TU Darmstadt / ULB / TUbiblio

Issue Based OCR Error Prediction in Video Streams

Siegmund, Dirk and Sacco, Luís Rüger and Kuijper, Arjan (2020):
Issue Based OCR Error Prediction in Video Streams.
In: Proceedings of the Signal Processing Conference: Algorithms, Architectures, Arrangements, and Applications (SPA 2020), pp. 75-80,
IEEE, virtual Conference, 23.-25.09., ISBN 9781728177465,
DOI: 10.23919/SPA50552.2020.9241245,
[Conference or Workshop Item]

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.

Item Type: Conference or Workshop Item
Erschienen: 2020
Creators: Siegmund, Dirk and Sacco, Luís Rüger and Kuijper, Arjan
Title: Issue Based OCR Error Prediction in Video Streams
Language: English
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.

Title of Book: Proceedings of the Signal Processing Conference: Algorithms, Architectures, Arrangements, and Applications (SPA 2020)
Publisher: IEEE
ISBN: 9781728177465
Uncontrolled Keywords: Video analysis, Image quality, Machine learning
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Interactive Graphics Systems
20 Department of Computer Science > Mathematical and Applied Visual Computing
Event Location: virtual Conference
Event Dates: 23.-25.09.
Date Deposited: 02 Dec 2020 12:28
DOI: 10.23919/SPA50552.2020.9241245
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details