基于内容的图象检索研究
|
摘要
随着多媒体技术及Internet技术的迅速发展，各行各业对图象的使用越来越广泛，图象信息资源的管理和检索显得越来越重要，其中基于内容的图象检索(CBIR,Content-based Image Retrieval)已经成为近几年来最活跃的研究领域之一。
基于内容的图象检索技术是指利用图象内容对图象进行查询。图象的内容包括图象的颜色特征、形状特征、纹理特征、语义特征等。本论文主要针对如何描述图象内容，准确、自动地提取特征，以及精确地对图象内容进行相似性度量。本文的主要工作和成果包括：
研究了目前国内外CBIR技术的现状、发展趋势及其应用状况，对基于内容的图象检索系统进行了分析，深入研究了图象检索中的关键技术，包括各种索引技术、相似性度量及其性能评价技术。
提出了一种改进的基于区域的形状索引的图象检索方法。首先基于主要颜色把图象分割成区域，然后把分割后得到的区域用作形状检索的输入。这样就可以把主要颜色区域和形状特征结合起来作为特征进行基于内容的图象检索，而且对平移、旋转和尺度大小具有不变性。试验证明这种方法比改进前的查准率和查全率要高。
提出了一种适合本文的形状特征的相似性度量方法。大量的试验证明了该方法的有效性。
根据上述的检索方法，本文设计了一个简单的图象检索系统。该系统具有可视性好，检索直观、方便的优点，可支持浏览查询和示例查询。
With the development of the technology of multimedia and internet, visual information is used more widely . As a result , the management and retrieval of image information are more important . As a key technique , content-based image retrieval(CBIR) has become one of the most active research areas in the past few years .
Content-based image retrieval(CBIR) is a technique for retrieving images on the basis of image features such as color, texture and shape,etc.
Key issues in CBIR include extracting features from raw images, matching query and stored images in a way that reflects human similarity judgment . The thesis researches how to derive features automatically and how to match image perceptual similarity as well as possible .The main work of the thesis includes:
The thesis researches the present, the future and the application of CBIR ,analyses the CBIR system ,and researches the key techniques of CBIR which consist of all kinds of indexing techniques, similarity measure and performance evaluation .
We propose a low-dimensional region-based shape index to retrieve images. The initial step in our approach is to segment images into regions on dominant colors. Image regions thus obtained after segmentation are used as input to the shape module. The index is invariant to translation, rotation and scaling. Experiment is done to demonstrate that the method is more efficient and effective than the method before modified.
We also propose a new shape similarity measure which is suitable for our method . Experiment is done to demonstrate that the method is more efficient and effective than the method before modified for retrieving images .
We design an actual image retrieval system for the above retrieval method .The system is simple and convenient, and supports query by example and query by scanning.
基于内容的图象检索技术是指利用图象内容对图象进行查询。图象的内容包括图象的颜色特征、形状特征、纹理特征、语义特征等。本论文主要针对如何描述图象内容，准确、自动地提取特征，以及精确地对图象内容进行相似性度量。本文的主要工作和成果包括：
研究了目前国内外CBIR技术的现状、发展趋势及其应用状况，对基于内容的图象检索系统进行了分析，深入研究了图象检索中的关键技术，包括各种索引技术、相似性度量及其性能评价技术。
提出了一种改进的基于区域的形状索引的图象检索方法。首先基于主要颜色把图象分割成区域，然后把分割后得到的区域用作形状检索的输入。这样就可以把主要颜色区域和形状特征结合起来作为特征进行基于内容的图象检索，而且对平移、旋转和尺度大小具有不变性。试验证明这种方法比改进前的查准率和查全率要高。
提出了一种适合本文的形状特征的相似性度量方法。大量的试验证明了该方法的有效性。
根据上述的检索方法，本文设计了一个简单的图象检索系统。该系统具有可视性好，检索直观、方便的优点，可支持浏览查询和示例查询。
With the development of the technology of multimedia and internet, visual information is used more widely . As a result , the management and retrieval of image information are more important . As a key technique , content-based image retrieval(CBIR) has become one of the most active research areas in the past few years .
Content-based image retrieval(CBIR) is a technique for retrieving images on the basis of image features such as color, texture and shape,etc.
