CN106778647A - A kind of method of recognition of face, server and system - Google Patents
A kind of method of recognition of face, server and system Download PDFInfo
- Publication number
- CN106778647A CN106778647A CN201611215206.1A CN201611215206A CN106778647A CN 106778647 A CN106778647 A CN 106778647A CN 201611215206 A CN201611215206 A CN 201611215206A CN 106778647 A CN106778647 A CN 106778647A
- Authority
- CN
- China
- Prior art keywords
- picture
- target photo
- server
- client
- similarity
- 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.)
- Granted
Links
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
- Studio Devices (AREA)
Abstract
The invention provides a kind of method of recognition of face, server and system.The system includes client and server.The client, for when user's click predeterminable area is detected, pointing out user to upload Target Photo；Wherein, the Target Photo is face samples pictures；The quantity of the Target Photo is at least two；The client, is additionally operable to send picture detection request to server；The server, for determining Target Photo set according to the pickup area；The server, is additionally operable to when it is determined that the picture processing pattern is intersection mode, travels through the Target Photo set to determine to match picture with the presence or absence of with the similarity of the Target Photo is all higher than predetermined threshold value in the Target Photo set；The server, if being additionally operable to match picture in the presence of what the similarity with the Target Photo was all higher than default similarity, the matching picture is sent to the client；The client, for showing the matching picture.
Description
Technical field
The present invention relates to field of face identification, and in particular to a kind of method of recognition of face, server and system.
Background technology
Face recognition technology refers to utilize image processing techniques, by camera acquisition facial image, and the figure to obtaining
A kind of technology of information is needed to obtain as comparing.At present, face recognition technology is widely used in security system, enterprise
The field such as industry management system and authentication.
And in practice, it has been found that when user needs other pictures that needs are obtained according to existing face print picture to believe
During breath, generally require the pictorial information that ceaselessly checking monitoring video camera or other picture pick-up devices collect and carry out manual identified needs
Image information, time-consuming for identification work, and efficiency is low, and inconvenience is brought to user.
The content of the invention
A kind of method of recognition of face, server and system are the embodiment of the invention provides, can be provided according to user
Whether the picture comprising face that picture searching monitor video is uploaded includes and user with the picture for determining monitor video upload
The picture that the picture of offer matches, and the picture that the match is successful is presented in predeterminated position；So as to not join manually
With in the case of, recognition of face is completed, and then greatly promote operating efficiency.
The system that embodiment of the present invention first aspect discloses recognition of face, the system includes client and server；
The client, for when user's click predeterminable area is detected, pointing out user to upload Target Photo；Wherein,
The Target Photo is face samples pictures；The quantity of the Target Photo is at least two；
The client, is additionally operable to detect the Target Photo and uploads when successfully, point out user's selection pickup area and
Picture processing pattern；
The client, is additionally operable to send picture detection request to server；Wherein, the picture detection request includes institute
State Target Photo, the pickup area and the picture processing pattern of user selection；
The server, for determining Target Photo set according to the pickup area；
The server, is additionally operable to when it is determined that the picture processing pattern is intersection mode, travel through the Target Photo
Gather with determine in the Target Photo set with the presence or absence of with the similarity of the Target Photo be all higher than predetermined threshold value
With picture；
The server, if exist in being additionally operable to the Target Photo set being all higher than with the similarity of the Target Photo
The matching picture of default similarity, then send the matching picture to the client；
The client, for showing the matching picture according to predetermined manner in Search Results viewing area.
With reference in a first aspect, in the first possible implementation of first aspect,
The client, is additionally operable to prompting user's seclected time section；
The client, is additionally operable to for the time period that the user selectes to be sent to the server；
The server, is additionally operable to judge whether the time period meets preset rules；
The server, specifically for when the time period preset rules are met, then according to adopting that the user selectes
Collection region and selected time period determine Target Photo set.
With reference to the first possible implementation of first aspect, in second possible implementation of first aspect,
The pickup area includes multiple regions；
The server, if there is the similarity with the Target Photo in being additionally operable to the Target Photo set more than pre-
If the matching picture of similarity, then the server determines the region belonging to each described matching picture；
The server, is additionally operable to count the quantity of the matching picture that each region includes；
The server, is additionally operable to match picture by the mark in each region and with corresponding to described each region
Quantity be sent to client；
The client, be additionally operable to display each region mark and with corresponding to described each area identification
Match the quantity of picture.
It is possible with reference to the first possible implementation of first aspect or first aspect or second of first aspect
Implementation, in the third possible implementation of first aspect,
The server, be additionally operable to determine the picture processing pattern for and during integrated mode, travel through the Target Photo collection
Close to determine to match picture more than predetermined threshold value with the presence or absence of the similarity with the first picture in the Target Photo set；Its
In, first picture is any one pictures in the Target Photo；
The server, if there is the similarity with first picture in being additionally operable to the Target Photo set more than pre-
If the matching picture of similarity, then the matching picture is sent to the client；
The client, for showing the matching picture according to predetermined manner in Search Results viewing area.
Second aspect present invention discloses a kind of server, it is characterised in that the server includes：
Receiving unit, the picture for receiving client transmission detects request；Wherein, the picture detection request includes institute
State the pickup area of Target Photo and user selection；The Target Photo is face samples pictures；The Target Photo
Quantity is at least two；
Determining unit, for determining Target Photo set according to the pickup area；
Traversal Unit, is additionally operable to when it is determined that the picture processing pattern is intersection mode, travel through the Target Photo collection
Close to determine in the Target Photo set with the presence or absence of being all higher than matching for predetermined threshold value with the similarity of the Target Photo
Picture；
Transmitting element, if there is the similarity with the Target Photo in being additionally operable to the Target Photo set more than default
The matching picture of similarity, then send the matching picture to the client.
