Unlock instant, AI-driven research and patent intelligence for your innovation.

Model updating method capable of protecting privacy, object identification method, system and device, medium and equipment

A technology for protecting privacy and object recognition, applied in the field of face recognition, it can solve problems such as personal information security threats, leakage, and face data theft, and achieve the effect of reducing personal information security threats and protecting privacy.

Active Publication Date: 2021-07-09
BEIJING REALAI TECH CO LTD
View PDF15 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, as the application of object recognition technology continues to penetrate into people's daily life, the data collected for object recognition will inevitably be misused. For example, the collected face data may be stolen or maliciously leaked, resulting in The security of people's personal information is greatly threatened

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
  • Model updating method capable of protecting privacy, object identification method, system and device, medium and equipment
  • Model updating method capable of protecting privacy, object identification method, system and device, medium and equipment
  • Model updating method capable of protecting privacy, object identification method, system and device, medium and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0276] As an optional implementation, the device may also include:

[0277] The first collection unit is used to collect the original data of the object to be identified through the data collection terminal before the first segmentation unit divides the feature data of the object to be identified into two sub-feature data;

[0278] The first extraction unit is configured to extract the feature data of the object to be identified from the raw data through a feature extractor deployed in the data collection terminal.

[0279] Among them, implementing this embodiment, the original data of the object to be identified can be collected through the data collection terminal, and the feature data of the original data can be extracted through the feature extractor deployed on the data collection terminal, so that the collected raw data can avoid Data transmission, thus avoiding the loss of original data during transmission and improving the security of original data.

[0280] As an opt...

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 embodiment of the invention provides a model updating method capable of protecting privacy, an object identification method, system and device, a medium and equipment. The method comprises the following steps: segmenting feature data of an object to be identified into two pieces of sub-feature data; respectively sending the two sub-feature data to two different storage nodes, wherein the two different storage nodes have a secure multi-party computing capability; providing the two different storage nodes respectively with a first feature library and a second feature library, wherein any feature library stores sub-feature data of an input object, the sub-feature data of the same object stored in different feature libraries are different, and complete feature data can be restored when the sub-feature data of the same object stored in the feature libraries are merged; and based on the first feature library, the second feature library and the two sub-feature data, performing similarity calculation by using a secure multi-party calculation mode to obtain an identification result. The privacy of the object can be protected, and the threat to personal information security is reduced.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of face recognition, and more specifically, embodiments of the present invention relate to a model update method, object recognition method, system, device, medium and equipment that can protect privacy. Background technique [0002] This section is intended to provide a background or context for implementations of the invention that are recited in the claims. The descriptions herein are not admitted to be prior art by inclusion in this section. [0003] Object recognition (especially biometric recognition) technology has developed rapidly and has been used in various fields such as administration, finance, public safety, transportation, etc., and has brought certain convenience to people's lives, such as face recognition, iris Identification, fingerprint recognition, voiceprint recognition or license plate recognition for liveness or identity verification. However, as the application...

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): G06K9/62G06K9/00G06F21/62G06F21/60H04L9/08
CPCG06F21/6245G06F21/602H04L9/0869H04L2209/46G06V10/96G06V10/94G06F18/22G06F18/214
Inventor 不公告发明人
Owner BEIJING REALAI TECH CO LTD