Face image restoration method based on dense expansion convolution self-coding adversarial network

Abstract

The invention discloses a face image restoration method based on a dense expansion convolution self-coding adversarial network. The method comprises the following steps: firstly, preprocessing face public data to obtain a face data set; secondly, constructing a dense expansion convolution self-coding adversarial network; then pre-training a dense expansion convolutional self-encoding generation network by utilizing reconstruction loss, and alternately carrying out the following training steps: (1) training a double-discrimination network by utilizing adversarial loss; (2) training a pre-trained generative network by using joint loss; and then obtaining a trained dense expansion convolution self-encoding generation network, finally inputting the image to be restored into the generation network, and fusing the generation image and the defect image to obtain a final restored image. According to the method, the face image restoration problem of serious semantic information loss and large-area random region loss is solved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a face image restoration method based on a densely expanded convolutional self-encoding confrontation network. Background technique [0002] Image restoration refers to the use of computer technology to automatically estimate the information of the damaged area of ​​the image and fill in the restored image. In the process of image collection, transmission, storage, etc., there will be many reasons to destroy the integrity of the image information, and the face image not only contains the identity information of the person, but also contains a wealth of important information such as the expression and psychological activities of the person. has a wide range of applications. How to effectively repair the damaged face image is particularly important for face recognition. [0003] Existing image inpainting methods can be divided into two categories: learning ty...

AI Technical Summary

Problems solved by technology

The learning-based inpainting method can repair images with missing semantic information by learning a large amount of image data and learning the prior and probability distribution of the data. Issues such as artifacts and poor visual similarity

Images