Skip to main content
Log in

A two-step framework for text line segmentation in historical Arabic and Latin document images

  • Special Issue Paper
  • Published:
International Journal on Document Analysis and Recognition (IJDAR) Aims and scope Submit manuscript

Abstract

One of the most important preliminary tasks in a transcription system of historical document images is text line segmentation. Nevertheless, this task remains complex due to the idiosyncrasies of ancient document images. In this article, we present a complete framework for text line segmentation in historical Arabic or Latin document images. A two-step procedure is described. First, a deep fully convolutional networks (FCN) architecture has been applied to extract the main area covering the text core. In order to select the highest performing FCN architecture, a thorough performance benchmarking of the most recent and widely used FCN architectures for segmenting text lines in historical Arabic or Latin document images has been conducted. Then, a post-processing step, which is based on topological structure analysis is introduced to extract complete text lines (including the ascender and descender components). This second step aims at refining the obtained FCN results and at providing sufficient information for text recognition. Our experiments have been carried out using a large number of Arabic and Latin document images collected from the Tunisian national archives as well as other benchmark datasets. Quantitative and qualitative assessments are reported in order to firstly pinpoint the strengths and weaknesses of the different FCN architectures and secondly to illustrate the effectiveness of the proposed post-processing method.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

Notes

  1. http://www.archives.nat.tn/.

  2. https://scriptnet.iit.demokritos.gr/competitions/5/.

  3. https://scriptnet.iit.demokritos.gr/competitions/~icdar2017htr/.

  4. https://read.transkribus.eu/.

  5. https://diuf.unifr.ch/main/hisdoc/diva-hisdb.

  6. https://www.primaresearch.org/RASM2018/.

  7. https://www.primaresearch.org/tools.

References

  1. Elhedda, W., Mehri, M., Mahjoub, M.A.: A comparative study of filtering approaches applied to color archival document images, arXiv preprint arXiv:1908.09007 (2019)

  2. Mechi, O., Mehri, M., Ingold, R., Amara, N.E.B.: A text line extraction method for archival document transcription. In: International Multi-conference on Systems, Signals and Devices, pp. 479–484 (2020)

  3. Jemni, S.K., Kessentini, Y., Kanoun, S.: Out of vocabulary word detection and recovery in Arabic handwritten text recognition. Pattern Recognit. 93, 507–520 (2019)

    Article  Google Scholar 

  4. Dutta, K., Krishnan, P., Mathew, M., Jawahar, C.V.: Offline handwriting recognition on Devanagari using a new benchmark dataset. In: International Workshop on Document Analysis Systems, pp. 25–30 (2018)

  5. Cai, J., Peng, L., Tang, Y., Liu, C., Li, P.: TH-GAN: generative adversarial network based transfer learning for historical Chinese character recognition. In: International Conference on Document Analysis and Recognition, pp. 178–183 (2019)

  6. Grüning, T., Leifert, G., Strauß, T., Labahn, R.: A robust and binarization free approach for text line detection in historical documents. In: International Conference on Document Analysis and Recognition, vol. 1, pp. 236–241 (2017)

  7. Kundu, S., Paul, S., Bera, S.K., Abraham, A., Sarkar, R.: Text-line extraction from handwritten document images using GAN. Expert Syst. Appl. 140, 112916 (2020)

    Article  Google Scholar 

  8. Garz, A., Fischer, A., Sablatnig, R., Bunke, H.: Binarization-free text line segmentation for historical documents based on interest point clustering. In: International Workshop on Document Analysis Systems, pp. 95–99 (2012)

  9. Saabni, R., Asi, A., El-Sana, J.: Text line extraction for historical document images. Pattern Recognit. Lett. 35, 23–33 (2014)

    Article  Google Scholar 

  10. Vo, Q.N., Lee, G.: Dense prediction for text line segmentation in handwritten document images. In: International Conference on Image Processing, pp. 3264–3268 (2016)

  11. Dutta, K., Krishnan, P., Mathew, M., Jawahar, C.: Towards spotting and recognition of handwritten words in Indic scripts. In: International Conference on Frontiers in Handwriting Recognition, pp. 32–37 (2018)

  12. Mandal, S., Choudhury, H., Prasanna, S.M., Sundaram, S.: DNN-HMM based large vocabulary online handwritten Assamese word recognition system. In: International Conference on Frontiers in Handwriting Recognition, pp. 321–326 (2018)

