Cross-age face recognition model training method, cross-age face recognition method and cross-age face recognition device

A model training and age-based technology, applied in the field of artificial intelligence, can solve the problem of low recognition accuracy of cross-age face recognition models, and achieve good recognition effect and improved recognition accuracy

Inactive Publication Date: 2022-03-25
深圳集智数字科技有限公司
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, the embodiments of the present disclosure provide a cross-age face recognition model training method,

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
  • Cross-age face recognition model training method, cross-age face recognition method and cross-age face recognition device
  • Cross-age face recognition model training method, cross-age face recognition method and cross-age face recognition device
  • Cross-age face recognition model training method, cross-age face recognition method and cross-age face recognition device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] In the following description, for the purpose of illustration rather than limitation, specific details such as specific system structures and techniques are presented for a thorough understanding of the embodiments of the present disclosure. It will be apparent, however, to one skilled in the art that the present disclosure may be practiced in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present disclosure with unnecessary detail.

[0033] A cross-age face recognition model training method, cross-age face recognition method and device according to embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0034] figure 1 It is a schematic flowchart of a cross-age face recognition model training method provided by an embodiment of the present disclosure. S...

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 artificial intelligence, and provides a cross-age face recognition model training method, a cross-age face recognition method and a cross-age face recognition device. The method comprises the steps that a training face image set is acquired, and the training face image set at least comprises a first face image and a second face image which belong to the same person at different ages and a third face image of another person; performing feature extraction on the training face image set to obtain a first age feature vector, a second age feature vector and a third age feature vector; calculating an age feature total loss value according to the first, second and third age feature vectors and a standard age feature vector; calculating a cross-age face feature loss value according to the first, second and third age feature vectors; and iteratively updating the basic recognition model according to the age feature total loss value and the cross-age face feature loss value until a preset iteration termination condition is reached, and obtaining a final cross-age face recognition model. The final cross-age face recognition model is good in recognition effect, and the recognition precision is obviously improved.

Description

technical field [0001] The present disclosure relates to the technical field of artificial intelligence, and in particular, to a training method for cross-age face recognition models, a recognition method and a device. Background technique [0002] Whether in the past, present or future, artificial intelligence technology is one of the hot research issues in computer science. Face recognition technology is an important branch of artificial intelligence technology. Among them, in the practical application of face recognition, many scenes of cross-age face recognition are usually involved, for example, face comparison at long intervals (for example, face comparison at intervals of 2 years and 5 years) ), search for trafficked children, etc. Therefore, cross-age face recognition has become one of the research focuses in the field of face recognition. [0003] The existing cross-age face recognition usually trains the robustness of the network by generating more face pictures...

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): G06V40/16G06K9/62G06N3/04G06N3/08G06V10/774G06V10/764G06V10/82
CPCG06N3/08G06N3/045G06F18/241G06F18/214
Inventor 黄泽元
Owner 深圳集智数字科技有限公司
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