ICDAR2017 Competition on Recognition of Early Indian Printed Documents – REID2017

Clausner, C, Antonacopoulos, A, Derrick, T and Pletschacher, S 2017, ICDAR2017 Competition on Recognition of Early Indian Printed Documents – REID2017 , in: 14th International Conference on Document Analysis and Recognition, 13-15 November 2017, Kyoto, Japan.

[img]
Preview
PDF - Accepted Version
Download (628kB) | Preview

Abstract

This paper presents an objective comparative evaluation of page analysis and recognition methods for historical documents with text mainly in Bengali language and script. It describes the competition (modus operandi, dataset and evaluation methodology) held in the context of ICDAR2017, presenting the results of the evaluation of seven methods – three submitted and four variations of open source state-of-the-art systems. The focus is on optical character recognition (OCR) performance. Different evaluation metrics were used to gain an insight into the algorithms, including new character accuracy metrics to better reflect the difficult circumstances presented by the documents. The results indicate that deep learning approaches are the most promising, but there is still a considerable need to develop robust methods that deal with challenges of historic material of this nature.

Item Type: Conference or Workshop Item (Paper)
Schools: Schools > School of Computing, Science and Engineering
Journal or Publication Title: Proceedings of the 14th International Conference on Document Analysis and Recognition (ICDAR2017)
Publisher: IEEE
Related URLs:
Depositing User: Mr Christian Clausner
Date Deposited: 20 Nov 2017 14:08
Last Modified: 08 Dec 2017 10:37
URI: http://usir.salford.ac.uk/id/eprint/44370

Actions (login required)

Edit record (repository staff only) Edit record (repository staff only)

Downloads

Downloads per month over past year