With reference to second aspect, in the first possible implementation of second aspect, the server also includes judging
Unit；
The receiving unit, is additionally operable to receive the time period that the client sends；
The judging unit, is additionally operable to judge whether the time period meets preset rules；
The determining unit, specifically for when the time period preset rules are met, then the server is according to described
The pickup area and selected time period that user selectes determine Target Photo set.
With reference to the first possible implementation of second aspect, in second possible implementation of second aspect
In, the pickup area includes multiple regions；The server also includes statistic unit；
The determining unit, if exist in being additionally operable to the Target Photo set being more than with the similarity of the Target Photo
The matching picture of default similarity, it is determined that the region belonging to each described matching picture；
The statistic unit, the quantity for counting the matching picture that each region includes；
The transmitting element, is additionally operable to match figure by the mark in each region and with corresponding to described each region
The quantity of piece is sent to the client.
With reference to the first possible implementation or the second possible reality of second aspect of second aspect or second aspect
Existing mode, in the third possible implementation of second aspect,
The determining unit, be additionally operable to determine the picture processing pattern for and during integrated mode, travel through the Target Photo
Gather to determine to match picture more than predetermined threshold value with the presence or absence of the similarity with the first picture in the Target Photo set；
Wherein, first picture is any one pictures in the Target Photo；
The transmitting element, if exist in being additionally operable to the Target Photo set being more than with the similarity of first picture
The matching picture of default similarity, then send the matching picture to the client.
Third aspect present invention discloses a kind of method of recognition of face, and methods described includes：
Receive the picture detection request that client sends；Wherein, picture detection request include the Target Photo and
The pickup area of user's selection；The Target Photo is face samples pictures；The quantity of the Target Photo is at least two
；
Target Photo set is determined according to the pickup area；
When it is determined that the picture processing pattern is intersection mode, travel through the Target Photo set to determine the target
In picture set picture is matched with the presence or absence of the similarity with the Target Photo more than predetermined threshold value；
If exist in the Target Photo set matching figure more than default similarity with the similarity of the Target Photo
Piece, then send the matching picture to the client.
With reference to the third aspect, in the first possible implementation of the third aspect, the server is according to the use
Before the selected pickup area in family and selected time period determine Target Photo set, methods described also includes
Receive the time period that the client sends；
Judge whether the time period meets preset rules；
The pickup area and selected time period that the server is selected according to the user determine Target Photo set, wrap
Include：
When the time period preset rules are met, then the server is selected according to the user pickup area and choosing
The fixed time period determines Target Photo set.
With reference to the first possible implementation of the third aspect, in second possible implementation of the third aspect
In, the pickup area includes multiple regions；Methods described also includes：
If exist in the Target Photo set matching figure more than default similarity with the similarity of the Target Photo
Piece, it is determined that the region belonging to each described matching picture；
Count the quantity of the matching picture that each region includes；
It is sent to by the mark in each region and with the quantity for matching picture corresponding to described each region described
Client.
With reference to second possible implementation of the third aspect, in the third possible implementation of the third aspect
In,
The pickup area includes multiple regions；Methods described also includes：
When it is determined that the picture processing pattern is for simultaneously integrated mode, travel through the Target Photo set to determine the target
In picture set picture is matched with the presence or absence of the similarity with the first picture more than predetermined threshold value；Wherein, first picture
Any one pictures in for the Target Photo；
The server, if there is the similarity with first picture in being additionally operable to the Target Photo set more than pre-
If the matching picture of similarity, then the matching picture is sent to the client.
Fourth aspect present invention discloses a kind of server, and the server includes：
Be stored with the memory of executable program code；
The processor coupled with the memory；
The processor calls the executable program code stored in the memory, performs as described in the third aspect
Method.
As can be seen that disclosing a kind of face identification system in the scheme of the embodiment of the present invention, the system includes client
And server.The client, for when user's click predeterminable area is detected, pointing out user to upload Target Photo；Wherein,
The Target Photo is face samples pictures；The quantity of the Target Photo is at least two；The client, is additionally operable to detection
Uploaded when successfully to the Target Photo, point out user selection pickup area and picture processing pattern；The client, is additionally operable to
Picture detection request is sent to server；Wherein, the picture detection request includes that the Target Photo, the user are selected
Pickup area and the picture processing pattern；The server, for determining Target Photo set according to the pickup area；
The server, is additionally operable to when it is determined that the picture processing pattern is intersection mode, travel through the Target Photo set with true
In the fixed Target Photo set picture is matched with the presence or absence of with the similarity of the Target Photo is all higher than predetermined threshold value；Institute
Server is stated, if exist in being additionally operable to the Target Photo set being more than default similarity with the similarity of the Target Photo
Matching picture, then send the matching picture to the client；The client, for Search Results viewing area according to
Predetermined manner shows the matching picture.By said system, the picture searching monitor video that can be provided according to user is uploaded
The picture comprising face whether determining in the picture that monitor video is uploaded comprising the figure that matches of picture provided with user
Piece, and the picture that the match is successful is presented in predeterminated position；Know so as in the case where not participating in manually, complete face
Not, and then operating efficiency is greatly promoted.
