Improved document image segmentation algorithm using multiresolution morphology

Syed Saqib Bukhari; Faisal Shafait; Thomas M. Breuel

doi:10.1117/12.873461

Translator Disclaimer

24 January 2011 Improved document image segmentation algorithm using multiresolution morphology

Syed Saqib Bukhari; Faisal Shafait; Thomas M. Breuel

Author Affiliations +

Proceedings Volume 7874, Document Recognition and Retrieval XVIII; 78740D (2011) https://doi.org/10.1117/12.873461
Event: IS&T/SPIE Electronic Imaging, 2011, San Francisco Airport, California, United States

Abstract

Page segmentation into text and non-text elements is an essential preprocessing step before optical character recognition (OCR) operation. In case of poor segmentation, an OCR classification engine produces garbage characters due to the presence of non-text elements. This paper describes modifications to the text/non-text segmentation algorithm presented by Bloomberg,¹ which is also available in his open-source Leptonica library.²The modifications result in significant improvements and achieved better segmentation accuracy than the original algorithm for UW-III, UNLV, ICDAR 2009 page segmentation competition test images and circuit diagram datasets.

Citation Download Citation

Syed Saqib Bukhari, Faisal Shafait, and Thomas M. Breuel "Improved document image segmentation algorithm using multiresolution morphology", Proc. SPIE 7874, Document Recognition and Retrieval XVIII, 78740D (24 January 2011); https://doi.org/10.1117/12.873461