Mathematical problem of straightening text lines

• Autorzy: Tymchenko O. , Kulczycka I. , Szturo K.
• Języki publikacji: EN

Abstrakty

EN

The rapid distribution of digital cameras has caused several new problems related to text recognition. Based on experimental studies, was revealed that existing OCR systems cannot cope with complex perspective and geometric distortions that arise when photographing text document. Therefore it is necessary to apply text documents pre-processing so that the text lines were straight and horizontal. This article briefly consider existing methods pre-processing documents and found that it depend on the type of distortion and not universal. Proposed new method involving the mathematical raising of straightened text lines on the image and heterogeneous distortion correction based on a page surface transformation model. This method is better than others because it is universal and corrects any type of distortion, including a combination of several types of distortion.

Słowa kluczowe

EN

recognition; optical recognition system; text document image; image distortions

• Wydawca: Wydawnictwo Uniwersytetu Warmińsko-Mazurskiego w Olsztynie
• Czasopismo: Technical Sciences / University of Warmia and Mazury in Olsztyn
• Rocznik: 2015
• Tom: nr 18(4)
• Strony: 313--321
• Opis fizyczny: Bibliogr. 8 poz., rys.

Twórcy

autor

Tymchenko O.

• Department of Safety Engineering, University of Warmia and Mazury

autor

Kulczycka I.

• Ukrainian Academy of Printing, Lviv

autor

Szturo K.

• Department of Safety Engineering, University of Warmia and Mazury

Bibliografia

• ARMS W. 2000. Digital Libraries. M.I.T. Press. On line: http://www.cs.cornell.edu/wya/diglib/ (access: October 2014).
• FU B., WU M., LI R., LI W., XU Z., YANG CH., 2007. A model based book dewarping method using text line detection. Proceedings of the Second International Workshop on Camera-Based Document Analysis and Recognition (CBDAR-2007), Curitiba, pp. 63-70. On line: http://imlab.jp/cbdar2007/proceedings/papers/P1.pdf (access: October 2014).
• JÄHNE B. Digital image processing. 2002. Springer, Berlin, p. 29. On line: http://cgrava.webhost.uoradea.ro/teaching/PAI/documentatie/Jahne-Digital-Image-Processing.pdf (access: October 2014).
• MARTI U.V. 2001. Using a statistical language model to improve the performance of an HMM-based cursive handwriting recognition system. Int. Journal of Pattern Recognition and Artifical Intelligence, 15(1): 65-90.
• MASALOVICH A.A. 2007. Use of patch Bez;e for approximation of distortion of text documents. In: // Labours 17 International Conference on Computer Graphics and Sight. Ed. A.A.Masalovich, L.M. Mesteckiy. Grafikon, Moscow. On line: http://www.machinelearning.ru/wiki/images/a/a2/ Gr-2007-Masalovich.pdf (access: October 2014).
• OCR Software Review. On line: http://ocr-software-review.toptenreviews.com (access: October 2014).
• PRATT W. 2007. Digital image processing. Fourth edition. PixelSoft, Inc. Los Altos, California. A Wiley-Interscience Publication, pp. 91-99. On line: https://docs.google.com/file/d/0B30qTepNcnnAOGhlOUQ4Z1o1Sm8/edit (access: October 2014).
• YIN X.-C., SUN J., NAOI S. 2007. Perspective rectification for mobile phone camera-based documents using a hybrid approach to vanishing point detection. Proceedings of the Second International Workshop on Camera-Based Document Analysis and Recognition (CBDAR-2007), Curitiba, pp. 37-44.