CN114969418A - Distributed face image retrieval platform, method, equipment and storage medium - Google Patents

Distributed face image retrieval platform, method, equipment and storage medium Download PDF

Info

Publication number
CN114969418A
CN114969418A CN202210605355.8A CN202210605355A CN114969418A CN 114969418 A CN114969418 A CN 114969418A CN 202210605355 A CN202210605355 A CN 202210605355A CN 114969418 A CN114969418 A CN 114969418A
Authority
CN
China
Prior art keywords
retrieval
face
distributed
face image
user
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210605355.8A
Other languages
Chinese (zh)
Inventor
朱雄
张腾腾
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Merchants Bank Co Ltd
Original Assignee
China Merchants Bank Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China Merchants Bank Co Ltd filed Critical China Merchants Bank Co Ltd
Priority to CN202210605355.8A priority Critical patent/CN114969418A/en
Publication of CN114969418A publication Critical patent/CN114969418A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2471—Distributed queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/51—Indexing; Data structures therefor; Storage structures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/53—Querying
    • G06F16/532—Query formulation, e.g. graphical querying
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Library & Information Science (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Fuzzy Systems (AREA)
  • Computing Systems (AREA)
  • Processing Or Creating Images (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The application discloses a face image retrieval platform based on a distribution type, a method, equipment and a storage medium, wherein the platform comprises a retrieval service module, a face image storage module, a feature extraction module and a distribution type retrieval engine, the retrieval service module is different from a calling interface of the face image storage module, asynchronous data synchronization is carried out between the retrieval service module and the face image storage module as well as between the distribution type retrieval engine, the face image storage module is used for acquiring face image data, extracting face feature information of the face image data and synchronously updating the face feature information and a user identification label into the distribution type retrieval engine, the retrieval service module is used for calling the feature extraction module to extract a feature value of an image to be retrieved in a face retrieval request and calling the distribution type retrieval engine to inquire the face feature information matched with the feature value when the face retrieval request is received, and obtaining a retrieval result. The method and the device solve the technical problem of low face image retrieval efficiency.

Description

Distributed face image retrieval platform, method, equipment and storage medium
Technical Field
The present application relates to the field of image processing technologies, and in particular, to a distributed face image retrieval platform, method, device, and storage medium.
Background
With the development of image processing and pattern recognition technologies, the application of face recognition and comparison is more and more extensive. For a face retrieval platform, a face picture captured by equipment is generally uploaded to the face retrieval platform, face features are extracted by a face algorithm, and then the face features are compared with the existing faces in a base library to output expected face identity information. However, when a large amount of new user data is put into a database during face recognition by the face retrieval platform, since face feature extraction and storage and face feature value retrieval exist in the same service, both storage and retrieval operations cannot be processed simultaneously, thereby reducing retrieval performance in the face retrieval platform and further resulting in slower face image retrieval efficiency.
Disclosure of Invention
The application mainly aims to provide a distributed face image retrieval platform, a distributed face image retrieval method, distributed face image retrieval equipment and a storage medium, and aims to solve the technical problem that face image retrieval efficiency is low in the prior art.
In order to achieve the above object, the present application further provides a facial image retrieval platform based on a distributed type, where the platform includes a retrieval service module, a facial image storage module, a feature extraction module, and at least one distributed retrieval engine, where a calling interface of the retrieval service module is different from a calling interface of the facial image storage module, and asynchronous data synchronization is performed between the retrieval service module and the facial image storage module and between the distributed retrieval engine, where:
the facial image warehousing module is used for acquiring facial image data of a target user, calling the feature extraction module to extract facial feature information corresponding to the facial image data, and synchronously updating the facial feature information and the user identification label association to the distributed retrieval engine;
and the retrieval service module is used for calling the feature extraction module to extract the feature value of the image to be retrieved in the face retrieval request when the face retrieval request is received, calling a distributed retrieval engine corresponding to the face retrieval request to inquire target face feature information matched with the feature value, and determining a face retrieval result based on the target face feature information.