Brief description of the drawings
Technical scheme in order to illustrate more clearly the embodiments of the present invention, below by to be used needed for embodiment
Accompanying drawing is briefly described, it should be apparent that, drawings in the following description are some embodiments of the present invention, general for this area
For logical technical staff, on the premise of not paying creative work, other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 is a kind of system schematic of recognition of face provided in an embodiment of the present invention；
Fig. 2 is a kind of structural representation of server provided in an embodiment of the present invention；
Fig. 3 is the structural representation of another server provided in an embodiment of the present invention；
Fig. 4 is a kind of schematic flow sheet of the method for recognition of face provided in an embodiment of the present invention；
Fig. 5 is the schematic flow sheet of the method for another recognition of face provided in an embodiment of the present invention；
Fig. 6 is a kind of physical arrangement schematic diagram of server provided in an embodiment of the present invention.
Specific embodiment
A kind of method of recognition of face, server and system are the embodiment of the invention provides, can be provided according to user
Whether the picture comprising face that picture searching monitor video is uploaded includes and user with the picture for determining monitor video upload
The picture that the picture of offer matches, and the picture that the match is successful is presented in predeterminated position；So as to not join manually
With in the case of, recognition of face is completed, and then greatly promote operating efficiency.
In order that those skilled in the art more fully understand the present invention program, below in conjunction with the embodiment of the present invention
Accompanying drawing, is explicitly described to the technical scheme in the embodiment of the present invention, it is clear that described embodiment is the present invention one
The embodiment divided, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not doing
Go out the every other embodiment obtained under the premise of creative work, should all belong to the scope of protection of the invention.
Term " first ", " second " and " the 3rd " occurred in description of the invention, claims and accompanying drawing etc. is to use
In the different objects of difference, and it is not intended to describe specific order.Additionally, term " comprising " and " having " and they are any
Deformation, it is intended that covering is non-exclusive to be included.For example contain process, method, system, the product of series of steps or unit
Or equipment is not limited to the step of having listed or unit, but alternatively also include the step of not listing or unit, or can
Selection of land also includes for these processes, method, product or other intrinsic steps of equipment or unit.
A kind of system of recognition of face is disclosed in one embodiment of the invention, it is characterised in that the system bag
Include client and server；The client, for when user's click predeterminable area is detected, pointing out user to upload target figure
Piece；Wherein, the Target Photo is face samples pictures；The quantity of the Target Photo is at least two；The client, also
Uploaded when successfully for detecting the Target Photo, point out user selection pickup area and picture processing pattern；The client
End, is additionally operable to send picture detection request to server；Wherein, picture detection request includes the Target Photo, described
The pickup area and the picture processing pattern of user's selection；The server, for determining mesh according to the pickup area
Mark on a map piece set；The server, is additionally operable to when it is determined that the picture processing pattern is intersection mode, travel through the target figure
Piece set is determining in the Target Photo set with the presence or absence of being all higher than predetermined threshold value with the similarity of the Target Photo
Matching picture；The server, if exist in being additionally operable to the Target Photo set being more than with the similarity of the Target Photo
The matching picture of default similarity, then send the matching picture to the client；The client, in Search Results
Viewing area shows the matching picture according to predetermined manner.
Fig. 1 is referred to, Fig. 1 is a kind of system 100 of recognition of face that one embodiment of the invention is provided.The system bag
Include client 10 and server 20.
, wherein it is desired to, it is noted that client 10 can be in smart mobile phone, panel computer, intelligent wearable equipment, calculating
Run on the electronic equipments such as machine.
Wherein, server 20 can be distributed server, or cloud data center, not be limited herein.
Wherein it is possible to understand, server 20 can connect multiple cameras, and camera can be to appearing in camera lens
Personage carry out real-time grasp shoot record, when occurring face in monitoring range, camera will capture automatically and by facial image with
The time mode of stream is sent in server 20.
Client 10, for when user's click predeterminable area is detected, pointing out user to upload Target Photo；
Wherein, the Target Photo includes face samples pictures, and the quantity of the Target Photo is at least two.
It is pointed out that predeterminable area can be a picture box, or a button, a blank is can also be
Region, is not limited herein.
Wherein it is possible to understand, user can also pull picture to predeterminable area.
Wherein, the form of Target Photo includes but is not limited to JPEG, BMP etc..
Wherein it is possible to understand, user can be used as Target Photo from picture is locally selected, it is also possible to call shooting
Head is shot to obtain Target Photo.
Wherein, user can be clicked with left button, or right button is clicked, and can also be double-clicked, and be not limited herein.
Client 10, is additionally operable to detect the Target Photo and uploads when successfully, points out user selection pickup area and figure
As tupe；
It is understood that the pickup area can be divided according to administrative region.Such as face of certain municipal police office
Pickup area bag A local police stations pickup area, B local police stations pickup area, C local police stations pickup area of identifying system etc..
It is understood that can also freely define, such as certain one layer of pickup area of building, two layers of pickup area etc.
Deng.Can also be teaching building region, dormitory region, dining room region of certain school etc..
Wherein, image processing mode includes but does not limit intersection mode and and integrated mode.
Client 10, is additionally operable to send picture detection request to server 20；Wherein, the picture detection request includes institute
State Target Photo, the pickup area and the picture processing pattern of user selection.
It is understood that the purpose of picture detection request is to allow server 20 to detect described described in client 10
Whether the photo matched with the Target Photo is photographed in pickup area.
Server 20, for determining Target Photo set according to the pickup area；
It is understood that such as pickup area is school dining room, then Target Photo set is exactly that the dining room owns
The captured photo including face in preset time range of camera.Wherein, the preset time range can be acquiescence,
Can also be artificial setting, such as can be three months in, in one month, in even three days etc., it is not limited herein.
