CN109101333A - Image characteristic extracting method, device, storage medium and electronic equipment - Google Patents
Image characteristic extracting method, device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN109101333A CN109101333A CN201810682410.7A CN201810682410A CN109101333A CN 109101333 A CN109101333 A CN 109101333A CN 201810682410 A CN201810682410 A CN 201810682410A CN 109101333 A CN109101333 A CN 109101333A
- Authority
- CN
- China
- Prior art keywords
- face
- terminal
- recognition
- personnel
- image
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5011—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals
- G06F9/5016—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals the resource being the memory
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
- G06F9/505—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering the load
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5072—Grid computing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Collating Specific Patterns (AREA)
Abstract
This disclosure relates to a kind of image characteristic extracting method, device, storage medium and electronic equipment, to solve the problem of a large amount of network bandwidths of consuming existing for image characteristics extraction in the related technology and expend a large amount of computing resources of recognition of face terminal.The graphic feature extracting method of the disclosure comprises determining that the operation conditions of multiple recognition of face terminals；According to the operation conditions of each face identification terminal, multiple personnel's images of pending feature extraction are subjected to subpackage processing；Personnel's image after subpackage is distributed to the recognition of face terminal of corresponding operating status, so that personnel's image that the multiple recognition of face end-on receives carries out feature extraction；The characteristic information that the multiple recognition of face terminal is sent is received respectively.
Description
Technical field
This disclosure relates to technical field of face recognition, and in particular, to a kind of image characteristic extracting method, device, storage
Medium and electronic equipment.
Background technique
Face recognition technology is a kind of biological identification technology for carrying out identification based on facial feature information of people,
Principle is to be stored in recognition of face terminal after magnanimity personnel image to be extracted to feature respectively as face recognition database, then
The image that camera captures is extracted and is compared in face recognition database after feature, the feature extraction of personnel's image
It is the basis of recognition of face.
In the related technology, mainly passing through cloud platform issues institute to each face identification terminal for the feature extraction of personnel's image
There is personnel's image of pending feature extraction, then each face identification terminal carries out feature respectively to all people person's image and mentions
It takes.If personnel's amount of images of pending feature extraction is numerous, all personnel's image is issued to each recognition of face
Terminal will just expend a large amount of network bandwidth, also, each face identification terminal carries out spy to all personnel's image received
Sign is extracted, and each a large amount of computing resource of face identification terminal will be also expended.
Summary of the invention
Purpose of this disclosure is to provide a kind of image characteristic extracting method, device, storage medium and electronic equipments, to solve
Image characteristics extraction is existing in the related technology expends a large amount of network bandwidths, and expends a large amount of computing resources of recognition of face terminal
The problem of.
In a first aspect, the disclosure provides a kind of image characteristic extracting method, comprising:
Determine the operation conditions of multiple recognition of face terminals；
According to the operation conditions of each face identification terminal, multiple personnel's images of pending feature extraction are carried out at subpackage
Reason；
Personnel's image after subpackage is distributed to the recognition of face terminal of corresponding operating status, so that the multiple face is known
Personnel's image that other end-on receives carries out feature extraction；
The characteristic information that the multiple recognition of face terminal is sent is received respectively.
Optionally, after receiving the characteristic information that the multiple recognition of face terminal is sent respectively, further includes:
According to the usage scenario of each face identification terminal, the characteristic information received is distributed to the multiple recognition of face
Terminal, to carry out recognition of face by the multiple recognition of face terminal.
Optionally, the characteristic information received is distributed to described by the usage scenario according to each face identification terminal
Multiple recognition of face terminals, comprising:
According to the usage scenario of each face identification terminal, the identification personnel of each face identification terminal are determined；
The corresponding characteristic information of identification personnel of the face identification terminal is sent to each face identification terminal respectively.
Optionally, in the usage scenario according to each face identification terminal, the characteristic information received is distributed to described more
Before a face identification terminal, further includes:
The identification information of the multiple recognition of face terminal is determined respectively, wherein the identification information is used for unique identification
Each face identification terminal；
According to the identification information, the usage scenario of each face identification terminal is determined.
Optionally, the operating status of the multiple recognition of face terminals of the determination, comprising:
Obtain the central processor CPU utilization rate and/or memory usage of the multiple recognition of face terminal；
According to the CPU usage and/or memory usage, the operation conditions of the multiple recognition of face terminal is determined.
Second aspect, the disclosure also provide a kind of image characteristics extraction device, and described device includes:
First determining module, for determining the operation conditions of multiple recognition of face terminals；
Subpackage processing module, for the operation conditions according to each face identification terminal, by the multiple of pending feature extraction
Personnel's image carries out subpackage processing；
First sending module, for personnel's image after subpackage to be distributed to the recognition of face terminal of corresponding operating status,
So that personnel's image that the multiple recognition of face end-on receives carries out feature extraction；
Receiving module, the characteristic information sent for receiving the multiple recognition of face terminal respectively.
Optionally, described device further include:
Second sending module distributes the characteristic information received for the usage scenario according to each face identification terminal
To the multiple recognition of face terminal, to carry out recognition of face by the multiple recognition of face terminal.
Optionally, second sending module includes:
Second determining module determines the knowledge of each face identification terminal for the usage scenario according to each face identification terminal
Others is member；
Third sending module, the identification personnel couple for giving each face identification terminal to send the face identification terminal respectively
The characteristic information answered.
Optionally, described device further include:
Third determining module, in the usage scenario according to each face identification terminal, the characteristic information received to be divided
Before issuing the multiple recognition of face terminal, the identification information of the multiple recognition of face terminal is determined respectively, wherein described
Identification information is used for each face identification terminal of unique identification；
4th determining module, for determining the usage scenario of each face identification terminal according to the identification information.
Optionally, the central processor CPU that first determining module is used to obtain the multiple recognition of face terminal makes
With rate and/or memory usage, and according to the CPU usage and/or memory usage, determine that the multiple recognition of face is whole
The operation conditions at end.
The third aspect, the disclosure also provide a kind of computer readable storage medium, are stored thereon with computer program, the journey
The step of any one the method in first aspect is realized when sequence is executed by processor.
Fourth aspect, the disclosure also provide a kind of electronic equipment, comprising:
Memory is stored thereon with computer program；
Processor, for executing the computer program in the memory, to realize any one institute in first aspect
The step of stating method.
Through the above technical solutions, the operation conditions of multiple recognition of face terminals can first be determined, then according to each face
Multiple personnel's images of pending feature extraction are carried out subpackage processing by the operation conditions of identification terminal, then by the people after subpackage
Member's image is distributed to the recognition of face terminal of corresponding operating status, so that personnel's image that multiple recognition of face end-ons receive
Feature extraction is carried out, finally receives the characteristic information that multiple recognition of face terminals are sent respectively.In this way, each face identification terminal is not
With the personnel's image for receiving all pending feature extractions, network bandwidth is saved, also, each face identification terminal only needs to dock
The personnel's image received carries out feature extraction, and does not have to carry out feature extraction to all personnel's image, and therefore, which also saves each
The computing resource of recognition of face terminal.
Other feature and advantage of the disclosure will the following detailed description will be given in the detailed implementation section.
Detailed description of the invention
Attached drawing is and to constitute part of specification for providing further understanding of the disclosure, with following tool
Body embodiment is used to explain the disclosure together, but does not constitute the limitation to the disclosure.In the accompanying drawings:
Fig. 1 is cloud platform and recognition of face terminal when the image characteristic extracting method of the disclosure to be applied to cloud platform
Configuration diagram；
Fig. 2 is the flow chart according to the image characteristic extracting method shown in one exemplary embodiment of the disclosure；
Fig. 3 is the block diagram according to the image characteristics extraction device shown in one exemplary embodiment of the disclosure；
Fig. 4 is the block diagram according to a kind of electronic equipment shown in one exemplary embodiment of the disclosure；
Fig. 5 is the block diagram according to another electronic equipment shown in one exemplary embodiment of the disclosure.
Specific embodiment
It is described in detail below in conjunction with specific embodiment of the attached drawing to the disclosure.It should be understood that this place is retouched
The specific embodiment stated is only used for describing and explaining the disclosure, is not limited to the disclosure.
Illustrate the application scenarios of the image characteristic extracting method of the disclosure first, the image characteristic extracting method of the disclosure can
To be applied to cloud platform, for example, SaaS (Software-as-a-Service, software service) platform, referring to Fig.1, cloud
Management has multiple recognition of face terminals under platform, and cloud platform can carry out data friendship by network and each face identification terminal
Mutually.Certainly, the disclosure can also be applied to recognition of face terminal, for example, multiple recognition of face terminals are interconnected by network,
When personnel's image that some recognition of face terminal is got is more, so that it may be divided personnel's image by disclosed method
Other face identification terminals are issued, carry out feature extraction by other face identification terminals.