Optionally, the distributed retrieval engines are separately deployed based on the service channel label.
Optionally, the face image storage module is further configured to acquire user information of a target user, and store the user information and face feature information in a preset face database in an associated manner, where the user information includes user identity information and a user identification tag.
And the retrieval service module is also used for inquiring the user identity information matched with the user identification label in a preset face database based on the user identification label in the face retrieval result.
Optionally, the facial image warehousing module exchanges data with the distributed retrieval engine through a kafka distributed system.
The application provides a face image retrieval method based on distribution, which comprises the following steps:
the application provides a face image retrieval method based on distribution, which comprises the following steps:
acquiring face image data of a target user;
extracting face feature information corresponding to the face image data, and synchronously updating the face feature information and the user identification label association of the target user into the distributed retrieval engine;
when a face retrieval request is received, extracting the features of an image to be retrieved in the face retrieval request to obtain the feature values of the image to be retrieved;
and calling a distributed retrieval engine corresponding to the face retrieval request to query the face feature information matched with the feature value to obtain a face retrieval result.
The step of calling the distributed retrieval engine corresponding to the face retrieval request comprises the following steps:
determining a business channel label corresponding to the face retrieval request;
and calling the distributed retrieval engine corresponding to the business channel label based on the mapping relation between the business channel label and the distributed retrieval engine.
After the step of extracting the face feature information corresponding to the face image data, the method further includes:
acquiring user information of the target user;
and storing the user information and the face feature information in a preset face database in an associated manner, wherein the user information comprises user identity information and a user identification tag.
After the step of querying the face feature information matched with the feature value to obtain a face retrieval result, the method further comprises the following steps:
and inquiring user identity information matched with the user identification label in the face database based on the user identification label in the face retrieval result.
The present application further provides a face image retrieval device based on the distributed type, where the face image retrieval device based on the distributed type is an entity device, and the face image retrieval device based on the distributed type includes: the system comprises a memory, a processor and a distribution-based facial image retrieval program stored on the memory, wherein the distribution-based facial image retrieval program is executed by the processor to realize the steps of the distribution-based facial image retrieval method.
The present application further provides a storage medium, which is a computer-readable storage medium, on which a distribution-based facial image retrieval program is stored, where the distribution-based facial image retrieval program is executed by a processor to implement the steps of the distribution-based facial image retrieval method as described above.
The application provides a face image retrieval platform, a face image storage module, a feature extraction module and at least one distributed retrieval engine based on a distributed mode, wherein the platform comprises a retrieval service module, the face image storage module, the feature extraction module and the at least one distributed retrieval engine, a calling interface of the retrieval service module is different from a calling interface of the face image storage module, asynchronous data synchronization is carried out between the retrieval service module and the face image storage module and between the distributed retrieval engine, and the method comprises the following steps: the facial image warehousing module is used for acquiring facial image data of a target user, calling the feature extraction module to extract facial feature information corresponding to the facial image data, and synchronously updating the facial feature information and the user identification label association to the distributed retrieval engine; the retrieval service module is used for calling the feature extraction module to extract the feature value of an image to be retrieved in the face retrieval request and calling a distributed retrieval engine corresponding to the face retrieval request to inquire target face feature information matched with the feature value and determine a face retrieval result based on the target face feature information when receiving the face retrieval request, so that the retrieval service module and the face image warehousing module are separated into independent modules, the system is ensured not to influence the throughput of normal face retrieval service when executing warehousing of a large amount of face image data, asynchronous data synchronization is carried out between the retrieval service module and the face image warehousing module and the distributed retrieval engine, the coupling among the systems is reduced, and the face image data can be synchronously updated to the distributed retrieval engine when being warehoused, therefore, the distributed deceleration engine is called to carry out retrieval service operation, the concurrency capability of system interaction is improved, and the efficiency of face image retrieval is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious to those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a schematic structural diagram of a distributed face image retrieval platform according to the present application;
fig. 2 is a schematic flowchart of a first embodiment of a distributed face image retrieval method according to the present application;
fig. 3 is a schematic structural diagram of a distributed face image retrieval device based on a hardware operating environment according to an embodiment of the present application.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The embodiment of the application provides a face image retrieval platform based on a distributed mode, and referring to fig. 1, fig. 1 is a schematic structural diagram of the face image retrieval platform based on the distributed mode in the application, the face image retrieval platform based on the distributed mode comprises a retrieval service module, a face image storage module, a feature extraction module, at least one distributed retrieval engine and a gateway, wherein a calling interface of the retrieval service module is different from a calling interface of the face image storage module, so that the retrieval service module and the face image storage module are disassembled into independent modules, normal throughput of face retrieval service is not affected while a large amount of face image data are stored, and the gateway is an external gateway for communicating the platform and application.
