Author Login Editor-in-Chief Peer Review Editor Work Office Work

Computer Engineering ›› 2019, Vol. 45 ›› Issue (11): 262-268. doi: 10.19678/j.issn.1000-3428.0052836

Previous Articles     Next Articles

Efficient Image Retrieval Scheme Based on Hybrid Similarity

ZENG Mengqi1, MA Weiyin2, LI Li1   

  1. 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

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. 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
  • 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)。

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

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

CLC Number: