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

Face recognition method based on random sampling

A random sampling and face recognition technology, applied to computer components, character and pattern recognition, instruments, etc., can solve problems such as no discriminant information and too small zero space

Inactive Publication Date: 2007-12-19
THE CHINESE UNIVERSITY OF HONG KONG
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Contrary to the Fisher face method, in N-LDA, the overfitting problem occurs when the number of training samples is large, because the null space is too small to contain enough discriminative information

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 random sampling
  • Face recognition method based on random sampling
  • Face recognition method based on random sampling

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] Specific embodiments of the present invention will be described below with reference to the accompanying drawings.

[0057]Although the dimensionality of the image space is high, only part of the space (subspace) includes discriminative information. These subspaces are spanned by eigenvectors corresponding to nonzero eigenvalues ​​in covariance C. The covariance matrix calculated from M training samples has at most M-1 eigenvectors corresponding to non-zero eigenvalues. In the remaining eigenvectors corresponding to zero eigenvalues, all training samples have zero projections and contain no discriminative information. Therefore, the two LDA algorithms in the present invention firstly project the high-dimensional image data to the M-1 dimensional PCA subspace, and then perform random sampling. Of course, it is also possible to directly perform random sampling on the original data without performing PCA processing.

[0058] Random subspace and random sample combination...

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

LDA is a common feature extraction technology used in face recognition. However, it usually meets small sample problem as processing high-dimension face data. Fisher face and null space LDA (N-LDA) are two common methods for dealing with the problem.However, in many states, the LDA classifier exerts over-fit to training set, and discards some useful recognition information. The present invention raises a method which uses combination of random subspace and random sample to repectively improve the different over-fit problems of two LDA classifiers by analyzing the same. The invention builds plural stable Fisher face and N-LDA classifiers by random sampling for proper vector and training sample. The two kinds of complementary type classifiers can be synthesized in fusion manner thereby almost being able to store all recognition information. The method can also be applied on other features to build face recognition system of robustness which integrally concerns shape, vein and Gabor reaction.

Description

technical field [0001] The present invention relates to a feature extraction technology for face recognition, in particular to a face recognition method utilizing random sampling. Background technique [0002] Linear Discriminant Analysis (LDA) is a common feature extraction technique for face recognition. According to Fisher criteria, LDA determines a set of projection vectors that maximizes the between-class scatter matrix and minimizes the intra-class scatter matrix in the projected feature space. Since there are usually only a small number of samples for training for each class of faces, the intra-class scatter matrix of the same class will not be well estimated and may become a singular matrix, so the LDA classifier usually has a bias, and for the training set very sensitive to small changes. [0003] The following briefly describes the principal component analysis (PCA) method and two conventional LDA face recognition methods, namely Fisher face (Fisherface) and the ...

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): G06K9/00
Inventor 汤晓鸥
Owner THE CHINESE UNIVERSITY OF HONG KONG
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com