Detail Feature Inpainting of Art Images in Online Educational Videos based on Double Discrimination Network

In order to improve the image detail restoration effect of online education videos and improve the quality of online education images, a method for image detail restoration of online education videos based on dual discriminant networks is proposed. Utilize the grayscale changes in the selected spatial domain to enhance the detailed features of the original video art image, and construct a dual discriminant generative adversarial network model to repair the enhanced image details. Using a U-Net structured generation network to generate images similar to detail regions, and using image detail features as input, the initial image restoration is completed by training the generation network. Improve the authenticity and consistency of output image details through global and local discriminant networks. The experimental results show that this method has a good image enhancement effect in restoring image detail features in online education video art, improving the dynamic range and grayscale contrast of the image, and has a significant effect on image detail repair. The average peak signal-to-noise ratio of this method is 30.108, and the average structural similarity is 0.961, proving that the repair effect of this method is good. The average PSNR of this method under Gaussian noise interference is 29.68, which proves the robustness of this method.