Text Line Aggregation

Christopher Beck, Alan Broun, Majid Mirmehdi, Tony Pipe, Chris Melhuish

2014

Abstract

We present a new approach to text line aggregation that can work as both a line formation stage for a myriad of text segmentation methods (over all orientations) and as an extra level of filtering to remove false text candidates. The proposed method is centred on the processing of candidate text components based on local and global measures. We use orientation histograms to build an understanding of paragraphs, and filter noise and construct lines based on the discovery of prominent orientations. Paragraphs are then reduced to seed components and lines are reconstructed around these components. We demonstrate results for text aggregation on the ICDAR 2003 Robust Reading Competition data, and also present results on our own more complex data set.

Paper Citation

in Harvard Style

Beck C., Broun A., Mirmehdi M., Pipe T. and Melhuish C. (2014). Text Line Aggregation . In Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-018-5, pages 393-401. DOI: 10.5220/0004817903930401

in Bibtex Style

@conference{icpram14,
author={Christopher Beck and Alan Broun and Majid Mirmehdi and Tony Pipe and Chris Melhuish},
title={Text Line Aggregation},
booktitle={Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2014},
pages={393-401},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004817903930401},
isbn={978-989-758-018-5},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Text Line Aggregation
SN - 978-989-758-018-5
AU - Beck C.
AU - Broun A.
AU - Mirmehdi M.
AU - Pipe T.
AU - Melhuish C.
PY - 2014
SP - 393
EP - 401
DO - 10.5220/0004817903930401