Abstract
Slant correction is an important part of the normalization task in OCR applications. Due to some special specifications of Farsi and Arabic manuscripts, conventional deslanting methods proposed for other languages do not work properly. In this paper, a fast method is first introduced to estimate the overall tilt of a handwritten word based on directional filters. After overall deslanting, a novel non-uniform slant estimation algorithm computes the remaining slant of each near-vertical stroke of the word, separately. Each candidate stroke is traced and its slant is calculated. A non-uniform slant correction algorithm is also proposed to reduce the remaining slants of each candidate stroke keeping the distortions of other strokes of the word at a minimum level. Thanks to the special characteristics of Farsi/Arabic scripts, slants are estimated in a specific strip of the written words. A comparison between our approach and three other prevalent methods is drawn. Experiments show that the proposed overall slant estimation method not only represents the least estimation error, but is also the fastest algorithm. The best results are achieved using the proposed overall and non-uniform deslanting methods. It is concluded that successful results can be achieved by considering the special specifications of these two languages.
Similar content being viewed by others
References
Li, Y., Naoi, S., Cheriet, M., Suen, C.Y.: A segmentation method for touching italic characters. In: ICPR04, pp. 594–597 (2004)
Yamaguchi T., Maruyama M., Miyao H., Nakano Y.: Digit recognition in a natural scene with skew and slant normalization. IJDAR 7, 168–177 (2005)
Pan, M., Yan, J., Xiao, Z.: An approach to tilt correction of vehicle license plate. In: International Conference on Mechatronics and Automation, ICMA (2007)
Kimura, F., Miyake, Y., Shridhar, M.: Handwritten ZIP code recognition using lexicon free word recognition algorithm. In: ICDAR, pp. 906–910 (1995)
Kavallieratou E., Fakotakis N., Kokkinakis G.: An unconstrained handwriting recognition system. IJDAR 4, 226–242 (2002)
Kavallieratou E., Fakotakis N., Kokkinakis G.: Slant estimation algorithm for OCR systems. Pattern Recognit. 34, 2515–2522 (2001)
Shridar, M., Kimura, F.: Handwritten address interpretation using word recognition with and without lexicon. In: Proceedings of IEEE International Conference on Systems, Man and Cybernetics, pp. 2341–2346 (1995)
Farooq, F., Govindaraju, V., Perrone, M.: Pre-processing methods for handwritten Arabic documents. In: ICDAR05, pp. 267–271(2005)
Ding, Y., Okada, M., Kimura, F., Miyake, Y.: Application of slant correction to handwritten Japanese address recognition. In: ICDAR01, pp. 670–674 (2001)
Nagabhushan, P., Angadi, S.A., Anami, B.S.: Geometric model and projection based algorithms for tilt correction and extraction of ascenders/descenders for cursive word recognition. In: International Conference on Signal Processing, Communications and Networking, ICSCN, pp. 488–491 (2007)
Nicchiotti, G., Scagliola, C.: Generalised projections: a tool for cursive handwriting normalisation. In: Fifth International Conference on Document Analysis and Recognition ICDAR (1999)
Vinciarelli A., Luettin J.: A new normalization technique for cursive handwritten words. Pattern Recognit. Lett. 22, 1043–1050 (2001)
Kavallieratou, E., Fakotakis, N., Kokkinakis, G.: New algorithms for skewing correction and slant removal on word-level. In: ICECS, pp. 1159–1162 (1999)
Ding, Y., Ohyama, W., Kimura, F., Shridhar, M.: Local slant estimation for handwritten english words. In: Ninth International Workshop on Frontiers in Handwriting Recognition, IWFHR, pp. 328–333 (2004)
Britto, A., de S., Sabourin, R., Lethelier, E., Bortolozzi, F., Suen, C.Y.: Improvement in handwritten numeral string recognition by slant normalization and contextual information. In: Proceedings of the 7th International Workshop on Frontiers of Handwriting Recognition, pp. 323–332 (2000)
Ballesteros J., Travieso C.M., Alonso J.B., Ferrer M.A.: Slant estimation of handwritten characters by means of Zernike moments. Elect. Lett. 41, 1110–1112 (2005)
Bertolami, R., Uchida, S., Zimmermann, M., Bunke, H.: Non-uniform slant correction for handwritten text line recognition. In: ICDAR, pp. 18–22 (2007)
Uchida, S., Taira, E., Sakoe, H.: Nonuniform slant correction using dynamic programming. In: ICDAR, pp. 434–438 (2001)
Sun, C., Si, D.: Skew and slant correction for document images using gradient direction. In: ICDAR, pp. 142–146 (1997)
You D.K., Kim G.H.: An efficient approach for slant correction of handwritten Korean strings based on structural properties. Pattern Recognit. Lett. 24, 2093–2101 (2003)
You, D.K., Kim, G.H.: Slant correction of handwritten strings based on structural properties of Korean characters. In: IWFHR, pp. 467–472 (2002)
Dong, J.X., Dominique, P., Krzyyzak, A., Suen, C.Y.: Cursive word skew/slant corrections based on Radon transform. In: ICDAR, pp. 478–483 (2005)
Ding, Y., Kimura, F., Miyake Y., Shridhar, M.: Accuracy improvement of slant estimation for handwritten words. In: ICPR, pp. 527–530 (2000)
Lorigo L.M., Govindaraju V.: Off-line arabic handwriting recognition: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 28, 712–724 (2006)
Ziaratban, M., Faez, K.: A novel two-stage algorithm for baseline estimation and correction in Farsi and Arabic handwritten text lines. In: International Conference on Pattern Recognition, pp. 1–15 (2008)
Pechwitz, M., Maddouri, S.S., Maergner, V., Ellouze, N., Amiri, H.: IFN/ENIT—database of handwritten Arabic words. In: CIFED, pp. 129–136 (2002)
Gonzalez R.C., Woods R.E.: Digital Image Processing, 2nd edn. Prentice-Hall, USA (2002)
Broumandnia A., Shanbehzadeh J., Rezakhah Varnoosfaderani M.: Persian/Arabic handwritten word recognition using M-band packet wavelet transform. Image Vision Comput. 26(6), 829–842 (2008)
Krzanowski W.J.: Principles of Multivariate Analysis. Oxford University Press, Oxford (1988)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ziaratban, M., Faez, K. Non-uniform slant estimation and correction for Farsi/Arabic handwritten words. IJDAR 12, 249–267 (2009). https://doi.org/10.1007/s10032-009-0092-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10032-009-0092-x