CN108491813A - Method and apparatus for fresh information - Google Patents
Method and apparatus for fresh information Download PDFInfo
- Publication number
- CN108491813A CN108491813A CN201810270170.XA CN201810270170A CN108491813A CN 108491813 A CN108491813 A CN 108491813A CN 201810270170 A CN201810270170 A CN 201810270170A CN 108491813 A CN108491813 A CN 108491813A
- Authority
- CN
- China
- Prior art keywords
- image
- registered images
- similarity
- facial image
- 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
- G06V40/172—Classification, e.g. identification
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- 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
Abstract
The embodiment of the present application discloses the method and apparatus for fresh information.One specific implementation mode of this method includes：Obtain the registered images set of the target image and target user of target user；Facial image is extracted from target image；For each registered images in registered images set, the similarity of the registered images and facial image is generated；Determine whether the minimum value in each similarity generated is more than or equal to preset similarity threshold；It is more than or equal to preset similarity threshold in response to determining, target image is added in registered images set.The embodiment realizes the update of the photo in the registered images set to target user.
Description
Technical field
The invention relates to field of computer technology, and in particular to the method and apparatus for being used for fresh information.
Background technology
Currently, face recognition technology is the artificial intelligence skill that the face feature based on user verifies the identity of user
Art.In technical field of face recognition, the facial image of acquisition is stored into equipment, meanwhile, with the growth of time, face
The face feature of image also can constantly change, and thus need to be updated the facial image in equipment.
Invention content
The embodiment of the present application proposes the method and apparatus for fresh information.
In a first aspect, the embodiment of the present application provides a kind of method for fresh information, this method includes：Obtain target
The target image of user and the registered images set of target user；Facial image is extracted from target image；For registered images
Each registered images in set, generate the similarity of the registered images and facial image；Determine each similarity generated
In minimum value whether be more than or equal to preset similarity threshold；It is more than or equal to preset similarity threshold in response to determining, it will
Target image is added in registered images set.
In some embodiments, for each registered images in registered images set, the registered images and people are generated
Before the similarity of face image, this method further includes：Determine the human face characteristic point in facial image, generate fisrt feature point to
Amount；And for each registered images in registered images set, the similarity of the registered images and facial image is generated, it wraps
It includes：It determines the human face characteristic point in the registered images, generates second feature point vector；Fisrt feature point vector sum is generated
The similarity of second feature point vector is determined as the similarity of the registered images and facial image.
In some embodiments, this method further includes：It is less than preset similarity threshold in response to determining, by registered images
It is deleted with the registered images of the similarity of facial image minimum in set.
In some embodiments, facial image is extracted from target image, including：Initial Face is extracted from target image
Image；Image procossing is carried out to Initial Face image, image procossing includes at least one of following：Noise reduction process, at image enhancement
Reason and illumination pretreatment；Using the Initial Face image after image procossing as the facial image of extraction.
Second aspect, the embodiment of the present application provide a kind of device for fresh information, which includes：Obtain dress
It sets, is configured to obtain the registered images set of the target image and target user of target user；Extraction element, be configured to from
Facial image is extracted in target image；Similarity generation unit is configured to for each registration figure in registered images set
Picture generates the similarity of the registered images and facial image；Determination unit is configured to determine in each similarity generated
Minimum value whether be more than or equal to preset similarity threshold；Adding device is configured to preset in response to determining to be more than or equal to
Similarity threshold, target image is added in registered images set.
In some embodiments, which further includes：Fisrt feature point vector determining module is configured to determine face figure
Human face characteristic point as in generates fisrt feature point vector；And similarity generation unit, including：Second feature point vector is really
Cover half block is configured to determine the human face characteristic point in the registered images, generates second feature point vector；Similarity determines mould
Block, be configured to by the similarity for the second feature point vector that fisrt feature point vector sum is generated be determined as the registered images with
The similarity of facial image.
In some embodiments, which further includes：Removing module is configured in response to determining less than preset similar
Threshold value is spent, will be deleted with the registered images of the similarity of facial image minimum in registered images set.
In some embodiments, facial image is extracted from target image, including：Initial Face is extracted from target image
Image；Image procossing is carried out to Initial Face image, image procossing includes at least one of following：Noise reduction process, at image enhancement
Reason and illumination pretreatment；Using the Initial Face image after image procossing as the facial image of extraction.
The third aspect, the embodiment of the present application provide a kind of electronic equipment, including：One or more processors；Memory,
For storing one or more programs, when one or more programs are executed by one or more processors so that one or more
A processor realizes the method as described in any realization method of first aspect.
Fourth aspect, the embodiment of the present application provide a kind of computer-readable medium, are stored thereon with computer program, should
The method as described in any realization method of first aspect is realized when program is executed by processor.
Method and apparatus provided by the embodiments of the present application for fresh information, by the target image for obtaining target user
With the registered images set of target user；Facial image is extracted from target image；For each note in registered images set
Volume image, generates the similarity of the registered images and facial image；Whether the minimum value in the determining each similarity generated
More than or equal to preset similarity threshold；It is more than or equal to preset similarity threshold in response to determining, target image is added to
In registered images set.Use this method and device that can add the target image of the target user of acquisition as a result, it is real
The update of the photo in the registered images set to target user is showed.
Description of the drawings
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application's is other
Feature, objects and advantages will become more apparent upon：
Fig. 1 is that this application can be applied to exemplary system architecture figures therein；
Fig. 2 is the flow chart according to one embodiment of the method for fresh information of the application；
Fig. 3 is the schematic diagram according to an application scenarios of the method for fresh information of the application；
Fig. 4 is the flow chart according to another embodiment of the method for fresh information of the application；
Fig. 5 is the structural schematic diagram according to one embodiment of the device for fresh information of the application；
Fig. 6 is adapted for the structural schematic diagram of the computer system of the server for realizing the embodiment of the present application.
Specific implementation mode
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to
Convenient for description, is illustrated only in attached drawing and invent relevant part with related.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 shows the exemplary system of the embodiment for the method for fresh information that can apply the embodiment of the present application
Framework 100.
As shown in Figure 1, system architecture 100 may include terminal device (being shown as entrance guard device in figure) 101, terminal device
(smart mobile phone is shown as in figure) 102, terminal device (gate that safety check is shown as in figure) 103, network 104 and server
105.Network 104 between terminal device 101,102,103 and server 105 provide communication link medium.Network 104
May include various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be interacted by network 104 with server 105 with using terminal equipment 101,102,103, to receive or send out
Send message etc..Camera can be installed on terminal device 101,102,103, or various client applications are installed, such as
Image processing class application, the application of photography and vedio recording class, searching class application, the application of browser class, social platform software etc..
Terminal device 101,102,103 can be hardware, can also be software.When terminal device 101,102,103 is hard
It can be the various electronic equipments that there is display screen and support image procossing when part, including but not limited to carry camera
Gate, smart mobile phone and the entrance guard device etc. with camera.When terminal device 101,102,103 is software, Ke Yian
In above-mentioned cited electronic equipment.Multiple softwares or software module may be implemented into it, can also be implemented as single soft
Part or software module.It is not specifically limited herein.
Server 105 can be to provide the server of various services, the mesh that for example, terminal device 101,102,103 uploads
Logo image carries out the image processing server of image procossing.Image processing server can divide the target image received
The processing such as analysis, and handling result (such as facial image) is fed back into terminal device.
It should be noted that above-mentioned facial image can also be stored directly in the local of server 105, server 105 can
Directly to extract the local facial image stored and be handled, at this point it is possible to which 101,102,103 and of terminal device is not present
Network 104.
In general, the method for fresh information that the embodiment of the present application is provided is executed by server 105.Correspondingly, it uses
It is generally positioned in server 105 in the device of fresh information.
In practice, image processing class application can also be installed in terminal device 101,102,103.Terminal device 101,
102,103 image processing class can also be based on using handling facial image, at this point, the method for fresh information also may be used
To be executed by terminal device 101,102,103.Correspondingly, for the device of fresh information can also be set to terminal device 101,
102, in 103.At this point, server 105 and network 104 can be not present in exemplary system architecture 100.
It should be noted that server can be hardware, can also be software.When server is hardware, may be implemented
At the distributed server cluster that multiple servers form, individual server can also be implemented as.It, can when server is software
To be implemented as that for example single software or software can also be implemented as providing the multiple softwares or software module of Distributed Services
Module.It is not specifically limited herein.
