基于内容的图像检索相关技术研究
|
摘要
随着数据库技术、多媒体技术以及计算机视觉技术的快速发展，图像作为一种重要的多媒体信息的载体，已经广泛地应用于众多领域。为了方便用户能够快速地、准确地从海量的图像资源中找到自己所需要的图像，基于内容的图像检索(CBIR)技术正逐渐成为目前研究的热点。
本文在理解和掌握基于内容的图像检索技术相关领域知识的基础上，主要对图像特征的提取方法进行了深入地研究，并完成了以下工作：
1、由于基于HSV空间的颜色直方图法不能有效地表达图像颜色分布的空间信息，所以本文在颜色直方图法的基础上，对图像颜色特征提取算法做了一些改进。在改进的分块主色法中，本文采用了一种矩形重叠式分块策略对图像进行分块来反映图像颜色分布的空间信息，同时也有效地弥补了传统分块策略没有考虑分块间联系的缺陷；在颜色聚合矢量法中，采用了更加符合人的视觉感受的HSV颜色空间模型来描述图像的颜色聚合矢量。最后通过实验验证了上述颜色提取算法的有效性，并对它们的性能进行了比较分析。
2、在基于改进的分块主色法的图像检索系统中引入了一种相关反馈机制，其主要思想是通过用户对检索结果的反馈信息获得一个反馈图像集，然后通过计算反馈图像集对应分块距离的加权方差来动态调整权值数组中的权重系数，最后利用新的权值数组进行图像检索。通过实验表明该相关反馈策略能够提高系统的查准率，能够更加有效地检索出用户所需的图像。
3、为了融合多种特征进行图像检索，提高系统的检索性能，本文主要对综合颜色特征和纹理特征的图像检索方法进行了研究，并实现了综合改进的分块主色法和灰度共生矩阵算法的图像检索方法，最后通过实验表明采用该图像检索方法能够有效地提高系统的查准率。
4、本文把基于内容的图像检索技术应用到CGProject项目的资源搜索模块中，设计并实现了一个图像检索系统CGProImageSearch系统，该系统在图像检索性能上做了一些优化，实验表明该系统在CGProject项目中具有良好的实用性。
Along with the development of computer vision, Multimedia and database technology, image information, a main kind of multimedia information, is widely used in many fields. In order to retrieval the images which user want to find quickly and accurately from large amount of images, so Content-based image retrieval (CBIR) technology has been studied a lot currently.
Based on the understanding of the content on CBIR and its related fields technology, this paper sets focus on the feature extraction of image, and the main research content of this paper include the following aspects.
Firstly, since HSV color histogram can't describe spatial information effectively, so this paper has made some modification on the retrieving algorithm of color feature. In the color indexing approach using the dominant colors of multi-resolution partitions uses an overlapping rectangle multi-resolution partitions way, and makes up the deficiency of traditional multi-resolution partitions ways; in the approach of Color Coherence Vectors, this paper chooses the HSV color model. By the experiment, this paper validates the feasibility of the above extracting color feature algorithms.
Secondly, in order to design an effective mechanism of relevance feedback using in image retrieval system based on color feature, this paper has studied and realized a color feature re-weighting approach for relevance feedback. With plentiful experiments, it is proved that the efficiency can be enhanced by using this method.
Thirdly, in order to use Multiple Features in image retrieval system, this paper has studied the image retrieval method using color feature and texture feature. To represent the color content of an image, the color indexing approach using the dominant colors of multi-resolution partitions is used. To represent texture feature, gray co-occurrence matrix is computed. Through the image retrieval experiment, better image retrieval performance can be achieved by combing two kinds of features.
At last, this paper has realized an image retrieval system, and this system can help users retrieval images they need more effectively from a large image library.
