Device to extract biometric feature vector, method to extract biometric feature vector and program to extract biometric feature vector

A feature vector and extraction device technology, applied in the field of biological feature vector extraction programs, can solve the problems of reduced comparison accuracy, variation, and reduced reproducibility of biological feature information, and achieves the effect of improving reproducibility

Active Publication Date: 2015-02-11
FUJITSU LTD
View PDF6 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, biometric information input by the user may vary depending on the input method or environment
Therefore, the reproducibility of

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
  • Device to extract biometric feature vector, method to extract biometric feature vector and program to extract biometric feature vector
  • Device to extract biometric feature vector, method to extract biometric feature vector and program to extract biometric feature vector
  • Device to extract biometric feature vector, method to extract biometric feature vector and program to extract biometric feature vector

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] FIG. 1(a) is a block diagram illustrating the hardware configuration of the living body feature vector extraction device 100 according to the first embodiment. figure 1 (b) is a schematic diagram of a biosensor 105 described later. refer to figure 1 (a), the biological feature vector extraction device 100 includes a CPU 101 , a RAM 102 , a storage device 103 , a display device 104 , a biological sensor 105 and the like. These respective devices are connected via a bus or the like.

[0031] The CPU (Central Processing Unit: Central Processing Unit) 101 is a central processing unit. CPU 101 includes one or more cores. RAM (Random Access Memory: Random Access Memory) 102 is a volatile memory that temporarily stores programs executed by CPU 101 , data processed by CPU 101 , and the like.

[0032] The storage device 103 is a nonvolatile storage device. As the storage device 103 , for example, a solid state drive (SSD) such as a ROM (Read Only Memory) or a flash memory, ...

Embodiment 2

[0049] In Example 1, for N points of interest f n , searching for the feature point with the smallest distance, and determining the small area image according to each feature point, but not limited thereto. In embodiment 2, each small area image is generated based on the brightness center of gravity of the vein image.

[0050] Figure 7 It is a flowchart showing an example of the generation process of the small region image according to this embodiment. refer to Figure 7 Then, the small area image generation unit 11 calculates the luminance center of gravity G(p, q) of the vein image acquired by the biometric sensor 105 (step S21). The center of gravity of luminance can be calculated according to the following formula, for example. i and j represent the coordinates of pixels, and P(i, j) represents the luminance value of each pixel.

[0051] 【Number 1】

[0052] G ( p , q ) =...

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

A device to extract a biometric feature vector includes: an obtain unit that obtains a biometric image; a unit to generate small region images that generates a plurality of small region images from the biometric image; a feature extractor that extracts biometric local feature amounts from the small region images; and a unit to generate a biometric feature vector that generates a biometric feature vector by combining the biometric local feature amounts in accordance with a predetermined rule, the biometric feature vector indicating a feature for identifying the biometric image, wherein the unit to generate small region images generates the plurality of small region images so that variability of biometric information amounts among the plurality of small region images is equal to or less than a predetermined value.

Description

technical field [0001] The invention relates to a living body feature vector extraction device, a living body feature vector extraction method, and a living body feature vector extraction program. Background technique [0002] As a highly reliable identity verification method, authentication using human biometric information such as fingerprints, palm prints, vein patterns, irises, face images, and voices is used. In addition, in the biometric authentication technology, there is an increasing demand for the technique of expressing biometric characteristic information useful for personal identification contained in biometric information as a biometric binary string represented by a binary string of "0" and "1". . By binarizing the biometric feature information, the size of the biometric feature information can be reduced and compared with a simple distance calculation, so that biometric authentication through a low-spec CPU such as an IC card can be realized, and a large amo...

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): G06K9/46G06K9/00G06T7/00
CPCG06K9/00067G06K9/00885G06K9/4619G06V40/1347G06V40/10G06V40/14G06V10/449G06V10/469G06F21/32
Inventor 松涛智明
Owner FUJITSU LTD
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