吉林大学学报(工学版) ›› 2016, Vol. 46 ›› Issue (2): 542-548.doi: 10.13229/j.cnki.jdxbgxb201602032

• 论文 • 上一篇    下一篇

特征点显著性约束的图像检索方法

赵宏伟1, 2, 李清亮1, 刘萍萍1, 2, 汤寰宇1   

  1. 1.吉林大学 计算机科学与技术学院,长春 130012;
    2.吉林大学 符号计算与知识工程教育部重点实验室,长春 130012
  • 收稿日期:2014-11-14 出版日期:2016-02-20 发布日期:2016-02-20
  • 通讯作者: 刘萍萍(1979-),女,副教授,博士.研究方向:移动视觉搜索,嵌入式技术.E-mail:liupp@jlu.edu.cn E-mail:zhaohw@jlu.edu.cn
  • 作者简介:赵宏伟(1962-),男,教授,博士生导师.研究方向:智能信息系统与嵌入式技术.E-mail:zhaohw@jlu.edu.cn
  • 基金资助:
    国家自然科学基金项目(61101155); 吉林省自然科学基金项目(201215045,20140101184JC)

Feature saliency constraint based image retrieval method

ZHAO Hong-wei1, 2, LI Qing-liang1, LIU Ping-ping1, 2, TANG Huan-yu1   

  1. 1.College of Computer Science and Technology, Jilin University, Changchun 130012,China;
    2.Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Center for Computer Fundamental Education,Jilin University, Changchun 130012,China
  • Received:2014-11-14 Online:2016-02-20 Published:2016-02-20

RICH HTML

0   

PDF (PC)

392

摘要： 图像检索的Bag of Words体系存在量化后的视觉词影响局部特征的辨别能力并且缺乏特征之间空间关系的缺点,影响检索效率.针对复杂背景的目标查询,提出了融合显著性信息的图像检索方法和基于显著特征点空间距离比的后验证方法.首先,提取图像显著目标区域,使用空间金字塔模型进行图像检索.然后,利用查询图像与检索图像匹配的显著特征对,计算任意两对显著特征点的距离比,保留满足阈值的比值,并求和,用以重新排序结果图像,得到最终的检索结果.实验结果表明:该方法显著提高了检索的精确度,并减少了几何验证过程的运算时间.

关键词: 图像检索, BoW模型, 空间金字塔, 几何验证, 显著性

Abstract: Objective retrieval plays an important role in daily life, however the model "Bag of words" exists some problems for image retrieval. For example, the quantified visual words reduce the discriminative power of the local features and the model does not capture the spatial relationship among local features, thus affecting the retrieval performance. In order to realize objective retrieval in complex environment, a feature saliency constraint based image retrieval method is proposed. By locating the salient object, this method can enhance the discriminative power of the local features and capture the spatial relationship among local features. First, the salient regions are distilled and the features inside these regions are marked as salient features. Second, the image retrieval is performed with spatial pyramid model using the salient features. Finally, the distance ratio of any two pairs of the features in each image is computed using the pair of salient features of the query image and retrieval image; then, the ratios which meet the threshold are recorded and their average is calculated to obtain the final results. Experimental results show that the proposed method improves the accuracy of the retrieval significantly and reduces the computing time during the geometric verification.

Key words: image retrieval, Bag of Words model, spatial pyramid, geometric verification, saliency

中图分类号: 

