Fully convolutional network with dilated convolutions for handwritten text line segmentation


We present a learning-based method for handwritten text line segmentation in document images. Our approach relies on a variant of deep fully convolutional networks (FCNs) with dilated convolutions. Dilated convolutions allow to never reduce the input resolution and produce a pixel-level labeling. The FCN is trained to identify X-height labeling as text line representation, which has many advantages for text recognition. We show that our approach outperforms the most popular variants of FCN, based on deconvolution or unpooling layers, on a public dataset. We also provide results investigating various settings, and we conclude with a comparison of our model with recent approaches defined as part of the cBAD (https://scriptnet.iit.demokritos.gr/competitions/5/) international competition, leading us to a 91.3% F-measure.

This is a preview of subscription content, access via your institution.

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


  1. 1.

    Please note that a preliminary work has been presented at the ICDAR-WML workshop [25].

  2. 2.


  3. 3.



  1. 1.

    Badrinarayanan, V., Kendall, A., Cipolla, R.: Segnet: A deep convolutional encoder–decoder architecture for image segmentation (2015). arXiv:1511.00561

  2. 2.

    Chen, L., Papandreou, V., Kokkinos, I., Murphy, K., Yuille, A.: Semantic image segmentation with deep convolutional nets and fully connected crfs (2014). arXiv:1412.7062

  3. 3.

    Chen, LC., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs (2016). arXiv:1606.00915

  4. 4.

    Chen, LC., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation (2017). arXiv:1706.05587

  5. 5.

    Eskenazi, S., Gomez-Krämer, P., Ogier, J.M.: A comprehensive survey of mostly textual document segmentation algorithms since 2008. Pattern Recognit. 64, 1–14 (2017)

    Article  Google Scholar 

  6. 6.

    Girshick, R.: Fast r-cnn. In: ICCV, pp. 1440–1448 (2015)

  7. 7.

    Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR, pp. 580–587 (2014)

  8. 8.

    Grüning, T., Labahn, R., Diem, M., Kleber, F., Fiel, S.: Read-bad: a new dataset and evaluation scheme for baseline detection in archival documents (2017). arXiv:1705.03311

  9. 9.

    Holschneider, M., Kronland-Martinet, R., Morlet, J., Tchamitchian, P.: A real-time algorithm for signal analysis with the help of the wavelet transform. In: Wavelets, pp. 286–297. Springer (1989)

  10. 10.

    Huang, W., Qiao, Y., Tang, X.: Robust scene text detection with convolution neural network induced mser trees. In: ECCV, pp. 497–511 (2014)

  11. 11.

    Krähenbühl, P.: Koltun, V.: Efficient inference in fully connected CRFs with gaussian edge potentials. In: NIPS, pp. 109–117 (2011)

  12. 12.

    LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)

    Article  Google Scholar 

  13. 13.

    Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C., Berg, A.: Ssd: Single shot multibox detector. In: ECCV, pp. 21–37. Springer (2016)

  14. 14.

    Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431–3440 (2015)

  15. 15.

    Moysset, B., Adam, P., Wolf, C., Louradour, J.: Space displacement localization neural networks to locate origin points of handwritten text lines in historical documents. In: Workshop on Historical Document Imaging and Processing, August (2015)

  16. 16.

    Moysset, B., Kermorvant, C., Wolf, C.: Full-page text recognition: learning where to start and when to stop. In: ICDAR (2017)

  17. 17.

    Moysset, B., Kermorvant, C., Wolf, C., Louradour, J.: Paragraph text segmentation into lines with recurrent neural networks. In: ICDAR, pp. 456–460 (2015)

  18. 18.

    Moysset, B., Louradour, J., Kermorvant, C., Wolf, C.: Learning text-line localization with shared and local regression neural networks. In: ICFHR (2016)

  19. 19.

    Murdock, M., Reid, S., Hamilton, B., Reese, J.: Icdar 2015 competition on text line detection in historical documents. In: ICDAR, pp, 1171–1175 (2015)

  20. 20.

    Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation. In: ICCV, pp. 1520–1528 (2015)

  21. 21.

    Paquet, T., Heutte, L., Koch, G., Chatelain, C.: A categorization system for handwritten documents. IJDAR 15(4), 315–330 (2012)

    Article  Google Scholar 

  22. 22.

    Parvez, M.T., Mahmoud, S.A.: Offline arabic handwritten text recognition: a survey. ACM Comput. Surv. (CSUR) 45(2), 23 (2013)

    Article  MATH  Google Scholar 

  23. 23.

    Peng, C., Zhang, X., Yu, G., Luo, G., Sun, J.: Large kernel matters—improve semantic segmentation by global convolutional network (2017). arXiv:1703.02719

  24. 24.

    Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. CoRR, abs/1612.08242 (2016)

  25. 25.

    Renton, G., Chatelain, C., Adam, S., Kermorvant, C., Paquet, T.: Handwritten text line segmentation using fully convolutional network. In 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), 2017, vol. 5, pp. 5–9. IEEE (2017)

  26. 26.

    Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. CoRR, abs/1505.04597 (2015)

  27. 27.

    Ryu, J., Koo, H.I., Cho, N.I.: Language-independent text-line extraction algorithm for handwritten documents. Signal Process. Lett. 21(9), 1115–1119 (2014)

    Article  Google Scholar 

  28. 28.

    Shi, Z., Setlur, S., Govindaraju, V.: A steerable directional local profile technique for extraction of handwritten arabic text lines. In: ICDAR, pp. 176–180 (2009)

  29. 29.

    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR, abs/1409.1556 (2014)

  30. 30.

    Stamatopoulos, N., Gatos, B., Louloudis, G., Pal, U., Alaei, A.: Icdar 2013 handwriting segmentation contest. In: ICDAR, pp. 1402–1406 (2013)

  31. 31.

    Stuner, B., Chatelain, C., Paquet, T.: LV-ROVER: lexicon verified recognizer output voting error reduction. CoRR, abs/1707.07432 (2017)

  32. 32.

    Vo, Q.N., Lee, G.: Dense prediction for text line segmentation in handwritten document images. In: ICIP, pp. 3264–3268 (2016)

  33. 33.

    Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions (2015). arXiv:1511.07122

  34. 34.

    Zhang, Z., Zhang, C., Shen, W., Yao, C., Liu, W., Bai, X.: Multi-oriented text detection with fully convolutional networks (2016). arXiv:1604.04018

  35. 35.

    Zheng, S., Jayasumana, S., Romera-Paredes, B., Vineet, V., Su, Z., Du, D., Huang, C., Torr, P.: Conditional random fields as recurrent neural networks. In: ICCV, pp. 1529–1537 (2015)

  36. 36.

    Zhu, S., Zanibbi, R.: A text detection system for natural scenes with convolutional feature learning and cascaded classification. In: CVPR, pp. 625–632 (2016)

Download references

Author information



Corresponding author

Correspondence to Guillaume Renton.

Additional information

This work has been supported by the French National grant ANR 16-LCV2-0004-01 Labcom INKS. This work is founded by the French region Normandy and the European Union. Europe acts in Normandy with the European Regional Development Fund (ERDF).

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Renton, G., Soullard, Y., Chatelain, C. et al. Fully convolutional network with dilated convolutions for handwritten text line segmentation. IJDAR 21, 177–186 (2018). https://doi.org/10.1007/s10032-018-0304-3

Download citation


  • Dilated Convolution
  • Fully Convolutional Network (FCN)
  • Text Line Segmentation
  • Unpooling Layers
  • Scene Text Detection