Fig. 2 be according to the flow chart of the image characteristic extracting method shown in one exemplary embodiment of the disclosure, referring to Fig. 2,
The image characteristic extracting method of the disclosure the following steps are included:
Step S201 determines the operation conditions of multiple recognition of face terminals.
Step S202, according to the operation conditions of each face identification terminal, by multiple personnel's images of pending feature extraction
Carry out subpackage processing.
Personnel's image after subpackage is distributed to the recognition of face terminal of corresponding operating status, so that multiple by step S203
Personnel's image that recognition of face end-on receives carries out feature extraction.
Step S204 receives the characteristic information that multiple recognition of face terminals are sent respectively.
The operating status of recognition of face terminal can be the state of characterization recognition of face terminal busy extent, for example, not numerous
Busy condition, compared with busy state, busy state, etc., the disclosure is not construed as limiting this.
Determine that the operating status of multiple recognition of face terminals can be the CPU (Central by recognition of face terminal
Processing Unit, central processing unit) utilization rate determination, it is also possible to the memory usage by recognition of face terminal
It is determining, it can also be what CPU usage and memory usage by combining recognition of face terminal determined, etc., the disclosure
This is not construed as limiting.That is, it is alternatively possible to obtaining the central processor CPU utilization rate and/or memory of multiple recognition of face terminals
Utilization rate determines the operation conditions of multiple recognition of face terminals then according to CPU usage and/or memory usage.
For example, the CPU usage for obtaining a face identification terminal is 90%, then can be true according to CPU usage
The operation conditions of the fixed face identification terminal be compared with busy state, or, the memory for obtaining a face identification terminal makes
It is 30% with rate, then the operation conditions of the face identification terminal can be determined for not busy state according to memory usage.
After the operation conditions for determining multiple recognition of face terminals, so that it may according to the operation shape of each face identification terminal
Multiple personnel's images of pending feature extraction are carried out subpackage processing by condition.
In subpackage processing, personnel's picture number that each face identification terminal is got be can be through each face identification terminal
What also accessible maximum data capacity determined, the corresponding data of personnel's picture number that each face identification terminal is finally got are held
Amount can be less than or equal to the maximum data capacity.For example, a face identification terminal, which has been determined, also according to operation conditions to locate
The maximum data capacity of reason is 20M, then personnel's image that the face identification terminal data capacity is 20M can be given, or
Person can also give personnel's image that the face identification terminal data capacity is less than 20M to reduce the load of face terminal,
The disclosure is not construed as limiting this.
For example, personnel's image of pending feature extraction is 100, there are two recognition of face terminals for management under the platform of cloud
A and B has determined that the operation conditions of recognition of face terminal A and B are respectively not busy state and busier shape according to CPU usage
State, and according to operation conditions determined maximum data capacity that recognition of face terminal A and B can also be handled be respectively 100M and
100 images are divided into two packets then carrying out subpackage processing and can be, include that data capacity is less than or waits in a packet by 20M
It include personnel image of the data capacity less than or equal to 20M in personnel's image of 100M, another packet.
If data capacity is 100M, corresponding personnel's picture number is 70, and data capacity is the corresponding personnel's image of 20M
Number is 30, then recognition of face terminal A can get 70 personnel's images or personnel's image more less than 70, face
Identification terminal B can get 30 personnel's images or personnel's image more less than 30, that is, be got over according to what operation conditions determined
The packet of busy recognition of face terminal point is smaller, and the personnel's picture number for including is fewer.
It should be noted that if after subpackage, there remains personnel's image of pending feature extraction, for example, it is above-mentioned into
In the example that personnel's image of row feature extraction is 100, if recognition of face terminal A divides to obtain personnel's figure more less than 70
Picture, recognition of face terminal B divide to obtain personnel's image more less than 30, then there is no be all sent to for this 100 personnel's images
Recognition of face terminal can be waited in such case, when full complement's figure that some recognition of face end-on receives
After carrying out feature extraction, personnel's image that residue does not issue is just sent to this recognition of face terminal and carries out feature extraction.
In addition, personnel's image that each face identification terminal is got can also be the operation shape according to each face identification terminal
Condition, proportional assignment.For example, personnel's image of pending feature extraction is 100, there are two faces to know for management under the platform of cloud
Other terminal A and B, according to CPU usage, it is determined that the personnel's image scaled of recognition of face terminal A and B got is respectively 70%
With 30%, 100 images are divided into two packets then carrying out subpackage processing and can be, including in this 100 images in a packet
70% image includes in 100 images 30% image in another packet, that is, recognition of face terminal A can get 70 people
Member's image, recognition of face terminal B can get 30 personnel's images.
It should be noted that multiple personnel's images of pending feature extraction for being carried out the tool of subpackage processing by the disclosure
Body mode includes but are not limited to above-mentioned two ways, and user can voluntarily determine the mode of subpackage processing according to demand, only
If being handled according to the subpackage that the operation conditions of each face identification terminal carries out.
After carrying out subpackage processing, the recognition of face that personnel's image after subpackage can be distributed to corresponding operating status is whole
End, so that personnel's image that multiple recognition of face end-ons receive carries out feature extraction.
For example, the result of subpackage processing is one in the example that personnel's image of above-mentioned pending feature extraction is 100
Include 70 personnel's images in data packet, include 30 personnel's images in another data packet, then will just be wrapped after subpackage processing
The data packet for including 70 personnel's images is sent to recognition of face terminal A, and the data packet including 30 personnel's images is sent to people
Face identification terminal B, then, recognition of face terminal A and B just carry out feature extraction to the personnel's image received.
After personnel's image that recognition of face end-on receives carries out feature extraction, each face identification terminal is just received respectively
The characteristic information of transmission.By taking the image characteristic extracting method of the disclosure is applied to cloud platform as an example, when each face identification terminal
After carrying out feature extraction to the personnel's image received, cloud platform just receives the feature letter that each face identification terminal is sent respectively
Breath.
It should be noted that for the ease of being managed to the characteristic information obtained after personnel's image and feature extraction, often
A personnel's image corresponds to an identification information, identification information unique identification personnel's image.It therefore, will in step S203
While personnel's image after subpackage is distributed to the recognition of face terminal of corresponding operating status, also by the corresponding mark of personnel's image
It number is sent to the recognition of face terminal of corresponding operating status, is mentioned likewise, recognition of face terminal carries out feature to personnel's image
After taking, when sending characteristic information, and corresponding identification number is sent together, in this case, receiving feature
When information, so that it may be managed by identification number to characteristic information, thus one by one by characteristic information and corresponding personal information
It is corresponding.
It optionally, can also be according to each face after receiving the characteristic information that multiple recognition of face terminals are sent respectively
The characteristic information received is distributed to multiple recognition of face terminals, to know by multiple faces by the usage scenario of identification terminal
Other terminal carries out recognition of face.
According to the usage scenario of each face identification terminal, characteristic information is distributed to multiple recognition of face terminals, rather than
All characteristic informations are distributed to multiple recognition of face terminals, then after camera captured image is carried out feature extraction
When being compared in face recognition database, corresponding characteristic information can be quickly found out in less characteristic information, this
Improve the efficiency of recognition of face.
Certainly, it if there is no higher requirement for the efficiency of recognition of face, can will also receive in the embodiments of the present disclosure
To all characteristic informations be distributed to each face identification terminal, then each face identification terminal is just using all characteristic informations as people
Face identification database carries out recognition of face.
For the method for determination of the usage scenario of each face identification terminal, the disclosure is not construed as limiting, below to possible side
Formula is illustrated.
Optionally, the identification information of multiple recognition of face terminals is determined respectively, then according to identification information, determines each face
The usage scenario of identification terminal
Identification information is for each face identification terminal of unique identification, for example, the equipment that can be recognition of face terminal
Number, etc., the disclosure is not construed as limiting this, as long as can determine the usage scenario of recognition of face terminal according to the identification information
?.
For example, the device numbering that the recognition of face terminal of primary sector is arranged in is 001, then being according to device numbering
001 can determine that the usage scenario of the face identification terminal is primary sector, that is, the face identification terminal first for identification
The related personnel of door.
