Image Restoration Using Deep Learning Based Image Completion

Phie Chyan(1*), Tri Saptadi(2)

(1) Program Studi Teknik Informatika, Fakultas Teknologi Informasi, Universitas Atma Jaya Makassar
(2) Program Studi Teknik Informatika, Fakultas Teknologi Informasi, Universitas Atma Jaya Makassar
(*) Corresponding Author

Abstract


Digital images can experience various disturbances in acquisition and storage, one of which is a disturbance indicated by damage to certain areas of the image field and causes the loss of some of the information represented by the image. One of the ways to restore an image experiencing disturbances like this is with image completion technology. Image completion is an image restoration technology capable of filling in or completing missing or corrupted parts of an image. Various methods have been developed for this image completion, starting from those based on basic image processing to the latest relying on artificial intelligence algorithms. This study aims to develop and implement an image completion model based on deep learning with the transfer learning method from the completion.net architecture. Using the Facesrub training dataset consisting of a collection of unique facial photos allows the model to understand facial attributes better. Compared to conventional image completion based on image patches, the method developed in this study can perform image filling in image gaps with more realistic results. Based on visual tests conducted on respondents, the results obtained enable respondents to understand all the information represented by the restored image, similar to the original image.


Keywords


Image completion; Image restoration; Deep learning; CNN; Completion net

Full Text:

PDF

References


P. Chyan and N. T. Saptadi, “Pemulihan Citra Berbasis Metode Markov Random Field,” JURIKOM (Jurnal Ris. Komputer), vol. 9, no. 2, p. 218, Apr. 2022.

P. Chyan, “PENERAPAN IMAGE ENHANCEMENT ALGORITHM UNTUK MENINGKATKAN KUALITAS CITRA TAK BERGERAK,” Inf. dan Teknol. Ilm., vol. 4, no. 3, May 2017.

P. Chyan, “Rancang Bangun Mesin Pencari Citra Dengan Pendekatan Temu Balik Berbasis Konten,” TEMATIKA, vol. 3, no. 2, 2015.

J. Bin Huang, S. B. Kang, N. Ahuja, and J. Kopf, “Image completion using planar structure guidance,” ACM Trans. Graph., vol. 33, no. 4, 2014.

G. Chican and M. Tamaazousti, “Constrained PatchMatch for image completion,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 8887, pp. 560–568, 2014.

J. Sun, L. Yuan, J. Jia, and H. Y. Shum, “Image completion with structure propagation,” ACM Trans. Graph., vol. 24, no. 3, pp. 861–868, Jul. 2005.

C. Zheng, T. J. Cham, J. Cai, and D. Phung, “Bridging Global Context Interactions for High-Fidelity Image completion,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2022-June, pp. 11502–11512, 2022.

S. Iizuka, E. Simo-Serra, and H. Ishikawa, “Globally and locally consistent image completion,” ACM Trans. Graph., vol. 36, no. 4, 2017.

Q. Li, L. Hu, Q. Shang, Y. Wang, L. Jiang, and W. Long, “Research Progress in the Field of Image completion,” Proc. - 2021 3rd Int. Conf. Artif. Intell. Adv. Manuf. AIAM 2021, pp. 398–402, 2021.

P. Aditya Laksana, “Restorasi Pada Citra Digital Menggunakan Pendekatan Exemplar Based Inpainting,” Oct. 2014.

A. H. Hasugian and I. Zufria, “Perancangan Sistem Restorasi Citra Dengan Metode Image Inpainting,” Algoritm. J. ILMU Komput. DAN Inform., vol. 2, no. 2, p. 31, Jan. 2019.

M. Failzal and A. Rao, “‘RECOGNITION of STRESS USING FACE IMAGE and FACIAL LANDMARKS,’” Int. Adv. Res. J. Sci. Eng. Technol., vol. 8, no. 5, pp. 792–797, 2021.

P. Chyan, “Image Enhancement Based On Bee Colony Algorithm,” J. Eng. Appl. Sci., vol. 14, no. 1, pp. 43–49, 2019.

J. Yang, R. Xu, Z. Qi, and Y. Shi, “Visual Anomaly Detection for Images: A Systematic Survey,” Procedia Comput. Sci., vol. 199, pp. 471–478, 2021.

P. Chyan, “Sistem Temu Balik Citra Menggunakan Ekstraksi Fitur Citra Dengan Klasifikasi Region Untuk Identifikasi Objek,” TEMATIKA, vol. 2, no. 2, pp. 63–72, 2014.

N. Akimoto, S. Kasai, M. Hayashi, and Y. Aoki, “360-Degree Image completion by Two-Stage Conditional Gans,” Proc. - Int. Conf. Image Process. ICIP, vol. 2019-September, pp. 4704–4708, Sep. 2019.

Q. Chen, G. Li, Q. Xiao, L. Xie, and M. Xiao, “Image completion via transformation and structural constraints,” Eurasip J. Image Video Process., vol. 2020, no. 1, pp. 1–18, Dec. 2020.

L. Theis, A. Van Den Oord, and M. Bethge, “A note on the evaluation of generative models,” 4th Int. Conf. Learn. Represent. ICLR 2016 - Conf. Track Proc., 2016.

A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” Commun. ACM, vol. 60, no. 6, pp. 84–90, Jun. 2017.

P. Isola, J. Y. Zhu, T. Zhou, and A. A. Efros, “Image-to-image translation with conditional adversarial networks,” Proc. - 30th IEEE Conf. Comput. Vis. Pattern Recognition, CVPR 2017, vol. 2017-January, pp. 5967–5976, Nov. 2017.

H. W. Ng and S. Winkler, “A data-driven approach to cleaning large face datasets,” 2014 IEEE Int. Conf. Image Process. ICIP 2014, pp. 343–347, 2014.




DOI: https://doi.org/10.32736/sisfokom.v12i3.1699

Refbacks

  • There are currently no refbacks.


Indexed By:

 


Creative Commons License
Jurnal Sisfokom (Sistem Informasi dan Komputer) has ISSN 2301-7988 and e-ISSN 2581-0588 which is published by Lembaga Penelitian dan Pengabdian Masyarakat (LPPM) ISB Atma Luhur under a Creative Commons Attribution-ShareAlike 4.0 International License.
Web Analytics Made Easy - StatCounter