CN108073724A - For generating the method and apparatus of information - Google Patents
For generating the method and apparatus of information Download PDFInfo
- Publication number
- CN108073724A CN108073724A CN201810007800.4A CN201810007800A CN108073724A CN 108073724 A CN108073724 A CN 108073724A CN 201810007800 A CN201810007800 A CN 201810007800A CN 108073724 A CN108073724 A CN 108073724A
- Authority
- CN
- China
- Prior art keywords
- image
- face
- users
- user
- feature vector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 239000013598 vector Substances 0.000 claims description 93
- 230000001815 facial effect Effects 0.000 claims description 28
- 230000004044 response Effects 0.000 claims description 21
- 238000000605 extraction Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 239000000284 extract Substances 0.000 claims description 4
- 238000000151 deposition Methods 0.000 claims 1
- 230000006870 function Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 238000012549 training Methods 0.000 description 8
- 238000013528 artificial neural network Methods 0.000 description 6
- 230000006854 communication Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 239000011449 brick Substances 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000009434 installation Methods 0.000 description 3
- 239000004570 mortar (masonry) Substances 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 239000007787 solid Substances 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000005284 excitation Effects 0.000 description 2
- 230000005291 magnetic effect Effects 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 210000004556 brain Anatomy 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 210000003127 knee Anatomy 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/5838—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Collating Specific Patterns (AREA)
Abstract
The embodiment of the present application discloses the method and apparatus for generating information.One specific embodiment of this method includes：Obtain the first image of the face-image comprising target user；Second image is selected from the image library collected in advance based on the first image, generates the second image collection, wherein, the second image includes the face-image of target user and the face-image of at least one other user；For each other users, determine to include the quantity of the second image of the face-image of the other users in the second image collection；Based on the quantity of the second image of the total quantity and identified face-image comprising the other users of the second image in the second image collection, generation target user and the related information of the other users.The embodiment can obtain the hint information for finding target user.
Description
Technical field
The invention relates to field of computer technology, and in particular to Internet technical field, it is more particularly, to raw
Into the method and apparatus of information.
Background technology
In application scenes, exist and seek Man's Demands, for example, the police find suspect, find and lose in case of criminal detection
Track children or old man etc..In practice, in the case where only providing target person photo, it will usually by issuing Lost (example
Such as, pass through newspaper, TV, broadcast, website etc.) or monitor video by manually browsing magnanimity by way of searched.
The content of the invention
The embodiment of the present application proposes the method and apparatus for generating information.
In a first aspect, the embodiment of the present application provides a kind of method for generating information, this method includes：Acquisition includes
First image of the face-image of target user；Second image is selected from the image library collected in advance based on the first image, it is raw
Into the second image collection, wherein, the second image includes the face-image of target user and the face figure of at least one other user
Picture；For each other users, determine to include the number of the second image of the face-image of the other users in the second image collection
Amount；Based on the second image in the second image collection total quantity and the identified face-image comprising the other users second
The quantity of image, generation target user and the related information of the other users.
In some embodiments, the second image, generation second are selected from the image library collected in advance based on the first image
Image collection, including：First eigenvector is generated from the facial characteristics of the first extracting target from images user；For in image library
Every image, extracted from the image each user facial characteristics generation second feature vector, calculate each second feature
The similarity of vector and first eigenvector is more than or equal to similarity threshold in response to existing with the similarity of first eigenvector
Second feature vector and be less than the second feature vector of similarity threshold with the similarity of first eigenvector, by the image
It is determined as the second image；Second image collection is generated based on the second definite image.
In some embodiments, the quantity of the second image of the face-image comprising the other users is determined, including：From
The second feature vector by the facial characteristics generation of the other users is selected in two feature vectors as with reference to feature vector；For
Every second image in second image collection, in response in the facial characteristics generation by each user in second image
There is the second feature vector for being more than or equal to similarity threshold with the similarity of reference feature vector in second feature vector, by this
Second image is determined as the second image of the face-image comprising the other users；Based on identified comprising the other users
Second image of face-image determines the quantity of the second image of the face-image comprising the other users.
In some embodiments, this method further includes：For each other users, in response to the face comprising the other users
The quantity of second image of portion's image is more than or equal to default amount threshold, and the height which is determined as to target user is closed
It is combined family；Push the related information of target user and identified highlights correlations user.
Second aspect, the embodiment of the present application provide a kind of device for being used to generate information, and device includes：Image acquisition list
Member is configured to obtain the first image of the face-image comprising target user；Image selection unit is configured to based on first
Image selects the second image from the image library collected in advance, generates the second image collection, wherein, the second image is used comprising target
The face-image at family and the face-image of at least one other user；Information generating unit is configured to for other each use
Family determines the quantity of the second image of the face-image comprising the other users in the second image collection；Based on the second image set
The quantity of second image of the total quantity of the second image and the identified face-image comprising the other users in conjunction generates mesh
Mark user and the related information of the other users.
In some embodiments, image selection unit includes：Extraction module is configured to from the first extracting target from images
The facial characteristics generation first eigenvector of user；Determining module is configured to for every image in image library, from the figure
The facial characteristics generation second feature vector of each user is extracted as in, calculates each second feature vector and first eigenvector
Similarity, in response to exist and first eigenvector similarity be more than or equal to similarity threshold second feature vector and
It is less than the second feature vector of similarity threshold with the similarity of first eigenvector, which is determined as the second image；It is raw
Into module, it is configured to generate the second image collection based on the second definite image.
