Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 정제창 | - |
dc.date.accessioned | 2016-08-24T07:31:30Z | - |
dc.date.available | 2016-08-24T07:31:30Z | - |
dc.date.issued | 2015-03 | - |
dc.identifier.citation | Web Applications and Networking (WSWAN), 2015 2nd World Symposium on , Page. 1-6 | en_US |
dc.identifier.isbn | 978-1-4799-8171-7 | - |
dc.identifier.ismn | 978-1-4799-8172-4 | - |
dc.identifier.uri | http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7210294&tag=1 | - |
dc.identifier.uri | http://hdl.handle.net/20.500.11754/22748 | - |
dc.description.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. | en_US |
dc.language.iso | en | en_US |
dc.publisher | WSWAN Organizing Committee | en_US |
dc.subject | Deep neural networks | en_US |
dc.subject | artificial neurons | en_US |
dc.subject | hyperbolic tangent neurons | en_US |
dc.subject | image compression | en_US |
dc.subject | logistic sigmoid neurons | en_US |
dc.title | Exploiting Deep Neural Networks for Digital Image Compression | en_US |
dc.type | Article | en_US |
dc.identifier.doi | 10.1109/WSWAN.2015.7210294 | - |
dc.relation.page | 1-6 | - |
dc.contributor.googleauthor | Hussain, Farhan | - |
dc.contributor.googleauthor | Jeong, Jechang | - |
dc.sector.campus | S | - |
dc.sector.daehak | COLLEGE OF ENGINEERING[S] | - |
dc.sector.department | DEPARTMENT OF ELECTRONIC ENGINEERING | - |
dc.identifier.pid | jjeong | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.