Line segmentation of handwritten text using histograms and tensor voting

• Autorzy: Babczyński Tomasz , Ptak Roman

Identyfikatory

DOI

10.34768/amcs-2020-0043

• Języki publikacji: EN

Abstrakty

EN

There are a large number of historical documents in libraries and other archives throughout the world. Most of them are written by hand. In many cases they exist in only one specimen and are hard to reach. Digitization of such artifacts can make them available to the community. But even digitized, they remain unsearchable, and an important task is to draw the contents in the computer readable form. One of the first steps in this direction is to recognize where the lines of the text are. Computational intelligence algorithms can be used to solve this problem. In the present paper, two groups of algorithms, namely, projection-based and tensor voting-based, are compared. The performance is evaluated on a data set and with the procedure proposed by the organizers of the ICDAR 2009 competition.

Słowa kluczowe

EN

document image processing; handwritten text; text line segmentation; projection profile; text string; offline cursive script recognition; ICDAR 2009 competition

PL

przetwarzanie obrazu dokumentu; tekst odręczny; segmentacja linii tekstu; profil projekcyjny; ciąg tekstowy

• Wydawca: Oficyna Wydawnicza Uniwersytetu Zielonogórskiego
• Czasopismo: International Journal of Applied Mathematics and Computer Science
• Rocznik: 2020
• Tom: Vol. 30, no. 3
• Strony: 585--596
• Opis fizyczny: Bibliogr. 38 poz., rys., tab.

Twórcy

autor

Babczyński Tomasz

• Department of Computer Engineering, Wrocław University of Science and Technology, Wybrzeże Wyspiańskiego 27, 50-370 Wrocław, Poland

autor

Ptak Roman

• Department of Computer Engineering, Wrocław University of Science and Technology, Wybrzeże Wyspiańskiego 27, 50-370 Wrocław, Poland

