Multi-modal score fusion method and device, computer readable storage medium and equipment

A fusion method and multi-modal technology, applied in the field of biometrics, can solve the problem that the multi-modal comparison score fusion method cannot give full play to different modalities, and achieve good recognition accuracy

Pending Publication Date: 2022-04-15
BEIJING TECHSHINO TECH +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the technical problem that the multi-modal comparison score fusion method in the prior art cannot give full play to the advantages of different modes and achieve good recognition accuracy, the present invention provides a multi-modal score fusion method, device, and computer-readable Storage media and equipment, the present invention can give full play to the advantages of different modalities and achieve good recognition accuracy

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
  • Multi-modal score fusion method and device, computer readable storage medium and equipment
  • Multi-modal score fusion method and device, computer readable storage medium and equipment
  • Multi-modal score fusion method and device, computer readable storage medium and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0106] The embodiment of the present invention provides a multimodal score fusion method, such as figure 1 As shown, the method includes:

[0107] S100: Obtain the first modal comparison score and the second modal comparison score, and use LFAR transformation to normalize the first modal comparison score and the second modal comparison score.

[0108] When performing multimodal recognition, it is first necessary to obtain the comparison scores of the two modalities, and use LFAR transformation to perform normalized alignment. The types of the first and second modalities are not limited. For example:

[0109] The first modal comparison score is the face comparison score, and the second modal comparison score is the iris comparison score;

[0110] Alternatively, the first modal comparison score is a fingerprint comparison score, and the second modal comparison score is a finger vein comparison score;

[0111] Alternatively, the first modal comparison score is the iris comparis...

Embodiment 2

[0162] An embodiment of the present invention provides a multimodal score fusion device, such as image 3 As shown, the device includes:

[0163] The comparison score acquisition module 10 is used to obtain the first modal comparison score and the second modal comparison score, and use LFAR transformation to normalize the first modal comparison score and the second modal comparison score .

[0164] The first mapping module 20 is configured to combine the normalized first modality comparison score and the second modality comparison score into score pairs, and perform polynomial kernel mapping on the score pairs to obtain high-dimensional data.

[0165] The fusion module 30 is used for inputting the high-dimensional data into the trained logistic regression model to obtain the fused comparison score.

[0166] Among them, such as Figure 4 As shown, the logistic regression model is trained by the following modules:

[0167] The training set construction module 10' is used to ...

Embodiment 3

[0208] The method described in the above-mentioned embodiment 1 provided in this specification 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 multimodal score fusion, including a memory for storing processor-executable instructions. When the instructions are executed by the processor, the multimodal score fusion method comprising Embodiment 1 is realized. A step of.

[0209] The present invention first normalizes and aligns the multimodal comparison scores, then uses polynomial kernel mapping to perform high-dimensional mapping on the multimodal comparison scores, and finally adopts a logistic regression algorithm to model the mapped scores, and passes the loss function Computes optimal parameters for a...

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 multi-modal score fusion method and device, a computer readable storage medium and equipment, and belongs to the field of biological recognition. The method comprises the following steps: acquiring a first modal comparison score and a second modal comparison score, and normalizing the first modal comparison score and the second modal comparison score by using LFAR transformation; forming a score pair by the normalized first modal comparison score and the normalized second modal comparison score, and performing polynomial kernel mapping on the score pair to obtain high-dimensional data; and inputting the high-dimensional data into the trained logistic regression model to obtain a fused comparison score. The method can give full play to the advantages of different modes, and achieves good recognition precision.

Description

technical field [0001] The invention relates to the field of biometric identification, in particular to a multimodal score fusion method, device, computer-readable storage medium and equipment. Background technique [0002] With the large-scale application of deep learning in the field of biometric recognition, the accuracy of face recognition, iris recognition and other image recognition-based tasks has been significantly improved. However, different biometric features have different advantages and disadvantages. For example, face recognition has a good non-contact experience and a high accuracy rate, but it is easy to be attacked by prostheses. Iris recognition has a high recognition rate and is not easy to falsify, but it has strict environmental requirements for image acquisition quality, and the recognition rate of blurred images is very low. Fingerprint identification is the most popular biometric identification method, but the identification rate is not very high and...

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): G06V40/10G06K9/62G06V10/80G06V10/774
Inventor 周军丁松王洋江武明
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