Face image aging synthesis method based on feature separation adversarial network

Abstract

The invention discloses a face image aging synthesis method based on a feature separation adversarial network, belongs to the technical field of computer vision, and relates to a face image aging synthesis method. The method comprises the steps: supposing that the age features of a face are distributed in a Manifold, extracting the hidden features of an original image through an Auto-encoder, adding a corresponding age condition, finally generating an adversarial network through the condition, synthesizing a face image of a specific age, and maintaining the identity corresponding to an original face image. The innovativeness of the invention lies in that the method achieves the constraint of the hidden features outputted by an Encoder through the intra-class distance measure, enables the hidden features to be exclusively correlated with the identity, and removes the information correlated with the age, so as to guarantee that the age of the generated image is matched with a target agein a better way after the age is added. The method can be used for the face image aging synthesis, the cross-age face recognition and beatifying software.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and relates to a face image aging synthesis method. Background technique [0002] The task of face image aging synthesis is to synthesize images of different age groups on the basis of retaining the identity characteristics of the original face image. With the development of computer vision technology, face aging synthesis algorithms have a wide range of needs and applications in many aspects, such as cross-age face recognition, Meitu software, etc. Therefore, many scholars have devoted themselves to the research in this field. Due to the influence of factors such as expression, light intensity, and posture in face images, the existing face aging algorithms have the defect of insufficient robustness, so face aging has great research value. The existing face aging algorithms are mainly divided into physical model-based methods and prototype-based methods. [0003] (1) Methods based on p...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the problem that the existing face aging synthesis method is easily disturbed by factors such as background, illumination, and facial decorations, resulting in a decrease in the authenticity of the synthesized image, the present invention provides a feature separation method based on the intra-class sample distance measurement, which combines hidden variables Information filtering irrelevant to identity characteristics

Images