  13. Murdock, M., Reid, S., Hamilton, B., Reese, J.: ICDAR 2015 competition on text line detection in historical documents. In: International Conference on Document Analysis and Recognition, pp. 1171–1175 (2015)

  14. Levi, G., Hassner, T.: Age and gender classification using convolutional neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 34–42 (2015)

  15. LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436–444 (2015)

    Article  Google Scholar 

  16. Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)

  17. Esteva, A., Kuprel, B., Novoa, R.A., Ko, J., Swetter, S.M., Blau, H.M., Thrun, S.: Dermatologist-level classification of skin cancer with deep neural networks. Nature 542, 115–118 (2017)

    Article  Google Scholar 

  18. Ammour, N., Alhichri, H., Bazi, Y., Benjdira, B., Alajlan, N., Zuair, M.: Deep learning approach for car detection in UAV imagery. Remote Sens. 9, 312 (2017)

    Article  Google Scholar 

  19. Vincent, N., Ogier, J.M.: Shall deep learning be the mandatory future of document analysis problems? Pattern Recognit. 86, 281–289 (2019)

    Article  Google Scholar 

  20. Pastor-Pellicer, J., Afzal, M.Z., Liwicki, M., Castro-Bleda, M.J.: Complete system for text line extraction using convolutional neural networks and watershed transform. In: International Workshop on Document Analysis Systems, pp. 30–35 (2016)

  21. Grüning, T., Leifert, G., Strauß, T., Michael, J., Labahn, R.: A two-stage method for text line detection in historical documents. Int. J. Doc. Anal. Recognit. 22, 285–302 (2019)

    Article  Google Scholar 

  22. Neche, C., Belaid, A., Kacem-Echi, A.: Arabic handwritten documents segmentation into text-lines and words using deep learning. In: International Conference on Document Analysis and Recognition Workshops, vol. 6, pp. 19–24 (2019)

  23. Renton, G., Chatelain, C., Adam, S., Kermorvant, C., Paquet, T.: Handwritten text line segmentation using fully convolutional network. In: International Conference on Document Analysis and Recognition, pp. 5–9 (2017)

  24. Diem, M., Kleber, F., Fiel, S., Grüning, T., Gatos, B.: cBAD: ICDAR 2017 competition on baseline detection. In: International Conference on Document Analysis and Recognition, pp. 1355–1360 (2017)

  25. Moysset, B., Kermorvant, C., Wolf, C., Louradour, J.: Paragraph text segmentation into lines with recurrent neural networks. In: International Conference on Document Analysis and Recognition, pp. 456–460 (2015)

  26. Simistira, F., Seuret, M., Eichenberger, N., Garz, A., Liwicki, M., Ingold, R.: Diva-hisdb: a precisely annotated large dataset of challenging Medieval manuscripts. In: International Conference on Frontiers in Handwriting Recognition, pp. 471–476 (2016)

  27. Strauß, T., Leifert, G., Labahn, R., Hodel, T., Mühlberger, G.: ICFHR 2018 competition on automated text recognition on a READ dataset. In: International Conference on Frontiers in Handwriting Recognition, pp. 477–482 (2018)

  28. Zhang, X., Tan, C.L.: Text line segmentation for handwritten documents using constrained seam carving. In: International Conference on Frontiers in Handwriting Recognition, pp. 98–103 (2014)

  29. Shi, Z., Setlur, S., Govindaraju, V.: A steerable directional local profile technique for extraction of handwritten Arabic text lines. In: International Conference on Document Analysis and Recognition, pp. 176–180 (2009)

  30. Alaei, A., Pal, U., Nagabhushan, P.: A new scheme for unconstrained handwritten text-line segmentation. Pattern Recognit. 44, 917–928 (2011)

    Article  Google Scholar 

  31. Louloudis, G., Gatos, B., Halatsis, C.: Text line detection in unconstrained handwritten documents using a block-based Hough transform approach. In: International Conference on Document Analysis and Recognition, pp. 599–603 (2007)

  32. Ryu, J., Koo, H.I., Cho, N.I.: Language-independent text-line extraction algorithm for handwritten documents. IEEE Signal Process. Lett. 21, 1115–1119 (2014)

