download0 view466
twitter facebook

공공누리This item is licensed Korea Open Government License

dc.contributor.author
김원준
dc.contributor.author
이용
dc.contributor.author
박민우
dc.contributor.author
이상환
dc.date.accessioned
2022-04-13T02:10:29Z
dc.date.available
2022-04-13T02:10:29Z
dc.date.issued
2019-09-11
dc.identifier.issn
2169-3536
dc.identifier.uri
https://repository.kisti.re.kr/handle/10580/16781
dc.description.abstract
A vast amount of pictures are taken every day by using cameras mounted on various mobile devices. Even though the clarity of such acquired images has been significantly improved due to the advance of the image sensor technology, the visual quality is hardly guaranteed under varying illumination conditions. In this paper, a novel yet simple method for low-light image enhancement is proposed via the maximal diffusion value. The key idea of the proposed method is to estimate the illumination component, which is likely to appear as the bright pixel even under the low-light condition, by exploring multiple diffusion spaces. Specifically, the illumination component can be accurately separated from the scene reflectance by selecting the maximal value at each pixel position of those diffusion spaces, and thus independently adjusted for the visual quality enhancement. That is, we propose to adopt the maximal value among diffused intensities at each pixel position, so-called maximal diffusion value, as the illumination component since illumination components buried in the dark tend to be revealed with bright intensities through the iterative diffusion process. In contrast to previous approaches that still pose difficulties to balance between over-saturated and conservative restorations, the proposed method improves the image quality without any significant distortion while successfully suppressing the problem of noise amplification. Experimental results on benchmark datasets show the efficiency and robustness of the proposed method compared to previous approaches introduced in literature.
dc.language.iso
eng
dc.publisher
IEEE
dc.relation.ispartofseries
IEEE Access;
dc.title
Low-Light Image Enhancement Based on Maximal Diffusion Values
dc.identifier.doi
10.1109/access.2019.2940452
dc.citation.volume
7
dc.contributor.approver
KOAR, ADMIN
dc.date.dateaccepted
2022-04-13T02:10:29Z
dc.date.datesubmitted
2022-04-13T02:10:29Z
dc.identifier.bibliographicCitation
vol. 7
dc.identifier.url
https://scienceon.kisti.re.kr/srch/selectPORSrchArticle.do?cn=NART99432937
dc.subject.keyword
Visual quality
dc.subject.keyword
varying illumination condition
dc.subject.keyword
low-light image enhancement
dc.subject.keyword
maximal diffusion value
dc.subject.keyword
multiple diffusion spaces
Appears in Collections:
7. KISTI 연구성과 > 학술지 발표논문
Files in This Item:
There are no files associated with this item.

Browse