Key issues in CBIR include extracting features from raw images, matching query and stored images in a way that reflects human similarity judgment . The thesis researches how to derive features automatically and how to match image perceptual similarity as well as possible .The main work of the thesis includes:
The thesis researches the present, the future and the application of CBIR ,analyses the CBIR system ,and researches the key techniques of CBIR which consist of all kinds of indexing techniques, similarity measure and performance evaluation .
We propose a low-dimensional region-based shape index to retrieve images. The initial step in our approach is to segment images into regions on dominant colors. Image regions thus obtained after segmentation are used as input to the shape module. The index is invariant to translation, rotation and scaling. Experiment is done to demonstrate that the method is more efficient and effective than the method before modified.
We also propose a new shape similarity measure which is suitable for our method . Experiment is done to demonstrate that the method is more efficient and effective than the method before modified for retrieving images .
We design an actual image retrieval system for the above retrieval method .The system is simple and convenient, and supports query by example and query by scanning.
引文
[1] 唐立军，段立娟，高文。基于内容的图象检索系统。中国科学院计算机技术研究所，2001。
[2] Lijuan Duan, Wen Gao. Data Mining in Image Database[C]. Joint Meeting of the 4th World Multiconference on Systemics, Cybemetics and Informatics(SCI2000) and the 6th International Conference on Information System Analysis and Synthesis(ISAS2000), Orlando, USA.
[3] 王文惠。基于内容的图象检索技术研究。国防科技大学博士论文。
[4] 杭燕，杨育彬，陈兆乾。基于内容的图象检索综述。计算机应用研究，2002．9。
[5] Gudivada V N and Raghavan V V, Content-based image retrieval systems, IEEE Computer, 1995, 28(9): 18～22
[6] 李向阳，庄越挺等。基于内容的图象检索技术与系统。计算机研究与发展，2001，38(3)：344～354
[7] 徐曼。基于内容的图象检索技术的研究与系统实现。南京理工大学硕士论文，2002．1。
[8] 曹莉华，柳伟等。基于多种主色调的图象检索算法研究与实现。计算机研究与发展，1999，36(1)：96～100
[9] 吴健康。数字图象分析。人民邮电出版社，1989
[10] 李厚强，刘玫凯等。一种彩色纹理图象的分割方法。计算机学报，2001，24(9)：965～971
[11] 柳伟，李国辉，曹莉华。一种基于内容的图象检索方法的实现，中国图象图形学报，1998，3，4
[12] Mohan S Kankanhail, Babu M Mehtre, Jian Kang Wu, "Cluster-based Color Matching for Image Retrieval", Pattern Recognition, 29(4): 701-707, 1995
[13] 胡晓峰，李国辉。多媒体系统。北京：人民邮电出版社，1997
[14] Jone R Smith, "Integrated Spatial and Feature Image system: Retrieval, Analysis And Compression", Ph.D Thesis, Columbia University, 1997
[15] Markus A Stricker, Alexander Dimai, " Color Indexing with Weak
Spatial Constrains", SPIE 2670: 29-40, 1996
[16]李志刚。基于颜色特征的图象检索匹配算法的研究及其系统的开发。中国农业大学硕士论文，2001，3
[17]李向阳，鲁东明等。基于色彩的图象数据库检索方法的研究。计算机研究于发展，1999，36(3)：359-363
[18]顾燕。基于内容的图象检索方法及其实验系统设计。河海大学硕士论文，2002。
[19]Chiou-Yann Tsai, Arbee L.P.Chen, Kai Essig. Efficient Image retrieval Approaches for Different Similarity Requirements. SPIE.2000, Vol.3972:471-482.
