Detection and rectification of arbitrary shaped scene texts by using text keypoints and links
Detection and recognition of scene texts of arbitrary shapes remain a grand challenge due to the super-rich text shape variation in text line orientations, lengths, curvatures, etc. This paper presents a mask-guided multi-task network that detects and rectifies scene texts of arbitrary shapes reliab...
Main Authors: | Xue, Chuhui, Lu, Shijian, Hoi, Steven |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Journal Article |
Language: | English |
Published: |
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/161795 |
Similar Items
-
Image-to-character-to-word transformers for accurate scene text recognition
by: Xue, Chuhui, et al.
Published: (2023) -
SUST and RUST: Two Datasets for Uyghur Scene Text Recognition
by: Kong Fanjie, et al.
Published: (2023-01-01) -
Improving transformer for scene text and handwritten text recognition
by: Tan, Yew Lee
Published: (2024) -
A Robot Object Recognition Method Based on Scene Text Reading in Home Environments
by: Shuhua Liu, et al.
Published: (2021-03-01) -
Lightweight Scene Text Recognition Based on Transformer
by: Xin Luan, et al.
Published: (2023-05-01)