198 399

Full metadata record

DC FieldValueLanguage
dc.contributor.author정제창-
dc.date.accessioned2020-09-14T02:09:41Z-
dc.date.available2020-09-14T02:09:41Z-
dc.date.issued2019-09-
dc.identifier.citationIEEE ACCESS, v. 7, Page. 138032-138042en_US
dc.identifier.issn2169-3536-
dc.identifier.urihttps://ieeexplore.ieee.org/document/8846754/-
dc.identifier.urihttps://repository.hanyang.ac.kr/handle/20.500.11754/153853-
dc.description.abstractJoint photographic experts group (JPEG) compression is lossy compression, and degradation of image quality worsens at high compression ratios. Therefore, a reconstruction process is required for a visually pleasant image. In this paper, we propose an end-to-end deep learning architecture for restoring JPEG images with high compression ratios. The proposed architecture changes a core principle of the squeeze and excitation network for low-level vision tasks where pixel-level accuracy is important. Instead of extracting global features, our network extracts locally embedded features and fine-tunes each feature value by using depthwise convolution. To reduce the computational complexity and parameters with large receptive fields, we use a combination of the recursive structure and feature map down- and up-scaling processes. We also propose a compact version of the proposed model by decreasing the number of filters and simplifying the network, which has about one-twentieth of the parameters of the baseline model. Experimental results reveal that our network outperforms conventional networks quantitatively, and the restored images are clear with sharp edges and smooth blocking boundaries. Furthermore, the compact model shows higher objective results while maintaining a low number of parameters. In addition, at a high compression ratio, the overall information, including details in the blocks, are lost owing to high quantization errors. We apply a generative adversarial network structure to restore these highly damaged blocks, and the results reveal that the image produced has details similar to those of the ground truth.en_US
dc.description.sponsorshipThis work was supported in part by the Research Fund of Signal Intelligence Research Center supervised by the Defense Acquisition Program Administration, and in part by the Agency for Defense Development, South Korea.en_US
dc.language.isoenen_US
dc.publisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INCen_US
dc.subjectConvolutional neural networken_US
dc.subjectJPEG image restorationen_US
dc.subjectgenerative adversarial networken_US
dc.titleLocal Excitation Network for Restoring a JPEG-Compressed Imageen_US
dc.typeArticleen_US
dc.identifier.doi10.1109/ACCESS.2019.2943155-
dc.relation.page138032-138042-
dc.relation.journalIEEE ACCESS-
dc.contributor.googleauthorYu, Songhyun-
dc.contributor.googleauthorJeong, Jechang-
dc.relation.code2019036307-
dc.sector.campusS-
dc.sector.daehakCOLLEGE OF ENGINEERING[S]-
dc.sector.departmentDEPARTMENT OF ELECTRONIC ENGINEERING-
dc.identifier.pidjjeong-
dc.identifier.orcidhttps://orcid.org/0000-0002-3759-3116-


qrcode

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

BROWSE