It should be understood that the number of the terminal device, network and server in Fig. 1 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.
With continued reference to Fig. 2, it illustrates the flow charts of one embodiment of the method for fresh information of the application
200.This is used for the method for fresh information, includes the following steps：
Step 201, the target image of target user and the registered images set of target user are obtained.
In the present embodiment, the executive agent (server 105 as shown in Figure 1) for being used for the method for fresh information can be first
Wired connection mode or radio connection is first passed through to obtain from terminal device (terminal device 101-103 as shown in Figure 1)
The target image of target user.Herein, target user can be the user of above-mentioned terminal device, can also be for image
Newer purpose and specified user.For example, in order to update the registered face image that user prestores, then the user can be specified to make
For target user.The image of the image of acquired target user, including but not limited to pre-stored image or live shooting, all may be used
Using as target image.
As an example, above-mentioned terminal device can be camera, the mobile phone with shooting function, the gate with camera
With the entrance guard device etc. with camera.User can carry out image taking using terminal device to target user, and will shooting
Image be sent to above-mentioned executive agent.
It in the present embodiment, can be according to the knowledge to above-mentioned target user after the target image for obtaining target user
Not (for example, recognition of face, the user identifier of input, user name etc.), from each registered images collection of each user to prestore
The registered images set of above-mentioned target user is obtained in conjunction.Registered images can be (such as recognition of face mesh for various purposes
) user images that prestore.
Step 202, facial image is extracted from target image.
In the present embodiment, the target image based on the target user obtained in step 201, above-mentioned executive agent can profits
Above-mentioned target image is handled with various processing means, extracts facial image.Here, can (example in several ways
Such as neural network model) realize facial image extraction.
In some optional realization methods of the present embodiment, it can be extracted first from the target image of target user
The image of the face of target user is as Initial Face image.Later, Initial Face image can be handled to obtain people
Face image.As an example, noise reduction process can be carried out to Initial Face image.Specifically, various existing noise reductions can be utilized
Algorithm, such as NL-Means (Non-Local means, non local average) and BM3D (Block-matching and 3D
Filtering, 3 dimension Block- matching filtering) etc., noise remove is carried out to Initial Face image.It optionally, can also be to Initial Face
Image carries out image enhancement processing.Can utilize existing various algorithm for image enhancement, as medium filtering, two dimensional wiener filtering or
Gassian low-pass filter etc. carries out enhancing processing to image.Optionally, illumination pretreatment can also be carried out to Initial Face image.
Specifically, various existing illumination pretreatment algorithms can be utilized, such as histogram equalization, gray correction, relative gradient, logarithm
Edge graph etc. handles Initial Face image.It is then possible to using Initial Face image after treatment as extraction
Facial image.
Step 203, for each registered images in registered images set, the phase of the registered images and facial image is generated
Like degree.
In the present embodiment, by by the face figure of each registered images and above-mentioned target user in registered images set
As carrying out similarity calculation, the similarity of each registered images and above-mentioned facial image is obtained.As an example, may be used various
Method calculates the similarity between two figures.For example, Histogram Matching, matrix decomposition mathematically may be used (for example, singular value
Decompose and Non-negative Matrix Factorization), the image similarity calculation method etc. of feature based point.
In some optional realization methods of the present embodiment, above-mentioned electronic equipment can be in the above-mentioned face figure extracted
As after, the characteristic point vector for acquiring the human face characteristic point of the facial image, and thus generating is as fisrt feature point vector.So
The characteristic point vector for acquiring the human face characteristic point in above-mentioned registered images again afterwards, and thus generating is as second feature point vector.
Using the similarity of fisrt feature point vector sum second feature point vector as the similarity for registered images and facial image.Practice
In, SIFT (Scale invariant features transform, Scale-invariant feature transform) algorithm, SURF can be passed through
(accelerating the feature with robustness of version, SpeededUp Robust Features) algorithm scheduling algorithm acquisition facial image
The human face characteristic point of human face characteristic point and above-mentioned registered images.The similarity calculating method that may be used between various vectors calculates
Similarity between registered images and facial image.
As an example, first, the people in human face characteristic point and registered images in facial image is obtained by SIFT algorithms
Face characteristic point.Then, the fisrt feature point vector sum registration figure corresponding to the human face characteristic point of the facial image is generated respectively
Second feature point vector corresponding to human face characteristic point as in.By calculating fisrt feature point vector sum second feature point vector
Similarity of the similarity as registered images and above-mentioned facial image.
