On the Use of Neural Text Generation for the Task of Optical Character Recognition

Mohammadi, Mahnaz, Jaf, Sardar, McGough, Andrew Stephen, Breckon, Toby P., Matthews, Peter, Theodoropoulos, Georgios and Obara, Boguslaw (2019) On the Use of Neural Text Generation for the Task of Optical Character Recognition. In: 16th ACS/IEEE International Conference on Computer Systems and Applications AICCSA 2019, 3-7 Nov. 2019, Abu Dhabi - UAE.

[img]
Preview
PDF
On the Use of Neural Text Generation for the Task.pdf - Accepted Version

Download (145kB) | Preview
[img] PDF (Administrator use only)
On the Use of Neural Text Generation for the Task of Optical Character Recognition.pdf - Published Version
Restricted to Repository staff only

Download (188kB) | Request a copy

Search Google Scholar

Abstract

Optical Character Recognition (OCR), is extraction of textual data from scanned text documents to facilitate
their indexing, searching, editing and to reduce storage space. Although OCR systems have improved significantly in recent years, they still suffer in situations where the OCR output does not match the text in the original document. Deep learning models have contributed positively to many problems but their full potential to many other problems are yet to be explored. In this paper we propose a post-processing approach based on the application deep learning to improve the accuracy of OCR system (minimizing the error rate).We report on the use of neural network language models to accomplish the task of correcting incorrectly predicted characters/words by OCR systems. We applied our approach to the IAM handwriting database. Our proposed approach delivers significant accuracy improvement of 20:41% in F-score, 10:86% in character level comparison using Levenshtein distance and 20:69% in document level comparison over previously reported context based OCR empirical results of IAM handwriting database.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Neural text generation, Optical character recognition, OCR, OCR post-processing, language models, neural language model, text generation, text prediction, IAM database, handwritten character recognition
Subjects: Computing > Data Science
Computing > Artificial Intelligence
Computing > Information Systems
Computing > Programming
Computing > Software Engineering
Divisions: Faculty of Technology > School of Computer Science
Depositing User: Sardar Jaf
Date Deposited: 06 Sep 2019 12:58
Last Modified: 30 Jun 2020 14:23
URI: http://sure.sunderland.ac.uk/id/eprint/11095
ORCID for Sardar Jaf: ORCID iD orcid.org/0000-0002-5620-0277

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year