Supercharge Your Innovation With Domain-Expert AI Agents!

A face recognition method based on Haar feature and eigenface recognition

A Hal feature and face recognition technology, applied in the field of adaptive face recognition, can solve the problems of low anti-noise ability and insufficient reliability

Inactive Publication Date: 2017-11-24
CHINA UNIV OF MINING & TECH (BEIJING)
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the structure of the feature space is easily affected by the irregular samples in the sample, which affects the two links of feature extraction and similarity calculation at the same time, resulting in low noise resistance and insufficient reliability.

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
  • A face recognition method based on Haar feature and eigenface recognition
  • A face recognition method based on Haar feature and eigenface recognition
  • A face recognition method based on Haar feature and eigenface recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The specific structure of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0034] Firstly, the basic flow of the face recognition method based on Haar feature and eigenface recognition is described, and the process is divided into initialization stage, training stage and recognition stage;

[0035] A. Reference figure 1 The initialization phase is described, and the specific steps are as follows:

[0036] (1) collect m 1 A target facial image is used as a positive sample, and m 0 The faces in the standard face library are used as negative samples, and the positive samples and negative samples constitute m training samples, where m=m 1 +m 0 ;

[0037] (2) Use the image size as a template to generate n non-repetitive rectangular filters, and each rectangular filter corresponds to a Haar feature operator h i ,i=1,2,...n, where

[0038] (3) Use each Haar characteristic operator h in turn i Extract the feature...

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 face recognition method based on Haar feature and eigenface recognition. The method constructs a low-dimensional feature space based on Haar feature and principal component analysis technology for feature extraction, and uses classifier technology The establishment of a model improves the idea of ​​linear combination of features in the old method. The essence of the introduction of this classifier is to use a nonlinear model to replace the traditional linear model, thereby greatly improving the accuracy of recognition.

Description

technical field [0001] The invention relates to a face recognition method based on Haar feature and eigenface recognition, in particular to an adaptive face recognition method using a classifier for online training, and belongs to the technical field of image pattern recognition. Background technique [0002] The general process of face recognition is as follows: the system inputs a face image with unidentified identity as the sample to be recognized, and several face images with known identities in the face database as training samples, and outputs the similarity of the sample to be recognized through the algorithm. degree to demonstrate protection of the identity of persons in unidentified facial images. The face recognition method mainly includes two parts: feature extraction and similarity calculation. [0003] The current relatively successful face recognition method is the eigenface method proposed by Viola and Jones in 2001. This method uses Haar features and princip...

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 Patents(China)
IPC IPC(8): G06K9/62G06F9/46
Inventor 霍跃华杜东壁曹洪治
Owner CHINA UNIV OF MINING & TECH (BEIJING)
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com