several issues were studied.
Image texture feature is a widely used low-level visual feature in CBIR society. In this paper, image texture was regarded as the signal generated by non-linear dynamic systems. Two non-linear signal analysis approaches, whose names are time series complexity approach and the Hilbert-Huang Transform(HHT), were used to extract the texture feature from images. The extracted texture features were used for image retrieval experiments.
The time series complexity approach was applied to image retrieval. Following conclusions were drawed: Image retrieval results were compared based on eight different time series complexity algorithms, which leaded to a conclusion that symbol dynamic-based and entropy-based complexity algorithms are not suitable for image retrieval. A complexity approach named CO complexity, which is based on Fourier spectrum analysis, is suitable for image retrieval. The CO complexity-based retrieval results are relevant to the scanning methods which convert image from two-dimensional structure to one-dimensional time seres form. Experimental results showed that the retrieval accuracy based on CO complexity algorithm with Hilbert scanning method is comparable to that based on Gabor feature, which is an excellent texture feature in image retrieval. Moreover, consuming time to extract the CO complexity-based texture feature is far shorter than that of the Gabor-based texture feature.
Motivated by the image binarized algorithms, a novel time series coarse graining framework was proposed.
Several texture features based on 2D-CO complexity measurement were proposed, whose names were complexity histogram and multi-scale complexity histogram, complexity co-occurrence matrix, complexity texture spectrum and multi-scale complexity feature. Experimental results showed that multi-scale complexity feature based on pyramid decomposition is a favourable texture feature.
The approach of texture image decomposition and texture feature extraction based on HHT, which can decompose the image into a set of functions denoted Intrinsic Mode Functions(IMF) and a residue, was presented. The extracted features were used for texture image retrieval. The Bidimensional Empirical Mode Decomposition(BEMD) method was used to decompose the texture image, the features extracted were the mean and standard deviation of the amplitude of the IMFs and their Hilbert transformations. Furthermore, according to the spatial relationship between local extrema points, a novel boundary processing approach based on clustering algorithm was proposed. Preliminary comparision experimental results showed that the texture image retrieval results based on HHT were encouraged.
Salient region of the natural image is the main part to describe the image semantic, which is called ROI(region of interesting). In this paper, a saliency-based bottom-up visual attention computational model which was motivated by visual physiological and psychophysical experimental results was used for natural image retrieval.
Interesting points in natural images were selected by using the visual attention computational model. Furthermore, local features around the interesting points were computed for natural image retrieval. The proposed local salient features were called image salient histogram, image salient signature and focus of attention(FOA) spatial relationship histogram. Experimental results showed that salient local feature which combine salient signature and FOA spatial relationship histogram can achieve better retrieval accuracy than global feature.
In this paper, natural image retrieval approach based on visual attention computational model and latent semantic indexing was also proposed.
Multi-instance learning(MIL) is a new machine learning framework which has the ability of "learning from ambiguity". MIL may be a hopeful approach to solve the difficult "semantic gap" problem in image retrieval. Designing good bag generator is an important problem in MIL. Two novel bag generators based on visual attention computational model and an effficient image segmentation algorithm whose name is JSEG were proposed. Natural image retrieval experiments were carded based on MIL and these two bag generators. Experimental results showed that bag generator based on JSEG algorithm can achieve better retrieval results than other bag generators introduced in some literatures.
The image perception threshold and its metric approach was proposed. Problem of the image perception threshold was studied on a natural image database based on image color/gray mode and different image transformation approaches by using computer and psychophysical experiments. The image transformation approaches used were scale transformation, Gaussian noise transformation and motion blurred transformation. According to the preliminary experimental results, following conclusions were drawed: There exists a perception threshold when human perceive the natural images. The image perception threshold can be measured by image entropy and image fractal dimension number. There exists a law similar with the Weber's law when human perceive the natural images. The ratio of metric of the difference image to that of the original image is independent of the image content and is relevant to both image color/gray mode and image transformation approaches.
A general-purpose image retrieval experimental platform was also developed. Reseachers can use this platform not only to carry out all kinds of image retrieval experiments without any coding, but also do academic intercommunion conveniently. This platform is very useful for image retrieval study.
引文
[1] 杨雄里．视觉的神经机制[M]．上海：上海科学技术出版社，1996．
[2] Google image search[EB/OL]. [2006-12-02]. http://images.google.com/.
[3] 百度图像搜索引擎[EB/OL]. [2006-12-02]. http://image.baidu.com/.
[4] Lycos image search[EB/OL]. [2006-12-02]. http://multimedia.lycos.com/.
[5] Alta Vista photo finder[EB/OL]. [2006-12-02]. http://image.altavista.com/.
[6] Smeulders A W M, Worring M, Santini S. Content-Based Image Retrieval at the End of the Early Years[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2000, 22(12): 1349-1380.
[7] Kheffi M L, Ziou D, Bernardi A. Image Retrieval From the World Wide Web: Issues, Techniques, and Systems[J]. ACM Computing Surveys, 2004, 36 (1): 35-67.
[8] Rui Y, Huang T S, Chang S F. Image Retrieval: Current Techniques, Promising Directions, and Open Issues[J]. Journal of Visual Communication and Image Representation, 1999, 10: 39-62.
[9] Datta R, Li J, Wang J Z. Content-Based Image Retrieval-Approaches and Trends of the New Age[A]. Proceeding of International Workshop on Multimedia Information Retrieval, ACM, November 11-12, Singapore, 2005, pp. 253-262.
[10] 章毓晋．基于内容的视觉信息检索[M]．北京：科学出版社，2003．
[11] 庄越挺，潘云鹤，吴飞．网上多媒体信息分析与检索[M]．北京：清华大学出版社，2002．
[12] Lew M S, Sebe N, Eakins J P. Challenges of Image and Video Retrieval[A]. Proceedings of the International Conference on Image and Video Retrieval (CIVR 2002), London, UK, July 18-19, 2002. Lecture Notes in Computer Science, Vol. 2383: 1-6.
[13] 万华林．图像检索中高层语义和低层可视特征的提取研究[D]．北京：中国科学院计算技术研究所，2002．
[14] 张磊．基于内容的图像检索中人机协同问题的研究[D]．北京：清华大学，2001．
[15] 唐立军．基于内容的图像检索系统研究和设计[D]．北京：中国科学院计算技术研究所，2001．
[16] 白雪生．基于内容检索及其相关技术的研究[D]．北京：清华大学，1998．
[17] Gentili S. Retrieving Visual Concepts in Image Databases[D]. Udine, Italy: University of Udine, 2003.
[18] Zachary J M. An Information Theoretic Approach to Content Based Image Retrieval[D]. Louisiana State University, 2000.
[19] Rui Y, Huang T S, Mehrotra S. Content-Based Image Retrieval with Relevance Feedback in MARS[A]. IEEE International Conference on Image Processing, 1997, pp. 815-818.
[20] Zhou X S, Huang T S. Relevance Feedback in Image Retrieval: A Comprehensive Review[J]. ACM Multimedia Systems Journal (Special Issue on CBIR), 2003, 8 (6): 536-544.
[21] Crucianu M, Ferecatu M, Boujemaa N. Relevance Feedback for Image Retrieval: A Short Survey[EB/OL]. [2006-12-17]. http://www-rocq.inda.fr/～crucianu/src/ShortSurveyRF.pdf.
[22] YouTube[EB/OL]. [2006-12-02]. http://www.youtube.com/.
[23] 六间房网站[EB/OL]. [2006-12-02]. http://www.6rooms.com/.
[24] Kheffi M L, Ziou D, Brahmi D. Atlas WISE: A Web-Based image Retrieval Engine[A]. Proceedings of the International Conference on Image and Signal Processing, 2003, pp. 69-77.
[25] Kherfi M L, Ziou D, Bernardi A. Web Image Search Engines: A Survey[EB/OL].[2006-12-17]. http://www.usherbrooke.ca/informatique/personnel/profs/DZiou.html.
[26] Ahmad I, Kiranyaz S, Gabbouj M. An Efficient Image Retrieval Scheme on Java Enabled Mobile Devices[A]. IEEE 7th Workshop on Multimedia Signal Processing, 2005, pp. 1-4.
[27] Guldogan O, Gabbouj M. Content-based image indexing and retrieval framework on symbian based mobile platform[EB/OL]. [2006-12-17].http://www.ee.bilkent.edu.tr/～signal/defevent/papers/cr1992.pdf.
[28] Dietrich M E. Picture archiving and communication systems (PACS) for medical application[J]. International Journal of Biomedical Computing, 1994, 35 (2): 91-124.
[29] 邱峰，田捷，曹勇等．PACS系统综述[J]．中国医学影像技术，2000，16(1)：73-75．
[30] Jones B F, Schaefer G, Zhu S Y. Content-based image retrieval for medical infrared images[A]. Proceedings of the 26th Annual International Conference of the IEEE EMBS, San Francisco, Calfonia, USA. September 1-5, 2004, pp. 1186-1187.
[31] Sub E B, Warach S, Cheung H. A Web-Based Medical Image Archive System[A]. Proceedings of SPIE on Medical Imaging: PACS and Integrated Medical Information Systems: Design and Evaluation, 2002, Vol. 4685: 31-41.
[32] Cross Language Evaluation Forum Campaign, CLEF[EB/OL]. [2006-12-02]. http://ir.shef.ac.uk/imageclef/.
[33] Jain A K, Vailaya A. Shape-Based Retrieval: A Case Study with Trademark Image Databases[J]. Pattern Recognition, 1998, 31 (9): 1369-1390.
[34] Forsyth D A, Fleck M M. Automatic Detection of Human Nudes[J]. International Journal of Computer Vision, 1999, 32 (1): 63-77.
[35] Li J, Wang J Z. Studying Digital Imagery of Ancient Paintings by Mixtures of Stochastic Models[J]. IEEE Transactions on Image Processing, 2004, 13 (3): 340-353.
