Comparison score fusion method and device for multi-modal biological recognition, medium and equipment

A technology of biometric identification and fusion method, which is applied in the field of comparison score fusion of multi-modal biometric identification, can solve the problems of not being able to achieve good recognition accuracy, and achieve the effect of improved recognition accuracy and high precision

Pending Publication Date: 2021-12-21
BEIJING TECHSHINO TECH +1
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem that the current comparison score fusion method in the prior art cannot achieve good recognition accuracy on bank data sets, the present invention provides a comparison score fusion method, device and medium for multimodal biometric identification And equipment, can achieve higher accuracy on bank and other data sets

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
  • Comparison score fusion method and device for multi-modal biological recognition, medium and equipment
  • Comparison score fusion method and device for multi-modal biological recognition, medium and equipment
  • Comparison score fusion method and device for multi-modal biological recognition, medium and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] An embodiment of the present invention provides a comparison score fusion method for multimodal biometric identification, such as figure 1 As shown, the method includes:

[0058] S100: Obtain comparison scores of multiple biometric features.

[0059] Assuming that there are K kinds of biometrics in the current multimodal biometrics, and each biometric has a corresponding comparison algorithm, then for a comparison, a set of K comparison scores can be obtained through the comparison algorithm {s 1 ,s 2 ,...,s K}, the i-th comparison score s in the set i That is, the comparison score of the i-th biological feature, where i=1,2,...,K. Alignment score fusion is to fuse these K alignment scores into a score s.

[0060] S200: Normalize the comparison score of each biological feature according to several set thresholds, wherein the several thresholds are corresponding comparison thresholds when the FAR of the biological feature on the training set is several specific val...

Embodiment 2

[0126] An embodiment of the present invention provides a comparison score fusion device for multimodal biometric identification, such as image 3 As shown, the device includes:

[0127] The comparison score acquisition module 10 is configured to acquire comparison scores of multiple biological features.

[0128] The normalization module 20 is used to normalize the comparison scores of each biological feature according to several thresholds set, wherein the several thresholds are the corresponding ratios when the FAR of the biological feature on the training set is a number of specific values. against the threshold.

[0129] The fusion module 30 is used to weight and sum the normalized comparison scores according to the weighting coefficients to obtain the fused comparison scores, wherein the weighting coefficient of the comparison scores of each biological feature is based on the The corresponding FRR is calculated when the FAR on the training set is several specific values....

Embodiment 3

[0150] The method described in the above-mentioned embodiment 1 provided by the present invention can implement business logic through a computer program and record it on a storage medium, and the storage medium can be read and executed by a computer to achieve the effect of the solution described in embodiment 1 of this specification. Therefore, the present invention also provides a computer-readable storage medium for fusion of comparison scores for multi-modal biometrics, including a memory for storing processor-executable instructions, and when the instructions are executed by the processor, the multi-modalities including Embodiment 1 can be realized. Steps in an alignment score fusion method for modal biometrics.

[0151] The present invention has the following beneficial effects:

[0152] The present invention obtains the comparison scores of each biological feature, and proposes a new normalization method and a fusion rule of weighted summation: use the corresponding co...

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 comparison score fusion method and device for multi-modal biological recognition, a medium and equipment, and belongs to the field of biological recognition. The method comprises the following steps: acquiring comparison scores of various biological features; normalizing the comparison score of each biological feature according to a plurality of set thresholds, wherein the plurality of thresholds are corresponding comparison thresholds when the FAR of the biological feature on the training set is a plurality of specific values; and performing weighted summation on the normalized comparison score according to a weighting coefficient to obtain a fused comparison score, wherein the weighting coefficient of the comparison score of each biological feature is calculated and obtained according to the corresponding FRR when the FAR of the biological feature on the training set is a plurality of specific values. According to the method and device, high precision can be achieved on data sets of banks and the like.

Description

technical field [0001] The invention relates to the field of biometric identification, in particular to a comparison score fusion method, device, medium and equipment for multimodal biometric identification. Background technique [0002] At present, the biometrics commonly used for identification include face, fingerprint, iris, finger vein, palm print, voice print and gait. Due to the continuous development of technology, a single biometric feature recognition has achieved relatively high accuracy. For example, face recognition has reached an accuracy of 99.8% on the commonly used LFW (Labled Faces in the Wild) test library. However, in practical applications, a single biometric recognition will reduce its accuracy due to some inherent limitations. For example, face recognition will be affected by light, posture, makeup, etc. Pattern recognition will be affected by cold hoarseness and so on. Existing research shows that multimodal biometric identification using complement...

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): G06K9/62G06F21/32
CPCG06F21/32G06F18/25
Inventor 周军孔勇
Owner BEIJING TECHSHINO TECH
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