[20]李鹏杰，杨树元。一种基于内容的图象检索系统ImageHunter。微电脑应用，2001，22(3)：138-142
[21]刘忠伟，章毓晋。综合利用颜色和纹理特征的图象检索。通信学报，1999，20(5)：36-40
[22]王志勇，池哲儒等。分形编码在图象检索中的应用。电子学报，2000，28(6)：19-23
[23]刘传才，杨静宇。一种新的图象纹理表示方法。计算机学报，2001，24(11)：1202-1209
[24]汪祖媛，梁栋等．基于树状小波分解的纹理图象检索。中国图象图形学报，2001，6(11)：1065-1069
[25]丁险峰，吴洪等。形状匹配综述。自动化学报，2001，27(9)：678-694
[26]刘威鑫。基于内容的图象信息查询研究。成都理工大学硕士论文，2002。
[27]姚玉荣，章毓晋。利用小波和矩进行基于形状的检索。中国图象图形学报，2000，5(3)：206-210
[28]S.Berretti, A.Del Bimbo and P.Pala Indexed retrieval by shape appearance IEEE Proc.-Vis. Image signal process. Vol. 147 No.4.August 2000:356-362
[29]刘忠伟，章毓晋。综合利用颜色和纹理特征的图象检索。通信学报，1999，20(5)：36-40
[30]Aki Kobayashi, Toshiyuki Yoshida and Yoshinori Sakai. Image Retrieval by Estimating Parameters of Distance Measure. SPIE,2000,Vol.3972:432-441
[31]段立娟，高文，马继勇。Rich Get Richer——图象检索中的一种自适应的相关反馈方法。计算机研究与发展。2001，8：961-965
[32] Cox I J , Miller M L, Omohundro S M et al . Pichunter: Bayesian relevance feedback for image retrieval system. Int'I Conf on Pattern Recognition. 1996:361-369
[33] M.Flickner etal., : Query by image and video content: the qbic system.IEEE Computer. 28(9),1995: 23-32
[34] W.Niblack etal., : The qbic project: Querying images by content using color, texture and shape. In Storage and Retrieval for Image and Video Databases(SPIE). 1908: 173-187
[35] V.E.Ogle and M.Stonebaker.: Chabot: Retrieval from a relation database of images. IEEE Computer. 28(9), 1995:40-48
[36] J.R.Smith and S.F.Chang.: Visualseek: A fully automated content-based image query system. ACM Multimedia. 1996:87-98
[37] C.Carson etal.,: Region-based image querying.: In CVPR'97 Workshop on Content-based Access to Image and Video libraries(CAIVL'97),1997
[38] M.J.Swain and D.H.Ballard,: Color indexing Intl. Journal of Computer Vision. Vol. 7 No. 1, 1991:11-32
[39] J.Hafer etal.,: Efficient color histogram indexing for quadratic form distance functions. PAMI. Vol. 17 No. 7 July,1995:729-736
[40] M.Stricker and A.Dimai.: Color indexing with weak spatial constraints. Proceedings of SPIE Storage and Retrieval of Still Image and Video Database Ⅳ. Vol.2670,1996:29-40
[41] J.Huang etal.: Image indexing using color correlograms. Proceeding of CVPR, 1997:762-768
[42] H.Zhang etal.,: Image retrieval based on color features: an evaluation study. Proceedings of SPIE. Vol.2606,1995:212-220
[43] K.C.Ravishankar, B.G.Prasad,S.K.Gupta and K.K.Biswas.: Dominant Color Region Based Indexing Technique for CBIR. In proceedings of the International Conference on Image Analysis and Proceeding(ICIAP'99). Venice. Italy .Sept, 1999:887-892
[44] X.Wan and C.J.Kuo.: A multiresolution color clustering approach to image indexing and retrieval. Proceedings of ICASSP.1998
[45] R.C.Gonzalez and P.Wintz.: Digital Image Proceeding. 2nd Edition. Addition Wesley. Reading. Mass, 1998
[46] D.Mohamad,G.Sulong and S.S.Ipson.: Trademark Matching using
Invariant Moments. Second Asia Conference on Computer Vision.5-8 Dec,Singapore, 1995
[47] G.Cortelazzo etal.,: Trademark Shapes Description by String-Matching Techniques. Pattern Recognition. 27(8), 1994:1005-1018
[48] A.K.Jain and A.Vailaya.: Image Retrieval using Color and shape. Second Asian Conference on Computer Vision.5-8 Dec.Singapore. 1995:529-533
[49] R.Mehrotra and J.E.Gary.: Similarity-Shape Retrieval in Shape Data Management. IEEE Computer. 28(9), 1995:57-62
[50] H.V.Jagadish.:A Retrieval Technique for Similarity Shapes. Proceedings of ACM SIGMOD. Colorado .ACM.New York. May,2001: 208-217
[51] G.Lu and A.Sajjanhar.: Region-Based Shape Representation and Similarity Measure Suitable for Content-Based Image Retrieval. Multimedia Systems. 7,1999:165-174
[52] K.C.Ravishankar. Color based indexing technique for image retrieval. M.Tech.Thesis, Dept. of CSE, IIT, New Delhi, India, 1998
[53] M.S.Kankanahalli,B.M.Mehtre, and J.K.Wu. Cluster-based color matching for image retrieval. Pattern Recognition,29(4): 701-708,1996
[54] T.F.Syeda-Mahmood. Data and model-driven selection using color regions. International Journal of Computer Vision, 21 (1/2): 9-36,1997.