本文在理解和掌握基于内容的图像检索技术相关领域知识的基础上，主要对图像特征的提取方法进行了深入地研究，并完成了以下工作：
1、由于基于HSV空间的颜色直方图法不能有效地表达图像颜色分布的空间信息，所以本文在颜色直方图法的基础上，对图像颜色特征提取算法做了一些改进。在改进的分块主色法中，本文采用了一种矩形重叠式分块策略对图像进行分块来反映图像颜色分布的空间信息，同时也有效地弥补了传统分块策略没有考虑分块间联系的缺陷；在颜色聚合矢量法中，采用了更加符合人的视觉感受的HSV颜色空间模型来描述图像的颜色聚合矢量。最后通过实验验证了上述颜色提取算法的有效性，并对它们的性能进行了比较分析。
2、在基于改进的分块主色法的图像检索系统中引入了一种相关反馈机制，其主要思想是通过用户对检索结果的反馈信息获得一个反馈图像集，然后通过计算反馈图像集对应分块距离的加权方差来动态调整权值数组中的权重系数，最后利用新的权值数组进行图像检索。通过实验表明该相关反馈策略能够提高系统的查准率，能够更加有效地检索出用户所需的图像。
3、为了融合多种特征进行图像检索，提高系统的检索性能，本文主要对综合颜色特征和纹理特征的图像检索方法进行了研究，并实现了综合改进的分块主色法和灰度共生矩阵算法的图像检索方法，最后通过实验表明采用该图像检索方法能够有效地提高系统的查准率。
4、本文把基于内容的图像检索技术应用到CGProject项目的资源搜索模块中，设计并实现了一个图像检索系统CGProImageSearch系统，该系统在图像检索性能上做了一些优化，实验表明该系统在CGProject项目中具有良好的实用性。
Along with the development of computer vision, Multimedia and database technology, image information, a main kind of multimedia information, is widely used in many fields. In order to retrieval the images which user want to find quickly and accurately from large amount of images, so Content-based image retrieval (CBIR) technology has been studied a lot currently.
Based on the understanding of the content on CBIR and its related fields technology, this paper sets focus on the feature extraction of image, and the main research content of this paper include the following aspects.
Firstly, since HSV color histogram can't describe spatial information effectively, so this paper has made some modification on the retrieving algorithm of color feature. In the color indexing approach using the dominant colors of multi-resolution partitions uses an overlapping rectangle multi-resolution partitions way, and makes up the deficiency of traditional multi-resolution partitions ways; in the approach of Color Coherence Vectors, this paper chooses the HSV color model. By the experiment, this paper validates the feasibility of the above extracting color feature algorithms.
Secondly, in order to design an effective mechanism of relevance feedback using in image retrieval system based on color feature, this paper has studied and realized a color feature re-weighting approach for relevance feedback. With plentiful experiments, it is proved that the efficiency can be enhanced by using this method.
Thirdly, in order to use Multiple Features in image retrieval system, this paper has studied the image retrieval method using color feature and texture feature. To represent the color content of an image, the color indexing approach using the dominant colors of multi-resolution partitions is used. To represent texture feature, gray co-occurrence matrix is computed. Through the image retrieval experiment, better image retrieval performance can be achieved by combing two kinds of features.
At last, this paper has realized an image retrieval system, and this system can help users retrieval images they need more effectively from a large image library.
引文
1 Pei Cheng Cheng, Jen Yuan Yeh et al. Comparison and Combination of Textual and Visual Features for Interactive Image Retrieval. ImageCLEE 2004,621-630.
2 李向阳，庄越挺，潘云鹤．基于内容的图像检索技术与系统．计算机研究与发展．2001，38(3)：347-352．
3 Niblack W, Barber R, Equitz W et al. The QBIC project: Querying images by content using color, texture, and shape. In: Proc SPIE Electronic Imaging: Science and Technology. San Jose, CA, 1993.
4 Bach J R, Fuller Charles, Copt Aet al. The Virage image search engine: An open framework for image management. In Proc of SPIE: Storage and retrieval for Still Image and Video Database Ⅳ. San Jose, 1996:76-87.
