CN110097007A - A kind of method and device for integrating a variety of face recognition engines - Google Patents
A kind of method and device for integrating a variety of face recognition engines Download PDFInfo
- Publication number
- CN110097007A CN110097007A CN201910362732.8A CN201910362732A CN110097007A CN 110097007 A CN110097007 A CN 110097007A CN 201910362732 A CN201910362732 A CN 201910362732A CN 110097007 A CN110097007 A CN 110097007A
- Authority
- CN
- China
- Prior art keywords
- face
- message
- picture
- data
- multi engine
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000012545 processing Methods 0.000 claims description 8
- 238000012546 transfer Methods 0.000 claims description 6
- 239000013589 supplement Substances 0.000 abstract description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 238000003032 molecular docking Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 239000000047 product Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/94—Hardware or software architectures specially adapted for image or video understanding
- G06V10/95—Hardware or software architectures specially adapted for image or video understanding structured as a network, e.g. client-server architectures
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of method for integrating a variety of face recognition engines, receives shooting record from the candid photograph equipment of front end by face picture transport gateway, and receive identity information from external system or storage pool;Picture stream is uniformly saved in picture cloud storage by face picture transport gateway, is sent data flow in a manner of message at face multi engine data access center and is stored;Resource data is distributed to specified recognition of face producer and handled by face multi engine data access center;Meanwhile the face Applied layer interface unified by the service opening of face multi engine unified interface, so that each face multi engine application platform is called.The present invention also provides devices corresponding to a kind of method.The invention has the advantages that: it can be managed collectively, be dispatched the work of each face identification system, realize the mutual supplement with each other's advantages of different engines, avoid resource data from repeating to store, promote the deployment efficiency of application platform.
Description
Technical field
The present invention relates to field of face identification, in particular to a kind of method and device for integrating a variety of face recognition engines.
Background technique
Recognition of face is a kind of biological identification technology for carrying out identification based on facial feature information of people.It there is now more
General-purpose interface is opened come more recognition of face service providers (hereinafter referred to as face producer), social unit is applied in selection
When face producer interface, the form for mostly showing respectively to dispose, individually, not interacting mutually causes face recognition engine to dock framework
The case where mode is relatively easy, and there are many restrictions, specific as follows:
One, the docking of face engine is without unified standard, and there is respective a set of interface standard in each face producer, and application platform is wanted
It adapts to face producer to develop, it is primary to access a set of new docking of just needs.
Two, human face data transmission mode is divided into video flowing, two class of picture stream, if video flowing is directly accessed by face producer
Monitoring point RTSP stream, and constructs video image capture, analysis, storage service, then, monitor point device and face identification system it
Between just need the docking number of N*N.Meanwhile analyzing gained picture and being stored respectively by each face identification system, nothing between each system
Method is mutually shared, wastes memory space.
The characteristics of in view of the access of face multi engine or more, limits, and builds a set of face multi engine dispatching platform with unified
It manages, dispatch the problem that each face identification system is urgent need to resolve.
Summary of the invention
The technical problem to be solved in the present invention is to provide a kind of method and device for integrating a variety of face recognition engines,
To realize the mutual supplement with each other's advantages of different faces identification engine, avoids picture from repeating to store, promote the deployment efficiency of application platform.
The present invention is implemented as follows: a kind of method for integrating a variety of face recognition engines, the method includes walking as follows
It is rapid:
Step S1, shooting record is received from the candid photograph equipment of front end by face picture transport gateway, and from outside
Identity information is received in system or storage pool;
Step S2, picture stream is uniformly saved in picture cloud storage by face picture transport gateway, by data flow with message
Mode is sent to face multi engine data access center and is stored;
Step S3, resource data is distributed at specified recognition of face producer by face multi engine data access center
Reason;Meanwhile the face Applied layer interface unified by the service opening of face multi engine unified interface, so that each face draws more
Application platform is held up to be called.
Further, the step S1 specifically:
A plurality of clusters are disposed using distributed strategy, a face picture transport gateway is respectively provided in each cluster;Respectively
Face picture transport gateway receives shooting record all in accordance with cluster locating for itself from the candid photograph equipment of front end, and is from outside
Identity information is received in system or storage pool.
