Enhancing image inpainting through image decomposition and deep neural networks

dc.citation.epage732
dc.citation.issue3
dc.citation.journalTitleМатематичне моделювання та комп'ютинг
dc.citation.spage720
dc.contributor.affiliationУніверситет Хасана ІІ Касабланки
dc.contributor.affiliationHassan II University of Casablanca
dc.contributor.authorБеллаж, К.
dc.contributor.authorБенмір, М.
dc.contributor.authorБужена, С.
dc.contributor.authorBellaj, K.
dc.contributor.authorBenmir, M.
dc.contributor.authorBoujena, S.
dc.coverage.placenameЛьвів
dc.coverage.placenameLviv
dc.date.accessioned2025-03-04T12:17:23Z
dc.date.created2023-02-28
dc.date.issued2023-02-28
dc.description.abstractПредставлено новий підхід до проблем розфарбовування, який поєднує методи декомпозиції домену (DDM) із глибокими нейронними мережами (DNN) для розв’язування диференціальних рівнянь у частинних похідних (PDE). По-перше, у цій статті розглядаються різні існуючі та нові підходи до малювання, підкреслюючи їхні переваги та недоліки в єдиній структурі. Після цього введено алгоритм, який висвітлює комбінацію методів DDM та DNN для розв’язування PDE запропонованої математичної моделі малювання. Для цієї моделі модифікований підхід, який був прийнятий, використовує метод DNN, який базується на згорткових нейронних мережах (CNN), щоб зменшити витрати на обчислення в нашому алгоритмі, зберігаючи при цьому точність. Накінець, експериментальні результати показують, що запропонованй метод значно перевершує існуючі для зображень високої роздільної здатності в плямах фарби.
dc.description.abstractA new approach to inpainting problems that combines domain decomposition methods (DDM) with deep neural networks (DNN) to solve partial differential equations (PDE) is presented. First, this article examines different existing and emerging approaches to inpainting while emphasizing their advantages and disadvantages in a unified framework. After that, we introduce an algorithm that highlights the combination of DDM and DNN techniques for solving PDEs of a proposed mathematical inpainting model. For this model, the modified approach that has been adopted uses the DNN method which is based on convolutional neural networks (CNN) to reduce the computational cost in our algorithm while maintaining accuracy. Finally, the experimental results show that our method significantly outperforms existing ones for high-resolution images in paint stains.
dc.format.extent720-732
dc.format.pages13
dc.identifier.citationBellaj K. Enhancing image inpainting through image decomposition and deep neural networks / K. Bellaj, M. Benmir, S. Boujena // Mathematical Modeling and Computing. — Lviv : Lviv Politechnic Publishing House, 2023. — Vol 10. — No 3. — P. 720–732.
dc.identifier.citationenBellaj K. Enhancing image inpainting through image decomposition and deep neural networks / K. Bellaj, M. Benmir, S. Boujena // Mathematical Modeling and Computing. — Lviv : Lviv Politechnic Publishing House, 2023. — Vol 10. — No 3. — P. 720–732.
dc.identifier.doidoi.org/10.23939/mmc2023.03.720
dc.identifier.urihttps://ena.lpnu.ua/handle/ntb/63509
dc.language.isoen
dc.publisherВидавництво Львівської політехніки
dc.publisherLviv Politechnic Publishing House
dc.relation.ispartofМатематичне моделювання та комп'ютинг, 3 (10), 2023
dc.relation.ispartofMathematical Modeling and Computing, 3 (10), 2023
dc.relation.references[1] Elharrouss O., Almaadeed N., Al-Maadeed S., Akbari Y. Image inpainting: A review. Neural Processing Letters. 51 (2), 2007–2028 (2020).
dc.relation.references[2] Bertalmio M., Sapiro G., Caselles V., Ballester C. Image inpainting. Proceedings of the 27th annual conference on Computer graphics and interactive techniques. 417–424 (2000).
dc.relation.references[3] Criminisi A., Shotton J., Konukoglu E. Decision forests: A unified framework for classification, regression, density estimation, manifold learning and semi-supervised learning. Foundations and trends R in computer graphics and vision. 7 (2–3), 81–227 (2012).
dc.relation.references[4] Boujena S., Bellaj K., El Guarmah E. M., Gouasnouane O. An improved nonlinear model for image inpainting. Applied Mathematical Sciences. 9 (124), 6189–6205 (2015).
dc.relation.references[5] Ben-Loghfyry A., Hakim A. Time-fractional diffusion equation for signal and image smoothing. Mathematical Modeling and Computing. 9 (2), 342–350 (2022).
