• Home
  • Search
  • Issue Based OCR Error Prediction in Video Streams
  • Cite Icon1
  • https://doi.org/10.23919/spa50552.2020.9241245Copy DOI Icon

Issue Based OCR Error Prediction in Video Streams

  • Sep 23, 2020
  • Dirk Siegmund +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

This paper increases the reliability of Optical Character Recognition (OCR) systems in natural scene by proposing a novel Image Quality Assessment (IQA) system. We propose to increase reliability based on the principle that OCR accuracy is a function of the quality of the input image. Detected text boxes are analyzed regarding their OCR score and different quality issues, such as blur, light and reflection effects. The novelty of our approach is to model IQA as a classification task, where one class represents high quality elements and each of the other classes represent a specific quality issue. We demonstrate how this methodology allows the training of IQA systems for complex quality metrics, even when no data labeled with the desired metric is available. Furthermore, a single IQA system outputs the quality score as well as the quality issues for a given image. We built on publicly available databases to generate 60k text boxes for each class and obtain 97,1% classification accuracy on a test set of 24k images. We conclude that the learnt quality metric is a valid indicator of common OCR errors by evaluating on the ICDAR 2003 Robust Word Recognition dataset.

Similar Papers
  • Conference Article
  • Citations3

DAF: differential ACE filtering image quality assessment by automatic color equalization

  • Jan 27, 2008
  • Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
  • S Ouni +3
  • PDF
  • Research Article
  • Citations5

HISP: Heterogeneous Image Signal Processor Pipeline Combining Traditional and Deep Learning Algorithms Implemented on FPGA

  • Aug 21, 2023
  • Electronics
  • Jie Chen +6
  • Research Article
  • Citations3

Improving Tesseract OCR Accuracy Using SymSpell Algorithm on Passport Data

  • Jan 27, 2025
  • Sinkron
  • Iqbaluddin Syam Had +2
  • Research Article
  • Citations32

An artificial intelligence-driven image quality assessment system for whole-body [18F]FDG PET/CT.

  • Dec 19, 2022
  • European Journal of Nuclear Medicine and Molecular Imaging
  • Chi Qi +7
  • Research Article
  • Citations14

A ParaBoost stereoscopic image quality assessment (PBSIQA) system

  • Feb 28, 2017
  • Journal of Visual Communication and Image Representation
  • Hyunsuk Ko +2
  • Conference Article
  • Citations62

Image quality assessment and human visual system

  • Jul 11, 2010
  • Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
  • Xinbo Gao +3
  • Research Article
  • Citations33

Optical Character Recognition System for Nastalique Urdu-Like Script Languages Using Supervised Learning

  • Sep 01, 2019
  • International Journal of Pattern Recognition and Artificial Intelligence
  • S S R Rizvi +3
  • Conference Article
  • Citations2

Towards Accurate and Efficient Image Quality Assessment with Interest Points

  • Apr 01, 2015
  • Xiang Zhang +3
  • Research Article
  • Citations1

A fully automated, expert-perceptive image quality assessment system for whole-body [18F]FDG PET/CT

  • Apr 18, 2025
  • EJNMMI Research
  • Cong Zhang +9
  • Conference Article
  • Citations57

Prediction of OCR accuracy using simple image features

  • Nov 19, 2002
  • L.R Blando +2
  • Research Article

PENILAIAN KUALITI IMEJ DIGITAL BERDASARKAN KAEDAH CIRI-CIRI SISTEM PENGLIHATAN MANUSIA DAN PRINSIP STRUKTUR IMEJ

  • May 30, 2016
  • Jurnal Teknologi
  • Bahbibi Rahmatullah +1
  • Conference Article

An Image Denoising Algorithm Based On Image Quality Assessment

  • Oct 01, 2020
  • Hainan Zhang +1
  • Conference Article
  • Citations6

Active learning for magnetic resonance image quality assessment

  • Mar 01, 2016
  • Annika Liebgott +4
  • Conference Article

<title>High-volume image quality assessment systems: tuning performance with an interactive data visualization tool</title>

  • Mar 25, 1999
  • Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
  • Patricia A Bresnahan +2
  • Research Article
  • Citations6

Deep Learning-Based Multifunctional End-to-End Model for Optical Character Classification and Denoising

  • Nov 15, 2023
  • Journal of Computational Methods in Engineering Applications
  • Shuguang Xiong +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.