Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Face recognition method and device based on knowledge federation, equipment, medium and system

A face recognition system and face recognition technology, applied in the field of face recognition methods, devices, equipment, media and systems based on knowledge federation, can solve the problem of poor model generalization ability, large differences in data distribution, and face data. Inability to use interoperability and other issues to achieve the effect of protecting data privacy and strong versatility

Inactive Publication Date: 2020-04-21
TONGDUN HLDG CO LTD
View PDF9 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, due to the inconsistent distribution of face data in various fields, such as ID photos of the public security system, face photos in complex scenes in the financial industry, and face photos in natural scenes in the security field, the data distribution is very different. The face recognition model trained on the face data set has poor generalization ability when applied to different application scenarios
For example, the face recognition model trained by the data set in the security field cannot be used in the financial and insurance industry
[0004] The collection of face data in various industries needs to abide by the relevant security regulations of personal information, making the face data collected by each of them unable to be used interoperably. Therefore, how to break the data silos and integrate face data from various fields to train a common face Recognition models to solve cross-industry face recognition problems are imminent

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 recognition method and device based on knowledge federation, equipment, medium and system
  • Face recognition method and device based on knowledge federation, equipment, medium and system
  • Face recognition method and device based on knowledge federation, equipment, medium and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] Embodiment 1 provides a face recognition method based on knowledge federation, which aims to obtain the federated model parameter ciphertext obtained through knowledge federation by sending the face recognition gradient ciphertext to a third-party terminal, and then train face recognition Model, realize face recognition based on the trained face recognition model. This method ensures that the user's original data does not leave the local institution terminal through encryption, and can effectively protect data privacy. The trained face recognition model has strong versatility and is suitable for face recognition in business scenarios in various fields.

[0048] Please refer to figure 1 As shown, a face recognition method based on knowledge federation includes the following steps:

[0049] S110. Acquire a face data set, and initialize a face recognition model according to preset parameters.

[0050] The face data set used by the terminal of the local institution can be...

Embodiment 2

[0072] Embodiment 2 discloses a face recognition device based on knowledge federation corresponding to the above embodiment 1, which is the virtual device structure of the above embodiment, please refer to figure 2 shown, including:

[0073] The data acquisition module 210 is used to acquire a face data set, and initialize a face recognition model according to preset parameters;

[0074] The training encryption module 220 is used to train the face recognition model based on the face data set to obtain a face recognition model gradient; the face recognition model gradient is encrypted to generate a face recognition gradient ciphertext;

[0075] The federated module 230 is configured to send the face recognition gradient ciphertext to a third-party terminal, so that the face recognition gradient ciphertext is decrypted, knowledge federated, and encrypted to obtain federated model parameter ciphertext;

[0076] The face recognition module 240 is used to receive the federated mo...

Embodiment 3

[0078] image 3 A schematic structural diagram of an electronic device provided in Embodiment 3 of the present invention, such as image 3 As shown, the electronic device includes a processor 310, a memory 320, an input device 330, and an output device 340; the number of processors 310 in a computer device may be one or more, image 3 Take a processor 310 as an example; the processor 310, memory 320, input device 330 and output device 340 in the electronic device can be connected by bus or other methods, image 3 Take connection via bus as an example.

[0079] The memory 320, as a computer-readable storage medium, can be used to store software programs, computer-executable programs and modules, such as program instructions / modules corresponding to the face recognition method based on knowledge federation in the embodiment of the present invention (for example, knowledge-based Data acquisition module 210, training encryption module 220, federation module 230 and face recognit...

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 face recognition method based on knowledge federation, and relates to the technical field of computers. The method comprises the following steps: training a face recognitionmodel based on an obtained face data set, generating a face recognition gradient ciphertext through encryption according to an obtained face recognition model gradient, and sending the face recognition gradient ciphertext to a third-party terminal, so that the face recognition gradient ciphertext is subjected to decryption, knowledge federation and encryption to obtain a federation model parameterciphertext; and continuing to train the face recognition model based on the federated model parameters obtained by decryption, and performing face recognition according to the trained face recognition model. According to the method, it is guaranteed that original data do not leave the local, data privacy can be effectively protected, and the face recognition model obtained through federation training is high in universality and suitable for service scenes of mechanism terminals in different fields. The invention further discloses a face recognition device based on knowledge federation, electronic equipment, a storage medium and a system. The scale of the mechanism terminal in the system is not limited, and joining or quitting can be flexibly selected.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a face recognition method, device, equipment, medium and system based on knowledge federation. Background technique [0002] Face recognition technology is widely used in the fields of finance, insurance, retail, security, and public security. Face recognition technology used in various fields has cross-industry requirements. Compare the photo with the ID photo called from the public security system; or when deploying control in the security industry, it is also necessary to compare the face photo captured by the surveillance camera with the ID photo in the public security system. [0003] However, due to the inconsistent distribution of face data in various fields, such as ID photos of the public security system, face photos in complex scenes in the financial industry, and face photos in natural scenes in the security field, the data distribution is very different. Th...

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): G06K9/00G06K9/62
CPCG06V40/16G06F18/214
Inventor 黄小刚李宏宇李晓林
Owner TONGDUN HLDG CO LTD
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
Eureka Blog
Learn More
PatSnap group products