International Conference on Computer and Knowledge Engineering

Home / 13th International Conference on Computer and Knowledge Engineering

Farsi Optical Character Recognition Using a Transformer-based Model

Authors :

Fatemeh Asadi Zeydabadi¹ Elham Shabaninia² Hossein Nezamabadi-pour³ Melika Shojaee⁴

1- Department of Electrical Engineering, Shahid Bahonar University of Kerman 2- Department of Applied Mathematics, Faculty of Sciences and Modern Technologies, Graduate University of Advanced 3- Department of Electrical Engineering, Shahid Bahonar University of Kerman 4- Department of Computer Engineering, Shahid Bahonar University of Kerman

Keywords :

Optical Character Recognition (OCR)،Deep learning method،transformer،Farsi language

Abstract :

Optical Character Recognition (OCR) techniques have made significant advances in recent years using new technologies such as Transformers for Latin languages. However, research on under-resourced languages, such as Farsi, remains limited. This is partly due to the complex nature of the Farsi script, which poses unique challenges for OCR. Farsi OCR is essential for various applications, such as document management, digital archiving, and automated data entry. This study introduces a transformer-based deep neural network to recognize Farsi words, achieving promising results. Specifically, we evaluate the performance of our method against state-of-the-art techniques on two datasets, Shotor and Sadri, and demonstrate accuracies of 99.75% and 99.23%, respectively. Our results outperform other methods and highlight the potential of transformer-based approaches for Farsi OCR.