Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Face Recognition Method Based on Short Video Training Method

A technology of face recognition and short video, which is applied in the field of face recognition based on short video training method, can solve the problems of reduced verification efficiency, low accuracy, complicated processing procedures, etc., to achieve improved distinction, improved recognition, The effect of improving accuracy

Active Publication Date: 2020-09-22
一石数字技术成都有限公司
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The object of the invention of the present invention is: in view of the above-mentioned existing problems, provide a kind of face recognition method and system based on the short video training method, solve the following problems: 1. Solve the problem of low accuracy based on single template matching recognition; 2. Solve the problem of huge demand for face image sources in building a face model based on the training method; 3. No need to consider the influence of foreign objects on the face; 4. No need to preprocess the collected images, and realize based on natural face images Recognize directly, solve the problem that the extra eigenvalues ​​brought by preprocessing affect the recognition results, and the complicated processing process brought about by preprocessing and reduce the verification efficiency; 5. Avoid the problem of using photos to forge living bodies for face recognition

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 Face Recognition Method Based on Short Video Training Method
  • A Face Recognition Method Based on Short Video Training Method
  • A Face Recognition Method Based on Short Video Training Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0112] All features disclosed in this specification, or all disclosed steps in a method or process, may be combined in any way except mutually exclusive features and / or steps.

[0113] Any feature disclosed in this specification (including any accompanying claims, abstract), unless expressly stated otherwise, may be replaced by other equivalent or alternative features serving a similar purpose. That is, unless expressly stated otherwise, each feature is but one example of a series of equivalent or similar features.

[0114] like figure 1 As shown, this embodiment discloses a face recognition method based on a short video training method, which includes the following steps:

[0115] S001: construct a reference face feature matrix for the face to be searched;

[0116] S100: Obtain a short video containing the target face;

[0117] S200: Identify and track the target face in the short video, and extract several target face pictures; the quality of the extracted target face pic...

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 recognition method based on a short video training method. The method includes: acquiring a short video containing a target face; identifying and tracking the target face in the short video, and extracting several target face pictures; Extracting the feature values ​​of several extracted target face pictures respectively, generating target face feature values ​​corresponding to the target face pictures respectively; combining several groups of target face feature values ​​corresponding to several target face pictures to generate target face features Matrix; compare the target face feature matrix with the preset reference face feature matrix to verify the target face. The present invention realizes accurate face recognition through the method of image feature value extraction without constructing a face model, and realizes fast face matching through rough positioning and fine positioning algorithms. The present invention has high precision identification algorithm and high anti-counterfeiting performance.

Description

technical field [0001] The invention relates to the field of video monitoring, in particular to a face recognition method based on a short video training method. Background technique [0002] The problem of identification is not only a difficult problem that people often encounter in daily life, but also is particularly important in various aspects such as national defense, scientific research, security, intelligent production and so on. As one of the most important branches of identity recognition, face recognition technology has always been a research hotspot in the industry because of its significance in maintaining national security and the safety of people's lives and property, as well as in counter-terrorism and anti-terrorism; With the rapid development of computer technology, the discipline of digital image technology and pattern recognition, the increasing improvement of artificial intelligence technology, the application range of face recognition technology is stil...

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
CPCG06V40/161G06V40/168G06V40/172
Inventor 卢荣新王泽民李珉施国鹏
Owner 一石数字技术成都有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products