Design method of distributed face basic information intermediate library service compatible with multiple algorithms

A basic information and design method technology, applied in the field of face basic information intermediate library service, can solve the problem that the face basic information intermediate library service does not have a mature solution, etc., to meet high concurrent data requests and large data volumes the effect of management

Pending Publication Date: 2019-10-15
上海韬安信息技术有限公司 +1
View PDF0 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] To sum up, in China and even in the world, there is not yet a mature solution for the basic face information intermediate library service

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
  • Design method of distributed face basic information intermediate library service compatible with multiple algorithms
  • Design method of distributed face basic information intermediate library service compatible with multiple algorithms
  • Design method of distributed face basic information intermediate library service compatible with multiple algorithms

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] This embodiment describes step S11 in detail, which specifically includes the following steps:

[0059] S111: Create a personnel information database, a personnel photo database and a face feature value database. The personnel information database is used to store the structured basic information of personnel, including the personnel global unique number, name, ID card, gender, personnel photo path, and personnel label . The personnel photo database stores the binary data of personnel photos on the picture server, and the facial feature value database stores the facial feature data extracted by the feature extraction system;

[0060] S112: importing the personnel basic information data and photos into the corresponding database and picture server respectively;

[0061] Among them, step S111 specifically needs to create a face information database and a related table structure (MYSQL database). In addition, the photo database is stored by a file server, and the correspo...

Embodiment 2

[0063] combine figure 2 , 3, 5, present embodiment describes in detail S12, another method of S13, S14, it comprises the following steps:

[0064] S121: Real-time monitoring of data changes in the personnel information database, including changes in personnel structured data and personnel photos;

[0065] S122: Push the changed personnel data (referring to the URL address of the personnel photo) to the feature extraction system for feature extraction operation;

[0066] S131: Receive in real time the personnel feature information pushed by the feature extraction system through the callback interface service, and perform data verification;

[0067] S132: Store the received personnel feature data in the feature value intermediate library, and update the feature extraction task status, including normal, face detection failure, picture download failure and other errors;

[0068] S141: After the feature callback service interface is operated, the received face feature data will ...

Embodiment 3

[0072] combine Figure 6 , another method of S15 is described in detail in this embodiment, which includes the following steps:

[0073] S151: To obtain detailed information and photos of personnel, the face recognition system first needs to call the authentication interface of the security API service, and pass in the application identification and application key provided in advance for authentication;

[0074] S152: Get the token value returned by the authentication, and pass in the person's global unique number and related parameters of the person's characteristic data obtained by the face recognition system;

[0075] S153: After entering the security API interface service, the server will verify the authority of the caller, record the log, and add a series of security operations to the photo watermark;

[0076] S154: finally return the detailed personnel basic information and photo information;

[0077] combine Figure 7 , each face recognition manufacturer wants to ob...

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 design method of a distributed face basic information intermediate library service compatible with multiple algorithms. The most important technology of the method is three-library separation refers to that a personnel basic information library, a personnel photo library and a face feature value library are stored separately, manufacturer and data isolation of the algorithm is realized through the face basic information security API interface. The data security is greatly improved, the data is prevented from being leaked, and all the data are associated together by the global unique number of the personnel. The intermediate library performs data encryption on the sensitive personnel information. A face feature extraction system is built by matching with each facerecognition algorithm manufacturer. The intermediate library feature management service schedules each system to extract face features, process incremental data and synchronously distribute feature data, and a security API interface service for providing face basic information for the face recognition application request. The API interface service realizes the functions of authority access control, sensitive information filtering, data information encryption, three-library separation, interface call limit limitation, interface call multiple authentication mechanism, picture watermarking, log tracing and the like.

Description

technical field [0001] The invention relates to the technical field of data information intermediate database security, in particular to a related design method of a multi-algorithm compatible distributed face basic information intermediate database service. Background technique [0002] At present, face recognition application systems at home and abroad independently maintain information, photos, and face feature databases of various personnel. Face recognition algorithm manufacturers have different face feature extraction algorithms, data structures, storage methods, and comparison algorithms. , the face feature data among various algorithm manufacturers cannot be shared, and the basic face information and personnel photo data lack a complete privacy protection and update mechanism. When using the face recognition algorithm system, it is necessary to input or batch import personnel information and photos into the face recognition system, establish a personnel information d...

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): G06F16/51G06F16/58G06F16/583G06F16/27G06F21/60G06F21/62G06K9/00
CPCG06F16/51G06F16/583G06F16/5866G06F16/27G06F21/602G06F21/6227G06F21/6245G06V40/172G06V40/168
Inventor 江振忠吴金泉浦云柴晓伟毛晓东黄凯
Owner 上海韬安信息技术有限公司
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