Blind face restoration method and system

Abstract

The invention discloses a blind face restoration method and system, and the method comprises the steps: collecting a blind face data set, evaluating the quality of the blind face data set through theLaplace gradient, and removing blurred and non-face images; enhancing image data for the blind face data set, and randomly distributing to obtain a training set and a test set; constructing an AFFNetnetwork; inputting the images of the training set into an AFFNet network, training the AFFNet network in combination with a reconstruction loss function, a perception loss function, a style loss function and a resistance loss function, and training and optimizing the AFFNet network by using an SGD optimization algorithm to obtain an optimal blind face restoration model; and inputting the image ofthe test set into the optimal blind face restoration model, and carrying out matching and selection to obtain an image with the highest accuracy as a final retrieval result. According to the scheme, the method has the advantages of being simple in logic, accurate, reliable and the like, and has high practical value and promotional value in the technical field of image processing.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a blind face restoration method and system. Background technique [0002] Blind face restoration as described in this paper is to restore low-quality degraded images (noise, artifacts and blurring and their combinations) into clear high-quality images. In recent years, the acquisition and sharing of face images has made great progress. On the one hand, with the development of image acquisition and display technology, more and more high-quality (HQ) visual media have emerged. On the other hand, degraded images and videos are still prevalent due to the diversity of acquisition devices, environment and object motion. Therefore, how to restore clear high-quality images from these degraded images has always been a valuable research topic in the field of computer vision. [0003] High-quality face images play a very important role in applications such as entertainment, surve...

AI Technical Summary

Problems solved by technology

However, due to the lack of direct monitoring information for guiding images, the curve subnetwork is difficult to train and has poor generalization ability;

[0008] Third, the guidance image and the degraded image are usually taken under different lighting conditions, with large background differences;

[0009] Fourth, cascade-based fusion methods are still limited in terms of complementarity between guidance and degraded images

Images