In some embodiments, the quantity of the second image of the face-image comprising the other users is determined, including：From
The second feature vector by the facial characteristics generation of the other users is selected in two feature vectors as with reference to feature vector；For
Every second image in second image collection, in response in the facial characteristics generation by each user in second image
There is the second feature vector for being more than or equal to similarity threshold with the similarity of reference feature vector in second feature vector, by this
Second image is determined as the second image of the face-image comprising the other users；Based on identified comprising the other users
Second image of face-image determines the quantity of the second image of the face-image comprising the other users.
In some embodiments, device further includes：User's determination unit is configured to for each other users, response
It is more than or equal to default amount threshold in the quantity of the second image of the face-image comprising the other users, the other users are true
It is set to the highlights correlations user of target user；Push unit is configured to push target user and is used with identified highlights correlations
The related information at family.
Method and apparatus provided by the embodiments of the present application for generating information, by based on the face including target user
First image of image selects the second image to generate the second image collection from image library, then determines to wrap in the second image collection
The quantity of second image of the face-image containing each other users ultimately produces associating for target user and each other users
Information, so as to obtain the hint information for finding target user.
Description of the drawings
By reading the detailed description made to non-limiting example made with reference to the following drawings, 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 for being used to generate one embodiment of the method for information according to the application；
Fig. 3 is the schematic diagram for being used to generate an application scenarios of the method for information according to the application；
Fig. 4 is the flow chart for being used to generate another embodiment of the method for information according to the application；
Fig. 5 is the structure diagram for being used to generate one embodiment of the device of information according to the application；
Fig. 6 is adapted for the structure diagram of the computer system of the server for realizing the embodiment of the present application.
Specific embodiment
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, illustrated only in attached drawing and invent relevant part with related.
It should be noted that in the case where there is no conflict, the feature in embodiment and embodiment in the 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 method for being used to generate information that can apply the application or the implementation for generating the device of information
The exemplary system architecture 100 of example.
As shown in Figure 1, system architecture 100 can include terminal device 101,102,103, network 104 and server 105.
Network 104 between terminal device 101,102,103 and server 105 provide communication link medium.Network 104 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be interacted with using terminal equipment 101,102,103 by network 104 with server 105, to receive or send out
Send message etc..Various telecommunication customer end applications can be installed, such as shopping class is applied, searched on terminal device 101,102,103
The application of rope class, instant messaging tools, mailbox client, social platform software etc..
Terminal device 101,102,103 can be the various electronic equipments for having display screen, include but not limited to intelligent hand
Machine, tablet computer, E-book reader, MP3 player (Moving Picture Experts Group Audio Layer
III, dynamic image expert's compression standard audio level 3), MP4 (Moving Picture Experts Group Audio
Layer IV, dynamic image expert's compression standard audio level 4) player, pocket computer on knee and desktop computer etc.
Deng.
Server 105 can be to provide the server of various services, such as the figure to the offer of terminal device 101,102,103
Image background server as carrying out feature extraction.Image background server can carry out image for receiving etc. analyzing etc.
Reason, and handling result (for example, related information of target user and other users) is fed back into terminal device.
It should be noted that the method for being used to generate information that the embodiment of the present application is provided generally is held by server 105
Row, correspondingly, the device for generating information is generally positioned in server 105.
It should be understood that the number of the terminal device, network and server in Fig. 1 is only schematical.According to realization need
Will, can have any number of terminal device, network and server.
With continued reference to Fig. 2, the flow for being used to generate one embodiment of the method for information according to the application is shown
200.This is used for the method for generating information, comprises the following steps：
Step 201, the first image of the face-image comprising target user is obtained.
In the present embodiment, for generating electronic equipment (such as the service shown in FIG. 1 of the method for information operation thereon
Device) can the face-image comprising target user be received from terminal device by wired connection mode or radio connection
First image.Wherein, target user can need the people that finds, for example, the suspect that the police are found in case of criminal detection, missing
Children or old man etc., the first image can be the photos of target user, can be included in the first image can to target user into
The face-image (for example, with front, clearly human face region) of row recognition of face.
It is pointed out that above-mentioned radio connection can include but is not limited to 3G/4G connections, WiFi connections, bluetooth
Connection, WiMAX connections, Zigbee connections, UWB (ultra wideband) connections and other currently known or exploitations in the future
Radio connection.
Step 202, the second image is selected from the image library collected in advance based on the first image, generates the second image set
It closes, wherein, the second image includes the face-image of target user and the face-image of at least one other user.
In the present embodiment, for generating electronic equipment (such as the service shown in FIG. 1 of the method for information operation thereon
Device) it can be beforehand through the image collecting device under line (for example, the installations such as solid shop/brick and mortar store, public place, both sides of the road are taken the photograph under line
As head) acquisition includes the images of at least two facial images (that is, face can be carried out by including at least two in the image of acquisition
The face-image of identification), obtain the image library for including multiple images；Be then based on step 201 reception includes target user's
First image of face-image is chosen from image library meets preset condition (comprising the face-image of target user and at least one
The face-image of other users) the second image, generate the second image collection, for example, from picture by way of picture searching
All second images for meeting preset condition are searched in storehouse.
In some optional realization methods of the present embodiment, step 202 can specifically include：
The first step generates first eigenvector from the facial characteristics of the first extracting target from images user.Specifically, it is above-mentioned
Electronic equipment can carry out Face datection to the first image that step 201 receives first, where determining the face of target user
Region (that is, face-image), wherein, Face datection is that face is modeled with the method for knowledge based or statistics, more to be detected
Region and the matching degree of faceform, so as to obtain the region there may be face；Feature based extraction algorithm (example afterwards
Such as, HOG (Histogram of Oriented Gradient, histograms of oriented gradients), LBP (Local Binary
Pattern, local binary patterns), Gabor wavelet scheduling algorithm) from identified human face region extract target user face
Feature is then based on extracted facial characteristics generation first eigenvector.
Second step for every image in image library, extracts the facial characteristics generation the of each user from the image
Two feature vectors calculate the similarity of each second feature vector and first eigenvector, in response to exist with fisrt feature to
The similarity of amount is more than or equal to the second feature vector of similarity threshold, which is determined as the second image.Specifically, it is above-mentioned
Multiple images that electronic equipment can include at least two facial images beforehand through the image acquisition device under line obtain
To image library；For every image in image library, above-mentioned electronic equipment can carry out Face datection first, determine in the image
Comprising all human face regions, afterwards from each face extracted region facial characteristics come generate second feature vector, then calculate
The similarity of each second feature vector and first eigenvector is more than etc. in response to existing with the similarity of first eigenvector
It is less than phase in the second feature vector of similarity threshold (for example, 97%, 95% etc.) and with the similarity of first eigenvector
Second feature like degree threshold value is vectorial (that is, the face-image comprising other users), which is determined as the second image.This
In, similarity calculating method well known to included angle cosine (cosine), Euclidean distance etc. may be employed to carry out similarity calculation.With
Exemplified by included angle cosine, the similarity between second feature vector and first eigenvector is equal to the folder between the two feature vectors
Cosine of an angle value.
3rd step generates the second image collection based on the second definite image.Above-mentioned electronic equipment is determined based on second step
Each second image generate the second image collection, meet all second images of preset condition so as to obtain hereafter retouched
The processing step stated.
In some optional realization methods of the present embodiment, facial characteristics generation the is extracted from first/second image
One/second feature vector can generate model realization by feature vector trained in advance, i.e. by face-image (for example, first
Face-image in image or the second image) input is to feature vector generation model trained in advance, so as to obtain feature vector
(for example, first eigenvector or second feature vector), feature vector generation model is used to characterize face-image and feature vector
Between correspondence.
Feature vector generation model can be artificial neural network, and artificial neural network is from information processing angle to human brain god
It is abstracted through metanetwork, establishes certain naive model, different networks is formed by different connection modes.Usually by substantial amounts of
It is interconnected to constitute between node (or neuron), a kind of each specific output function of node on behalf, is known as excitation function.
Connection between each two node all represents one for the weighted value by the connection signal, is referred to as weight and (is called to do and join
Number), the output of network is then according to the different and different of the connection mode of network, weighted value and excitation function.Feature vector generates mould
Type generally includes multiple layers, and each layer includes multiple nodes, in general, the weight of the node of same layer can be identical, different layers
The weight of node can be different, therefore multiple layers of parameter of feature vector generation model can not also be same.
In some optional realization methods of the present embodiment, feature vector generation model is trained as follows
It arrives：Above-mentioned electronic equipment can obtain multiple training samples first, and each training sample includes face-image and and face-image
The corresponding feature vector of corresponding feature vector, wherein face-image can be predetermined；Then, by each training sample
In face-image as input, it is trained using feature vector corresponding with face-image in each training sample as exporting
Obtain feature vector generation model.Above-mentioned electronic equipment training can be initialization feature vector generation model, and initialization is special
The feature vector generation model that sign vector generation model can be unbred feature vector generation model or training is not completed,
Each layer of the feature vector generation model of initialization can be provided with initial parameter, and parameter is in the training of feature vector generation model
It can constantly be adjusted in the process.Initialization feature vector generation model can be various types of indisciplines or not train
Obtained by the artificial neural network of completion or the artificial neural network that a variety of indisciplines or training is completed are combined
Model, for example, initialization feature vector generation model can be unbred convolutional neural networks or without instruction
Experienced Recognition with Recurrent Neural Network can also be to unbred convolutional neural networks, unbred Recognition with Recurrent Neural Network and not
Housebroken full articulamentum is combined obtained model.
Step 203, for each other users, the face-image comprising the other users in the second image collection is determined
The quantity of second image；Total quantity and the identified face for including the other users based on the second image in the second image collection
The quantity of second image of portion's image, generation target user and the related information of the other users.
