17 March 2017 Slant rectification in Russian passport OCR system using fast Hough transform
Author Affiliations +
Proceedings Volume 10341, Ninth International Conference on Machine Vision (ICMV 2016); 103410P (2017) https://doi.org/10.1117/12.2268725
Event: Ninth International Conference on Machine Vision, 2016, Nice, France
Abstract
In this paper, we introduce slant detection method based on Fast Hough Transform calculation and demonstrate its application in industrial system for Russian passports recognition. About 1.5% of this kind of documents appear to be slant or italic. This fact reduces recognition rate, because Optical Recognition Systems are normally designed to process normal fonts. Our method uses Fast Hough Transform to analyse vertical strokes of characters extracted with the help of x-derivative of a text line image. To improve the quality of detector we also introduce field grouping rules. The resulting algorithm allowed to reach high detection quality. Almost all errors of considered approach happen on passports of nonstandard fonts, while slant detector works in appropriate way.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Elena Limonova, Elena Limonova, Pavel Bezmaternykh, Pavel Bezmaternykh, Dmitry Nikolaev, Dmitry Nikolaev, Vladimir Arlazarov, Vladimir Arlazarov, } "Slant rectification in Russian passport OCR system using fast Hough transform", Proc. SPIE 10341, Ninth International Conference on Machine Vision (ICMV 2016), 103410P (17 March 2017); doi: 10.1117/12.2268725; https://doi.org/10.1117/12.2268725
PROCEEDINGS
5 PAGES


SHARE
RELATED CONTENT

Quality assessment of glass jewelry stones
Proceedings of SPIE (December 01 2017)
Locally adaptive document skew detection
Proceedings of SPIE (April 03 1997)
Extraction of tire size code using local phase
Proceedings of SPIE (November 24 2009)
Fast algorithm for skew detection
Proceedings of SPIE (March 05 1996)

Back to Top