A Transformer-Based Framework for Scene Text Recognition

A Transformer-Based Framework for Scene Text Recognition

Scene Text Recognition (STR) has become a popular and long-standing research problem in computer vision communities. Almost all the existing approaches mainly adopt the connectionist temporal classification (CTC) technique. However, these existing approaches are not much effective for irregular STR....

Full description

Bibliographic Details
Main Authors: Prabu Selvam, Joseph Abraham Sundar Koilraj, Carlos Andres Tavera Romero, Meshal Alharbi, Abolfazl Mehbodniya, Julian L. Webber, Sudhakar Sengan
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Connectionist temporal classification
scene text recognition
self-attention
transformer
optical character recognition
deep learning
Online Access:https://ieeexplore.ieee.org/document/9894408/

Internet

https://ieeexplore.ieee.org/document/9894408/

Similar Items