In the present embodiment, for generating the method for information operation electronic equipment thereon (for example, clothes shown in FIG. 1
Be engaged in device) can based on step 202 generate the second image collection, determine in the other users outside target user it is each other
Number (i.e. the second image of the face-image comprising the other users that the face-image of user occurs in the second image collection
Quantity) number in same second image is appeared in as target user and the other users；Then, based on the second image set
Close and second image of the face-image in the second image collection of the other users in the number that occurs (or, comprising this other
The quantity of second image of the face-image of user) target user and the related information of the other users are generated, wherein, association letter
Breath can include target user and the other users and appear in number (or ratio, such as identified in same second image
The ratio of the total quantity of second image in number and the second image collection), the information of the other users is (for example, the other users
Face-image etc.).
In the present embodiment, the number (or ratio) that two users are appeared in same image is higher, illustrates two users
Between contact it is closer, in other words the number (or ratio) reflect to a certain extent the two users in the future appear in it is same
Probability in image.For example, to find target user " Zhang San ", method through this embodiment has obtained 100 and has included user
The image of the face-image of " Zhang San ", and have in this 100 images comprising user " Zhang San " in 45 images comprising use
The face-image at family " Li Si ", that is to say, that the face-image of user " Zhang San " and the face-image of user " Li Si " appear in
The ratio of same image is 45%, then target user " Zhang San " can be found by tracking user " Li Si ", so as to be to seek
Target user " Zhang San " is looked for provide effective hint information, improves the success rate of missing.
It should be noted that due to the randomness and uncertainty of Image Acquisition, to target user in the embodiment of the present application
Face-image and other users position of the face-image in the second image and distance be not limited, as long as two users go out
It can think that the two users have certain incidence relation in present same second image.
In some optional realization methods of the present embodiment, the second figure of the face-image comprising the other users is determined
The quantity of picture, including：The second feature vector that selection is generated by the facial characteristics of the other users from second feature vector is made
For reference feature vector；For every second image in the second image collection, in response to by each in second image
Exist in the second feature vector of the facial characteristics generation of user and be more than or equal to similarity threshold with the similarity of reference feature vector
Second image is determined as the second image of the face-image comprising the other users by the second feature vector of value；Based on institute
Second image of the definite face-image comprising the other users determines the second figure of the face-image comprising the other users
The quantity of picture.
By taking Fig. 3 which will be described as an example, other users can include user B, C, D etc., which is user B
When, it is possible, firstly, to which the face-image of user B in the second image 3061 (or second image 3063 or 3064) is corresponding second special
Sign vector is as with reference to feature vector；Afterwards, for each the second image, by each other users in second image
The second feature vector of facial characteristics generation (calculates similarity) compared with reference feature vector, in response to above-mentioned second feature
There is the second feature vector for being more than or equal to similarity threshold with reference feature vector similarity in vector, then by second image
It is determined as the second image of the face-image comprising user B；Then, based on the second of the definite face-image comprising user B
Image (for example, second image 3061,3063 and 3064) can determine the quantity of the second image of the face-image comprising user B
For 3.Similar, when the other users are user C, it may be determined that the quantity of the second image of the face-image comprising user C
For 2 ... ..., and so on.
With continued reference to Fig. 3, Fig. 3 is to be illustrated according to the present embodiment for generating one of the application scenarios of the method for information
Figure.In the application scenarios of Fig. 3, user (for example, the police or missing crew family members) will include user A by terminal 301 first
The photo (that is, first of (that is, target user, user A can be missing crews that the suspect that the police are found or family members find etc.)
Image) it is sent to server 302；Afterwards, server 302 based on above-mentioned photo from the image library collected in advance (for example, by under line
Camera 303 gather in advance image composition image library) in selection comprising user A face-image the second image 306,
Generate the second image collection 305；Then, for face-image be included in the second image at least one other user (for example,
User B, C, D etc.) in each other users, determine comprising the other users face-image the second image quantity (example
Such as, the quantity of the second image of the face-image comprising user B is 3, the quantity of the second image of the face-image comprising user C
For 2,1) quantity of the second image of the face-image comprising user D is；Then, based on the second image collection 305 and determine
The face-image comprising user B/C/D the second image quantity generation user A and user B/C/D related information (for example,
Related information 3071~3074 in related information set 307, wherein, related information 3071 associates letter for user A and user B's
Breath, related information 3072 are the related information ... ... of user A and user C, and so on).It can be with by the related information of generation
The hint information for finding user A is provided, for example, finding user A by tracking user B/C/D.
The method that above-described embodiment of the application provides determines the face-image of target user by way of recognition of face
Letter is associated with what the face-image of other users appeared in number in same image and generation target user and other users
Breath, so as to obtain the hint information (for example, face-image etc.) in related information for finding target user.
With further reference to Fig. 4, it illustrates for generating the flow 400 of another embodiment of the method for information.The use
In the flow 400 of the method for generation information, comprise the following steps：
Step 401, the first image of the face-image comprising target user is obtained.
In the present embodiment, for generating electronic equipment (such as the service shown in FIG. 1 of the method for information operation thereon
Device) can the face-image comprising target user be received from terminal device by wired connection mode or radio connection
First image.Wherein, target user can need the people that finds, for example, the suspect that the police are found in case of criminal detection, missing
Children or old man etc., the first image can be the photos of target user, can be included in the first image can to target user into
The face-image (for example, with front, clearly human face region) of row recognition of face.
Step 402, the second image is selected from the image library collected in advance based on the first image, generates the second image set
It closes, wherein, the second image includes the face-image of target user and the face-image of at least one other user.
In the present embodiment, for generating electronic equipment (such as the service shown in FIG. 1 of the method for information operation thereon
Device) it can be beforehand through the image collecting device under line (for example, the installations such as solid shop/brick and mortar store, public place, both sides of the road are taken the photograph under line
As head) acquisition includes the images of at least two facial images (that is, face can be carried out by including at least two in the image of acquisition
The face-image of identification), obtain the image library for including multiple images；Be then based on step 401 reception includes target user's
Face-image and the face-image of at least one other user) the first image chosen from image library meet preset condition (bag
Second image of the face-image containing target user generates the second image collection, for example, from picture by way of picture searching
All second images for meeting preset condition are searched in storehouse.
Step 403, for each other users, the face-image comprising the other users in the second image collection is determined
The quantity of second image；Total quantity and the identified face for including the other users based on the second image in the second image collection
The quantity of second image of portion's image, generation target user and the related information of the other users.
In the present embodiment, for generating the method for information operation electronic equipment thereon (for example, clothes shown in FIG. 1
Be engaged in device) can based on step 402 generate the second image collection, determine in the other users outside target user it is each other
Number (i.e. the second image of the face-image comprising the other users that the face-image of user occurs in the second image collection
Quantity) number in same image is appeared in as target user and the other users；Then, based on the second image collection and
Number that the face-image of the other users occurs in the second image collection (or, the face-image comprising the other users
The quantity of second image) target user and the related information of the other users are generated, wherein, related information can include target and use
Family and the other users appear in number in same image (or the in ratio, such as definite number and the second image collection
The ratio of the total quantity of two images), the information (for example, face-image etc.) of the other users.
Step 404, for each other users, in response to the number of the second image of the face-image comprising the other users
Amount is more than or equal to default amount threshold, which is determined as to the highlights correlations user of target user.
In the present embodiment, for each other users in other users (for example, user B, C, D shown in Fig. 3), use
It can be in response to comprising this its in the method operation electronic equipment (for example, server shown in FIG. 1) thereon of generation information
The quantity of second image of the face-image of his user is more than or equal to default amount threshold (for example, second in the second image collection
60% of amount of images etc.), which is determined as to the highlights correlations user of target user, here, the height of target user
It can be a user or more than one user to spend association user.For example, in the application scenarios of Fig. 3, the second figure
The total quantity of the second image is 4 during image set closes, and the quantity of the second image of the face-image comprising user B is 3, includes user C
Face-image the second image quantity for 2, the quantity of the second image of the face-image comprising user D is 1, works as present count
When measuring 60% that threshold value is the total quantity of the second image in the second image collection, user B is the highlights correlations user of user A.
It should be noted that default amount threshold can be absolute figure, for example, 50,100 etc. or relative number
Value, for example, in the second image collection the second amount of images 40%, 50%, 60% etc., those skilled in the art can basis
The needs of practical application scene are configured.
Step 405, the related information of target user and identified highlights correlations user are pushed.
In the present embodiment, for generating the method for information operation electronic equipment thereon (for example, clothes shown in FIG. 1
Business device) related information of the highlights correlations user (for example, user B of Fig. 3) that target user and step 404 determine can be pushed,
For example, above-mentioned related information is pushed to terminal 301 shown in Fig. 3.
Figure 4, it is seen that compared with the corresponding embodiments of Fig. 2, in the present embodiment for the method that generates information
Flow 400 the step of highlighting the highlights correlations user of definite target user and pushing related information.The present embodiment is retouched as a result,
The scheme stated can be based on big data (quantity of the second image is enough in the second image collection) acquisition and be contacted with target user
Close other users so that the hint information of the searching target user obtained is more accurate, further improve searching mesh
Mark the success rate of user.
With further reference to Fig. 5, as the realization to method shown in above-mentioned each figure, this application provides one kind for generating 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 server.
As shown in figure 5, the present embodiment includes for generating the device 500 of information：Image acquisition unit 501, image choosing
Select unit 502 and information generating unit 503.Wherein, image acquisition unit 501 is configured to obtain the face for including target user
First image of image；Image selection unit 502 is configured to select from the image library collected in advance based on the first image
Two images generate the second image collection, wherein, the second image includes the face-image of target user and at least one other user
Face-image；And information generating unit 503 is configured to for each other users, is determined to include in the second image collection and is somebody's turn to do
The quantity of second image of the face-image of other users；Based on the second image in the second image collection total quantity and determine
The face-image comprising the other users the second image quantity, generation target user and the other users associate letter
Breath.
In the present embodiment, for generate the device 500 of information image acquisition 501 can by wired connection mode or
Person's radio connection receives the first image of the face-image comprising target user from terminal device.Wherein, target user can
To be to need the people found, for example, the police are found in case of criminal detection suspect, missing child or old man etc., the first image can
To be the photo of target user, the face-image (example that recognition of face can be carried out to target user can be included in the first image
Such as, there is front, clearly human face region).
