GERIS: A game-theoretic framework for filtering instance-dependent label noise in license plate data augmentation

Jalili Shani, Seyedeh Sara; Ahmadian, Rouhollah; Rahmani, Amin; Bideh, Mahdi; Ghatee, Mehdi

doi:10.22060/ajmc.2025.23680.1288

GERIS: A game-theoretic framework for filtering instance-dependent label noise in license plate data augmentation

Articles in Press

Document Type : Original Article

Authors

Seyedeh Sara Jalili Shani ¹

Rouhollah Ahmadian ²

Amin Rahmani ²

Mahdi Bideh ²

Mehdi Ghatee ²

¹ Department of Computer Science, University of Alberta, Alberta, Canada

² Department of Mathematics and Computer Science, Amirkabir University of Technology (Tehran Polytechnic), Iran

10.22060/ajmc.2025.23680.1288

Abstract

In this paper, we propose GERIS, a game-theoretic framework for instance selection in the data augmentation phase of license plate recognition systems. During augmentation, synthetic license plate images are generated and transformed using stochastic noise to simulate real-world conditions. However, certain noise configurations lead to highly distorted, unreadable images that degrade model performance by introducing instance-dependent label noise. GERIS formulates a non-cooperative game in which each noise vector competes for inclusion in the training set based on its similarity to labeled data and its contribution to model reliability. By identifying and pruning low-quality instances, GERIS improves the overall quality of the augmented dataset. Unlike traditional black-box learning methods, GERIS offers a transparent, theoretically grounded mechanism for data filtering. Experimental results demonstrate that GERIS outperforms existing instance selection methods in terms of classification accuracy and robustness.

Keywords

License plate recognition

Data augmentation

Instance-dependent noisy label

Non-cooperative game

Instance selection

Subjects