Extremely Low-light Image Enhancement with Scene Text Restoration
Paper i proceeding, 2022

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.

Författare

Pohao Hsu

National Tsing Hua University

Che-Tsung Lin

Chalmers, Elektroteknik, Signalbehandling och medicinsk teknik

Chun Chet Ng

University of Malaya

Jie-Long Kew

University of Malaya

Mei Yih Tan

National Tsing Hua University

Shang-Hong Lai

National Tsing Hua University

Chee Seng Chan

University of Malaya

Christopher Zach

Chalmers, Elektroteknik, Signalbehandling och medicinsk teknik

Proceedings - International Conference on Pattern Recognition

10514651 (ISSN)

Vol. 2022 317-323
978-1-6654-9062-7 (ISBN)

International Conference on Pattern Recognition
Montréal Québec, Canada,

Ämneskategorier

Datorseende och robotik (autonoma system)

DOI

10.1109/ICPR56361.2022.9956716

ISBN

9781665490627

Mer information

Senast uppdaterat

2024-01-03