In the present embodiment, above-mentioned image selection unit 502 can beforehand through under line image collecting device (for example,
The camera of the installations such as solid shop/brick and mortar store, public place, both sides of the road under line) gather the image for including at least two facial images
(that is, two face-images that can carry out recognition of face are included at least in the image of acquisition), obtains the figure for including multiple images
As storehouse；The first image of the face-image comprising target user that above-mentioned image acquisition unit 501 receives is then based on from image
It is chosen in storehouse and meets the of preset condition (face-image of face-image and at least one other user comprising target user)
Two images generate the second image collection, for example, searching the institute for meeting preset condition from picture library by way of picture searching
There is the second image.
In some optional realization methods of the present embodiment, above-mentioned image selection unit 502 includes extraction module, determines
Module and generation module.Wherein, extraction module is configured to from the facial characteristics of the first extracting target from images user generation the
One feature vector；Determining module is configured to, for every image in image library, extract the face of each user from the image
Portion's feature generation second feature vector calculates the similarity of each second feature vector and first eigenvector, in response to existing
It is more than or equal to the second feature vector of similarity threshold and phase with first eigenvector with the similarity of first eigenvector
Like second feature vector of the degree less than similarity threshold, which is determined as the second image；Generation module is configured to be based on
The second definite image generates the second image collection.
In the present embodiment, above- mentioned information generation unit 503 can be based on the generation of above-mentioned image selection unit 502 second
Image collection determines the face-image of each other users in the other users outside target user in the second image collection
The number (i.e. the quantity of the second image of the face-image comprising the other users) of appearance is as other use of target user and this
Family appears in the number in same image；Then, the face-image based on the second image collection and the other users is in the second figure
Image set close in occur number (or, quantity of the second image of the face-image comprising the other users) generation target user with
The related information of the other users, wherein, related information can include target user and appear in same image with the other users
In number (ratio of the total quantity of the second image in or ratio, such as definite number and the second image collection), this other
The information (for example, face-image etc.) of user.
In some optional realization methods of the present embodiment, the second figure of the face-image comprising the other users is determined
The quantity of picture, including：The second feature vector that selection is generated by the facial characteristics of the other users from second feature vector is made
For reference feature vector；For every second image in the second image collection, in response to by each in second image
Exist in the second feature vector of the facial characteristics generation of user and be more than or equal to similarity threshold with the similarity of reference feature vector
Second image is determined as the second image of the face-image comprising the other users by the second feature vector of value；Based on institute
Second image of the definite face-image comprising the other users determines the second figure of the face-image comprising the other users
The quantity of picture.
In some optional realization methods of the present embodiment, device 500 further includes user's determination unit and push unit.
Wherein, user's determination unit is configured to for each other users, in response to of the face-image comprising the other users
The quantity of two images is more than or equal to default amount threshold, which is determined as to the highlights correlations user of target user；It pushes away
Unit is sent to be configured to the related information of push target user and identified highlights correlations user.
The device that above-described embodiment of the application provides determines the face-image of target user by way of recognition of face
Letter is associated with what the face-image of other users appeared in number in same image and generation target user and other users
Breath, so as to obtain the hint information (for example, face-image in related information) for finding target user.
Below with reference to Fig. 6, it illustrates suitable for being used for realizing the computer system 600 of the server of the embodiment of the present application
Structure diagram.Server shown in Fig. 6 is only an example, should not be to the function of the embodiment of the present application and use scope band
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 program in random access storage device (RAM) 603 from storage part 608 and
Perform various appropriate actions 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.
I/O interfaces 605 are connected to 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 part 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 performs 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 read from it
Computer program be mounted into as needed storage part 608.
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, including being carried on computer-readable medium
On computer program, which includes for the program code of the method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed from network by communications portion 609 and/or from detachable media
611 are mounted.When the computer program is performed by central processing unit (CPU) 601, perform what is limited in the present processes
Above-mentioned function.
It should be noted that computer-readable medium described herein can be computer-readable signal media or meter
Calculation machine readable storage medium storing program for executing either the two any combination.Computer readable storage medium for example can be --- but not
It is limited to --- electricity, magnetic, optical, electromagnetic, system, device or the device of infrared ray or semiconductor or arbitrary above combination.Meter
The more specific example of calculation machine readable storage medium storing program for executing can include but is not limited to：Electrical connection with one or more conducting wires, just
It takes formula computer disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type and 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 application, computer readable storage medium can any include or store journey
The tangible medium of sequence, the program can be commanded the either device use or in connection of execution system, device.And at this
In application, computer-readable signal media can include in a base band or as carrier wave a part propagation data-signal,
Wherein carry computer-readable program code.Diversified forms may be employed in the data-signal of this propagation, including but it is unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium beyond storage medium is read, which can send, propagates or transmit and be used for
By instruction execution system, device either device use or program in connection.It is included on computer-readable medium
Program code can be transmitted with any appropriate medium, be included but not limited to：Wirelessly, electric wire, optical cable, RF etc. or above-mentioned
Any appropriate combination.
It can be with one or more programming languages or its calculating for combining to write to perform the operation of the application
Machine 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
Fully to perform on the user computer, partly perform, performed as an independent software package on the user computer,
Part performs or performs on a remote computer or server completely on the remote computer on the user computer for part.
