RESTORATION OF OLD MALAY JAWI MANUSCRIPTS USING MUMFORD-SHAH AND BERTALMIO INPAINTING MODELS

Authors

  • Nurul Nabilah Zainal Department of Mathematics, Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA, 40450 Shah Alam, Selangor, Malaysia
  • Nur Fatini Mohammad Yuri Department of Mathematics, Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA, 40450 Shah Alam, Selangor, Malaysia
  • Abdul Kadir Jumaat Department of Mathematics, Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA, 40450 Shah Alam, Selangor, Malaysia ; Institute for Big Data Analytics and Artificial Intelligence (IBDAAI), Universiti Teknologi MARA, 40450, Shah Alam, Selangor, Malaysia

DOI:

https://doi.org/10.24191/mjoc.v7i1.14882

Keywords:

Bertalmio Model, Image Inpainting, Mumford-Shah Model, Old Malay Jawi Manuscripts

Abstract

Jawi is the earliest writing script of the Malay Archipelago that was derived from Arabic letters. Old Malay Jawi manuscripts may provide vital information about the legacy, cultures, and historical evolution of the Malay Archipelago over time. However, while preserved, old Malay Jawi manuscripts tend to be damaged. Image inpainting is a process of reconstructing missing parts of an image which can be used to restore the old Malay Jawi manuscripts. The Mumford-Shah and Bertalmio inpainting models are two well-known and effective methods for solving the image inpainting problem. Hence, the aim of this study is to determine which model is better at restoring corrupted input images of the old Malay Jawi manuscripts. A sample of thirty (30) old Malay Jawi manuscript images were obtained from Kumpulan Penyelidikan Etnomatematik Melayu (KUPELEMA). The corrupted images were restored using both models, implemented using the MATLAB software. The Structural Similarity Index Measure (SSIM) and Mean Absolute Error (MAE) were utilized to assess the quality of the results. The numerical experiment demonstrates that the average values of SSIM and MAE for Mumford-Shah inpainting model are 0.9380 and 0.0151 respectively, while the values for the Bertalmio inpainting model are 0.8762 and 0.0255 respectively. This indicates that the Mumford-Shah inpainting model is more effective than Bertalmio inpainting model. The algorithms used in this study can be upgraded to a software framework for commercial use and can be implemented for other kinds of digitized data.

References

Abdullah, S. A., & Jumaat, A. K. (2022). Selective image segmentation models using three distance functions. Journal of Information and Communication Technology, 21, 95-116.

Ambrosio, L., & Tortorelli, V. M. (1990). Approximation of functionals depending on jumps by elliptic functionals via gamma convergence. Communications on Pure and Applied Mathematics, 43, 999-1036.

Ashikhmin, M. (2001). Synthesizing natural textures. In Symposium on Interactive 3D graphics, 2001 (pp. 217-226). SIGGRAPH.

Barbu, T. (2018). Second-order anisotropic diffusion based framework for structural inpainting. Proceedings of the Romanian Academy, Series A, 19(2), 329-336.

Bertalmio, M. (2001). Processing of flat and nonflat image information on arbitrary manifolds. [Ph.D. thesis, The University of Minnesota]. Citeseer, https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.2.957&rep=rep1&type=pdf.

Bonneel, N., Coeurjolly, D., Gueth, P., & Lachaud, J. O. (2018). Mumford-Shah mesh processing using the Ambrosio-Tortorelli functional. Computer Graphics Forum, 37(7), 75-85.

Chan, T. F., & Shen, J. (2002). Mathematical models for local nontexture inpaintings. SIAM Journal on Applied Mathematics, 62, 1019-1043.

Dang, T., & Phan, K. (2020). A weighted total variation based image denoising model using mean curvature. Optik, 217, 164940.

Esedoglu, S., & Shen, J. (2002). Digital inpainting based on the Mumford-Shah-Euler image model. European Journal of Applied Mathematics, 13, 353-370.

Halid, S. (2020). 34 Manuskrip Simpan Rahsia Sains, Matematik. A post at Berita Harian available at https://upm.edu.my/berita/manuskrip_sains_dan_matematik_tamadun_melayu_abad_ke_17_ditemui_metrotv-58717?L=en.

Hays, J., & Efros, A. A. (2007, May). Scene completion using millions of photographs. In Computer Graphics Proceedings, Annual Conference Series 2007 (pp. 1-7). SIGGRAPH.

Huang, J.B., Kopf, J., Ahuja, N., & Kang, S. B. (2013). Transformation guided image completion. In IEEE International Conference on Computational Photography (ICCP) (pp. 1-9). IEEE.

Jumaat, A. K., & Chen, K. (2020). Three-dimensional convex and selective variational image segmentation model. Malaysian Journal of Mathematical Sciences, 14(3), 437-450.

Jumaat, A. K., & Chen, K. (2019). A reformulated convex and selective variational image segmentation model and its fast multilevel algorithm. Numerical Mathematics Theory Methods and Applications, 12(2), 403-437. http://dx.doi.org/10.4208/nmtma.OA-2017-0143.

Jumaat, A. K., & Chen, K. (2018). Fast algorithm for selective image segmentation model. International Journal of Engineering and Technology (UAE), 7(4), 41-44.

Jumaat, A. K., & Chen, K. (2017). An optimization-based multilevel algorithm for variational image segmentation models. Electronic Transactions on Numerical Analysis, 46, 474-504.

Jumaat, A. K., Yasiran, S. S., Malek, A. A., Rahman, W. E. Z. W. A., Badrin, N., Osman, S. H., Rafiee, S. R., & Mahmud, R. (2014). Performance comparison of Canny and Sobel edge detectors on Balloon Snake in segmenting masses. In J. Jaafar, L. A. Rahim, & E. E. Mustapha (Eds.), International Conference on Computer and Information Sciences (ICCOINS) (pp. 116-120). IEEE. https://doi.org/10.1109/ICCOINS.2014.6868368.

Jumaat, A. K., Rahman, W. E., Ibrahim, A., Yasiran, S. S., Mahmud, R., & Malek, A. A. (2012). Masses characterization based on angular margin measurement. In D. Al-Dabass, Z. Ibrahim, K. H. Ghazali, & S. W. Mawawi (Eds.), International Conference on Computational Intelligence, Modelling and Simulation (pp. 265-269). IEEE. https://doi.org/10.1109/CIMSim.2012.50.

Kaur, A., Raj, A., & Indu, S. (2020). Inpainting of Irregular Holes in a Manuscript using UNet and Partial Convolution. In Second International Conference on Inventive Research in Computing Applications (ICIRCA) (pp. 778-784). IEEE.

KUPELEMA (2021). Kumpulan Penyelidikan Etnomatematik Melayu. A post at INSPEM available at https://inspem.upm.edu.my/ laboratori/ laboratori_etnomatematik_ dan_didaktik/kumpulan_ penyelidikan_etnomatematik_melayu_kupelema-54857.

Mumford, D., & Shah, J. (1989). Optimal approximations by piecewise smooth functions and associated variational problems. Communications on Pure and Applied Mathematics, 42(5), 577-685.

Rana, M. S., Hassan, M. M., & Bhuiyan, T. (2017). An Enhanced Model for Inpainting on Digital Images Using Dynamic Masking. Journal of Communications, 12(4), 248-253.

Razak, Z. (2016). Old Jawi manuscript: Digital recognition [Ph.D. thesis, University of Malaya]. UM, http://studentsrepo.um.edu.my/6757/.

Rocha, C., Deborah, H., & Hardeberg, J. Y. (2018). Ink bleed-through removal of historical manuscripts based on Hyperspectral imaging. Lecture Notes in Computer Science (pp. 473-480). Springer.

Schonlieb, C.B. (2015a). The Mumford-Shah Image Model for Inpainting. In Partial Differential Equation Methods for Image Inpainting. Cambridge: Cambridge University Press.

Schonlieb, C.B. (2015b). Transport Inpainting. In Partial Differential Equation Methods for Image Inpainting. Cambridge: Cambridge University Press.

Thanh, D. N. H., Prasath, V. B. S., Son, N. V., & Hieu, L. M. (2019). An adaptive image inpainting method based on the modified mumford-shah model and multiscale parameter estimation. Computer Optics, 43(2), 251-257.

Tsai, A., Yezzi, A., Jr., & Willsky, A. S. (2001). Curve evolution implementation of the Mumford-Shah functional for image segmentation, denoising, interpolation, and magnification. IEEE Transactions on Image Processing, 10, 1169-1186.

Yasiran, S. S., Jumaat, A. K., Abdul Malek, A., Hashim, F. H., Dhaniah Nasrir, N., Azirah Sayed Hassan, S. N., Ahmad, N., & Mahmud, R. (2012). Microcalcifications segmentation using three edge detection techniques. In M. R. Mahmood, U. M. Noor, & M. K. Hamzah (Eds.), International Conference on Electronic Devices, Systems, and Applications (pp. 207-211). IEEE. https://doi.org/10.1109/ICEDSA.2012.6507798.

Yasiran, S. S., Jumaat, A. K., Manaf, M., Ibrahim, A., Wan Eny Zarina, W. A. R., Malek, A., Laham, M. F., & Mahmud, R. (2011). Comparison between GVF snake and ED snake in segmenting microcalcifications. In M. K. Hamzah, W. Mansor, & N. M. Tahir (Eds.), International Conference on Computer Applications and Industrial Electronics (pp. 597-601). IEEE. https://doi.org/10.1109/ICCAIE.2011.6162204.

Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., & Huang, T. (2019). Free-form Image Inpaint- ing with Gated Convolution. In 2019 IEEE/CVF International Conference on Computer Vision (ICCV) (pp. 4470-4479). IEEE.

Zaman, N. A. K., Rahman, W. E. Z. W. A., Jumaat, A. K., & Yasiran, S. S. (2015). Classification of breast abnormalities using artificial neural network. Paper presented at the AIP Conference Proceedings,1660, 1-7. https://doi.org/10.1063/1.4915671.

Zhang, L., Chen, Q., Hu, B., & Jiang, S. (2020). Text guided neural image inpainting. In 28th ACM International Conference on Multimedia (pp. 1302-1310). ACM.

Zhao, Y., Price, B., Cohen, S., & Gurari, D. (2019). Guided Image Inpainting: Replacing an image region by pulling content from another image. In 2019 IEEE Winter Conference on Applications of Computer Vision (WACV) (pp. 1514-1523). IEEE.

Downloads

Published

2022-03-31

How to Cite

Zainal, N. N. ., Mohammad Yuri, N. F. ., & Jumaat, A. K. . (2022). RESTORATION OF OLD MALAY JAWI MANUSCRIPTS USING MUMFORD-SHAH AND BERTALMIO INPAINTING MODELS. Malaysian Journal of Computing, 7(1), 1047–1055. https://doi.org/10.24191/mjoc.v7i1.14882