Abstract
Image restoration is a branch of image processing that involves a mathematical deterioration and restoration model to restore an original image from a degraded image. This research aims to restore blurred images that have been corrupted by a known or unknown degradation function. Image restoration approaches can be classified into 2 groups based on degradation feature knowledge: blind and non-blind techniques. In our research, we adopt the type of blind algorithm. A deep learning method (SR) has been proposed for single image super-resolution. This approach can directly learn an end-to-end mapping between low-resolution images and high-resolution images. The mapping is expressed by a deep convolutional neural network (CNN). The proposed restoration system must overcome and deal with the challenges that the degraded images have unknown kernel blur, to deblur degraded images as an estimation from original images with a minimum rate of error.
Highlights
Image restoration can be defined as one of the conventional problems in the low-level vision that was commonly studied in the literature
Image restoration represents an operation that takes a corrupted image attempting at the estimate the original image
The restoration of the image is divided into two phases, these phases are: the degradation phase and restoration phase, Fig. 1 shows these two phases [1]: 1) Degradation phase: During this phase, the original image is degraded with blurring function and the extra noise function
Summary
Image restoration can be defined as one of the conventional problems in the low-level vision that was commonly studied in the literature. The proposed model has been referred to as the restoration SR CNN that is applied to the super-resolution on the blurred/noisy images with a priori unknown (i.e. blind) amount of the blurring. This model has been experimentally validated and it has been shown that the proposed architecture has been more suitable for the reconstruction of the blurred images in comparison to the results that have been obtained using the Bicubic approach [2], [4] in blind scenarios
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