In the situation for being related to remote computer, remote computer can pass through the network of any kind --- including LAN (LAN)
Or wide area network (WAN)-be connected to subscriber computer or, it may be connected to outer computer (such as utilizes Internet service
Provider passes through Internet connection).
Flow chart and block diagram in attached drawing, it is illustrated that according to the system of the various embodiments of the application, method and computer journey
Architectural framework in the cards, function and the operation of sequence product.In this regard, each box in flow chart or block diagram can generation
The part of one module of table, program segment or code, the part of the module, program segment or code include one or more use
In the executable instruction of logic function as defined in realization.It should also be noted that it is marked at some as in the realization replaced in box
The function of note can also be occurred with being different from the order marked in attached drawing.For example, two boxes succeedingly represented are actually
It can perform substantially in parallel, they can also be performed in the opposite order sometimes, this is depending on involved function.Also to note
Meaning, the combination of each box in block diagram and/or flow chart and the box in block diagram and/or flow chart can be with holding
The dedicated hardware based system of functions or operations as defined in row is realized or can use specialized hardware and computer instruction
Combination 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 set in the processor, for example, can be described as：A kind of processor bag
Include image acquisition unit, image selection unit and information generating unit.Wherein, the title of these units is not under certain conditions
The restriction to the unit in itself is formed, for example, image acquisition unit is also described as " obtaining the face for including target user
The unit of first image of image ".
As on the other hand, present invention also provides a kind of computer-readable medium, which can be
Included in device described in above-described embodiment；Can also be individualism, and without be incorporated the device in.Above-mentioned calculating
Machine readable medium carries one or more program, when said one or multiple programs are performed by the device so that should
Device：Obtain the first image of the face-image comprising target user；It is selected based on the first image from the image library collected in advance
It selects the second image, generates the second image collection, wherein, the second image includes the face-image of target user and at least one other
The face-image of user；For each other users, the face-image comprising the other users in the second image collection is determined
The quantity of second image；Total quantity and the identified face for including the other users based on the second image in the second image collection
The quantity of second image of portion's image, generation target user and the related information of the other users.
The preferred embodiment and the explanation to institute's application technology principle that above description is only the application.People in the art
Member should be appreciated that invention scope involved in the application, however it is not limited to the technology that the particular combination of above-mentioned technical characteristic forms
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
The other technical solutions for being combined and being formed.Such as features described above has similar work(with (but not limited to) disclosed herein
The technical solution that the technical characteristic of energy is replaced mutually and formed.
Claims (10)
1. a kind of method for generating information, including：
Obtain the first image of the face-image comprising target user；
Second image is selected from the image library collected in advance based on described first image, generates the second image collection, wherein, the
Two images include the face-image of the target user and the face-image of at least one other user；
For each other users, determine to include the second image of the face-image of the other users in second image collection
Quantity；Total quantity and the identified face figure comprising the other users based on the second image in second image collection
The quantity of second image of picture generates the related information of the target user and the other users.
It is 2. described to be selected based on described first image from the image library collected in advance according to the method described in claim 1, wherein
The second image is selected, generates the second image collection, including：
The facial characteristics generation first eigenvector of the target user is extracted from described first image；
For every image in described image storehouse, extracted from the image each user facial characteristics generate second feature to
Amount calculates the vectorial similarity with the first eigenvector of each second feature, in response to exist with the fisrt feature to
The similarity of amount is more than or equal to the second feature vector of similarity threshold and is less than with the similarity of the first eigenvector
The second feature vector of similarity threshold, is determined as the second image by the image；
Second image collection is generated based on the second definite image.
3. according to the method described in claim 2, wherein, second image for determining the face-image comprising the other users
Quantity, including：
The second feature vector by the facial characteristics generation of the other users is selected from second feature vector as with reference to feature
Vector；
For every second image in second image collection, in response in the face by each user in second image
Exist in the second feature vector of portion's feature generation and be more than or equal to the similarity threshold with the similarity of the reference feature vector
Second image is determined as the second image of the face-image comprising the other users by the second feature vector of value；
Face figure comprising the other users is determined based on the second image of the identified face-image comprising the other users
The quantity of second image of picture.
4. according to the method described in claim 1, wherein, the method further includes：
For each other users, it is more than or equal in advance in response to the quantity of the second image of the face-image comprising the other users
If amount threshold, which is determined as to the highlights correlations user of the target user；
Push the related information of the target user and identified highlights correlations user.
5. it is a kind of for generating the device of information, including：
Image acquisition unit is configured to obtain the first image of the face-image comprising target user；
Image selection unit is configured to select the second image from the image library collected in advance based on described first image, raw
Into the second image collection, wherein, the second image includes the face-image of the target user and the face of at least one other user
Portion's image；
Information generating unit is configured to for each other users, is determined in second image collection comprising other use
The quantity of second image of the face-image at family；Based on the total quantity of the second image in second image collection and identified
The quantity of second image of the face-image comprising the other users, generate the target user and the other users associates letter
Breath.
