Lin, Che-Tsung and Ng, Chun Chet and Tan, Zhi Qin and Nah, Wan Jun and Wang, Xinyu and Kew, Jie Long and Hsu, Pohao and Lai, Shang Hong and Chan, Chee Seng and Zach, Christopher (2025) Text in the dark: Extremely low-light text image enhancement. Signal Processing: Image Communication, 130. p. 117222. ISSN 0923-5965, DOI https://doi.org/10.1016/j.image.2024.117222.
Full text not available from this repository.Abstract
Extremely low-light text images pose significant challenges for scene text detection. Existing methods enhance these images using low-light image enhancement techniques before text detection. However, they fail to address the importance of low-level features, which are essential for optimal performance in downstream scene text tasks. Further research is also limited by the scarcity of extremely low-light text datasets. To address these limitations, we propose a novel, text-aware extremely low-light image enhancement framework. Our approach first integrates a Text-Aware Copy-Paste (Text-CP) augmentation method as a preprocessing step, followed by a dual-encoder-decoder architecture enhanced with Edge-Aware attention modules. We also introduce text detection and edge reconstruction losses to train the model to generate images with higher text visibility. Additionally, we propose a Supervised Deep Curve Estimation (Supervised-DCE) model for synthesizing extremely low-light images, allowing training on publicly available scene text datasets such as IC15. To further advance this domain, we annotated texts in the extremely low-light See In the Dark (SID) and ordinary LOw-Light (LOL) datasets. The proposed framework is rigorously tested against various traditional and deep learning-based methods on the newly labeled SID-Sony-Text, SID-Fuji-Text, LOL-Text, and synthetic extremely low-light IC15 datasets. Our extensive experiments demonstrate notable improvements in both image enhancement and scene text tasks, showcasing the model's efficacy in text detection under extremely low-light conditions. Code and datasets will be released publicly at https://github.com/chunchet-ng/Text-in-the-Dark.
| Item Type: | Article |
|---|---|
| Funders: | UNSPECIFIED |
| Uncontrolled Keywords: | Extremely low-light image enhancement; Edge attention; Text aware augmentation; Scene text detection; Scene text recognition |
| Subjects: | T Technology > TK Electrical engineering. Electronics Nuclear engineering |
| Divisions: | Universiti Malaya |
| Depositing User: | Ms. Juhaida Abd Rahim |
| Date Deposited: | 21 Feb 2025 01:54 |
| Last Modified: | 21 Feb 2025 01:54 |
| URI: | http://eprints.um.edu.my/id/eprint/47346 |
Actions (login required)
 |
View Item |
