합성곱 신경망 기반 JPEG 압축 품질에 따른 영상 분류
- Authors
- 정제창; 류창현; 유송현
- Issue Date
- Nov-2017
- Publisher
- 대한전자공학회
- Citation
- 대한전자공학회 학술대회, pp.882 - 885
- Indexed
- OTHER
- Journal Title
- 대한전자공학회 학술대회
- Start Page
- 882
- End Page
- 885
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/3988
- Abstract
- In this paper, we propose a method for predicting the compression quality of compressed images in JPEG (joint photographic coding experts group) using convolutional neural network. We use the widely used image processing program, Photoshop, to construct the learning data by compressing the original image with various compression quality, and we use this to learn the proposed model. Experimental results show that the proposed model can predict the quality of compressed JPEG images with arbitrary quality. Except for very high quality or low quality, it showed high accuracy. These results are expected to be useful when estimating the approximation of compression quality of a JPEG file which has lost the header information of the image or lack of information.
- 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/3988)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.