The usage scenario that recognition of face terminal is determined by identification information, since identification information is unique identification recognition of face
Terminal, it may therefore be assured that the accuracy of the recognition of face terminal usage scenario determined, to guarantee to distribute characteristic information
To the recognition of face terminal of corresponding usage scenario.
Optionally, according to the usage scenario of each face identification terminal, the characteristic information received is distributed to multiple faces
Identification terminal can be the first usage scenario according to each face identification terminal, determine the identification personnel of each face identification terminal, so
Send the corresponding characteristic information of identification personnel of the face identification terminal to each face identification terminal respectively afterwards.
Since the usage scenario of recognition of face terminal is different, corresponding identification personnel are different, for example, being arranged in office
The corresponding identification personnel of the recognition of face terminal of C are the staff of office C, and the recognition of face terminal of class D is arranged in
Corresponding identification personnel are the teacher and classmate of class D, and therefore, it is necessary to elder generations according to the usage scenario of recognition of face terminal, are determined
The identification personnel of each face identification terminal.
After the identification personnel for determining each face identification terminal, so that it may send the people to each face identification terminal respectively
The corresponding characteristic information of identification personnel of face identification terminal.For example, be office C according to the usage scenario of recognition of face terminal,
It has been determined that the identification personnel of the face identification terminal are the staff E1 and staff E2 of office C, then just giving this
Recognition of face terminal sends staff E1 and the corresponding characteristic information of staff E2, in this way, the face identification terminal is in people
During face identifies, it is only necessary to which the image for capturing camera carries out spy corresponding with the two staff after feature extraction
Reference breath is compared, rather than all features corresponding with all images of pending feature extraction are compared, this is certain
The efficiency of recognition of face is improved in degree.
Based on the same inventive concept, referring to Fig. 3, the disclosure also provides a kind of image characteristics extraction device 300, comprising:
First determining module 301, for determining the operation conditions of multiple recognition of face terminals；
Subpackage processing module 302, for the operation conditions according to each face identification terminal, by the more of pending feature extraction
A personnel's image carries out subpackage processing；
First sending module 303, the recognition of face for personnel's image after subpackage to be distributed to corresponding operating status are whole
End, so that personnel's image that multiple recognition of face end-ons receive carries out feature extraction；
Receiving module 304, the characteristic information sent for receiving multiple recognition of face terminals respectively.
Optionally, device 300 further include:
Second sending module distributes the characteristic information received for the usage scenario according to each face identification terminal
To multiple recognition of face terminals, to carry out recognition of face by multiple recognition of face terminals.
Optionally, the second sending module includes:
Second determining module determines the knowledge of each face identification terminal for the usage scenario according to each face identification terminal
Others is member；
Third sending module, the identification personnel couple for giving each face identification terminal to send the face identification terminal respectively
The characteristic information answered.
Optionally, device 300 further include:
Third determining module, in the usage scenario according to each face identification terminal, the characteristic information received to be divided
Before issuing multiple recognition of face terminals, the identification information of multiple recognition of face terminals is determined respectively, wherein identification information is used for
Each face identification terminal of unique identification；
4th determining module, for determining the usage scenario of each face identification terminal according to identification information.
Optionally, the first determining module 301 is used to obtain the central processor CPU utilization rate of multiple recognition of face terminals
And/or memory usage, and according to CPU usage and/or memory usage, determine the operation shape of multiple recognition of face terminals
Condition.
About the device in above-described embodiment, wherein modules execute the concrete mode of operation in related this method
Embodiment in be described in detail, no detailed explanation will be given here.
Fig. 4 is the block diagram of a kind of electronic equipment 400 shown according to an exemplary embodiment.As shown in figure 4, the electronics is set
Standby 400 may be provided as a recognition of face terminal, comprising: processor 401, memory 402.The electronic equipment 400 can be with
Including multimedia component 403, one or more of input/output (I/O) interface 404 and communication component 405.
