CN109446893A - Face identification method, device, computer equipment and storage medium - Google Patents
Face identification method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109446893A CN109446893A CN201811075694.XA CN201811075694A CN109446893A CN 109446893 A CN109446893 A CN 109446893A CN 201811075694 A CN201811075694 A CN 201811075694A CN 109446893 A CN109446893 A CN 109446893A
- Authority
- CN
- China
- Prior art keywords
- face
- processed
- target face
- profile
- candidate target
- 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
- 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
-
- 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
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses face identification method, device, computer equipment and storage mediums, and wherein method includes: the profile information for obtaining every face in picture to be processed respectively；It executes following operation for face to be processed using every face in picture as face to be processed respectively: filtering out the candidate target face being consistent with the profile information of face to be processed from target face database；The target face to match with face to be processed is selected from candidate target face.Using scheme of the present invention, treatment effeciency etc. can be improved.
Description
[technical field]
The present invention relates to Computer Applied Technology, in particular to face identification method, device, computer equipment and storage is situated between
Matter.
[background technique]
Currently, when carrying out recognition of face, it will usually by the way of full library searching, i.e., by the people in picture to be processed
Face is compared with every target face in target face database respectively, to determine the target face to match.This mode by
In needing to carry out full library searching, therefore inefficiency.
[summary of the invention]
In view of this, the present invention provides face identification method, device, computer equipment and storage mediums.
Specific technical solution is as follows:
A kind of face identification method, comprising:
The profile information of every face in picture to be processed is obtained respectively；
It is executed following using every face in the picture as face to be processed for the face to be processed respectively
Operation:
The candidate target face being consistent with the profile information of the face to be processed is filtered out from target face database；
The target face to match with the face to be processed is selected from candidate target face.
According to one preferred embodiment of the present invention, the profile information for obtaining every face in picture to be processed respectively
Include:
The profile diagram of every face in the picture is extracted respectively；
By analyzing the profile diagram, the corresponding profile label of each profile diagram is generated respectively.
According to one preferred embodiment of the present invention, the profile filtered out from target face database with the face to be processed
The candidate target face that information is consistent includes:
For every target face in the target face database, the delineator of the target face saved is calculated separately
Similarity between label and the profile label of the face to be processed, if the similarity is greater than or equal to preset threshold
Value, then be determined as the candidate target face for the target face.
According to one preferred embodiment of the present invention, described select from candidate target face matches with the face to be processed
Target face include:
Obtain the face characteristic of the face to be processed；
For every candidate target face, calculate separately the face characteristic of the candidate target face saved with it is described
Similarity between the face characteristic of face to be processed；
The maximum candidate target face of similarity is determined as the target face to match with the face to be processed.
A kind of face identification device, comprising: acquiring unit and recognition unit；
The acquiring unit, for obtaining the profile information of every face in picture to be processed respectively；
The recognition unit, for respectively using every face in the picture as face to be processed, for it is described to
Face is handled, following operation is executed: filtered out from target face database and be consistent with the profile information of the face to be processed
Candidate target face；The target face to match with the face to be processed is selected from candidate target face.
According to one preferred embodiment of the present invention, the acquiring unit extracts the wheel of every face in the picture respectively
Exterior feature figure, by analyzing the profile diagram, generates the corresponding profile label of each profile diagram respectively.
According to one preferred embodiment of the present invention, the recognition unit is directed to every target face in the target face database,
The similarity between the profile label of the target face saved and the profile label of the face to be processed is calculated separately,
If the similarity is greater than or equal to preset threshold value, the target face is determined as the candidate target face.
According to one preferred embodiment of the present invention, the recognition unit obtains the face characteristic of the face to be processed, for
Every candidate target face calculates separately the face characteristic and the face to be processed of the candidate target face saved
The maximum candidate target face of similarity is determined as matching with the face to be processed by the similarity between face characteristic
Target face.
A kind of computer equipment, including memory, processor and be stored on the memory and can be in the processor
The computer program of upper operation, the processor realize method as described above when executing described program.
A kind of computer readable storage medium is stored thereon with computer program, real when described program is executed by processor
Now method as described above.