Server 20, is additionally operable to when it is determined that the picture processing pattern is intersection mode, travel through the Target Photo collection
Close to determine in the Target Photo set with the presence or absence of being all higher than matching for predetermined threshold value with the similarity of the Target Photo
Picture；
For example, such as Target Photo is now two pictures, respectively A pictures and B pictures, if Target Photo collection
There is a pictures C in conjunction, wherein, the similarity of C and A is more than predetermined threshold value, and the similarity of C and B is more than predetermined threshold value, that
C is exactly to match picture.
, wherein it is desired to, it is noted that images match refer to by certain matching algorithm between two width or multiple image
By the coefficient correlation of the window of formed objects in comparison object area and the field of search in identification same place, such as two dimensional image matching,
The window center point in the field of search corresponding to coefficient correlation maximum is taken as same place.Its essence is the condition in primitive similitude
Under, with the optimal search problem of matching criterior.
Wherein, images match can be divided mainly into the matching based on gray scale and the matching based on feature.
Wherein, the basic thought of Gray-scale Matching:2D signal as is regarded image with the viewpoint for counting, using statistical correlation
Method find signal between relevant matches.Using two correlation functions of signal, their similitude is evaluated of the same name to determine
Point.Gray-scale Matching by using certain similarity measurement, such as correlation function, covariance function, difference quadratic sum, difference absolute value and
Estimate extreme value, judge the corresponding relation in two images.
Wherein, characteristic matching refer to by extracting the feature of two or more images (feature such as point, line, surface) respectively, it is right
Feature enters line parameter description, a kind of algorithm for then being matched with described parameter.Residing for feature-based matching
The feature that the image of reason is generally comprised has color characteristic, textural characteristics, shape facility, locus feature etc..Characteristic matching is first
First image is pre-processed to extract its high-level feature, the matching correspondence pass of feature between two images is then set up
System, usually used feature primitive has point feature, edge feature and provincial characteristics.Characteristic matching needs to use many such as matrixes
Computing, the solution of gradient, also have the mathematical operation such as Fourier transform and Taylor expansion.Conventional feature extracting and matching method
Have：Statistical method, geometric method, modelling, signal transacting method, boundary characteristic method, fourier shape description method, geometry parameter method, shape
Shape Moment invariants etc..
Server 20, if pre- in the presence of being all higher than with the similarity of the Target Photo in being additionally operable to the Target Photo set
If the matching picture of similarity, then the matching picture is sent to client 10；
Wherein, the default similarity can be system default, can also be artificial setting, not show herein.
For example, default similarity can be 90%, 92%, 95% etc..
Client 10, for showing the matching picture according to predetermined manner in Search Results viewing area.
Wherein it is possible to understand, Search Results viewing area can be the position of system default, can also be that user selectes
Position.
Wherein, show that the matching picture includes according to predetermined manner：Time sequencing according to shooting shows the matching
Picture；
Wherein, show that the matching picture includes according to predetermined manner：According to the numbering of the video camera belonging to matching picture
Shown.The matching picture that No. 1 video camera shoots such as first is shown, then shows the matching picture that No. 2 video cameras shoot, herein
It is not limited.
Wherein it is possible to understand, if matching picture is excessive, user can be checked with page turning.
Optionally, in addition to according to Target Photo and pickup area search matching picture, the system can be with for the system
Picture searching is carried out according to Target Photo, time period and pickup area.
Client 10, is additionally operable to prompting user's seclected time section；
Wherein, the time period can user input, or user selected on the calendar that system is provided.
Wherein, the dimension of the time period can with difference, can specific to day, can also specific to hour or minute,
This is not limited.
Client 10, is additionally operable to for the time period that the user selectes to be sent to server 20；
Server 20, is additionally operable to judge whether the time period meets preset rules；
Such as, the time period should be the past time, if being related to the time in future, the time period does not just meet
Preset rules.
Server 20, specifically for when the time period preset rules are met, then server 20 is selected according to the user
Fixed pickup area and selected time period determines Target Photo set.
Optionally, the pickup area includes multiple regions；The number of the matching picture that each region includes can also be determined
Amount；Specifically：
Server 20, if there is the similarity with the Target Photo in being additionally operable to the Target Photo set more than default
The matching picture of similarity, it is determined that the region belonging to each described matching picture；
For example, such as user have selected the dining room region and dormitory region of certain school at that time, then will will match
Picture is classified, to determine every source of matching.That is, which region every matching picture is belonging to.Dining room
What video camera shot just belongs to dining room region, and what similarly dormitory video camera shot just belongs to dormitory region.
For example, if when user have selected A local police stations region and B local police stations region, then which will now determine
A little matching pictures are that the camera in A local police stations region shoots, and the matching picture that A local police stations camera shoots just belongs to A and sends
Institute region.
Server 20, is additionally operable to count the quantity of the matching picture that each region includes；
Such as, matching picture has 100 altogether.The matching picture that so A local police stations include may just have 60, B local police stations
Comprising matching picture may just have 40.
Server 20, be additionally operable to by the mark in each region and with the picture that matches corresponding to described each region
Quantity is sent to client；
Client 10, be additionally operable to display each region mark and with corresponding to described each area identification
Quantity with picture.
Wherein, client 10 can be shown in the form of a list.
Optionally, each pickup area has multiple video cameras, then user can select the shooting of each pickup area
Machine inquires about the matching picture of the shot by camera chosen.It is specific as follows：
Client 10, is additionally operable to, when detecting the user and choosing the mark of first area, be sent to server 20 and believed
Breath obtains request, and described information obtains request includes the mark of the first area；Wherein, the first area is described many
Any one region in individual region；
Such as, row's area identification, such as A local police stations, B local police stations etc. are shown on the interface of client 10.
Server 20, the corresponding target area of mark for determining the first area, and obtain the target area
Inside photograph the mark of the video camera of matching picture；
Such as, user have selected the mark in A local police stations, then will now show photographing in A local police stations region
The mark of the video camera with picture.Such as video camera A (3), means that video camera A has photographed 3 matching pictures.
Server 20, is additionally operable to the mark to video camera described in client feedback；
Client 10, the camera identification of matching picture is photographed for showing in the first area；Wherein, described
One target area is any one region in the multiple target area；
Client 10, is additionally operable to, when detecting the first camera identification and being selected, show the ground of first video camera
Reason position, the matching picture for shooting and every shooting time of matching picture；Wherein, first camera identification is many
Any one camera identification in the individual camera identification.
Wherein it is possible to understand, when the user clicks on the mark of video camera A, the installation position of video camera A will be shown
Put, and the 3 matching pictures for shooting, and every shooting time of matching picture.Other information is not being enumerated herein.
Wherein, when the user clicks on the mark of video camera A, the installation position of video camera A can be directly shown on map
Put.
Server 20, be additionally operable to determine the picture processing pattern for and during integrated mode, travel through the Target Photo set
To determine to match picture more than predetermined threshold value with the presence or absence of the similarity with the picture in the Target Photo set；Its
In, first picture is any one pictures in the Target Photo；
The server 20, if exist in being additionally operable to the Target Photo set being more than with the similarity of the Target Photo
The matching picture of default similarity, then send the matching picture to the client；
The client 10, for showing the matching picture according to predetermined manner in Search Results viewing area.
Optionally, if the picture processing pattern for and during integrated mode, server 20 will judge Target Photo set
In with the presence or absence of the picture that matches with the similarity of the first picture more than predetermined threshold value, the first picture is any in Target Photo
One pictures.
Specifically, server 20, be additionally operable to determine the picture processing pattern for and during integrated mode, travel through the target figure
Piece set is determining to match figure more than predetermined threshold value with the presence or absence of the similarity with the first picture in the Target Photo set
Piece；Wherein, first picture is any one pictures in the Target Photo；
Server 20, if there is the similarity with first picture in being additionally operable to the Target Photo set more than default
The matching picture of similarity, then send the matching picture to the client；
For example, Target Photo includes picture A and B, if in the presence of pictures a C's, C and A in Target Photo set
Similarity is more than predetermined threshold value, or the similarity of C and B is more than predetermined threshold value, then C is exactly to match picture.
Client 10, for showing the matching picture according to predetermined manner in Search Results viewing area.
As shown in Fig. 2 Fig. 2 describes the concrete structure of server 20, server 20 includes：
Receiving unit 210, the picture for receiving client transmission detects request；Wherein, the picture detection request bag
Include the pickup area of the Target Photo and user selection；The Target Photo is face samples pictures；The target figure
The quantity of piece is at least two；
Determining unit 220, for determining Target Photo set according to the pickup area；
Traversal Unit 230, is additionally operable to when it is determined that the picture processing pattern is intersection mode, travel through the Target Photo
Gather with determine in the Target Photo set with the presence or absence of with the similarity of the Target Photo be all higher than predetermined threshold value
With picture；
Transmitting element 240, if exist in being additionally operable to the Target Photo set being more than with the similarity of the Target Photo
The matching picture of default similarity, then send the matching picture to the client.
Based on Fig. 2, as shown in figure 3, server 20 also includes judging unit 250；
Receiving unit 210, is additionally operable to receive the time period that client 10 sends；
Judging unit 250, is additionally operable to judge whether the time period meets preset rules；
Determining unit 220, specifically for when the time period preset rules are met, then server 20 is according to the user
Selected pickup area and selected time period determines Target Photo set.
Optionally, the determining unit 220, be additionally operable to determine the picture processing pattern for and during integrated mode, travel through institute
Target Photo set is stated to determine to be more than predetermined threshold value with the presence or absence of the similarity with the picture in the Target Photo set
Matching picture；Wherein, first picture is any one pictures in the Target Photo；
Transmitting element 240, if exist in being additionally operable to the Target Photo set being more than with the similarity of the Target Photo
The matching picture of default similarity, then send the matching picture to the client.
As shown in figure 4, Fig. 4 discloses a kind of method of recognition of face, the main body that the method is performed is server, the side
Method includes：
S301, the picture detection request for receiving client transmission.
Wherein, the picture detection request includes the pickup area of the Target Photo and user selection；The mesh
Piece of marking on a map is face samples pictures；The quantity of the Target Photo is at least two.
S302, Target Photo set is determined according to the pickup area.
S303, when it is determined that the picture processing pattern is intersection mode, travel through the Target Photo set to determine
State in Target Photo set and match picture more than predetermined threshold value with the presence or absence of the similarity with the Target Photo.
If exist in S304, the Target Photo set with the similarity of the Target Photo be more than default similarity
With picture, then the matching picture is sent to the client.
From the above it can be seen that the invention provides a kind of method of recognition of face, server receives the picture inspection that client sends
Survey request；Wherein, the picture detection request includes the pickup area of the Target Photo and user selection；The target
Picture is face samples pictures；The quantity of the Target Photo is at least two；Target Photo is determined according to the pickup area
Set；When it is determined that the picture processing pattern is intersection mode, travel through the Target Photo set to determine the target figure
In piece set picture is matched with the presence or absence of the similarity with the Target Photo more than predetermined threshold value；If the Target Photo collection
Exist in conjunction and match picture more than default similarity with the similarity of the Target Photo, then send described to the client
Matching picture.The picture comprising face uploaded by the above method, the picture searching monitor video that can be provided according to user
Whether determining in the picture that monitor video is uploaded comprising the picture that matches of picture provided with user, and by the match is successful
Picture is presented in predeterminated position；So as in the case where not participating in manually, complete recognition of face, and then greatly promote work
Make efficiency.
