Exploiting Deep Neural Networks for Digital Image Compression

Title
Exploiting Deep Neural Networks for Digital Image Compression
Authors
정제창
Keywords
Deep neural networks; artificial neurons; hyperbolic tangent neurons; image compression; logistic sigmoid neurons
Issue Date
2015-03
Publisher
WSWAN Organizing Committee
Citation
Web Applications and Networking (WSWAN), 2015 2nd World Symposium on , Page. 1-6
Abstract
Deep neural networks (DNNs) are increasingly being researched and employed as a solution to various image and video processing tasks. In this paper we address the problem of digital image compression using DNNs. We use two different DNN architectures for image compression i.e. one employing the logistic sigmoid neurons and the other engaging the hyperbolic tangent neurons. Experiments show that the network employing the hyperbolic tangent neurons out performs the one with the sigmoid neurons. Results indicate that the hyperbolic tangent neurons not only improve the PSNR of the reconstructed images by a significant 2~5dB on average but they also converge several order of magnitude faster than the logistic sigmoid neurons.
URI
http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7210294&tag=1http://hdl.handle.net/20.500.11754/22748
ISBN
978-1-4799-8171-7
ISMN
978-1-4799-8172-4
DOI
http://dx.doi.org/10.1109/WSWAN.2015.7210294
Appears in Collections:
COLLEGE OF ENGINEERING[S](공과대학) > DEPARTMENT OF ELECTRONIC ENGINEERING(융합전자공학부) > Articles
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE