EUVIMEDEUVIMED entdecken
Crossref

Scene Text Detection Based on Text Stroke Components

Xinyue Hou iD, Pengsen Cheng iD, Hongyu Gao iD, Xin Li iD, Jiayong Liu iD

International Journal of Neural Systems · 2025

DOI: 10.1142/s0129065725500200 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Neural Systems, 2025. Verfasst von Xinyue Hou und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Cyber Science and Engineering, Sichuan University, Chengdu 610207, Sichuan, P. R. China. Hauptthemen laut MEDLINE: Pattern Recognition, Automated, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 55 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The detection of scene text holds significant importance across a variety of application scenarios. However, previous methods were insufficient for detecting and recognizing text instances, such as variations in text size, chaotic background and diverse text orientations. To address these challenges, this paper proposes a novel methodology based on Text Stroke Components (TSC). The method leverages Harris corner detection to identify critical points of text strokes, such as endpoints, turning points, and curvatures. By analyzing the clustered regions of these points, the approach effectively localizes text characters. To enhance the detection process, a transparency parameter [Formula: see text] is introduced to control the fusion between original images and corner-detection images. This improves the localization of key stroke points, and reduces background noise interference. The proposed method is evaluated through extensive experiments, demonstrating superior performance compared to existing scene text detectors. Furthermore, the method is jointly trained with the ABINet recognition model across all stages. Comprehensive experiments conducted on 13 datasets reveal that this approach significantly outperforms SOTA methods. These results underscore the advantages of using text stroke components for key-point localization through the corner detection algorithm in scene text detection.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Pattern Recognition, AutomatedImage Processing, Computer-AssistedHumansAlgorithmsNeural Networks, Computer

Stichwörter der Autor:innen

Text stroke componentscorner detectionscene text detection

Autor:innen und Institutionen

  • School of Cyber Science and Engineering, Sichuan University, Chengdu 610207, Sichuan, P. R. China.

ORCID-Profile: Xinyue Hou, Pengsen Cheng, Hongyu Gao, Xin Li, Jiayong Liu

Zitieren

APA

Hou, X., Cheng, P., Gao, H., Li, X., & Liu, J. (2025). Scene Text Detection Based on Text Stroke Components. International Journal of Neural Systems. https://doi.org/10.1142/s0129065725500200

Vancouver

Hou X, Cheng P, Gao H, Li X, Liu J. Scene Text Detection Based on Text Stroke Components. International Journal of Neural Systems. 2025. doi:10.1142/s0129065725500200

BibTeX
@article{Hou2025,
  author = {Hou, Xinyue and Cheng, Pengsen and Gao, Hongyu and Li, Xin and Liu, Jiayong},
  title = {Scene Text Detection Based on Text Stroke Components},
  journal = {International Journal of Neural Systems},
  year = {2025},
  doi = {10.1142/s0129065725500200}
}
Kostenlos starten →