SRR-GAN: Super-Resolution based Recognition with GAN for Low-Resolved Text Images

Text images convey important information for various applications, while the recognition of low-resolution text images is a challenge. Most existing methods solve this problem using a cascaded scheme in two steps: image super-resolution and high-resolution text recognition. In this paper, we propose...

Full description

Saved in:
Bibliographic Details
Published in2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR) pp. 1 - 6
Main Authors Xu, Ming-Chao, Yin, Fei, Liu, Cheng-Lin
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.09.2020
Subjects
Adversarial Learning
Feature extraction
Handwriting recognition
Image recognition
Image restoration
Image segmentation
Super-Resolution
Text recognition
Training
Online AccessGet full text

Cover

More Information
Summary:Text images convey important information for various applications, while the recognition of low-resolution text images is a challenge. Most existing methods solve this problem using a cascaded scheme in two steps: image super-resolution and high-resolution text recognition. In this paper, we propose a novel framework, called SRR-GAN, which integrates text recognition with super-resolution via adversarial learning. By joint training of recognition and super-resolution models, more generic features for images of various quality can be learned, so as to yield high recognition performance for both high-resolution and low-resolution images. Experiments on natural scene and handwritten texts demonstrate that SRR-GAN outperforms the cascaded scheme on low-resolution images. The results show that SRR-GAN can improve recognition accuracies by 10%-20% relatively on five datasets of scene/handwritten texts. Meanwhile, SRR-GAN maintains high performance on high-resolution images.
DOI:10.1109/ICFHR2020.2020.00012