Furthermore, asynchronous data synchronization is carried out between the retrieval service module and the face image storage module as well as between the face image storage module and the distributed retrieval engine, coupling among the systems is reduced, data exchange is carried out between the face image storage module and the distributed retrieval engine through a Kafka distributed system, when a large number of users call the face image storage module to store face image data, flow can be cached in the Kafka, the situation that the retrieval engine is down due to sharp increase of the flow is avoided, the situation that the retrieval service module is dragged and collapsed due to slow storage of the retrieval engine is also avoided, and the concurrency capability of system interaction is improved.
Additionally, referring to fig. 1, in order to implement isolation of service data of different services, the distributed search engines in the platform are isolated according to service channels, that is, different applications represent different service channels, and different service channels are configured with corresponding service channel tags, so that an independent distributed search engine is deployed for each service channel, and when one distributed search engine is down, normal operation of services of other service channels is not affected, thereby implementing horizontal capacity expansion of each distributed search engine, and the overall platform system has better scalability in the horizontal and vertical directions to improve platform search performance.
In order to more clearly introduce the working principle of the distributed face image retrieval platform, the embodiment of the present application is described by the following steps S10 to S20.
Step S10, the facial image storage module is used to obtain facial image data of a target user, and call the feature extraction module to extract facial feature information corresponding to the facial image data, and synchronously update the facial feature information and the user identification label association to the distributed retrieval engine;
in this embodiment, referring to fig. 1, the flow sequence corresponding to the labels one, two, three, four, five, six and seven is a flow sequence of inputting face image data, specifically, firstly, face image data of a target user is obtained, and then the feature extraction module is called to extract face feature information corresponding to the face image data through the feature extraction module, where each user has a corresponding unique identification ID (user identification tag in this embodiment), and then the face feature information and the user identification tag are associated and updated to the distributed search engine synchronously, and additionally, the face image inputting module is further configured to obtain user information of the target user and store the user information and the face feature information in a preset face database in an associated manner, where the user information includes user identity information and the user identification tag, therefore, in the retrieval service module, the face database comprises databases such as MySQL and Redis, it needs to be noted that the MySQL database is persistent storage data, the Redis database is a local cache, and since the retrieval in the Redis database is faster than the efficiency in the MySQL database, and the Redis database is easy to lose data, in the application, the data are respectively stored in the MySQL and the Redis databases, so that in the subsequent retrieval process, rapid retrieval can be directly performed in the Redis database, and when the Redis database is lost or the engine is restarted, the query is performed in the MySQL database.
Step S20, the retrieval service module is configured to, when receiving a face retrieval request, invoke the feature extraction module to extract a feature value of an image to be retrieved in the face retrieval request, invoke a distributed retrieval engine corresponding to the face retrieval request to query target face feature information matched with the feature value, and determine a face retrieval result based on the target face feature information.
In this embodiment, referring to fig. 1, the flow sequence corresponding to reference numerals 1, 2, 3, 4, 5, 6, 7, and 8 is a face retrieval flow sequence, specifically, when a retrieval service module receives a face retrieval request, the feature extraction module is called to extract a feature value of an image to be retrieved in the face retrieval request, and then according to a service channel tag in the face retrieval request, a distributed retrieval engine corresponding to the service channel tag is scheduled, so as to query target face feature information matching the feature value, in an implementation manner, a similarity distance between the feature value and each face feature information in the distributed retrieval engine is calculated, and then based on the similarity distance, the target face feature information is determined, and then a user identification tag of a correlation degree of the target face feature information is returned to the retrieval service module, in order to improve the retrieval efficiency, the retrieval service module searches the Redis database for the user identity information corresponding to the user identification tag, so that the user identity information is returned to a front-end application interface of the platform, and in addition, if the Redis database cannot search the user identity information corresponding to the user identification tag, the user identity information corresponding to the user identification tag in the MySQL database is required, so that the user identity information corresponding to the user identification tag can be searched, and when an engine is restarted, the Redis database is emptied, the user identity information corresponding to the user identification tag in the MySQL database is required, so that the user identity information corresponding to the user identification tag can be searched.
According to the scheme, the retrieval service module and the face image storage module are divided into independent modules, the system is guaranteed not to affect the throughput of normal face retrieval service when a large amount of face image data are stored in the storage, asynchronous data synchronization is carried out between the retrieval service module and the face image storage module and between the distributed retrieval engine, the coupling between the systems is reduced, and then the face image data can be synchronously updated to the distributed retrieval engine when being stored in the storage, so that the concurrency capability of system interaction is improved and the face image retrieval efficiency is improved by calling the distributed deceleration engine to carry out retrieval service operation.
Further, referring to fig. 2, an embodiment of the present application provides a method for retrieving a facial image based on a distributed manner, where the method for retrieving a facial image based on a distributed manner further includes:
step A10, acquiring the face image data of a target user;
step A20, extracting face feature information corresponding to the face image data, and synchronously updating the face feature information and the user identification label association of the target user into the distributed retrieval engine;
after the step of extracting the face feature information corresponding to the face image data, the method further includes:
step a1, acquiring the user information of the target user;
step a2, storing the user information and the face feature information in a preset face database in an associated manner, wherein the user information includes user identity information and a user identification tag.
In this embodiment, specifically, the facial image data of the target user is acquired through a facial image warehousing module, where a management user may input a shooting device into the facial image warehousing module on the platform or directly shoot through a shooting device corresponding to the platform to obtain facial image data, and extract user identity information and a user identification tag of the target user, where the user identification tag is used to uniquely identify a user identifier, and further, the facial feature information corresponding to the facial image data is extracted through a feature extraction module, so that the facial feature information and the user identification tag of the target user are associated and synchronously updated to the distributed retrieval engine, and as asynchronous data synchronization is performed between the retrieval service module and the facial image warehousing module and the distributed retrieval engine, the phenomenon of crash and false death of the retrieval service module due to slow data warehousing of the distributed retrieval engine is avoided, and the face feature information, the user identity information and the user identification tag are stored in a preset face database in an associated mode, so that the specific identity information of the user can be inquired based on the face database.
Step A30, when a face retrieval request is received, extracting the features of an image to be retrieved in the face retrieval request to obtain the feature values of the image to be retrieved;
step A40, a distributed retrieval engine corresponding to the face retrieval request is called to query the face feature information matched with the feature value, and a face retrieval result is obtained.
After the step a40, the method further includes:
step A50, based on the user identification label in the face retrieval result, querying the user identity information matched with the user identification label in the face database.
In this embodiment, specifically, when the retrieval service module receives a face retrieval request, the feature extraction module is called to extract a feature value of an image to be retrieved in the face retrieval request, wherein features can be extracted based on a pre-constructed feature extraction model to further determine a service channel label corresponding to the face retrieval request, further, based on a mapping relationship between the service channel label and a distributed retrieval engine, the distributed retrieval engine corresponding to the service channel label is called to query face feature information matching with the feature value to obtain a face retrieval result, for example, an algorithm for calculating distance can be used to compare the feature value of the face image to be retrieved with face feature information in a pre-constructed face database, and face feature information of one or more persons with similarity in a set range in the comparison result is used as target face feature information, and then determining a user identification label associated with the target face feature information, taking the user identification label as the face retrieval result, and further inquiring user identity information matched with the user identification label in the face database based on the user identification label in the face retrieval result, so as to return the user identity information to the front application interface.
It should be further noted that steps a10 to a50 do not indicate an execution sequence, and the retrieval service module and the face image warehousing module are divided into independent modules, and step a10 and step a20 are in an independent parallel operation relationship with a30, a40 and step a50, that is, the face image warehousing and retrieval service can be simultaneously operated, so that the efficiency of face image retrieval is improved.
The embodiment of the application provides a distributed face image retrieval method, namely, face image data of a target user are obtained; extracting face feature information corresponding to the face image data, and synchronously updating the face feature information and the user identification label association of the target user into the distributed retrieval engine; when a face retrieval request is received, extracting a characteristic value of an image to be retrieved in the received face retrieval request; and calling a distributed retrieval engine corresponding to the face retrieval request to inquire the face characteristic information matched with the characteristic value to obtain a face retrieval result, wherein the retrieval service module and the face image warehousing module are split into independent modules, so that the system is ensured not to influence the throughput of normal face retrieval service while executing warehousing of a large amount of face image data, asynchronous data synchronization is carried out between the retrieval service module and the face image warehousing module as well as between the retrieval service module and the distributed retrieval engine, the coupling among the systems is reduced, and when the face image data is warehoused, the face image data is synchronously updated to the distributed retrieval engine, so that the interactive concurrency capability and the retrieval efficiency of the system are improved.
Referring to fig. 3, fig. 3 is a schematic structural diagram of a distributed face image retrieval device based on a hardware operating environment according to an embodiment of the present application.
As shown in fig. 3, the distributed face image retrieval apparatus may include: a processor 1001, such as a CPU, a memory 1005, and a communication bus 1002. The communication bus 1002 is used for realizing connection communication between the processor 1001 and the memory 1005. The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a memory device separate from the processor 1001 described above.
Optionally, the distributed face image retrieval device may further include a rectangular user interface, a network interface, a camera, RF (Radio Frequency) circuits, a sensor, an audio circuit, a WiFi module, and the like. The rectangular user interface may comprise a Display screen (Display), an input sub-module such as a Keyboard (Keyboard), and the optional rectangular user interface may also comprise a standard wired interface, a wireless interface. The network interface may optionally include a standard wired interface, a wireless interface (e.g., WIFI interface).
Those skilled in the art will appreciate that the configuration of the distributed based face image retrieval device shown in fig. 3 does not constitute a limitation of the distributed based face image retrieval device and may include more or less components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 3, a memory 1005, which is a kind of computer storage medium, may include therein an operation platform, a network communication module, and a distribution-based face image retrieval program. The operation platform is a program for managing and controlling hardware and software resources of the distributed facial image retrieval device, and supports the operation of the distributed facial image retrieval program and other software and/or programs. The network communication module is used for realizing communication among the components in the memory 1005 and with other hardware and software in the distributed face image retrieval platform.
In the distributed-based facial image retrieval apparatus shown in fig. 3, the processor 1001 is configured to execute a distributed-based facial image retrieval program stored in the memory 1005, and implement the steps of any one of the above-described distributed-based facial image retrieval methods.
The specific implementation of the distributed face image retrieval device is basically the same as that of the distributed face image retrieval method, and is not described herein again.