Can be seen that based on above-mentioned introduction can for every face in picture to be processed using scheme of the present invention
Preliminary screening is carried out to the target face in target face database first with the profile information of the face of acquisition, to obtain candidate
Target face, and then the target face to match can be finally selected from candidate target face, compared to existing way, the present invention
Candidate target face quickly first can be oriented based on profile information in the scheme, subsequent need to compare to considerably reduce
Face quantity, and then improve treatment effeciency.
[Detailed description of the invention]
Fig. 1 is the flow chart of face identification method first embodiment of the present invention.
Fig. 2 is the flow chart of face identification method second embodiment of the present invention.
Fig. 3 is the composed structure schematic diagram of face identification device embodiment of the present invention.
Fig. 4 shows the block diagram for being suitable for the exemplary computer system/server 12 for being used to realize embodiment of the present invention.
[specific embodiment]
In order to be clearer and more clear technical solution of the present invention, hereinafter, referring to the drawings and the embodiments, to institute of the present invention
The scheme of stating is further described.
Obviously, described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on the present invention
In embodiment, those skilled in the art's all other embodiment obtained without creative efforts, all
Belong to the scope of protection of the invention.
Fig. 1 is the flow chart of face identification method first embodiment of the present invention.As shown in Figure 1, including in detail below
Implementation.
In 101, the profile information of every face in picture to be processed is obtained respectively.
In 102, respectively using every face in picture as face to be processed, for face to be processed, execute 103~
Operation shown in 104.
In 103, the candidate target people being consistent with the profile information of face to be processed is filtered out from target face database
Face.
In 104, the target face to match with face to be processed is selected from candidate target face.
In the present embodiment, in picture to be processed include how many face with no restriction, can be one, be also possible to
Multiple, but usually require that as front face.
For every face in picture to be processed, its profile information is obtained respectively.Specifically, it can extract respectively first
The profile diagram of every face in picture out can generate the corresponding delineator of profile diagram by analyzing profile diagram later
Label.
For how to extract the profile diagram of face with no restriction in the present embodiment.For example, the side of Canny operator can be used
Edge detection algorithm extracts the profile diagram of face, and this method carries out binaryzation to image using global threshold, and then extracts face
Profile.For another example, the method based on complexion model and gradient operator can also be used.It for another example, can also be using based on geometry
The facial contour extraction method of movable contour model finds facial contour etc. using the ellipticalness constraint of face shape.
After extracting the profile diagram of face, the corresponding profile of profile diagram can be generated by analyzing profile diagram
Label.For example, the shape of face of face can be determined, using the shape of face determined as delineator based on the face mask curve of face
Label.
How shape of face classification is carried out with no restriction, for example, can be generally divided into eight types the characteristics of according to Asian's shape of face
Type: (1) almond-shaped shape of face；(2) oval shape of face；(3) round shape of face；(4) oblong shape of face；(5) rectangular shape of face；(6) rectangular
Shape shape of face；(7) diamond shape shape of face；(8) triangle shape of face.
In practical applications, the feature of different shapes of face can be set separately in advance, and then pass through the face mask of analysis face
Curve determines that it is consistent with which kind of feature, and then using corresponding shape of face as the profile label determined.
It can divide respectively using every face in picture to be processed as face to be processed for every face to be processed
It following Zhi Hang not operate: firstly, filtering out the candidate mesh being consistent with the profile information of face to be processed from target face database
Mark face selects the target face to match with face to be processed later from candidate target face.
It can be reserved for the characteristic information and identity information for having every target face in target face database, identity information may include surname
Name, gender etc., characteristic information may include profile label of face etc..
In this way, screening the candidate target face being consistent with the profile information of face to be processed from target face database
When, for every target face in target face database, can calculate separately the profile label of the target face saved with wait locate
The similarity between the profile label of face is managed, it, can be by the target person if similarity is greater than or equal to preset threshold value
Face is determined as candidate target face.
The specific value of threshold value can be determined according to actual needs, for example, the value range of similarity is 0-1, then threshold value
Value can be 1, might be less that 1, such as 0.8.If value be 1, illustrate only when target face profile label and to
When the profile label of processing face is identical, target face can be just determined as to candidate target face.In some cases, such as
When profile label includes multiple, when such as other than shape of face also including the other labels of the colour of skin, if the profile label of target face
It is not exactly the same with the profile label of face to be processed, but similarity is very high, target face can also be determined as candidate target
Face.