[36] Csillaghy A, Hinterberger H, Benz A O. Content-Based Image Retrieval in Astronomy[J]. Information Retrieval, 2000, 3: 229-241.
[37] 王上飞，王煦法．图像情感检索研究的进展与展望[J]．电路与系统学报，2005，10(4)：102-110．
[38] 曹莉华，柳伟，李国辉．基于多种主色调的图像检索算法研究与实现[J]．计算机研究与发展，1999，36(1)：96-100．
[39] 刘忠伟，章毓晋．利用局部累加直方图进行彩色图象检索[J]，中国图象图形学报，1998，3(7)： 532-537．
[40] Zhang H J, Low C Y, Smoliar S W. Video parsing, Retrieval and browsing: an integrated an integrated and content-based solution[A]. Proceedings of the 3rd ACM International Conference on Multimedia, 1995, San Francisco, USA, pp. 15-24.
[41] Gong Y, Zhang H, Chuan H C. An Image Database System With Content Capturing and Fast Image Indexing Abilities[A]. IEEE International Conference on Multimedia Computing and Systems, Boston, USA, May, 1994, pp. 121-130.
[42] Smith J R, Chang S F. Tools and techniques for color image retrieval[A]. Procedding of SPIE on Storage and Retrieval for Still Image and Video Databases Ⅳ, 1996, Vol. 2670: 426-437.
[43] Huang J, Kumar S R, Mitra M. Image indexing using color correlograms[A]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, San Juan, Puerto Rico, June 1997, pp. 762-768.
[44] Pass G, Zabih R. Histogram refinement for content-based image retrieval[A]. IEEE Workshop on Applications of Computer Vision, 1996, pp. 96-102.
[45] Sethi I K, Coman I, Day B. Color-WISE: A system for image similarity retrieval using color[A]. Proceedings of SPIE on Storage and Retrieval for Image and Video Databases, Vol. 3312, February 1998, pp. 140-149.
[46] Tao Y, Grosky W I. Spatial Color Indexing Using Rotation, Translation and Scale Invariant Anglograms[J]. Multimedia Tools and Applications, 2001, 15 (3): 247-268.
[47] 周培德．计算几何-算法分析与设计[M]．北京：清华大学出版社，2000．
[48] Rao A B, Srihari R K, Zhang Z F. Spatil Color Histogram for Content-Based Retrieval[A]. Proceeding of 11th IEEE International Conference on Tools with Artificial Intelligence. Chicago, Illinois, USA, November 1999 , pp: 183-186.
[49] Stricker M, Orengo M. Similarity of Color images[A]. Proceeding of SPIE on Storage and Retrieval for Image and Video Databases Ⅲ, Feb. 1995, Vol. 2420: 381-392.
[50] Jacobs C E, Finkelstein A, Salesin D H. Fast multiresolution image querying[A]. Proceedings of the 22nd Annual Conference on Computer Graphics and Interactive Techniques, 1995, pp. 277-286.
[51] Worring M, Gevers T. Interactive Retrieval of Color Images[EB/OL]. [2006-12-05].http://staff.science.uva.nl/～gevers/pub/GeversIJIG01.pdf.
[52] Gevers T, Smeulders A W. Content-based Image Retrieval by Viewpoint-invariant Image Indexing[J]. Image and Vision Computing, 1999, 17 (7): 475-488.
[53] Tamura H, Mori S, Yamawaki T. Texture features corresponding to visual perception[J]. IEEE Transactions on Systems, Man and Cybernetics. 1978, 8 (6): 460-473.
[54] Flickner M, Sawhney H, Niblack W. Query by Image and Video Content: The OBIC System[J]. IEEE Computer, 1995, 28 (9): 23-32.
[55] Li X L, Liu Z K, Yu N H. Generalized 3D Co-occurrence Matrix for Visual Information Retrieval[J]. Journal of Circuits and Systems, 2002, 7 (2): 10-12.
[56] Mao J, Jain A K. Texture classification and segmentation using multi-resolution simultaneous autoregressive models[J]. Pattern Recognition, 1992, 25 (2): 173-188.
[57] Picard R W, Kabir T, Liu F. Real-time Recognition with the entire Brodatz Texture Database[A]. IEEE Conference on Computer Vision and Pattern Recognition, June, 1993, New York, pp. 638-639.
[58] Liu F, Picard R W. Periodicity, directionality, and randomness: Wold features for image modeling and retrieval[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18 (7): 722-733.
[59] Pentland A, Picard R W, Scarloff S. Photobook: Tools for content-based manipulation of image databases[A]. Proceeding of SPIE on Storage and Retrieval for Image and Video Database[A]. Bellingham, Wash, 1994: 34-47.
[60] He D C, Wang L. Texture Features based on Texture Spectrum[J]. Pattern Recognition, 1991, 24 (5): 391-399.
[61] 施智平，胡宏，李清勇．基于纹理谱描述子的图像检索[J]．软件学报，2005，16(6)：1039-1045．
[62] Bhagavathy S, Chhabra K. A Wavelet-based Image Retrieval System[EB/OL]. [2006-12-08]. http://vision.ece.ucsb.edu/～sitaram/pdf/ece278a.pdf.
[63] WIRES: Wavelet-based Image Retrieval System[EB/OL]. [2006-12-01].http://home.hol.is.uec.ac.jp/kobayaka/wire.html.
[64] 汪祖媛，梁栋，李斌．基于树状小波分解的纹理图像检索[J]．中国图像图形学报，2001，6(11)：1065-1069．
[65] Mandal M K, Aboulnasr T. Fast Wavelet Histogram Techniques for Image Indexing[J]. Computer Vision and Image Understanding, 1999, 75 (1-2): 99-110.
[66] Ma W Y, Manjunath B S. A comparison of wavelet transform features for texture image annotation[A]. Proceedings of IEEE International Conference on Image Processing, 1995, Washington, D C, USA, pp. 256-259.
[67] 汪云九，齐翔林．初级视觉的Gabor函数模型的研究进展[J]．生物物理学报，1993，9(3)：508-513．
[68] Manjunath B S, Ma W Y. Texture Features for Browsing and Retrieval of Image Data[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18 (8): 837-842.
[69] 张超，木拉提·哈米提，刘伟．复杂度直方图及其在图像检索中的应用[J]．计算机工程与应用，2006，42(2)：215-217．
[70] 周洁．纹理分析新方法与非线性降维在图像检索中的应用研究[D]．杭州：浙江大学，2006．
[71] 容观澳．计算机图象处理[M]．北京：清华大学出版社，2000．
[72] Hu M. Visual pattern recognition by moment invariants[J]. IRE Transactions on Information Theory, 1962, 8 (2): 179-187.
[72] Flusser J, Suk T. Pattern Recognition by Affine Moment Invariants[J]. Pattern Recognition, 1993, 26 (1): 167-174.
[73] 金丰华，秦磊，汪蕙等．几何矩不变量在基于内容医学图像检索中的应用[J]．山东生物医学工程，2002，21：7-10．
[74] 邬浩，潘云鹤，庄越挺，杨宇艇．基于对象形状的图像查询技术[J]．软件学报，1998，9(5)：343-349．
[75] 李颖．生物学启发下的计算机视觉算法的研究[D]．北京：中国科学院生物物理研究所，2001
[76] SQUID Home Page[EB/OL]. [2006-12-01].http://www.ee.surrey.ac.uk/Research/VSSP/imagedb/demo.html.
[77] Chuang G, Kuo J. Wavelet descriptor of planar curves: theory and application[J]. IEEE Transactions on Image Processing, 1996, 5 (1): 56-70.
[78] 刘继敏．基于形状检索的研究[D]．北京：中国科学院计算技术研究所，2000．
[79] 孙君顶，丁振国，周利华．基于图像信息熵与空间分布熵的彩色图像检索方法[J]．红外与毫米波学报，2005，24(2)：135-139．
[80] Viola P A, Wells W M. Alignment by maximization of mutual information[J]. International Journal of Computer Vision. 1997, 24 (2): 137-154.
[81] 李顺山，杨明星，庄天戈．基于互信息方法的医学图像检索[J]．红外与毫米波学报，2001，20(5)：370-374．
[82] Shneier M, Mottaleb M A. Exploiting the JPEG compression scheme for image retrieval[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18 (8): 849-853.
[83] 李晓华，沈兰荪．基于压缩域的图像检索技术[J]．计算机学报，2003，26(9)：1051-1059．
[84] Ladret P, Dugue A G. Categorization and Retrieval of Scene Photographs from a JPEG Compressed Database[J]. Pattern Analysis and Applications, 2001, 4: 185-199.
[85] Ordonez J R, Cazuguel G, PuenIes J.-Joint spatial-spectral indexing of medical images exploiting the JPEG compression scheme[A]. Proceedings of the IEEE on the Second Joint EMBS-BMES Conference, Houston, Texas, USA, 23-26 October 2002, pp. 1015-1016.
[86] 陈守吉，张立明．分形与图像压缩[M]．上海：上海科技教育出版社．1998．
[87] Nappi M, Polese G, Tortora G. FIRST: Fractal Indexing and Retrieval SysTem for Image Databases[J]. Image and Vision Computing, 1998, 16: 1019-1031.
[88] Distasi R, Nappi M, Tucci M. FIRE: Fractal Indexing With Robust Extensions for Image Databases[J]. IEEE Transactions on Image Processing, 2003, 12 (3): 373-384.
[89] Koenen R, Pereira F. MPEG-7: A standardised description of audiovisual content[J]. Signal Processing: Image Communication, 2000, 16: 5-13.
[90] Manjunath B S, Ohm J R, Vasudevan V V. Color and Texture Descriptors[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2001, 11(6): 703-715.
[91] Bober M. MPEG-7 Visual Shape Descriptors[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2001, 11 (6): 716-719.
[92] Blobworld, Image retrieval using regions[EB/OL]. [2006-12-01]. http://elib.cs.berkeley.edu/blobworld/.
