基于局部特征的图像检索技术研究
|
摘要
基于内容的图像检索(CBIR)是利用图像本身的信息,借助现有的图像处理技术和构造新的算法来辨别图像特征的机制,并根据每幅图像中的可比较特征来进行检索。目前大量的基于内容的图像检索研究都是全局图像信息,然而在大多数情况下,用户更关心的是图像中具有一定语义的区域,为了达到这种效果,一些图像检索系统中引入了图像自动分割和自动区域提取技术,然而到目前为止还不存在一种通用的方法,同时也没有一个判断分割质量的标准,因而分割结果必然会导致与人的主观认识上的差异,也导致无法准确地提取相关区域的视觉特征,同时也降低了检索结果的效果。为了解决上述问题,本文主要侧重研究基于局部特征的图像检索。研究的具体的方法如下：
提出了一种综合颜色和图像轮廓曲线特征的检索方法。该方法首先分割图像并提取图像中感兴趣对象的轮廓,接着对提取的轮廓进行仿射变换及最小值化处理,经处理后的轮廓带有边缘的完整信息,并具有几何不变性；其次,利用聚类的颜色信息,提取主聚类的直方图,所提取的直方图不仅包含了主聚类的颜色信息也包含了该聚类的空间位置信息。最后,利用检索对象与被检索对象的颜色距离直方图及轮廓曲线距离偏差的加权平均度量检索及被检索对象的相似性。
提出了一种基于感兴趣区域的检索方法,用户需要在整幅图片中选择自己要检索的物体作为检索对象。该算法将Mean shift跟踪的思想运用到基于内容的图像检索中,但经典的Mean Shift跟踪算法利用颜色直方图来跟踪目标,并没有考虑到尺度的变化和目标像素的空间位置,针对上述问题,本文首先提出了一种快速自适应调整窗宽尺度的算法,该算法能够快速、准确的查找检索图像中目标的大小来改变窗宽的尺度,其次,在传统的直方图中加入空间信息,该信息反映目标像素的空间位置,提高跟踪的鲁棒性,最后,利用颜色分布熵来度量两幅图片的相似度,该方法更能真实反映物体的空间结构。实验表明对经典的mean shift做一系列的改进,可以提高跟踪定位的准确性和检索效果的精确性。
开发了一个基于内容的图像检索引擎,该软件实现了基于内容的图像检索的主要方法。该软件基于B/S架构,软件根据图像检索的不同特征及检索需求,实现了四种不同的图像检索方法,其中实现的基于主聚类匹配的图像检索方法是本科研团队独立创新的结果,其主要优点在于该算法在提取特征时不只是局限于单一的特征提取,而是综合了图像的多重特征,从而提高了图像检索的精度。
Content-based image retrieval (CBIR) is a kind of new technique, which applies image low-level information and currently existing processing methods to extract image feature and match between images. Currently most widely used CBIR methods are based on global image information. However, for practical application users are more focus on certain semantic features of an image. In order to achieve rational results, these methods based on image segmentation and auto regional feature extraction are introduced into some image retrieval systems. Unfortunately, so far there is no a general method and a segmentation quality standard. It is obvious that the human perception for vision has subjectivity, because this kind of subjectivity the effectiveness of image retrieval is affected. In order to address the above problems, this paper mainly is devoted to explore such a kind of image retrieval methods based on local feature. In this article, two kinds of new methods are proposed, i.e., an image retrieval method composited of color and shape features, an image retrieval method based on adaptive detecting and extracting an object of interesting (ROI), and an image retrieval engine system based on web has also been developed.
The rest of this article is organized as follows:
An image retrieval method compositing features of color and object contour curve is presented. Firstly, an image is segmented into multi-clusters. Secondly, an interesting object in image is extracted. Furthermore, its contour is extracted. Thirdly, the contour is transformed by affine, and processed by the minimum. The contour contains the whole information of interesting object and preserves geometric invariance. In addition, a histogram for primary cluster with color feature is extracted. Such an extracted histogram contains not only color information but also spatial location information. Finally, a weighted average for color distance histogram and distance deviation of contour curve is applied as similarity measure to match between two images. Experimental results show that the proposed method achieves a better retrieval precision.
Another method, which is called a novel image retrieval method based on region of interest (ROI), combines multiple features with mean shift (MFMS) tracking algorithm and EM scale transformation (EMST). For typical mean shift (MS) tracking method only color histogram is considered, other features, such as spatial distribution and texture feature, are neglected. Hence, it is easy to fall failure during detection ROI. However, in our proposed method spatial distribution is integrated into MS, therefore, intuitively for detecting ROI MFMS is of a more fine effectiveness. In fact, experimental results also show that MFMS is able to detect the position of ROI more accurately and robustly than one of MS. In addition, the EMST uses EM-like algorithm to estimate the local position and covariance matrix, which describes the approximate scale of ROI. It is better to quickly and accurately describe such a scale change in the process of image retrieval.
