Abstract.

This paper presents text fields extraction algorithm for Russian citizen passport. The algorithm is based on image processing, such as morphology, and template matching. The experimental results on the dataset, contains a large number of images from video streams, scanners and photo cameras, show effectiveness and very good score rate of the proposed algorithm. The method may be generalized on the large set of documents such as ID cards, driving licenses, visas and etc.

Keywords:

text fields extraction, document recognition, video stream, image processing, morphology, Hough transform, template matching

PP. 65-73.

References

1. Polevoy D., Bulatov K., Skorykina N., Chernov T., Arlazarov V., Sheshkus A. «Key Aspects of Document Recognition Using  Small Digital Cameras», Herald of the RFBR, 2016, №4 (92), pp. 97-108.
2. Arlasarov V.V., Zhukovsky A.E., Krivtsov V.E., Nikolaev D.P., Polevoy D.V. « Analysis of features of the use of fixed and  mobile small-sized digital video camera for OCR », Information Technologies and Computing Systems, 2014, №3, pp. 71-81.
3. Junga K., Kimb K.I., Jain A.K., “Text information extraction in images and video: a survey”, Pattern Recognition, 2004, pp.  977-997.
4. Zhukovsky A., Arlazarov V., Postnikov V., Krivtsov V. «Segments Graph-Based Approach for Smartphone Document  Capture» Proceedings SPIE. Eighth International Conference on Machine Vision (ICMV 2015), 2015, V. 9875, 98750P, pp. 1-7.
5. Chernov T. S. «Glare detection and filtering in document recognition tasks on mobile devices», ISA RAS proceedings, 2017,  Vol. 67, № 1, pp. 67-74.
6. Wu J.C., Hsieh J.W., Chen Y.S., “Morphologybased text line extraction”, Machine Vision and Applications, 2008, pp. 195-207.
7. Rodolfo P. dos Santos, Gabriela S. Clemente, Tsang Ing Ren, George D.C. Calvalcanti, “Text Line Segmentation Based on  Morphology and Histogram Projection”, Proceedings of ICDAR ‘09, 2009, pp. 651-655.
8. M. van Herk. “A Fast Algorithm for Local Minimum and Maximum Filters on Rectangular and Octagonal Kernels”, Pattern  Recognition Letters, 1992, pp. 517-521.
9. Limonova E., Terekhin A., Nikolaev D., Arlazarov V.V. «Fast Implementation of Morphological Filtering Using ARM NEON  Extension», International Journal of Applied Engineering Research, 2016, V. 11, № 24, pp. 11675-11680.
10. Nikolaev D.P., Karpenko S.M., Nikolaev I.P. and Nikolayev P.P., “Hough Transform: Underestimated Tool in the Computer  Vision Field”, Proceedings of ECMS ‘08, 2008, pp. 238-246.
11. Otsu N., «A threshold selection method from graylevel histograms», IEEE Trans. Sys., Man., Cyber. 9, 1979, pp. 62-66.