Further, in the step S1, include device id in the shooting record, capture the time and capture figure
Piece;The identity information includes portrait library ID, name, identification card number, gender or certificate photo.
Further, in the step S2, the message collection received is deposited at face multi engine data access center
In message-oriented middleware, it includes transport gateway access message that received message, which is concentrated, equipment access message, captures data message, body
Part infomational message, heartbeat message or other increased service messages on demand.
Further, the step S3 is specifically included:
Step S31, face picture transport gateway and the candid photograph of access are configured in face multi engine data access center
Equipment, and configured candid photograph equipment is bound with corresponding recognition of face producer;
Step S32, resource data is distributed to corresponding face according to binding relationship by face multi engine data access center
Identify producer;Recognition of face producer is total to after receiving resource data by the picture cloud storage address for including in message
Access is enjoyed, and picture stream is handled with respective face recognition algorithms;
Step S33, by face multi engine unified interface service come the Applied layer interface of unified all recognition of face producers
Standard, and the face Applied layer interface for opening to the outside world unified, so that each face multi engine application platform is called.
The present invention is implemented as follows: a kind of device for integrating a variety of face recognition engines, described device includes that data obtain
Modulus block, data memory module and interface unified modules;
The data acquisition module, for receiving shooting note from the candid photograph equipment of front end by face picture transport gateway
Record, and identity information is received from external system or storage pool;
Picture stream is uniformly saved in picture cloud storage for face picture transport gateway by the data memory module, will
Data flow is sent to face multi engine data access center in a manner of message and is stored;
Resource data is distributed to specified face for face multi engine data access center by the interface unified modules
Identification producer is handled;Meanwhile the face Applied layer interface unified by the service opening of face multi engine unified interface,
So that each face multi engine application platform is called.
Further, the data acquisition module specifically:
A plurality of clusters are disposed using distributed strategy, a face picture transport gateway is respectively provided in each cluster;Respectively
Face picture transport gateway receives shooting record all in accordance with cluster locating for itself from the candid photograph equipment of front end, and is from outside
Identity information is received in system or storage pool.
Further, in the data acquisition module, include device id in the shooting record, capture the time and grab
Clap picture;The identity information includes portrait library ID, name, identification card number, gender or certificate photo.
Further, in the data memory module, message collection that face multi engine data access center will receive
It deposits in message-oriented middleware, it includes transport gateway access message that received message, which is concentrated, equipment access message, captures datagram
Text, identity information message, heartbeat message or other increased service messages on demand.
Further, the interface unified modules specifically include binding unit, processing unit and interface Unified Element;
The binding unit, for configuring the face picture transport gateway of access in face multi engine data access center
And equipment is captured, and configured candid photograph equipment is bound with corresponding recognition of face producer;
Resource data is distributed to pair by the processing unit for face multi engine data access center according to binding relationship
The recognition of face producer answered;Recognition of face producer is after receiving resource data, by the picture cloud storage that includes in message
Location carries out share and access, and handles with respective face recognition algorithms picture stream;
The interface Unified Element, for unifying all recognition of face producers by face multi engine unified interface service
Applied layer interface standard, and the face Applied layer interface for opening to the outside world unified, for the progress of each face multi engine application platform
It calls.
The present invention has the advantage that the present invention is collected by face picture transport gateway and summarizing resource data, by
Face multi engine data access center binding distribution resource data, and service come unification and open by face multi engine unified interface
Interface standard is put, to realize the unified management of resource, recognition of face producer, face multi engine application platform.In other words, will
The present invention can be considered a face multi engine dispatching platform, can be managed collectively, be dispatched by the face multi engine dispatching platform
The mutual supplement with each other's advantages of different engines is realized in the work of each face identification system, is avoided resource data from repeating to store, is promoted application platform
Deployment efficiency.
Detailed description of the invention
The present invention is further illustrated in conjunction with the embodiments with reference to the accompanying drawings.
Fig. 1 is a kind of flow diagram for the method for integrating a variety of face recognition engines of the present invention.
