Advancing Multinational License Plate Recognition Through Synthetic and Real Data Fusion: A Comprehensive Evaluation

2025-01-01

IET Intelligent Transport Systems

AI Summary

This study addresses the limitations of existing license plate recognition methods in cross-country, multi-scenario applications, where performance degrades significantly under data scarcity and poor generalization—particularly in low-data regimes. For the first time, it systematically investigates the synergistic effects of three synthetic data generation strategies: template-based synthesis, character permutation, and generative adversarial networks (GANs). By integrating multi-source synthetic data with limited real-world samples, the authors conduct end-to-end training and evaluation of 16 OCR models across 12 publicly available international license plate datasets. Experimental results demonstrate that the proposed approach consistently outperforms state-of-the-art methods and commercial systems in both in-domain and cross-domain settings. Notably, it achieves robust recognition accuracy even with minimal real data, substantially enhancing model generalization and practical applicability.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Automatic license plate recognition (ALPR) is a frequent research topic due to its wide‐ranging practical applications. While recent studies use synthetic images to improve license plate recognition (LPR) results, there remain several limitations in these efforts. This work addresses these constraints by comprehensively exploring the integration of real and synthetic data to enhance LPR performance. We subject 16 optical character recognition (OCR) models to a benchmarking process involving 12 public datasets acquired from various regions. Several key findings emerge from our investigation. Primarily, the massive incorporation of synthetic data substantially boosts model performance in both intra‐ and cross‐dataset scenarios. We examine three distinct methodologies for generating synthetic data: template‐based generation, character permutation, and utilizing a generative adversarial network (GAN) model, each contributing significantly to performance enhancement. The combined use of these methodologies demonstrates a notable synergistic effect, leading to end‐to‐end results that surpass those reached by state‐of‐the‐art methods and established commercial systems. Our experiments also underscore the efficacy of synthetic data in mitigating challenges posed by limited training data, enabling remarkable results to be achieved even with small fractions of the original training data. Finally, we investigate the trade‐off between accuracy and speed among different models, identifying those that strike the optimal balance in each intra‐dataset and cross‐dataset settings.

Problem

• License Plate Recognition
• Synthetic Data
• Real Data Fusion
• Multinational
• OCR

Innovation

• synthetic data fusion
• license plate recognition
• GAN-based synthesis
• cross-dataset generalization
• OCR benchmarking