[93] Carson C, Belongie S, Greenspan H. Blobworld: image segmentation using expectation-maximization and its application to image querying[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24 (8): 1026-1038.
[94] Wang J Z, Li J, Wiederhold G. SIMPLIcity: Semantics-Sensitive Integrated Matching for Picture Llbraries[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2001, 23 (9): 947-963.
[95] Chen Y X, Wang J Z. A Region-Based Fuzzy Feature Matching Approach to Content-Based Image Retrieval[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24 (9): 1252-1267.
[96] Tian Q, Wu Y, Huang T S. Combine User Defined Region-of-Interest and Spatial Layout for Image Retrieval[A]. IEEE 2000 International Conference on Image Processing (ICIP 2000), Vol. 3: 746-749, Vancouver, BC, Canada, 2000.
[97] 张健沛，闫锐，杨静．基于兴趣区域的图像检索方法的研究[J]．哈尔滨工程大学学报，2003，24(3)：283-286．
[98] Harris C, Stephens M. A Combined Corner and Edge Detector[EB/OL]. [2005-10-08] www.csse.uwa.edu.au/～pk/Research/MatlabFns/Spatial/Docs/Harris/.
[99] Lindeberg T. Feature detection with automatic scale selection[J]. International Journal of Computer Vision, 1998, 30 (2): 79-116.
[100] Schmid C, Mohr R, Bauckhage C. Evaluation of interest point detectors[J]. International Journal of Computer Vision, 2000, 37 (2): 151-172.
[101] Kadir T, Brady M. Scale, Saliency and Image Description[J]. International Journal of Computer Vision, 2001, 45 (2): 83-105.
[102] Sebe N, Lew M S. Comparing salient point detectors[J]. Pattern Recognition Letters, 2003, 24(1-3): 89-96.
[103] Lowe D G. Distinctive Image Features from Scale-Invariant Keypoints[J]. International Journal ofComputer Vision, 2004, 60 (2): 91-110.
[104] Koch C, Ullman S. Shifts in selective visual attention: towards the underlying neural circuitry[J]. Human Neurobiology, 1985, 4 (4): 219-227.
[105] Itti L, Koch C, Niebur E. A model of saliency-based visual-attention for rapid scene analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20 (11): 1254-1259.
[106] Ma Y F, Zhang H J. Contrast-based Image Attention Analysis by Using Fuzzy Growing[A]. Proceedings of the 11th ACM International Conference on Multimedia[A]. Berkeley, Calffonia, USA, 2003, pp. 374-381.
[107] Weijer J, Gevers T, Bagdanov A D. Boosting Color Saliency in Image Feature Detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28 (1): 150-156.
[108] Schmid C, Mohr R. Local greyvalue invariants for image retrieval[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19 (5): 530-534.
[109] 孟繁杰，郭宝龙．一种基于兴趣点颜色及空间分布的图像检索方法[J]．西安电子科技大学学报(自然科学版)，2005，32(2)：256-259．
[110] 曾智勇，张学军，崔江涛．基于显著兴趣点颜色及空间分布的图像检索新方法[J]．光子学报，2006，35(2)：308-311．
[111] Tian Q, Sebe N, Lew M S. Image retrieval using wavelet-based salient points[J]. Journal of Electronic Imaging, Special Issue on Storage and Retrieval of Digital Media, 2001, 10 (4): 835-849.
[112] Halawani A, Burkhardt H. Image Retrieval by Local Evaluation of Nonlinear Kernel Functions around Salient Points[A]. Proceedings of the 17th International Conference on Pattern Recognition, 2004, Vol2: 955-960.
[113] Sivic J, Zisserman A. Video Google: A Text Retrieval Approach to Object Matching in Videos[A]. Proceedings. of the Ninth IEEE International Conference on Computer Vision, 2003, Vol. 2: 1470-1477.
[114] Li F F. Visual Recognition: Computational Models and Human Psychophysics[D]. Pasadena, California, USA: California lnstitute of Technology, 2005.
[115] 斯白露．基于感兴趣区域的图像检索方法[D]．北京：中科院计算技术研究所，2002．
[116] Photosynth Technology[EB/OL]. [2006-12-08]. http://labs.live.com/photosynth/.
[117] Autostitch: A new dimension in automatic image stitching[EB/OL]. [2006-12-17]. http://www.cs.ubc.ca/～mbrown/autostitch/autostitch.html.
[118] Matthew Brown's Research Page[EB/OL]. [2006-12-18]. http://www.cs.ubc.ca/～mbrown/research/research.html.
[119] 边肇祺，张学工．模式识别(第二版)[M]．北京：清华大学出版社，2000．
[120] 阎平凡，张长水．人工神经网络与模拟进化计算[M]．北京：清华大学出版社，2000．
[121] 杨行峻，郑群里．人工神经网络与盲信号处理[M]．北京：清华大学出版社，2003．
[122] 阎平凡，黄端旭．人工神经网络：模型，分析与应用[M]．合肥：安徽教育出版社，1993．
[123] 黄振华，吴诚一．模式识别原理[M]．杭州：浙江大学出版社，1991．
[124] 孙即祥．现代模式识别[M]．长沙：国防科技大学出版社，2002．
[125] Multidimensional Scaling[EB/OL]. [2006-12-10]. http://www.statsoft.com/textbook/stmulsca.html.
[126] Bouman CA, Chen S, Lowe M J. Clustered component analysis for FMRI signal estimation and classification[A]. International Conference on Image Processing, 2000, Vol. 1: 609-612.
[127] Canonical Discriminant Analysis Introduction[EB/OL]. [2006-12-10].http://bioweb.wku.edu/courses/Biol483/483lects12.htm.
[128] Roweis S, Saul L. Nonlinear dimensionality reduction by locally linear embedding[J]. Science, 2000, 290 (5500): 2323-2326.
[129] Donoho D L, Grimes C. Hessian eigenmaps: New locally linear embedding techniques for high-dimensional data[J]. Proceedings of the National Academy of Sciences, 2003, 100 (10): 5591-5596.
[130] Tenenbaum J B, Silva V, Langford J C. A Global Geometric Framework for Nonlinear Dimensionality Reduction[J]. Science, 2000, 290 (5500): 2319-2323.
[131] Belkin M, Niyogi P. Laplacian Eigenmaps for Dimensionality Reduction and Data Representation[J]. Neural Computation, 2003, 15 (6): 1373-1396.
[132] He X F, Niyogi P. Locality Preserving Projections[EB/OL]. [2006-12-09]. http://books.nips.cc/papers/files/nips16/NIPS2003_AA20.pdf.
[133] Zhang Z Y, Zha H Y. Principal manifolds and nonlinear dimensionality reduction via tangent space alignment[J]. SIAM Journal of Scientific Computing, 2004, 26 (1): 313-338.
[134] GTM homepage[EB/OL]. [2006-12-10]. http://www.ncrg.aston.ac.uk/GTM/.
[135] Agrafiotis D K, Xu H F. A self-organizing principle for learning nonlinear manifolds[J]. Proceedings of the National Academy of Sciences, 2002, 99 (25): 15869-15872.
[136] Sinha U, Kangarloo H. Principal Component Analysis for Contentbased Image Retrieval[J]. Radiographics, 2002, 22 (5): 1271-1289.
[137] Turk M, Pentland A. Eigenfaces for recognition[J]. Journal of Cognitive Neuroscience, 1991, 3 (1): 71-86.
[138] Jiao Y H, Yang B, Wang H. SVD Based Robust Image Content Retrieval[A]. International Conference on Intelligent Information Hiding and Multimedia, 2006, pp. 351-354.
[139] Gong Y H, Liu X. Video summarization and retrieval using singular value decomposition[J]. Mnltimedia Systems, 2003, 9: 157-168.
[140] Katsumata N, Matsuyama Y. Similar-Image Retrieval Systems Using ICA and PCA Bases[J]. Proceedings of International Joint Conference on Neural Networks, Montreal, Canada, July 31-August 4, 2005, pp. 1229-1234.
[141] Zeng X Y, Chen Y W, Nakao Z. Image Retrieval Based on Independent Components of Color Histograms[A]. Lecture Notes in Computer Science on Knowledge-Based Intelligent Information and Engineering Systems, 2003, Vol. 2773: 1435-1442.
[142] Wang J Z's Research Group, The Pennsylvania State University. Test image database[EB/OL]. [2005-10-08]. http://wang.ist.psu.edu/docs/related/.
[143] Sun G X, Liu J, Sun J D. Locally Salient Feature Extraction Using ICA for Content-Based Face Image Retrieval[A]. First International Conference on Innovative Computing, Information and Control, 2006, Vol. 1: 644-647.
[144] 刘骏伟，吴飞，庄越挺．基于SVM和ICA的视频帧字幕自动定位与提取[J]．中国图象图形学报，2003，8(11)：1334-1340．
[145] Swets D L, Weng J. Using Discriminant Eigenfeatures for Image Retrieval[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18 (8): 831-836.
[146] Beatty M, Manjunath B S. Dimensionality Reduction Using Multi-Dimensional Scaling for Content-Based Retrieval[A]. IEEE International Conference on Image Processing, 1997, Vol. 2: 835-838.
[147] 徐志节，杨杰，王猛．一种新的彩色图像降维方法[J]．上海交通大学学报，2004，38(12)：2063-2067．
[148] He X F. Laplacian Eigenmaps for Image Retrieval[D]. Chicago, USA: The University of Chicago, 2002.
[149] Zhang H J, Zhong D. A Scheme for Visual Feature Based Image Retrieval[A]. Proceedings of SPIE on Storage and Retrieval for Image and Video Databases Ⅲ, 1995, Vol. 2420: 36-46.
[150] Russell R, Sinha P. Perceptually-based Comparison of Image Similarity Metrics[EB/OL]. [2006-12-12]. https://dspace.mit.edu/bitstream/1721.1/7235/2/AIM-2001-014.pdf.
[151] Swain M J, Ballard D H. Color indexing[J]. International Journal of Computer Vision, 1991, 7 (1): 11-32.
