Motion blurred image blind restoration method using improved generative adversarial network

Abstract

The invention discloses a motion blurred image blind restoration method using an improved generative adversarial network. A clear image is obtained through adversarial training of a generative networkand a judgment network, which is characterized in that a blurring kernel does not need to be estimated, and end-to-end image blind restoration can be realized. The generative network is a full convolutional neural network combined with a residual error network, can deepen a network layer, and shortens the training time. The judgment network is a binary classification network consisting of a convolutional layer, a pooling layer and a full connection layer, and is used for judging the image restored by the generative network or the original clear image. A loss function adopts a least mean square error of smooth and non-saturation gradients, can optimize network training, and avoids gradient disappearance. An image fidelity term is added in the loss function of the generative network and used for constraining distribution of the restored image to be closer to the clear image.

Description

technical field [0001] The invention belongs to the technical field of image processing. Background technique [0002] Blind restoration of blurred images is a basic subject in image processing tasks. Restoring motion blurred images when the blur kernel is unknown is a serious ill-posed problem. In the traditional blind restoration of blurred images, the image and blur kernel are mainly constrained by various prior knowledge, and a strongly constrained image restoration model with generalization ability is established. Accurate blur kernel estimation is the key, and a fast model is required For this reason, these problems have become the bottleneck that affects the practical application of blurred image blind restoration technology for a long time. [0003] Deep learning has the characteristics of automatic feature extraction and powerful computing power, and has become the development direction of blurred image restoration research. Although deep learning can realize the ...

AI Technical Summary

Problems solved by technology

The problem with this type of method is that it is difficult to calculate and the process of tuning parameters is complicated. At the same time, it is still necessary to estimate the blur kernel in most cases.

Recently, some scholars have proposed a full network that does not estimate the fuzzy kernel, but the research is still in its infancy, the designed network is more complex, and the training is unstable

Images