Text line aggregation

Beck, C., Broun, A., Mirmehdi, M., Pipe, A. G. and Melhuish, C. (2014) Text line aggregation. In: De Marsico, M., Tabbone, A. and Fred, A., eds. (2014) Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods. ESEO, pp. 393-401. ISBN 9789897580185 Available from: http://eprints.uwe.ac.uk/29036

Full text not available from this repository

Publisher's URL: http://dx.doi.org/10.5220/0004817903930401


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.

Item Type:Book Section
Additional Information:Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods, March 6-8 2014, in ESEO, Angers, Loire Valley, France
Uncontrolled Keywords:text aggregation, line construction, text detection
Faculty/Department:Faculty of Environment and Technology
ID Code:29036
Deposited By: B. Jones
Deposited On:06 Jun 2016 13:23
Last Modified:09 Jun 2016 11:31

Request a change to this item