Geometry and Topology Preserving Hashing for SIFT Feature

In recent years, content-based image retrieval has been of concern because of practical needs on Internet services, especially methods that can improve retrieving speed and accuracy. The SIFT feature is a well-designed local feature. It has mature applications in feature matching and retrieval, wher...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on multimedia 2019-06, Vol.21 (6), p.1563-1576
Main Authors: Kang, Chen, Zhu, Li, Qian, Xueming, Han, Junwei, Wang, Meng, Tang, Yuan Yan
Format: Article
Language:English
Subjects:
CBIR
Computer Science
geometric information
Geometry
GTPH
Hamming distance
hashing
Image enhancement
Image management
Image retrieval
Matching
SIFT
Similarity
Topology
Training
Visualization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In recent years, content-based image retrieval has been of concern because of practical needs on Internet services, especially methods that can improve retrieving speed and accuracy. The SIFT feature is a well-designed local feature. It has mature applications in feature matching and retrieval, whereas the raw SIFT feature is high dimensional, with high storage cost as well as computational cost in feature similarity measurements. Thus, we propose a hashing scheme for fast SIFT feature-based image matching and retrieval. First, a training process of the hashing function involves geometric and topological information being introduced; second, a geometry-enhanced similarity evaluation that considers both the global and details of images in evaluation is explained. Compared with state-of-the-art methods, our method achieves better performance.
ISSN:1520-9210
1941-0077
DOI:10.1109/TMM.2018.2883868