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

Quick robust human face matching method

A face image and matching method technology, which is applied in the direction of instruments, character and pattern recognition, computer parts, etc., can solve the problems of limiting the application of deformation models and slow calculation speed

Inactive Publication Date: 2007-06-27
北京海鑫科金高科技股份有限公司
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0068] 2. Calculation speed is slow: From a calculation point of view, general optimization algorithms (such as gradient descent method) need to calculate the gradient of the error function in each iteration step, and finally boil down to calculating the partial derivative of the pixel error at each pixel
[0069] These two shortcomings limit the application of deformable models in practical face matching devices

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
  • Quick robust human face matching method
  • Quick robust human face matching method
  • Quick robust human face matching method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0086] The technical solution of the present invention will be further described below in conjunction with the accompanying drawings.

[0087] Input face image I novel The texture information and shape information implicit in can be used to directly guide the optimization of the corresponding model parameters. However, in the error function (11), the shape and texture parameters are tightly coupled and cannot be directly exploited from I novel Inspirational information obtained from . The practical significance of minimizing the error function (11) is to find the optimal shape (and pose) and texture parameters, so that the face image synthesized by the model is closest to the input face image. From the calculation strategy point of view, this is equivalent to finding the model parameters so that the shape and texture of the input face can be optimally matched by the model at the same time. This is the unique face matching strategy provided by the present invention. Method ...

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

This invention is about a fast and crude match method for the human face figures. It fully takes advantage of the inspiration information concealed in the human face figure input, and uses the random optimization method and crude estimation technology, to design the match system. It not only strengthens the ability of the match system to jump out of the partial minima point in the optimization for the parameters, but also can effectively resist the disadvantageous influence on the human face figure input caused by the change of light, shading, noise and so on. It can effectively restore the figure information being lost or contaminated, and simultaneously the calculation speed is also improved. This own vital and practical significance to problems just as the human face identification.

Description

technical field [0001] The invention relates to a method for analyzing human biological features, in particular to a method for matching human face images based on computer vision technology. Background technique [0002] With the rapid improvement of computer computing power and storage capacity, biometric technology is widely used in the field of identification such as security authentication because of its unique stability, uniqueness and convenience. Compared with the method of using fingerprints, irises and other human biometrics for identification, using face recognition is more friendly and convenient, so face recognition technology stands out and gradually enters the practical field. [0003] Identity verification based on face images can be used in security and attendance, network security, banking, customs border inspection, property management, military security, and computer login systems of government agencies. For example, public security monitoring, prison mo...

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): G06K9/00
Inventor 刘晓春陆乃将张长水
Owner 北京海鑫科金高科技股份有限公司
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