Communications in Information and Systems

Volume 17 (2017)

Number 3

Deep hashing using an extreme learning machine with convolutional networks

Pages: 133 – 146

DOI: http://dx.doi.org/10.4310/CIS.2017.v17.n3.a1

Authors

Zhiyong Zeng (College of Mathematics and Informatics, Fujian Normal University, Fuzhou, China)

Shiqi Dai (College of Mathematics and Informatics, Fujian Normal University, Fuzhou, China)

Yunsong Li (School of Communication and Engineering, Xidian University, Xi’an, China)

Dunyu Chen (College of Electrical Engineering and Computer Science, Yuan Ze University, Taoyuan, Taiwan)

Abstract

In this paper, we present a deep hashing approach for large scale image search. It is different from most existing deep hash learning methods which use convolutional neural networks (CNN) to execute feature extraction to learn binary codes. These methods could achieve excellent results, but they depend on an extreme huge and complex networks. We combine an extreme learning machine (ELM) with convolutional neural networks to speed up the training of deep learning methods. In contrast to existing deep hashing approaches, our method leads to faster and more accurate feature learning. Meanwhile, it improves the generalization ability of deep hashing. Experiments on large scale image datasets demonstrate that the proposed approach can achieve better results with state-of-the-art methods with much less complexity.

Full Text (PDF format)

hiyong Zeng’s research supported in part by the Key Research Funds of Fujian Province under Grant 2013H0020.