ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술지 Patch Orientation-specified Network for Learning-based Image Super-resolution
Cited 3 time in scopus Download 9 time Share share facebook twitter linkedin kakaostory
저자
유석봉, 한미경
발행일
201911
출처
Electronics Letters, v.55 no.23, pp.1233-1235
ISSN
0013-5194
출판사
IET
DOI
https://dx.doi.org/10.1049/el.2019.1219
협약과제
19MH1500, 5G 기반의 스마트시티 서비스 개발 및 실증, 한미경
초록
Learning-based image super-resolution is considered as a promising solution to reconstruct a high-resolution image from a low-resolution image. To improve the super-resolution performance dramatically, this Letter focuses on the effect of training dataset on the performance and proposes an image super-resolution scheme based on patch orientation-specified network. In particular, a deep neural network is trained using patches with a specific orientation and angular transformation is combined with the neural network to cope with various orientations in input patches. Experimental results show the suggested network model is superior to existing state-of-the-art super-resolution alternatives.
KSP 제안 키워드
Angular Transformation(AT), Deep neural network(DNN), Image super resolution, Learning-based, Low-resolution images, Network model, existing state, high resolution image, state-of-The-Art