一种基于区域检测的图像检索相关反馈方法

doi:10.3969/j.issn.1006-2475.2015.01.015

摘要/Abstract

摘要： 提出一种基于用户兴趣区域检测的图像检索相关反馈学习方法，利用用户反馈为正相关的图像进行学习，进而猜测用户意图，获得更令用户满意的检索结果。该反馈学习方法的框架如下：1）对正相关的反馈图像与查询图像进行特征匹配；2）对匹配的特征使用RANSAC模型进行校准；3）进行区域选取。在选取了兴趣区域以后，可以将该区域直接抠取或将其中的特征点权值增强作为新的待查图像进行检索，提高检索的精度。实验表明本文方法可以返回更符合用户心意的检索结果。

关键词: 相关反馈, 区域检测, 图像检索

Abstract: This paper proposed a relevance feedback approach in image retrieve system. The approach is based on the detection of interest region of the query user. This approach makes use of the positively relevant images which are labeled by user and learn the user intention of the query so that the return images satisfy the user better. This approach can be divided into 3 steps: 1) match the features of positively relevant images to those of the query image; 2) verify the matched points using RANSAC model; 3) select the interest region according to the verified points. As the interest region has been selected, one can use this region or put more weight on the features in this region as a new query image. The results of the experiments show that this approach can improve the precise of the retrieval and return images that satisfy the user better.

Key words: relevance feedback, region detection, image retrieval

中图分类号:

TP393

王梦蕾. 一种基于区域检测的图像检索相关反馈方法[J]. 计算机与现代化, doi: 10.3969/j.issn.1006-2475.2015.01.015.

WANG Meng-lei. A Relevance Feedback Method Based on Interest Region Detection in Image Retrieval System#br#[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2015.01.015.

参考文献

［1］Sabri Boughorbel, Nozha Boujemaa, Constantin Vertan. Histogrambased color signatures for image indexing［C］// Proceedings of Information Processing and Management of Uncertainty in KnowledgeBased Systems. 2002:1-7.
［2］Peter Howarth, Stefan Ruger. Evaluation of texture features for contentbased image retrieval［C］// Proceedings of the 3rd International Conference on Image and Video Retrieval. 2004:326-334.
［3］David G Lowe. Distinctive image features from scaleinvariant keypoints［J］. International Journal of Computer Vision, 2004,60(2):91-110.
［4］Yong Rui, Thomas S Huang, Michael Ortega, et al. Relevance feedback: A power tool for interactive contentbased image retrieval［J］. IEEE Transactions on Circuits and Video Technology, 1998,8(5):644-655.
［5］吴洪,卢汉清,马颂德. 基于图像内容检索中相关反馈技术的回顾［J］. 计算机学报, 2005,28(12):1969-1979.
［6］Wang Xiangyang, Zhang Beibei, Yang Hongying. Active SVMbased relevance feedback using multiple classifiers ensemble and features reweighting［J］. Engineering Applications of Artificial Intelligence, 2013,26(1):368-381.
［7］Yang Yi, Nie Feiping, Xu Dong, et al. A multimedia retrieval framework based on semisupervised ranking and relevance feedback［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012,34(4):723-742.
［8］Hota R N, Syed S, Krishna P R. Localfeaturebased image retrieval with weighted relevance feedback［J］. International Journal of Business Intelligence and Data Mining, 2010,5(4):353-369.
［9］Chen Ke, Xiong Zhiyong, Xian Xuefeng, et al. An image retrieval approach with relevance feedback［C］// Proceedings of the 2011 IEEE International Conference on Computer Science and Automation Engineering. 2011:683-687.
［10］Marakakis A, Galatsanos N, Likas A, et al. Application of relevance feedback in content based image retrieval using Gaussian mixture models［C］// Proceedings of the 20th IEEE International Conference on Tools with Artificial Intelligence. 2008:141-148.
［11］AzimiSadjadi M R, Salazar J, Srinivasan S. An adaptable image retrieval system with relevance feedback using kernel machines and selective sampling［J］. IEEE Transactions on Image Process, 2009,18(7):1645-1659.
［12］Zhang Lining, Wang Lipo, Lin Weisi. A semantic subspace learning method to exploit relevance feedback log data for image retrieval［C］// 2013 IEEE Symposium on Computational Intelligence and Data Mining. 2013:178-183.
［13］Tao Dacheng, Tang Xiaoou, Li Xuelong, et al. A symmetric bagging and random subspace for support vector machinesbased relevance feedback in image retrieval［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006,28(7):1088-1099.
［14］Martin A Fischler, Robert C Bolles. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography［J］. Comm. of the ACM, 1981,24(6):381-395.
［15］Richard Hartley, Andrew Zisserman. Multiple View Geometry in Computer Vision［M］. 2nd ed. Cambridge University Press, 2003:32-33.
［16］Datta R, Joshi D, Li J, et al. Image retrieval: Ideas, influences, and trends of the new age［J］. ACM Computing Surveys, 2008,40(2):61-65.
［17］Lin YenYu, Liu TjngLuh, Chen HuannTzong. Semantic manifold learning for image retrieval［C］// Proceedings of the 13th Annual ACM International Conference on Multimedia. 2005:249-258.
［18］Yong Rui, Thomas S Huang, Mehrotra S. Contentbased image retrieval with relevance feedback in mmars［C］// Proceedings of the 1997 IEEE International Conference on Image Processing. 1997(2),815-818.

