利用位置信息加权词汇树的图像检索

doi:10.16182/j.issn1004731x.joss.201710017

系统仿真学报 ›› 2017, Vol. 29 ›› Issue (10): 2353-2360.doi: 10.16182/j.issn1004731x.joss.201710017

利用位置信息加权词汇树的图像检索

陈莹, 郭佳宇

江南大学轻工过程先进控制教育部重点实验室,江苏无锡 214000

收稿日期:2015-10-13 发布日期:2020-06-04
作者简介:陈莹(1976-),女,浙江丽水,博士,教授,研究方向为信息融合、模式识别。
基金资助:
国家自然科学基金(61104213, 61573168),江苏省产学研前瞻性联合研究项目(BY2015019-15)

Image Retrieval Using Weighted Vocabulary Tree with Location Information

Chen Ying, Guo Jiayu

Key Laboratory of Advanced Control Light Process, Jiangnan University, Wuxi 214000, China

Received:2015-10-13 Published:2020-06-04

摘要/Abstract

摘要： 针对基于SIFT特征匹配的图像检索方法忽略空间位置信息的缺陷,提出了基于空间位置信息加权词汇树的图像检索方法。利用分层词汇树将图像SIFT特征量化为视觉单词,将图像匹配转换成视觉单词权值向量匹配。由于单纯的视觉单词权值向量匹配忽略了视觉单词之间的相互位置影响,生成SIFT点的空间位置影响信息,根据SIFT点与视觉单词之间的从属关系,将SIFT点的空间位置影响信息聚类为视觉单词之间的位置影响,将视觉单词的空间位置信息作为加权系数,加入到视觉单词的权值匹配中去,细化特征之间的匹配得分,通过相似度排序检索相似图像。实验结果表明,该算法能有效提高图像检索的精确度。

关键词: 词汇树, 位置信息, 向量匹配, 图像检索

Abstract: Aiming at the positional information ignorance problem in image retrieval based on SIFT feature matching, an image retrieval approach using weighted vocabulary tree based on the spatial location information was proposed. The vocabulary tree is used in the method to quantify SIFT features as the visual words, converting the image match into the visual words' weight vector match. Because only visual words' weight match ignored the mutual position effect, SIFT points' spatial location information was generated, and was classified into the position effect of visual words according to affiliation between SIFT points and visual words. The spatial location information of the visual words was used as the weighting factor of weight vector matches, refining the matching score between features. Similar images were retrieved by similarity sort. The experimental results show that the algorithm can effectively improve the accuracy of the image retrieval.

Key words: vocabulary tree, location information, vector matching, image retrieval

中图分类号:

TP391

陈莹, 郭佳宇. 利用位置信息加权词汇树的图像检索[J]. 系统仿真学报, 2017, 29(10): 2353-2360.

Chen Ying, Guo Jiayu. Image Retrieval Using Weighted Vocabulary Tree with Location Information[J]. Journal of System Simulation, 2017, 29(10): 2353-2360.

参考文献

[1] Kesorn K, Poslad S.An enhanced Bag-of-Visual word vector space model to represent visual content in athletics images[J]. IEEE Trans on Multimedia(S1520-9210), 2012, 14(1): 211-222.
[2] Nistér D, Stewénius H.Scalable recognition with a vocabulary tree[C]// Proc of the IEEE Conference on Computer Vision and Pattern Recognition, New York, USA, June 17-22, 2006. Piscataway, NJ, USA: IEEE, 2006: 2161-2168.
[3] 陈赟, 沈一帆. 基于词汇树的图片搜索[J]. 计算机工程, 2010, 36(6): 189-191.
( Chen Yun, Shen Yifan.Image search based on vocabulary tree[J]. Computer Engineering, 2010, 36(6): 189-191.)
[4] Jégou H, Douze M, Schmid C.Improving bag-of-feature for large scale image search[J]. Int'l Journal of Computer Vision(S1573-1405), 2010, 87(3): 316-336.
[5] Qin Jianzhao, Yung N H C. Scene categorization via contextual visual words[J]. Pattern Recognition ISSN号(S0031-3203), 2010, 43(5): 1874-1888.
[6] Tang Wenbin, Cai Rui, Li Zhiwei, et al.Contextual synonym dictionary for visual object retrieval[C]// Proc of the 19th International Conference on Multi Media. Scottsdale, USA, Nov 28- Dec 1, 2011. Scottsdale, USA: ACM Multimedia, 2011: 503-512.
[7] Wang Xiaoyu, Yang Ming, Cour T, et al.Contextual weighting for vocabulary tree based image retrieval[C]// Proc of the 13th IEEE International Conference on Computer Vision, Barcelona, Spain, Nov 6-13, 2011. Piscataway, NJ, USA: IEEE, 2011: 209-216.
[8] 朱道广, 郭志刚, 赵勇威. 基于空间上下文加权词汇树的图像检索方法[J]. 模式识别与人工智能, 2013, 26(11): 1050-1056.
(Zhu Daoguang, Guo Zhigang, Zhao Yongwei.Image Retrieval with Spatial Context Weighting Based Vocabulary Tree[J]. Pattern Recognition and Artificial Intelligence, 2013, 26(11): 1050-1056 .)
[9] Jégou H, Douze M, Schmid C.Hamming embedding and weak geometric consistency for large scale image search[C]// The 10th European Conference on Computer Vision, Marseille, France, 2008. Heidelberg, Berlin, Germany: Springer, 2008: 304-317.
[10] Deng J, Dong W, Socher R, et al.ImageNet: A large-scale hierarchical image database[C]// IEEE International Conference on Computer Vision and Pattern Recognition, CVPR 2008. Anchorage, Alaska, USA, June 20-26, 2009. Piscataway, NJ, USA: IEEE, 2009: 248-255

利用位置信息加权词汇树的图像检索

Image Retrieval Using Weighted Vocabulary Tree with Location Information

PDF (PC)

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

[1]	吴宇豪, 曹雪峰, 彭锦超, 徐连瑞. 基于运动结构图的无人机序列影像三维重建[J]. 系统仿真学报, 2020, 32(6): 1094-1102.
[2]	李亚栋, 莫红, 王世豪, 周忠, 吴威. 基于图像描述的人物检索方法[J]. 系统仿真学报, 2018, 30(7): 2794-2800.
[3]	梁丰, 张志利, 李向阳, 汤志波. 基于小波变换和Kalman滤波的虚拟人空间位置处理[J]. 系统仿真学报, 2016, 28(1): 213-219.