[55] Color and Shape Index for Region-Based Image Retrieval. www.cse.iitd.emet.in/~bgprasad/20590716, pdf.
[2] Lijuan Duan, Wen Gao. Data Mining in Image Database[C]. Joint Meeting of the 4th World Multiconference on Systemics, Cybemetics and Informatics(SCI2000) and the 6th International Conference on Information System Analysis and Synthesis(ISAS2000), Orlando, USA.
[3] 王文惠。基于内容的图象检索技术研究。国防科技大学博士论文。
[4] 杭燕，杨育彬，陈兆乾。基于内容的图象检索综述。计算机应用研究，2002．9。
[5] Gudivada V N and Raghavan V V, Content-based image retrieval systems, IEEE Computer, 1995, 28(9): 18～22
[6] 李向阳，庄越挺等。基于内容的图象检索技术与系统。计算机研究与发展，2001，38(3)：344～354
[7] 徐曼。基于内容的图象检索技术的研究与系统实现。南京理工大学硕士论文，2002．1。
[8] 曹莉华，柳伟等。基于多种主色调的图象检索算法研究与实现。计算机研究与发展，1999，36(1)：96～100
[9] 吴健康。数字图象分析。人民邮电出版社，1989
[10] 李厚强，刘玫凯等。一种彩色纹理图象的分割方法。计算机学报，2001，24(9)：965～971
[11] 柳伟，李国辉，曹莉华。一种基于内容的图象检索方法的实现，中国图象图形学报，1998，3，4
[12] Mohan S Kankanhail, Babu M Mehtre, Jian Kang Wu, "Cluster-based Color Matching for Image Retrieval", Pattern Recognition, 29(4): 701-707, 1995
[13] 胡晓峰，李国辉。多媒体系统。北京：人民邮电出版社，1997
[14] Jone R Smith, "Integrated Spatial and Feature Image system: Retrieval, Analysis And Compression", Ph.D Thesis, Columbia University, 1997
[15] Markus A Stricker, Alexander Dimai, " Color Indexing with Weak
Spatial Constrains", SPIE 2670: 29-40, 1996
[16]李志刚。基于颜色特征的图象检索匹配算法的研究及其系统的开发。中国农业大学硕士论文，2001，3
[17]李向阳，鲁东明等。基于色彩的图象数据库检索方法的研究。计算机研究于发展，1999，36(3)：359-363
[18]顾燕。基于内容的图象检索方法及其实验系统设计。河海大学硕士论文，2002。
[19]Chiou-Yann Tsai, Arbee L.P.Chen, Kai Essig. Efficient Image retrieval Approaches for Different Similarity Requirements. SPIE.2000, Vol.3972:471-482.
[20]李鹏杰，杨树元。一种基于内容的图象检索系统ImageHunter。微电脑应用，2001，22(3)：138-142
[21]刘忠伟，章毓晋。综合利用颜色和纹理特征的图象检索。通信学报，1999，20(5)：36-40
[22]王志勇，池哲儒等。分形编码在图象检索中的应用。电子学报，2000，28(6)：19-23
[23]刘传才，杨静宇。一种新的图象纹理表示方法。计算机学报，2001，24(11)：1202-1209
[24]汪祖媛，梁栋等．基于树状小波分解的纹理图象检索。中国图象图形学报，2001，6(11)：1065-1069
[25]丁险峰，吴洪等。形状匹配综述。自动化学报，2001，27(9)：678-694
[26]刘威鑫。基于内容的图象信息查询研究。成都理工大学硕士论文，2002。
[27]姚玉荣，章毓晋。利用小波和矩进行基于形状的检索。中国图象图形学报，2000，5(3)：206-210
[28]S.Berretti, A.Del Bimbo and P.Pala Indexed retrieval by shape appearance IEEE Proc.-Vis. Image signal process. Vol. 147 No.4.August 2000:356-362
[29]刘忠伟，章毓晋。综合利用颜色和纹理特征的图象检索。通信学报，1999，20(5)：36-40
[30]Aki Kobayashi, Toshiyuki Yoshida and Yoshinori Sakai. Image Retrieval by Estimating Parameters of Distance Measure. SPIE,2000,Vol.3972:432-441
[31]段立娟，高文，马继勇。Rich Get Richer——图象检索中的一种自适应的相关反馈方法。计算机研究与发展。2001，8：961-965
[32] Cox I J , Miller M L, Omohundro S M et al . Pichunter: Bayesian relevance feedback for image retrieval system. Int'I Conf on Pattern Recognition. 1996:361-369
[33] M.Flickner etal., : Query by image and video content: the qbic system.IEEE Computer. 28(9),1995: 23-32
[34] W.Niblack etal., : The qbic project: Querying images by content using color, texture and shape. In Storage and Retrieval for Image and Video Databases(SPIE). 1908: 173-187
