Original scientific paper

https://doi.org/10.17559/TV-20210413111850

Image and Graph Restoration Dependent on Generative Adversarial Network Algorithm

Yuanhao Cao ; North China University of Water Resources and Electric Power, Henan, Zhengzhou, 450046, China

Abstract

As a research hotspot in the field of deep learning, image inpainting is of great significance in people's real life. There are various problems in the existing image inpainting algorithms, resulting in the visual inability to meet people's requirements. In view of the defects of the existing image inpainting algorithms, such as low accuracy, poor visual consistency and unstable training, in this paper the missing content is generated by adjusting the available data. For a data set, first analyze the samples in the data set into sample points in the probability distribution, quickly generate a large number of forged images by using the generation countermeasure network, search the code of the closest damaged image, and then infer the missing content through the generation model. Combining the semantic loss function and perceptual loss function, the problem that the gradient is easy to disappear is solved. Experiments show that the algorithm improves the accuracy of image restoration, can generate more realistic repaired images, is suitable for the repair of various types of images, and realizes the realism of photos.

Keywords

Deep Learning; Generative Adversarial Network; Generative Model; Image Restoration; Loss Function

Hrčak ID:

264037

URI

https://hrcak.srce.hr/264037

Publication date:

7.11.2021.

Visits: 1.158 *