Image Retrieval Based On ResNet and KSH

DOI

10.2991/ncce-18.2018.70How to use a DOI?

Keywords

ResNet, KSH, hash learning, deep learning

Abstract

Hashing have has been successfully applied to different methods regarding a wide range of problems. It is fairly very effective for large-scale image retrieval in reducing the processing time. Although a number of hashing methods have been developed in recent years. Most of them the methods are based on hand-crafted features, which might not be optimally compatible with the hashing procedure for dealing with large datasets. Furthermore, recently, deep hash learning has been proposed to generate hash code, simultaneously, extracting to better extract the image features, which has shown better performance than the traditional methods of hand-crafted features. In this paper, we propose a new supervised hashing framework based on deep Residual Networks and kernel-based supervised hashing (KSH). Firstly, we exploit the learning abilities of deep residual network to mine the inherent hidden relationship of image content, extract deep feature descriptors, and increase the visual expression of images Secondly, kernel-based supervised hashing is applied to learn from the high-dimensional image feature and map into low-dimensional hamming space and achieve compact Hash codes. Finally, image retrieval is accomplished in low-dimensional hamming space. Experimental results of MNIST, CIFAR-10, CIFAR-100 and Caltech 256 show that the expression ability of visual feature is effectively improved and the image retrieval performance is substantially boosted compared with other related methods.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Jinyun Lu
PY  - 2018/05
DA  - 2018/05
TI  - Image Retrieval Based On ResNet and KSH
BT  - Proceedings of the 2018 International Conference on Network, Communication, Computer Engineering (NCCE 2018)
PB  - Atlantis Press
SP  - 452
EP  - 459
SN  - 1951-6851
UR  - https://doi.org/10.2991/ncce-18.2018.70
DO  - 10.2991/ncce-18.2018.70
ID  - Lu2018/05
ER  -