Specific embodiment
Refering to Figure 1, a kind of preferred embodiment for the method for integrating a variety of face recognition engines, the method includes
Following steps:
Step S1, shooting record is received from the candid photograph equipment of front end by face picture transport gateway, and from outside
Identity information is received in system or storage pool;
Wherein, the step S1 specifically:
A plurality of clusters are disposed using distributed strategy, a face picture transport gateway, example are respectively provided in each cluster
Such as, all candid photograph equipment in the same administrative region can be divided into the same cluster, and a face picture is set and is passed
Defeated gateway receives the data of all candid photograph equipment in the respective administrative areas;Each face picture transfer gateway is all in accordance with locating for itself
Cluster receives shooting record from the candid photograph equipment of front end, and receives identity information from external system or storage pool.
Due to, requiring to dispose many candid photograph equipment in actual use, (candid photograph disposed in a city is set
Standby magnitude may be up to thousands of), some face picture transfer gateways are affixed one's name to therefore, it is necessary to multi-section to share processing pressure, with reality
Now concurrent data is efficiently treated through.
In the step S1, include device id in the shooting record, capture the time and capture picture;The identity
Information includes portrait library ID, name, identification card number, gender or certificate photo.
Step S2, picture stream is uniformly saved in picture cloud storage by face picture transport gateway, by data flow with message
Mode is sent to face multi engine data access center and is stored, that is to say, that the face multi engine data in the present invention connect
Entering center is to be communicated by way of sending and receiving message with each face picture transport gateway;The present invention passes through upper
Communication mechanism is stated, face multi engine data access center is allowed to erect the transmission of entire front-end collection data, and and can
To monitor the equipment state (passing through heartbeat message) under the network.
In the step S2, the message collection received is deposited in message-oriented middleware by face multi engine data access center
In, the message-oriented middleware can be Kafka, ActiveMQ etc., and it includes transport gateway access message that received message, which is concentrated, is set
Standby access message captures data message, identity information message, heartbeat message or other increased service messages on demand.
Step S3, resource data is distributed at specified recognition of face producer by face multi engine data access center
Reason;Meanwhile the face Applied layer interface unified by the service opening of face multi engine unified interface, so that each face draws more
Application platform is held up to be called.
Wherein, the step S3 is specifically included:
Step S31, face picture transport gateway and the candid photograph of access are configured in face multi engine data access center
Equipment, and configured candid photograph equipment is bound with corresponding recognition of face producer, in this way, when face multi engine data connect
Enter center when receiving candid photograph data message or identity information message, so that it may message is sent to according to binding relationship
Corresponding recognition of face producer can both be communicated by message-oriented middleware, can also be passed through when specifically being sent
The candid photograph data-interface that adds and identity information interface are communicated in the service of face multi engine unified interface.
Step S32, resource data (is captured data message or identity information report by face multi engine data access center
Text) according to binding relationship it is distributed to corresponding recognition of face producer;Recognition of face producer passes through report after receiving resource data
The picture cloud storage address (a string of accessible url) for including in text carries out share and access, and uses respective recognition of face
Algorithm handles picture stream, including the operation such as is modeled to picture, is put in storage, analyzes with face recognition algorithms;Having
When body is implemented, recognition of face producer needs to provide the api interface document of respective face recognition products, that is to say, that each face is known
Other producer open applications layer interface, for face multi engine unified interface service call, without the recognition of face of open bottom
Algorithm.
Step S33, by face multi engine unified interface service come the Applied layer interface of unified all recognition of face producers
Standard, and the face Applied layer interface for opening to the outside world unified, so that each face multi engine application platform is called.Due to each one
Face identifies that the Applied layer interface standard of producer is different, by face multi engine unified interface service come unified all recognition of face factories
Family Applied layer interface standard after, can make each face multi engine application platform that need to only develop once, and without again with
The variation of recognition of face producer interface and be changed.
For example, increasing interface, gender of the gender field (1- male, 2- female) of possible A producer with B producer newly for identity information
Field (0- male, 1- female, 2- are unknown) is different, at this moment, so that it may unified mark is provided by face multi engine unified interface service
Quasi- interface, i.e., the service of face multi engine unified interface can integrate gender field, and provide for application layer such as gender field
(0- is unknown, 1- is male, 2- female) is more reasonable in this way, interface of more fully seeking unity of standard.
