Face feature code conversion method and device and electronic equipment

A technology of face features and transformation methods, applied in the field of face recognition, can solve the problem that face recognition models cannot be universal, and achieve the effects of enhancing linear separability, reducing information loss, and improving transformation accuracy

Inactive Publication Date: 2021-06-11
成都市威虎科技有限公司
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem that different face recognition models cannot be used universally, and provide a face feature code conversion method and device and electronic equipment

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 feature code conversion method and device and electronic equipment
  • Face feature code conversion method and device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] In order to make the object, technical solution and advantages of the present invention more clear, the present invention will be further described in detail below in conjunction with the examples. The specific embodiments described here are only used to explain the present invention, not to limit the invention.

[0058] At present, for each face image, the feature codes obtained by different face recognition technologies are different, so the application layer of each face recognition device corresponds to a set of feature codes. Modifying the deployment of the application layer greatly reduces convenience and wastes labor costs. To solve this problem, such as figure 2 As shown, the present embodiment provides a method for converting face signatures, comprising the following steps:

[0059] First, build a deep neural network model, such as figure 1 Shown is a schematic diagram of the network structure of the deep neural network model constructed by the present inv...

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 discloses a face feature code conversion method and device and electronic equipment. The method comprises the steps of forming a sample data set in one-to-one correspondence with a source feature code, a target feature code and a face identity identification number; constructing a deep neural network to train a main task and an auxiliary task, dividing the whole network structure into a feature mapping part, a class classification part and an intra-class distance regression part, and finally improving the model performance by optimizing a loss value, wherein the main function of the feature mapping part is to map a source feature code to a high-dimensional feature space and improve linear separability, the category classification part is used for making up for information loss in the feature code conversion process, and the intra-class distance regression part improves the mapping performance of the feature codes by optimizing the distance between the source feature code and the target feature code of the same class through regression.

Description

technical field [0001] The invention relates to the technical field of face recognition, in particular to a face feature code conversion method and device and electronic equipment. Background technique [0002] With the rapid development of artificial intelligence technology, many smart devices have come to people's surroundings, making people's lives convenient everywhere. At the same time, when using devices, there will be a lot of personal information exchanges, so people have begun to pay special attention to their own information security. People's security awareness has promoted the development of identity verification technology, making it a common process in the process of personal information identification, such as face and fingerprint identification used in various applications. [0003] Face recognition technology occupies a very important position in biometric technology because of its advantages of easy collection and non-contact. In recent years, face recogn...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06V40/168G06V10/48G06N3/045G06F18/214
Inventor 桑高丽卢丽闫超胡二建
Owner 成都市威虎科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap