# A First Look at Dataset Bias in License Plate Recognition

arXiv: https://arxiv.org/abs/2208.10657 · HTML: https://mlsanity.com/paper/2208.10657/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 39 references that are in the map.
- First posted on arXiv 23 Aug 2022.

## Builds on (most cited first, 17 of 17)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [A Deeper Look at Dataset Bias](https://mlsanity.com/paper/1505.01257/) (2015)
- [A Robust Real-Time Automatic License Plate Recognition Based on the YOLO Detector](https://mlsanity.com/paper/1802.09567/) (2018)
- [Detect and Correct Bias in Multi-Site Neuroimaging Datasets](https://mlsanity.com/paper/2002.05049/) (2020)
- [An Efficient and Layout-Independent Automatic License Plate Recognition System Based on the YOLO detector](https://mlsanity.com/paper/1909.01754/) (2019)
- [A Robust Attentional Framework for License Plate Recognition in the Wild](https://mlsanity.com/paper/2006.03919/) (2020)
- [Benchmark for License Plate Character Segmentation](https://mlsanity.com/paper/1607.02937/) (2016)
- [On the Cross-dataset Generalization in License Plate Recognition](https://mlsanity.com/paper/2201.00267/) (2022)
- [Rethinking and Designing a High-performing Automatic License Plate Recognition Approach](https://mlsanity.com/paper/2011.14936/) (2020)
- [Vehicle-Rear: A New Dataset to Explore Feature Fusion for Vehicle Identification Using Convolutional Neural Networks](https://mlsanity.com/paper/1911.05541/) (2019)
- [Towards Image-based Automatic Meter Reading in Unconstrained Scenarios: A Robust and Efficient Approach](https://mlsanity.com/paper/2009.10181/) (2020)
- [Unified Chinese License Plate Detection and Recognition with High Efficiency](https://mlsanity.com/paper/2205.03582/) (2022)
- [Learning to Unlearn: Building Immunity to Dataset Bias in Medical Imaging Studies](https://mlsanity.com/paper/1812.01716/) (2018)
- [DELP-DAR System for License Plate Detection and Recognition](https://mlsanity.com/paper/1910.01853/) (2019)
- [Light In The Black: An Evaluation of Data Augmentation Techniques for COVID-19 CT's Semantic Segmentation](https://mlsanity.com/paper/2205.09722/) (2022)
- [Segmentation-Free Approaches for Handwritten Numeral String Recognition](https://mlsanity.com/paper/1804.09279/) (2018)

## Built on by (most cited first, 18 of 18)

- [Do We Train on Test Data? The Impact of Near-Duplicates on License Plate Recognition](https://mlsanity.com/paper/2304.04653/) (2023)
- [Combining Attention Module and Pixel Shuffle for License Plate Super-Resolution](https://mlsanity.com/paper/2210.16836/) (2022)
- [Face Super-Resolution Using Stochastic Differential Equations](https://mlsanity.com/paper/2209.12064/) (2022)
- [Leveraging Model Fusion for Improved License Plate Recognition](https://mlsanity.com/paper/2309.04331/) (2023)
- [Super-Resolution of License Plate Images Using Attention Modules and Sub-Pixel Convolution Layers](https://mlsanity.com/paper/2305.17313/) (2023)
- [Enhancing License Plate Super-Resolution: A Layout-Aware and Character-Driven Approach](https://mlsanity.com/paper/2408.15103/) (2024)
- [Improving Small Drone Detection Through Multi-Scale Processing and Data Augmentation](https://mlsanity.com/paper/2504.19347/) (2025)
- [Advancing Multinational License Plate Recognition Through Synthetic and Real Data Fusion: A Comprehensive Evaluation](https://mlsanity.com/paper/2601.07671/) (2026)
- [LPLCv2: An Expanded Dataset for Fine-Grained License Plate Legibility Classification](https://mlsanity.com/paper/2604.08741/) (2026)
- [DACov: A Deeper Analysis of Data Augmentation on the Computed Tomography Segmentation Problem](https://mlsanity.com/paper/2303.05912/) (2023)
- [SamLP: A Customized Segment Anything Model for License Plate Detection](https://mlsanity.com/paper/2401.06374/) (2024)
- [Revisiting Vehicle Color Recognition in Long-Tailed Surveillance Scenarios](https://mlsanity.com/paper/2606.13625/) (2026)
- [Veri-Car: Towards Open-world Vehicle Information Retrieval](https://mlsanity.com/paper/2411.06864/) (2024)
- [Iranian License Plate Recognition Using a Reliable Deep Learning Approach](https://mlsanity.com/paper/2305.02292/) (2023)
- [BLPR: Robust License Plate Recognition under Viewpoint and Illumination Variations via Confidence-Driven VLM Fallback](https://mlsanity.com/paper/2604.09927/) (2026)
- [What Are We Really Measuring? Rethinking Dataset Bias in Web-Scale Natural Image Collections via Unsupervised Semantic Clustering](https://mlsanity.com/paper/2604.13610/) (2026)
- [VeriCam: A Verification Baseline for the Classification of Unknown Data](https://mlsanity.com/paper/2608.31107/) (2026)
- [A Benchmark for Vehicle Attribute Classification in Cross-Domain Surveillance Scenarios](https://mlsanity.com/paper/2609.01584/) (2026)

## Abstract (arXiv)

Public datasets have played a key role in advancing the state of the art in License Plate Recognition (LPR). Although dataset bias has been recognized as a severe problem in the computer vision community, it has been largely overlooked in the LPR literature. LPR models are usually trained and evaluated separately on each dataset. In this scenario, they have often proven robust in the dataset they were trained in but showed limited performance in unseen ones. Therefore, this work investigates the dataset bias problem in the LPR context. We performed experiments on eight datasets, four collected in Brazil and four in mainland China, and observed that each dataset has a unique, identifiable "signature" since a lightweight classification model predicts the source dataset of a license plate (LP) image with more than 95% accuracy. In our discussion, we draw attention to the fact that most LPR models are probably exploiting such signatures to improve the results achieved in each dataset at the cost of losing generalization capability. These results emphasize the importance of evaluating LPR models in cross-dataset setups, as they provide a better indication of generalization (hence real-world performance) than within-dataset ones.