Negative sample selection method in biometrics identification and apparatus thereof

A biometric identification and anti-sample technology, applied in the field of pattern recognition, can solve problems such as affecting the identity authentication system and affecting the authentication function of the identity authentication system.

Active Publication Date: 2012-03-21
GUANGDONG VIMICRO
View PDF1 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existence of misunderstanding is the main problem that affects the real practicality of the identity authentication system. Due to misunderstanding, the sam...

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
  • Negative sample selection method in biometrics identification and apparatus thereof
  • Negative sample selection method in biometrics identification and apparatus thereof
  • Negative sample selection method in biometrics identification and apparatus thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] refer to figure 2 , is a flow chart of a method for selecting counter samples in biometric identification according to Embodiment 1 of the present invention.

[0042] Step 201, determining the distribution of existing counter samples in the sample space;

[0043] Classifiers are often used in biometric identification to classify samples. A classifier is a machine learning program whose design goal is to automatically classify given data after learning. It can be used in search engines and various retrieval programs, and it is also widely used in data analysis and prediction. field. The essence of the classifier is a mathematical model. There are currently many branches for different models, including: Bayes (Bayesian) network classifier, decision tree algorithm, clustering algorithm, SVM (Support Vector Machine) algorithm, etc.

[0044] The classifier achieves the purpose of classification through sample training. The samples are divided into positive samples and n...

Embodiment 2

[0069] This embodiment will take face recognition as an example for more detailed description.

[0070] refer to Figure 4 , is a flow chart of a counter-sample selection method for a face authentication system described in Embodiment 2 of the present invention.

[0071] Step 401, counter-sample feature extraction;

[0072] The purpose of feature extraction is to transform sample images (including positive samples and negative samples) from image space to feature space. The mapping from image space to feature space reduces the distance between samples of the same type and increases the distance between samples of different classes. Thereby increasing the separability between samples.

[0073] For face recognition, each face image is a two-dimensional matrix, such as a face image with a width of w and a height of h, which is a point in the w*h dimensional space. Since there is a lot of redundant information and non-identifying information on the human face, if the original i...

Embodiment 3

[0091] refer to Figure 5 , is a structural diagram of a counter-sample selection device in biometric identification according to Embodiment 3 of the present invention.

[0092] The anti-sample selection device mainly includes:

[0093] The negative sample number determination module 52 is used to determine the number N of negative samples to be selected after determining the distribution of existing negative samples in the sample space;

[0094] The negative sample selection module 53 is configured to select the negative sample with the largest dispersion among the N negative samples from the existing negative samples.

[0095]Preferably, the counter-sample selection device may also include:

[0096] The feature extraction module 51 is used to perform feature extraction on positive samples and negative samples to complete the transformation of all samples from image space to feature space; after feature extraction, the distribution of positive samples and negative samples i...

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 provides a negative sample selection method in biometrics identification and an apparatus thereof so as to solve a misrecognition problem in the biometrics identification. The method comprises the following steps: determining distribution of existing negative samples in a sample space; determining a negative sample number N to be selected; selecting the negative sample with the largest dispersion between the N negative samples in the existing negative samples. By using the negative sample selection method based on space dispersion analysis, under the condition of the certain negative sample number, the negative sample which can cover the face space most and most effectively reduce a misrecognition rate can be selected from the existing negative samples. Face authentication system performance can be raised. In addition, the method and the apparatus of the invention are also suitable for other bioinformation identity authentication systems, wherein the other bioinformation comprises: fingerprints, irises and the like.

Description

technical field [0001] The invention relates to the technical field of pattern recognition, in particular to a method and device for selecting counter samples in biological feature recognition. Background technique [0002] Biometric recognition technology is a science that utilizes individual's unique physiological and behavioral characteristics to achieve identity recognition and (or) individual verification purposes, such as recognition of face, fingerprint, palm print, iris, voice, etc. In the biometric identification technology, the recognition technology characterized by human face has developed very rapidly in recent years. [0003] With the development of face recognition technology, face recognition-related application systems are gradually increasing. As an application system related to face recognition technology, face authentication systems have achieved more and more applications in automatic access control, face login, etc. . The face authentication system us...

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): G06K9/62G06K9/66G06K9/00
Inventor 王俊艳黄英
Owner GUANGDONG VIMICRO
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap