Text extraction method for historical Tibetan document images based on block projections

Abstract

Text extraction is an important initial step in digitizing the historical documents. In this paper, we present a text extraction method for historical Tibetan document images based on block projections. The task of text extraction is considered as text area detection and location problem. The images are divided equally into blocks and the blocks are filtered by the information of the categories of connected components and corner point density. By analyzing the filtered blocks’ projections, the approximate text areas can be located, and the text regions are extracted. Experiments on the dataset of historical Tibetan documents demonstrate the effectiveness of the proposed method.

References

[1] SébastienE., Gomez-KrämerP., OgierJ. M.. Pattern Recognition, 2017, 64: 1

[2] HaD.-T., Duc-DungN., LeD. H.. Pattern Recognition Letters, 2016, 80: 137

[3] YuM.. Computer Engineering and Applications, 2013, 49: 195

[4] XiaoR.. South-Center University for Nationalities, 2011,

[5] BukhariSyed Saqib. 2012 International Conference on Frontiers in Handwriting Recognition, 2012, 639

[6] KavithaA. S.. Egyptian Informatics Journal, 2016, 17: 189

[7] ZengF.. Journal of Software, 2013, 8: 1827

[8] VikasY., RagotN.. 2016 12^th Iapr International Workshop on Document Analysis Systems, 2016, 281

[9] RamelJ. Y.. International Journal on Document Analysis and Recognition, 2007, 9: 243

[10] AmyW., AndersenT., SmithE. H. B.. 2011 International Conference on Document Analysis and Recognition IEEE Computer Society, 2011, 1245

[11] SinghV., KumarB.. 2014 International Conference on Computer Communication and Informatics IEEE, 2014, 1

[12] ChenK.. 2015 13^th International Conference on Document Analysis and Recognition, 2015, 1101

[13] ChenK.. 2016 12^th Iapr Workshop on Document Analysis Systems IEEE Computer Society, 2016, 299