Unlock instant, AI-driven research and patent intelligence for your innovation.

Facial image recognizing method capable of increasing comparison correct rate

A face image and recognition method technology, which is applied in the field of face image recognition, can solve problems such as performance degradation and imperfect LBP operator, and achieves the effects of convenient reduction, low comparison accuracy rate and accuracy improvement.

Inactive Publication Date: 2016-07-13
CIVIL AVIATION UNIV OF CHINA
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among them, the face recognition algorithm generally adopts the basic local binary pattern (LBP) algorithm. Although this algorithm is very efficient in computing time and can achieve a certain comparison accuracy, for this algorithm, LBP The operator itself is not perfect, especially when the dimensions of the training samples are as high as thousands or even tens of thousands, its performance will drop sharply

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
  • Facial image recognizing method capable of increasing comparison correct rate
  • Facial image recognizing method capable of increasing comparison correct rate
  • Facial image recognizing method capable of increasing comparison correct rate

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The face image recognition method capable of improving the accuracy of comparison provided by the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0024] The human face image recognition method that can improve the comparison accuracy provided by the present invention comprises the following steps carried out in order:

[0025] 1) Convert the two face images to be compared into grayscale images respectively, and then convert each pixel in each grayscale image into an actual grayscale value through the library function of opencv1.0, thus obtaining a Gray value matrix;

[0026] 2) Divide the above gray value matrix evenly into 3×3 blocks to obtain 9 small gray value matrices;

[0027] 3) Take a small gray value matrix, and take out the small blocks of the gray value matrix of 3×3 successively from the first row, thereby obtaining a plurality of small blocks of the gray value matrix of 3×3;

[002...

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

Provided is a facial image recognizing method capable of increasing a comparison correct rate. The method comprises the steps of: adopting a partitioning technology to partition two facial images to be compared; connecting partitioned LBP histograms in series to form a high-dimensional LPB histogram; using a classical principal component analysis (PCA) method to reduce dimensions; and finally using a similarity calculating method to perform similarity comparison. According to the invention, the simplification of the dimensions is more convenient and the experimental result indicates that the accuracy of the characteristic extraction can be improved effectively, and thus the problem that the traditional facial image comparison correct rate is low is solved.

Description

technical field [0001] The invention belongs to the technical field of image recognition, and in particular relates to a face image recognition method capable of improving the comparison accuracy. Background technique [0002] At present, face recognition technology has been used in image search, payment recognition and other fields. The essence is to use biometrics for security authentication, so it has been widely used. Among them, the face recognition algorithm generally adopts the basic local binary pattern (LBP) algorithm. Although this algorithm is very efficient in computing time and can achieve a certain comparison accuracy, for this algorithm, LBP The operator itself is not perfect, especially when the dimensions of the training samples are as high as thousands or even tens of thousands, its performance will drop sharply. Contents of the invention [0003] In order to solve the above problems, the object of the present invention is to provide a face image recogni...

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): G06K9/00G06K9/62
CPCG06V40/16G06F18/22
Inventor 熊育婷薛凯张茹李伟辉晏南根
Owner CIVIL AVIATION UNIV OF CHINA