Face anti-counterfeiting method based on multi-loss deep fusion

A depth and face technology, which is applied in the field of face anti-counterfeiting technology based on multi-loss deep fusion, can solve the problems of weakening the generalization performance of the algorithm and reducing the accuracy, so as to improve the low generalization performance, enhance the overall fit, and improve The effect of robust performance

Active Publication Date: 2019-10-18
WUHAN UNIV
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the data collection methods, scenes, lighting, and image quality of different data sets are more or less different. When cross-testing data from different data sets, the accuracy often decreases, which weakens the algorithm. generalization performance

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 anti-counterfeiting method based on multi-loss deep fusion
  • Face anti-counterfeiting method based on multi-loss deep fusion
  • Face anti-counterfeiting method based on multi-loss deep fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The present invention will be further described in detail below in conjunction with the embodiments and the accompanying drawings, but the embodiments of the present invention are not limited thereto.

[0039] This embodiment is used to implement training and testing based on the data sets CASIA-FASD and Replay-Attack.

[0040] like figure 1 As shown, this embodiment selectively learns the local detail network based on the LASSO loss, and integrates the multi-scale global features obtained by the ASPP network structure, and compares it with the results of existing algorithms, specifically including the following steps:

[0041] (1) Prepare experimental data. For each piece of video data, image frames are extracted frame by frame. The number of training and testing pictures in the CASIA dataset is 89652 and 130172 respectively, and the training and testing pictures in the Replay-Attack dataset are 91769 and 92113 respectively;

[0042] (2) Get the image category label....

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 face anti-counterfeiting method based on multi-loss depth combination. Local features and micro-texture features are learned by adopting a plurality of local parallel networks. Meanwhile, in order to further reduce noise learning and improve the robust performance of various data sources, local feature sparsity constraints are enhanced based on the grouping LASSO regularization, sparse processing is conducted on learned features, and the effect of selecting the features is achieved. In addition, the features of the ASPP multi-scale global information module are fused to enhance the model integrating degree. Compared with the prior art, the method has the advantages that the generalization ability of the algorithm is considered from the data set difference, and thetest accuracy of the algorithm model among different data sets is improved while the classification accuracy is ensured.

Description

technical field [0001] The invention relates to face anti-counterfeiting technology, in particular to a face anti-counterfeiting technology based on multi-loss deep fusion. Background technique [0002] The widespread application of face recognition technology has aroused people's thinking about its security. As a new identity authentication method, although face identity is convenient and real-time, these characteristics also leave opportunities for malicious attackers. When an attacker uses a photo or video of an authenticated person to impersonate an identity, the system may misidentify and give permission, posing a threat to identity security. Therefore, it is essential to strengthen the reliability of identity recognition by detecting the authenticity of face identity. In the research field of face anti-counterfeiting, most of the existing technologies mainly rely on deep features extracted by deep learning methods for identity discrimination. Differences in represen...

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): G06K9/00G06K9/62G06N3/08
CPCG06N3/084G06V40/168G06V40/172G06V40/40G06F18/214G06F18/253
Inventor 朱荣彭冬梅胡瑞敏杨敏刘斯文赵雅盺
Owner WUHAN UNIV
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