At present,the image is prone to defects during storage or transmission.In order to obtain complete im-age information,this paper put forward a method of repairing defective images based on deep generative model.At first,wavelet linear transformation features were utilized to select an appropriate threshold during the wavelet inverse transformation and remove image noise thus obtaining the initial image.Then,a generative adversarial network in deep generative models was used to enhance the quality of the defective image.Meanwhile,the problem of image restoration was transformed into a pixel-filling problem,thus shortening the distance between the structural part and the damaged area.After that,a preliminary filled result for the defective image was generated.Finally,the PDE finite difference method was adopted to repair the central point of the defective image.At the same time,the artificial restoration meth-od was used to modify the weight of the isophote direction,thus achieving the restoration of the defective image.Ex-perimental results show that the proposed method has good restoration effect and can retain the original image informa-tion to the greatest extent.
关键词
图像修复/小波的线性变换/生成对抗网络/等照度线方向/图像增强
Key words
Image restoration/Linear transformation of wavelet/Generative adversarial network GAN/Isophote direction/Image enhancement
维普
万方数据