fast blind image deblurring using smoothing-enhanching regularizer
S. KOUSALYA, M.E.,M.J.YAMINI SARANYA,E.SWAPNA
Published in International Journal of Advanced Research in Computer Science Engineering and Information Technology
ISSN: 2321-3337 Impact Factor:1.521 Volume:6 Issue:3 Year: 04 May,2021 Pages:1637-1642
Abstract
Image Restoration is the process of recovering the original image by removing noise and blur from image. Image blur is difficult to avoid in many situations like photography, to remove motion blur caused by camera shake, radar imaging to remove the effect of image system response etc. Image noise is unwanted environment condition such as rain, snow etc. The image degradation could come from coding artifacts, resolution limitation, transmission noise, object motion, camera shake, or a combination of them. Image decomposition is used for decomposing the distorted image into a texture layer (High Frequency HR Component) and a structure layer (Low Frequency LF Component) with the goal to separate HF and LF artifacts. The existing system is a flexible deep CNN framework which exploits the frequency characteristics of different types of artifacts. Hence, the same approach can be employed for a variety of image restoration tasks by adjusting the architecture. For reducing the artifacts with similar frequency characteristics, a quality enhancement network which adopts residual and recursive learning is proposed. Residual learning is utilized to speed up the training process and boost the performance; recursive learning is adopted to significantly reduce the number of training parameters, as well as boost the performance deblurring, which can help us to build image deblurring models more accurately. While global edges selection methods tend to fail in capturing dense image structures, the edges are easy to be affected by noise and blur. In this paper, we propose an image deblurring method based on local edges selection.
Kewords
CNN – Convolutional Neural Network, ReLU – Rectified Linear Unit, MTCNN - Multitask Cascaded Convolutional Networks
Reference
[1]: 1. Z. Zha, X. Yuan, B. Wen, J. Zhang, J. Zhou, and C. Zhu, “Image restoration using joint patch-group-based sparse representation,” IEEE Transactions on Image Processing, vol. 29, pp. 7735– 7750, 2020. [2]: 2. J. Yang, J. Wright, T. S. Huang, and Y. Ma, “Image superresolution via sparse representation,” IEEE Transactions on Image Processing, vol. 19, no. 11, pp. 2861– 2873, Nov 2010. [3]:W. Dong, L. Zhang, G. Shi, and X. Li, “Nonlocally centralized sparse representation for image restoration,” IEEE Transactions on Image Processing, vol. 22, no. 4, pp. 1620– 1630, April 2013 [4]: 5. B. Wen, S. Ravishankar, and Y. Bresler, “Structured overcomplete sparsifying transform learning with convergence guarantees and applications,” International Journal of Computer Vision, vol. 114, no. 2-3, pp. 137– 167, 2015.