[35] V.E.Ogle and M.Stonebaker.: Chabot: Retrieval from a relation database of images. IEEE Computer. 28(9), 1995:40-48
[36] J.R.Smith and S.F.Chang.: Visualseek: A fully automated content-based image query system. ACM Multimedia. 1996:87-98
[37] C.Carson etal.,: Region-based image querying.: In CVPR'97 Workshop on Content-based Access to Image and Video libraries(CAIVL'97),1997
[38] M.J.Swain and D.H.Ballard,: Color indexing Intl. Journal of Computer Vision. Vol. 7 No. 1, 1991:11-32
[39] J.Hafer etal.,: Efficient color histogram indexing for quadratic form distance functions. PAMI. Vol. 17 No. 7 July,1995:729-736
[40] M.Stricker and A.Dimai.: Color indexing with weak spatial constraints. Proceedings of SPIE Storage and Retrieval of Still Image and Video Database Ⅳ. Vol.2670,1996:29-40
[41] J.Huang etal.: Image indexing using color correlograms. Proceeding of CVPR, 1997:762-768
[42] H.Zhang etal.,: Image retrieval based on color features: an evaluation study. Proceedings of SPIE. Vol.2606,1995:212-220
[43] K.C.Ravishankar, B.G.Prasad,S.K.Gupta and K.K.Biswas.: Dominant Color Region Based Indexing Technique for CBIR. In proceedings of the International Conference on Image Analysis and Proceeding(ICIAP'99). Venice. Italy .Sept, 1999:887-892
[44] X.Wan and C.J.Kuo.: A multiresolution color clustering approach to image indexing and retrieval. Proceedings of ICASSP.1998
[45] R.C.Gonzalez and P.Wintz.: Digital Image Proceeding. 2nd Edition. Addition Wesley. Reading. Mass, 1998
[46] D.Mohamad,G.Sulong and S.S.Ipson.: Trademark Matching using
Invariant Moments. Second Asia Conference on Computer Vision.5-8 Dec,Singapore, 1995
[47] G.Cortelazzo etal.,: Trademark Shapes Description by String-Matching Techniques. Pattern Recognition. 27(8), 1994:1005-1018
[48] A.K.Jain and A.Vailaya.: Image Retrieval using Color and shape. Second Asian Conference on Computer Vision.5-8 Dec.Singapore. 1995:529-533
[49] R.Mehrotra and J.E.Gary.: Similarity-Shape Retrieval in Shape Data Management. IEEE Computer. 28(9), 1995:57-62
[50] H.V.Jagadish.:A Retrieval Technique for Similarity Shapes. Proceedings of ACM SIGMOD. Colorado .ACM.New York. May,2001: 208-217
[51] G.Lu and A.Sajjanhar.: Region-Based Shape Representation and Similarity Measure Suitable for Content-Based Image Retrieval. Multimedia Systems. 7,1999:165-174
[52] K.C.Ravishankar. Color based indexing technique for image retrieval. M.Tech.Thesis, Dept. of CSE, IIT, New Delhi, India, 1998
[53] M.S.Kankanahalli,B.M.Mehtre, and J.K.Wu. Cluster-based color matching for image retrieval. Pattern Recognition,29(4): 701-708,1996
[54] T.F.Syeda-Mahmood. Data and model-driven selection using color regions. International Journal of Computer Vision, 21 (1/2): 9-36,1997.
[55] Color and Shape Index for Region-Based Image Retrieval. www.cse.iitd.emet.in/~bgprasad/20590716, pdf.