Abstract
The performance of handwriting recognition systems has undergone significant improvement in recent years. However, the accuracy of these systems for multiple cursive scripts, including Arabic and Urdu, is still limited due to the lack of labeled training data. Handwriting generators are a potential solution to this problem. Previous research on Urdu handwriting generation has primarily focused on generating realistic ligatures using Generative Adversarial Networks (GANs) with common adversarial loss but has not addressed the issue of maintaining content and generated image entanglement. This paper aims to address this gap by proposing a content-controlled training approach for Urdu Handwriting Generation with pre-trained recognizer loss. Our generation model is trained on a diverse set of printed ligatures and then fine-tuned with transfer learning on handwritten images. In this paper, a new metric for evaluating the performance of handwriting generation systems is also suggested, which is specifically tailored to the context of handwriting generation tasks. To our knowledge, this is the first Urdu handwriting generation system that is capable of generating content-controlled images.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Naeem, M.F., Awan, A.A., Shafait, F., ul-Hasan, A.: Impact of ligature coverage on training practical urdu OCR systems. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, pp. 131–136, IEEE (2017)
Wali, A., Hussain, S.: Context-sensitive Shape-substitution in Nastaliq writing system: analysis and formulation. In: Sobh, T. (ed.) Innovations and Advanced Techniques in Computer and Information Sciences and Engineering. Springer, Dordrecht (2007). https://doi.org/10.1007/978-1-4020-6268-1_10
Graves, A.: Generating sequences with recurrent neural networks. In: arXiv, preprint arXiv:1308.0850 (2013)
Aksan, E., Pece, F., Hilliges, O.: DeepWriting: making digital ink editable via deep generative modeling. In: Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems, pp. 1–14 (2018)
Alonso, E., Moysset, B., Messina, R.: Adversarial generation of handwritten text images conditioned on sequences. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 481–486, Sydney, Australia, IEEE (2019)
Ji, B., Chen, T.: Generative adversarial network for handwritten text. In: arXiv, preprint arXiv:1907.11845 (2019)
Haines, T.S., Mac Aodha, O., Brostow, G.J.: My text in your handwriting. ACM Trans. Graph. (TOG) 35(3), 1–18 (2016)
Fogel, S., Averbuch-Elor, H., Cohen, S., Mazor, S., Litman, R.: ScrabbleGAN: semi-supervised varying length handwritten text generation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4324–4333 (2020)
Farooqui, F.F., Hassan, M., Younis, M.S., Siddhu, M.K.: Offline handwritten Urdu word spotting using random data generation. IEEE Access 8, 131119–131136 (2020)
Sharif, M., Ul-Hasan, A., Shafait, F.: Urdu handwritten ligature generation using generative adversarial networks (GANs). In: Frontiers in Handwriting Recognition: 18th International Conference, ICFHR 2022, Hyderabad, India, 4–7 December 2022, Proceedings, pp. 421–435, (2022)
El-Korashy, A., Shafait, F.: Search space reduction for holistic ligature recognition in Urdu Nastalique script. In: 12th IAPR International Conference on Document Analysis and Recognition (ICDAR), Washington, DC, USA, pp. 1125–1129 (2013)
Riaz, N., Arbab, H., Maqsood, A., Nasir, K.B., Ul-Hasan, A., Shafait, F.: Conv-transformer architecture for unconstrained off-lineUrdu handwriting recognition. Int. J. Document Anal. Recogn. (IJDAR) 25, 373–384 (2022)
Bin Ahmed, S., Naz, S., Swati, S., Razzak, I., Umar, A.I., Ali Khan, A.: UCOM Offline Dataset-an Urdu handwritten dataset generation. Int. Arab J. Inf. Technol. (IAJIT) 14, 239–245 (2017)
Taylor, O.: PANGO: an open-source unicode text layout engine. In: 25th Internationalization and Unicode Conference, Unicode Consortium, Washington DC, USA (2004)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448–456, Lille, France (2015)
Goodfellow, I., et al.: Generative Adversarial Networks. Commun. ACM 63(11), 139–144 (2020)
Fregier, Y., Gouray, J.-B.: Mind2Mind: transfer learning for GANs. In: Nielsen, F., Barbaresco, F. (eds.) GSI 2021. LNCS, vol. 12829, pp. 851–859. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-80209-7_91
Zia, N.S., Naeem, M.F., Raza, S.M.K., Khan, M.M., Ul-Hasan, A., Shafait, F.: A convolutional recursive deep architecture for unconstrained Urdu handwriting recognition. In: Neural Computing and Applications, pp. 1635–1648 (2022)
Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. In: arXiv, preprint arXiv:1312.6114 (2013)
Davis, B., Tensmeyer, C., Price, B., Wigington, C., Morse, B., Jain, R.: Text and style conditioned GAN for generation of offline handwriting lines. In: arXiv, preprint arXiv:2009.00678 (2020)
Khrulkov, V., Oseledets, I.: Geometry score: a method for comparing generative adversarial networks. In: International Conference on Machine Learning, pp. 2621–2629. Stockholm, Sweden (2018)
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: Advances in Neural Information Processing Systems, 30, California, USA (2017)
Khattak, I.U., Siddiqi, I., Khalid, S., Djeddi, C.: Recognition of Urdu ligatures - a holistic approach. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 71–75, Washington, DC, USA. IEEE (2015)
Image and Text Corpora. https://www.cle.org.pk/clestore/index.htm
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Memon, Z., Ul-Hasan, A., Shafait, F. (2023). Content-Aware Urdu Handwriting Generation. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds) Document Analysis and Recognition - ICDAR 2023. ICDAR 2023. Lecture Notes in Computer Science, vol 14190. Springer, Cham. https://doi.org/10.1007/978-3-031-41685-9_27
Download citation
DOI: https://doi.org/10.1007/978-3-031-41685-9_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-41684-2
Online ISBN: 978-3-031-41685-9
eBook Packages: Computer ScienceComputer Science (R0)