DATA PROCESSING AND ANALYSIS
P. V. Bezmaternykh Text Image Normalization Using Fast Hough Transform
INTELLIGENCE SYSTEMS AND TECHNOLOGIES
MATHEMATICAL MODELLING
MATHEMATICAL FOUNDATIONS OF INFORMATION TECHNOLOGY
P. V. Bezmaternykh Text Image Normalization Using Fast Hough Transform
Abstract. 

The tasks of text image normalization arise simultaneously in several modules of the automatic document image recognition system. The paper presents a solution for two classical tasks of geometric normalization of a digital text image: compensation for the global document skew angle and slant elimination for its textual fragments. For both tasks, which differ in the type of geometric distortions, the solution is based on a single method of image analysis of the fast Hough transform. This method is specified and two algorithms for solving these problems are proposed, and they are tested: for the task of slant normalization – on a variety of both known dataset and on a specially collected and published dataset of Cyrillic fragments KRUS, for the task of document skew normalization – on the popular DISEC dataset. It is shown that a distinctive feature of the proposed method is high speed with the ability to process a large range of angles, and the method itself can be successfully applied in systems for automatic processing of document images.

Keywords: 

image normalization, fast Hough transform, document image analysis.

DOI 10.14357/20718632240401 

EDN VOYYXQ

PP. 3-16.

References

1. Arlazarov V.V., Andreeva E.I., Bulatov K.B., Nikolaev D.P., Petrova O.O., Savelev B.I., Slavin O.A., “Document image analysis and recognition: A survey,” Computer Optics, vol. 46, no 4, pp. 567-589, 2022, DOI: 10.18287/2412-6179-CO-1020.
2. A. V. Brukhtiy and P. A. Kuratov, “The method of a printed string segmentation on a grey image,” Trudy ISA RAN 64(4), 80–83 (2014).
3. Chernov T.S., Ilin D.A., Bezmaternykh P.V., Faradzhev I.A., Karpenko S.M., “Research of Segmentation Methods for Images of Document Textual Blocks Based on the Structural Analysis and Machine Learning,” Vestnik RFFI,  № 4, pp. 55-71, 2016, DOI: 10.22204/2410-4639-2016-092-04-55-71.
4. Chernyshova Y.S., Sheshkus A.V., Arlazarov V.V. Twostep CNN framework for text line recognition in cameracaptured images // IEEE Access. — 2020. — Т. 8. — С. 32587-32600. — DOI: 10.1109/ACCESS.2020.2974051.
5. Brady M.L., Yong W., “Fast parallel discrete approximation algorithms for the Radon transform,” SPAA’92, 91–99, ACM, New York, NY, USA (1992).
6. Nikolaev D. P., Karpenko S. M., Nikolaev I. P., Nikolayev P. P. Hough transform: underestimated tool in the computer vision field // ECMS 2008, 2008, pp. 238-243, DOI:10.7148/2008.
7. Ershov E.I., Terekhin A.P., Karpenko S.M., Nikolaev D.P., “O tochnoy otsenke netochnostey approksimatsii pryamykh v algoritme bystrogo preobrazovaniya khafa,” in Proceeding of the Information Technology and Systems - 2015, 858–868, GSP-4, 127994 (2015).
8. Hull J.J., “Document image skew detection: Survey and annotated bibliography,” DAS 1996, Malvern, PA, USA, October 14-16, 1996, Selected papers., 40–66 (1996).
9. Eynard L., Emptoz H., “Italic or roman: Word style recognition without a priori knowledge for old printed documents.” in ICDAR, 823–827, IEEE Computer Society (2009).
10. Brodic D., Milivojevic Z., “Text skew detection using combined entropy algorithm,” Information Technology And Control 46, 2017.
11. Papandreou A., Gatos B., Perantonis S., Gerardis I., “Efficient skew detection of printed document images based on novel combination of enhanced profiles,” IJDAR 17, 433–454, 2014.
12. Srihari S., Govindaraju V., “Analysis of textual images using the hough transform,” Machine Vision and Applications 2, pp. 141–153, 1989.
13. Boukharouba A., “A new algorithm for skew correction and baseline detection based on the randomized hough transform,” Journal of King Saud University - Computer and Information Sciences 29, 29–38, 2017.
14. Yu B., Jain A., “A robust and fast skew detection algorithm for generic documents,” Pattern Recognition 29, 1599–1629, 1996. 
15. Stahlberg F., Vogel S., “Document skew detection based on hough space derivatives,” in 2015 13th International Conference on Document Analysis and Recognition (ICDAR), IEEE, 2015. 
16. Bozinovic R., Srihari S., “Off-line cursive script word recognition,” IEEE Trans. Pattern Anal. Mach. Intell. 11, pp. 68–83, 1989.
17. Uchida S., Taira E., Sakoe H., “Nonuniform slant correction using dynamic programming,” in ICDAR, 434–438, IEEE Computer Society (2001).
18. Zhang L., Lu Y., Tan C., “Italic font recognition using stroke pattern analysis on wavelet decomposed word images,” in ICPR (4), 835–838, IEEE Computer Society (2004).
19. Fan K., Huang C., “Italic detection and rectification,” J. Inf. Sci. Eng. 23(2), 403–419 (2007).
20. Pastor M., Toselli A., Vidal E., “Projection profile based algorithm for slant removal.,” in ICIAR(2), Lecture Notes in Computer Science 3212, 183–190, Springer (2004). 
21. Stahlberg F., Vogel S., “The QCRI recognition system for handwritten arabic,” 276–286 (2015).
22. Aliev M.A., Kunina I.A., Nikolaev D.P., Polevoy D.V., “On the practical aspects of computing the hough image by the Brady-Yong algorithm,” Informatsionnye protsessy 23(2), 250–273 (2023), 10.53921/18195822_2023_23_2_250.
23. Bocharov D.A., “A linear regression method robust to extreme stationary clutter,” Sensory systems 34(1), 44–56 (2020), 10.31857/S0235009220010059.
24. Papandreou A., Gatos B., Louloudis G., Stamatopoulos N., “ICDAR 2013 document image skew estimation contest (DISEC 2013),” in ICDAR, (2013).
25. Bera S., Chakrabarti A., Lahiri S., Barney Smith E., Sarkar R., “Normalization of unconstrained handwritten words in terms of slope and slant correction,” Pattern Recognition Letters 128, pp. 488–495, 2019.

2024 / 04
2024 / 03
2024 / 02
2024 / 01

© ФИЦ ИУ РАН 2008-2018. Создание сайта "РосИнтернет технологии".