Lightweight Scene Text Recognition Based on Transformer
Sensors · 05.05.2023 · 23 (9) · 4490
DOI: 10.3390/s23094490 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 05.05.2023. Verfasst von Xin Luan und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Information Science and Engineering, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation, National Natural Science Foundation of China Joint Fund Project.
Abstract (Originalsprache)
Scene text recognition (STR) has been a hot research field in computer vision, aiming to recognize text in natural scenes using computers. Currently, attention-based encoder–decoder frameworks struggle to precisely align feature regions with the target object when dealing with complex and low-quality images, a phenomenon known as attention drift. Additionally, with the rise of Transformer, the increasing size of parameters results in higher computational costs. In order to solve the above problems, based on the latest research results of Vision Transformer (ViT), we utilize an additional position-enhancement branch to alleviate attention drift and dynamically fused position information with visual information to achieve better recognition accuracy. The experimental results demonstrate that our model achieves a 3% higher average recognition accuracy on the test set compared to the baseline. Meanwhile, our model maintains the advantage of a small number of parameters and fast inference speed, achieving a good balance between accuracy, speed, and computational load.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Information Science and Engineering, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China.
- Xinjiang Laboratory of Multi-Language Information Technology, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China.
- Xinjiang Multilingual Information Technology Research Center, Xinjiang University, No. 777 Huarui Street, Urumqi 830017, China.
Förderung
- National Natural Science Foundation
- National Natural Science Foundation of China Joint Fund Project
Zitieren
APA
Luan, X., Zhang, J., Xu, M., Silamu, W., & Li, Y. (2023). Lightweight Scene Text Recognition Based on Transformer. Sensors, 23(9), 4490. https://doi.org/10.3390/s23094490
Vancouver
Luan X, Zhang J, Xu M, Silamu W, Li Y. Lightweight Scene Text Recognition Based on Transformer. Sensors. 2023;23(9):4490. doi:10.3390/s23094490
BibTeX
@article{Luan2023,
author = {Luan, Xin and Zhang, Jinwei and Xu, Miaomiao and Silamu, Wushouer and Li, Yanbing},
title = {Lightweight Scene Text Recognition Based on Transformer},
journal = {Sensors},
year = {2023},
volume = {23},
number = {9},
pages = {4490},
doi = {10.3390/s23094490}
}
EUVIMED