[1]	王欣怡, 尹四清, 洪军. 融合注意力机制的非对称深度监督哈希[J]. 计算机与现代化, 2023, 0(05): 26-31.
[2]	王文，徐亦白，卢杉，冯宇. 一种结合区域检测和语义分割的SLAM技术[J]. 计算机与现代化, 2019, 0(07): 55-.
[3]	刘琪,张鹏程,王继民. 基于相关反馈的时间序列相似性搜索[J]. 计算机与现代化, 2018, 0(02): 22-26.
[4]	韩丹丹，韩立新. 基于张量局部保持投影算法的图像检索[J]. 计算机与现代化, 2017, 0(1): 71-74.
[5]	郭海凤1，2，陈月霞1，孙周宝2. 改进的ISOMAP算法在人脸识别中的应用[J]. 计算机与现代化, 2015, 0(9): 25-29.
[6]	朱凌云1,朱征宇1,2,齐新勇1. 融合多种内容特征的图像检索算法[J]. 计算机与现代化, 2015, 0(9): 17-21.
[7]	陈秋平. 考虑视觉显著性的部分相似图像检索[J]. 计算机与现代化, 2015, 0(4): 82-85,89.
[8]	濮永仙. 基于图像内容检索的作物病害识别数据库系统研究[J]. 计算机与现代化, 2015, 0(4): 54-60.
[9]	关永洪. 基于非抽样轮廓波变换和矩阵F-范数的旋转不变纹理图像检索方法[J]. 计算机与现代化, 2013, 1(9): 95-97,1.
[10]	何文斌;梁利姣. 基于改进Gabor函数的图像检索[J]. 计算机与现代化, 2013, 1(7): 138-141.
[11]	郭海凤,李广水,仇彬任 . 基于融合多特征的社会网上图像检索方法[J]. 计算机与现代化, 2013, 12(12): 159-163.
[12]	强振平;陈旭;林宏. 一种基于半径和角度直方图描述形状的图像检索方法[J]. 计算机与现代化, 2012, 1(201): 35-38.
[13]	江少锋;杨书勤. 联合相关反馈在医学图像检索中的应用[J]. 计算机与现代化, 2012, 208(12): 55-59.
[14]	王汉;王兵;李悦;汤进. 基于R树的图像检索方法[J]. 计算机与现代化, 2011, 1(1): 103-3.
[15]	张舒娟;王庆民. 基于多特征的图像检索研究[J]. 计算机与现代化, 2010, 1(01): 124-127.