A method for generating a multi-angle face image based on a generative adversarial network model

Abstract

The invention discloses a method for generating a multi-angle face image based on a generative adversarial network model. The method comprises the steps of obtaining a request for generating a face image with a specified angle based on an original face image, then respectively extracting a contour feature and a five-sense organ feature of the original face image, and finally inputting the specified angle, the contour feature and the five-sense organ feature into a pre-trained generative adversarial network model to obtain a target face image. Visibly, according to the method, the purpose of generating the face image at any specified angle based on the face image is achieved through the pre-trained generative adversarial network model, and the influence of face posture changes on identity recognition is avoided. In addition, the invention further provides a device and equipment for generating the multi-angle face image based on the generative adversarial network model and a computer readable storage medium, and the effects of the device and equipment correspond to the effects of the method.

Description

technical field [0001] The present invention relates to the field of image processing, in particular to a method, apparatus, device and computer-readable storage medium for generating a multi-angle face image based on a generative confrontation network model. Background technique [0002] Face recognition is a kind of biometric identification technology based on human facial feature information. For the input face image or video stream, first determine whether there is a human face, and if there is a human face, further provide the position, size and position information of each main facial organ of each face. Then, based on this information, the identity feature data contained in each face is further extracted and compared with the known faces to identify the identity of each face. [0003] Face recognition is mainly used for identity recognition. However, the technical bottleneck of face recognition is how to deal with the change of face posture, that is, in different ima...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method, device, equipment and computer-readable storage medium for generating multi-angle face images based on a generative confrontation network model, so as to solve the difficulty of identity recognition based on face images due to the increase in face posture changes The problem

Images