In addition, the present application further provides a face image retrieval system based on the distribution type, where the face image retrieval system based on the distribution type includes:
the acquisition module is used for acquiring the face image data of a target user;
the updating module is used for extracting the face feature information corresponding to the face image data and synchronously updating the face feature information and the user identification label association of the target user into the distributed retrieval engine;
the extraction module is used for extracting the features of the image to be retrieved in the face retrieval request when the face retrieval request is received to obtain the feature value of the image to be retrieved;
and the query module is used for calling a distributed retrieval engine corresponding to the face retrieval request to query the face feature information matched with the feature value to obtain a face retrieval result.
Optionally, the distributed face image retrieval system further includes:
determining a business channel label corresponding to the face retrieval request;
and calling the distributed retrieval engine corresponding to the business channel label based on the mapping relation between the business channel label and the distributed retrieval engine.
Optionally, the distributed face image retrieval system further includes:
acquiring user information of the target user;
and storing the user information and the face feature information in a preset face database in an associated manner, wherein the user information comprises user identity information and a user identification tag.
Optionally, the distributed face image retrieval system further includes:
and inquiring user identity information matched with the user identification label in the face database based on the user identification label in the face retrieval result.
The specific implementation of the distributed face image retrieval platform is basically the same as that of the distributed face image retrieval method, and is not described herein again.
The embodiment of the present application provides a storage medium, which is a computer-readable storage medium, and the computer-readable storage medium stores one or more programs, which can be further executed by one or more processors for implementing the steps of any one of the above-mentioned methods for retrieving facial images based on distribution.
The specific implementation manner of the computer-readable storage medium of the present application is substantially the same as that of each embodiment of the above-described distributed face image retrieval method, and is not described herein again.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings, or which are directly or indirectly applied to other related technical fields, are included in the scope of the present application.

Claims (10)

1. A face image retrieval platform based on distribution type comprises a retrieval service module, a face image storage module, a feature extraction module and at least one distributed retrieval engine, wherein the calling interface of the retrieval service module is different from the calling interface of the face image storage module, asynchronous data synchronization is carried out between the retrieval service module and the face image storage module as well as between the distributed retrieval engine, and the steps of:
the facial image warehousing module is used for acquiring facial image data of a target user, calling the feature extraction module to extract facial feature information corresponding to the facial image data, and synchronously updating the facial feature information and the user identification label association to the distributed retrieval engine;
and the retrieval service module is used for calling the feature extraction module to extract the feature value of the image to be retrieved in the face retrieval request when the face retrieval request is received, calling a distributed retrieval engine corresponding to the face retrieval request to inquire target face feature information matched with the feature value, and determining a face retrieval result based on the target face feature information.
2. The distributed human face image retrieval platform based on claim 1, wherein the distributed retrieval engines are separately deployed based on business channel labels.
3. The distributed human face image retrieval platform of claim 1,
the face image storage module is further used for acquiring user information of a target user and storing the user information and face feature information into a preset face database in an associated manner, wherein the user information comprises user identity information and a user identification tag;
and the retrieval service module is also used for inquiring the user identity information matched with the user identification label in a preset face database based on the user identification label in the face retrieval result.
4. The distributed human face image retrieval platform based on claim 1, wherein the human face image warehousing module exchanges data with the distributed retrieval engine through a kafka distributed system.
5. A face image retrieval method based on distribution, which is applied to the face image retrieval platform based on distribution of claims 1 to 4, the face image retrieval method based on distribution comprises:
acquiring face image data of a target user;
extracting face feature information corresponding to the face image data, and synchronously updating the face feature information and the user identification label association of the target user into the distributed retrieval engine;
when a face retrieval request is received, extracting the features of an image to be retrieved in the face retrieval request to obtain the feature values of the image to be retrieved;
and calling a distributed retrieval engine corresponding to the face retrieval request to query the face feature information matched with the feature value to obtain a face retrieval result.