6. device according to claim 5, wherein, described image selecting unit includes：
Extraction module, be configured to extract from described first image the target user facial characteristics generate fisrt feature to
Amount；
Determining module is configured to, for every image in described image storehouse, extract the face of each user from the image
Feature generation second feature vector, calculates the vectorial similarity with the first eigenvector of each second feature, in response to depositing
Be more than or equal to the similarity of the first eigenvector second feature vector of similarity threshold and with it is described first special
The similarity of sign vector is less than the second feature vector of similarity threshold, which is determined as the second image；
Generation module is configured to generate the second image collection based on the second definite image.
7. device according to claim 6, wherein, second image for determining the face-image comprising the other users
Quantity, including：
The second feature vector by the facial characteristics generation of the other users is selected from second feature vector as with reference to feature
Vector；
For every second image in second image collection, in response in the face by each user in second image
Exist in the second feature vector of portion's feature generation and be more than or equal to the similarity threshold with the similarity of the reference feature vector
Second image is determined as the second image of the face-image comprising the other users by the second feature vector of value；
Face figure comprising the other users is determined based on the second image of the identified face-image comprising the other users
The quantity of second image of picture.
8. device according to claim 5, wherein, described device further includes：
User's determination unit is configured to for each other users, in response to of the face-image comprising the other users
The quantity of two images is more than or equal to default amount threshold, and the highlights correlations which is determined as to the target user are used
Family；
Push unit is configured to push the related information of the target user and identified highlights correlations user.
9. a kind of server, including：
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are performed by one or more of processors so that one or more of processors are real
The now method as described in any in claim 1-4.
10. a kind of computer readable storage medium, is stored thereon with computer program, wherein, described 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 |
|---|---|---|---|
| CN201810007800.4A CN108073724A (en) | 2018-01-04 | 2018-01-04 | For generating the method and apparatus of information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810007800.4A CN108073724A (en) | 2018-01-04 | 2018-01-04 | For generating the method and apparatus of information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108073724A true CN108073724A (en) | 2018-05-25 |
Family
ID=62156386
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810007800.4A Pending CN108073724A (en) | 2018-01-04 | 2018-01-04 | For generating the method and apparatus of information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108073724A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013161416A (en) * | 2012-02-08 | 2013-08-19 | Sony Corp | Server, client terminal, system and program |
| CN104850600A (en) * | 2015-04-29 | 2015-08-19 | 百度在线网络技术（北京）有限公司 | Method and device for searching images containing faces |
| CN106250439A (en) * | 2016-07-26 | 2016-12-21 | 四川长虹电器股份有限公司 | Cohesion display systems and method between photo personage |
| CN106777030A (en) * | 2016-12-08 | 2017-05-31 | 北京小米移动软件有限公司 | Information-pushing method and device |
| US20170228453A1 (en) * | 2016-02-04 | 2017-08-10 | Adobe Systems Incorporated | Photograph organization based on facial recognition |
-
2018
- 2018-01-04 CN CN201810007800.4A patent/CN108073724A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013161416A (en) * | 2012-02-08 | 2013-08-19 | Sony Corp | Server, client terminal, system and program |
| CN104850600A (en) * | 2015-04-29 | 2015-08-19 | 百度在线网络技术（北京）有限公司 | Method and device for searching images containing faces |
| US20170228453A1 (en) * | 2016-02-04 | 2017-08-10 | Adobe Systems Incorporated | Photograph organization based on facial recognition |
| CN106250439A (en) * | 2016-07-26 | 2016-12-21 | 四川长虹电器股份有限公司 | Cohesion display systems and method between photo personage |
| CN106777030A (en) * | 2016-12-08 | 2017-05-31 | 北京小米移动软件有限公司 | Information-pushing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108446390A (en) | Method and apparatus for pushed information | |
| CN108171207A (en) | Face identification method and device based on video sequence | |
| CN109214343A (en) | Method and apparatus for generating face critical point detection model | |
| CN107908789A (en) | Method and apparatus for generating information | |
| CN109308490A (en) | Method and apparatus for generating information | |
| CN109446990A (en) | Method and apparatus for generating information | |
| EP3893125A1 (en) | Method and apparatus for searching video segment, device, medium and computer program product | |
| CN110198432A (en) | Processing method, device, computer-readable medium and the electronic equipment of video data | |
| CN108416323A (en) | The method and apparatus of face for identification | |
| CN109086719A (en) | Method and apparatus for output data | |
| CN109376267A (en) | Method and apparatus for generating model | |
| CN109977839A (en) | Information processing method and device | |
| CN109871834A (en) | Information processing method and device | |
| CN109145828A (en) | Method and apparatus for generating video classification detection model | |
| CN108062416A (en) | For generating the method and apparatus of label on map | |
| CN109919003A (en) | Face identification method, terminal device and computer readable storage medium | |
| CN109902644A (en) | Face identification method, device, equipment and computer-readable medium | |
| CN108549848A (en) | Method and apparatus for output information | |
| CN108171208A (en) | Information acquisition method and device | |
| CN109241921A (en) | Method and apparatus for detecting face key point | |
| CN110298716A (en) | Information-pushing method and device | |
| CN108334498A (en) | Method and apparatus for handling voice request | |
| CN108133197A (en) | For generating the method and apparatus of information | |
| CN108600250A (en) | Authentication method | |
| CN108446659A (en) | Method and apparatus for detecting facial image |
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: 20180525 |