Bibliografia

• [1] Alaei, A., Nagabhushan, P. and Pal, U. (2011). Piece-wise painting technique for line segmentation of unconstrained handwritten text: A specific study with Persian text documents, Pattern Analysis and Applications 14(4): 381–394.
• [2] Arivazhagan, M., Srinivasan, H. and Srihari, S. (2007). A statistical approach to line segmentation in handwritten documents, Document Recognition and Retrieval XIV 65000: 245–255.
• [3] Basu, S., Chaudhuri, C., Kundu, M., Nasipuri, M. and Basu, D.K. (2007). Text line extraction from multi-skewed handwritten documents, Pattern Recognition 40(6): 1825–1839.
• [4] Boykov, Y. and Kolmogorov, V. (2004). An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision, IEEE Transactions on Pattern Analysis and Machine Intelligence 26(9): 1124–1137.
• [5] Brodić, D. (2012). Extended approach to water flow algorithm for text line segmentation, Journal of Computer Science and Technology 27(1): 187–194.
• [6] Brodić, D. (2015). Text line segmentation with water flow algorithm based on power function, Journal of Electrical Engineering 66(3): 132–141.
• [7] Brodić, D. and Milivojević, Z. (2011). A new approach to water flow algorithm for text line segmentation, Journal of Universal Computer Science 17(1): 30–47.
• [8] Eskenazi, S., Gomez-Krämer, P. and Ogier, J.-M. (2017). A comprehensive survey of mostly textual document segmentation algorithms since 2008, Pattern Recognition 64: 1–14.
• [9] Feldbach, M. and Tönnies, K. (2001). Robust line detection in historical church registers, 23rd DAGM Symposium on Pattern Recognition, Munich, Germany, pp. 140–147.
• [10] Franken, E., van Almsick, M., Rongen, P., Florack, L. and ter Haar Romeny, B. (2006). An efficient method for tensor voting using steerable filters, European Conference on Computer Vision, Graz, Austria, pp. 228–240.
• [11] Gatos, B., Stamatopoulos, N. and Louloudis, G. (2011). ICDAR 2009 handwriting segmentation contest, International Journal on Document Analysis and Recognition 14(1): 25–33.
• [12] Han, S., Lee, M.-S. and Medioni, G. (1997). Non-uniform skew estimation by tensor voting, Workshop on Document Image Analysis (DIA’97), San Juan, Puerto Rico, pp. 1–4.
• [13] Kennard, D.J. and Barrett, W.A. (2006). Separating lines of text in free-form handwritten historical documents, 2nd International Conference on Document Image Analysis for Libraries (DIAL’06), Lyon, France, pp. 12–23.
• [14] LeBourgeois, F. (1997). Robust multifont OCR system from gray level images, Proceedings of the 4th International Conference on Document Analysis and Recognition, Ulm, Germany, Vol. 1, pp. 1–5.
• [15] Lee, M.-S. and Medioni, G. (1997). Inferred descriptions in terms of curves, regions and junctions from sparse, noisy binary data, 3rd International Workshop on Visual Form, Capri, Italy, pp. 350–367.
• [16] Li, Y., Zheng, Y., Doermann, D. and Jaeger, S. (2008). Script-independent text line segmentation in freestyle handwritten documents, Pattern Analysis and Machine Intelligence, IEEE Transactions on 30(8): 1313–1329.
• [17] Likforman-Sulem, L., Hanimyan, A. and Faure, C. (1995). A hough based algorithm for extracting text lines in handwritten documents, Proceedings of the 3rd International Conference on Document Analysis and Recognition, Montreal, Quebec, Canada, Vol. 2, pp. 774–777.
• [18] Likforman-Sulem, L., Zahour, A. and Taconet, B. (2007). Text line segmentation of historical documents: A survey, International Journal of Document Analysis and Recognition 9(2): 123–138.
• [19] Louloudis, G., Gatos, B., Pratikakis, I. and Halatsis, C. (2008). Text line detection in handwritten documents, Pattern Recognition 41(12): 3758–3772.
• [20] Louloudis, G., Gatos, B., Pratikakis, I. and Halatsis, C. (2009). Text line and word segmentation of handwritten documents, Pattern Recognition 42(12): 3169–3183.
• [21] Maggiori, E., Manterola, H.L. and del Fresno, M. (2014). Perceptual grouping by tensor voting: A comparative survey of recent approaches, IET Computer Vision 9(2): 259–277.
• [22] Medioni, G. and Kang, S.B. (2004). Emerging Topics in Computer Vision, Prentice Hall, Upper Saddle River, NJ.
• [23] Mordohai, P. and Medioni, G. (2006). Tensor voting: A perceptual organization approach to computer vision and machine learning, Synthesis Lectures on Image, Video, and Multimedia Processing 2(1): 1–136.
• [24] Naz, S. (2015). Segmentation techniques for recognition of Arabic-like scripts: A comprehensive survey, Springer Journal of Education and Information Technologies 21(5): 1225–1241.
• [25] Nguyen Dinh, T. and Lee, G.S. (2011). Text line segmentation in handwritten document images using tensor voting, IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E94.A(11): 2434–2441.
• [26] Nguyen Dinh, T., Park, J.-H. and Lee, G.-S. (2010). Voting based text line segmentation in handwritten document images, 10th IEEE International Conference on Computer and Information Technology, Bradford, UK, pp. 529–535.
• [27] Pach, J.L. and Bilski, P. (2014). Robust method for the text line detection and splitting of overlapping text in the Latin manuscripts, Machine Graphics and Vision 23(3–4): 11–22.
• [28] Papavassiliou, V., Katsouros, V. and Carayannis, G. (2010). A morphological approach for text-line segmentation in handwritten documents, 2010 International Conference on Frontiers in Handwriting Recognition (ICFHR), Kolkata, India, pp. 19–24.
• [29] Phillips, I.T. and Chhabra, A.K. (1999). Empirical performance evaluation of graphics recognition systems, IEEE Transactions on Pattern Analysis and Machine Intelligence 21(9): 849–870.
• [30] Ptak, R., Żygadło, B. and Unold, O. (2017). Projection-based text line segmentation with a variable threshold, International Journal of Applied Mathematics and Computer Science 27(1): 195–206, DOI: 10.1515/amcs-2017-0014.
• [31] Pu, Y. and Shi, Z. (1999). A natural learning algorithm based on hough transform for text lines extraction in handwritten documents, Advances in Handwriting Recognition 34: 141–150.
• [32] Razak, Z., Zulkiflee, K., Idris, M.Y.I., Tamil, E.M., Noorzaily, M., Noor, M., Salleh, R., Yaakob, M., Yusof, Z.M. and Yaacob, M. (2008). Off-line handwriting text line segmentation: A review, International Journal of Computer Science and Network Security 8(7): 12–20.
• [33] Sarkar, R., Malakar, S., Das, N., Basu, S., Kundu, M. and Nasipuri, M. (2011). Word extraction and character segmentation from text lines of unconstrained handwritten Bangla document images, Journal of Intelligent Systems 20(3): 227–260.
• [34] Vo, Q.N., Kim, S.H., Yang, H.J. and Lee, G.S. (2018). Text line segmentation using a fully convolutional network in handwritten document images, IET Image Processing 12(3): 438–446.
• [35] Wong, K.Y., Casey, R.G. and Wahl, F.M. (1982). Document analysis system, IBM Journal of Research and Development 26(6): 647–656.
• [36] Wu, J.-C., Hsieh, J.-W. and Chen, Y.-S. (2008). Morphology-based text line extraction, Machine Vision and Applications 19(3): 195–207.
• [37] Wu, T.-P., Yeung, S.-K., Jia, J., Tang, C.-K. and Medioni, G. (2012). A closed-form solution to tensor voting: Theory and applications, IEEE Transactions on Pattern Analysis and Machine Intelligence 34(8): 1482–1495.
• [38] Zhang, C. and Lee, G.S. (2011). Text line segmentation in Chinese handwritten text images, 17th Korea–Japan Joint Workshop on Frontiers of Computer Vision (FCV), Ulsan, South Korea, pp. 253–255.

Uwagi

PL

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).