5 Smith J R, Chang S f. VisualSEEK: A fully automated content-based image query system. In: The Fourth ACM Int'l Multimedia Conf 96 Proc (ACM Multimedia 96). Boston, 1996.
6 王文惠，周良柱，万建伟．基于内容的图像检索技术的研究和发展．计算机工程与应用．2001，22(5)：54-56．
7 Moores. CN Data coding applied to mechanical organization knowledge. A m Doc2, 1951: 20-32.
8 Wang C J, Yang Y B, Chen S F. Algorithms of high-level semantic-based image retrieval. Journal of Software, 2004,15(10): 1461～1469.
9 B. Y. Ricardo, R. N. Berthier. Modern Information Retrieval.机械工业出版社.2004.
10 M. J. Swain, D. H. Ballard. Color indexing. International journal of Computer Vision, 1991, 7(1): 11-32.
11 G. Pass, R. Zabih, J. Miller. Comparing images using color coherence vectors. Proceedings of 4th ACM Conference on Multimedia. Boston, 1996:65-73.
12 M. Stricker, M. Orengo. Similarity of color images. Proceedings of SPIE Storage and Retrieval for Image and Video Databases Ⅲ. San Jose ,1995:381-392.
13 W. Hsu, T. S. Chua et al. An integrated color-spatial approach to content-based image retrieval, Proc. ACM Multimedia Conference, 1995:305-313.
14 葛小菁，张宏喜，李兰英．图像检索中纹理特征提取的研究．哈尔滨理工大学学报．2005，10(1)：122-124．
15 R. M. Haralick, K. Shanmugam, Texture features for image classification, IEEE Transactions on Systems,Man and Cybernetics,1973:610-623.
16 H. Tamura ,S. Mori, T. Yamawaki, Texture features corresponding to visual perception, IEEE Transactions On Systems, Man, and Cybernetics, 8(6),1978:460-473.
17 J.R. Smith, S. F. Chang, Automated binary texture feature sets for image retrieval, Proceedings of IEEE international conference on Acoustics, Speech and signal processing ,Atlanta, 1996:2239-2242.
18 T. H. Chang, C. J. Kuo, Texture analysis and classification with tree-structured wavelet transform, IEEE Transactions on Image Processing,1993,2(4):429-441.
19 W. Y. Ma ,B. S. Manjunath, A comparison of wavelet transform features for textures image annotation, Proceedings of IEEE international conference on Image Processing. 1995:256-259.
20 E.G. Simona, Nicolai Petkov, Peter Kruizinga. Comparison of Texture Features Based on Gabor Filters. IEEE Transactions on Image Processing.2002,11(10): 1160-1167.
21 陆军，王润生．区域结构及多尺度纹理分析．国防科技大学学报，2000，22(6)：91-95．
22 史萍，吕四化．基于形状图像检索系统的设计和实现．中国传媒大学学报自然科学版．2006，13(3)：87-92．
23 蔡菲，蔡珣，史同广．一种基于形状特征的图像检索方法．计算机应用与软件．2005，22(12)：44-49．
24 封筠，王彦芳，王小平．小波分析在基于内容的图像检索技术中的应用．微计算机信息．2006，22(13)：223-227．
25 章志勇，潘志庚，张明敏．基于多尺度通用傅里叶描述子的灰度图像检索．中国图像图形学报2005，10(5)：611-615．
26 曲桂红，张大力，阎平凡．数字空间轮廓的小波描述子．电子与信息学报，2002，24(6)：794-799．
27 M.K.Hu, visual pattern recognition by moment invariants, IEEE Transactions on Information Theory, 1962,8(2): 179-187.
28 黄勇，王崇骏，王亮等．基于形状不变矩的图像检索算法的研究．计算机应用研究．2004，22(7)：256-260．
29 贺玲，吴玲达，蔡益朝．基于内容图像检索中的索引技术．计算机应用研究．2005，22(11)：34-38．
30 卢佳，宋余庆，周成兵．图像数据库索引技术的研究与探讨．计算机工程与设计．2005，26(7)：1759-1761．
31 A. Guttman, R-trees: a dynamic index structure for spatial searching, Proceedings of ACM SIGMOD international conference on Management of Data, 1984:47-57.
32 N. Beckmann, H. P. Kriegel, R. Schneider, et al, The R~*-Tree: An efficient and robust access method for points and rectangles, Proceedings of ACM SIGMOD international conference on Management of Data,1990:322-331.
33 D. A. White, R. Jain, Similarity indexing with the SS-tree, Proceedings of the Twelfth International Conference on Data Engineering, 1996:516-523.
34 陈沽，石跃祥．基于SVM的图像低层特征与高层语义的关联．计算机应用研究．2006，23(9)：250-252．
35 邢伟利．图像检索中颜色的特征提取及匹配算法．微机发展．2004，14(2)：86-88．
36 Tversky A. Features of similarity. Psychological Review, 1977, 8(4):327-352.
37 Yossi Rubner,Jan Puzicha. Empirical Evaluation of Dissimilarity Measures for Color and Texture. Computer Vision and Image Understanding, 2001,8(4):25-43.
38 Aki Kobayashi, Toshiyuki Yoshida, et al. Image Retrieval by Estimating Parameters of Distance Measure. SPIE. 2000, 39(72):432-441.
39 Zhong Su, Hongjiang Zhang, Stan Li et al. Relevance Feedback in Content-Based Image Retrieval: Bayesian Framework, Feature Subspaces, and Progressive Learning[J]. IEEE Transactions on Image Processing,2003,12(8):924-936.
40 Y Rui,T S Huang, M Ortega et al. Relevance feedback: A power tool for interactive content-based image retrieval[J].IEEE Transaction on Circuits and Video Technology, 1998,8(5): 644-655.
41 Yimin Wu, Aidong Zhang. A feature re-weighting approach for relevance feedback in image retrieval[C].In: International Conference on Image Processing, Proceedings, 2002(2):581-584.
42 Ye Lu, Hongjiang Zhang, Wenyin Liu et al. Joint semantics and feature based image retrieval using relevance feedback[J].IEEE Transactions on Multimedia, 2003,5(3):339-347.
43 R．C．Gonzalez，R，E．Woods．阮秋琦，阮宇智译．数字图像处理(第二版)．北京：电子工业出版社，2006：224-233．
44 J. Scharcanski, H.C. Shen, et al. Color quantization for color texture analysis. Proceedings of Computers and Digital Techniques, 1993:109-114.
45 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．
46 冀亚丽．基于内容的鲁棒的图像方法的研究和系统实现．西南师范大学．硕士论文．2005．
47 何清法，李国杰．综合分块主色和相关反馈技术的图像检索方法．计算机辅助设计与图形学学报，2001(10)：912-917．
48 Anne H. H. Ngu, Quan Z. Sheng. Combing Multi-visual Feature for Efficient Indexing in a Large Image Database. In VLDB. 2001,9:279-293.
49 Seyoon Jeong, Kyuheon Kim, et al. An Effective Method for Combining Multiple Features of Imgge Retrieval. IEEE Transaction On Tencon. 1999.
50 Y. Rui, T.S. Huang, S. Mehrotra. A Relevance Feedback Architecture in Content-Based Multimedia Information. In Proceedings of IEEE Workshop on Content-Based Access of Image and Video Libraries. June 1997:82-89.
2 李向阳，庄越挺，潘云鹤．基于内容的图像检索技术与系统．计算机研究与发展．2001，38(3)：347-352．
3 Niblack W, Barber R, Equitz W et al. The QBIC project: Querying images by content using color, texture, and shape. In: Proc SPIE Electronic Imaging: Science and Technology. San Jose, CA, 1993.
4 Bach J R, Fuller Charles, Copt Aet al. The Virage image search engine: An open framework for image management. In Proc of SPIE: Storage and retrieval for Still Image and Video Database Ⅳ. San Jose, 1996:76-87.
5 Smith J R, Chang S f. VisualSEEK: A fully automated content-based image query system. In: The Fourth ACM Int'l Multimedia Conf 96 Proc (ACM Multimedia 96). Boston, 1996.
6 王文惠，周良柱，万建伟．基于内容的图像检索技术的研究和发展．计算机工程与应用．2001，22(5)：54-56．
7 Moores. CN Data coding applied to mechanical organization knowledge. A m Doc2, 1951: 20-32.
8 Wang C J, Yang Y B, Chen S F. Algorithms of high-level semantic-based image retrieval. Journal of Software, 2004,15(10): 1461～1469.
9 B. Y. Ricardo, R. N. Berthier. Modern Information Retrieval.机械工业出版社.2004.
10 M. J. Swain, D. H. Ballard. Color indexing. International journal of Computer Vision, 1991, 7(1): 11-32.
11 G. Pass, R. Zabih, J. Miller. Comparing images using color coherence vectors. Proceedings of 4th ACM Conference on Multimedia. Boston, 1996:65-73.
12 M. Stricker, M. Orengo. Similarity of color images. Proceedings of SPIE Storage and Retrieval for Image and Video Databases Ⅲ. San Jose ,1995:381-392.
13 W. Hsu, T. S. Chua et al. An integrated color-spatial approach to content-based image retrieval, Proc. ACM Multimedia Conference, 1995:305-313.
14 葛小菁，张宏喜，李兰英．图像检索中纹理特征提取的研究．哈尔滨理工大学学报．2005，10(1)：122-124．
15 R. M. Haralick, K. Shanmugam, Texture features for image classification, IEEE Transactions on Systems,Man and Cybernetics,1973:610-623.
16 H. Tamura ,S. Mori, T. Yamawaki, Texture features corresponding to visual perception, IEEE Transactions On Systems, Man, and Cybernetics, 8(6),1978:460-473.
17 J.R. Smith, S. F. Chang, Automated binary texture feature sets for image retrieval, Proceedings of IEEE international conference on Acoustics, Speech and signal processing ,Atlanta, 1996:2239-2242.
18 T. H. Chang, C. J. Kuo, Texture analysis and classification with tree-structured wavelet transform, IEEE Transactions on Image Processing,1993,2(4):429-441.
19 W. Y. Ma ,B. S. Manjunath, A comparison of wavelet transform features for textures image annotation, Proceedings of IEEE international conference on Image Processing. 1995:256-259.
20 E.G. Simona, Nicolai Petkov, Peter Kruizinga. Comparison of Texture Features Based on Gabor Filters. IEEE Transactions on Image Processing.2002,11(10): 1160-1167.
21 陆军，王润生．区域结构及多尺度纹理分析．国防科技大学学报，2000，22(6)：91-95．
22 史萍，吕四化．基于形状图像检索系统的设计和实现．中国传媒大学学报自然科学版．2006，13(3)：87-92．
23 蔡菲，蔡珣，史同广．一种基于形状特征的图像检索方法．计算机应用与软件．2005，22(12)：44-49．
24 封筠，王彦芳，王小平．小波分析在基于内容的图像检索技术中的应用．微计算机信息．2006，22(13)：223-227．
25 章志勇，潘志庚，张明敏．基于多尺度通用傅里叶描述子的灰度图像检索．中国图像图形学报2005，10(5)：611-615．
26 曲桂红，张大力，阎平凡．数字空间轮廓的小波描述子．电子与信息学报，2002，24(6)：794-799．
27 M.K.Hu, visual pattern recognition by moment invariants, IEEE Transactions on Information Theory, 1962,8(2): 179-187.
28 黄勇，王崇骏，王亮等．基于形状不变矩的图像检索算法的研究．计算机应用研究．2004，22(7)：256-260．
29 贺玲，吴玲达，蔡益朝．基于内容图像检索中的索引技术．计算机应用研究．2005，22(11)：34-38．
30 卢佳，宋余庆，周成兵．图像数据库索引技术的研究与探讨．计算机工程与设计．2005，26(7)：1759-1761．
31 A. Guttman, R-trees: a dynamic index structure for spatial searching, Proceedings of ACM SIGMOD international conference on Management of Data, 1984:47-57.
32 N. Beckmann, H. P. Kriegel, R. Schneider, et al, The R~*-Tree: An efficient and robust access method for points and rectangles, Proceedings of ACM SIGMOD international conference on Management of Data,1990:322-331.
33 D. A. White, R. Jain, Similarity indexing with the SS-tree, Proceedings of the Twelfth International Conference on Data Engineering, 1996:516-523.
34 陈沽，石跃祥．基于SVM的图像低层特征与高层语义的关联．计算机应用研究．2006，23(9)：250-252．
35 邢伟利．图像检索中颜色的特征提取及匹配算法．微机发展．2004，14(2)：86-88．
36 Tversky A. Features of similarity. Psychological Review, 1977, 8(4):327-352.
37 Yossi Rubner,Jan Puzicha. Empirical Evaluation of Dissimilarity Measures for Color and Texture. Computer Vision and Image Understanding, 2001,8(4):25-43.
38 Aki Kobayashi, Toshiyuki Yoshida, et al. Image Retrieval by Estimating Parameters of Distance Measure. SPIE. 2000, 39(72):432-441.
39 Zhong Su, Hongjiang Zhang, Stan Li et al. Relevance Feedback in Content-Based Image Retrieval: Bayesian Framework, Feature Subspaces, and Progressive Learning[J]. IEEE Transactions on Image Processing,2003,12(8):924-936.
40 Y Rui,T S Huang, M Ortega et al. Relevance feedback: A power tool for interactive content-based image retrieval[J].IEEE Transaction on Circuits and Video Technology, 1998,8(5): 644-655.
41 Yimin Wu, Aidong Zhang. A feature re-weighting approach for relevance feedback in image retrieval[C].In: International Conference on Image Processing, Proceedings, 2002(2):581-584.
42 Ye Lu, Hongjiang Zhang, Wenyin Liu et al. Joint semantics and feature based image retrieval using relevance feedback[J].IEEE Transactions on Multimedia, 2003,5(3):339-347.
43 R．C．Gonzalez，R，E．Woods．阮秋琦，阮宇智译．数字图像处理(第二版)．北京：电子工业出版社，2006：224-233．
44 J. Scharcanski, H.C. Shen, et al. Color quantization for color texture analysis. Proceedings of Computers and Digital Techniques, 1993:109-114.
45 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．
46 冀亚丽．基于内容的鲁棒的图像方法的研究和系统实现．西南师范大学．硕士论文．2005．
47 何清法，李国杰．综合分块主色和相关反馈技术的图像检索方法．计算机辅助设计与图形学学报，2001(10)：912-917．
48 Anne H. H. Ngu, Quan Z. Sheng. Combing Multi-visual Feature for Efficient Indexing in a Large Image Database. In VLDB. 2001,9:279-293.
49 Seyoon Jeong, Kyuheon Kim, et al. An Effective Method for Combining Multiple Features of Imgge Retrieval. IEEE Transaction On Tencon. 1999.
50 Y. Rui, T.S. Huang, S. Mehrotra. A Relevance Feedback Architecture in Content-Based Multimedia Information. In Proceedings of IEEE Workshop on Content-Based Access of Image and Video Libraries. June 1997:82-89.