An image retrieval engine based on web has also been implemented, which is a kind of software package based on CBIR and B/S architecture. With respect to the different user, this software has implemented four different image retrieval functions. A primary clustering matching method, whose advantage is to use multi-features, is proposed by our research team.
提出了一种综合颜色和图像轮廓曲线特征的检索方法。该方法首先分割图像并提取图像中感兴趣对象的轮廓,接着对提取的轮廓进行仿射变换及最小值化处理,经处理后的轮廓带有边缘的完整信息,并具有几何不变性；其次,利用聚类的颜色信息,提取主聚类的直方图,所提取的直方图不仅包含了主聚类的颜色信息也包含了该聚类的空间位置信息。最后,利用检索对象与被检索对象的颜色距离直方图及轮廓曲线距离偏差的加权平均度量检索及被检索对象的相似性。
提出了一种基于感兴趣区域的检索方法,用户需要在整幅图片中选择自己要检索的物体作为检索对象。该算法将Mean shift跟踪的思想运用到基于内容的图像检索中,但经典的Mean Shift跟踪算法利用颜色直方图来跟踪目标,并没有考虑到尺度的变化和目标像素的空间位置,针对上述问题,本文首先提出了一种快速自适应调整窗宽尺度的算法,该算法能够快速、准确的查找检索图像中目标的大小来改变窗宽的尺度,其次,在传统的直方图中加入空间信息,该信息反映目标像素的空间位置,提高跟踪的鲁棒性,最后,利用颜色分布熵来度量两幅图片的相似度,该方法更能真实反映物体的空间结构。实验表明对经典的mean shift做一系列的改进,可以提高跟踪定位的准确性和检索效果的精确性。
开发了一个基于内容的图像检索引擎,该软件实现了基于内容的图像检索的主要方法。该软件基于B/S架构,软件根据图像检索的不同特征及检索需求,实现了四种不同的图像检索方法,其中实现的基于主聚类匹配的图像检索方法是本科研团队独立创新的结果,其主要优点在于该算法在提取特征时不只是局限于单一的特征提取,而是综合了图像的多重特征,从而提高了图像检索的精度。
Content-based image retrieval (CBIR) is a kind of new technique, which applies image low-level information and currently existing processing methods to extract image feature and match between images. Currently most widely used CBIR methods are based on global image information. However, for practical application users are more focus on certain semantic features of an image. In order to achieve rational results, these methods based on image segmentation and auto regional feature extraction are introduced into some image retrieval systems. Unfortunately, so far there is no a general method and a segmentation quality standard. It is obvious that the human perception for vision has subjectivity, because this kind of subjectivity the effectiveness of image retrieval is affected. In order to address the above problems, this paper mainly is devoted to explore such a kind of image retrieval methods based on local feature. In this article, two kinds of new methods are proposed, i.e., an image retrieval method composited of color and shape features, an image retrieval method based on adaptive detecting and extracting an object of interesting (ROI), and an image retrieval engine system based on web has also been developed.
The rest of this article is organized as follows:
An image retrieval method compositing features of color and object contour curve is presented. Firstly, an image is segmented into multi-clusters. Secondly, an interesting object in image is extracted. Furthermore, its contour is extracted. Thirdly, the contour is transformed by affine, and processed by the minimum. The contour contains the whole information of interesting object and preserves geometric invariance. In addition, a histogram for primary cluster with color feature is extracted. Such an extracted histogram contains not only color information but also spatial location information. Finally, a weighted average for color distance histogram and distance deviation of contour curve is applied as similarity measure to match between two images. Experimental results show that the proposed method achieves a better retrieval precision.
Another method, which is called a novel image retrieval method based on region of interest (ROI), combines multiple features with mean shift (MFMS) tracking algorithm and EM scale transformation (EMST). For typical mean shift (MS) tracking method only color histogram is considered, other features, such as spatial distribution and texture feature, are neglected. Hence, it is easy to fall failure during detection ROI. However, in our proposed method spatial distribution is integrated into MS, therefore, intuitively for detecting ROI MFMS is of a more fine effectiveness. In fact, experimental results also show that MFMS is able to detect the position of ROI more accurately and robustly than one of MS. In addition, the EMST uses EM-like algorithm to estimate the local position and covariance matrix, which describes the approximate scale of ROI. It is better to quickly and accurately describe such a scale change in the process of image retrieval.
An image retrieval engine based on web has also been implemented, which is a kind of software package based on CBIR and B/S architecture. With respect to the different user, this software has implemented four different image retrieval functions. A primary clustering matching method, whose advantage is to use multi-features, is proposed by our research team.
引文
[1]J. Hafner et al., Efficient color histogram indexing for quadratic form distance functions [J], IEEE Trans. Pattern Anal. Mach. Intell,1995,17(7):729-736.