Step 204, determine whether the minimum value in each similarity generated is more than or equal to preset similarity threshold.
In the present embodiment, it, for each registered images in above-mentioned registered images set, is calculated by step 203
The similarity of the registered images and above-mentioned facial image.Later, it can be determined that determining each registered images and facial image
Whether the minimum value in similarity is more than or equal to preset similarity threshold.Herein, preset similarity threshold can be people
For the similarity threshold of setting.
Step 205, it is more than or equal to preset similarity threshold in response to determining, target image is added to registered images collection
In conjunction.
In the present embodiment, if it is determined that go out minimum value in the similarity of each registered images and facial image and be more than etc.
In preset similarity threshold, then target image is added in registered images set.
As an example, when target user A reaches the office building with entrance guard device, the camera shooting on entrance guard device is operated in
Head obtains the target image of target user A.Later, the corresponding registered images set of the target user A can be obtained.It is used from target
After the target image of family A extracts facial image, by each registered images in above-mentioned facial image and registered images set into
Row similarity calculation, judges whether the minimum value in each similarity generated is more than or equal to preset similarity threshold.When
Determine that each registered images are more than or equal to preset similarity threshold with the minimum value in facial image similarity, by target figure
As being added in registered images set.
It is the signal according to an application scenarios of the method for fresh information of the application with continued reference to Fig. 3, Fig. 3
Figure.In the application scenarios of Fig. 3, when target user B reaches gate 301, the camera operated on gate 301 obtains target
The target image 302 of user B, and send target image 302 to server 305.Server 305 carries out target image 301
Image recognition after identifying target user B, obtains the corresponding registered images set of the target user B 304.Server 305 from
Facial image 303 is extracted in target image 302, by each registration in above-mentioned facial image 303 and registered images set 304
Image carries out similarity calculation, judges whether the minimum value in each similarity generated is more than or equal to preset similarity threshold
Value.If it is determined that each registered images are more than or equal to preset similarity threshold with the minimum value in 303 similarity of facial image
Value, the target image 302 of target user B is added in registered images set 304, registered images set 306 is obtained.
Method provided by the embodiments of the present application for fresh information obtains the target image and mesh of target user first
Mark the registered images set of user；Later, facial image is extracted from target image；For each note in registered images set
Volume image, generates the similarity of the registered images and facial image；Whether the minimum value in the determining each similarity generated
More than or equal to preset similarity threshold；It is more than or equal to preset similarity threshold in response to determining, target image is added to
In registered images set.It uses this method that can add the target image of the target user of acquisition as a result, realizes pair
The update of photo in the registered images set of target user.
With further reference to Fig. 4, it illustrates the flow charts 400 of another embodiment of the method for fresh information, should
The flow chart 400 of method for fresh information, includes the following steps：
Step 401, the target image of target user and the registered images set of target user are obtained.
Step 402, facial image is extracted from target image.
Step 403, for each registered images in registered images set, the phase of the registered images and facial image is generated
Like degree.
Step 404, determine whether the minimum value in each similarity generated is more than or equal to preset similarity threshold.
Step 405, it is more than or equal to preset similarity threshold in response to determining, target image is added to registered images collection
In conjunction.
In the present embodiment, the behaviour of the concrete operations of step 401-405 and step 201-205 in embodiment shown in Fig. 2
Make essentially identical, details are not described herein.
Step 406, it is less than preset similarity threshold in response to determining, by the phase with facial image in registered images set
It is deleted like the minimum registered images of degree.
In the present embodiment, after the similarity for obtaining each registered images and facial image in registered images set,
The minimum similarity of value is determined from these similarities.Whether continue the similarity of judgment value minimum more than or equal to preset similar
Spend threshold value.It, will be similar to facial image in registered images set when minimum similarity is less than preset similarity threshold
The minimum registered images of degree are deleted.
As an example, when target user C reaches the office building with entrance guard device, the camera shooting on entrance guard device is operated in
Head obtains the target image of target user C, while obtaining the corresponding registered images set of the target user C.Later, target is used
Each registered images in the facial image and registered images set of family C carry out similarity calculation, judge each phase generated
Whether it is more than or equal to preset similarity threshold like the minimum value in degree, when determining that each registered images are similar to facial image
Minimum value in degree is more than or equal to preset similarity threshold, and target image is added in registered images set.When determining
Each registered images are less than preset similarity threshold, the registered images collection that will be obtained with the minimum value in facial image similarity
The registered images deletion with facial image similarity minimum in conjunction.
Figure 4, it is seen that compared with the corresponding embodiments of Fig. 2, the method for fresh information in the present embodiment
Flow chart 400 the step of increasing being deleted with the registered images of the similarity of facial image minimum in registered images set.
The scheme of the present embodiment description can not only add the target image of the target user of acquisition as a result, can also will note
It is deleted with the registered images of the similarity minimum of facial image in volume image collection, the registration to target user is furthermore achieved
Effective update of photo in image collection.
With further reference to Fig. 5, as the realization to method shown in above-mentioned each figure, this application provides one kind for updating letter
One embodiment of the device of breath, the device embodiment is corresponding with embodiment of the method shown in Fig. 2, which can specifically answer
For in various electronic equipments.
As shown in figure 5, the device 500 for fresh information of the present embodiment includes：Acquiring unit 501, extraction unit
502, similarity generation unit 503, determination unit 504 and adding device 505.Wherein, acquiring unit 501 are configured to obtain
The target image of target user and the registered images set of target user；Extraction unit 502 is configured to carry from target image
Take facial image；Similarity generation unit 503 is configured to for each registered images in registered images set, and generating should
The similarity of registered images and facial image；Determination unit 504 is configured to determine the minimum in each similarity generated
Whether value is more than or equal to preset similarity threshold；Adding device 505 is configured to be more than or equal to preset phase in response to determining
Like degree threshold value, target image is added in registered images set.
In the present embodiment, acquiring unit 501, extraction unit 502, the similarity being used in the device 500 of fresh information
Generation unit 503, the specific processing of determination unit 504 and adding device 505 and its caused technique effect can refer to respectively
The related description of step 201, step 202, step 203, step 204 and step 205 in Fig. 2 corresponding embodiments, herein no longer
It repeats.
In some optional realization methods of the present embodiment, above-mentioned apparatus 500 can also include：Fisrt feature point vector
Determining module (not shown) is configured to determine the human face characteristic point in facial image, generates fisrt feature point vector.At this moment,
Similarity generation unit, including：Second feature point vector determining module (not shown), is configured to determine in the registered images
Human face characteristic point generates second feature point vector；Similarity determining module (not shown) is configured to fisrt feature point vector
It is determined as the similarity of the registered images and facial image with the similarity of the second feature point vector generated.
In some optional realization methods of the present embodiment, above-mentioned apparatus 500 can also include：Deleting unit (is not shown
Go out), it is configured to be less than preset similarity threshold in response to determining, by the similarity with facial image in registered images set
Minimum registered images are deleted.
In some optional realization methods of the present embodiment, extraction unit 502 can be further configured to：From target
Initial Face image is extracted in image；Image procossing is carried out to Initial Face image, image procossing includes at least one of following：Drop
It makes an uproar processing, image enhancement processing and illumination pretreatment；Using the Initial Face image after image procossing as the facial image of extraction.
The device that above-described embodiment of the application provides, by extracting facial image from the target image of target user,
Each registered images in the registered images set of facial image and the target user obtained are subjected to similarity-rough set, work as institute
When minimum value in each similarity generated is more than or equal to preset similarity threshold, target image is added to registered images
In set.The target image of the target user of acquisition can be added by using above-mentioned apparatus, realizes and target is used
The update of photo in the registered images set at family.
Below with reference to Fig. 6, it illustrates the computer systems 600 suitable for the server for realizing the embodiment of the present application
Structural schematic diagram.Server shown in Fig. 6 is only an example, should not be to the function and use scope band of the embodiment of the present application
Carry out any restrictions.
As shown in fig. 6, computer system 600 includes central processing unit (CPU) 601, it can be read-only according to being stored in
Program in memory (ROM) 602 or be loaded into the program in random access storage device (RAM) 603 from storage section 608 and
Execute various actions appropriate and processing.In RAM 603, also it is stored with system 600 and operates required various programs and data.
CPU 601, ROM 602 and RAM 603 are connected with each other by bus 604.Input/output (I/O) interface 605 is also connected to always
Line 604.
It is connected to I/O interfaces 605 with lower component：Importation 606 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 607 of spool (CRT), liquid crystal display (LCD) etc. and loud speaker etc.；Storage section 608 including hard disk etc.；
And the communications portion 609 of the network interface card including LAN card, modem etc..Communications portion 609 via such as because
The network of spy's net executes communication process.Driver 610 is also according to needing to be connected to I/O interfaces 605.Detachable media 611, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on driver 610, as needed in order to be read from thereon
Computer program be mounted into storage section 608 as needed.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed by communications portion 609 from network, and/or from detachable media
611 are mounted.When the computer program is executed by central processing unit (CPU) 601, limited in execution the present processes
Above-mentioned function.
It should be noted that computer-readable medium shown in the application can be computer-readable signal media or meter
Calculation machine readable medium either the two arbitrarily combines.Computer readable storage medium for example can be --- but it is unlimited
In --- electricity, system, device or the device of magnetic, optical, electromagnetic, infrared ray or semiconductor, or the arbitrary above combination.It calculates
The more specific example of machine readable storage medium storing program for executing can include but is not limited to：Being electrically connected, be portable with one or more conducting wires
Formula computer disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable programmable read only memory
(EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device or
The above-mentioned any appropriate combination of person.In this application, can be any include computer readable storage medium or storage program
Tangible medium, the program can be commanded execution system, device either device use or it is in connection.And in this Shen
Please in, computer-readable signal media may include in a base band or as the data-signal that a carrier wave part is propagated,
In carry computer-readable program code.Diversified forms may be used in the data-signal of this propagation, including but not limited to
Electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer-readable
Any computer-readable medium other than storage medium, the computer-readable medium can send, propagate or transmit for by
Instruction execution system, device either device use or program in connection.The journey for including on computer-readable medium
Sequence code can transmit with any suitable medium, including but not limited to：Wirelessly, electric wire, optical cable, RF etc. or above-mentioned
Any appropriate combination.
Flow chart in attached drawing and block diagram, it is illustrated that according to the system of the various embodiments of the application, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part for a part for one module, program segment, or code of table, above-mentioned module, program segment, or code includes one or more
Executable instruction for implementing the specified logical function.It should also be noted that in some implementations as replacements, institute in box
The function of mark can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are practical
On can be basically executed in parallel, they can also be executed in the opposite order sometimes, this is depended on the functions involved.Also it wants
It is noted that the combination of each box in block diagram or flow chart and the box in block diagram or flow chart, can use and execute rule
The dedicated hardware based systems of fixed functions or operations is realized, or can use the group of specialized hardware and computer instruction
It closes to realize.
Being described in unit involved in the embodiment of the present application can be realized by way of software, can also be by hard
The mode of part is realized.Described unit can also be arranged in the processor, for example, can be described as：A kind of processor packet
Include acquiring unit, extraction unit, similarity generation unit, determination unit and adding device.Wherein, the title of these units is at certain
The restriction to the unit itself is not constituted in the case of kind, for example, acquiring unit is also described as " obtaining target user's
The unit of the registered images set of target image and target user ".
As on the other hand, present invention also provides a kind of computer-readable medium, which can be
Included in computer described in above-described embodiment；Can also be individualism, and without be incorporated the electronic equipment in.On
It states computer-readable medium and carries one or more program, when said one or multiple programs are executed by the device
When so that the device：Obtain the registered images set of the target image and target user of target user；It is extracted from target image
Facial image；For each registered images in registered images set, the similarity of the registered images and facial image is generated；Really
Whether the minimum value in the fixed each similarity generated is more than or equal to preset similarity threshold；It is more than or equal in response to determination
Target image is added in registered images set by preset similarity threshold.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.People in the art
Member should be appreciated that invention scope involved in the application, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from foregoing invention design, it is carried out by above-mentioned technical characteristic or its equivalent feature
Other technical solutions of arbitrary combination and formation.Such as features described above has similar work(with (but not limited to) disclosed herein
Can technical characteristic replaced mutually and the technical solution that is formed.
