Reading in the Dark: Low-light Scene Text Recognition

TL;DR

This paper introduces a new dataset and methods for recognizing scene text in low-light environments, emphasizing the importance of joint training and a novel image enhancement module for improved accuracy.

Contribution

It presents a large-scale low-light scene text dataset, a novel re-render low-light image enhancement module, and a comprehensive benchmark for low-light text recognition.

Findings

Standalone LLIE or OCR models perform poorly in low-light conditions.

Joint training of enhancement and recognition models improves accuracy.

The RLLIE module enhances real-world low-light scene text recognition.

Abstract

Accurate text recognition in low-light environments is essential for intelligent systems in applications ranging from autonomous vehicles to smart surveillance. However, challenges such as poor illumination and noise interference remain underexplored. To address this gap, we introduce LSTR, a large-scale Low-light Scene Text Recognition dataset comprising 11,273 low-light images generated from well-lit datasets (ICDAR2015, IIIT5K, and WordArt), along with ESTR, which includes 60 real nighttime street-scene images in English and Spanish for exclusive evaluation. We explore two solution strategies: (1) employing Optical Character Recognition (OCR) models with fine-tuning and LoRA-based fine-tuning and (2) a joint training strategy that integrates a low-light image enhancement (LLIE) module with an OCR model. In particular, we propose a novel re-render LLIE (RLLIE) module, which demonstrates improved performance on real-world data. Through extensive experimentation, we analyze various training strategies and address a key research question: \emph{How bright is bright enough for effective scene text recognition?} Our results indicate that standalone LLIE or OCR models perform inadequately under low-light conditions, highlighting the advantages of specialized, jointly trained text-centric approaches. Additionally, we provide a comprehensive benchmark to support future research in robust low-light scene text recognition. https://huggingface.co/datasets/lumimusta/Low-light_Scene_Text_Dataset.