[152] Hafner J, Sawhney H S, Equitz W. Efficient Color Histogram Indexing for Quadratic Form Distance Functions[3]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995, 17 (7): 729-736.
[153] 梁艳梅，翟宏琛，母国光．模糊集理论在彩色图像检索中的应用[J]．物理学报，2002，51(12)：2671-2675．
[154] Rubner Y, Tomasi C, Guibas L J. The earth mover's distance as a metric for image retrieval[3]. International Journal of Computer Vision, 2000, 40 (2): 99-121.
[155] Santini S, Jain R. Similarity Measures[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1999, 21 (9): 871-883.
[156] Frese T, Bouman C A, Allebach P. A methodology for designing image similarity metrics based on human visual system models[A]. Proceedings of SPIE, International Society for Optical Engineering Proceedings on Human Vision and Electronic Imaging Ⅱ, 1997, Vol. 3016, pp. 472-483.
[157] Rogowitz B E, Frese T, Smith J R. Perceptual Image Similarity Experiments[EB/OL]. [2006-12-12]. http://www.research.ibm.com/visualanalysis/papers/spie_ei98.pdf.
[158] Mojsilovic A, Rogowitz B. Capturing image semantics with low-level descriptors[A]. International Conference on Image Processing, 2001, Vol. 1: 18-21.
[159] Mojsilovic A, Gomes J. Semantic based categorization, browsing and retrieval in medical image databases[A]. International Conference on Image Processing, 2002, Vol. 3: 145-148.
[160] Neumann D, Gegenfurtuer K R. Image retrieval and perceptual similarity[J]. ACM Transactions on Applied Perception, 2006, 3 (1): 31-47.
[161] 阮迪云，寿天德．神经生理学[M]．合肥：中国科学技术大学出版社，1992．
[162] Derrington A M, Krauskopf J, Lennie P. Chromatic mechanisms in lateral geniculate nucleus of macaque[J]. Journal of Physiology, 1984, 357: 241-265.
[163] Li B T, Chang E, Wu C T. DPF-a perceptual distance function for image retrieval[A]. International Conference on Image Processing, 2002, Vol. 2: 597-600.
[164] 木拉提·哈米提．基于内容医学图像检索方法的研究[R]．杭州：浙江大学，2005．
[165] Gordon S, Greenspan H, Goldberger J. Applying the information bottleneck principle to unsupervised clustering of discrete and continuous image representations[A]. Ninth IEEE International Conference on Computer Vision, 2003, Vol. 1: 13-16.
[166] Laaksonen J, Koskela M, Laakso S. PicSOM-content-based image retrieval with self-organizing maps[J]. Pattern Recognition Letters, 2000, 21 (13-14): 1199-1207.
[167] Puzicha J, Hofmann T, Buhmann J M. Histogram clustering for unsupervised segmentation and image retrieval[J]. Pattern Recognition Letters, 1999, 20 (9): 889-909.
[168] Chen Y X, Wang J Z, Krovetz R. CLUE: Cluster-based Retrieval of Images by Unsupervised Learning[J]. IEEE Transactions on Image Processing, 2005, 14 (8): 1187-1201.
[169] CLUE: Cluster-based Image Retrieval[EB/OL]. [2006-12-12].http://wang.ist.psu.edu/IMAGE/clue/.
[170] Shi J B, Malik J. Normalized cuts and image segmentation[J]. IEEE Trans Pattern Analysis and Machine Intelligence, 2000, 22 (8): 888-905.
[171] Zheng X, Cai D, He X F. Locality preserving clustering for image database[A]. Proceedings of the 12th Annual ACM International Conference on Multimedia, 2004, pp. 885-891.
[172] Nguyen G P, Worring M. Optimizing similarity based visualization in content based image retrieval[A]. IEEE International Conference on Multimedia and Expo, 2004, Vol. 2: 759-762.
[173] 孙建军，成颖，丁芹等．信息检索技术[M]．北京：科学出版社，2004．
[174] Rui Y, Huang T S, Ortega M. Relevance feedback: a power tool in interactive content-based image retrieval[J]. IEEE Transactions on Circuits and Systems for Video Technology, 1998, 8(5): 644-655.
[175] 吴洪，卢汉清，马颂德．基于内容图像检索中相关反馈技术的回顾[J]．计算机学报，2005，28(12)：1969-1979．
[176] Rui Y, Huang T S, Mehrotra S. A relevance feedback architecture for content-based multimediainformation retrieval systems[A]. IEEE Workshop on Content-Based Access of Image and Video Libraries, 1997, pp. 82-89.
[177] Huang J, Kumar S R, Mitra M. Combining supervised learning with color correlograms for content-based image retrieval[A]. Proceedings of the 5th ACM International Conference on Multimedia, Seattle, Washington, USA, 1997, 325-334.
[178] Ishikawa Y, Subramanya R, Faloutsos C. MindReader: Querying databases through multiple examples[A]. Proceedings of the 24th International Conference on Very Large Data Bases (VLDB), 1998, pp. 218-227.
[179] Rui Y, Huang T S. A novel relevance feedback technique in image retrieval[A]. Proceedings of the 7th ACM International Conference on Multimedia, 1999, pp. 67-70.
[180] Meilhac C, Nastar C. Relevance feedback and category search in image databases[A]. IEEE International Conference on Multimedia Computing and Systems, 1999, Vol. pp. 512-517.
[181] Cox I J, Miller M L, Minks T P. The Bayesian image retrieval system, PicHunter: theory, implementation, and psychophysical experiments[J]. IEEE Transactions on Image Processing, 2000, 9(1): 20-37.
[182] Vasconcelos N, Lippman A. Bayesian Relevance Feedback for Content-Based Image Retrieval[A]. Proceedings of the IEEE Workshop on Content-based Access of Image and Video Libraries, 2000, pp. 63-67.
[183] 段立娟，高文，马继勇．Rich Get Richer-图像检索中的一种自适应的相关反馈方法[J]．计算机研究与发展，2001，38(8)：960-965．
[184] 王崇骏，杨育彬，陈世福．基于高层语义的图像检索算法[J]．软件学报，2004，15(10)：1461-1469．
[185] 苏中，马少平，张宏江．基于内容图像检索的特征子空间抽取[J]．软件学报，2003，14(2)：190-193．
[186] N．Cristianini，J．S．Taylor著，李国正等译．支持向量机导论[M]．北京：电子工业出版社，2004．
[187] 张学工．关于统计学习理论与支持向量机[J]．自动化学报，2000，26(1)：32-42．
[188] Zhang L, Lin F Z, Zhang B. Support vector machine learning for image retrieval[A]. International Conference on Image Processing, 2001, Vol. 2: 721-724.
[189] Chen Y, Zhou X S, Huang T S. One-class SVM for learning in image retrieval[A]. Proceedings of International Conference on Image Processing, 2001, pp. 34-37.
[190] Nigam K, McCallum A, Thrun S. Text classification from labeled and unlabeled documents using EM[J]. Machine Learning, 1999, 39 (2-3): 103-134.
[191] (美)Mitchell T M著，(中)曾华军，张银奎译．机器学习[M]．北京：机械工业出版 社，2003．
[192] Wu Y, Tian Q, Huang T S. Discriminant EM algorithm with application to image retrieval[A]. Preceedings of IEEE Conference Computer Vision and Pattern Recognition, 2000, 222-227.
[193] Angluin D. Queries and concept learning[J]. Machine Learning, 1988, 2 (4): 319-342.
[194] Tong S, Chang E. Support vector machine active learning for image retrieval[A]. Proceedings of the Ninth ACM international conference on Multimedia, 2001, pp. 107-118.
[195] Zhou Z H, Chen K J, Jiang Y. Exploiting unlabeled data in content-based image retrieval[A]. Proceedings of the 15th European Conference on Machine Learning, 2004, Lecture Notes in Computer Science, Vol. 3201: 525-536.
[196] Hansen L K, Salamon P. Neural Network Ensembles[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12 (10): 993-1001.
[197] 周志华，陈世福．神经网络集成[J]．计算机学报，2002，25(1)：1-8．
[198] Freund Y, Schapire R E. A decision-theoretic generalization of on-line learning and an application to boosting[J]. Journal of Computer and System Science, 1997, 55 (1): 119-139.
[199] Tieu K, Viola P. Boosting Image Retrieval[J]. International Journal of Computer Vision, 2004, 56 (1-2): 17-36.
[200] Huang S H, Wu Q J, Lai S H. Improved AdaBoost-Based Image Retrieval with Relevance Feedback via Paired Feature Learning[A]. Lecture Notes in Computer Science, 2005, Vol. 3568: 660-670.
[201] 武勃，黄畅，艾海舟．基于连续Adaboost算法的多视角人脸检测[J]．计算机研究与发展，2005，42(9)：1612-1621．
[202] 李闯，丁晓青，吴佑寿．一种基于直方图特征和AdaBoost的图像中的文字定位算法[J]．中国图象图形学报，11(3)：325-331．
[203] Seung H S, Lee D D. The Manifold Ways of Perception[J]. Science, 2000, 290 (5500): 2268-2269.
[204] 徐蓉，姜峰，姚鸿勋．流形学习概述[J]．智能系统学报，2006，1(1)：44-51．
[205] He J R, Li M J, Zhang H J. Manifold-ranking based image retrieval[A]. Proceedings of the 12th Annual ACM international conference on Multimedia, 2004, 9-16.
[206] He X F, Ma W Y, Zhang H J. Learning an image manifold for retrieval[A]. Proceedings of the 12th Annual ACM international conference on Multimedia, 2004, 17-23.
[207] Lin Y Y, Liu T L, Chen H T. Semantic manifold learning for image retrieval[A]. Proceedings of the 13th Annual ACM international conference on Multimedia, 2005, 249-258.
[208] Dietterich T G, Lathrop R H, Lozano P T. Solving the multiple-instance problem with axis-parallel rectangles[J]. Artificial Intelligence, 1997, 89 (1-2): 31-71.
