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

Face recognition method based on adaptive weighting and local characteristic fusion

An adaptive weighting and local feature technology, applied in the field of image processing, can solve the problems of lower face recognition rate and weak feature identification ability, achieve good recognition effect, improve recognition reliability, and suppress noise interference

Inactive Publication Date: 2017-04-26
SHANDONG UNIV
View PDF2 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The method based on local features in the prior art only extracts a single feature of the image, such as the LBP operator only extracts the texture feature of the image, and the single feature is lacking in the expression of the face image
At the same time, the texture is rich in the image, and the sub-regions with edge changes contain a lot of information. On the contrary, they only contain a small amount of information. The existing technology treats different regions of the face image indiscriminately, which will lead to weak identification of the extracted features and reduce the Face recognition rate

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
  • Face recognition method based on adaptive weighting and local characteristic fusion
  • Face recognition method based on adaptive weighting and local characteristic fusion
  • Face recognition method based on adaptive weighting and local characteristic fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] Such as Figure 1-3 shown.

[0057] A face recognition method based on adaptive weighted local feature fusion, comprising the following steps:

[0058] (1) Divide the selected face database into training samples and test samples;

[0059] (2) Perform geometric clipping and gamma correction preprocessing on the training samples and test samples in sequence;

[0060] (3) the image after the step (2) pretreatment is divided into m equal and non-overlapping sub-blocks of size, calculates the information entropy of each sub-block, obtains the weighting coefficient of each sub-block according to the information entropy; m=3× 3;

[0061] (4) Use the local binary mode to extract the texture features of the preprocessed image in step (2); note that any point in the image is (x, y), in a ring with the pixel point (x, y) as the center and R as the radius There are p sampling points uniformly distributed on the neighborhood, and the pixel gray value g of the pixel point (x, y) ...

Embodiment 2

[0066] The face recognition method based on adaptive weighted local feature fusion as described in Embodiment 1, the difference is that the steps are as follows:

[0067] When processing the image in step (2), first cut the sample geometrically into a picture with a size of 100 pixels × 100 pixels, and use gamma correction to adjust the contrast of the image. The realization formula is as follows:

[0068] I(x,y)=I(x,y) gamma .

[0069] Use gamma correction to adjust the contrast of the image to reduce the impact of illumination changes on the face image and suppress the interference of noise.

Embodiment 3

[0071] The face recognition method based on adaptive weighted local feature fusion described in Embodiment 2, the difference is that the gamma value is 0.5.

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 relates to a face recognition method based on adaptive weighting and local characteristic fusion. The method comprises the main steps of firstly performing blocking on an image, calculating information entropy of each subblock and obtaining a weighting coefficient of the subblock, then extracting a texture characteristic of the image in a local binary pattern, extracting edge information of the image by means of a histogram of gradient, performing adaptively weighted partial characteristic fusion on a sample image, and finally performing classified recognition by means of a nearest neighbor method. According to the face recognition method, robustness of the local texture characteristic and the edge characteristic of the image to image local shadow and illumination change is utilized; a finally output characteristic has relatively high interference resistance and relatively high discriminating capability; and a good recognition effect is realized on the condition of illumination and gesture change.

Description

technical field [0001] The invention relates to a face recognition method based on adaptive weighted local feature fusion, which belongs to the technical field of image processing. Background technique [0002] As a typical pattern recognition problem, face recognition is a hotspot of interdisciplinary research in image processing, machine vision, artificial intelligence, etc. Strong, in line with human cognitive habits and other advantages. Face recognition technology has broad application prospects in public security and economic and financial fields such as access control and anti-theft systems, identity authentication, video surveillance, criminal investigation and law enforcement. In recent years, face recognition technology has developed rapidly. [0003] Although the research on face recognition technology has achieved rich theoretical results, there is still a distance between the existing theoretical methods and practical applications, which cannot meet many situat...

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): G06K9/00G06K9/46G06K9/62
CPCG06V40/171G06V10/247G06V10/467G06V10/40G06V10/462G06F18/24143G06F18/22G06F18/253
Inventor 姜威韩彤炜刘晓芳闫旭
Owner SHANDONG UNIV
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