آمار

تعداد نشریات9
تعداد شماره‌ها446
تعداد مقالات5,719
تعداد مشاهده مقاله8,018,448
تعداد دریافت فایل اصل مقاله6,527,279
Jalili Shani, Seyedeh Sara, Ahmadian, Rouhollah, Rahmani, Amin, Bideh, Mahdi, Ghatee, Mehdi. (1404). GERIS: A game-theoretic framework for filtering instance-dependent label noise in license plate data augmentation. نشریه مهندسی عمران امیرکبیر, (), -. doi: 10.22060/ajmc.2025.23680.1288
Seyedeh Sara Jalili Shani; Rouhollah Ahmadian; Amin Rahmani; Mahdi Bideh; Mehdi Ghatee. "GERIS: A game-theoretic framework for filtering instance-dependent label noise in license plate data augmentation". نشریه مهندسی عمران امیرکبیر, , , 1404, -. doi: 10.22060/ajmc.2025.23680.1288
Jalili Shani, Seyedeh Sara, Ahmadian, Rouhollah, Rahmani, Amin, Bideh, Mahdi, Ghatee, Mehdi. (1404). 'GERIS: A game-theoretic framework for filtering instance-dependent label noise in license plate data augmentation', نشریه مهندسی عمران امیرکبیر, (), pp. -. doi: 10.22060/ajmc.2025.23680.1288
Jalili Shani, Seyedeh Sara, Ahmadian, Rouhollah, Rahmani, Amin, Bideh, Mahdi, Ghatee, Mehdi. GERIS: A game-theoretic framework for filtering instance-dependent label noise in license plate data augmentation. نشریه مهندسی عمران امیرکبیر, 1404; (): -. doi: 10.22060/ajmc.2025.23680.1288

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

AUT Journal of Mathematics and Computing
مقالات آماده انتشار، پذیرفته شده، انتشار آنلاین از تاریخ 16 دی 1404
نوع مقاله: Original Article
شناسه دیجیتال (DOI): 10.22060/ajmc.2025.23680.1288
نویسندگان
Seyedeh Sara Jalili Shani1؛ Rouhollah Ahmadian2؛ Amin Rahmani2؛ Mahdi Bideh2؛ Mehdi Ghatee* 2
1Department of Computer Science, University of Alberta, Alberta, Canada
2Department of Mathematics and Computer Science, Amirkabir University of Technology (Tehran Polytechnic), Iran
چکیده
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.
کلیدواژه‌ها
License plate recognition؛ Data augmentation؛ Instance-dependent noisy label؛ Non-cooperative game؛ Instance selection
آمار
تعداد مشاهده مقاله: 82


سامانه مدیریت نشریات علمی. طراحی و پیاده سازی از سیناوب