• Home
  • Search
  • Text Image Super Resolution Using Deep Attention Neural Network
  • Cite Icon2
  • https://doi.org/10.1109/gcce53005.2021.9621914Copy DOI Icon

Text Image Super Resolution Using Deep Attention Neural Network

  • Oct 12, 2021
  • Yun Liu +5 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

In this paper, we propose a super-resolution method for text images to improve the accuracy of optical character recognition (OCR). The accuracy of OCR is closely related to the resolution of the image, and when OCR is applied to low resolution text images, satisfactory results are often not obtained. In the proposed method, we extract more representative feature information from text images by combining channel and spatial attention. Furthermore, we propose a new loss function called “edge loss”. Experimental results show that the recognition accuracy of text images by our SR method is 5.87% higher than that of the original low-resolution images, and also higher than the results of BICUBIC and the baseline model.

Similar Papers
  • PDF
  • Research Article
  • Citations2

Pixel-Level Degradation for Text Image Super-Resolution and Recognition

  • Nov 05, 2023
  • Electronics
  • Xiaohong Qian +4
  • Book Chapter
  • Citations18

Building Super-Resolution Image Generator for OCR Accuracy Improvement

  • Jan 01, 2020
  • Xujun Peng +1
  • Conference Article
  • Citations4

A Lightweight Deep Residual Attention Network for Single Image Super Resolution

  • Feb 23, 2023
  • Inderjeet +1
  • Dissertation

Improving OCR Accuracy of Damaged Pictures with Generative Adversarial Networks

  • Dec 11, 2019
  • Pu Du
  • Book Chapter
  • Citations13

FAWA: Fast Adversarial Watermark Attack on Optical Character Recognition (OCR) Systems

  • Jan 01, 2021
  • Lu Chen +2
  • Book Chapter
  • Citations1

Automatic Annotation Method for Document Image Binarization in Real Systems

  • Jan 01, 2020
  • Ryosuke Odate
  • Conference Article
  • Citations63

A Fast Alignment Scheme for Automatic OCR Evaluation of Books

  • Jan 01, 2011
  • Ismet Zeki Yalniz +1
  • Conference Article
  • Citations1

Towards a Higher Accuracy of Optical Character Recognition of Chinese Rare Books in Making Use of Text Model

  • May 08, 2019
  • Hsiang-An Wang +1
  • Research Article
  • Citations1

Optical character recognition system with natural language processing for data recovery on scanned old academic card reports

  • Dec 09, 2024
  • Acta Scientiarum. Technology
  • Edwin Roi Casas-Huamanta +5
  • PDF
  • Conference Article
  • Citations3

OCR Processing of Swedish Historical Newspapers Using Deep Hybrid CNN–LSTM Networks

  • Jan 01, 2021
  • Molly Brandt Skelbye +1
  • Research Article
  • Citations2

A conclusive methodology for rating OCR performance

  • Jul 26, 2005
  • Journal of the American Society for Information Science and Technology
  • Nathan E Brener +2
  • Conference Article
  • Citations18

Document image OCR accuracy prediction via latent Dirichlet allocation

  • Aug 01, 2015
  • Xujun Peng +2
  • Research Article
  • Citations11

AN ACCURATE AND EFFICIENT SKEW ESTIMATION TECHNIQUE FOR SOUTH INDIAN DOCUMENTS: A NEW BOUNDARY GROWING AND NEAREST NEIGHBOR CLUSTERING BASED APPROACH

  • Jan 01, 2007
  • International Journal of Robotics and Automation
  • V.N.M Aradhya +2
  • Research Article

Rectification of curved document images based on single view three-dimensional reconstruction.

  • Sep 28, 2016
  • Journal of the Optical Society of America. A, Optics, image science, and vision
  • Lai Kang +4
  • Conference Article
  • Citations7

Poor Man's OCR Post-Correction

  • Jun 01, 2017
  • Harald Hammarström +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.