As shown in figure 5, Fig. 5 discloses a kind of method of recognition of face, the main body that the method is performed is server, the side
Method includes：
S401, the picture detection request for receiving client transmission；Wherein, the picture detection request includes the target figure
Piece and the pickup area of user selection；The Target Photo is face samples pictures；The quantity of the Target Photo is at least
It is two；
S402, Target Photo set is determined according to the pickup area；
S403, when it is determined that the picture processing pattern is intersection mode, travel through the Target Photo set to determine
State in Target Photo set and match picture more than predetermined threshold value with the presence or absence of the similarity with the Target Photo；
If exist in S404, the Target Photo set with the similarity of the Target Photo be more than default similarity
With picture, then the matching picture is sent to the client.
S405, when it is determined that the picture processing pattern for and during integrated mode, travel through the Target Photo set to determine
State in Target Photo set and match picture more than predetermined threshold value with the presence or absence of the similarity with the first picture；Wherein, described
One picture is any one pictures in the Target Photo.
If exist in S406, the Target Photo set with the similarity of first picture be more than default similarity
With picture, then the matching picture is sent to the client.
S407, the time period for receiving the client transmission；
S408, judge whether the time period meets preset rules；
S409, when the time period preset rules are met, then the acquisition zone that the server is selected according to the user
Domain and selected time period determine Target Photo set.
It is hereby understood that the present embodiment has expanded picture processing pattern being and integrated mode and the collection selected according to the user
The step of region and selected time period determine Target Photo set, so as to further improve operating efficiency.
Fig. 6 is referred to, in another embodiment of the present invention, there is provided a kind of server.The server 500 includes
CPU501, memory 502, bus 503.
Wherein, CPU501 performs the program being stored in advance in memory 502, and the implementation procedure is specifically included：
Receive the picture detection request that client sends；Wherein, picture detection request include the Target Photo and
The pickup area of user's selection；The Target Photo is face samples pictures；The quantity of the Target Photo is at least two
；
Target Photo set is determined according to the pickup area；
When it is determined that the picture processing pattern is intersection mode, travel through the Target Photo set to determine the target
In picture set picture is matched with the presence or absence of the similarity with the Target Photo more than predetermined threshold value；
If exist in the Target Photo set matching figure more than default similarity with the similarity of the Target Photo
Piece, then send the matching picture to the client.
Optionally, the pickup area and selected time period that the server is selected according to the user determine Target Photo
Before set, the implementation procedure also includes：
Receive the time period that the client sends；
Judge whether the time period meets preset rules；
The pickup area and selected time period that the server is selected according to the user determine Target Photo set, wrap
Include：
When the time period preset rules are met, then the server is selected according to the user pickup area and choosing
The fixed time period determines Target Photo set.
Optionally, the pickup area includes multiple regions；The implementation procedure also includes：
Determine the picture processing pattern for and during integrated mode, the Target Photo set is traveled through to determine the target figure
In piece set picture is matched with the presence or absence of the similarity with the first picture more than predetermined threshold value；Wherein, first picture is
Any one pictures in the Target Photo；
If exist in the Target Photo set matching figure more than default similarity with the similarity of first picture
Piece, then send the matching picture to the client.
As can be seen that in the scheme of the embodiment of the present invention, server receives the picture detection request that client sends；Its
In, the picture detection request includes the pickup area of the Target Photo and user selection；The Target Photo is behaved
Face samples pictures；The quantity of the Target Photo is at least two；Target Photo set is determined according to the pickup area；When true
When the fixed picture processing pattern is intersection mode, travel through the Target Photo set to determine to be in the Target Photo set
The no similarity in the presence of with the Target Photo matches picture more than predetermined threshold value；If in the Target Photo set exist with
The similarity of the Target Photo is more than the matching picture of default similarity, then send the matching picture to the client.
By the above method, the picture comprising face of the picture searching monitor video upload that can be provided according to user is to determine monitoring
Whether the picture that the picture provided with user matches is included in the picture that video is uploaded, and the picture that the match is successful is being preset
Position is presented；So as in the case where not participating in manually, complete recognition of face, and then greatly promote operating efficiency.
In embodiment shown in earlier figures 4, Fig. 5, the structure that each step method flow can be based on the server is realized.
In embodiment shown in earlier figures 2, Fig. 3, the structure that each unit function can be based on the server is realized.
In the above-described embodiments, the description to each embodiment all emphasizes particularly on different fields, and does not have the portion described in detail in certain embodiment
Point, may refer to the associated description of other embodiment.
In several embodiments provided herein, it should be understood that disclosed device, can be by another way
Realize.For example, device embodiment described above is only schematical, such as the division of described unit is only one kind
Division of logic function, can there is other dividing mode when actually realizing, such as multiple units or component can combine or can
To be integrated into another system, or some features can be ignored, or not perform.It is another, it is shown or discussed each other
Coupling or direct-coupling or communication connection can be the INDIRECT COUPLING or communication connection of device or unit by some interfaces,
Can be electrical or other forms.
The unit that is illustrated as separating component can be or may not be it is physically separate, it is aobvious as unit
The part for showing can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be according to the actual needs selected to realize the mesh of this embodiment scheme
's.
In addition, during each functional unit in each embodiment of the invention can be integrated in a processing unit, it is also possible to
It is that unit is individually physically present, it is also possible to which two or more units are integrated in a unit.Above-mentioned integrated list
Unit can both be realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.
If the integrated unit is to realize in the form of SFU software functional unit and as independent production marketing or use
When, can store in a computer read/write memory medium.Based on such understanding, technical scheme is substantially
The part for being contributed to prior art in other words or all or part of the technical scheme can be in the form of software products
Embody, the computer software product is stored in a storage medium, including some instructions are used to so that a computer
Equipment (can be personal computer, server or network equipment etc.) perform each embodiment methods described of the invention whole or
Part steps.And foregoing storage medium includes：USB flash disk, read-only storage (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), mobile hard disk, magnetic disc or CD etc. are various can be with store program codes
Medium.
The above, the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although with reference to preceding
Embodiment is stated to be described in detail the present invention, it will be understood by those within the art that：It still can be to preceding
State the technical scheme described in each embodiment to modify, or equivalent is carried out to which part technical characteristic；And these
Modification is replaced, and does not make the scope of the essence disengaging various embodiments of the present invention technical scheme of appropriate technical solution.
Claims (10)
1. a kind of system of recognition of face, it is characterised in that the system includes client and server；
The client, for when user's click predeterminable area is detected, pointing out user to upload Target Photo；Wherein, it is described
Target Photo is face samples pictures；The quantity of the Target Photo is at least two；
The client, is additionally operable to detect the Target Photo and uploads when successfully, points out user selection pickup area and picture
Tupe；
The client, is additionally operable to send picture detection request to server；Wherein, the picture detection request includes the mesh
Mark on a map piece, the user selection pickup area and the picture processing pattern；
The server, for determining Target Photo set according to the pickup area；
The server, is additionally operable to when it is determined that the picture processing pattern is intersection mode, travel through the Target Photo set
To determine to match figure with the presence or absence of with the similarity of the Target Photo is all higher than predetermined threshold value in the Target Photo set
Piece；
The server, if exist in being additionally operable to the Target Photo set to be all higher than presetting with the similarity of the Target Photo
The matching picture of similarity, then send the matching picture to the client；
The client, for showing the matching picture according to predetermined manner in Search Results viewing area.
2. system according to claim 1, it is characterised in that
The client, is additionally operable to prompting user's seclected time section；
The client, is additionally operable to for the time period that the user selectes to be sent to the server；
The server, is additionally operable to judge whether the time period meets preset rules；
The server, specifically for when the time period preset rules are met, then the acquisition zone selected according to the user
Domain and selected time period determine Target Photo set.
3. system according to claim 2, it is characterised in that the pickup area includes multiple regions；
The server, if exist in being additionally operable to the Target Photo set being more than default phase with the similarity of the Target Photo
Like degree matching picture, then the server determine each it is described matching picture belonging to region；
The server, is additionally operable to count the quantity of the matching picture that each region includes；
The server, be additionally operable to by the mark in each region and with the number for matching picture corresponding to described each region
Amount is sent to client；
The client, be additionally operable to display each region mark and with matching corresponding to described each area identification
The quantity of picture.
4. according to any described system of claims 1 to 3, it is characterised in that
The server, be additionally operable to determine the picture processing pattern for and during integrated mode, travel through the Target Photo set with
Determine to match picture more than predetermined threshold value with the presence or absence of the similarity with the first picture in the Target Photo set；Wherein,
First picture is any one pictures in the Target Photo；
The server, if exist in being additionally operable to the Target Photo set being more than default phase with the similarity of first picture
Like the matching picture of degree, then the matching picture is sent to the client；
The client, for showing the matching picture according to predetermined manner in Search Results viewing area.
5. a kind of server, it is characterised in that the server includes：
Receiving unit, the picture for receiving client transmission detects request；Wherein, the picture detection request includes the mesh
Mark on a map piece and the user selection pickup area；The Target Photo is face samples pictures；The quantity of the Target Photo
At least two；
Determining unit, for determining Target Photo set according to the pickup area；
Traversal Unit, is additionally operable to when it is determined that the picture processing pattern is intersection mode, travel through the Target Photo set with
Determine to match picture with the presence or absence of with the similarity of the Target Photo is all higher than predetermined threshold value in the Target Photo set；
Transmitting element, if existing in being additionally operable to the Target Photo set similar more than default to the similarity of the Target Photo
The matching picture of degree, then send the matching picture to the client.
6. server according to claim 5, it is characterised in that the server also includes judging unit；
The receiving unit, is additionally operable to receive the time period that the client sends；
The judging unit, is additionally operable to judge whether the time period meets preset rules；
The determining unit, specifically for when the time period preset rules are met, then the server is according to the user
Selected pickup area and selected time period determines Target Photo set.
7. the server according to claim 5 or 6, it is characterised in that
The determining unit, be additionally operable to determine the picture processing pattern for and during integrated mode, travel through the Target Photo set
To determine to match picture more than predetermined threshold value with the presence or absence of the similarity with the first picture in the Target Photo set；Its
In, first picture is any one pictures in the Target Photo；
The transmitting element, if there is the similarity with first picture in being additionally operable to the Target Photo set more than default
The matching picture of similarity, then send the matching picture to the client.
8. a kind of method of recognition of face, it is characterised in that methods described includes：
Receive the picture detection request that client sends；Wherein, picture detection request includes the Target Photo and described
The pickup area of user's selection；The Target Photo is face samples pictures；The quantity of the Target Photo is at least two；
Target Photo set is determined according to the pickup area；
When it is determined that the picture processing pattern is intersection mode, travel through the Target Photo set to determine the Target Photo
In set picture is matched with the presence or absence of the similarity with the Target Photo more than predetermined threshold value；
If exist in the Target Photo set matching picture more than default similarity with the similarity of the Target Photo,
The matching picture is sent to the client.
