Unlock instant, AI-driven research and patent intelligence for your innovation.

Multi-scene compatible face recognition method, device, electronic device and storage medium

A face recognition, multi-scene technology, applied in the field of electronic equipment and storage media, multi-scene compatible face recognition, can solve the problems of low recognition accuracy, poor model stability, serious queuing, etc., to achieve recognition accuracy High, high stability, the effect of improving efficiency

Active Publication Date: 2022-07-12
HANGZHOU MOREDIAN TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, a single face recognition model is often not able to cope with a variety of scenarios well. Recognition, if the entrance of some occasions, such as the entrance of the subway station or the entrance of attendance registration, etc., because the person to be recognized needs to make actions to clean up the face covering, it usually leads to serious queues and the passage efficiency of the entrance is too low
[0003] The face recognition technology based on convolutional neural network relies heavily on the data in the training set. Only the model trained under a sufficiently rich data set can cope with a variety of scenarios. However, excessive increase in model parameters The amount will lead to poor stability of the model, and under the premise of not increasing the amount of model parameters too much, the recognition accuracy is very low

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
  • Multi-scene compatible face recognition method, device, electronic device and storage medium
  • Multi-scene compatible face recognition method, device, electronic device and storage medium
  • Multi-scene compatible face recognition method, device, electronic device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application. In addition, it will also be appreciated that while such development efforts may be complex and lengthy, for those of ordinary skill in the art to which the present disclosure pertains, the techniques disclosed in this application Some changes in design, manufacture or production based on the content are only conventional technical means, and it should not be understood that ...

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 present application relates to a multi-scene compatible face recognition method, device, electronic device and storage medium, belonging to the technical field of face recognition. The method includes: acquiring a picture of a face to be recognized; Extract the first feature, the second feature and the third feature from the face picture to be recognized; weight the second feature and the third feature to obtain the fourth feature; combine the fourth feature and the first feature to obtain the combined feature ; Compare the merged feature with the feature of the face image in the base library, and determine the recognition result according to the comparison result. Through the present application, it is possible to accurately and efficiently identify common faces, faces wearing masks, and faces with different skin tones.

Description

technical field [0001] The present application relates to the technical field of face recognition, and in particular, to a face recognition method, apparatus, electronic device and storage medium compatible with multiple scenarios. Background technique [0002] At present, a single face recognition model is often unable to deal with a variety of scenarios well. For example, in a general face recognition scenario, it is necessary to manually remove the occluder (such as a mask) in front of the face in order to accurately identify the face. Recognition, if there are entrances in some occasions, such as subway entrances or attendance registration gates, etc., because the identified person needs to take actions to clear face coverings, it usually leads to serious queues, and the efficiency of the entrance is too low. [0003] The face recognition technology based on convolutional neural network relies heavily on the data in the training set. Only models trained on a sufficiently...

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 Patents(China)
IPC IPC(8): G06V40/16G06V10/56G06V10/774G06V10/82G06K9/62G06N3/04
CPCG06N3/045G06F18/214
Inventor 陈白洁王月平
Owner HANGZHOU MOREDIAN TECH CO LTD