Text in the Dark: Extremely Low-Light Text Image Enhancement
Che-Tsung Lin, Chun Chet Ng, Zhi Qin Tan, Wan Jun Nah, Xinyu Wang, Jie, Long Kew, Pohao Hsu, Shang Hong Lai, Chee Seng Chan, Christopher Zach

TL;DR
This paper introduces a novel encoder-decoder framework with edge-aware attention and specialized loss functions for enhancing extremely low-light text images, significantly improving text detection and recognition performance.
Contribution
It proposes a new enhancement method focusing on low-level features and introduces a supervised deep curve estimation model to synthesize low-light images, addressing dataset scarcity.
Findings
Outperforms state-of-the-art in image quality and text recognition metrics
Effective in low-light conditions on multiple datasets
Provides publicly available code and datasets for further research
Abstract
Extremely low-light text images are common in natural scenes, making scene text detection and recognition challenging. One solution is to enhance these images using low-light image enhancement methods before text extraction. However, previous methods often do not try to particularly address the significance of low-level features, which are crucial for optimal performance on downstream scene text tasks. Further research is also hindered by the lack of extremely low-light text datasets. To address these limitations, we propose a novel encoder-decoder framework with an edge-aware attention module to focus on scene text regions during enhancement. Our proposed method uses novel text detection and edge reconstruction losses to emphasize low-level scene text features, leading to successful text extraction. Additionally, we present a Supervised Deep Curve Estimation (Supervised-DCE) model to…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsDigital Media Forensic Detection
MethodsFocus