[209] 蔡自兴，李枚毅．多示例学习及其研究现状[J]．控制与决策，2004，19(6)：607-610．
[210] Maron O. Learning from Ambiguity[D]. Cambridge, Boston, USA: Massachusetts Institute of Technology, 1998.
[211] Zhang Q, Goldman S A, Yu W. Content-Based Image Retrieval Using Multiple-lnstance Learning[EB/OL]. [2006-12-12]. http://www.cs.wustl.edu/～sg/icml-cbir.ps.
[212] Zhou Z H, Zhang M L, Chen K J. A novel bag generator for image database retrieval with multi-instance learning techniques[A]. Proceedings of the 15th IEEE International Conference on Tools with Artificial Intelligence, 2003, pp. 565-569.
[213] Rahmani R, Goldman S A, Zhang H. Localized content based image retrieval[A]. Proceedings of the 7th ACM SIGMM International workshop on Multimedia Information Retrieval, 2005, pp. 227-236.
[214] Accio! Online Demo[EB/OL]. [2006-12-15]. http://www.cs.wustl.edu/accio/demo.html.
[215] Zhang C C, Chert X. Region-Based Image Clustering and Retrieval Using Multiple Instance Learning[A]. Lecture Notes in Computer Science, 2005, Vol. 3568: 194-204.
[216] Zhang C C, Chen S C, Shyu M L. Multiple object retrieval for image databases using multiple instance learning and relevance feedback[A]. IEEE International Conference on Multimedia and Expo, 2004, Vol. 2: 775-778.
[217] 黎铭，薛晓冰，周志华．基于多示例学习的中文Web目录页面推荐[J]．软件学报，2004，15(9)：1328-1335．
[218] Ho C G, Ho T B, David C. Kernel principal component analysis for content based image retrieval[A]. Pacific-Asia conference on advances in knowledge discovery and data mining, Hanoi, 18-20, May, 2005. Lecture notes in computer science, Vol. 3518, pp. 844-849.
[219] Wang L, Chan K L, Xue P. A Criterion for Optimizing Kernel Parameters in KBDA for Content-Based Image Retrieval[J]. IEEE Transactions on System Man and Cybernetics-Part B, 2005, 53 (3): 556-562.
[220] Wang L, Gao Y, Chan K L. Retrieval with knowledge-driven kernel design: an approach to improving SVM-based CBIR with relevance feedback[A]. IEEE International Conference on Computer Vision, 2005, Vol. 2: 1355-1362.
[221] 卢进军，杨杰，梁栋．基于非负矩阵分解的相关反馈图像检索算法[J]．上海交通大学学报，2005，39(4)：578-581．
[222] 张亮，周向东，张琪．图像检索中基于长期学习的动态用户模型[J]．软件学报，2005，16(2)：233-238．
[223] 张亮，施伯乐，周向东．发掘相关反馈日志中关联信息的图像检索方法[J]．软件学报，2004，15(1)：41-48．
[224] 周向东，张亮，张琪．基于反馈日志分析的图像检索相关反馈方法[J]．计算机研究与发展，2004，41(1)：111-117．
[225] Chapelle O, Haffner P, Vapnik V N. Support vector machines for histogram-based image classification[J]. IEEE Transactions on Neural Networks, 1999, 10 (5): 1055-1064.
[226] Jing F, Li M J, Zhang H J. Support vector machines for region-based image retrieval[EB/OL]. [2006-12-14]. http://citeseer.ist.psu.edu/560186.html.
[227] Chen Y X. A machine learning approach to content-based image indexing and retrieval[D]. Pennsylvania, USA: The Pennsylvania State University, 2000.
[228] 万华林，Chowdhury M U．基于支持向量机的图像语义分类[J]．软件学报，2003，14(11)：1891-1899．
[229] Iqbal Q, Aggarwal J K. Perceptual Grouping for Image Retrieval and Classification[A]. Third IEEE Computer Society Workshop on Perceptual Organization in Computer Vision, Vancouver, BC, Canada, July 8, 2001, pp. 19-1-19-4.
[230] Chert Y X, Wang J Z. Image Categorization by Learning and Reasoning with Regions[J]. Journal of Machine Learning Research, 2004, 5: 913-939.
[231] Maron O, Ratan A L. Multiple-instance learning for natural scene classification[A]. Proceedings of the 15th International Conference on Machine Learning, 1998, 341-349.
[232] Vogel J. Semantic Scene Modeling and Retrieval[D]. Swiss Federal Institute of Technology, Zurich: Swissland, 2004.
[233] Quelhas P, Odobez J M. Natural Scene Image Modeling using Color and Texture Visterms[EB/OL]. [2006-12-15]. http://www.idiap.ch/～quelhas/papers/CIVR2006.pdf.
[234] Quelhas P, Monay F, Odobez J M. Modeling Scenes with Local Descriptors and Latent Aspects[A]. IEEE International Conference on Computer Vision, 2005, pp. 883-890.
[235] Csurka G, Dance C R, Fan L X. Visual Categorization with Bags of Keypoints[EB/OL].[2006-12-12]. http://www.xrce.xerox.com/Publications/Attachments/2004-010/2004_010.pdf.
[236] Schmid C. Constructing models for content-based image retrieval[A]. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2001, Vol. 2: 39-45.
[237] Schmid C. Weakly Supervised Learning of Visual Models and Its Application to Content-Based Retrieval[J]. International Journal of Computer Vision, 2004, 56 (1-2): 7-16.
[238] Deerwester S, Dumais S, Furnas G. Indexing by latent sematic analysis[J]. Journal of the American Society for Information Science, 1990, 41 (6): 391-407.
[239] Zhao R, Grosky W I. Negotiating the semantic gap: from feature maps to semantic landscapes[J]. Pattern Recognition, 2002, 35 (3): 593-600.
[240] Zhao R, Grosky W I. Narrowing the Semantic Gap-lmproved Text-Based Web Document Retrieval Using Visual Features[J]. IEEE Transactions on Multimedia, 2002, 4 (2): 189-200.
[241] Hare J S, Lewis P H, Leow W K. On image retrieval using salient regions with vector-spaces and latent semantics[A]. International Conference on Image and Video Retrieval, Lecture Notes in Computer Science, 2005, Vol. 3568: 540-549.
[242] 木拉提·哈米提，刘伟，童勤业．纹理谱直方图与潜在语义标引在图像检索中的应用[J]．科技通报，2006，22(3)：389-394．
[243] Lee D D, Seung H S. Learning the parts of objects by non-negative matrix factorization[J]. Nature, 1999, 401 (6755): 788-791.
[244] Lee D D, Seung H S. Algorithms for non-negative matrix factorization[J]. Advances in Neural Information Processing Systems, 2001, 13: 556-562.
[245] 刘维湘，郑南宁，游屈波．非负矩阵分解及其在模式识别中的应用[J]．科学通报，2006，51(3)：241-250．
[246] 梁栋，杨杰，卢进军．基于非负矩阵分解的隐含语义图像检索[J]．上海交通大学学报，2006，40(5)：787-790．
[247] French J C, Chapin A C, Martin W N. An application of multiple viewpoints to content-based image retrieval[A]. Proceedings of the IEEE Joint Conference on Digital Libraries, 2003, pp. 128-130.
[248] VBIR-Visual-Based Image Retrieval[EB/OL]. [2006-12-16]. http://www.techfak.uni-bielefeld.de/ags/ni/projects/eyetrack/eye_cbir.html.
[249] Shirahatti N V, Barnard K. Evaluating Image Retrieval[A]. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005, Vol. 1: 955-961.
[250] 韦娜，耿国华，周明全．基于内容的图像检索系统性能评价[J]．中国图象图形学报，2004，9(11)：1271-1276．
[251] 茹立云，彭潇，苏中．基于内容图像检索中的特征性能评价[J]．计算机研究与发展，2003，40(11)：1566-1570．
[252] SIMBA-Search IMages By Appearance[EB/OL]. [2006-12-17]. http://simba.informatik.uni-freiburg.de/.
[253] UCID-An Uncompressed Colour Image Database[EB/OL]. [2006-12-17]. http://www-users.aston.ac.uk/～schaefeg/datasets/UCID/ucid.html.
[254] Washington University Image database[EB/OL]. [2006-12-17]. http://www.cs.washington.edu/research/imagedatabase/groundtruth/.
[255] CIT Image Database[EB/OL]. [2006-12-17]. http://www.vision.caltech.edu/html-files/archive.html.
[256] Zurich Building Image Database[EB/OL]. [2006-12-17]. http://www.vision.ee.ethz.ch/showroom/zubud/index.en.html.
[257] Wang J Z's Home Page[EB/OL]. [2006-12-17]. http://infolab.stanford.edu/～wangz/home/.
[258] Theo Gevers's Home Page[EB/OL]. [2006-12-17]. http://staff.science.uva.nl/～gevers/.
[259] Hongjiang Zhang's Home Page[EB/OL]. [2006-12-17]. http://research.microsoft.com/users/hizhang/.
[260] Kobus Barnard's Home Page[EB/OL]. [2006-12-17]. http://kobus.ca/.
[261] Veltkamp R C, Tanase M. Content-Based Image Retrieval Systems: A Survey[EB/OL]. [2005-10-11]. http://www.aa-lab.cs.uu.nl/cbirsurvey/.
[262] 徐志伟，冯百明，李伟．网格计算技术[M]．北京：电子工业出版社，2004．
[263] Tuceryan M, Jain A K. Texture Analysis, in The Handbook of Pattern Recognition and Computer Vision (2nd Edition), by Chen C H, Pau L F, Wang P S P (eds.)[M], pp. 207-248, Singapore: World Scientific Publishing Corporation, 1998.
[264] 张建国．不变性纹理分析[D]．北京：中国科学院自动化研究所，2002．
[265] Brodatz P. Textures: A Photographic Album for Artists and Designers[M]. New York: Dover, 1966.