Wherein, processor 401 is used to control the integrated operation of the electronic equipment 400, is mentioned with the characteristics of image for completing above-mentioned
Take all or part of the steps in method.Memory 402 is for storing various types of data to support in the electronic equipment 400
Operation, these data for example may include the finger of any application or method for operating on the electronic equipment 400
Order and the relevant data of application program, such as contact data, the message of transmitting-receiving, picture, audio, video etc..The storage
Device 402 can be realized by any kind of volatibility or non-volatile memory device or their combination, such as static random
It accesses memory (Static Random Access Memory, abbreviation SRAM), electrically erasable programmable read-only memory
(Electrically Erasable Programmable Read-Only Memory, abbreviation EEPROM), erasable programmable
Read-only memory (Erasable Programmable Read-Only Memory, abbreviation EPROM), programmable read only memory
(Programmable Read-Only Memory, abbreviation PROM), and read-only memory (Read-Only Memory, referred to as
ROM), magnetic memory, flash memory, disk or CD.Multimedia component 403 may include screen, audio component, camera shooting group
Part.Wherein screen for example can be touch screen, and audio component is used for output and/or input audio signal, and camera assembly is for catching
Catch personnel's image.For example, audio component may include a microphone, microphone is for receiving external audio signal.It is received
Audio signal can be further stored in memory 402 or be sent by communication component 405.Audio component further includes at least
One loudspeaker is used for output audio signal.I/O interface 404 provides interface between processor 401 and other interface modules,
Other above-mentioned interface modules can be keyboard, mouse, button etc..These buttons can be virtual push button or entity button.It is logical
Letter component 405 is for carrying out wired or wireless communication between the electronic equipment 400 and other equipment.Wireless communication, such as Wi-
Fi, bluetooth, near-field communication (Near Field Communication, abbreviation NFC), 2G, 3G or 4G or they one of or
Several combinations, therefore the corresponding communication component 405 may include: Wi-Fi module, bluetooth module, NFC module.
In one exemplary embodiment, electronic equipment 400 can be by one or more application specific integrated circuit
(Application Specific Integrated Circuit, abbreviation ASIC), digital signal processor (Digital
Signal Processor, abbreviation DSP), digital signal processing appts (Digital Signal Processing Device,
Abbreviation DSPD), programmable logic device (Programmable Logic Device, abbreviation PLD), field programmable gate array
(Field Programmable Gate Array, abbreviation FPGA), controller, microcontroller, microprocessor or other electronics member
Part is realized, for executing above-mentioned image characteristic extracting method.
In a further exemplary embodiment, a kind of computer readable storage medium including program instruction is additionally provided, it should
The step of above-mentioned image characteristic extracting method is realized when program instruction is executed by processor.For example, the computer-readable storage
Medium can be the above-mentioned memory 402 including program instruction, and above procedure instruction can be by the processor 401 of electronic equipment 400
It executes to complete above-mentioned image characteristic extracting method.
Fig. 5 is the block diagram of a kind of electronic equipment 500 shown according to an exemplary embodiment.For example, electronic equipment 500 can
To be provided as a server.Referring to Fig. 5, electronic equipment 500 includes processor 522, and quantity can be one or more, with
And memory 532, for storing the computer program that can be executed by processor 522.The computer program stored in memory 532
May include it is one or more each correspond to one group of instruction module.In addition, processor 522 can be configured as
The computer program is executed, to execute above-mentioned image characteristic extracting method.
In addition, electronic equipment 500 can also include power supply module 526 and communication component 550, which can be with
It is configured as executing the power management of electronic equipment 500, which, which can be configured as, realizes electronic equipment 500
Communication, for example, wired or wireless communication.In addition, the electronic equipment 500 can also include input/output (I/O) interface 558.Electricity
Sub- equipment 500 can be operated based on the operating system for being stored in memory 532, such as Windows ServerTM, Mac OS
XTM, UnixTM, LinuxTM etc..
In a further exemplary embodiment, a kind of computer readable storage medium including program instruction is additionally provided, it should
The step of above-mentioned image characteristic extracting method is realized when program instruction is executed by processor.For example, the computer-readable storage
Medium can be the above-mentioned memory 532 including program instruction, and above procedure instruction can be by the processor 522 of electronic equipment 500
It executes to complete above-mentioned image characteristic extracting method.
The preferred embodiment of the disclosure is described in detail in conjunction with attached drawing above, still, the disclosure is not limited to above-mentioned reality
The detail in mode is applied, in the range of the technology design of the disclosure, a variety of letters can be carried out to the technical solution of the disclosure
Monotropic type, these simple variants belong to the protection scope of the disclosure.
It is further to note that specific technical features described in the above specific embodiments, in not lance
In the case where shield, can be combined in any appropriate way, in order to avoid unnecessary repetition, the disclosure to it is various can
No further explanation will be given for the combination of energy.
