Face feature extraction method and face recognition model training method and device

A face feature and feature extraction technology, applied in the field of image processing, can solve problems such as unfavorable face recognition model application, low face recognition efficiency, and more resource consumption, so as to improve the recognition effect, reduce resource consumption, improve The effect of efficiency

Pending Publication Date: 2022-07-29
SHENZHEN SENSETIME TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method uses all the multiple models corresponding to different scenes. When the model scale is large, it means that the recognition process needs to consume more resources and increase time-consuming, resulting in low efficiency of face recognition, which is not conducive to human recognition. Application of Face Recognition Model in Actual Combat Scenarios

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 extraction method and face recognition model training method and device
  • Face feature extraction method and face recognition model training method and device
  • Face feature extraction method and face recognition model training method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] In order to make those skilled in the art better understand the technical solutions in one or more embodiments of the present disclosure, the following will describe the technical solutions in one or more embodiments of the present disclosure with reference to the accompanying drawings in one or more embodiments of the present disclosure. The technical solutions are clearly and completely described, and obviously, the described embodiments are only a part of the embodiments of the present disclosure, but not all of the embodiments. Based on one or more embodiments of the present disclosure, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present disclosure.

[0036] figure 1 A flow chart of a method for extracting facial features provided by at least one embodiment of the present disclosure is shown. The extraction of the facial features can be, for example, a given facial image,...

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 embodiment of the invention provides a face feature extraction method and device and a face recognition model training method and device. The method comprises the steps that a to-be-recognized face picture and face attribute features corresponding to the face picture are acquired; selecting at least one expert sub-model from a plurality of expert sub-models included in a hybrid expert network as a target sub-model according to the face picture and the face attribute characteristics; and performing feature extraction processing on the face picture through the target sub-model to obtain a face feature corresponding to the face picture. According to the embodiment of the invention, the face recognition effect can be improved, the calculation amount can be reduced, and the recognition efficiency is improved.

Description

technical field [0001] The present disclosure relates to image processing technologies, and in particular, to a method for extracting face features, a method and device for training a face recognition model. Background technique [0002] Face recognition is an important branch of computer vision, and its related technologies have been widely used in the field of security monitoring. The on-site environment of face recognition is often complex and changeable, and there are many challenges in recognition technology. For example, changes in lighting conditions or changes in the camera may cause the captured faces to be blurred, making face recognition more difficult; there are also some faces wearing masks, which also increases the difficulty of face recognition. [0003] In the related art, the recognition effect of the face recognition model can be improved by increasing the model scale. One way to increase the size of the model may be to extract features from multiple mode...

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): G06V40/16G06N3/04G06N3/08
CPCG06N3/08G06N3/042G06N3/045
Inventor 黄德亮朱烽赵瑞
Owner SHENZHEN SENSETIME TECH CO LTD
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