[266] Julesz B. Textons, the elements of texture perception, and their interactions[J]. Nature, 1981, 290 (5802): 91-97.
[267] Campbell F W, Robson J G. Application of Fourier Analysis to the Visibility of Gratings[J]. Journal of Physiology, 1968, 197 (2): 551-566.
[268] Devalois R L, Albrecht D G, Thorell L G. Spatial-frequency selectivity of cells in macaque visual cortex[J]. Vision Research, 1982, 22 (5): 545-559.
[269] Liu X W, Wang D L. Image and Texture Segmentation Using Local Spectral Histograms[J]. IEEE Transactions on Image Processing, 2006, 15 (10): 3066-3077.
[270] 郝柏林．复杂性的刻画与“复杂性科学”[J]．物理，30(8)：466-471，2001．
[271] 谢惠民．复杂性与动力系统[M]．上海：上海科技教育出版社，1994．
[272] Huang N E, Shen Z, Long S R. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceeding of Royal Society, London, 1998, A454: 903-995.
[273] 沈恩华．脑电的复杂度分析[D]．上海：复旦大学，2004．
[274] 刘忠轩，彭思龙．方向EMD分解与其在纹理分割中的应用[J]．中国科学(E辑)，2005，35(2)：113-123．
[275] Department of Neurobiology and Behavior, Cornell University. Measuring the "Complexity" of a time sefies[EB/OL]. [2006-09-21]. http://www.nbb.cornell.edu/neurobio/land/PROJECTS/Complexity/index.html.
[276] Kolmogorov A N. Three approaches to the quantitative definition of information[J]. Problems of Information Transmission, 1965, 1 (1): 1-7.
[277] Cover T, Thomas J. Elements of Information Theory[M]. New York: Wiley Interscience, 1991.
[278] Lempel A, Ziv J. On the complexity of finite sequences[J]. IEEE Transactions on lnformation Theory, 1976, 22 (1): 75-88.
[279] Kaspar K, Schuster H G. Easily calculable measure for the complexity of spatio-temporal patterns[J]. Physical Review A, 1987, 36 (2): 842-848.
[280] 徐京华．生命科学中的物理问题讲座第八讲-人脑电图的复杂性[J]．物理，1995，24(2)：113-119．
[281] 李凌云，童勤业．分区复杂性在时间序列分析中的应用[J]．电子学报，2000，28(12)：97-98．
[282] 柯大观，张宏，童勤业．格子复杂性和符号序列的细粒化[J]物理学报，2005，54(2)：534-542．
[283] Bandt C, Pompe B. Permutation Entropy: A Natural Complexity Measure for Time Series[J]. Physical Review Letters, 2002, 88(17): 174102-1-174102-4.
[284] 柯大观．格子复杂性与动力系统的分划[D]．杭州：浙江大学，2005．
[285] Tong Q Y, Kong J, Xu J H. A note on analyzing schizophrenic EEG with complexity measure[J]. Chaos, Solitons and Fractals, 1996, 7 (3): 371-375.
[286] 童勤业，孔军，徐京华．脑电复杂性分析的新方法[J]．中国生物医学工程学报，1998，17(3)：222-225．
[287] 孟欣．意识的定量刻划[D]．上海：复旦大学，2001．
[288] 伍文凯．脑电的非线性时间序列分析[D]．杭州：浙江大学，1999．
[289] 刘慧，丁北生，刘洁．局限性癫痫脑电时间序列的三种复杂度计算比较[J]．生物物理学报，1998，14(2)：269-274．
[290] 张红煊，朱贻盛，牛金海．异常心电节律VT和VF信号的复杂性分析[J]．物理学报，2000，49(8)：1416-1422．
[291] 裴文江，李克，杨绿溪．基于复杂性度量的心率变异信号非线形分析[J]．生物物理学报，1998，14(4)：706-712．
[292] 朱家富，杨浩，何为．基于高阶复杂性测度的心率变异信号分析[J]．生物物理学报，2004，20(3)：193-197．
[293] 董筠．心音的非线性时间序列分析[D]．杭州：浙江大学，2003．
[294] 蔡立羽，王志中，张海虹．基于复杂性度量的表面肌电信号分类方法[J]．生物物理学报，2000，16(1)：119-124．
[295] 陈乐．声纹分析的非线性动力学方法研究[D]．杭州：浙江大学，2001．
[296] 李敏丹，张宏，童勤业．基于复杂性的说话人识别技术探讨[J]．航天医学与医学工程，2003，16(3)：215-219．
[297] 李敏丹．非线性动力学方法在声纹分析中的应用[D]．杭州：浙江大学，2003．
[298] 李轶．说话人识别[D]．杭州：浙江大学，2003．
[299] 曹华．复杂性分析方法在语音及图像处理中的应用研究[D]．杭州：浙江大学，2004．
[300] Pincus S M. Approximate entropy as a measure of system complexity[J]. Proceedings of the National Academy of Sciences, 1991, 88: 2297-2301.
[301] Richman J S, Moorman J R. Physiological time-series analysis using approximate entropy and sample entropy[J]. Am J Physiol Heart Circ Physiol, 2000, 278: H2039-H2049.
[302] 汤晓军，宋卓，杨卓．双任务事件中脑电信号的熵计算[J]．生物物理学报，2005，21(5)：371-376．
[303] 蔡觉平，李赞，宋文涛．一种混沌伪随机序列复杂度分析法[J]．物理学报，2003，52(8)：1871-1876．
[304] 陈芳，顾凡及，徐京华．一种新的人脑信息传输复杂性的研究[J]．生物物理学报，1998，14(3)：508-512．
[305] Personal Website (by Lima M), Visual Complexity[EB/OL]. [2006-10-09].http://www.visualcomplexity.com/vc/.
[306] Donded D C. Visual Complexity: A Review[J]. Psychological Bulletin, 2006, 132 (1):73-97.
[307] Donderi D C. An information theory analysis of visual complexity and dissimilarity[J]. Perception, 2006, 35: 823-835.
[308] Computer Science Department, University of California, Los Angeles. Klinger A, Salingaros N A. A Pattern Measure[EB/OL]. [2006-10-07].http://www.cs.ucla.edu/～klinger/javadir/pattern.html.
[309] Computer Science Department, University of California, Los Angeles. Gu Z. Pattern Measure[EB/OL]. [2006-10-07]. http://www.math.utsa.edu/～salingar/PatternMeasure.html.
[310] Patel L N, Holt P O B. Testing a computational model of visual complexity in background scenes[A]. Proceedings of ACIVS 2000(Advanced Concepts for Intelligent Systems), July, 2000, Baden, pp. 119-123.
[311] Patel L N, Holt P O B. SymGeons: A Prototype Model of Visual Complexity with Implications For Visual Control Tasks[J]. Technology and Work, 2001, 3 (3): 177-187.
[312] Biederman I. Recognition-by-Components: A Theory of Human Image Understanding[J]. Psychological Review, 1987, 94 (2): 115-147.
[313] Riglis E. Modeling Complexity in Visual Images[EB/OL]. [2006-06-10].http://citeseer.ist.psu.edu/472472.html.
[314] Heaps C, Handel S. Similarity and features of natural textures[J]. Journal of Experimental Psychology: Human Perception and Performance, 1999, 25 (2): 299-320.
[315] Oliva A, Mack M L, Shrestha M. Identifying the Perceptual Dimensions of Visual Complexity of Scenes[EB/OL]. [2006-10-18]. http://cvcl.mit.edu/Papers/Oliva CogSc04.pdf.
[316] Taylor R P, Spehar B, Wise J A. Perceptual and Physiological Responses to the Visual Complexity of Pollock's Dripped Fractal Patterns[J]. Journal of Non-linerar Dynamics, Psychology and Life Sciences, 2005, 9: 115-125.
[317] Rigau J, Feixas M, Sbert M. An Information Theoretic Framework for Image Complexity[A]. Eurographics Workshop on Computacional Aesthetics in Graphics, Visualization and Imaging, May 2005, Girona, Spain, pp. 177-184.
[318] Feixas M. An Information-Theory Framework for the Study of the Complexity of Visibility and Radiosity in a Scene[D]. Barcelona, Spain: Universitat Politecnica de Catalunya, 2002.
[319] Peters R A, Strickland R N. Image Complexity Metrics for Automatic Target Recognizers[A]. Automatic Target Recognizer Systems and Technology Conference, 30-31, October, Naval Surface Warfare Center, Silver Springs, USA, pp. 1-17.
[320] Ullman S, Naquet M V, Sali E. Visual features of intermediate complexity and their use in classification[J]. Nature Neuroscience, 2002, 5 (7): 682-687.
[321] Kong J, Chi Z R. Image Classification using Kolmogorov Complexity Measure with Randomly Extracted Blocks[J]. IEICE Transaction on Information and Systems, 1998, E81-D (11): 1239-1246.
[322] 孔军．生物医学工程中的信号处理与模型分析的非线性动力学研究[D]．杭州：浙江大学，1999．
[323] 毛大伟，张宏，童勤业．利用不同尺度下复杂性的差异区分文字和照片[J]．计算机辅助设计与图形学学报，2005，17(8)：1834-1838．
[324] 丁吉昌．分尺度复杂性方法在医学图像纹理分析上的应用[D]．杭州：浙江大学，2005．
[325] 陈旭，庄天戈，滑炎卿．复杂性测度特征在肺部HRCT图像分析中的应用[J]．上海交通大学学报，2003，37(2)：224-227．
[326] Rosenstiel. Data set I[EB/OL]. [2005-12-13]. http://ida.first.fraunhofer.de/projects/bci/competition_iii/desc_I.html.
[327] Linguistic Data Consortium, University of Pennsylvania. YOHO Speaker Verification DataBase[EB/OL]. [2006-10-11]. http://www.ldc.upenn.edu/Catalog/docs/yoho/.
[328] Fan K C, Wang L S. Classification of document blocks using density feature and connectivity histogram[J]. Pattern Recognition Letters, 1995, 16 (9): 955-962.