In addition, any combination can also be carried out between a variety of different embodiments of the disclosure, as long as it is without prejudice to originally
Disclosed thought equally should be considered as disclosure disclosure of that.
Claims (10)
1. a kind of image characteristic extracting method characterized by comprising
Determine the operation conditions of multiple recognition of face terminals；
According to the operation conditions of each face identification terminal, multiple personnel's images of pending feature extraction are subjected to subpackage processing；
Personnel's image after subpackage is distributed to the recognition of face terminal of corresponding operating status, so that the multiple recognition of face is whole
It holds and feature extraction is carried out to the personnel's image received；
The characteristic information that the multiple recognition of face terminal is sent is received respectively.
2. the method according to claim 1, wherein receiving what the multiple recognition of face terminal was sent respectively
After characteristic information, further includes:
According to the usage scenario of each face identification terminal, it is whole that the characteristic information received is distributed to the multiple recognition of face
End, to carry out recognition of face by the multiple recognition of face terminal.
3. according to the method described in claim 2, it is characterized in that, the usage scenario according to each face identification terminal, is incited somebody to action
The characteristic information received is distributed to the multiple recognition of face terminal, comprising:
According to the usage scenario of each face identification terminal, the identification personnel of each face identification terminal are determined；
The corresponding characteristic information of identification personnel of the face identification terminal is sent to each face identification terminal respectively.
4. according to the method described in claim 2, it is characterized in that, will be connect in the usage scenario according to each face identification terminal
The characteristic information received is distributed to before the multiple recognition of face terminal, further includes:
Determine the identification information of the multiple recognition of face terminal respectively, wherein the identification information for unique identification each one
Face identification terminal；
According to the identification information, the usage scenario of each face identification terminal is determined.
5. method according to claim 1 to 4, which is characterized in that the operation of the multiple recognition of face terminals of determination
State, comprising:
Obtain the central processor CPU utilization rate and/or memory usage of the multiple recognition of face terminal；
According to the CPU usage and/or memory usage, the operation conditions of the multiple recognition of face terminal is determined.
6. a kind of image characteristics extraction device, which is characterized in that described device includes:
First determining module, for determining the operation conditions of multiple recognition of face terminals；
Subpackage processing module, for the operation conditions according to each face identification terminal, by multiple personnel of pending feature extraction
Image carries out subpackage processing；
First sending module, for personnel's image after subpackage to be distributed to the recognition of face terminal of corresponding operating status, so that
Personnel's image that the multiple recognition of face end-on receives carries out feature extraction；
Receiving module, the characteristic information sent for receiving the multiple recognition of face terminal respectively.
7. device according to claim 6, which is characterized in that described device further include:
The characteristic information received is distributed to institute for the usage scenario according to each face identification terminal by the second sending module
Multiple recognition of face terminals are stated, to carry out recognition of face by the multiple recognition of face terminal.
8. device according to claim 6, which is characterized in that second sending module includes:
Second determining module determines the identification people of each face identification terminal for the usage scenario according to each face identification terminal
Member；
Third sending module, the identification personnel for giving each face identification terminal to send the face identification terminal respectively are corresponding
Characteristic information.
9. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is held by processor
The step of any one of claim 1-5 the method is realized when row.