  • TP391
[1] Han Jun-wei, Xu Ming, Li Xin, et al. Interactive object-based image retrieval and annotation on iPad[J]. Multimedia Tools and Applications, 2014,72(3):2275-2297.
[2] Li Zhen-wei, Zhang Jing, Liu Xin, et al. Creating the bag-of-words with spatial context information for image retrieval[J]. Applied and Meterials and Materials, 2014,556-562:4788-4791.
[3] Fischler M A, Bolles R C. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography[J].Communications of the ACM, 1981,24(6): 381-395.
[4] Philbin J, Chum O, Isard M, et al. Object retrieval with large vocabularies and fast spatial matching[C]//CVPR'07,IEEE Conference on, Minneapolis,MN,2007: 1-8.
[5] Perd'och M,Chum O,Matas J.Efficient representation of local geometry for large scale object retrieval[C]//2009 IEEE Conference on Computer Vision and Pattern Recognition,Miami,FL,2009:9-16.
[6] Jegou H, Douze M, Schmid C. Hamming embedding and weak geometric consistency for large scale image search[C]//10th European Conference on Computer Vision,Marseille,France,2008:304-317.
[7] Zhao W L, Wu X, Ngo C W. On the annotation of web videos by efficient near-duplicate search[J]. Multimedia, IEEE Transactions on, 2010,12(15): 448-461.
[8] Tsai S S, Chen D, Takacs G, et al. Fast geometric re-ranking for image-based retrieval[C]//Image Processing (ICIP), 2010 17th IEEE International Conference on,Hong Kong,2010:1029-1032.
[9] Lazebnik S, Schmid C, Ponce J. Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories[C]//2006 IEEE Computer Society Conference on,New York,NY,2006:2169-2178.
[10] Chen X, Zhao H, Liu P, et al. Automatic salient object detection via maximum entropy estimation[J]. Optics Letters, 2013,38(10): 1727-1729.
[11] 吴晓雨, 何彦, 杨磊, 等. 基于改进形状上下文特征的二值图像检索[J]. 光学精密工程, 2015, 23(1): 302-309.
Wu Xiao-yu, He Yan, Yang Lei, et al. Binary image retrieval based on improved shape context algorithm[J]. Optics and Precision Engineering, 2015, 23(1): 302-309.
[12] 王灿进, 孙涛, 陈娟. 局部不变特征匹配的并行加速技术研究[J]. 液晶与显示, 2014, 29(2) 266-274.
Wang Can-jin, Sun Tao, Chen Juan. Binary image retrieval based on improved shape context algorithm[J]. Chinese Journal of Liquid Crystal and Displays , 2014, 29(2) 266-274.
[13] 田浩南, 张叶. 基于边缘及特征点匹配的立体图像质量评价[J]. 液晶与显示, 2015, 30(4) 666-672.
Tian Hao-nan, Zhang Ye. Quality evaluation of stereo image based on edge and characteristic point matching[J]. Chinese Journal of Liquid Crystal and Displays, 2015, 30(4) 666-672.
[14] Zhou W, Li H, Lu Y, et al. SIFT match verification by geometric coding for large-scale partial-duplicate web image search[J]. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP), 2013,9(1):4.
[1] 苏寒松,代志涛,刘高华,张倩芳. 结合吸收Markov链和流行排序的显著性区域检测[J]. 吉林大学学报(工学版), 2018, 48(6): 1887-1894.
[2] 赵宏伟, 李清亮, 汤寰宇, 臧雪柏. 基于局部邻域约束的空间验证方法[J]. 吉林大学学报(工学版), 2016, 46(1): 265-270.
[3] 张文杰, 熊庆宇. 基于对比度与空间位置特征的显著性区域检测[J]. 吉林大学学报(工学版), 2015, 45(5): 1709-1716.
[4] 赵世杰, 韩军伟, 贺胜, 程塨, 郭雷. 视频显著性计算模型及其在广告插入中的应用[J]. 吉林大学学报(工学版), 2014, 44(01): 235-240.
[5] 董傲霜, 宋宏亮. 基于SIFT特征和颜色融合的图像检索方法[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 440-444.
[6] 赵宏伟, 陈霄, 石景海, 马凌蛟. 综合颜色和形状特征的交通标志图像检索算法[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 128-132.
[7] 张久文, 米进财, 张同峰. 基于双树复小波和广义高斯密度的纹理图像检索[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 60-63.
[8] 张旭, 郭宝龙, 孟繁杰, 孙伟. 基于IPDSH兴趣点空间区域划分的图像检索[J]. 吉林大学学报(工学版), 2013, 43(05): 1408-1414.
[9] 陈绵书1,杨树媛1,赵志杰2,付平1,孙元3,李晓妮1,孙言1,齐小隐1. 多点多样性密度算法及其在图像检索中的应用[J]. 吉林大学学报(工学版), 2011, 41(05): 1456-1460.
[10] 刘静波, 王莹, 郭洋, 许海丽, 林松毅, 殷涌光. 蛋清生物活性肽组分的优选[J]. 吉林大学学报(工学版), 2010, 40(增刊): 389-0394.
[11] 刘桂霞, 田原, 郑明, 赖丽娜, 臧雪柏, 周春光. 基于元分析的差异表达基因识别[J]. 吉林大学学报(工学版), 2010, 40(05): 1308-1312.
[12] 郑雅羽,田翔.陈耀武. 基于时空特征融合的视觉注意模型[J]. 吉林大学学报(工学版), 2009, 39(06): 1625-1630.
[13] 裴玉龙，王永岗，杨光 . 评价交通系统与城市发展适应性的改进层次分析算法[J]. 吉林大学学报(工学版), 2008, 38(01): 42-47.
[14] 张国敏，殷建平，祝恩，强永刚 . 遥感图像中基于视觉显著性的分层目标检测[J]. 吉林大学学报(工学版), 2007, 37(03): 625-0629.
[15] 邵承会, 阚君武, 唐可洪. 盐田铺膜机动力损耗和参数显著性分析[J]. 吉林大学学报(工学版), 2002, (2): 64-67.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 《吉林大学学报(工学版)》编辑部
地址：长春市人民大街5988号　电话：+86-431-85095297　传真：+86-431-85094074　E-mail: xbgxb@jlu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发