Reduction of Compression Artifacts Using a Densely Cascading Image Restoration Network
- Authors
- Lee, Yooho; Park, Sang-hyo; Rhee, Eunjun; Kim, Byung-Gyu; Jun, Dongsan
- Issue Date
- Sep-2021
- Publisher
- MDPI
- Keywords
- computer vision; deep learning; convolutional neural network; image processing; image restoration; single image artifacts reduction; dense networks; residual networks; channel attention networks
- Citation
- APPLIED SCIENCES-BASEL, v.11, no.17, pp 1 - 13
- Pages
- 13
- Journal Title
- APPLIED SCIENCES-BASEL
- Volume
- 11
- Number
- 17
- Start Page
- 1
- End Page
- 13
- URI
- https://scholarworks.sookmyung.ac.kr/handle/2020.sw.sookmyung/146418
- DOI
- 10.3390/app11177803
- ISSN
- 2076-3417
2076-3417
- Abstract
- Since high quality realistic media are widely used in various computer vision applications, image compression is one of the essential technologies to enable real-time applications. Image compression generally causes undesired compression artifacts, such as blocking artifacts and ringing effects. In this study, we propose a densely cascading image restoration network (DCRN), which consists of an input layer, a densely cascading feature extractor, a channel attention block, and an output layer. The densely cascading feature extractor has three densely cascading (DC) blocks, and each DC block contains two convolutional layers, five dense layers, and a bottleneck layer. To optimize the proposed network architectures, we investigated the trade-off between quality enhancement and network complexity. Experimental results revealed that the proposed DCRN can achieve a better peak signal-to-noise ratio and structural similarity index measure for compressed joint photographic experts group (JPEG) images compared to the previous methods.
- Files in This Item
-
- Appears in
Collections - ETC > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.