Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Encrypted face recognition method based on ciphertext domain

A face recognition and face image technology, applied in character and pattern recognition, instruments, computing, etc., can solve the problem of less research on face recognition methods for encrypted images, and the feature vector of encrypted images can resist routine, geometry, illumination, and occlusion Attack research is also less and other issues, to achieve the effect of strong resistance to conventional attacks and ensure information security

Inactive Publication Date: 2017-08-15
HAINAN UNIVERSITY
View PDF0 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The eigenvector of a face image is the most basic attribute to distinguish a face. At present, there are few studies on face recognition methods of encrypted images based on DFT transform and chaotic map (Logistic Map) in the cloud environment, and the features extracted from encrypted images There are few studies on vectors that are resistant to conventional, geometric, lighting, and occlusion attacks

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
  • Encrypted face recognition method based on ciphertext domain
  • Encrypted face recognition method based on ciphertext domain
  • Encrypted face recognition method based on ciphertext domain

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0112] Below in conjunction with accompanying drawing, the present invention is further described, and emulation platform is Matlab2010a, randomly selects a face image, is recorded as F={F(i, j)|F(i, j)∈[0,255]; 1≤i≤ M,1≤j≤N}, the size of the image is 92x112, see figure 1 , see the encrypted face image figure 2 , expressed as E(i,j), and the corresponding DFT complex coefficient matrix is ​​ED(i,j). Considering robustness and time complexity, we select 4x4=16 DFT complex matrix (here a complex number is regarded as two coefficients of real part and imaginary part), and obtain 32-bit binary sequence as feature vector. The robustness of the feature vector is detected by calculating the normalized correlation coefficient NC (Normalized Cross Correlation).

[0113] Next, we use specific experiments to judge the anti-conventional attack, anti-geometric attack, and anti-light and occlusion capabilities of the feature vector of the face image in the DFT ciphertext domain.

[0114...

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 an encrypted face recognition method based on a ciphertext domain. The encrypted face recognition method belongs to the field of multimedia signal processing. The encrypted face recognition method comprises the steps of: firstly, encrypting face images in a frequency domain by using nature of a Logistic Map; extracting face eigenvectors through performing DTF transform on encrypted images; and performing encryption on a face to be detected in a transform domain, extracting encrypted feature eigenvectors in a DFT transform domain, and carrying out face recognition through calculating similarities among the eigenvectors. The encrypted face recognition method is an encrypted face recognition technology based on the ciphertext domain, and has good resistance to conventional attack, geometric attack, occlusion, lighting and the like attacks.

Description

technical field [0001] The invention relates to an encrypted face recognition method based on a ciphertext domain, belonging to the field of multimedia signal processing. [0002] technical background [0003] As an effective biometric identification technology, face recognition technology has become a research hotspot in the field of image engineering and pattern recognition due to its huge application value and market potential. In recent years, it has been widely used in various fields, such as entertainment and criminal investigation. , access control system, military and so on. [0004] As the network becomes more and more developed, information security and privacy protection have become one of the mainstream topics today. The information is transmitted to a third party for storage, and how to keep the information from being leaked has become the focus of research. At present, most face recognition is retrieved and recognized in the plaintext domain, so how to solve t...

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): G06K9/00G06T1/00
CPCG06T1/005G06V40/171
Inventor 李京兵刘畅韩先花曹春杰
Owner HAINAN UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com