Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Face picture style conversion method and device, electronic equipment and storage medium

A style conversion and picture technology, applied in the field of face recognition, can solve the problems of low richness of training data, high cost of attack masks, poor accuracy of generalization ability of human face detection model, etc., to ensure security and improve generalization Effects of Power and Accuracy

Pending Publication Date: 2022-06-17
BEIJING XUEZHITU NETWORK TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The attack challenge faced by the existing face recognition system is an open-set problem, that is, there will always be attack masks of new materials or crafts on the market, such as resin masks, plaster masks or silicone hood masks, etc. However, in During the training process of the live face detection model, the cost of m

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Face picture style conversion method and device, electronic equipment and storage medium
  • Face picture style conversion method and device, electronic equipment and storage medium
  • Face picture style conversion method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0060]为了能够更加详尽地了解本公开实施例的特点与技术内容，下面结合附图对本公开实施例的实现进行详细阐述，所附附图仅供参考说明之用，并非用来限定本公开实施例。在以下的技术描述中，为方便解释起见，通过多个细节以提供对所披露实施例的充分理解。然而，在没有这些细节的情况下，一个或多个实施例仍然可以实施。在其它情况下，为简化附图，熟知的结构和装置可以简化展示。

[0061]本公开实施例的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本公开实施例的实施例。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含。

[0062]除非另有说明，术语“多个”表示两个或两个以上。

[0063]本公开实施例中，字符“ / ”表示前后对象是一种“或”的关系。例如，A / B表示：A或B。

[0064]术语“和 / 或”是一种描述对象的关联关系，表示可以存在三种关系。例如，A和 / 或B，表示：A或B，或，A和B这三种关系。

[0065]术语“对应”可以指的是一种关联关系或绑定关系，A与B相对应指的是A与B之间是一种关联关系或绑定关系。

[0066]结合图1所示，生成对抗网络(Generative Adversarial Network，GAN)是通过生成器(Generator)和判别器(Discriminator)不断博弈，进而使生成器学习到数据的分布的神经网络学习模型。在训练过程中，生成器的目标就是尽量生成看起来真实的图片去欺骗判别器。而判别器的目标就是尽量辨别出生成器生成的图片和真实的图片。这样，生成器和判别器构成了一个动态的“博弈过程”，最终双方博弈的结果就是，生成器生成的假样本与真样本几乎没有差别，从而导致判别器不能区分真样本还是假样本，此时生成器和判别器达到了平衡，整个训练过程结束。

[0067]在相关技术中，大量GAN模型，例如Cycle GAN、Big GAN和Style GAN已经被研发应用于从随机噪声输入生成高质量多样化的生成图片。近来研究表明，GAN可以在中间特征和隐层空间有效编码富语义信息。这些理论可以通过改变隐层空间编码，合成具有变化多样特性的图片。

[0068]在相关技术中，人脸识别系统面临诸多安全上的风险，为了应对这一挑战，训练一个人脸活体检...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to the technical field of face recognition, and discloses a face picture style conversion method, which comprises the following steps: constructing a first generator and a second generator based on a Cycle GAN algorithm, so that the first generator realizes picture style conversion from a first style to a second style, the second generator is used for realizing picture style conversion from the second style to the first style; training the first generator and the second generator according to the obtained first face data set and the second face data set, so as to enable the loss value between the first generator and the second generator to converge; and obtaining any attack face picture of a first style or a second style, and realizing picture style conversion of the attack face picture through the first generator or the second generator. The invention further discloses a face picture style conversion device, electronic equipment and a storage medium.

Description

technical field [0001] The present application relates to the technical field of face recognition, for example, to a method and device for style conversion of a face picture, electronic equipment, and a storage medium. Background technique [0002] At present, due to the rapid development of computer science and electronic technology, face recognition is becoming the second largest biometric authentication method in the world after fingerprint recognition in terms of market share. It has been applied in many fields, such as electronic door locks, electronic access control and financial payment and many other fields. At the same time, face recognition systems also face many security risks, such as video attacks, photo attacks, and mask attacks. [0003] In the process of implementing the embodiments of the present disclosure, it is found that at least the following problems exist in related technologies: [0004] The attack challenge faced by the existing face recognition s...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06V40/16G06V10/74G06V10/774G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06N3/045G06F18/22G06F18/214
Inventor 刘星赵晨旭唐大闰
Owner BEIJING XUEZHITU NETWORK TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com