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

A Method of Optimizing Face Recognition Based on Face Attributes

A technology of face recognition and face recognition, which is applied in the field of face recognition, can solve the problem that the attributes of faces cannot be fully supported, and achieve the effect of improving accuracy

Active Publication Date: 2021-11-23
广州市金其利信息科技有限公司
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is to overcome the defects of the prior art and provide a method for optimizing face recognition based on face attributes, which solves the problem that the algorithms of different companies cannot achieve all face recognition for different face attributes Maximum Support Questions

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
  • A Method of Optimizing Face Recognition Based on Face Attributes
  • A Method of Optimizing Face Recognition Based on Face Attributes

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The preferred embodiments of the present invention will be described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described here are only used to illustrate and explain the present invention, and are not intended to limit the present invention.

[0020] Such as Figure 1-Figure 2 As shown, a method for optimizing face recognition based on face attributes includes the following steps:

[0021] Step 1. Before starting face recognition, it is necessary to test the mainstream face recognition algorithms currently on the market. It has been determined how well different algorithms support different face attributes. In this way, a large-scale face database is first established, which contains different attributes of face images, the face library contains faces with different attributes, such as female faces and male faces, and then perform face attribute detection on these face images, and classify the face images...

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 method for optimizing face recognition based on face attributes, and particularly relates to the technical field of face recognition, comprising the following steps: Step 1. Before starting face recognition, it is necessary to recognize the mainstream faces in the current market Algorithms are tested to determine the degree of support of different algorithms for different face attributes. This method of optimizing face recognition based on face attributes is a method of selecting different face recognition algorithms for face recognition according to the classification of face attributes. On the basis of mainstream face recognition algorithms in other markets, it is classified according to face attributes. , and find the recognition algorithm that is most suitable for a certain type of face, so as to maximize the accuracy of face recognition, and solve the current problem of face recognition. The algorithms of various companies cannot do it for different face attributes The question of maximum support.

Description

technical field [0001] The invention relates to the technical field of face recognition, in particular to a method for optimizing face recognition based on face attributes. Background technique [0002] The current face recognition technology is relatively mature, and many manufacturers have developed relatively reliable face recognition algorithms. However, the algorithms of each company are relatively independent, and the models of each algorithm are affected by the training data and training scenarios. Different, the trained AI model has a certain bias. For example, some models are more accurate in recognizing female faces, some models are more accurate in recognizing male faces, some models perform relatively well in scenes with strong light, and some models perform better in scenes with insufficient light, etc. As a result, the algorithms of various companies cannot provide maximum support for different face attributes. Contents of the invention [0003] The technic...

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): G06K9/00
CPCG06V40/172G06V40/161G06V40/168G06V40/45
Inventor 蔡泳鑫周修龙王剑李辉高燕祥
Owner 广州市金其利信息科技有限公司