International Journal of Engineering Research in Computer Science and Engineering (IJERCSE)

Restoring Deteriorated Images using Deep Learning Techniques: Region Filling, Median Filter

Author : Basavaraj Patil ¹ Ananya C M ² Anusha Vinod Nayak ³ Ashrita S Naik ⁴ Harshitha B R ⁵

Date of Publication :21st July 2022

Abstract: \Image restoration is a technique for recovering images from corrupted images that have blur and noise, lowering the image's quality. Motion blur, low resolution, moisture in the atmosphere, and other factors can all contribute to image noise. For noise removal, there are a variety of restoration techniques and a spatial domain filter. To eliminate blur and scratches in deteriorated photographs, an image restoration method has been developed. Deep learning has gained popularity as a method for image restoration during the last few years. Denoising and other image restoration operations are necessary steps in many image processing applications. Image fusion using the stacked median operator, low resolution detail improvement using guided super sampling, and repeated visual consistency assessment and refining are the three processes in the restoration process. Two VAEs (Variational Autoencoders) are trained in this model to translate old and clean pictures into two latent spaces, respectively. This is due to the fact that they are all using supervised learning, which is a difficulty created by the domain gap between the original image and the ones synthesized for training. The suggested project offers a cost-effective solution that can deal with noise, picture rotations, and occlusions.`.

Reference :

1. Anita Yadav, Anil Khatak, “Survey on image restoration techniques”, International Journal for Technological Research in Engineering, Volume: 5, Issue: 4, ISSN Number: 2347 – 471, December 2017.
2. K. Baia, X. Liaoa, Q. Zhanga, X. Jiaa, and S. Liua, “Survey of Learning Based Single Image Super-Resolution Reconstruction Technology”, Mathematical Theory of Images and Signal Representing, Processing, Analysis, Recognition, and Understanding, ISSN Number: 1054-6618, Volume: 30, Issue: August 6, Year 2020, DOI Number: 10.1134/S1054661820040045.
3. Cristiano R Steffens, Lucas R. V. Messias, Paulo Drews, Silvia S. D, “CNN based Image Restoration”, Gernal of Intelligent and Robotics System, ISSN:609-626, YearJanuary 2020.
4. Junyi Chai, Hao Zeng, Anming Li, Eric W.T. Nagi, “Deep Learning in computer vision: A critical review of emerging techniques and application scenarios”, Machine Learning with Applications, Volume: 6, ISSN Number: 2666-8270, August 2021
5. Ankita, Er. Lavina, “Image Restoration using Decision Based Filtering Techniques”, International Journal of Engineering Development and Research, Volume: 4, Issue: 3, ISSN Number: 2321-9939, Year: 2017.
6. Jiwon Kim, Jung Kwon Lee and Kyoung Mu Lee, “Accurate Image Super-Resolution Using Very Deep Convolutional Network”, International Journal on Computer Vision, ISSN Number: 1016-1022, Volume: 40, Issue:1.
7. Ayad A. Al-Ani, Mohammed Sahib Mahdi Altaei and Sally Ali Abdul Ameer Alrubaie, “Colour Image Restoration Using Iterative Mead’s Filter”, Al-Nahrain Journal of Science, Volume: 21, Issue: 4, December, 2018.
8. Ziyu Wan, Bo Zhang, Dongdong Chen, Pan Zhang, Dong Chen, Jing Liao, “Old Photo Restoration via Deep Latent Space Translation”, Journal of Latex Class Files, Volume: 14, Issue:8, August 2015.
9. Nitin Agarwal, Prashant Sinha, Avinash Kumar, Shobha Bagai, “Fast and Dynamic Image Restoration using Laplace equation based Image Inpainting”, DU journal of Undergraduate research and Innovation, Volume:1, Issue: 03, Year: 2015.
10. Xu Xiaoling, Zheng Haiyu, Zhang Fengqin, Li Hechen, Zhang Minghui, “Poisson Image Restoration via Transformed Network”, Journal of the Optical Society of America, Year: 2020
11. Y. Ren, X. Yu, R. Zhang, T. H. Li, S. Liu, and G. Li, “Structure flow: Image inpainting via structure-aware appearance flow,” arXiv preprint arXiv:1908.03852, 2019.
12. Murat Tekalp, Michele Covell, Radu Timofte, Chao Dong- “Introduction to the Issue of Deep Learning for Image/Video Restoration and Compression”, IEEE Journal of Selected topics in Signal Processing, Volume: 15, Issue: 02, ISSN Number: 1932-4553, February 2021, DOI Number: 10.1109/JSTSP.2021.3053364
13. Surbhi Sarode, Shunottara Sarade, Twinkle Kakonde, Ashish Palundarkar- “Image Restoration and Enhancement using Deep Learning”, International Journal of Engineering Applied Sciences and Technology , Volume: 4, Issue: 11, ISSN Number: 2455-2143, March 2020.
14. K. Sai Dinesh ; G. Uganya, “Deblurring of Images using Novel Deconvolutional Neural Network (DNN) Algorithm to Enhance the Accuracy and Comparing with Richardson-Lucy Deconvolution Algorithm (RLD)”, Revista Geintec, Volume: - 11, Issue: 09-06, ISSN Number: 2237-0722, Year 2021.
15. A.S.Sahil Hussain, A.Vignesh, S.Meenatchi Sundaram, A.Neela madheswari,“Automatic Colorization and Restoring of gray scale images using Deep Learning”, Think India Journal, Volume: 22, Issue: 10-November, ISSN Number: 0971-1260, Year 2019.
16. Feng Li, Runmin Cong, Huihui Bai, Yifan He, Yao Zhao, Senior Member, and Ce Zhu, “Learning Deep Interleaved Networks with Asymmetric Co-Attention for Image Restoration”, Journal of Latex Class Files, Volume: 14, Issue: 8, ISSN Number: 2010-1568, Year AUGUST 2015.
17. Himanshu Joshi, Jitendra Sheetlani, “Image Restoration Techniques in Image Processing: An Illustrative Review”, International Journal of Advance Research in Science and Engineering, Volume: 06, Issue: 01, ISSN Number: 2319-8354, December 2017.
18. Ruilong Chen, Lyudmila Mihaylova, Hao Zhu, Nidhal Carla Bouayana. “A Deep Learning Framework for Joint Image Restoration and Recognition”, Circuits, Systems, and Signal Processing 39, ISSN Number: 1561-1580, August 2019.
19. Puneet Kaushik, Mridula Chawla, Gyanender Kumar, “Comparative Analysis of Different Technique for Detection of Noise in Restored Image”, International Journal of Engineering and Computer science, ISSN Number: 2319-7242, Volume: 4, Issue: 7, July 2015.
20. [Book] Ian Goodfellow and Yoshua Bengio and Aaron Courville, “Deep Learning”, The MIT Press; Illustrated edition (November 18, 2016).
21. [Book]M. Arjovsky, S. Chintala, and L. Bottou, “Wasserstein gan,” arXiv preprint arXiv:1701.07875, 2017.
22. [Book]K. Nazeri, E. Ng, T. Joseph, F. Qureshi, and M. Ebrahimi, “Edgeconnect: Generative image inpainting with adversarial edge learning,” 2019.
23. K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, “Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising,” IEEE Transactions on Image Processing, vol. 26, no. 7, pp. 3142–3155, 2017.
24. D. Ulyanov, A. Vedaldi, and V. Lempitsky, “Deep image prior,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 9446– 9454