dc.relation.references[6] Gouasnouane O., Moussaid N., Boujena S., Kabli K. A nonlinear fractional partial differentiation equation for image inpainting. Mathematical Modeling and Computing. 9 (3), 536–546 (2022).
dc.relation.references[7] Kichenassamy S. The Perona–Malik paradox. SIAM Journal on Applied Mathematics. 57 (5), 1328–1342 (1997).
dc.relation.references[8] Voci F., Eiho S., Sugimoto N., Sekibuchi H. Estimating the gradient in the Perona–Malik equation. IEEE Signal Processing Magazine. 21 (3), 39–65 (2004).
dc.relation.references[9] Bellaj K., Boujena S., El Guarmah E. M., Gouasnouane O. One approach for image denoising based on finite element method and domain decomposition technique. International Journal of Applied Physics and Mathematics. 7 (2), 141–147 (2017).
dc.relation.references[10] Boujena S., Pousin J., El Guarmah E. M., Gouasnouane O. An improved nonlinear model for image restoration. Pure and Applied Functional Analysis. 2 (4), 599–623 (2017).
dc.relation.references[11] Kharazmi E., Zhang Z., Karniadakis G. E. hp-VPINNs: Variational physics-informed neural networks with domain decomposition. Computer Methods in Applied Mechanics and Engineering. 374, 113547 (2021).
dc.relation.references[12] Firsov D., Lui S. H. Domain decomposition methods in image denoising using Gaussian curvature. Journal of Computational and Applied Mathematics. 193 (2), 460–473 (2006).
dc.relation.references[13] Smith B. F. Domain decomposition methods for partial differential equations. Parallel Numerical Algorithms. 225–243 (1997).
dc.relation.references[14] Chan T. F., Mathew T. P. Domain decomposition algorithms. Acta Numerica. 3, 61–143 (1994).
dc.relation.references[15] Van Eck D., McAdams D. A., Vermaas P. E. Functional decomposition in engineering: a survey. International Design Engineering Technical Conferences and Computers and Information in Engineering Conference. 227–236 (2007).
dc.relation.references[16] Mahoney M. W., Drineas P. CUR matrix decompositions for improved data analysis. Proceedings of the National Academy of Sciences. 106 (3), 697–702 (2009).
dc.relation.references[17] Wang Z., He G., Du W., Zhou J., Han X., Wang J., He H., Guo X., Wang J., Kou Y. Application of parameter optimized variational mode decomposition method in fault diagnosis of gearbox. IEEE Access. 7, 44871–44882 (2019).
dc.relation.references[18] Han D.-R. A survey on some recent developments of alternating direction method of multipliers. Journal of the Operations Research Society of China. 10 (1), 1–52 (2022).
dc.relation.references[19] Kelleher J. D. Deep learning. MIT Press (2019).
dc.relation.references[20] Alaa K., Atountiand M., Zirhem M. Image restoration and contrast enhancement based on a nonlinear reaction-diffusion mathematical model and divide & conquer technique. Mathematical Modeling and Computing. 8 (3), 549–559 (2021).
dc.relation.references[21] Alaa H., Alaa N., Aqel F., Lefraich H. A new Lattice Boltzmann method for a Gray–Scott based model applied to image restoration and contrast enhancement. Mathematical Modeling and Computing. 9 (2), 187–202 (2022).
dc.relation.references[22] Alaa N., Alaa K., Atounti M., Aqel F. A new mathematical model for contrast enhancement in digital images. Mathematical Modeling and Computing. 9 (2), 342–350 (2022).
dc.relation.references[23] Pintor M., Angioni D., Sotgiu A., Demetrio L., Demontis A., Biggio B., Roli F. ImageNet-Patch: A dataset for benchmarking machine learning robustness against adversarial patches. Pattern Recognition. 134, 109064 (2023).
dc.relation.references[24] Li D., Ling H., Kim S. W., Kreis K., Fidler S., Torralba A. BigDatasetGAN: Synthesizing ImageNet with Pixel-wise Annotations. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 21330–21340 (2022).
dc.relation.references[25] Prabhu V. U., Yap D. A., Wang A., Whaley J. Covering up bias in CelebA-like datasets with Markov blankets: A post-hoc cure for attribute prior avoidance. ArXiv preprint arXiv:1907.12917 (2019).
dc.relation.references[26] Zhu H., Wu W., Zhu W., Jiang L., Tang S., Zhang L., Liu Z., Loy C. C. CelebV-HQ: A large-scale video facial attributes dataset. European Conference on Computer Vision. 650–667 (2022).
dc.relation.references[27] Xie K., Gao L., Lu Z., Li C., Xi Q., Zhang F., Sun J., Lin T., Sui J., Ni X. Inpainting the metal artifact region in MRI images by using generative adversarial networks with gated convolution. Medical Physics. 49 (10), 6424–6438 (2022).
dc.relation.references[28] Yi Z., Tang Q., Azizi S., Jang D., Xu Z. Contextual residual aggregation for ultra high-resolution image inpainting. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 7508–7517 (2020).
dc.relation.references[29] Li J., Wang N., Zhang L., Du B., Tao D. Recurrent feature reasoning for image inpainting. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 7760–7768 (2020).
dc.relation.references[30] Zhao H., Kong X., He J., Qiao Y., Dong C. Efficient image super-resolution using pixel attention. European Conference on Computer Vision. 56–72 (2020).
dc.relation.references[31] Zhu M., He D., Li X., Li C., Li F., Liu X., Ding E., Zhang Z. Image inpainting by end-to-end cascaded refinement with mask awareness. IEEE Transactions on Image Processing. 30, 4855–4866 (2021).
dc.relation.references[32] Wang N., Zhang Y., Zhang L. Dynamic selection network for image inpainting. IEEE Transactions on Image Processing. 30, 1784–1798 (2021).
dc.relation.referencesen[1] Elharrouss O., Almaadeed N., Al-Maadeed S., Akbari Y. Image inpainting: A review. Neural Processing Letters. 51 (2), 2007–2028 (2020).
dc.relation.referencesen[2] Bertalmio M., Sapiro G., Caselles V., Ballester C. Image inpainting. Proceedings of the 27th annual conference on Computer graphics and interactive techniques. 417–424 (2000).
dc.relation.referencesen[3] Criminisi A., Shotton J., Konukoglu E. Decision forests: A unified framework for classification, regression, density estimation, manifold learning and semi-supervised learning. Foundations and trends R in computer graphics and vision. 7 (2–3), 81–227 (2012).
dc.relation.referencesen[4] Boujena S., Bellaj K., El Guarmah E. M., Gouasnouane O. An improved nonlinear model for image inpainting. Applied Mathematical Sciences. 9 (124), 6189–6205 (2015).
dc.relation.referencesen[5] Ben-Loghfyry A., Hakim A. Time-fractional diffusion equation for signal and image smoothing. Mathematical Modeling and Computing. 9 (2), 342–350 (2022).
dc.relation.referencesen[6] Gouasnouane O., Moussaid N., Boujena S., Kabli K. A nonlinear fractional partial differentiation equation for image inpainting. Mathematical Modeling and Computing. 9 (3), 536–546 (2022).
dc.relation.referencesen[7] Kichenassamy S. The Perona–Malik paradox. SIAM Journal on Applied Mathematics. 57 (5), 1328–1342 (1997).
dc.relation.referencesen[8] Voci F., Eiho S., Sugimoto N., Sekibuchi H. Estimating the gradient in the Perona–Malik equation. IEEE Signal Processing Magazine. 21 (3), 39–65 (2004).
dc.relation.referencesen[9] Bellaj K., Boujena S., El Guarmah E. M., Gouasnouane O. One approach for image denoising based on finite element method and domain decomposition technique. International Journal of Applied Physics and Mathematics. 7 (2), 141–147 (2017).
dc.relation.referencesen[10] Boujena S., Pousin J., El Guarmah E. M., Gouasnouane O. An improved nonlinear model for image restoration. Pure and Applied Functional Analysis. 2 (4), 599–623 (2017).
dc.relation.referencesen[11] Kharazmi E., Zhang Z., Karniadakis G. E. hp-VPINNs: Variational physics-informed neural networks with domain decomposition. Computer Methods in Applied Mechanics and Engineering. 374, 113547 (2021).
dc.relation.referencesen[12] Firsov D., Lui S. H. Domain decomposition methods in image denoising using Gaussian curvature. Journal of Computational and Applied Mathematics. 193 (2), 460–473 (2006).
dc.relation.referencesen[13] Smith B. F. Domain decomposition methods for partial differential equations. Parallel Numerical Algorithms. 225–243 (1997).
dc.relation.referencesen[14] Chan T. F., Mathew T. P. Domain decomposition algorithms. Acta Numerica. 3, 61–143 (1994).
dc.relation.referencesen[15] Van Eck D., McAdams D. A., Vermaas P. E. Functional decomposition in engineering: a survey. International Design Engineering Technical Conferences and Computers and Information in Engineering Conference. 227–236 (2007).
dc.relation.referencesen[16] Mahoney M. W., Drineas P. CUR matrix decompositions for improved data analysis. Proceedings of the National Academy of Sciences. 106 (3), 697–702 (2009).
