“Unveiling New Artistic Dimensions in Calligraphic Arabic Script with Generative Adversarial Networks” by Sobhan, Pasquier and Tindale
Conference:
Type(s):
Title:
- Unveiling New Artistic Dimensions in Calligraphic Arabic Script with Generative Adversarial Networks
Session/Category Title: Script & Prescribe
Presenter(s)/Author(s):
Abstract:
We present an artistic exploration into calligraphic Arabic script, focusing on the nastaliq style predominant in Iran, by harnessing the affordances of Generative Adversarial Networks (GANs). Recognizing the unique challenges posed by Arabic script’s cursive nature and its inadequate representation by conventional tools, our work seeks to bridge the gap between traditional calligraphy and novel technological capabilities. Two custom datasets are introduced, Nas4-60k and Nas4-60k-aug, designed to train our generative networks in producing calligraphic Arabic. Utilizing the StyleGAN2-ada architecture, our approach successfully generates stylistically coherent and high-quality calligraphic samples. These samples exhibit meaningful feature extraction and generalization of calligraphic features, extending beyond the training sets. Furthermore, our system reveals a continuous spectrum of calligraphic features through latent space interpolations, leading to the creation of dynamic, innovative artworks that blend traditional and contemporary elements of Arabic calligraphy. Drawing inspiration from the compositional form of siyah-mashq, our work culminates in multiple publicly presented artworks that exhibit a new mode of creative expression and highlight the potential of GANs in unveiling new artistic dimensions in calligraphic Arabic script.
References:
[1]
Wikipedia. 2023. Arabic script. Retrieved December 15, 2023 from https://en.wikipedia.org/wiki/Arabic script/.
Google Scholar
[2]
Britannica. 2023. Arabic alphabet. Retrieved December 15, 2023 from https://www.britannica.com/topic/Arabic-alphabet/.
Google Scholar
[3]
Sheila S. Blair. 2006. Islamic calligraphy. Edinburgh University Press.
Google Scholar
[4]
Charbel Dagher. 2017. Arabic Hurufiyya: Art and Identity. Skira.
Google Scholar
[5]
Behrooz Parhami. 2019. Evolutionary Changes in Persian and Arabic Scripts to Accommodate the Printing Press, Typewriting, and Computerized Word Processing. Tugboat (Proc 40th Annu. Meet. TeX Users Group Palo Alto CA August) 40, 2 (2019), 179–186.
Google Scholar
[6]
Titus Nemeth. 2013. Arabic type-making in the machine age: the influence of technology on the form of Arabic type, 1908–1993. Ph.D. Dissertation. University of Reading.
Google Scholar
[7]
Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative Adversarial Nets. In Advances in Neural Information Processing Systems, Curran Associates, Inc.
Google Scholar
[8]
Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Bj?rn Ommer. 2022. High-resolution image synthesis with latent diffusion models. In Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA. 10674–10685. https://doi.org/10.1109/CVPR52688.2022.01042
Crossref
Google Scholar
[9]
Tero Karras, Samuli Laine, Miika Aittala, Janne Hellsten, Jaakko Lehtinen, and Timo Aila. 2020. Analyzing and Improving the Image Quality of StyleGAN. In Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA. 8107–8116. https://doi.org/10.1109/CVPR42600.2020.00813
Crossref
Google Scholar
[10]
Gabriel Vigliensoni, Phoenix Perry, and Rebecca Fiebrink. 2022. A Small-Data Mindset for Generative AI Creative Work. In Generative AI and HCI – CHI 2022 Workshop. Online.
Google Scholar
[11]
Aaron Hertzmann. 2020. Visual Indeterminacy in GAN Art. Leonardo 53, 4 (Jul. 2020), 424–428. https://doi.org/10.1162/leon_a_01930.
Crossref
Google Scholar
[12]
Maryam Ekhtiar. 2006. Practice Makes Perfect: The Art of Calligraphy Exercises (Siy?h Mashq) in Iran. Muqarnas, 23, 1 (Nov. 2006), 107–130.
Google Scholar
[13]
Sahar Homami. 2023. Sahar. Retrieved December 15, 2023 from https://saharhomami.com/.
Google Scholar
[14]
Weidi Zhang and Donghao Ren. 2021. Cangjie. In SIGGRAPH Asia 2020 Art Gallery, (SA ’20), Virtual Event, Republic of Korea. Association for Computing Machinery, New York, NY, USA. https://doi.org/10.1145/3414686.3427153
Digital Library
Google Scholar
[15]
Yuan Guo, Zhouhui Lian, Yingmin Tang, and Jianguo Xiao. 2018. Creating New Chinese Fonts based on Manifold Learning and Adversarial Networks. In Proceedings of the 39th Annual European Association for Computer Graphics Conference: Short Papers (EG), Delft, The Netherlands. Eurographics Association, Goslar, DEU. 61–64.