[329] Zhang X S, Roy R J, Jensen E W. EEG Complexity as a Measure of Depth of Anesthesia for Patients[J]. IEEE Transactions on Biomedical Engineering, 2001, 48 (12): 1424-1433.
[330] Kamata S, Eason R O, Bandou Y. A New Algorithm for N-Dimensional Hilbert Scanning[J]. IEEE Transactions on Image Processing, 1999, 8 (7): 964-973.
[331] Marusic B, Kale I, Tasic J. Image Compression Based on Fast Adaptive Resampling on a Hilbert-Peano Curve[A]. May, 1999, IEEE Conference on Instrumentation and Measurement Technology, Venice, Italy, Vol. 1: 156-159.
[332] 王笋，徐小双．Hilbert曲线扫描矩阵的生成算法及其Matlab程序代码[J]．中国图象图形学报，2006，11(1)：119-122．
[333] 刘向东，朱志良，王光兴．图象扫描波动性度量及Hilbert扫描矩阵的快速生成[J]．中国图象图形学报，2002，7(A)：539-542．
[334] 孟欣，沈恩华，陈芳．脑电图复杂度分析中的粗粒化问题Ⅰ-过分粗粒化和三种复杂度的比较[J]．生物物理学报，2000，16(4)：701-706．
[335] 沈恩华，邱志诚，孟欣．脑电图复杂度分析中的粗粒化问题Ⅱ-量化对复杂度计算的影响[J]．生物物理学报，2000，16(4)：707-710．
[336] 毛大伟．分尺度复杂性及希尔伯特-黄变换在脑电分析中的应用[D]．杭州：浙江大学，2005．
[337] 和卫星，陈晓平．LZ复杂度算法中的二值化方法分析及改进[J]．江苏大学学报(自然科学版)，2004，25(3)：261-264．
[338] 吴一全，朱兆达．图像处理中阈值选取方法30年(1962-1992)的进展(一)[J]．数据采集与处理，1993，8(3)：193-201．
[339] 吴一全，朱兆达．图像处理中阈值选取方法30年(1962-1992)的进展(二)[J]．数据采集与处理，1993，8(4)：268-281．
[340] Otsu N. A threshold selection method from gray level histograms[J]. IEEE Transaction on Systems, Man and Cybernetics, 1979, 9 (1): 62-66.
[341] 王东生，曹磊．混沌、分形及其应用[M]．合肥：中国科技大学出版社，1995．
[342] Vision and Modeling Group, MIT Media Laboratory, Massachusetts Institute of Technology. VisTex database[EB/OL]. [2006-10-16]. http://vismod.media.mit.edu/vismod/imagery/VisionTexture/.
[343] Smith G. MeasTex Image Texture Database[EB/OL]. [2006-10-16]. http://www.texturesynthesis.com/meastex/meastex.html.
[344] Computer Vision Laboratory, Columbia University. Columbia-Utrecht Reflectance and Texture Database[EB/OL]. [2006-10-16]. http://wwwl.cs.columbia.edu/CAVE/software/curet/index.php.
[345] University of Oulu. University of Oulu Texture Database[EB/OL]. [2006-10-16]. http://www.outex.oulu.fi/temp/.
[346] Texture Lab, Heriot-Watt University. Photex Photometric Image Database[EB/OL]. [2006-10-16]. http://www.macs.hw.ac.uk/texturelab/database/Photex/index.htm.
[347] Wu J. Comparing Texture Databases[EB/OL]. [2006-10-16]. http://www.taurusstudio.net/research/pmtexdb/compare.htm.
[348] Lee H Y, Lee H K, Ha Y H. Spatial Color Descriptor for Image Retrieval and Video Segmentation[J]. IEEE Transactions on Multimedia, 2003, 5 (3): 358-367.
[349] Gabor D. Theory of Communication[J]. Journal of the Institute of Electrical Engineers, 1946, 93 (26): 429-457.
[350] Marcelja S. Mathematical Description of the Responses of Simple Cortical Cells[J], Journal of Optical Society of American, 1980, 70 (11): 1297-1300.
[351] Daugman J G.. Two dimensional spectral analysis of cortical receptive field profiles[J]. Vision Research, 1980, 20 (10): 847-856.
[352] 许廷发．Gabor小波神经网络算法及其在灰度图像目标识别中的应用研究[D]．长春：中国科学院长春光机所，2003．
[353] 汪云九，齐翔林．视觉系统初级信息加工的一种数学模型(Ⅰ)-模型的空间性质[J]．生物物理学报，1985，1(2)：123-132．
[354] 潘卓华，齐翔林，汪云九．视觉系统初级信息加工的一种数学模型(Ⅱ)-模型的时间特性[J]．生物物理学报，1985，1(3)：189-198．
[355] Ma L, Tan T N, Wang Y H. Personal identification based on iris texture analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25 (12): 1519-1533.
[356] Chaudhuri B B, Sarkar N. Texture Segmentaion Using Fractal Dimension[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995, 17 (1): 72-77.
[357] Lindgren K, Moore C, Nordahl M. Complexity of Two-Dimensional Patterns[EB/OL]. [2006-10-16]. http://citeseer.ist.psu.edu/350354.html.
[358] 刘伟，童勤业．序列虹膜图像质量的评价方法[J]．计算机辅助设计与图形学学报，2005，17(12)：2739-2743．
[359] 胡广书．数字信号处理-理论、算法与实现(第二版)[M]．北京：清华大学出版社，2003．
[360] 张宪超，李宁，陈国良．离散余弦变换的改进的算术傅立叶变换算法[J]．电子学报，2000，28(9)：88-90．
[361] Costa M, Goldberger A L, Peng C K. Multiscale Entropy Analysis of Complex Physiologic Time Series[J]. Physical Review Letters, 2002, 89 (6): 068102-1-068102-4.
[362] Stricker M, Dimai A. Color Indexing with Weak Spatial Constraints[A]. Proceedings of SPIE on Storage and Retrieval for Image and Video Databases Ⅳ, 1996, Vol. 2670: 29-40.
[363] 姜丹．信息论与编码[M]．合肥：中国科技大学出版社，2001．
[364] Hadjidemetriou E, Grossberg M D, Nayar S K. Multiresolution Histograms and Their Use for Recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(7): 831-847.
[365] Hadjidemetriou E, Grossberg M D, Nayar S K. Multiresolution Histograms and their Use for Texture Classification[EB/OL]. [2006-10-12]. http://www1.cs.columbia.edu/CAVE/publications/pdfs/Hadjidemetriou_TEXTURE03.pdf.
[366] Burr P, Adelson E. The Laplacian pyramid as a compact image code[J]. IEEE Transactions on Communications, 1983, 31 (4): 532-540.
[367] Haralick R M. Statistical and Structural Approaches to Texture[J]. Proceedings of the IEEE, 1979, 67 (5): 786-804.
[368] 梁学章，何甲兴，王新民．小波分析[M]．北京：国防工业出版社，2005．
[369] Radiology Department, Geneva University Hospital. Casimage database[EB/OL]. [2006-04-21]. http://www.casimage.com/.
[370] Arias of Gastrointestinal Endoscopy, Images from Capsule Endoscopy[EB/OL]. [2005-06-17]. http://www.endoatlas.com/.
[371] 中国动脉粥样硬化网，病理图谱图片[EB／OL]．[2005-06-17]．http://www.sinoas.com/Photo/pic04/Index.html.
[372] 黄海．基于Hilbert-Huang变换的语音信号特征信息提取方法与实验研究[D]．杭州：浙江大学，2005．
[373] 赵治栋．基于舒张期心音信号分析与特征提取的冠心病无损诊断研究[D]．杭州：浙江大学，2004．
[374] Nunes J C, Bouaoune Y, Delechelle E. Image Analysis by Bidimensional Empirical Mode Decomposition[J]. Image and Vision Computing, 2003, 21 (12): 1019-1026.
[375] Nunes J C, Niang O, Bouaoune Y. Bidimensional Empirical Mode Decomposition Modified for Texture Analysis[A]. Lecture Notes in Computer Science, 2003, Vol. 2749: 171-177.
[376] Delechelle E, Nunes J C, Lemoine J. Empirical mode decomposition synthesis of fractional processes in 1D and 2D-space[J]. Image and Vision Computing, 2005, 23: 799-806.
[377] Nunes J C, Guyot S, Delechelle E. Texture analysis based on local analysis of the Bidimensional Empirical Mode Decomposition[J]. Machine Vision and Applications, 2005, 16 (3): 177-188.
[378] Linderhed A. 2D empirical mode decompositions in the spirit of image compression[A]. Wavelet and Independent Component Analysis Applications Ⅸ, SPIE Proceedings Vol. 4738, April 2002, pp. 1-8.
[379] Linderhed A. Adaptive Image Compression with Wavelet Packets and Empirical Mode Decomposition[D]. Linkoping, Sweden: Linkoping University, 2004.
[380] Liu Z X, Peng S L. Boundary Processing of Bidimensional EMD Using Texture Synthesis[J]. IEEE Signal Processing Letters, 2005, 12 (1): 33-36.
[381] Damerval C, Meignen S, Pettier V. A fast algorithm for bidimensional EMD[J]. IEEE Signal Processing Letters, 2005, 12 (10): 701-704.
[382] Wu Z H, Huang N E. A study of the characteristics of white noise using the empirical mode decomposition method[J]. Proceeding of Royal Society, London, 2004, A460: 1597-1611.
[383] Bulow T, Sommer G. Hypercomplex Signals-A Novel Extension of the Analytic Signal to the Multidimensional Case[J]. IEEE Transactions on Signal Processing, 2001, 49(11): 2844-2852.
[384] The JPEG committee home page[EB/OL]. [2004-10-10]. http://www.ipeg.org/jpeg2000/.
[385] Bulthoff H H, Lee S W, Poggio T. Biologically Motivated Computer Vision[M]. Springer Publishing Company, New Yerk, 2003.
