Search: onr:"swepub:oai:research.chalmers.se:4a0180c6-8ce8-496e-b9f6-05f014f8464d" >
Extremely Low-light...
Extremely Low-light Image Enhancement with Scene Text Restoration
-
- Hsu, Pohao (author)
- National Tsing Hua University
-
- Lin, Che-Tsung, 1979 (author)
- Chalmers tekniska högskola,Chalmers University of Technology
-
- Ng, Chun Chet (author)
- University of Malaya
-
show more...
-
- Kew, Jie-Long (author)
- University of Malaya
-
- Tan, Mei Yih (author)
- National Tsing Hua University
-
- Lai, Shang-Hong (author)
- National Tsing Hua University
-
- Chan, Chee Seng (author)
- University of Malaya
-
- Zach, Christopher, 1974 (author)
- Chalmers tekniska högskola,Chalmers University of Technology
-
show less...
-
(creator_code:org_t)
- ISBN 9781665490627
- 2022
- 2022
- English.
-
In: Proceedings - International Conference on Pattern Recognition. - 1051-4651. - 9781665490627 ; 2022-August, s. 317-323
- Related links:
-
https://ieeexplore.i...
-
show more...
-
https://doi.org/10.1...
-
https://research.cha...
-
show less...
Abstract
Subject headings
Close
- Deep learning based methods have made impressive progress in enhancing extremely low-light images - the image quality of the reconstructed images has generally improved. However, we found out that most of these methods could not sufficiently recover the image details, for instance the texts in the scene. In this paper, a novel image enhancement framework is proposed to specifically restore the scene texts, as well as the overall quality of the image simultaneously under extremely low-light images conditions. Particularly, we employed a selfregularised attention map, an edge map, and a novel text detection loss. The quantitative and qualitative experimental results have shown that the proposed model outperforms stateof-the-art methods in terms of image restoration, text detection, and text spotting on See In the Dark and ICDAR15 datasets.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)
Publication and Content Type
- kon (subject category)
- ref (subject category)
Find in a library
To the university's database