    Article  Google Scholar 

  33. Kiumarsi, E., Alaei, A.: A hybrid method for text line extraction in handwritten document images. In: International Conference on Frontiers in Handwriting Recognition, pp. 241–246 (2018)

  34. Likforman-Sulem, L., Hanimyan, A., Faure, C.: A Hough-based algorithm for extracting text lines in handwritten documents. In: International Conference on Document Analysis and Recognition, pp. 774–777 (1995)

  35. Oliveira, S.A., Seguin, B., Kaplan, F.: dhSegment: a generic deep-learning approach for document segmentation. In: International Conference on Frontiers in Handwriting Recognition, pp. 7–12 (2018)

  36. Barakat, B., Droby, A., Kassis, M., El-Sana, J.: Text line segmentation for challenging handwritten document images using fully convolutional network. In: International Conference on Frontiers in Handwriting Recognition, pp. 374–379 (2018)

  37. Mechi, O., Mehri, M., Ingold, R., Amara, N.E.B.: Text line segmentation in historical document images using an adaptive U-Net architecture. In: International Conference on Document Analysis and Recognition, pp. 369–374 (2019)

  38. Barakat, B.K., Droby, A., Alasam, R., Madi, B., Rabaev, I., Shammes, R., El-Sana, J.: Unsupervised text line segmentation, arXiv preprint arXiv:2003.08632 (2020)

  39. Vo, Q.N., Kim, S.H., Yang, H.J., Lee, G.S.: Text line segmentation using a fully convolutional network in handwritten document images. IET Image Process. 12, 438–446 (2017)

    Article  Google Scholar 

  40. Kiessling, B., Ezra, D.S.B., Miller, M.T.: BADAM: a public dataset for baseline detection in Arabic-script manuscripts. In: International Workshop on Historical Document Imaging and Processing, pp. 13–18 (2019)

  41. Alberti, M., Vögtlin, L., Pondenkandath, V., Seuret, M., Ingold, R., Liwicki, M.: Labeling, cutting, grouping: an efficient text line segmentation method for Medieval manuscripts. In: International Conference on Document Analysis and Recognition, pp. 1200–1206 (2019)

  42. Zayene, O., Essefi Amamou, S., Amara, N.E.B.: Arabic video text recognition based on multi-dimensional recurrent neural networks. In: International Conference on Computer Systems and Applications, pp. 725–729 (2017)

  43. Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 234–241 (2015)

  44. Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9, 62–66 (1979)

    Article  Google Scholar 

  45. Mehri, M., Gomez-Krämer, P., Héroux, P., Boucher, A., Mullot, R.: A texture-based pixel labeling approach for historical books. Pattern Anal. Appl. 20(2), 325–364 (2015)

  46. Mehri, M., Héroux, P., Sliti, N., Gomez-Krämer, P., Amara, N.E.B., Mullot, R.: Extraction of homogeneous regions in historical document images. In: International Conference on Computer Vision Theory and Applications, pp. 47–54 (2015)

  47. Clausner, C., Antonacopoulos, A., Mcgregor, N., Wilson-Nunn, D.: ICFHR 2018 competition on recognition of historical Arabic scientific manuscripts—RASM2018. In: International Conference on Frontiers in Handwriting Recognition, pp. 471–476 (2018)

  48. Pletschacher, S., Antonacopoulos, A.: The PAGE (page analysis and ground truth elements) format framework. In: International Conference on Pattern Recognition, pp. 257–260 (2010)

  49. Galibert, O., Kahn, J., Oparin, I.: The zonemap metric for page segmentation and area classification in scanned documents. In: International Conference on Image Processing, pp. 2594–2598 (2014)

Download references

Acknowledgements

This work has been funded under the “19PEJC-08-02” Grant agreement number by the Tunisian Ministry of Higher Education and Scientific Research that is gratefully acknowledged. The authors would like also to thank the Tunisian national archives for providing access to their digital collections.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Olfa Mechi.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Appendix

Appendix

See Table 7.

Table 7 Description of the four evaluated network architectures in our work

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Mechi, O., Mehri, M., Ingold, R. et al. A two-step framework for text line segmentation in historical Arabic and Latin document images. IJDAR 24, 197–218 (2021). https://doi.org/10.1007/s10032-021-00377-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10032-021-00377-1

Keywords

Navigation