9. method according to claim 8, it is characterised in that the pickup area that the server is selected according to the user
Before determining Target Photo set with the selected time period, methods described also includes
Receive the time period that the client sends；
Judge whether the time period meets preset rules；
The pickup area and selected time period that the server is selected according to the user determine Target Photo set, including：
When the time period preset rules are met, then the server is selected according to the user pickup area and selected
Time period determines Target Photo set.
10. method according to claim 8 or claim 9, it is characterised in that the pickup area includes multiple regions；The side
Method also includes：
When it is determined that the picture processing pattern is for simultaneously integrated mode, travel through the Target Photo set to determine the Target Photo
In set picture is matched with the presence or absence of the similarity with the first picture more than predetermined threshold value；Wherein, first picture is institute
State any one pictures in Target Photo；
If exist in the Target Photo set matching picture more than default similarity with the similarity of first picture,
The matching picture is sent to the client.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611215206.1A CN106778647B (en) | 2016-12-24 | 2016-12-24 | A kind of method of recognition of face, server and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611215206.1A CN106778647B (en) | 2016-12-24 | 2016-12-24 | A kind of method of recognition of face, server and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106778647A true CN106778647A (en) | 2017-05-31 |
| CN106778647B CN106778647B (en) | 2018-07-17 |
Family
ID=58927215
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611215206.1A Active CN106778647B (en) | 2016-12-24 | 2016-12-24 | A kind of method of recognition of face, server and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106778647B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104133899A (en) * | 2014-08-01 | 2014-11-05 | 百度在线网络技术（北京）有限公司 | Method and device for generating picture search library and method and device for searching for picture |
| CN104317946A (en) * | 2014-10-31 | 2015-01-28 | 上海交通大学 | Multi-key image-based image content retrieval method |
| US20150098632A1 (en) * | 2013-10-08 | 2015-04-09 | Omron Corporation | Monitoring system, monitoring method, monitoring program, and recording medium in which monitoring program is recorded |
| CN105095831A (en) * | 2014-05-04 | 2015-11-25 | 深圳市贝尔信智能系统有限公司 | Face recognition method, device and system |
| CN105956051A (en) * | 2016-04-26 | 2016-09-21 | 乐视控股（北京）有限公司 | Information finding method, device and system |
-
2016
- 2016-12-24 CN CN201611215206.1A patent/CN106778647B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150098632A1 (en) * | 2013-10-08 | 2015-04-09 | Omron Corporation | Monitoring system, monitoring method, monitoring program, and recording medium in which monitoring program is recorded |
| CN105095831A (en) * | 2014-05-04 | 2015-11-25 | 深圳市贝尔信智能系统有限公司 | Face recognition method, device and system |
| CN104133899A (en) * | 2014-08-01 | 2014-11-05 | 百度在线网络技术（北京）有限公司 | Method and device for generating picture search library and method and device for searching for picture |
| CN104317946A (en) * | 2014-10-31 | 2015-01-28 | 上海交通大学 | Multi-key image-based image content retrieval method |
| CN105956051A (en) * | 2016-04-26 | 2016-09-21 | 乐视控股（北京）有限公司 | Information finding method, device and system |
Non-Patent Citations (1)
| Title |
|---|
| 邓健康 等: "基于移动平台的快速相似脸检索", 《北京航空航天大学学报》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106778647B (en) | 2018-07-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106844492B (en) | A kind of method of recognition of face, client, server and system | |
| CN108596277B (en) | Vehicle identity recognition method and device and storage medium | |
| CN107093171B (en) | Image processing method, device and system | |
| CN105745687B (en) | Context aware Moving target detection | |
| CN109685141B (en) | Robot article sorting visual detection method based on deep neural network | |
| TWI416068B (en) | Object tracking method and apparatus for a non-overlapping-sensor network | |
| US9613258B2 (en) | Image quality assessment | |
| CN108090406B (en) | Face recognition method and system | |
| CN109215055A (en) | A kind of target's feature-extraction method, apparatus and application system | |
| CN109887040A (en) | The moving target actively perceive method and system of facing video monitoring | |
| CN103679674A (en) | Method and system for splicing images of unmanned aircrafts in real time | |
| CN105740426A (en) | Human face recognition based picture sending method and apparatus | |
| CN111898486B (en) | Monitoring picture abnormality detection method, device and storage medium | |
| CN110825900A (en) | Training method of feature reconstruction layer, reconstruction method of image features and related device | |
| CN109409250A (en) | A kind of across the video camera pedestrian of no overlap ken recognition methods again based on deep learning | |
| CN109784171A (en) | Car damage identification method for screening images, device, readable storage medium storing program for executing and server | |
| CN111460884A (en) | Multi-face recognition method based on human body tracking | |
| CN111263955A (en) | Method and device for determining movement track of target object | |
| CN111723773A (en) | Remnant detection method, device, electronic equipment and readable storage medium | |
| CN111291646A (en) | People flow statistical method, device, equipment and storage medium | |
| CN110992500B (en) | Attendance checking method and device, storage medium and server | |
| CN112132892A (en) | Target position marking method, device and equipment | |
| CN106845355B (en) | A kind of method of recognition of face, server and system | |
| CN110287957B (en) | Low-slow small target positioning method and positioning device | |
| CN110738229B (en) | Fine-grained image classification method and device and electronic equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |