Scene Uyghur Recognition Based on Visual Prediction Enhancement
Sensors · 20.10.2023 · 23 (20) · 8610
DOI: 10.3390/s23208610 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 20.10.2023. Verfasst von Yaqi Liu und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Information Science and Engineering, Xinjang University, No. 777 Huarui Street, Urumqi 830017, China. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Technology Research on Uyghur Chinese Speech Translation System, Internet Chinese Information Processing Verification System for Public Safety and Social Management, National 973 Key R&D Program—Internet Chinese Information Processing Verification System for Public Safety and Social Management.
Abstract (Originalsprache)
Aiming at the problems of Uyghur oblique deformation, character adhesion and character similarity in scene images, this paper proposes a scene Uyghur recognition model with enhanced visual prediction. First, the content-aware correction network TPS++ is used to perform feature-level correction for skewed text. Then, ABINet is used as the basic recognition network, and the U-Net structure in the vision model is improved to aggregate horizontal features, suppress multiple activation phenomena, better describe the spatial characteristics of character positions, and alleviate the problem of character adhesion. Finally, a visual masking semantic awareness (VMSA) module is added to guide the vision model to consider the language information in the visual space by masking the corresponding visual features on the attention map to obtain more accurate visual prediction. This module can not only alleviate the correction load of the language model, but also distinguish similar characters using the language information. The effectiveness of the improved method is verified by ablation experiments, and the model is compared with common scene text recognition methods and scene Uyghur recognition methods on the self-built scene Uyghur dataset.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Information Science and Engineering, Xinjang 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.
ORCID-Profile: Yaqi Liu, Fanjie Kong, Yanbing Li
Förderung
- Key Technology Research on Uyghur Chinese Speech Translation System
- Internet Chinese Information Processing Verification System for Public Safety and Social Management
- National 973 Key R&D Program—Internet Chinese Information Processing Verification System for Public Safety and Social Management
- National Natural Science Foundation of China—Key Technology Research on Uyghur Chinese Speech Translation System
Zitieren
APA
Liu, Y., Kong, F., Xu, M., Silamu, W., & Li, Y. (2023). Scene Uyghur Recognition Based on Visual Prediction Enhancement. Sensors, 23(20), 8610. https://doi.org/10.3390/s23208610
Vancouver
Liu Y, Kong F, Xu M, Silamu W, Li Y. Scene Uyghur Recognition Based on Visual Prediction Enhancement. Sensors. 2023;23(20):8610. doi:10.3390/s23208610
BibTeX
@article{Liu2023,
author = {Liu, Yaqi and Kong, Fanjie and Xu, Miaomiao and Silamu, Wushour and Li, Yanbing},
title = {Scene Uyghur Recognition Based on Visual Prediction Enhancement},
journal = {Sensors},
year = {2023},
volume = {23},
number = {20},
pages = {8610},
doi = {10.3390/s23208610}
}
EUVIMED