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

High-detection-precision face recognition method

A technology with high detection accuracy and face recognition, applied in the field of face recognition, it can solve the problems of low detection accuracy and few parameters returned in the detection result, and achieve the effect of high recognition accuracy, fast recognition speed and advanced technology.

Inactive Publication Date: 2020-03-27
湖北讯獒信息工程有限公司
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existing face recognition technology has the following problems: (1) low detection accuracy; (2) few parameters in the detection return result, etc.

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
  • High-detection-precision face recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] Such as figure 1 As shown, a face recognition method with high detection accuracy includes:

[0041] S1, image acquisition, using a high-definition camera to complete image acquisition;

[0042] S2, portrait detection and positioning, using OpenCV to complete the positioning and detection of the face in the image acquisition of step S1; in the step, including blur correction processing, by extracting feature point position markers, and using the distance between the eyebrow position and the feature point used as the posture feature again detection positioning;

[0043] S3, feature extraction, use one or more of boost, mlp, knearest, nbayes, svm, rtrees machine learning algorithms to complete feature extraction and modeling on the cloud platform, and finally perform model comparison to complete face recognition.

[0044] In this embodiment, the face recognition solution completes image acquisition through a high-definition camera, uses OpenCV to complete face positioni...

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 high-detection-precision face recognition method, and the method comprises the steps: S1, image collection: employing a high-definition camera to complete the image collection; s2, portrait detection and positioning: positioning and detecting the human face in the image acquisition in the step S1 by using OpenCV, wherein in the step, fuzzy correction processing is included, feature point position marks are extracted, and the distance between the eyebrow center position and the used feature points is used as posture features for re-detection and re-positioning; and S3,feature extraction: completing feature extraction and modeling on the cloud platform by using one or more of boost, mlp, knearest, nbays, svm and rtrees machine learning algorithms, and finally performing model comparison to complete face recognition. The method has the advantages of being high in recognition speed, high in recognition accuracy, advanced in technology, good in system expansibility and the like.

Description

technical field [0001] The invention relates to the technical field of face recognition, and more specifically, to a face recognition method with high detection accuracy. Background technique [0002] Face recognition is a biometric technology for identification based on human facial feature information. In addition to the two major fields of security and finance, face recognition has been widely used in transportation, education, medical care, police, e-commerce and many other scenarios, and has shown significant application value. Face recognition is the collection of human facial features and information. For the displayed facial image, first detect whether there is a human face in the shooting lens. Coordinates, shape and other information. After the processor extracts the information, it compares it to known facial features to identify the user. It includes three main contents: face detection, face tracking, and face comparison. The existing face recognition technol...

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 Applications(China)
IPC IPC(8): G06K9/00G06N3/04
CPCG06V40/161G06V40/168G06V40/178G06N3/045
Inventor 王孝元
Owner 湖北讯獒信息工程有限公司
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

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