A Scene Text Detector for Text with Arbitrary Shapes
Joint Authors
Wu, Weijia
Xing, Jici
Yang, Cheng
Wang, Yuxing
Zhou, Hong
Source
Mathematical Problems in Engineering
Issue
Vol. 2020, Issue 2020 (31 Dec. 2020), pp.1-11, 11 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2020-06-11
Country of Publication
Egypt
No. of Pages
11
Main Subjects
Abstract EN
The performance of text detection is crucial for the subsequent recognition task.
Currently, the accuracy of the text detector still needs further improvement, particularly those with irregular shapes in a complex environment.
We propose a pixel-wise method based on instance segmentation for scene text detection.
Specifically, a text instance is split into five components: a Text Skeleton and four Directional Pixel Regions, then restoring itself based on these elements and receiving supplementary information from other areas when one fails.
Besides, a Confidence Scoring Mechanism is designed to filter characters similar to text instances.
Experiments on several challenging benchmarks demonstrate that our method achieves state-of-the-art results in scene text detection with an F-measure of 84.6% on Total-Text and 86.3% on CTW1500.
American Psychological Association (APA)
Wu, Weijia& Xing, Jici& Yang, Cheng& Wang, Yuxing& Zhou, Hong. 2020. A Scene Text Detector for Text with Arbitrary Shapes. Mathematical Problems in Engineering،Vol. 2020, no. 2020, pp.1-11.
https://search.emarefa.net/detail/BIM-1201889
Modern Language Association (MLA)
Wu, Weijia…[et al.]. A Scene Text Detector for Text with Arbitrary Shapes. Mathematical Problems in Engineering No. 2020 (2020), pp.1-11.
https://search.emarefa.net/detail/BIM-1201889
American Medical Association (AMA)
Wu, Weijia& Xing, Jici& Yang, Cheng& Wang, Yuxing& Zhou, Hong. A Scene Text Detector for Text with Arbitrary Shapes. Mathematical Problems in Engineering. 2020. Vol. 2020, no. 2020, pp.1-11.
https://search.emarefa.net/detail/BIM-1201889
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1201889