Blur Removal In Natural Digital Images Using Self-reference Generative Networks

Authors

  • Asem Khmag aculty of Engineering, University of Zawia, 00218 Azzawiya city Zawia, Libya
  • R. Ramlee

Keywords:

Classifications, Deblurring, Generative Networks, Image Restoration, Noise Removal, Restoration

Abstract

The blur detection in a single image is considered as a pivotal issue in digital image processing applications, especially when the blurring is spatially-varying. This study introduces self-reference generative network (SR-GN) algorithm in order to deblur a digital natural blurred image. The proposed method divides the contaminated image into two main parts, which are the clear part and blur parts. The blur parts which caused by the shadowy channel are less sparse while the other parts have some dark patches, which can be cleaned by avenging them. In addition, due to the global performance of the proposed algorithm on public database, multicomponent loss function is utilized in order to perform further classification to the original patches of the blurred image to distinguish it from the contaminated counterparts as the experimental results demonstrated. The experimental results show that the proposed technique has an improvement in visual quality, and objective results as well in comparison to related advanced blur removal algorithms.

References

P. Yanwei, H. Zhu, X. Li and X. Li, “Classifying discriminative features for blur detection”, IEEE transactions on cybernetics, vol. 46, no. 10, pp. 2220-2227, 2015.

P. Jinshan, D. Sun, H. Pfister and M. Yang, “Blind image deblurring using dark channel prior ”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 40, no. 10, pp. 2315 – 2328, 2018.

C. Ledig, L. Theis, F. Huszár, J. Caballero, A. Cunningham, A. Acosta, A. Aitken, A. Tejani, J. Totz, Z. Wang, and W. Shi, “Photo Realistic Single Image Super-Resolution Using a Generative Adversarial Network, ” In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 105-114. 2017.

X. Hu, X. Liu, Z. Wang, X. Li, W. Peng and G. Cheng, “ESRGAN: RTSRGAN: Real-Time Super-Resolution Generative Adversarial Networks,” Seventh International Conference on Advanced Cloud and Big Data (CBD), 2019.

D. Ugur, and G. Unal, “Patch-based image inpainting with generative adversarial networks,” arXiv preprint arXiv, 2018.

L. Avisek, A.Jain, D. Nadendla and P. Biswas, “Improved Techniques for GAN based Facial Inpainting,” arXiv preprint arXiv, 2018.

A. Khmag and N. Kamarudin, “Clustring-based natural image denoising using dictionary learning approach in wavelet domain,” Soft computing, vol. 23, no.17, pp.8013-8027, 2019.

R. Liu, Y. He and S. Cheng, “Learning Collaborative Generation Correction Modules for Blind Image Deblurring and Beyond” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.

A. Khmag, S. Al Haddad, A. Ramlee, N. Kamarudin and F. Malallah, “Natural image noise removal using nonlocal means and hidden Markov models in transform domain,” The visual Computer, vol. 34, no. 12, pp. 1661-1675, 2017.

A. Khmag and N. Kamarudin, “Natural Image Deblurring using Recursive Deep Convolutional Neural Network (R-DbCNN) and Second-Generation Wavelets,” The IEEE International Conference on Signal and Image Processing Applications (IEEE ICSIPA), 2019.

O. Kupyn, V. Budzan and M. Mykhailych, “DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8183-8192, 2018.

A. Khmag, AR. Ramli, SJ. Hashim and S. Al Haddad, “Additive noise reduction in natural images using second generation wavelet transform hidden Markov models,”IEEJ Transactions on electrical and electronic engineering, vol.11, no.3, pp.339-347, 2016.

L. Yuan, J. Sun, L. Quan, and H.-Y. Shum, “Image deblurring with blurred/noisy image pairs,” in Proc. ACM SIGGRAPH, San Diego, CA, USA, pp. 1-es, 2007.

J. Pan, D. Sun and H. Pfister, “Blind Image Deblurring Using Dark Channel Prior,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.40, no.10, pp. 2315 – 2328, 2018.

J. Sun, W. Cao, Z. Xu and J. Ponce, “Learning a convolutional neural network for non-uniform motion blur removal,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 769-777, 2015.

S. Nah, T. H. Kim and K. M. Lee, "Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 257-265, 2017.

T. M. Nimisha, A. K. Singh and A. N. Rajagopalan, “Blur-Invariant Deep Learning for Blind-Deblurring,” in IEEE International Conference on Computer Vision (ICCV), pp. 4762-4770, 2017.

J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde- Farley, S. Ozair, A. Courville and Y. Bengio, “Generative Adversarial Nets,” in Advances in Neural Information Processing Systems, vol. 27, pp. 1-9, 2014.

Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, and A. Courville, "Improved Training of Wasserstein GANs," In Advances in neural information processing systems, pp. 5767-5777, 2017.

X. Tao, H. Gao and Y. Wang, “Scale-recurrent Network for Deep Image Deblurring,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.

Y. Bahat, N. Efrat and M. Irani, “Non-uniform Blind Deblurring by Reblurring,” IEEE International Conference on Computer Vision (ICCV), 3306-3314, 2017.

F. Yu, W. Xian, Y. Chen, F. Liu, M. Liao, V. Madhavan and T. Darrell, “BDD100K: A Diverse Driving Video Database with

Scalable Annotation Tooling,” arXiv, 2018.

K. Purohit, A. Shah and A. Rajagopalan, “Learning Based Single Image Blur Detection and Segmentation,” 25th IEEE International Conference on Image Processing (ICIP), pp.2202-2206, 2018.

Y. Chen, T. Wunderli, “Adaptive total variation for image restoration in BV space,” Journal of Math. Anal. App, vol. 272, pp. 117 – 137, 2002.

Z. Wang, A. C. Bovik, H. R. Sheikh and E. P. Simoncelli, “Image quality assessment: From error visibility to structural similarity,” IEEE Transactions on Image Processing, vol. 13, no. 4, pp. 600-612, 2004.

G. Guiliang and Z. Kai, “Local Blurred Natural Image Restoration Based on Self-Reference Deblurring Generative

Adversarial Networks,” IEEE International Conference on Signal and Image Processing Applications (IEEE ICSIPA 2019), pp. 231-235, 2019.

A. Odena, J. Buckman, C. Olsson, T. B. Brown, C. Olah, C. Raffel, and I. Goodfellow, “Is generator conditioning causally related to GAN performance?,” pp. 43-56, 2018.

Downloads

Published

2021-09-28

How to Cite

Khmag, A., & Ramlee, R. . (2021). Blur Removal In Natural Digital Images Using Self-reference Generative Networks. Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 13(3), 61–65. Retrieved from https://jtec.utem.edu.my/jtec/article/view/6121