10. a kind of electronic equipment characterized by comprising
Memory is stored thereon with computer program；
Processor, for executing the computer program in the memory, to realize described in any one of claim 1-5
The step of method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810682410.7A CN109101333A (en) | 2018-06-27 | 2018-06-27 | Image characteristic extracting method, device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810682410.7A CN109101333A (en) | 2018-06-27 | 2018-06-27 | Image characteristic extracting method, device, storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109101333A true CN109101333A (en) | 2018-12-28 |
Family
ID=64845230
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810682410.7A Pending CN109101333A (en) | 2018-06-27 | 2018-06-27 | Image characteristic extracting method, device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109101333A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110909629A (en) * | 2019-11-06 | 2020-03-24 | 浙江大华技术股份有限公司 | Face recognition data processing method and device, computer equipment and storage medium |
| CN111353357A (en) * | 2019-01-31 | 2020-06-30 | 杭州海康威视数字技术股份有限公司 | Face modeling system, method and device |
| CN113590381A (en) * | 2021-06-30 | 2021-11-02 | 北京旷视科技有限公司 | Feature distribution method and device, electronic equipment and computer-readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102222213A (en) * | 2010-07-29 | 2011-10-19 | 郑文明 | Distributed vision computing method based on open type Web Service framework |
| CN104253850A (en) * | 2014-01-07 | 2014-12-31 | 深圳市华傲数据技术有限公司 | Distributed task scheduling method and system |
| CN107832690A (en) * | 2017-10-30 | 2018-03-23 | 广东欧珀移动通信有限公司 | The method and Related product of recognition of face |
| CN107918561A (en) * | 2017-11-17 | 2018-04-17 | 东北大学 | A kind of method for allocating tasks in industrial allocation formula data collecting system |
| US20180143856A1 (en) * | 2016-11-18 | 2018-05-24 | Sap Se | Flexible job management for distributed container cloud platform |
-
2018
- 2018-06-27 CN CN201810682410.7A patent/CN109101333A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102222213A (en) * | 2010-07-29 | 2011-10-19 | 郑文明 | Distributed vision computing method based on open type Web Service framework |
| CN104253850A (en) * | 2014-01-07 | 2014-12-31 | 深圳市华傲数据技术有限公司 | Distributed task scheduling method and system |
| US20180143856A1 (en) * | 2016-11-18 | 2018-05-24 | Sap Se | Flexible job management for distributed container cloud platform |
| CN107832690A (en) * | 2017-10-30 | 2018-03-23 | 广东欧珀移动通信有限公司 | The method and Related product of recognition of face |
| CN107918561A (en) * | 2017-11-17 | 2018-04-17 | 东北大学 | A kind of method for allocating tasks in industrial allocation formula data collecting system |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111353357A (en) * | 2019-01-31 | 2020-06-30 | 杭州海康威视数字技术股份有限公司 | Face modeling system, method and device |
| CN110909629A (en) * | 2019-11-06 | 2020-03-24 | 浙江大华技术股份有限公司 | Face recognition data processing method and device, computer equipment and storage medium |
| CN110909629B (en) * | 2019-11-06 | 2023-04-07 | 浙江大华技术股份有限公司 | Face recognition data processing method and device, computer equipment and storage medium |
| CN113590381A (en) * | 2021-06-30 | 2021-11-02 | 北京旷视科技有限公司 | Feature distribution method and device, electronic equipment and computer-readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108776934B (en) | Distributed data calculation method and device, computer equipment and readable storage medium | |
| CN105975407B (en) | Memory address mapping method and device | |
| CN106919918B (en) | Face tracking method and device | |
| CN112769897B (en) | Synchronization method and device of edge calculation message, electronic equipment and storage medium | |
| CN109101333A (en) | Image characteristic extracting method, device, storage medium and electronic equipment | |
| US10440262B2 (en) | Electronic device and method for processing image | |
| CN110035004B (en) | User name card sharing method, friend adding method and related device | |
| CN112905350A (en) | Task scheduling method and device, electronic equipment and storage medium | |
| US20150309809A1 (en) | Electronic device and method of linking a task thereof | |
| CN105468513B (en) | Test method, device and system based on mobile terminal | |
| US20160036810A1 (en) | Electronic device and method of transceiving data | |
| CN113766487B (en) | Cloud mobile phone information acquisition method, device, equipment and medium | |
| CN109688183A (en) | Group control device recognition methods, device, equipment and computer readable storage medium | |
| US11770458B1 (en) | Systems for exchanging data using intermediate devices | |
| CN103516851A (en) | Cloud testing platform system for wireless products | |
| CN112783731B (en) | Abnormal device detection method, device and storage medium | |
| JP2018088162A (en) | Information processing device, information processing method, and program | |
| CN109196460A (en) | Transmission method, server, storage system, terminal device and the system of data | |
| KR20150133509A (en) | Method for managing data flow and device for the same | |
| CN109450885B (en) | Network data interception method and device, electronic equipment and storage medium | |
| CN106251456B (en) | A kind of electronic queuing system and method | |
| CN108200604A (en) | Data transmission method and device | |
| CN108810243A (en) | Information displaying method, device, terminal and computer readable storage medium | |
| CN113342505A (en) | Thread identification method, thread identification device, storage medium and electronic equipment | |
| CN207853942U (en) | A kind of cloud platform management system based on mobile terminal |
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: 20181228 |
|
| RJ01 | Rejection of invention patent application after publication |