After obtaining candidate target face, it can further select from candidate target face and match with face to be processed
Target face, to obtain final required result.
Specifically, the face characteristic of face to be processed can be obtained, and is directed to every candidate target face, calculates separately and is protected
Similarity between the face characteristic for the candidate target face deposited and the face characteristic of face to be processed, and then most by similarity
Big candidate target face is determined as the target face to match with face to be processed.
As previously mentioned, can be reserved for the characteristic information and identity information for having every target face in target face database, wherein special
Reference breath may include the profile label of face, additionally can include face characteristic etc..
For how to obtain face characteristic with no restriction in the present embodiment.For example, the people based on geometrical characteristic can be used
Face characteristic extracting method, the face feature extraction method based on principal component analysis, the face characteristic extraction side based on template matching
Method etc..Preferably, also face characteristic can be extracted based on depth learning technology.Nerve net such as by imitating human cerebral cortex
Network, the convolutional neural networks model proposed using means such as convolution, Chi Hua, nonlinear changes are available more abstract more essential
Visual signature.
The face characteristic extracted can behave as feature vector form.The face that each candidate target face can be calculated separately is special
Similarity between sign and the face characteristic of face to be processed can select the maximum candidate target face of similarity, by this later
Candidate target face is as the final required target face to match with face to be processed.
Based on above-mentioned introduction, Fig. 2 is the flow chart of face identification method second embodiment of the present invention.As shown in Fig. 2,
Including implementation in detail below.
In 201, the profile diagram of the face to be processed in picture to be processed is extracted.
In the present embodiment, it is assumed that only include a face in picture to be processed, extract the profile diagram of the face.
In 202, by analyzing profile diagram, the corresponding profile label of profile diagram is generated.
The corresponding shape of face of profile diagram is such as analyzed, as profile label.
In 203, the profile label of each target face in target face database and the profile of face to be processed are calculated separately
Similarity between label.
In 204, similarity is determined as candidate target greater than the target face more than or equal to preset threshold value
Face.
Assuming that including altogether 1000 faces in target face database, after being handled by mode shown in 203-204, select wherein
50 target faces as candidate target face.
In 205, the face characteristic of face to be processed is obtained.
In 206, it calculates separately between the face characteristic of each candidate target face and the face characteristic of face to be processed
Similarity.
In 207, the maximum candidate target face of similarity is determined as the target face to match with face to be processed.
It such as calculates separately similar between the face characteristic of 50 candidate target faces and the face characteristic of face to be processed
Degree, to obtain 50 calculated results, selects the maximum calculated result of wherein value, by the corresponding target face of the calculated result
As the target face to match with face to be processed.
It can be reserved for the identity information for having every target face in target face database, in this way, according to the target face to match
Identity information be that can determine that the identity information of face to be processed.
It should be noted that for the various method embodiments described above, for simple description, therefore, it is stated as a series of
Combination of actions, but those skilled in the art should understand that, the present invention is not limited by the sequence of acts described because
According to the present invention, certain steps can use other sequences or carry out simultaneously.Secondly, those skilled in the art should also know
It knows, the embodiments described in the specification are all preferred embodiments, and related actions and modules is not necessarily of the invention
It is necessary.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment
Point, it may refer to the associated description of other embodiments.
In short, first candidate target quickly can be oriented based on profile information using scheme described in above-mentioned each method embodiment
Face, thus considerably reduce the subsequent face quantity for needing to compare, and then improve treatment effeciency etc..
The introduction about embodiment of the method above, below by way of Installation practice, to scheme of the present invention carry out into
One step explanation.
Fig. 3 is the composed structure schematic diagram of face identification device embodiment of the present invention.As shown in Figure 3, comprising: obtain
Unit 301 and recognition unit 302.
Acquiring unit 301, for obtaining the profile information of every face in picture to be processed respectively.
Recognition unit 302, for respectively using every face in picture as face to be processed, for face to be processed,
It executes following operation: filtering out the candidate target face being consistent with the profile information of face to be processed from target face database；
The target face to match with face to be processed is selected from candidate target face.
