Face image restoration method introducing attention mechanism

Abstract

The invention relates to a face image restoration method introducing an attention mechanism, and the method comprises the steps: (1) obtaining an original data set, carrying out the image preprocessing, obtaining a needed face image data set, and reasonably dividing and arranging the face image data set into a test set and a data set; (2) inputting the training data set into an image restoration model introduced into a context attention layer for training, wherein two parallel encoder networks are introduced into a generator network, one encoder network is used for performing convolution operation to extract advanced feature images, and the other encoder is used for introducing a context attention layer network to realize long-range association between a foreground region and a backgroundregion; and (3) inputting the test data set into the trained face restoration model, and testing the restoration capability of the trained restoration model for the defective face image. According tothe method, after the context attention layer is introduced, the problem that the background region information cannot be fully utilized by the restoration model due to the limited receptive field size of the convolutional neural network is solved, the long-range association of the background information and the foreground region is realized, and the background region information is fully utilizedto fill the foreground region. After the context attention layer is introduced, the restoration model obtains a better restoration effect on some detail textures, and the restoration effect of the face image is also improved on the whole.

Description

technical field [0001] The invention relates to the field of image restoration, in particular to a human face image restoration method introducing an attention mechanism. Background technique [0002] The advent of the information age has made digital image information the main way for people to transmit information to each other. In the process of acquiring, compressing, and transmitting massive image information, it is inevitable that some information will be lost. The information is of great significance in many fields. Traditional image restoration methods can be mainly divided into two categories: structure-based and texture-based. They can achieve better repair results in the case of small-scale information loss, but the repair effect drops sharply when the defect area becomes larger. The emergence of deep learning methods, especially the emergence of generative confrontation networks and deep convolutional neural networks, enables us to achieve better results in imag...

AI Technical Summary

Problems solved by technology

Traditional image restoration methods can be mainly divided into two categories: structure-based and texture-based. They can achieve better repair results in the case of small-scale information loss, but the repair effect drops sharply when the defect area becomes larger.

Images