Digital Library
Google Scholar
[16]
Pengyuan Lyu, Xiang Bai, Cong Yao, Zhen Zhu, Tengteng Huang, and Wenyu Liu. 2017. Auto-Encoder Guided GAN for Chinese Calligraphy Synthesis. In 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Kyoto, Japan, 1095–1100. https://doi.org/10.1109/ICDAR.2017.181
Crossref
Google Scholar
[17]
Yuchen Tian. 2017. zi2zi: Master Chinese Calligraphy with Conditional Adversarial Networks. Retrieved December 15, 2023 from https://kaonashi-tyc.github.io/2017/04/06/zi2zi.html
Google Scholar
[18]
Xu Chen, Lei Wu, Minggang He, Lei Meng, and Xiangxu Meng. 2021. MLFont: Few-Shot Chinese Font Generation via Deep Meta-Learning. In Proceedings of the 2021 International Conference on Multimedia Retrieval, Taipei, Taiwan. Association for Computing Machinery, New York, NY, USA, 37–45. https://doi.org/10.1145/3460426.3463606
Digital Library
Google Scholar
[19]
Haruka Aoki, Koki Tsubota, Hikaru Ikuta, and Kiyoharu Aizawa. 2021. Few-Shot Font Generation with Deep Metric Learning. In 25th International Conference on Pattern Recognition (ICPR), January 10-15, 2021, Milan, Italy. IEEE, 8539–8546. https://doi.org/10.1109/ICPR48806.2021.9412254
Crossref
Google Scholar
[20]
Ismail B. Mustapha, Shafaatunnur Hasan, Hatem Nabus, and Siti M. Shamsuddin. 2022. Conditional Deep Convolutional Generative Adversarial Networks for Isolated Handwritten Arabic Character Generation. Arabian Journal for Science and Engineering, 47, 2 (Jul. 2021), 1309–1320. https://doi.org/10.1007/s13369-021-05796-0
Crossref
Google Scholar
[21]
Tahani Alkhodidi, Lamia Aljoudi, Aisha Fallatah, Aya Bashy, Norah Alqahtani, Nujood Almajnooni, Ahad Allhabi, Telawa Albarakati, and Tarik Alafif. 2021. GEAC: Generating and Evaluating Handwritten Arabic Characters Using Generative Adversarial Networks. In 2021 International Conference on Computational Intelligence and Knowledge Economy (ICCIKE), March 17-18, 2021, Dubai, United Arab Emirates. IEEE, 228–233. https://doi.org/10.1109/ICCIKE51210.2021.9410746
Crossref
Google Scholar
[22]
Mahmood A. Ahmed, Mohsen Ali, Jassim A. Jassim, and Hesham M. Al-Ammal. 2021. Generative Adversarial Networks (GAN) for Arabic Calligraphy. In 2021 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT), September 29-30, 2021, Zallaq, Bahrain. IEEE, 652–657. https://doi.org/10.1109/3ICT53449.2021.9581388
Crossref
Google Scholar
[23]
Eloi Alonso, Bastien Moysset, and Ronaldo Messina. 2019. Adversarial Generation of Handwritten Text Images Conditioned on Sequences. In 2019 International Conference on Document Analysis and Recognition (ICDAR), September 20-25, 2019, Sydney, NSW, Australia. IEEE, 481–486. https://doi.org/10.1109/ICDAR.2019.00083
Crossref
Google Scholar
[24]
Moftah Elzobi, Ayoub Al-Hamadi, Zaher Al-Aghbari, and Laslo Dings. 2013. IESK-ArDB: A database for handwritten Arabic and an optimized topological segmentation approach. International Journal on Document Analysis and Recognition (IJDAR), 16, 3 (Sept. 2013), 295–308. https://doi.org/10.1007/s10032-012-0190-z
Digital Library
Google Scholar
[25]
Mario Pechwitz, Samia Snoussi, Volker M?rgner, Noureddine Ellouze, and Hamid Amiri. 2002. IFN/ENIT-database of handwritten Arabic words. In Proc. of CIFED, 2. Citeseer, 127–136.
Google Scholar
[26]
Zaid Alyafeai, Maged S. Al-shaibani, Mustafa Ghaleb, and Yousif A. Al-Wajih. 2021. Calliar: An Online Handwritten Dataset for Arabic Calligraphy. Neural Computing and Applications, 34, 23 (Dec. 2022), 20701–20713. https://doi.org/10.1007/s00521-022-07537-2
Digital Library
Google Scholar
[27]
Randa I. Elanwar, Wenda Qin, Margrit Betke, and Derry Wijaya. 2021. Extracting text from scanned Arabic books: a large-scale benchmark dataset and a fine-tuned Faster-R-CNN model. International Journal on Document Analysis and Recognition (IJDAR), 24, 4 (Dec. 2021), 349–362. https://doi.org/10.1007/s10032-021-00382-4
Digital Library
Google Scholar
[28]
Ibrahim Abdelaziz and Sherif Abdou. 2014. AltecOnDB: A Large-Vocabulary Arabic Online Handwriting Recognition Database. arXiv:1412.7626. Retrieved from https://arxiv.org/abs/1412.7626
Google Scholar
[29]
Mahmoud Badry, Hesham A. Hassan, Hanaa Bayomi, and Hussien Oakasha. 2018. QTID: Quran Text Image Dataset. International Journal of Advanced Computer Science and Applications (IJACSA), 9, 3, Paper 51. https://doi.org/10.14569/IJACSA.2018.090351
Crossref
Google Scholar
[30]
Amir M. Moslehi. 2017. Mirza Typeface. Retrieved December 15, 2023 from http://www.amirmahdimoslehi.com/Works/mirza/.
Google Scholar
[31]
MaryamSoft. 2021. QalamBartar. Retrieved December 15, 2023 from https://maryamsoft.com/qalambartar/.
Google Scholar
[32]
Jonas Kraasch and Philippe Pasquier. 2022. Autolume-Live: Turning GANs into a Live VJing tool. In Proceedings of the Tenth Conference on Computation, Communication, Aesthetics & X (xCoAx), July 6-8, 2022, Coimbra, Portugal. 168–185.
Crossref
Google Scholar
ACM Digital Library Publication:
- Unveiling New Artistic Dimensions in Calligraphic Arabic Script with Generative Adversarial Networks
