Exploiting deep neural networks for digital image compression
- Authors
- Hussain, Farhan; Jeong, Jechang
- Issue Date
- Mar-2015
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Keywords
- artificial neurons; Deep neural networks; hyperbolic tangent neurons; image compression; logistic sigmoid neurons
- Citation
- 2015 2nd World Symposium on Web Applications and Networking, WSWAN 2015, pp.1 - 6
- Indexed
- SCOPUS
- Journal Title
- 2015 2nd World Symposium on Web Applications and Networking, WSWAN 2015
- Start Page
- 1
- End Page
- 6
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/157729
- DOI
- 10.1109/WSWAN.2015.7210294
- ISSN
- 0000-0000
- 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.
- Files in This Item
-
Go to Link
- Appears in
Collections - 서울 공과대학 > 서울 융합전자공학부 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/157729)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.