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

A method and a system for face verification based on depth learning

A face verification and deep learning technology, applied in the field of computer vision, can solve the problems of disturbing face verification and discrimination, and the verification results are not accurate enough, and achieve the effect of wide application and accurate detection results.

Inactive Publication Date: 2018-12-14
EVERSEC BEIJING TECH
View PDF7 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the existing face verification technology has a fast verification speed, it is greatly affected by the environment. For example, when the face is blocked by accessories or disturbed by beards, it will interfere with the discrimination of face verification, resulting in inaccurate verification results.

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 and a system for face verification based on depth learning
  • A method and a system for face verification based on depth learning
  • A method and a system for face verification based on depth learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0071] figure 1 It is a schematic flowchart of the face verification method based on deep learning in Embodiment 1 of the present invention. see figure 1 , the present embodiment provides a face verification method based on deep learning, including:

[0072] Constructing a first image set based on multiple first images, and constructing a second image set based on multiple second images; correspondingly training a face detection model according to the first image set, and training a feature extraction model according to the second image set; The image to be detected containing the face is input into the face detection model, and the face image to be verified is extracted; the face image to be verified is processed and corrected by the feature extraction model, and the face feature information in each face image to be verified is extracted; The face feature information calculates the similarity between any two face images to be verified, and obtains the verification results o...

Embodiment 2

[0095] see figure 1 and Figure 4 , the present embodiment provides a face verification system based on deep learning, including a first image acquisition unit 1, a second image acquisition unit 2, a first model training unit 3, a second model training unit 4, and a face image acquisition unit 5, face feature extraction unit 6 and face verification unit 7; the output end of the first image acquisition unit 1 is connected with the input end of the first model training unit 3, and the output end of the second image acquisition unit 2 is connected with the second model training unit The input end of unit 4 is connected, and the output end of the first model training unit 3 and the second model training unit 4 is connected with the input end of human face image acquisition unit 5 respectively, and the output end of human face image acquisition unit 5 is extracted with human face feature The input end of unit 6 is connected, and the output end of face feature extraction unit 6 is ...

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 and a system for face verification based on depth learning, which can accurately detect the face with body hair or accessories, and improve the applicable range and accuracy of face recognition. The method includes constructing a first image set based on a plurality of first images and constructing a second image set based on a plurality of second images; traininga face detection model according to the first image set, and training a feature extraction model according to the second image set; Input the image to be detected containing human face into the face detection model, and extracting the face image to be verified; using the feature extraction model to process and correct the face image to be verified, and extracting the face feature information in each face image to be verified. The similarity of any two face images to be verified is calculated based on the face feature information, and the verification results of the two face images to be verified are obtained. The system comprises the method proposed in the technical proposal.

Description

technical field [0001] The present invention relates to the technical field of computer vision, in particular to a face verification method and system based on deep learning. Background technique [0002] Biometric identification technology is currently the most convenient and safe identification technology. Biometric identification technology identifies the person himself, and does not require markers other than the person. Biometric recognition technology uses human physiological and behavioral characteristics for identification, mainly including fingerprint recognition, face recognition, iris recognition, gait recognition, etc. Among them, face recognition is a hot spot in the field of biometric identification. Compared with the currently widely used fingerprint identification technology, it has significant advantages such as intuition, convenience, non-contact, friendliness, and high user acceptance. [0003] One of the cores of face recognition is face verification. T...

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): G06K9/00G06K9/46G06K9/62
CPCG06V40/161G06V40/168G06V40/172G06V10/464G06F18/22G06F18/214
Inventor 李玉惠陈晓光傅强金红杨满智蔡琳刘长永
Owner EVERSEC BEIJING TECH
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com