Wherein, acquiring unit 301 can extract the profile diagram of every face in picture to be processed respectively, pass through later
Profile diagram is analyzed, generates the corresponding profile label of each profile diagram respectively.For example, can be based on the face mask song of face
Line determines the shape of face of face, using the shape of face determined as profile label.
How shape of face classification is carried out with no restriction, for example, can be generally divided into eight types the characteristics of according to Asian's shape of face
Type: (1) almond-shaped shape of face；(2) oval shape of face；(3) round shape of face；(4) oblong shape of face；(5) rectangular shape of face；(6) rectangular
Shape shape of face；(7) diamond shape shape of face；(8) triangle shape of face.
Recognition unit 302 can respectively using every face in picture to be processed as face to be processed, for every to
Face is handled, following operation is executed respectively: being consistent firstly, being filtered out from target face database with the profile information of face to be processed
The candidate target face of conjunction selects the target face to match with face to be processed later from candidate target face.
It can be reserved for the characteristic information and identity information for having every target face in target face database, identity information may include surname
Name, gender etc., characteristic information may include profile label of face etc..
Recognition unit 302 can calculate separately saved target face for every target face in target face database
Similarity between profile label and the profile label of face to be processed, if similarity is greater than or equal to preset threshold value,
Target face can be then determined as to candidate target face.
After obtaining candidate target face, recognition unit 302 can be selected further from candidate target face and to from
The target face that reason face matches, to obtain final required result.
Specifically, recognition unit 302 can obtain the face characteristic of face to be processed, and be directed to every candidate target face,
The similarity between the face characteristic of saved candidate target face and the face characteristic of face to be processed is calculated separately, in turn
The maximum candidate target face of similarity is determined as the target face to match with face to be processed.
As previously mentioned, can be reserved for the characteristic information and identity information for having every target face in target face database, wherein special
Reference breath may include the profile label of face, additionally can include face characteristic etc..
The specific workflow of Fig. 3 shown device embodiment please refers to the related description in preceding method embodiment, no longer
It repeats.
In short, first candidate target people quickly can be oriented based on profile information using scheme described in above-mentioned apparatus embodiment
Face, thus considerably reduce the subsequent face quantity for needing to compare, and then improve treatment effeciency etc..
Fig. 4 shows the block diagram for being suitable for the exemplary computer system/server 12 for being used to realize embodiment of the present invention.
The computer system/server 12 that Fig. 4 is shown is only an example, should not function and use scope to the embodiment of the present invention
Bring any restrictions.
As shown in figure 4, computer system/server 12 is showed in the form of universal computing device.Computer system/service
The component of device 12 can include but is not limited to: one or more processor (processing unit) 16, memory 28, connect not homology
The bus 18 of system component (including memory 28 and processor 16).
Bus 18 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts
For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC)
Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Computer system/server 12 typically comprises a variety of computer system readable media.These media, which can be, appoints
What usable medium that can be accessed by computer system/server 12, including volatile and non-volatile media, it is moveable and
Immovable medium.
Memory 28 may include the computer system readable media of form of volatile memory, such as random access memory
Device (RAM) 30 and/or cache memory 32.Computer system/server 12 may further include it is other it is removable/no
Movably, volatile/non-volatile computer system storage medium.Only as an example, storage system 34 can be used for reading and writing
Immovable, non-volatile magnetic media (Fig. 4 do not show, commonly referred to as " hard disk drive ").Although not shown in fig 4, may be used
To provide the disc driver for reading and writing to removable non-volatile magnetic disk (such as " floppy disk "), and it is non-volatile to moving
Property CD (such as CD-ROM, DVD-ROM or other optical mediums) read and write CD drive.In these cases, each drive
Dynamic device can be connected by one or more data media interfaces with bus 18.Memory 28 may include at least one program
Product, the program product have one group of (for example, at least one) program module, these program modules are configured to perform the present invention
The function of each embodiment.
Program/utility 40 with one group of (at least one) program module 42 can store in such as memory 28
In, such program module 42 includes --- but being not limited to --- operating system, one or more application program, other programs
It may include the realization of network environment in module and program data, each of these examples or certain combination.Program mould
Block 42 usually executes function and/or method in embodiment described in the invention.
Computer system/server 12 can also be (such as keyboard, sensing equipment, aobvious with one or more external equipments 14
Show device 24 etc.) communication, it is logical that the equipment interacted with the computer system/server 12 can be also enabled a user to one or more
Letter, and/or with the computer system/server 12 any is set with what one or more of the other calculating equipment was communicated
Standby (such as network interface card, modem etc.) communicates.This communication can be carried out by input/output (I/O) interface 22.And
And computer system/server 12 can also pass through network adapter 20 and one or more network (such as local area network
(LAN), wide area network (WAN) and/or public network, such as internet) communication.As shown in figure 4, network adapter 20 passes through bus
18 communicate with other modules of computer system/server 12.It should be understood that although not shown in the drawings, computer can be combined
Systems/servers 12 use other hardware and/or software module, including but not limited to: microcode, device driver, at redundancy
Manage unit, external disk drive array, RAID system, tape drive and data backup storage system etc..
The program that processor 16 is stored in memory 28 by operation, at various function application and data
Reason, such as realize the method in Fig. 1 or embodiment illustrated in fig. 2.
The present invention discloses a kind of computer readable storage mediums, are stored thereon with computer program, the program quilt
Processor will realize the method in embodiment as shown in Figure 1 or 2 when executing.
It can be using any combination of one or more computer-readable media.Computer-readable medium can be calculating
Machine readable signal medium or computer readable storage medium.Computer readable storage medium for example can be --- but it is unlimited
In system, device or the device of --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, or any above combination.It calculates
The more specific example (non exhaustive list) of machine readable storage medium storing program for executing includes: electrical connection with one or more conducting wires, just
Taking formula computer disk, hard disk, random access memory (RAM), read-only memory (ROM), erasable type may be programmed read-only storage
Device (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device,
Or above-mentioned any appropriate combination.In this document, computer readable storage medium can be it is any include or storage journey
The tangible medium of sequence, the program can be commanded execution system, device or device use or in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including --- but
It is not limited to --- electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be
Any computer-readable medium other than computer readable storage medium, which can send, propagate or
Transmission is for by the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In --- wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
Further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion
Divide and partially executes or executed on a remote computer or server completely on the remote computer on the user computer.?
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or
Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as mentioned using Internet service
It is connected for quotient by internet).
In several embodiments provided by the present invention, it should be understood that disclosed device and method etc. can pass through
Other modes are realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of the unit,
Only a kind of logical function partition, there may be another division manner in actual implementation.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of hardware adds SFU software functional unit.
The above-mentioned integrated unit being realized in the form of SFU software functional unit can store and computer-readable deposit at one
In storage media.Above-mentioned SFU software functional unit is stored in a storage medium, including some instructions are used so that a computer
It is each that equipment (can be personal computer, server or the network equipment etc.) or processor (processor) execute the present invention
The part steps of embodiment the method.And storage medium above-mentioned include: USB flash disk, mobile hard disk, read-only memory (ROM,
Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic or disk etc. it is various
It can store the medium of program code.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Within mind and principle, any modification, equivalent substitution, improvement and etc. done be should be included within the scope of the present invention.
Claims (10)
1. a kind of face identification method characterized by comprising
The profile information of every face in picture to be processed is obtained respectively；
Following operation is executed for the face to be processed using every face in the picture as face to be processed respectively:
The candidate target face being consistent with the profile information of the face to be processed is filtered out from target face database；
The target face to match with the face to be processed is selected from candidate target face.
2. the method according to claim 1, wherein
The profile information for obtaining every face in picture to be processed respectively includes:
The profile diagram of every face in the picture is extracted respectively；
By analyzing the profile diagram, the corresponding profile label of each profile diagram is generated respectively.
3. according to the method described in claim 2, it is characterized in that,
It is described that the candidate target face packet being consistent with the profile information of the face to be processed is filtered out from target face database
It includes:
For every target face in the target face database, calculate separately the profile label of the target face saved with
Similarity between the profile label of the face to be processed, if the similarity is greater than or equal to preset threshold value,
The target face is determined as the candidate target face.
4. the method according to claim 1, wherein
The target face to match with the face to be processed of selecting from candidate target face includes:
Obtain the face characteristic of the face to be processed；
For every candidate target face, the face characteristic of the candidate target face saved is calculated separately with described wait locate
Manage the similarity between the face characteristic of face；
The maximum candidate target face of similarity is determined as the target face to match with the face to be processed.
5. a kind of face identification device characterized by comprising acquiring unit and recognition unit；
The acquiring unit, for obtaining the profile information of every face in picture to be processed respectively；
The recognition unit, for respectively using every face in the picture as face to be processed, for described to be processed
Face executes following operation: filtering out the candidate being consistent with the profile information of the face to be processed from target face database
Target face；The target face to match with the face to be processed is selected from candidate target face.
6. device according to claim 5, which is characterized in that
The acquiring unit extracts the profile diagram of every face in the picture respectively, by dividing the profile diagram
Analysis, generates the corresponding profile label of each profile diagram respectively.
7. device according to claim 6, which is characterized in that
The recognition unit calculates separately the target face saved for every target face in the target face database
Profile label and the face to be processed profile label between similarity, if the similarity be greater than or equal to set in advance
The target face is then determined as the candidate target face by fixed threshold value.
8. device according to claim 5, which is characterized in that
The recognition unit obtains the face characteristic of the face to be processed, for every candidate target face, calculates separately institute
The similarity between the face characteristic of the candidate target face and the face characteristic of the face to be processed saved, will be similar
It spends maximum candidate target face and is determined as the target face to match with the face to be processed.
9. a kind of computer equipment, including memory, processor and it is stored on the memory and can be on the processor
The computer program of operation, which is characterized in that the processor is realized when executing described program as any in Claims 1 to 4
Method described in.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that described program is processed
Device realizes method as described in any one of claims 1 to 4 when executing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811075694.XA CN109446893A (en) | 2018-09-14 | 2018-09-14 | Face identification method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811075694.XA CN109446893A (en) | 2018-09-14 | 2018-09-14 | Face identification method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109446893A true CN109446893A (en) | 2019-03-08 |
Family
ID=65531027
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811075694.XA Pending CN109446893A (en) | 2018-09-14 | 2018-09-14 | Face identification method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109446893A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109839115A (en) * | 2019-03-21 | 2019-06-04 | 北京中飞艾维航空科技有限公司 | A kind of UAV Landing method, apparatus and storage medium |
| CN110009646A (en) * | 2019-04-15 | 2019-07-12 | 天意有福科技股份有限公司 | A kind of generation method of electron album, device, electronic equipment and storage medium |
| CN111460910A (en) * | 2020-03-11 | 2020-07-28 | 深圳市新镜介网络有限公司 | Face type classification method and device, terminal equipment and storage medium |
| CN112149559A (en) * | 2020-09-22 | 2020-12-29 | 沈澈 | Face recognition method and device, readable storage medium and computer equipment |
| CN113689147A (en) * | 2021-09-15 | 2021-11-23 | 武汉乐知科技有限公司 | Machine learning algorithm for teaching quality assessment |
| CN115953823A (en) * | 2023-03-13 | 2023-04-11 | 成都运荔枝科技有限公司 | Face recognition method based on big data |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1341401A (en) * | 2001-10-19 | 2002-03-27 | 清华大学 | Main unit component analysis based multimode human face identification method |
| EP1416425B1 (en) * | 2002-11-04 | 2007-10-24 | Samsung Electronics Co., Ltd. | System and method for detecting a face |
| CN101162499A (en) * | 2006-10-13 | 2008-04-16 | 上海银晨智能识别科技有限公司 | Method for using human face formwork combination to contrast |
| CN104573644A (en) * | 2014-12-29 | 2015-04-29 | 天津瑞为拓新科技发展有限公司 | Multi-mode face identification method |
| CN107358219A (en) * | 2017-07-24 | 2017-11-17 | 艾普柯微电子（上海）有限公司 | Face identification method and device |
| CN108062518A (en) * | 2017-12-07 | 2018-05-22 | 北京小米移动软件有限公司 | Type of face detection method and device |
-
2018
- 2018-09-14 CN CN201811075694.XA patent/CN109446893A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1341401A (en) * | 2001-10-19 | 2002-03-27 | 清华大学 | Main unit component analysis based multimode human face identification method |
| EP1416425B1 (en) * | 2002-11-04 | 2007-10-24 | Samsung Electronics Co., Ltd. | System and method for detecting a face |
| CN101162499A (en) * | 2006-10-13 | 2008-04-16 | 上海银晨智能识别科技有限公司 | Method for using human face formwork combination to contrast |
| CN104573644A (en) * | 2014-12-29 | 2015-04-29 | 天津瑞为拓新科技发展有限公司 | Multi-mode face identification method |
| CN107358219A (en) * | 2017-07-24 | 2017-11-17 | 艾普柯微电子（上海）有限公司 | Face identification method and device |
| CN108062518A (en) * | 2017-12-07 | 2018-05-22 | 北京小米移动软件有限公司 | Type of face detection method and device |
Non-Patent Citations (1)
| Title |
|---|
| 王昆翔: "《智能理论与警用智能技术》", 31 May 2009 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109839115A (en) * | 2019-03-21 | 2019-06-04 | 北京中飞艾维航空科技有限公司 | A kind of UAV Landing method, apparatus and storage medium |
| CN110009646A (en) * | 2019-04-15 | 2019-07-12 | 天意有福科技股份有限公司 | A kind of generation method of electron album, device, electronic equipment and storage medium |
| CN110009646B (en) * | 2019-04-15 | 2023-08-18 | 天意有福科技股份有限公司 | Electronic album generation method and device, electronic equipment and storage medium |
| CN111460910A (en) * | 2020-03-11 | 2020-07-28 | 深圳市新镜介网络有限公司 | Face type classification method and device, terminal equipment and storage medium |
| CN112149559A (en) * | 2020-09-22 | 2020-12-29 | 沈澈 | Face recognition method and device, readable storage medium and computer equipment |
| CN113689147A (en) * | 2021-09-15 | 2021-11-23 | 武汉乐知科技有限公司 | Machine learning algorithm for teaching quality assessment |
| CN115953823A (en) * | 2023-03-13 | 2023-04-11 | 成都运荔枝科技有限公司 | Face recognition method based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109446893A (en) | Face identification method, device, computer equipment and storage medium | |
| US8031947B2 (en) | Method and system for rapid matching of video streams | |
| CN107958455B (en) | Image definition appraisal procedure, device, computer equipment and storage medium | |
| CN107545241A (en) | Neural network model is trained and biopsy method, device and storage medium | |
| WO2021139324A1 (en) | Image recognition method and apparatus, computer-readable storage medium and electronic device | |
| CN110175527A (en) | Pedestrian recognition methods and device, computer equipment and readable medium again | |
| CN102945366B (en) | A kind of method and device of recognition of face | |
| CN109214238A (en) | Multi-object tracking method, device, equipment and storage medium | |
| CN107609466A (en) | Face cluster method, apparatus, equipment and storage medium | |
| CN110163096B (en) | Person identification method, person identification device, electronic equipment and computer readable medium | |
| US11126827B2 (en) | Method and system for image identification | |
| CN109543560A (en) | Dividing method, device, equipment and the computer storage medium of personage in a kind of video | |
| WO2011152843A1 (en) | Clothing-based image clustering based on cluster ensemble sets | |
| CN107092874A (en) | Personal identification method, apparatus and system based on electrocardio and fingerprint fusion feature | |
| CN110232340A (en) | Establish the method, apparatus of video classification model and visual classification | |
| CN111125390A (en) | Database updating method and device, electronic equipment and computer storage medium | |
| CN109784243B (en) | Identity determination method and device, neural network training method and device, and medium | |
| CN109376717A (en) | Personal identification method, device, electronic equipment and the storage medium of face comparison | |
| CN110941978B (en) | Face clustering method and device for unidentified personnel and storage medium | |
| Haji et al. | Real time face recognition system (RTFRS) | |
| CN109885597A (en) | Tenant group processing method, device and electric terminal based on machine learning | |
| CN111738199B (en) | Image information verification method, device, computing device and medium | |
| CN107944381A (en) | Face tracking method, device, terminal and storage medium | |
| CN113486752A (en) | Emotion identification method and system based on electrocardiosignals | |
| Rehman | Light microscopic iris classification using ensemble multi‐class support vector machine |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190308 |