Abstract
This work proposes a practical and powerful segmentation approach that allows touching or overlapping characters in adjacent text lines or words within Arabic manuscripts to be segmented correctly. It is the first deep learning-based method proposed to solve this problem. It is based on a modified U-Net named AR2U-net: an Attention-based Recurrent Residual U-net model trained to separate touching characters. It is trained on the LTP (Local Touching Patches) database to segment touching characters in a pixel-wise classification. The network labels pixels of the touching characters’ images in four classes: pixels of background, pixels of the first character, pixels of the second character, and those where characters touch. Once the segmentation is done, the separation of touching text lines or words can be done efficiently and speedily. We also propose a post-treatment to segment successive touching text lines in this work. Experimental results on the LTP database show that our proposed method is practical in copes with touching and overlapped characters separation. It achieves higher accuracy of 94.6% than those reported in the state-of-the-art.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Alaei, A., Pal, U., Nagabhushan, P.N.: A new scheme for unconstrained handwritten text-line segmentation. Pattern Recogn. 44(04), 917–928 (2011)
Alom, M.Z., Hasan, M., Yakopcic, C., Taha, T., Asari, V.: Recurrent residual convolutional neural network based on U-net (R2U-net) for medical image segmentation (2018)
Aouadi, N., Kacem, A.: A proposal for touching component segmentation in Arabic manuscripts. Pattern Anal. Appl. 20, 1–23 (2017)
Belongie, S.J., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. TPAMI 24(04), 509–522 (2002)
Kang, L., Doermann, D.: Template based segmentation of touching components in handwritten text lines, pp. 569–573 (2011)
Kang, L., Doermann, D.S., Cao, H., Prasad, R., Natarajan, P.: Local segmentation of touching characters using contour based shape decomposition. In: 2012 10th IAPR International Workshop on Document Analysis Systems, pp. 460–464 (2012)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7–9 May 2015, Conference Track Proceedings (2015)
Kumar, J., Abd-Almageed, W., Kang, L., Doermann, D.S.: Handwritten Arabic text line segmentation using affinity propagation. In: DAS 2010, pp. 135–142 (2010)
Kumar, J., Kang, L., Doermann, D., Abd-Almageed, W.: Segmentation of handwritten textlines in presence of touching components. In: 2011 International Conference on Document Analysis and Recognition, pp. 109–113 (2011)
Ling, H., Jacobs, D.W.: Shape classification using the inner-distance. IEEE Trans. Pattern Anal. Mach. Intell. 29(02), 286–299 (2007)
Amiri, S., Aouadi, N., Echi, A.K.: Segmentation of connected components in Arabic handwritten document. In: International Conference on Computational Intelligence: Modeling Techniques and Applications (CIMTA), vol. 10, pp. 738–746 (2013)
Ouwayed, N., Belaïd, A.: Separation of overlapping and touching lines within handwritten Arabic documents. In: Jiang, X., Petkov, N. (eds.) CAIP 2009. LNCS, vol. 5702, pp. 237–244. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-03767-2_29
Piquin, P., Viard-Gaudin, C., Barba, D.: Coopration des outils de segmentation et de binarisation de documents. Olloque National sur l’Ecrit et le Document, pp. 283–292 (1994)
Sun, H., et al.: AUnet: attention-guided dense-upsampling networks for breast mass segmentation in whole mammograms. Phys. Med. Biol. 65, 055005 (2019)
Aïcha, B., Takwa, G., Echi, A.K.: Unconstrained handwritten Arabic text-lines segmentation based on AR2U-net. In: 2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 349–354 (2020)
Ullah, I., Azmi, M.S., Desa, M.I., Alomari, Y.M.: Segmentation of touching Arabic characters in handwritten documents by overlapping set theory and contour tracing. Int. J. Adv. Comput. Sci. Appl. 10(5), 155–160 (2019)
Zahour, A., Taconet, B., Likforman-Sulem, L., Boussellaa, W.: Overlapping and multi-touching text-line segmentation by block covering analysis. Pattern Anal. Appl. 12, 335–351 (2008)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Gader, T.B.A., Echi, A.K. (2022). Deep Learning-Based Segmentation of Connected Components in Arabic Handwritten Documents. In: Bennour, A., Ensari, T., Kessentini, Y., Eom, S. (eds) Intelligent Systems and Pattern Recognition. ISPR 2022. Communications in Computer and Information Science, vol 1589. Springer, Cham. https://doi.org/10.1007/978-3-031-08277-1_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-08277-1_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-08276-4
Online ISBN: 978-3-031-08277-1
eBook Packages: Computer ScienceComputer Science (R0)