Claims (10)
1. a kind of method for fresh information, including：
Obtain the registered images set of the target image and the target user of target user；
Facial image is extracted from the target image；
For each registered images in the registered images set, it is similar to the facial image to generate the registered images
Degree；
Determine whether the minimum value in each similarity generated is more than or equal to preset similarity threshold；
It is more than or equal to preset similarity threshold in response to determining, the target image is added to the registered images set
In.
2. according to the method described in claim 1, wherein, scheming for the registration of each of described registered images set described
Picture generates the registered images with before the similarity of the facial image, and the method further includes：
It determines the human face characteristic point in the facial image, generates fisrt feature point vector；And
Each registered images in the registered images set generate the phase of the registered images and the facial image
Like degree, including：
It determines the human face characteristic point in the registered images, generates second feature point vector；
The similarity for the second feature point vector that the fisrt feature point vector sum is generated is determined as the registered images and institute
State the similarity of facial image.
3. according to the method described in claim 1, wherein, the method further includes：
It is less than preset similarity threshold in response to determining, by the similarity with the facial image in the registered images set
Minimum registered images are deleted.
4. according to any method in claim 1-3, wherein it is described to extract facial image from the target image,
Including：
Initial Face image is extracted from the target image；
Image procossing is carried out to the Initial Face image, described image processing includes at least one of following：Noise reduction process, image
Enhancing processing and illumination pretreatment；
Using the Initial Face image after image procossing as the facial image of extraction.
5. a kind of device for fresh information, described device include：
Acquiring unit is configured to obtain the registered images set of the target image and the target user of target user；
Extraction unit is configured to extract facial image from the target image；
Similarity generation unit is configured to, for each registered images in the registered images set, generate the registration figure
As the similarity with the facial image；
Determination unit, is configured to determine whether the minimum value in each similarity generated is more than or equal to preset similarity
Threshold value；
Adding device is configured to be more than or equal to preset similarity threshold in response to determining, the target image is added to
In the registered images set.
6. device according to claim 5, wherein described device further includes：
Fisrt feature point vector determining module is configured to determine the human face characteristic point in the facial image, it is special to generate first
Sign point vector；And
The similarity generation unit, including：
Second feature point vector determining module is configured to determine the human face characteristic point in the registered images, generates second feature
Point vector；
Similarity determining module is configured to the similar of the second feature point vector for being generated the fisrt feature point vector sum
Degree is determined as the similarity of the registered images and the facial image.
7. device according to claim 5, wherein described device further includes：
Deleting unit, be configured in response to determine be less than preset similarity threshold, by the registered images set with institute
The registered images for stating the similarity minimum of facial image are deleted.
8. according to any device in claim 5-7, wherein the extraction unit is further configured to：
Initial Face image is extracted from the target image；
Image procossing is carried out to the Initial Face image, described image processing includes at least one of following：Noise reduction process, image
Enhancing processing and illumination pretreatment；
Using the Initial Face image after image procossing as the facial image of extraction.
9. a kind of electronic equipment, including：
One or more processors；
Memory, for storing one or more programs,
When one or more of programs are executed by one or more of processors so that one or more of processors
Realize the method as described in any in claim 1-4.
10. a kind of computer-readable medium, is stored thereon with computer program, which is characterized in that the program is executed by processor
Methods of the Shi Shixian as described in any in claim 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810270170.XA CN108491813A (en) | 2018-03-29 | 2018-03-29 | Method and apparatus for fresh information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810270170.XA CN108491813A (en) | 2018-03-29 | 2018-03-29 | Method and apparatus for fresh information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108491813A true CN108491813A (en) | 2018-09-04 |
Family
ID=63316735
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810270170.XA Pending CN108491813A (en) | 2018-03-29 | 2018-03-29 | Method and apparatus for fresh information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108491813A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111723655A (en) * | 2020-05-12 | 2020-09-29 | 五八有限公司 | Face image processing method, device, server, terminal, equipment and medium |
| CN112115740A (en) * | 2019-06-19 | 2020-12-22 | 北京海益同展信息科技有限公司 | Method and apparatus for processing image |
| CN116523909A (en) * | 2023-06-30 | 2023-08-01 | 广州市斯睿特智能科技有限公司 | Visual detection method and system for appearance of automobile body |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101477621A (en) * | 2009-02-20 | 2009-07-08 | 深圳华为通信技术有限公司 | Image updating process and apparatus based on human face recognition |
| US20150379717A1 (en) * | 2014-06-30 | 2015-12-31 | Toshiba Tec Kabushiki Kaisha | Information processing apparatus and method for updating feature values of products for object recognition |
| CN105913051A (en) * | 2016-05-26 | 2016-08-31 | 京东方科技集团股份有限公司 | Device and method for updating template library for face image recognition |
| CN107818301A (en) * | 2017-10-16 | 2018-03-20 | 阿里巴巴集团控股有限公司 | Update the method, apparatus and electronic equipment of biometric templates |
-
2018
- 2018-03-29 CN CN201810270170.XA patent/CN108491813A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101477621A (en) * | 2009-02-20 | 2009-07-08 | 深圳华为通信技术有限公司 | Image updating process and apparatus based on human face recognition |
| US20150379717A1 (en) * | 2014-06-30 | 2015-12-31 | Toshiba Tec Kabushiki Kaisha | Information processing apparatus and method for updating feature values of products for object recognition |
| CN105913051A (en) * | 2016-05-26 | 2016-08-31 | 京东方科技集团股份有限公司 | Device and method for updating template library for face image recognition |
| CN107818301A (en) * | 2017-10-16 | 2018-03-20 | 阿里巴巴集团控股有限公司 | Update the method, apparatus and electronic equipment of biometric templates |
Non-Patent Citations (2)
| Title |
|---|
| 李晓东: "《基于子空间和流形学习的人脸识别算法研究》", 30 June 2013 * |
| 高卫 等: "《光电干扰效果评估方法》", 30 July 2006 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112115740A (en) * | 2019-06-19 | 2020-12-22 | 北京海益同展信息科技有限公司 | Method and apparatus for processing image |
| CN112115740B (en) * | 2019-06-19 | 2024-04-09 | 京东科技信息技术有限公司 | Method and apparatus for processing image |
| CN111723655A (en) * | 2020-05-12 | 2020-09-29 | 五八有限公司 | Face image processing method, device, server, terminal, equipment and medium |
| CN111723655B (en) * | 2020-05-12 | 2024-03-08 | 五八有限公司 | Face image processing method, device, server, terminal, equipment and medium |
| CN116523909A (en) * | 2023-06-30 | 2023-08-01 | 广州市斯睿特智能科技有限公司 | Visual detection method and system for appearance of automobile body |
| CN116523909B (en) * | 2023-06-30 | 2023-09-29 | 广州市斯睿特智能科技有限公司 | Visual detection method and system for appearance of automobile body |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108062780B (en) | Method for compressing image and device | |
| CN110677598B (en) | Video generation method and device, electronic equipment and computer storage medium | |
| CN107578017B (en) | Method and apparatus for generating image | |
| CN108416323B (en) | Method and device for recognizing human face | |
| WO2020006961A1 (en) | Image extraction method and device | |
| CN108446387A (en) | Method and apparatus for updating face registration library | |
| CN108269254A (en) | Image quality measure method and apparatus | |
| CN108509915A (en) | The generation method and device of human face recognition model | |
| CN108229419A (en) | For clustering the method and apparatus of image | |
| CN107220652B (en) | Method and device for processing pictures | |
| CN108986169A (en) | Method and apparatus for handling image | |
| CN108494778A (en) | Identity identifying method and device | |
| CN108280477A (en) | Method and apparatus for clustering image | |
| CN109034069A (en) | Method and apparatus for generating information | |
| CN109410253B (en) | For generating method, apparatus, electronic equipment and the computer-readable medium of information | |
| CN108363999A (en) | Operation based on recognition of face executes method and apparatus | |
| CN108491813A (en) | Method and apparatus for fresh information | |
| CN108388889B (en) | Method and device for analyzing face image | |
| CN108446650A (en) | The method and apparatus of face for identification | |
| CN108229375B (en) | Method and device for detecting face image | |
| CN109241934A (en) | Method and apparatus for generating information | |
| CN108280422A (en) | The method and apparatus of face for identification | |
| CN110648289A (en) | Image denoising processing method and device | |
| CN108335390A (en) | Method and apparatus for handling information | |
| CN107886559A (en) | Method and apparatus for generating picture |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180904 |
|
| RJ01 | Rejection of invention patent application after publication |