Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Rapid face recognition method with angle resistance and shielding interference

A face recognition and angle technology, applied in the field of biometrics, can solve the problems of unsatisfactory recognition effect and limited ability of face image connotation features, so as to improve the classification level, avoid slow convergence speed and obvious comparison effect Effect

Active Publication Date: 2018-09-07
SOUTH CHINA UNIV OF TECH
View PDF11 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This kind of method has limited ability to extract the connotative features of face images, and its recognition effect is also unsatisfactory.

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
  • Rapid face recognition method with angle resistance and shielding interference
  • Rapid face recognition method with angle resistance and shielding interference
  • Rapid face recognition method with angle resistance and shielding interference

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0045] Such as figure 1 As shown, the main flow of the fast face recognition method for resisting angle and occlusion interference in this embodiment includes the following steps:

[0046] The first step is to obtain the training set, expand, adjust and preprocess the training set.

[0047] Adjust the face training set to ensure that side faces and face pictures wearing glasses account for 10% to 20% of the training set. Random cropping and random flipping are used to expand the data set, and the single-channel pictures in the data set are expanded into three-channel pictures, and the expanded training set is adjusted to a size of 160x160. The method of extending the three-channel image of the single-channel image is to assign the RGB three-channel value of each pixel of the image to the value of the pixel of the single-channel image. The image is standardized, and the standardized processing method is x is the image pixel value, image_x std is the normalized pixel valu...

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 present invention provides a rapid face recognition method with angle resistance and shielding interference. The method comprises the steps of: collecting an image training set through face detection and cutting of faces, performing regulation and extension of the training set, and performing standardization preprocessing; inputting the training set into a constructed neural network for training to store a parameter model; regulating test data to an appropriate size and an appropriate quantity of channels, performing standardization preprocessing of the test data, putting the test data into a prediction network to obtain face image feature vectors, and determining whether two faces belong to the same person or not through calculation of a distance of the face image feature vectors. There is no special requirements for a face shooting angle, the comparison result of images of faces with glasses wearing is obvious, therefore, it is not worry about the influence of side face angles and glasses shielding problems on the face comparison. Besides, the comparison method is simple, gpu is utilized to speed up and improve the calculation performances, and the rapid face recognition method with angle resistance and shielding interference can be applied to a real-time environment.

Description

technical field [0001] The invention belongs to the technical field of biological identification, and relates to a fast face identification method resistant to angle and occlusion interference. Background technique [0002] The development of face recognition technology began to rise in the 1970s, and it is one of the hottest research problems in the field of computer vision so far. In recent years, with the rapid development of modern information technology and people's urgent need for automatic identity verification, biometric technology has developed rapidly in recent years. Modern biometric technology mainly uses the inherent physiological and behavioral characteristics of the human body to identify and identify individuals through the combination of computers and advanced technical means. It mainly includes: fingerprint recognition, retina recognition, iris recognition, vein recognition, gait recognition, face recognition, etc. Among them, face recognition, as the most...

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): G06K9/00G06K9/62G06V10/764G06V10/774
CPCG06V40/16G06V40/168G06V40/172G06F18/22G06F18/24G06F18/214G06N3/04G06N3/063G06N3/082G06V10/454G06V10/82G06V10/764G06V10/774G06N3/048G06N3/08G06T3/4046G06T2207/20081G06T2207/20084G06T2207/20132G06T2207/30201G06V40/161G06F18/2413
Inventor 黄翰刘迪郝志峰
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products