Unconstrained Bilingual Scene Text Reading Using Octave as a Feature Extractor

Unconstrained Bilingual Scene Text Reading Using Octave as a Feature Extractor

Reading text and unified text detection and recognition from natural images are the most challenging applications in computer vision and document analysis. Previously proposed end-to-end scene text reading methods do not consider the frequency of input images at feature extraction, which slows down...

Full description

Bibliographic Details
Main Authors: Direselign Addis Tadesse, Chuan-Ming Liu, Van-Dai Ta
Format: Article
Language:English
Published: MDPI AG 2020-06-01
Series:Applied Sciences
Subjects:
octave convolution
bilingual scene text reading
Ethiopic script
attention
Online Access:https://www.mdpi.com/2076-3417/10/13/4474

Internet

https://www.mdpi.com/2076-3417/10/13/4474

Similar Items