6. The distributed face image retrieval method according to claim 5, wherein the step of calling a distributed retrieval engine corresponding to the face retrieval request comprises:
determining a business channel label corresponding to the face retrieval request;
and calling the distributed retrieval engine corresponding to the business channel label based on the mapping relation between the business channel label and the distributed retrieval engine.
7. The distributed-based facial image retrieval method according to claim 5, further comprising, after the step of extracting facial feature information corresponding to the facial image data:
acquiring user information of the target user;
and storing the user information and the face feature information into a preset face database in an associated manner, wherein the user information comprises user identity information and a user identification tag.
8. The distributed-based face image retrieval method of claim 7, wherein after the step of querying the face feature information matched with the feature value to obtain a face retrieval result, the method further comprises:
and inquiring user identity information matched with the user identification label in the face database based on the user identification label in the face retrieval result.
9. A distribution-based face image retrieval apparatus, characterized in that the distribution-based face image retrieval apparatus comprises: a memory, a processor and a distributed face image retrieval program stored on the memory,
the distributed-based facial image retrieval program is executed by the processor to implement the steps of the distributed-based facial image retrieval method according to any one of claims 5 to 8.
10. A storage medium which is a computer-readable storage medium, wherein the computer-readable storage medium stores thereon a distribution-based facial image retrieval program, and the distribution-based facial image retrieval program is executed by a processor to implement the steps of the distribution-based facial image retrieval method according to any one of claims 5 to 8.
CN202210605355.8A 2022-05-31 2022-05-31 Distributed face image retrieval platform, method, equipment and storage medium Pending CN114969418A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210605355.8A CN114969418A (en) 2022-05-31 2022-05-31 Distributed face image retrieval platform, method, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210605355.8A CN114969418A (en) 2022-05-31 2022-05-31 Distributed face image retrieval platform, method, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN114969418A true CN114969418A (en) 2022-08-30

Family

ID=82957283

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210605355.8A Pending CN114969418A (en) 2022-05-31 2022-05-31 Distributed face image retrieval platform, method, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN114969418A (en)

Similar Documents

Publication Publication Date Title
CN102831405B (en) Method and system for outdoor large-scale object identification on basis of distributed and brute-force matching
CN110046268B (en) High-dimensional space kNN query method based on inverted position sensitive hash index
CN102880854B (en) Distributed processing and Hash mapping-based outdoor massive object identification method and system
CN112052733A (en) Database construction method, face recognition device and electronic equipment
CN111339171A (en) Data query method, device and equipment
WO2023273058A1 (en) Identity identification method, system and apparatus, and computer device and storage medium
CN112286907A (en) Database configuration method and device, electronic equipment and readable storage medium
CN111813744A (en) File searching method, device, equipment and storage medium
CN113590433B (en) Data management method, data management system, and computer-readable storage medium
CN110928900B (en) Multi-table data query method, device, terminal and computer storage medium
CN107968798B (en) Network management resource label obtaining method, cache synchronization method, device and system
CN113674049A (en) Commodity shelf position identification method and system based on picture search and storage medium
CN113626449A (en) Data storage method, data query method and related equipment
CN114969418A (en) Distributed face image retrieval platform, method, equipment and storage medium
CN112333182B (en) File processing method, device, server and storage medium
CN112269894B (en) Article pool generation method, image search method, device, electronic equipment and medium
CN111191612B (en) Video image matching method, device, terminal equipment and readable storage medium
CN111382650B (en) Commodity shopping processing system, method and device and electronic equipment
CN113094530B (en) Image data retrieval method and device, electronic equipment and storage medium
CN114168684B (en) Face modeling warehouse-in service implementation method and device based on asynchronous mechanism
CN111611322A (en) User information correlation method and system
CN114399058B (en) Model updating method, related device, equipment and storage medium
US20190057269A1 (en) Device for selecting and describing points of interest in a sequence of images, for example for the pairing of points of interest
CN117558056B (en) Accompanying relation recognition method and system based on face image
CN112751928B (en) Cross-terminal information interconnection method, device, computer equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination