基于混合相似度的高效图像检索方案

doi:10.19678/j.issn.1000-3428.0052836

计算机工程 ›› 2019, Vol. 45 ›› Issue (11): 262-268. doi: 10.19678/j.issn.1000-3428.0052836

基于混合相似度的高效图像检索方案

曾梦琪¹, 马蔚吟², 李力¹

1. 上海交通大学电子信息与电气工程学院, 上海 200240;
2. 南京医科大学数学与计算机教研室, 南京 211166

收稿日期:2018-10-10 修回日期:2018-11-27 发布日期:2018-12-03
作者简介:曾梦琪(1995-),女,硕士,主研方向为图像检索、数据库技术;马蔚吟(通信作者),高级实验师;李力,副教授。
基金资助:
国家自然科学基金（U1636210）。

Efficient Image Retrieval Scheme Based on Hybrid Similarity

ZENG Mengqi¹, MA Weiyin², LI Li¹

1. School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China;
2. Office of Mathematics and Computer Department, Nanjing Medical University, Nanjing 211166, China

Received:2018-10-10 Revised:2018-11-27 Published:2018-12-03

摘要/Abstract

摘要： 融合文本和视觉信息进行图像检索可避免图像低层视觉特征与高层语义之间的语义鸿沟，但在提高检索质量的同时难以保证检索效率。为此，针对基于文本和内容的混合图像检索，通过结合曼哈顿哈希、倒排索引和R树等技术，设计一个新型的索引结构CAT树和相应的top-k检索算法，并由此提出三段式图像检索方案。在基准图像数据集上的实验结果表明，该方案可以在保持准确率的前提下，显著提升图像检索的效率。

关键词: 图像检索, 语义鸿沟, 索引, 视觉特征, R树

Abstract: Fusion of visual and text information can bridge the semantic gap between low-level visual features of images and high-level semantics,and thus improve retrieval quality. However,retrieval efficiency is consequently reduced.To address this problem,this paper designs a novel index structure,CAT-tree,and a corresponding top-k retrieval algorithm for hybrid image retrieval based on fusion of text and content.The CAT tree and its top-k algorithm are designed by combining Manhattan Hashing,Inverted Index and R-tree.On this basis,a three-way image retrieval scheme is proposed.Experimental results on benchmark image datasets show that the proposed scheme can remarkably improve the image retrieval efficiency without the loss of accuracy.

Key words: image retrieval, semantic gap, index, visual feature, R-tree

中图分类号:

TP391

曾梦琪, 马蔚吟, 李力. 基于混合相似度的高效图像检索方案[J]. 计算机工程, 2019, 45(11): 262-268.

ZENG Mengqi, MA Weiyin, LI Li. Efficient Image Retrieval Scheme Based on Hybrid Similarity[J]. Computer Engineering, 2019, 45(11): 262-268.

https://www.ecice06.com/CN/Y2019/V45/I11/262

图/表 6

20191118171615

20191118171618

20191118171621

20191118171624

20191118171631

20191118171633

参考文献

[1] ZHANG Chen,CHAI J Y,JIN Rong.User term feedback in interactive text-based image retrieval[C]//Proceedings of SIGIR'05.New York,USA:ACM Press,2005:51-58.
[2] LI Wen,DUAN Lixin,XU Dong,et al.Text-based image retrieval using progressive multi-instance learning[C]//Proceedings of ICCV'11.Washington D.C.,USA:IEEE Press,2011:2049-2055.
[3] SMEULDERS A W M,WORRING M,SANTINI S,et al.Content-based image retrieval at the end of the early years[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(12):1349-1380.
[4] 张少博,全书海,石英,等.基于颜色矩的图像检索算法研究[J].计算机工程,2014,40(6):252-255.
[5] DATTA R,JOSHI D,LI Jia,et al.Image retrieval:ideas,influences,and trends of the new age[J].ACM Computing Surveys,2008,40(2):1-60.
[6] 王小龙,沈新宁,杜建洪.一种基于区域综合特征的图像检索算法[J].计算机工程,2014,40(11):229-232.
[7] ZHOU X S,HUANG T S.Unifying keywords and visual contents in image retrieval[J].IEEE Multimedia,2002,9(2):23-33.
[8] CLINCHANT S,AH-PINE J,CSURKA G.Semantic combination of textual and visual information in multimedia retrieval[C]//Proceedings of ICMR'11.New York,USA:ACM Press,2011:44.
[9] CAICEDO J C,MORENO J G.Combining visual features and text data for medical image retrieval using latent semantic kernels[C]//Proceedings of MIR'10.New York,USA:ACM Press,2010:359-366.
[10] LONG Mingsheng,CAO Yue,WANG Jianmin,et al.Composite correlation quantization for efficient multimodal retrieval[C]//Proceedings of ACM SIGIR Conference on Research and Development in Information Retrieval.New York,USA:ACM Press,2016:579-588.
[11] OLIVA A,TORRALBA A.Modeling the shape of the scene:a holistic representation of the spatial envelope[J].International Journal of Conflict and Violence,2001,42(3):145-175.
[12] SIVIC J,ZISSERMAN A.Video Google:text retrieval approach to object matching in videos[C]//Proceedings of ICCV'03.Washington D.C.,USA:IEEE Press,2003:1470-1477.
[13] ZHAI Chengxiang,LAFFERTY J.A study of smoothing methods for language models applied to information retrieval[J].ACM Transactions on Information Systems,2004,22(2):179-214.
[14] KONG Weihao,LI Wujun,GUO Minyi.Manhattan hashing for large-scale image retrieval[C]//Proceedings of ACM SIGIR Conference on Research and Development in Information Retrieval.New York,USA:ACM Press,2012:45-54.
[15] CAO Xin,CHEN Lisi,CONG Gao,et al.Spatial keyword querying[C]//Proceedings of International Conference on Conceptual Modeling.Berlin,Germany:Springer-Verlag,2012:16-29.
[16] ZOBEL J,MOFFAT A.Inverted files for text search engines[J].ACM Computing Surveys,2006,38(2).
[17] GUTTMAN A.R-trees:a dynamic index structure for spatial searching[C]//Proceedings of SIGMOD'84.New York,USA:ACM Press,1984:47-57.
[18] GONG Y,LAZEBNIK S,GORDO A,et al.Iterative quantization:a procrustean approach to learning binary codes[C]//Proceedings of CVPR'11.Washington D.C.,USA:IEEE Press,2011:817-824.
[19] HJALTASON G R,SAMET H.Distance browsing in spatial databases[J].ACM Transactions on Database Systems,1999,24(2):265-318.
[20] GRUBINGER M,CLOUGH P,MÜLLER H,et al.The IAPR TC-12 benchmark:a new evaluation resource for visual information systems[C]//Proceedings of Workshop OntoImage 2006.Genoa,Italy:[s,n.],2006:1-11.
[21] RUSSELL B C,TORRALBA A,MURPHY K P,et al.LabelMe:a database and Web-based tool for image annotation[J].International Journal of Computer Vision,2008,77(1/2/3):157-173.
[22] CHUA T S,TANG Jinhui,HONG Richang,et al.NUS-WIDE:a real-world Web image database from national university of Singapore[C]//Proceedings of ACM International Conference on Image and Video Retrieval.Washington D.C.,USA:ACM Press,2009.
[23] DEPEURSINGE A,MÜLLER H.Fusion techniques for combining textual and visual information retrieval[C]//Proceedings of ImageCLEF'10.Berlin,Germany:Springer-Verlag,2010:95-114.
[24] MAMOU J,SZNAJDER B,SZNAJDER B,et al.A unified inverted index for an efficient image and text retrieval[C]//Proceedings of SIGIR'09.New York.USA:ACM Press,2009:814-815.

选择文件类型/文献管理软件名称

选择包含的内容

基于混合相似度的高效图像检索方案

Efficient Image Retrieval Scheme Based on Hybrid Similarity

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	董峰, 王永欣, 马玉玲, 王奎奎. 原型对齐和域感知的零样本哈希[J]. 计算机工程, 2024, 50(5): 260-271.
[2]	熊浩然, 何震瀛. 支持均匀缩放的不等长时间子序列查询方法[J]. 计算机工程, 2024, 50(1): 60-67.
[3]	何悦, 陈广胜, 景维鹏, 徐泽堃. 基于深度多相似性哈希方法的遥感图像检索[J]. 计算机工程, 2023, 49(2): 206-212.
[4]	唐榕, 李骞, 唐绍恩. 基于多目标的能见度检测方法[J]. 计算机工程, 2023, 49(2): 314-320.
[5]	高峰, 李秋, 顾进广. 基于图结构特征采样数据摘要的联邦知识图谱查询[J]. 计算机工程, 2023, 49(1): 73-81.
[6]	彭红艳, 李杰, 石贞奎, 李先贤. 一种基于区块链可验证的加密图像检索方案[J]. 计算机工程, 2022, 48(2): 25-33,39.
[7]	汤文琳, 谢凯, 文畅, 贺建飚. 深度聚类索引下的海量地震数据快速三维可视化[J]. 计算机工程, 2022, 48(11): 275-283.
[8]	白梅, 苌仕涵, 王习特. 基于位置的路网Skyline查询处理研究[J]. 计算机工程, 2022, 48(1): 127-134.
[9]	夏磊, 杨华, 宋玉蓉. 多用户载波索引差分混沌移位键控通信系统及性能分析[J]. 计算机工程, 2021, 47(5): 181-188.
[10]	蔡瑞初, 林峰极, 郝志峰, 王立, 温雯. 面向轨迹流数据的索引构建与存储方法研究[J]. 计算机工程, 2021, 47(3): 62-70.
[11]	顾岩, 赵崇宇, 黄平. 基于高阶统计信息的深度哈希学习模型[J]. 计算机工程, 2020, 46(7): 260-267,276.
[12]	周骑骏, 王鹏, 汪卫. DSI:一种基于动态分段的时间序列查询索引[J]. 计算机工程, 2020, 46(2): 88-95.
[13]	唐鸿成, 文畅, 冯文祥, 谢凯, 方文青. 基于智能聚类模型的海量数据快速显示方法[J]. 计算机工程, 2019, 45(8): 53-59.
[14]	代亚兰,何朗,黄樟灿. 基于稀疏自编码的无监督图像哈希算法[J]. 计算机工程, 2019, 45(5): 222-225,236.
[15]	张浩盛伦,李翀,柯勇,张士波. 一种分布式用户浏览点击模型算法[J]. 计算机工程, 2019, 45(3): 1-6.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于混合相似度的高效图像检索方案

Efficient Image Retrieval Scheme Based on Hybrid Similarity

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献

相关文章 15

编辑推荐

Metrics

本文评价