Refering to Figure 1, a kind of device for integrating a variety of face recognition engines of the present invention, described device includes that data obtain
Modulus block, data memory module and interface unified modules;
The data acquisition module, for receiving shooting note from the candid photograph equipment of front end by face picture transport gateway
Record, and identity information is received from external system or storage pool;
Wherein, the data acquisition module specifically:
A plurality of clusters are disposed using distributed strategy, a face picture transport gateway, example are respectively provided in each cluster
Such as, all candid photograph equipment in the same administrative region can be divided into the same cluster, and a face picture is set and is passed
Defeated gateway receives the data of all candid photograph equipment in the respective administrative areas;Each face picture transfer gateway is all in accordance with locating for itself
Cluster receives shooting record from the candid photograph equipment of front end, and receives identity information from external system or storage pool.
Due to, requiring to dispose many candid photograph equipment in actual use, (candid photograph disposed in a city is set
Standby magnitude may be up to thousands of), some face picture transfer gateways are affixed one's name to therefore, it is necessary to multi-section to share processing pressure, with reality
Now concurrent data is efficiently treated through.
In the data acquisition module, includes device id in the shooting record, captures the time and capture picture;Institute
Stating identity information includes portrait library ID, name, identification card number, gender or certificate photo.
Picture stream is uniformly saved in picture cloud storage for face picture transport gateway by the data memory module, will
Data flow is sent to face multi engine data access center in a manner of message and is stored, that is to say, that the people in the present invention
Face multi engine data access center is to be led to by way of sending and receiving message with each face picture transport gateway
Letter;The present invention allows face multi engine data access center to erect entire front-end collection number by above-mentioned communication mechanism
According to transmission, and and the equipment state (passing through heartbeat message) under the network can be monitored.
In the data memory module, the message collection received is deposited in message by face multi engine data access center
In middleware, the message-oriented middleware can be Kafka, ActiveMQ etc., and it includes that transport gateway accesses that received message, which is concentrated,
Message, equipment access message capture data message, identity information message, heartbeat message or other increased business reports on demand
Text.
Resource data is distributed to specified face for face multi engine data access center by the interface unified modules
Identification producer is handled;Meanwhile the face Applied layer interface unified by the service opening of face multi engine unified interface,
So that each face multi engine application platform is called.
Wherein, the interface unified modules specifically include binding unit, processing unit and interface Unified Element;
The binding unit, for configuring the face picture transport gateway of access in face multi engine data access center
And equipment is captured, and configured candid photograph equipment is bound with corresponding recognition of face producer, in this way, when face draws more
Data access center is held up when receiving candid photograph data message or identity information message, so that it may will report according to binding relationship
Text is sent to corresponding recognition of face producer, when specifically being sent, can both be communicated by message-oriented middleware,
It can be communicated by the candid photograph data-interface that adds in the service of face multi engine unified interface and identity information interface.
The processing unit, for face multi engine data access center by resource data (i.e. candid photograph data message or
Identity information message) according to binding relationship it is distributed to corresponding recognition of face producer;Recognition of face producer is receiving number of resources
According to rear, share and access is carried out by the picture cloud storage address (a string of accessible url) for including in message, and with respective
Face recognition algorithms picture stream is handled, including picture is modeled with face recognition algorithms, be put in storage, is analyzed
Operation;In the specific implementation, recognition of face producer needs to provide the api interface document of respective face recognition products, that is to say, that
Each recognition of face producer open applications layer interface, for face multi engine unified interface service call, without open bottom
Face recognition algorithms.
The interface Unified Element, for unifying all recognition of face producers by face multi engine unified interface service
Applied layer interface standard, and the face Applied layer interface for opening to the outside world unified, for the progress of each face multi engine application platform
It calls.Since the Applied layer interface standard of each recognition of face producer is different, serviced by face multi engine unified interface come unified
After the Applied layer interface standard of all recognition of face producers, it can make each face multi engine application platform that need to only develop one
It is secondary, and need not be changed again with the variation of recognition of face producer interface.
The present invention in the specific implementation, can support the access of multi-protocols, such as SOCKET, MQ, TCP/IP, FTP, HTTP are
It can access, therefore, can utmostly reduce the cost input of access point, guarantee the convenience and compatibility of extension.It can support
Mostly cluster distributed deployment, to realize that multiple spot accesses data.A variety of face recognition engines can also be supported to access, supported but not
It is limited to capture the shared realization of the multiple resources data such as face picture, static identity picture, video format file, supports but unlimited
It is unified in the standard of the faces application interfaces such as recognition of face, colleague's analysis, space-time collision.
In conclusion the present invention is collected by face picture transport gateway and summarizing resource data, by face multi engine
Data access center binding distribution resource data, and serviced by face multi engine unified interface come unified and open interface mark
Standard, to realize the unified management of resource, recognition of face producer, face multi engine application platform.It in other words, can will be of the invention
It is considered as a face multi engine dispatching platform, can be managed collectively by the face multi engine dispatching platform, dispatch each face knowledge
The work of other system, realizes the mutual supplement with each other's advantages of different engines, and resource data is avoided to repeat to store, and promotes the deployment effect of application platform
Rate.
Although specific embodiments of the present invention have been described above, those familiar with the art should be managed
Solution, we are merely exemplary described specific embodiment, rather than for the restriction to the scope of the present invention, it is familiar with this
The technical staff in field should be covered of the invention according to modification and variation equivalent made by spirit of the invention
In scope of the claimed protection.
Claims (10)
1. a kind of method for integrating a variety of face recognition engines, it is characterised in that: described method includes following steps:
Step S1, shooting record is received from the candid photograph equipment of front end by face picture transport gateway, and from external system
Or identity information is received in storage pool;
Step S2, picture stream is uniformly saved in picture cloud storage by face picture transport gateway, by data flow in a manner of message
Face multi engine data access center is sent to be stored;
Step S3, resource data is distributed to specified recognition of face producer and handled by face multi engine data access center;
Meanwhile the face Applied layer interface unified by the service opening of face multi engine unified interface, for each face multi engine
Application platform is called.
2. a kind of method for integrating a variety of face recognition engines according to claim 1, it is characterised in that: the step S1
Specifically:
A plurality of clusters are disposed using distributed strategy, a face picture transport gateway is respectively provided in each cluster;Each face
Picture transfer gateway receives shooting record all in accordance with cluster locating for itself from the candid photograph equipment of front end, and from external system or
Identity information is received in storage pool.
3. a kind of method for integrating a variety of face recognition engines according to claim 1, it is characterised in that: in the step
In S1, includes device id in the shooting record, captures the time and capture picture;The identity information include portrait library ID,
Name, identification card number, gender or certificate photo.
4. a kind of method for integrating a variety of face recognition engines according to claim 1, it is characterised in that: in the step
In S2, face multi engine data access center deposits in the message collection received in message-oriented middleware, and received message is concentrated
Message is accessed including transport gateway, equipment accesses message, captures data message, identity information message, heartbeat message or other
On-demand increased service message.
5. a kind of method for integrating a variety of face recognition engines according to claim 1, it is characterised in that: the step S3
It specifically includes:
Step S31, the face picture transport gateway of access is configured in face multi engine data access center and captures equipment,
And configured candid photograph equipment is bound with corresponding recognition of face producer;
Step S32, resource data is distributed to corresponding recognition of face according to binding relationship by face multi engine data access center
Producer;Recognition of face producer carries out shared visit after receiving resource data, through the picture cloud storage address for including in message
It asks, and picture stream is handled with respective face recognition algorithms;
Step S33, unify the Applied layer interface standard of all recognition of face producers by face multi engine unified interface service,
And the face Applied layer interface for opening to the outside world unified, so that each face multi engine application platform is called.
6. a kind of device for integrating a variety of face recognition engines, it is characterised in that: described device includes data acquisition module, data
Memory module and interface unified modules;
The data acquisition module, for receiving shooting record from the candid photograph equipment of front end by face picture transport gateway,
And identity information is received from external system or storage pool;
Picture stream is uniformly saved in picture cloud storage for face picture transport gateway, by data by the data memory module
Stream is sent to face multi engine data access center in a manner of message and is stored;
Resource data is distributed to specified recognition of face for face multi engine data access center by the interface unified modules
Producer is handled;Meanwhile the face Applied layer interface unified by the service opening of face multi engine unified interface, for
Each face multi engine application platform is called.
7. a kind of device for integrating a variety of face recognition engines according to claim 6, it is characterised in that: the data obtain
Modulus block specifically:
A plurality of clusters are disposed using distributed strategy, a face picture transport gateway is respectively provided in each cluster;Each face
Picture transfer gateway receives shooting record all in accordance with cluster locating for itself from the candid photograph equipment of front end, and from external system or
Identity information is received in storage pool.
8. a kind of device for integrating a variety of face recognition engines according to claim 6, it is characterised in that: in the data
It obtains in module, includes device id in the shooting record, captures the time and capture picture;The identity information includes portrait
Library ID, name, identification card number, gender or certificate photo.
9. a kind of device for integrating a variety of face recognition engines according to claim 6, it is characterised in that: in the data
In memory module, face multi engine data access center deposits in the message collection received in message-oriented middleware, received report
In collected works include transport gateway access message, equipment access message, capture data message, identity information message, heartbeat message or
The other increased service messages on demand of person.
10. a kind of method for integrating a variety of face recognition engines according to claim 6, it is characterised in that: the interface
Unified modules specifically include binding unit, processing unit and interface Unified Element;
The binding unit, for configured in face multi engine data access center access face picture transport gateway and
Equipment is captured, and configured candid photograph equipment is bound with corresponding recognition of face producer;
Resource data is distributed to corresponding by the processing unit for face multi engine data access center according to binding relationship
Recognition of face producer;Recognition of face producer after receiving resource data, by the picture cloud storage address that includes in message into
Row share and access, and picture stream is handled with respective face recognition algorithms;
The interface Unified Element, for the answering come unified all recognition of face producers by face multi engine unified interface service
With layer interface standard, and the face Applied layer interface for opening to the outside world unified, so that each face multi engine application platform is called.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910362732.8A CN110097007A (en) | 2019-04-30 | 2019-04-30 | A kind of method and device for integrating a variety of face recognition engines |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910362732.8A CN110097007A (en) | 2019-04-30 | 2019-04-30 | A kind of method and device for integrating a variety of face recognition engines |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110097007A true CN110097007A (en) | 2019-08-06 |
Family
ID=67446643
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910362732.8A Pending CN110097007A (en) | 2019-04-30 | 2019-04-30 | A kind of method and device for integrating a variety of face recognition engines |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110097007A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110738156A (en) * | 2019-10-10 | 2020-01-31 | 武汉普利商用机器有限公司 | face recognition system and method based on message middleware |
CN110738175A (en) * | 2019-10-17 | 2020-01-31 | 北京旷视科技有限公司 | Face image processing method and device, computer equipment and storage medium |
CN111339345A (en) * | 2020-02-26 | 2020-06-26 | 北京国网信通埃森哲信息技术有限公司 | Method, system and storage medium for differential shielding of multi-platform face recognition service interface |
CN111428615A (en) * | 2020-03-20 | 2020-07-17 | 杭州涂鸦信息技术有限公司 | Face recognition method, system and device of cross-platform Internet of things IPC |
CN111914746A (en) * | 2020-07-31 | 2020-11-10 | 安徽华速达电子科技有限公司 | Method and system for relieving load of face recognition equipment |
CN111988540A (en) * | 2020-08-20 | 2020-11-24 | 合肥维信诺科技有限公司 | Image acquisition method and system and display panel |
CN112508769A (en) * | 2020-12-28 | 2021-03-16 | 浪潮云信息技术股份公司 | Method for constructing multi-task computer vision application service based on deep learning |
CN113034715A (en) * | 2021-03-02 | 2021-06-25 | 创优数字科技(广东)有限公司 | Attendance data processing method and device, server and storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20090065416A (en) * | 2007-12-17 | 2009-06-22 | 한국전자통신연구원 | System and method for providing integrated software management |
CN101706872A (en) * | 2009-11-26 | 2010-05-12 | 上海交通大学 | Universal open type face identification system |
CN104966006A (en) * | 2015-05-14 | 2015-10-07 | 苏州市公安局苏州工业园区分局 | Intelligent face identification system based on cloud variation platform |
-
2019
- 2019-04-30 CN CN201910362732.8A patent/CN110097007A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20090065416A (en) * | 2007-12-17 | 2009-06-22 | 한국전자통신연구원 | System and method for providing integrated software management |
CN101706872A (en) * | 2009-11-26 | 2010-05-12 | 上海交通大学 | Universal open type face identification system |
CN104966006A (en) * | 2015-05-14 | 2015-10-07 | 苏州市公安局苏州工业园区分局 | Intelligent face identification system based on cloud variation platform |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110738156A (en) * | 2019-10-10 | 2020-01-31 | 武汉普利商用机器有限公司 | face recognition system and method based on message middleware |
CN110738156B (en) * | 2019-10-10 | 2022-12-02 | 武汉普利商用机器有限公司 | Face recognition system and method based on message middleware |
CN110738175A (en) * | 2019-10-17 | 2020-01-31 | 北京旷视科技有限公司 | Face image processing method and device, computer equipment and storage medium |
CN111339345A (en) * | 2020-02-26 | 2020-06-26 | 北京国网信通埃森哲信息技术有限公司 | Method, system and storage medium for differential shielding of multi-platform face recognition service interface |
CN111339345B (en) * | 2020-02-26 | 2023-09-19 | 北京国网信通埃森哲信息技术有限公司 | Multi-platform face recognition service interface differentiated shielding method, system and storage medium |
CN111428615A (en) * | 2020-03-20 | 2020-07-17 | 杭州涂鸦信息技术有限公司 | Face recognition method, system and device of cross-platform Internet of things IPC |
CN111428615B (en) * | 2020-03-20 | 2023-10-31 | 杭州涂鸦信息技术有限公司 | Face recognition method, system and device of IPC (Internet of things) of cross-platform |
CN111914746A (en) * | 2020-07-31 | 2020-11-10 | 安徽华速达电子科技有限公司 | Method and system for relieving load of face recognition equipment |
CN111914746B (en) * | 2020-07-31 | 2024-05-03 | 安徽华速达电子科技有限公司 | Method and system for relieving load of face recognition equipment |
CN111988540A (en) * | 2020-08-20 | 2020-11-24 | 合肥维信诺科技有限公司 | Image acquisition method and system and display panel |
CN112508769A (en) * | 2020-12-28 | 2021-03-16 | 浪潮云信息技术股份公司 | Method for constructing multi-task computer vision application service based on deep learning |
CN113034715A (en) * | 2021-03-02 | 2021-06-25 | 创优数字科技(广东)有限公司 | Attendance data processing method and device, server and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110097007A (en) | A kind of method and device for integrating a variety of face recognition engines | |
Yasumoto et al. | Survey of real-time processing technologies of iot data streams | |
Ahmed et al. | The role of big data analytics in Internet of Things | |
WO2020116928A1 (en) | Method and apparatus for management of network based media processing functions in wireless communication system | |
CN101784989B (en) | Method and system for allocating network adapter resources among logical partitions | |
CN110266815B (en) | Micro service network system based on block chain | |
US11443613B2 (en) | Real-time crime center solution with text-based tips and panic alerts | |
CN112511218A (en) | Satellite ground station monitoring system based on microservice | |
CN106027969A (en) | Mobile video monitoring platform | |
CN110851248A (en) | Asynchronous task data processing method and device and computer readable storage medium | |
CN111506297A (en) | Mobile top layer design system | |
CN114830080A (en) | Data distribution flow configuration method and device, electronic equipment and storage medium | |
CN104038654B (en) | Relay, client terminal device and method | |
CN103581238A (en) | Unified service platform of ubiquitous network and service implementing method | |
Perwej et al. | An empirical study on the current state of internet of multimedia things (IoMT) | |
Schönberger | Do we need a refined choreography notion | |
CN1151635C (en) | General dispatching system based on content adaptive for colony network service | |
CN107171959A (en) | Dynamic routing method and dynamic routing system based on SOA | |
Narita et al. | Enhanced RSNP for applying to the network service platform-implementation of a face detection function | |
CN101621530A (en) | Method and device for dispatching load balancing network resource based on light path share | |
Milev | Integration of software solutions via an intermediary web service | |
CN106027968A (en) | Mobile auxiliary inspection method | |
Baber et al. | Supporting implicit coordination between distributed teams in disaster management | |
CN113132678A (en) | Data transmission method and device, electronic equipment and storage medium | |
JP3681313B2 (en) | Data distribution method |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190806 |
|
RJ01 | Rejection of invention patent application after publication |