[2]M. Stricker, A. Dimai, Color indexing with weak spatial constraints [J], Proc. SPIE, Storage Retrieval Still Image Video Databases Ⅳ,1996,29-40.
[3]Thomas Hurtut,Yann Gousseau, Francis Schmitt. Adaptive image retrieval based on the spatial organization of colors [J]. Computer Vision and Image Understanding,2008:112: 101-113.
[4]C. Lin and R. Chellappa, Classification of partial 2-D shapes using Fourier descriptors, IEEE Trans. Patt. Anal. Mach. Intel,1987,9 (5):686-690.
[5]J. Flusser and T. Suk, Pattern recognition by affine moment invariants [J], Pattern Recognition.1993,26(1):167-174.
[6]E. Rahtu, M. Salo, and J. Heikkil"a, Affine invariant pattern recognition using multiple scale convolution [J], IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005,27(6):908-918.
[7]HaraliekRM, ShanmugamK, Dinstein1. Texture features for image classification [J]. IEEE Transactions On System Man and Cybernetics,1973,3(6):768-780.
[8]Tamura H, MoriS, YamawakiT. Texture features corresponding to visual Perception [J].IEEE Transactions on system Man and Cybernetics,1978,8(6):460-473.
[9]Mao J, JainAK. Texture classification and segmentation using multi-resolution Simultaneous autoregressive models [J].Pattern Recognition,1992,25(2):173-188.
[10]pentland A P. Fraetal-based Description of Natural Scenes [J].IEEE Transactions Pattern Analysis and Madeline Intelligence,1984,6(6):661-674.
[11]C. Yang, R. Duraiswami, and L. Davis. Efficient mean-shift tracking via a new similarity measure, In Proc. IEEE Conf.on Computer Vision and Pattern Recognition (CVPR),2005.
[12]Collins R.T. Mean-Shift blob tracking through scale space [J], Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2003:234-240.
[13]I. Sethi, R.Jain. Finding trajectories of feature points in a monocular image sequence [J], IEEE Trans. Part. Analysis Mach. Intell,1997,19(1):56-73.
[14]N.Paragios, R.Deriche. Geodesic active contours and level sets for the detention and tracking of moving objects [J]. IEEE Trans. ppat. Analy. Mach. Intell,2000, 22(3):266-280.
[15]A.Blake, M.Isard, Active Contours [J], Springer-Verlag,1998.
[16]B.Hom, Sehunk. Determining optical flow [J]. Arific.Intell,1981,17,185-203.
[17]J.Barron, D.Fleel, S. Bceauchemin. Performance of Optical Flow Techniques [J]. IJCV, 1994,12:43-77.
[18]Y.Chen, Y.Rui, T.Huang. JPDAF based hmm for real-time contour tracking [J]. In IEEE Conference on Computer Vision and Pattern Recognition.2001,543-550.
[19]C.Hue, J.L.Cadre, Prez. Sequential Monte carol methods for multiple target tracking and data fusion [J]. IEEE Trans, Sign, Process,2002,.50(2):309-325.
[20]M.Isard, A.Blake. Condensation:Unifying Low-level and high-level tracking in a stochastic framework [J]. Proc of the Fifth European Cof. On Computer Vision. Berlin, 1998,839-908.
[21]J.Maccormick, F.Maccormick. Stochastic algorithms for visual tracking [M]. Paris Telos Press.2003.
[22]M. Flickner, H. Sawhney et al. Query by image and video content [J]. The QBIC System. IEEE Computer,1995,28 (9):23-32.
[23]A. Pentland, R.W. Picard, and S. Sclaroff. Photo book:tools for content-based manipulation of image database[C]. Proc. SPIE,1994,2185:34-47.
[24]Xiao Zhang, Zhiwei Li, Lei Zhang, Wei-Ying Ma, and Heung-Yeung Shum, Efficient Indexing for Large Scale Visual Search [J], in Proc. Internal Conference on Computer Vision (ICCV), Kyoto, Japan, September,2009.
[25]J.R. Smith and S.F. Chang. VisualSEEK:a fully automated content-based image query system[C]. Proc. ACM Multimedia,1996:87-98.
[26]W.Y. Ma and B. Manjunath. NETRA:A toolbox for navigating large image databases[J], Multimedia Systems,1999,7(3).
[27]C. Carson, M. Thomas, S. Belongie, J.M.Hellerstein, and J.Malik.Blobworld:a system for region-based image indexing and retrieval [J]. Proc.Visual Information Systems, 1999:5.9-516.
[28]J.Z. Wang, J. Li, and G. Wiederhold. SIMPLIcity:semantics-sensitive integrated matching for picture libraries [J]. IEEE Trans. on PAMI,2001,23(9):1-17.
[29]Xin-Jing Wang, Mo Yu, Lei Zhang, Rui Cai, Wei-Ying Ma. Argo:Intelligent Advertising by Mining a User's Interest from His Photo Collections, In Proc. of the 3rd Annual International Workshop on Data Mining and Audience Intelligence for Advertising (ADKDD), in conjunction with SIGKDD, Paris, France, June 2009.
[30]Smith J R, Chang S F. VisualSEEK:A Fully Automated Content-Based Image Query System[C]. In Proc. ACM Multimedia,1996:87-98.
[31]M. Swain and D. Ballard, Color indexing, International Journal of Computer Vision [J]. 1991,7(1).
[32]Liang Y M, Zhai H C, Chavel P. Fuzzy color-image retrieval [J]. Optics Columniations, 2002,247-250.
[33]Thomas Hurtut, Yann Gousseau, Francis Schmitt. Adaptive image retrieval based on the spatial organization of colors [J]. Computer Vision and Image Understanding,2008, 112:101-113.
[34]Wenbing Chen, Oizhou Li, Jianwei Yang. Image Retrieval Based on Composite of Mean Shift and Assignment Model [J]. Fifth International Conference on Information Assurance and Security.2009,1568-571.
[35]Plotze, R.O., Falvo, M., Pdua, J.G., Bernacci, L.C., Vieira, M.L.C., Oliveira, G.C.X., Bruno,O.M., Leaf shape analysis using the multi-scale Murkowski fractal dimension, a new morphometric method:a study with Passiflora (Passifloraceae) [J]. Can. J. Botany, 2005,83(3):287-301.
[36]A. Frome, Y. Singer, F. Sha, and J. Malik, Learning Globally-Consistent Local Distance Functions for Shape-Based Image Retrieval and Classification. In ICCV,2007.
[37]Gonzalez, R.C., Woods, R.E., Digital Image Processing [J]. second ed. Prentice Hall. 2002.
[38]Huertas, A., Medioni, G.G. Detection of intensity changes with sub-pixel accuracy using Laplacian-Gaussian masks [J]. IEEE Trans. Pattern Anal. Machine Intell.1986,8(5): 651-664.
[39]Kass, M., Witkin, A., Terzopoulos, D. Snakes:Active contour models[J]. Internat. J. Comput. Vision,1998,1(4):321-331.
[40]Batista, J., Freitas, R. An adaptive gradient-based boundary detector for MRI images of brain [J].In:Image Processing and its Applications,1999,456:440-445.
[41]Wai-Tak Wong, Frank Y. Shih, Jung Liu. Shape-based image retrieval using support vector machines, Fourier descriptors and self-organizing maps. [J]. Information Sciences 2007,177:1878-1891.
[42]Jianguo Zhang, Tieniu Tan. Affine invariant classification and retrieval of texture images [J]. Pattern Recognition,2003,36:657-664.
[43]B.G. Prasad, K.K. Biswas, S.K. Gupta. Region-based image retrieval using integrated color, shape, and location index. [J]. Computer Vision and Image Understanding.2004, 94:193-233.
[44]C.-H. Ko, Y.-P. Tsai, Z.-C. Shih, and Y.-P. Hung, "A new image segmentation method for removing background of object movies by learning shape priors." [J]. inProc. IEEE Int'l Conf. Pattern Recognition,2006.
[45]Cheng Y. Mean shift, mode seeking and clustering [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence,1995,17(8):790-799.
[46]D. Comanicui, P. Meer, Mean shift:a robust approach toward feature space analysis [J].IEEE Trans. Pattern Anal. Mach. Intell.,2002,24(5).
[47]Miguel A, Carreira-Perpinan. Gaussian Mean-Shift Is an EM Algorithm [J].IEEE Trans. Pattern Anal. Mach. Intell,2007,29(5).
[48]Nicolas Zlatoff, Bruno Tellez, Atilla Baskurt. Combining local belief from low-level primitives for perceptual grouping [M]. Pattern Recognition,2008,41:1215-1229.
[49]黄晶,倪林.基于颜色块的半径和角度直方图的图像检索[J]Computer Engineering, 2008,34(10).
[50]Dhiraj Josht Jia Li, Ritendra Datta and James Z.Wang, Image retrieval:Ideas, influences, and trends of the new age [J], ACM Computing Surveys,2008,40,1-60.
[51]J. Li J. Z. Wang and G. Wiederhold, Simplicity:semantics-sensitive integrated matching for picture libraries [J], IEEE Trans. pattern analysis and machine intelligence,2001, 23:947-963.
[52]H.Greenspan J.Malik C.Carson, S.Belongie, Blobword:image segmentation using e-mandates application to image querying [J], IEEE Trans. Pattern analysis and machine intelligence,2002,24:1026-1038.
[53]H.-J. Zhang B. Zhang F. Jing, M. Li, An efficient and effective region-based image retrieval framework[J], IEEE Trans. Amer. Math. Soc,2004,13(5):669-709.
[54]H.Luo G.Xu J.Fan, Y.Gao, Statistical modeling and conceptualization of natural images [J], Pattern recognition,2005,38:865-885.
[55]C.-E.Guo J.Luo, Perceptual grouping of segmented regions in color images [J], Pattern recognition,2003,36:2781-2792.
[56]W.E.L.Grimson, J.W.Hsieh, Spatial template extraction for image retrieval by region matching [J], IEEE Trans. Image Process,2003,12:1404-1415.
[57]Chin-ChunChang Chi-Han Chung, Shyi-ChyiCheng, Adaptive image segmentation for region-based object retrieve valuing generalized Hough transform [J], Pattern recognition, 2010,43:3219-3232.
[58]Y. CHEN and J. Z. WANG, A region-based fuzzy feature matching approach to content based image retrieval [J], IEEE Trans. Pattern Anal.Mach. Intell,2002,24:252-1267.
[59]Y. Tomast C. Rubner and L.J guibas, The earth mover's distance as a metric for image retrieval [J], Int. J. Comput. Vision,2000,40:99-121.
[60]Wang J. Wiederhold G. Li, J., Irm:Integrated region matching for image retrieval, In Proceedings of the ACM international conference on multimedia,2000,147-156.
[61]McGarry K. Tait-J. Tsai, C.-F., Image classification using hybrid neural network [J], In Proceedings of the ACM SIGIR conference on research and development in information retrieval,2003,431-432.
[62]Gao Y.-L. Luo H.-Z. Xu-G.-Y Fan, J.-P., Automatic image annotation by using concept-sensitive salient objects for image content representation [J], In Proceedings of the ACM SIGIR conference on research and development in information retrieval,2004, 361-368.
[63]Philippe-Henri Gosselin Sylvie Philipp-Foliguet, Julien Gony, Frebir:An image retrieval system based on fuzzy region matching [J], Computer Vision and Image Understanding,2009,113:693-707.
[64]Mayron L. Borba G. Gamba H. Marques, O., Using visual attention to extract regions of interest in the context of image retrieval [J], In Proceedings of ACM annual southeast regional conference,2006,638-643
[65]K. A. Hua K. Vu and W. Tavanapong, Image retrieval based on regions of interest [J], IEEE Trans. on Knowledge and Data Engineering,2003,15:1045-1049.
[66]Yi-Tung Liu Rung-Ching Chen Yung-Kuan Chan, Yu-An Ho, A ROI image retrieval method based on CVAAO [J], Image and Vision Computing,2008,26:1540-1549.
[67]James Z. Wang Jia Li, Automatic linguistic indexing of pictures by a statistical modeling approach, IEEE Trans. Pattern Anal. Mach. Intell,2003,25:1075-1088.
[68]James Z. Wang Jia Li, Real-time computerized annotation of pictures [J], IEEE Trans.Pattern Anal. Mach. Intell,2008,30:985-1002.
[69]SUKTHANKAR R. SCHNEIDERMAN H. HOIEM, D. and L. HUS-TON, Object-based image retrieval using the statistical structure of images [J], In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2004.
[70]Christoph H. Lampert, Detecting objects in large image collections and videos by efficient sub-image retrieval [J], in Proc. IEEE Intl. Conf. on Computer Vision (ICCV),2009.
[71]Ramesh V Meer P, Comaniciu D, Kernel-based object tracking [J], IEEE Trans. Pattern Anal. Mach. Intell,2003,25:564-575.
[72]R.T. Collins, Mean-shift blob tracking through scale space [J], Proceedings of the IEE Computer Society Conference on Computer Vision and Pattern Recognition,2003,2: 234-240.
[73]S.T. Birchfield, S. Rangarajan, Hybrid particle filter and mean shift tracker with adaptive transition model [J], IEEE International Conference on Acoustics, Speech, and Signal Processing,2005,221-224.
[74]Z. Zhu, Q. Ji, K. Fujimura, K. Lee, Combining kalman filtering and mean shift for real time eye tracking under active IR illumination [J], in:IEEE International Conference on Pattern Recognition,2002,4.
[75]Imad Zoghlami Vasu Parameswaran, Visvanathan Ramesh, Tunable kernels for tracking, IEEE Comput. Soc. Conf. on Computer Vision and Pattern Recognition [J],2006, 2179-2186.
[76]Ben Kroose Zoran Zivkovic, An em-like algorithm for color histogram based object tracking [J], IEEE Comput. Soc. Conf. on Computer Vision and Pattern Recognition, 2004,798-803.
[77]P. Bouthemy R.V. Babu, P. Prez, Robust tracking with motion estimation and local kernel-based color modeling [J], Image and Vision Computing,2007,1205-1216.
[78]Jiangtao Cuib Lihua Zhoub Junding Suna, Ximin Zhangb, Image retrieval based on color distribution entropy [J], Pattern Recognition Letter,2006,1122-1126.
[2]M. Stricker, A. Dimai, Color indexing with weak spatial constraints [J], Proc. SPIE, Storage Retrieval Still Image Video Databases Ⅳ,1996,29-40.
[3]Thomas Hurtut,Yann Gousseau, Francis Schmitt. Adaptive image retrieval based on the spatial organization of colors [J]. Computer Vision and Image Understanding,2008:112: 101-113.
[4]C. Lin and R. Chellappa, Classification of partial 2-D shapes using Fourier descriptors, IEEE Trans. Patt. Anal. Mach. Intel,1987,9 (5):686-690.
[5]J. Flusser and T. Suk, Pattern recognition by affine moment invariants [J], Pattern Recognition.1993,26(1):167-174.
[6]E. Rahtu, M. Salo, and J. Heikkil"a, Affine invariant pattern recognition using multiple scale convolution [J], IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005,27(6):908-918.
[7]HaraliekRM, ShanmugamK, Dinstein1. Texture features for image classification [J]. IEEE Transactions On System Man and Cybernetics,1973,3(6):768-780.
[8]Tamura H, MoriS, YamawakiT. Texture features corresponding to visual Perception [J].IEEE Transactions on system Man and Cybernetics,1978,8(6):460-473.
[9]Mao J, JainAK. Texture classification and segmentation using multi-resolution Simultaneous autoregressive models [J].Pattern Recognition,1992,25(2):173-188.
[10]pentland A P. Fraetal-based Description of Natural Scenes [J].IEEE Transactions Pattern Analysis and Madeline Intelligence,1984,6(6):661-674.
[11]C. Yang, R. Duraiswami, and L. Davis. Efficient mean-shift tracking via a new similarity measure, In Proc. IEEE Conf.on Computer Vision and Pattern Recognition (CVPR),2005.
[12]Collins R.T. Mean-Shift blob tracking through scale space [J], Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2003:234-240.
[13]I. Sethi, R.Jain. Finding trajectories of feature points in a monocular image sequence [J], IEEE Trans. Part. Analysis Mach. Intell,1997,19(1):56-73.
[14]N.Paragios, R.Deriche. Geodesic active contours and level sets for the detention and tracking of moving objects [J]. IEEE Trans. ppat. Analy. Mach. Intell,2000, 22(3):266-280.
[15]A.Blake, M.Isard, Active Contours [J], Springer-Verlag,1998.
[16]B.Hom, Sehunk. Determining optical flow [J]. Arific.Intell,1981,17,185-203.
[17]J.Barron, D.Fleel, S. Bceauchemin. Performance of Optical Flow Techniques [J]. IJCV, 1994,12:43-77.
[18]Y.Chen, Y.Rui, T.Huang. JPDAF based hmm for real-time contour tracking [J]. In IEEE Conference on Computer Vision and Pattern Recognition.2001,543-550.
[19]C.Hue, J.L.Cadre, Prez. Sequential Monte carol methods for multiple target tracking and data fusion [J]. IEEE Trans, Sign, Process,2002,.50(2):309-325.
[20]M.Isard, A.Blake. Condensation:Unifying Low-level and high-level tracking in a stochastic framework [J]. Proc of the Fifth European Cof. On Computer Vision. Berlin, 1998,839-908.
[21]J.Maccormick, F.Maccormick. Stochastic algorithms for visual tracking [M]. Paris Telos Press.2003.
[22]M. Flickner, H. Sawhney et al. Query by image and video content [J]. The QBIC System. IEEE Computer,1995,28 (9):23-32.
[23]A. Pentland, R.W. Picard, and S. Sclaroff. Photo book:tools for content-based manipulation of image database[C]. Proc. SPIE,1994,2185:34-47.
[24]Xiao Zhang, Zhiwei Li, Lei Zhang, Wei-Ying Ma, and Heung-Yeung Shum, Efficient Indexing for Large Scale Visual Search [J], in Proc. Internal Conference on Computer Vision (ICCV), Kyoto, Japan, September,2009.
[25]J.R. Smith and S.F. Chang. VisualSEEK:a fully automated content-based image query system[C]. Proc. ACM Multimedia,1996:87-98.
[26]W.Y. Ma and B. Manjunath. NETRA:A toolbox for navigating large image databases[J], Multimedia Systems,1999,7(3).
[27]C. Carson, M. Thomas, S. Belongie, J.M.Hellerstein, and J.Malik.Blobworld:a system for region-based image indexing and retrieval [J]. Proc.Visual Information Systems, 1999:5.9-516.
[28]J.Z. Wang, J. Li, and G. Wiederhold. SIMPLIcity:semantics-sensitive integrated matching for picture libraries [J]. IEEE Trans. on PAMI,2001,23(9):1-17.
[29]Xin-Jing Wang, Mo Yu, Lei Zhang, Rui Cai, Wei-Ying Ma. Argo:Intelligent Advertising by Mining a User's Interest from His Photo Collections, In Proc. of the 3rd Annual International Workshop on Data Mining and Audience Intelligence for Advertising (ADKDD), in conjunction with SIGKDD, Paris, France, June 2009.
[30]Smith J R, Chang S F. VisualSEEK:A Fully Automated Content-Based Image Query System[C]. In Proc. ACM Multimedia,1996:87-98.
[31]M. Swain and D. Ballard, Color indexing, International Journal of Computer Vision [J]. 1991,7(1).
[32]Liang Y M, Zhai H C, Chavel P. Fuzzy color-image retrieval [J]. Optics Columniations, 2002,247-250.
[33]Thomas Hurtut, Yann Gousseau, Francis Schmitt. Adaptive image retrieval based on the spatial organization of colors [J]. Computer Vision and Image Understanding,2008, 112:101-113.
[34]Wenbing Chen, Oizhou Li, Jianwei Yang. Image Retrieval Based on Composite of Mean Shift and Assignment Model [J]. Fifth International Conference on Information Assurance and Security.2009,1568-571.
[35]Plotze, R.O., Falvo, M., Pdua, J.G., Bernacci, L.C., Vieira, M.L.C., Oliveira, G.C.X., Bruno,O.M., Leaf shape analysis using the multi-scale Murkowski fractal dimension, a new morphometric method:a study with Passiflora (Passifloraceae) [J]. Can. J. Botany, 2005,83(3):287-301.
[36]A. Frome, Y. Singer, F. Sha, and J. Malik, Learning Globally-Consistent Local Distance Functions for Shape-Based Image Retrieval and Classification. In ICCV,2007.
[37]Gonzalez, R.C., Woods, R.E., Digital Image Processing [J]. second ed. Prentice Hall. 2002.
[38]Huertas, A., Medioni, G.G. Detection of intensity changes with sub-pixel accuracy using Laplacian-Gaussian masks [J]. IEEE Trans. Pattern Anal. Machine Intell.1986,8(5): 651-664.
[39]Kass, M., Witkin, A., Terzopoulos, D. Snakes:Active contour models[J]. Internat. J. Comput. Vision,1998,1(4):321-331.
[40]Batista, J., Freitas, R. An adaptive gradient-based boundary detector for MRI images of brain [J].In:Image Processing and its Applications,1999,456:440-445.
[41]Wai-Tak Wong, Frank Y. Shih, Jung Liu. Shape-based image retrieval using support vector machines, Fourier descriptors and self-organizing maps. [J]. Information Sciences 2007,177:1878-1891.
[42]Jianguo Zhang, Tieniu Tan. Affine invariant classification and retrieval of texture images [J]. Pattern Recognition,2003,36:657-664.
[43]B.G. Prasad, K.K. Biswas, S.K. Gupta. Region-based image retrieval using integrated color, shape, and location index. [J]. Computer Vision and Image Understanding.2004, 94:193-233.
[44]C.-H. Ko, Y.-P. Tsai, Z.-C. Shih, and Y.-P. Hung, "A new image segmentation method for removing background of object movies by learning shape priors." [J]. inProc. IEEE Int'l Conf. Pattern Recognition,2006.
[45]Cheng Y. Mean shift, mode seeking and clustering [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence,1995,17(8):790-799.
[46]D. Comanicui, P. Meer, Mean shift:a robust approach toward feature space analysis [J].IEEE Trans. Pattern Anal. Mach. Intell.,2002,24(5).
[47]Miguel A, Carreira-Perpinan. Gaussian Mean-Shift Is an EM Algorithm [J].IEEE Trans. Pattern Anal. Mach. Intell,2007,29(5).
[48]Nicolas Zlatoff, Bruno Tellez, Atilla Baskurt. Combining local belief from low-level primitives for perceptual grouping [M]. Pattern Recognition,2008,41:1215-1229.
[49]黄晶,倪林.基于颜色块的半径和角度直方图的图像检索[J]Computer Engineering, 2008,34(10).
[50]Dhiraj Josht Jia Li, Ritendra Datta and James Z.Wang, Image retrieval:Ideas, influences, and trends of the new age [J], ACM Computing Surveys,2008,40,1-60.
[51]J. Li J. Z. Wang and G. Wiederhold, Simplicity:semantics-sensitive integrated matching for picture libraries [J], IEEE Trans. pattern analysis and machine intelligence,2001, 23:947-963.
[52]H.Greenspan J.Malik C.Carson, S.Belongie, Blobword:image segmentation using e-mandates application to image querying [J], IEEE Trans. Pattern analysis and machine intelligence,2002,24:1026-1038.
[53]H.-J. Zhang B. Zhang F. Jing, M. Li, An efficient and effective region-based image retrieval framework[J], IEEE Trans. Amer. Math. Soc,2004,13(5):669-709.
[54]H.Luo G.Xu J.Fan, Y.Gao, Statistical modeling and conceptualization of natural images [J], Pattern recognition,2005,38:865-885.
[55]C.-E.Guo J.Luo, Perceptual grouping of segmented regions in color images [J], Pattern recognition,2003,36:2781-2792.
[56]W.E.L.Grimson, J.W.Hsieh, Spatial template extraction for image retrieval by region matching [J], IEEE Trans. Image Process,2003,12:1404-1415.
[57]Chin-ChunChang Chi-Han Chung, Shyi-ChyiCheng, Adaptive image segmentation for region-based object retrieve valuing generalized Hough transform [J], Pattern recognition, 2010,43:3219-3232.
[58]Y. CHEN and J. Z. WANG, A region-based fuzzy feature matching approach to content based image retrieval [J], IEEE Trans. Pattern Anal.Mach. Intell,2002,24:252-1267.
[59]Y. Tomast C. Rubner and L.J guibas, The earth mover's distance as a metric for image retrieval [J], Int. J. Comput. Vision,2000,40:99-121.
[60]Wang J. Wiederhold G. Li, J., Irm:Integrated region matching for image retrieval, In Proceedings of the ACM international conference on multimedia,2000,147-156.
[61]McGarry K. Tait-J. Tsai, C.-F., Image classification using hybrid neural network [J], In Proceedings of the ACM SIGIR conference on research and development in information retrieval,2003,431-432.
[62]Gao Y.-L. Luo H.-Z. Xu-G.-Y Fan, J.-P., Automatic image annotation by using concept-sensitive salient objects for image content representation [J], In Proceedings of the ACM SIGIR conference on research and development in information retrieval,2004, 361-368.
[63]Philippe-Henri Gosselin Sylvie Philipp-Foliguet, Julien Gony, Frebir:An image retrieval system based on fuzzy region matching [J], Computer Vision and Image Understanding,2009,113:693-707.
[64]Mayron L. Borba G. Gamba H. Marques, O., Using visual attention to extract regions of interest in the context of image retrieval [J], In Proceedings of ACM annual southeast regional conference,2006,638-643
[65]K. A. Hua K. Vu and W. Tavanapong, Image retrieval based on regions of interest [J], IEEE Trans. on Knowledge and Data Engineering,2003,15:1045-1049.
[66]Yi-Tung Liu Rung-Ching Chen Yung-Kuan Chan, Yu-An Ho, A ROI image retrieval method based on CVAAO [J], Image and Vision Computing,2008,26:1540-1549.
[67]James Z. Wang Jia Li, Automatic linguistic indexing of pictures by a statistical modeling approach, IEEE Trans. Pattern Anal. Mach. Intell,2003,25:1075-1088.
[68]James Z. Wang Jia Li, Real-time computerized annotation of pictures [J], IEEE Trans.Pattern Anal. Mach. Intell,2008,30:985-1002.
[69]SUKTHANKAR R. SCHNEIDERMAN H. HOIEM, D. and L. HUS-TON, Object-based image retrieval using the statistical structure of images [J], In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2004.
[70]Christoph H. Lampert, Detecting objects in large image collections and videos by efficient sub-image retrieval [J], in Proc. IEEE Intl. Conf. on Computer Vision (ICCV),2009.
[71]Ramesh V Meer P, Comaniciu D, Kernel-based object tracking [J], IEEE Trans. Pattern Anal. Mach. Intell,2003,25:564-575.
[72]R.T. Collins, Mean-shift blob tracking through scale space [J], Proceedings of the IEE Computer Society Conference on Computer Vision and Pattern Recognition,2003,2: 234-240.
[73]S.T. Birchfield, S. Rangarajan, Hybrid particle filter and mean shift tracker with adaptive transition model [J], IEEE International Conference on Acoustics, Speech, and Signal Processing,2005,221-224.
[74]Z. Zhu, Q. Ji, K. Fujimura, K. Lee, Combining kalman filtering and mean shift for real time eye tracking under active IR illumination [J], in:IEEE International Conference on Pattern Recognition,2002,4.
[75]Imad Zoghlami Vasu Parameswaran, Visvanathan Ramesh, Tunable kernels for tracking, IEEE Comput. Soc. Conf. on Computer Vision and Pattern Recognition [J],2006, 2179-2186.
[76]Ben Kroose Zoran Zivkovic, An em-like algorithm for color histogram based object tracking [J], IEEE Comput. Soc. Conf. on Computer Vision and Pattern Recognition, 2004,798-803.
[77]P. Bouthemy R.V. Babu, P. Prez, Robust tracking with motion estimation and local kernel-based color modeling [J], Image and Vision Computing,2007,1205-1216.
[78]Jiangtao Cuib Lihua Zhoub Junding Suna, Ximin Zhangb, Image retrieval based on color distribution entropy [J], Pattern Recognition Letter,2006,1122-1126.