[386] Itti L, Koch C. Computational modelling of visual attention[J]. Nature Reviews Neuroscience, 2001, Vol. 2: 194-202.
[387] Bundesen C, Habekost T. Attention, In Lamberts K, Goldstone R. (Eds.), Handbook of Cognition[M]. Sage Publications, London, 2004.
[388] 王甦，汪圣安．认知心理学[M]．北京：北京大学出版社，1992．
[389] Treisman A M, Gelade G. A feature-integration theory of attention[J]. Cognitive Psychology, 1980, 12 (1): 97-136.
[390] Wolfe J M. Guided Search 2.0: A Revised Model of Visual Search[J]. Psychonomic Bulletin &Review, 1994, 1 (2): 202-238.
[391] Phaf H R, Heijden V D, Hudson P. SLAM: A connectionist model for attention in visual. selection tasks[J]. Cognitive Psychology, 1990, 22: 273-341.
[392] Humphreys G W, Muller H J. SEarch via recursive rejection (SERR): a connectionist model of visual search[J]. Cognitive Psychology, 1993, 25 (1): 43-110.
[393] Heinke D, Humphreys G W. Selective attention for identification model: simulating visual neglect[J]. Computer Vision and Image Understanding, 2005, 100 (1-2): 172-197.
[394] Mozer M C. The Perception of Multiple Objects-A Connectionist Approach[M]. Cambridge, Boston: The MIT Press, 1991.
[395] Veldea F, Kamps M, Gwendid T. CLAM: Closed-loop attention model for visual search[J]. Neurocomputing, 2004, 58-60: 607-612.
[396] Itti L, Koch C. A saliency-based search mechanism for overt and covert shifts of visual attention[J]. Vision Research, 2000, 40 (10-12): 1489-1506.
[397] Itti L. Models of Bottom-Up and Top-Down Visual Attention[D]. Pasadena, California, USA: California Institute of Technology, 2000.
[398] Milanese R. Detecting Salient Regions in an Image: from Biological Evidence to Computer Implementation[D]. Geneva, Switzerland: University of Geneva, 1993.
[399] Bamidele A, Stentiford F W M, Morphett J. An Attention-Based Approach to Content-Based Image Retrieval[J]. BT Technology Journal, 2004, 22 (3): 151-160.
[400] Tsotsos J K, Culhane S M. Modelling Visual Attention via Selective Tuning[J]. Artificial Intelligence, 1995, 78 (10): 507-545.
[401] 王璐．选择性注意的计算模型[D]．北京：中科院自动化研究所，2003．
[402] Ouerhani N, Archip N, Hangli H. A color image segmentation method based on seeded region growing and visual attention[l]. International. Journal of Image Processing and Communication, 2002, 8 (1): 3-11.
[403] Ouerhani N, Hangli H. MAPS: Multiscale Attention-based PreSegmentation of Color Images[A]. Lecture Notes in Computer Science, 2003, Vol. 2695: 537-549.
[404] Walther D, Rutishauser U, Koch C. Selective visual attention enables learning and recognition of multiple objects in cluttered scenes[J]. Computer Vision and Image Understanding, 2005, 100 (1-2): 41-63.
[405] Frintrop S. VOCUS: A Visual Attention System for Object Detection and Goal-Directed Search[D]. Bonn, Germany: University of Bonn, 2005.
[406] Fan X, Xie X, Ma W Y. Visual attention based image browsing on mobile devices[A]. International Conference on Multimedia and Expo, 2003, Vol. 1: 53-56.
[407] Chen L Q, Xie X, Fan X. A visual attention model for adapting images on small displays[J]. Multimedia Systems, 2003, 9 (4): 353-364.
[408] Gentili S. Retrieving Visual Concepts in Image Databases[D]. Udine, Italy: University of Udine, 2003.
[409] 刘伟，张宏，童勤业．视觉注意计算模型及其在自然图像压缩中的应用[J]．浙江大学学报(工学版)，2007，41(4)：115-119．
[410] 顾凡及，汪云九．侧抑制网络中的信息处理[M]．北京：科学出版社，1983．
[411] 寿天德．视觉信息处理的脑机制[M]．上海：上海科技教育出版社，1997．
[412] (日)福岛邦彦著，(中)马万禄等译．视觉生理与仿生学[M]．北京：科学出版社，1980．
[413] 徐科等．神经生物学纲要[M]．北京：科学出版社，2000．
[414] (日)应用物理学会，光学讨论会编，(中)杨雄里译．生理光学：眼的光学与视觉[M]．北京：科学出版社，1980．
[415] 杨雄里．视觉的神经机制[M]．上海：上海科学技术出版社，1996．
[416] 中国科学院生物物理研究所五室二组译．视觉模式识别译文集[M]．北京：科学出版社，1980．
[417] 吴乐正等．人工视觉[M]．北京：科学出版社，1980．
[418] Riesenhuber M, Poggio T. Models of object recognition[J]. Nature Neuroscience, 2000, supplement 3: 1199-1204.
[419] Thorpe S J, Thorpe M F. Seeking Categories in the Brain[J]. Science, 2002, 291 (5502): 260-262.
[450] 水仁德．特征变化的时空条件对视觉客体表征连续性的影响[D]．杭州：浙江大学，2005．
[451] Li F F, VanRullen R, Koch C. Rapid natural scene categorization in the near absence of attention[J]. Proceedings of National Academy of Sciences, 2002, 99 (14): 9596-9601.
[452] Dillon J C. The Neural Basis of Visual Function (Vision and Visual Dysfunction) [M]. Boca Raton, Florida, USA: CRC Press, 1991.
[453] Luschow A, Nothdurft H C. Pop-out of orientation but no pop-out of motion at isolnminance[J]. Vision Research, 1993, 33 (1): 91-104.
[454] Engel S, Zhang X, Wandell B. Colour tuning in human visual cortex measured with functional magnetic resonance imaging[J]. Nature, 1997, 388 (6637): 68-71.
[455] Devalois R L, Albrecht D G, Thorell L G. Spatial-frequency selectivity of cells in macaque visual cortex[J]. Vision Research, 1982, 22 (5): 545-559.
[456] Tootell R B, Hamilton S L, Silverman M S. Functional anatomy of macaque striate cortex, I: Ocular dominance, binocular interactions and baseline conditions[J]. Journal of Neuroscience, 1988, 8(5): 1500-1530.
[457] Gottlieb J P, Kusunoki M, Goldberg M E. The Representation of Visual Salience in Monkey Parietal Cortex[J]. Nature, 1998, 39 (6666): 481-484.
[458] Kwak H W, Egeth H. Consequences of allocating attention to locations and to other attributes[J]. Perception and Psychophysics, 1992, 51(5): 455-464.
[459] Klein R M. Inhibition of return[J]. Trends in Cognitive Sciences, 2000, 4 (4): 138-147.
[460] Riesenhuber M, Poggio T. Hierarchical models of object recognition in cortex[J]. Nature Neuroscience, 1999, 2 (11): 1019-1025.
[461] Walther D, Itti L, Riesenhuber M. Attentional Selection for Object Recognition-a Gentle Way[A]. Lecture Notes in Computer Science, 2002, Vol. 2525: 472-479.
[462] Golub G H, Loan C F V. Matrix Computations (Third Edition) [M]. Baltimore: Johns Hopkins University Press, 1996.
[463] Wang J, Zucker J D. Solving the multiple-instance problem: a lazy learning approach[EB/OL]. [2007-01437]. http://cogprints.org/2124/00/wang_ICML2000.pdf.
[464] Andrews S, Tsochantaridis I, Hofmann T. Support Vector Machines for Multiple-lnstance Learning[EB/OL]. [2007-01-07]. http://books.nips.cc/papers/files/nips15/AA10.ps.gz.
[465] Parsons S, Bigham J. Possibility theory and the generalised Noisy OR model[EB/OL]. [2007-01-07]. http://citeseer.ist.psu.edu/29278.html.
[466] 钱迪颂(主编)．运筹学(修订版)[M]．北京：清华大学出版社，1990．
[467] Deng Y N, Manjunath B S. Unsupervised segmentation of color-texture regions in images and video[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23 (8): 800-810.
[468] JSEG Project[EB/OL]. [2007-01-22]. http://vision.ece.uesb.edu/segmentation/iseg/.
[469] (美)Kantowitz B H，Roediger H L，Elmes D G著，(中)郭秀艳等译．实验心理学-掌握心理学的研究[M]．上海：华东师范大学出版社，2001．
[470] (美)P H 林赛，DA诺曼著，(中)孙晔，王甦等译．人的信息加工-心理学概论[M]．北京：科学出版社，1987．
[471] (美)托马斯L贝纳特著，(中)旦明译．感觉世界-感觉和知觉导论[M]．北京：科学出版社，1983．
[472] 朱滢．实验心理学[M]．北京：北京大学出版社，2000．
[473] 史忠植，余志华．认知科学和计算机[M]．北京：科学普及出版社，1990．
[474] Allen H T. Assessing Landscape Visual Complexity and It's Relationship to Perceived Scenic Beauty[D]. Utah State University, 1995.
[475] 邹建成，铁小匀．数字图像的二维Arnold变换及其周期性[J]．北方工业大学学报，2000，12(1)：10-14．
[476] Canny J. A Computational Approach to Edge Detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8 (6): 679-698.
[477] 舒华．心理与教育研究中的多因素实验设计[M]．北京：北京师范大学出版社，1994．
[478] Cogent 2000 MATLAB Teolbox[EB/OL]. [2005-07-10].http://www.vislab.ucl.ac.uk/Cogent2000/index.html.
[479] Yanai K, Barnard K. Image region entropy: a measure of "visualness" of web images associated with one concept[A]. Proceedings of the 13th annual ACM international conference on Multimedia, 2005, pp. 419-422.
[480] QBIC Home Page, IBM's Query By Image Content[EB/OL]. [2007-01-03]. http://wwwqbic.almaden.ibm.com/.