Face synthesis for forgery detection

Patent metadata

Field	Value
Publication number	US-12505652-B2
Application number	US-202217989169-A
Country	US
Kind code	B2
Filing date	Nov 17, 2022
Priority date	Jul 27, 2020
Publication date	Dec 23, 2025
Grant date	Dec 23, 2025

Abstract

This application relates to a face image processing method, apparatus, computer device, and storage medium. The method includes acquiring a first face image and a second face image, the first face image and the second face image being images of real faces; generating a first updated face image with non-real face image characteristics based on the first face image; adjusting color distribution of the first updated face image according to color distribution of the second face image to obtain a first adjusted face image; acquiring a target face mask of the first face image, the target face mask being generated by randomly deforming a face region of the first face image; and blending the first adjusted face image and the second face image according to the target face mask to obtain a target face image. Accordingly, a diversity of target face images can be generated.

First claim

What is claimed is:

1 . A face image processing method, performed by a computer device, comprising:
acquiring a first face image and a second face image, the first face image and the second face image being images of real faces; generating a first updated face image with non-real face image characteristics based on the first face image; adjusting color distribution of the first updated face image according to color distribution of the second face image to obtain a first adjusted face image; acquiring a target face mask of the first face image, the target face mask being generated by randomly deforming a face region of the first face image; performing face occlusion detection on the second face image to obtain a face occlusion region; adjusting the target face mask according to the face occlusion region to obtain an adjusted face mask; blending the first adjusted face image and the second face image according to the adjusted face mask to obtain a target face image; and training a face detection model using the target face image, the face detection model being used for determining authenticity of a face image, the determining the authenticity of the face image comprising detecting whether the face image is a non-real face image forged through a technical means.

2 . The method according to claim 1 , wherein the generating the first updated face image with the non-real face image characteristics based on the first face image comprises:
calculating weights of pixel points in the first face image by using a Gaussian function to obtain a fuzzy weight matrix of the pixel points; and obtaining fuzzy pixel values of the pixel points according to original pixel values of the pixel points in the first face image and the fuzzy weight matrix of the pixel points, and generating the first updated face image with the non-real face image characteristics based on the fuzzy pixel values of the pixel points.

3 . The method according to claim 1 , wherein generating the first updated face image with the non-real face image characteristics based on the first face image comprises:
acquiring a compression ratio, and compressing the first face image by using the compression ratio to obtain a compressed first face image; and using the compressed first face image as the first updated face image with the non-real face image characteristics.

4 . The method according to claim 1 , wherein the generating the first updated face image with the non-real face image characteristics based on the first face image comprises:
generating a Gaussian noise value, and adding the Gaussian noise value to the pixel values of the first face image to obtain the first updated face image with the non-real face image characteristics.

5 . The method according to claim 1 , wherein the acquiring the target face mask of the first face image, the target face mask being generated by randomly deforming a face region of the first face image comprises:
extracting face keypoints in the first face image, and determining a face region of the first face image according to the face keypoints; and randomly adjusting positions of the face keypoints in the face region of the first face image to obtain a deformed face region, and generating the target face mask according to the deformed face region.

6 . The method according to claim 1 , wherein the adjusting the target face mask according to the face occlusion region to obtain the adjusted face mask comprises:
calculating differences between mask values of pixel points in the target face mask and occlusion values of pixel points in the face occlusion region, and using the differences as mask adjustment values; and obtaining the adjusted face mask according to the mask adjustment values.

7 . The method according to claim 1 , wherein the adjusting the color distribution of the first updated face image according to the color distribution of the second face image to obtain the first adjusted face image comprises:
acquiring a target color adjustment algorithm identification, and calling a target color adjustment algorithm according to the target color adjustment algorithm identification, the target color adjustment algorithm comprising at least one of a color migration algorithm and a color matching algorithm; and adjusting, based on the target color adjustment algorithm, the color distribution of the first updated face image to be consistent with the color distribution of the second face image to obtain the first adjusted face image.

8 . The method according to claim 1 , wherein the blending the first adjusted face image and the second face image according to the target face mask to obtain the target face image comprises:
acquiring a target image blending algorithm identification, and calling a target image blending algorithm according to the target image blending algorithm identification; the target image blending algorithm comprising at least one of an alpha blending algorithm, a Poisson blending algorithm, and a neural network algorithm; and blending, by using the target image blending algorithm, the first adjusted face image and the second face image based on the target face mask to obtain a target face image.

9 . The method according to claim 8 , wherein the blending, by using the target image blending algorithm, the first adjusted face image and the second face image based on the target face mask to obtain the target face image comprises:
determining a first adjusted face region from the first adjusted face image according to the target face mask; and blending the first adjusted face region to a position of the face region in the second face image to obtain the target face image.

10 . The method according to claim 8 , wherein the blending, by using the target image blending algorithm, the first adjusted face image and the second face image based on the target face mask to obtain the target face image comprises:
determining a region of interest from the first adjusted face image according to the target face mask, and calculating a first gradient field of the region of interest and a second gradient field of the second face image; determining a blended gradient field according to the first gradient field and the second gradient field, and calculating a blended divergence field by using the blended gradient field; and determining a second blended pixel value based on the blended gradient field, and obtaining the target face image according to the second blended pixel value.

11 . The method according to claim 1 , wherein the training of the face detection model comprises the following operations:
acquiring a real face image data set and a target face image data set, various target face images in the target face image data set being generated by using different first real face images and second real face images in the real face image data set; using the target face image data set as a current face image data set, using various real face images in the real face image data set as positive sample data, using various current face images in the current face image data set as negative sample data, and performing training by using a deep neural network algorithm to obtain a current face detection model; acquiring test face image data, and testing the current face detection model by using the test face image data to obtain corresponding accuracy of the current face detection model, the test face image data and the real face image data set being different data sets; acquiring an updated target face image data set when the accuracy is less than a preset accuracy threshold, the updated target face image data set comprising various target face images in the target face image

Assignees

• Tencent Tech Shenzhen Co Ltd

Inventors

• Zhang Yong
• Luo Yuchen
• Yan Junchi
• Liu Wei

Classifications

• G06T11/10

  Texturing; Colouring; Generation of textures or colours (retouching, inpainting or scratch removal G06T5/77) · CPC title

• G09G2340/10

  Mixing of images, i.e. displayed pixel being the result of an operation, e.g. adding, on the corresponding input pixels · CPC title

• G09G5/377

  for mixing or overlaying two or more graphic patterns (G09G5/02, G09G5/397 take precedence) · CPC title

• G06T5/50

  using two or more images, e.g. averaging or subtraction · CPC title

• G06T3/18

  Image warping, e.g. rearranging pixels individually · CPC title