dc.relation.referencesen[17] Wang Z., He G., Du W., Zhou J., Han X., Wang J., He H., Guo X., Wang J., Kou Y. Application of parameter optimized variational mode decomposition method in fault diagnosis of gearbox. IEEE Access. 7, 44871–44882 (2019).
dc.relation.referencesen[18] Han D.-R. A survey on some recent developments of alternating direction method of multipliers. Journal of the Operations Research Society of China. 10 (1), 1–52 (2022).
dc.relation.referencesen[19] Kelleher J. D. Deep learning. MIT Press (2019).
dc.relation.referencesen[20] Alaa K., Atountiand M., Zirhem M. Image restoration and contrast enhancement based on a nonlinear reaction-diffusion mathematical model and divide & conquer technique. Mathematical Modeling and Computing. 8 (3), 549–559 (2021).
dc.relation.referencesen[21] Alaa H., Alaa N., Aqel F., Lefraich H. A new Lattice Boltzmann method for a Gray–Scott based model applied to image restoration and contrast enhancement. Mathematical Modeling and Computing. 9 (2), 187–202 (2022).
dc.relation.referencesen[22] Alaa N., Alaa K., Atounti M., Aqel F. A new mathematical model for contrast enhancement in digital images. Mathematical Modeling and Computing. 9 (2), 342–350 (2022).
dc.relation.referencesen[23] Pintor M., Angioni D., Sotgiu A., Demetrio L., Demontis A., Biggio B., Roli F. ImageNet-Patch: A dataset for benchmarking machine learning robustness against adversarial patches. Pattern Recognition. 134, 109064 (2023).
dc.relation.referencesen[24] Li D., Ling H., Kim S. W., Kreis K., Fidler S., Torralba A. BigDatasetGAN: Synthesizing ImageNet with Pixel-wise Annotations. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 21330–21340 (2022).
dc.relation.referencesen[25] Prabhu V. U., Yap D. A., Wang A., Whaley J. Covering up bias in CelebA-like datasets with Markov blankets: A post-hoc cure for attribute prior avoidance. ArXiv preprint arXiv:1907.12917 (2019).
dc.relation.referencesen[26] Zhu H., Wu W., Zhu W., Jiang L., Tang S., Zhang L., Liu Z., Loy C. C. CelebV-HQ: A large-scale video facial attributes dataset. European Conference on Computer Vision. 650–667 (2022).
dc.relation.referencesen[27] Xie K., Gao L., Lu Z., Li C., Xi Q., Zhang F., Sun J., Lin T., Sui J., Ni X. Inpainting the metal artifact region in MRI images by using generative adversarial networks with gated convolution. Medical Physics. 49 (10), 6424–6438 (2022).
dc.relation.referencesen[28] Yi Z., Tang Q., Azizi S., Jang D., Xu Z. Contextual residual aggregation for ultra high-resolution image inpainting. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 7508–7517 (2020).
dc.relation.referencesen[29] Li J., Wang N., Zhang L., Du B., Tao D. Recurrent feature reasoning for image inpainting. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 7760–7768 (2020).
dc.relation.referencesen[30] Zhao H., Kong X., He J., Qiao Y., Dong C. Efficient image super-resolution using pixel attention. European Conference on Computer Vision. 56–72 (2020).
dc.relation.referencesen[31] Zhu M., He D., Li X., Li C., Li F., Liu X., Ding E., Zhang Z. Image inpainting by end-to-end cascaded refinement with mask awareness. IEEE Transactions on Image Processing. 30, 4855–4866 (2021).
dc.relation.referencesen[32] Wang N., Zhang Y., Zhang L. Dynamic selection network for image inpainting. IEEE Transactions on Image Processing. 30, 1784–1798 (2021).
dc.rights.holder© Національний університет “Львівська політехніка”, 2023
dc.subjectглибокі нейронні мережи
dc.subjectметоди декомпозиції домену
dc.subjectрозфарбовування
dc.subjectмашинне навчання
dc.subjectрівняння в частинних похідних
dc.subjectdeep neural
dc.subjectdomain decomposition methods
dc.subjectinpainting
dc.subjectmachine learning
dc.subjectpartial differential equations
dc.titleEnhancing image inpainting through image decomposition and deep neural networks
dc.title.alternativeПокращення розфарбовування зображень за допомогою декомпозиції зображення та глибоких нейронних мереж
dc.typeArticle

Files

Original bundle

Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
2023v10n3_Bellaj_K-Enhancing_image_inpainting_720-732.pdf
Size:
1.56 MB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
2023v10n3_Bellaj_K-Enhancing_image_inpainting_720-732__COVER.png
Size:
443.56 KB
Format:
Portable Network Graphics

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.81 KB
Format:
Plain Text
Description: