Face image synthesis method and device and computer readable storage medium

Abstract

The invention relates to an image processing technology, particularly provides a face image synthesis method and device and a storage medium, and aims to solve the problem of how to perform accurate face recognition by using a face image under the condition that the actual age of a person is inconsistent with the age of the person represented by the face image. The method comprises the steps of performing generative adversarial training on a face image synthesis model according to an image training sample, so that a face synthesis image corresponding to a first age generated by the face image synthesis model according to a second face image and a second age is similar to the first face image, and the first age of the first face image is higher than the second age of the second face image; and then generating a face synthesis image corresponding to the expected age by using the trained face image synthesis model. Based on the above implementation mode, the face image consistent with the actual age of the person can be generated according to the face image of the person and the actual age, so that accurate face recognition can be performed by using the face image.

Description

technical field [0001] The present invention relates to the technical field of image processing, and specifically provides a face image synthesis method, device and computer-readable storage medium. Background technique [0002] With the rapid development of face recognition technology, face recognition technology has been widely used in security and other fields for personnel tracking and monitoring. However, in some application scenarios, the backup face image of the monitored person may not be consistent with the actual age of the monitored person, and then it is impossible to use this backup face image to perform accurate face recognition on the monitored person to determine whether Identify the person being monitored. For example, when tracking a monitored person, only the face image of the monitored person when he was 10 years old is stored in the face image database, and the actual age of the monitored person is 30 years old. Performing face recognition on the face ...

AI Technical Summary

Problems solved by technology

However, in some application scenarios, the backup face image of the monitored person may not be consistent with the actual age of the monitored person, and then it is impossible to use this backup face image to perform accurate face recognition on the monitored person to determine whether Identify the person being monitored

For example, when tracking a monitored person, only the face image of the monitored person when he was 10 years old is stored in the face image database, and the actual age of the monitored person is 30 years old. Face recognition of the face image, tracking the monitored person, will produce a huge error, resulting in tracking failure

Images