A Dataset and Model for Realistic License Plate Deblurring

TL;DR

This paper introduces a large-scale dataset for license plate deblurring and proposes a novel GAN-based model that effectively restores license plate images affected by motion blur, improving recognition accuracy in real-world scenarios.

Contribution

The paper presents the first large-scale license plate deblurring dataset and a specialized GAN model with modules for feature fusion, text reconstruction, and detail perception.

Findings

The LPBlur dataset enables effective training and testing of deblurring models.

The proposed LPDGAN outperforms existing methods in realistic license plate deblurring.

The model improves license plate recognition accuracy in motion-blurred conditions.

Abstract

Vehicle license plate recognition is a crucial task in intelligent traffic management systems. However, the challenge of achieving accurate recognition persists due to motion blur from fast-moving vehicles. Despite the widespread use of image synthesis approaches in existing deblurring and recognition algorithms, their effectiveness in real-world scenarios remains unproven. To address this, we introduce the first large-scale license plate deblurring dataset named License Plate Blur (LPBlur), captured by a dual-camera system and processed through a post-processing pipeline to avoid misalignment issues. Then, we propose a License Plate Deblurring Generative Adversarial Network (LPDGAN) to tackle the license plate deblurring: 1) a Feature Fusion Module to integrate multi-scale latent codes; 2) a Text Reconstruction Module to restore structure through textual modality; 3) a Partition Discriminator Module to enhance the model's perception of details in each letter. Extensive experiments validate the reliability of the LPBlur dataset for both model training and testing, showcasing that our proposed model outperforms other state-of-the-art motion deblurring methods in realistic license plate deblurring scenarios. The dataset and code are available at https://github.com/haoyGONG/LPDGAN.