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

A multi-intelligent terminal shared face secret recognition method based on cloud environment

A recognition method and multi-intelligence technology, applied in the fields of cryptography and computer vision, can solve the problem that cryptographic tools are not efficient, and achieve the effect of protection security, simple process structure, and easy implementation.

Active Publication Date: 2019-05-24
韶鼎人工智能科技有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Recently, many researchers have focused on privacy-preserving computer vision problems, most of them using cryptography tools that are not efficient

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
  • A multi-intelligent terminal shared face secret recognition method based on cloud environment
  • A multi-intelligent terminal shared face secret recognition method based on cloud environment
  • A multi-intelligent terminal shared face secret recognition method based on cloud environment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0043] A face detector has a strong classifier of the form:

[0044]

[0045] h n (x) is a threshold function of the type

[0046]

[0047] Among them, y n ∈F L is the threshold function h n (x) hyperplane. h n (x) parameter α n ∈F,β n ∈ F, θ n ∈F is determined during training; N is the number of weak classifiers, n∈(0,N-1).

[0048] The stealth inner product algorithm is described by formula (3), formula (4) and formula (5):

[0049] For the vector set Y=y 1 ,...y n , the third party converts each vector y i , i∈(1,n), decomposed into two vectors {y′ according to the following principle i ,y″ i}: for each y i,j ∈y i , if s j ∈S,s j =1, then y' i,j =y" i,j =y i,j ;otherwise, Among them, r∈R is a random number. Then, use (M 1 , M 2 ) encrypt {y′ i ,y′ A}for The output is:

[0050]

[0051] Among...

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 cloud-based multi-smart terminal shared face concealment recognition method proposed by the present invention can be performed under a safe protocol, and at the same time can simultaneously protect the privacy of user image data and the privacy of a third-party face detector. The present invention applies the secure inner product algorithm to secure face detection in the cloud environment for the first time, which not only realizes the ciphertext storage of user images, but also provides the function of querying the required images in the ciphertext state, and also ensures that third parties The face detector is not leaked. In addition, since the form of user image storage is encrypted with a standard encryption algorithm, the reliability of data security can be guaranteed, and the secure inner product algorithm is used for each query, and the complexity of the algorithm is related to the selected encryption matrix dimension. The complexity is low and can be flexibly configured according to computing power and security requirements. The amount of local calculation is small, and a large number of calculations are processed by the cloud with powerful computing power, which effectively shortens the detection time. And the encryption method is easy to realize by software, and the present invention can be widely applied to cloud computing, face recognition and the like.

Description

technical field [0001] The invention belongs to the fields of cryptography and computer vision, in particular to a method for concealed face detection and recognition, in particular to a cloud environment-based multi-smart terminal shared face concealed recognition method. Background technique [0002] In the era of mobile Internet, a surge of mobile users backs up their photos to cloud servers. When a huge number of images are stored on the cloud server, the privacy of users becomes an issue that cannot be ignored, for example, the face information of family members, the possible relationship between people, the geographic location where the photo was taken, home address, work unit, school, etc. etc. will be exposed to unknown dangerous people, threatening personal and property safety. So images should be stored in ciphertext rather than plaintext. At the same time, the face detector used in the face image retrieval service provided by the cloud server is also provided by...

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 Patents(China)
IPC IPC(8): G06K9/00G06F21/60G06K9/62
CPCG06F21/602G06V40/161G06F18/22
Inventor 金鑫马铭鑫宋承根赵耿李晓东袁鹏田玉露刘妍
Owner 韶鼎人工智能科技有限公司
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