CN105279496B - A kind of method and apparatus of recognition of face - Google Patents
A kind of method and apparatus of recognition of face Download PDFInfo
- Publication number
- CN105279496B CN105279496B CN201510703783.4A CN201510703783A CN105279496B CN 105279496 B CN105279496 B CN 105279496B CN 201510703783 A CN201510703783 A CN 201510703783A CN 105279496 B CN105279496 B CN 105279496B
- Authority
- CN
- China
- Prior art keywords
- information
- face characteristic
- characteristic information
- face
- user equipment
- 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.)
- Active
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
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- 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
Abstract
The present invention provides a kind of method and apparatus of recognition of face, this method comprises: obtaining the first face characteristic information of headend equipment collected first user equipment information and facial image；Incidence relation between maintenance second user facility information and the second face characteristic information in advance；From searching in second user facility information and acquiring multiple matched information of first user equipment information in the first face characteristic information period, associated second face characteristic information of multiple first user equipment informations is found；Corresponding second face characteristic information of the first face characteristic information is filtered out from associated second face characteristic information of multiple first user equipment informations, determines face recognition result.According to the technical solution of the present invention, management server is not to be based only on the face characteristic information of the collected facial image of headend equipment, determines face recognition result, is not entirely dependent on the face characteristic information of facial image, so as to promote face recognition accuracy rate, the reliability of recognition of face is promoted.
Description
Technical field
The present invention relates to video technique field more particularly to a kind of method and apparatus of recognition of face.
Background technique
In recent years, with computer, network and image procossing, the rapid development of transmission technology, video monitoring is popularized
Change trend is more and more obvious, and video monitoring gradually marches toward high Qinghua, and intelligent, video monitoring system can be applied to numerous
Field, such as intelligent transportation, wisdom garden, safe city etc..
With the fast development of computer image recognition technology, in video monitoring system, face recognition technology has more
More application demands, such as the face snap of entrance, face attendance, personnel deploy to ensure effective monitoring and control of illegal activities, and face provides face characteristic abundant
Information can play an important role in personnel's identification process.
In current face recognition technology, recognition of face can be carried out based on the video image comprising face.Specifically,
It extracts face characteristic information from the video image comprising face, and will be stored in the face characteristic information of extraction and face database
Face characteristic information is compared one by one, obtains the sequencing of similarity of face, and it is highest to select from face database similarity
Face is exported as recognition result.
Aforesaid way places one's entire reliance upon the face characteristic information of video image, and video image is very high to environmental requirement, by
Light, angle influence, poor anti jamming capability, and knowledge rate is leaked in recognition of face and False Rate is high, or even whether cannot be distinguished is true people
The face inverted image on facial image, glass door on face, such as clothes.
Summary of the invention
The present invention provides a kind of method of recognition of face, is applied in management server, the described method comprises the following steps:
Obtain the first face characteristic information of headend equipment collected first user equipment information and facial image；Maintenance second in advance
Incidence relation between user equipment information and the second face characteristic information；It is searched from second user facility information and acquisition the
Multiple matched information of first user equipment information in one face characteristic information period, find multiple first user equipment informations
Associated second face characteristic information；It is sieved from associated second face characteristic information of multiple first user equipment informations
Corresponding second face characteristic information of first face characteristic information is selected, determines face recognition result.
It is described to be used from lookup in second user facility information and multiple first in the first face characteristic information period of acquisition
The matched information of family facility information, it is described before finding associated second face characteristic information of multiple first user equipment informations
Method further include: judge in the second all face characteristic informations with the presence or absence of the similarity between the first face characteristic information
Meet the second face characteristic information of preset requirement；If so, the similarity between the first face characteristic information is met pre-
If it is required that the second face characteristic information as face recognition result；It is searched from second user facility information if not, executing
Multiple matched information of first user equipment information in the first face characteristic information period of acquisition, find multiple first users
The process of associated second face characteristic information of facility information.
It is described that described is filtered out from associated second face characteristic information of multiple first user equipment informations
Corresponding second face characteristic information of one face characteristic information, determines the process of face recognition result, specifically includes: by described
One face characteristic information is compared with associated each second face characteristic information of multiple first user equipment informations,
It obtains associated each second face characteristic information of multiple first user equipment informations and first face characteristic is believed
The similarity of breath；Highest second face characteristic information of similarity is selected, as face recognition result.
The second user facility information includes following one or any combination: body-worn information, the sequence of mobile terminal
Row number, the MAC Address of mobile terminal, the number of mobile terminal, SIM card sequence number；First user equipment information includes
Content is identical as the content that the second user facility information includes.
The present invention provides a kind of device of recognition of face, is applied in management server, described device specifically includes: obtaining
Module for obtaining collected first user equipment information of headend equipment, and obtains the collected face of the headend equipment
First face characteristic information corresponding to image；Maintenance module, for safeguarding second user facility information and the second face in advance
Incidence relation between characteristic information；Enquiry module, it is special with the first face of acquisition for being searched from second user facility information
Multiple matched information of first user equipment information in info period are levied, multiple first user equipment informations associated the are found
Two face characteristic informations；Determining module, for believing from associated second face characteristic of multiple first user equipment informations
Corresponding second face characteristic information of first face characteristic information is filtered out in breath, determines face recognition result.
The enquiry module is also used to when being searched from second user facility information with the first face characteristic information of acquisition
It is special to find associated second face of multiple first user equipment informations for multiple matched information of first user equipment information in section
Before reference breath, judge in the second all face characteristic informations with the presence or absence of the phase between first face characteristic information
Meet the second face characteristic information of preset requirement like degree；It searches and adopts from second user facility information if it is not, then executing
Collect multiple matched information of first user equipment information in the first face characteristic information period, finds multiple first user equipmenies
The process of second face characteristic information of information association；The determining module is also used to when query result, which is, is, then will be with institute
It states the similarity between the first face characteristic information and meets the second face characteristic information of preset requirement as face recognition result.
The determining module, specifically for from associated second face characteristic of multiple first user equipment informations
Corresponding second face characteristic information of first face characteristic information is filtered out in information, determines the process of face recognition result
In, associated each second face characteristic of first face characteristic information and multiple first user equipment informations is believed
Breath is compared, and obtains associated each second face characteristic information of multiple first user equipment informations and described first
The similarity of face characteristic information；Highest second face characteristic information of similarity is selected, as face recognition result.
The second user facility information includes following one or any combination: body-worn information, the sequence of mobile terminal
Row number, the MAC Address of mobile terminal, the number of mobile terminal, SIM card sequence number；First user equipment information includes
Content is identical as the content that the second user facility information includes.
Based on the above-mentioned technical proposal, in the embodiment of the present invention, the collected user equipment information of headend equipment can be based on
With the face characteristic information of facial image, face recognition result is determined, rather than be based only on the collected face figure of headend equipment
The face characteristic information of picture, determines face recognition result, is not entirely dependent on the face characteristic information of facial image, to pass through
Various dimensions information determines face recognition result, promotes face recognition accuracy rate, reduces face leakage discrimination and False Rate, promotes people
The reliability of face identification.
Detailed description of the invention
Fig. 1 is the flow chart of the method for the recognition of face in one embodiment of the present invention；
Fig. 2 is the flow chart of the method for the recognition of face in another embodiment of the present invention；
Fig. 3 is the hardware structure diagram of the management server in one embodiment of the present invention；
Fig. 4 is the structure chart of the device of the recognition of face in one embodiment of the present invention.
Specific embodiment
Aiming at the problems existing in the prior art, a kind of method that recognition of face is proposed in the embodiment of the present invention, this method
It can apply in the management server (such as VM (Video Management, video management) server) of video monitoring system,
As shown in Figure 1, the method for the recognition of face may comprise steps of:
Step 101, the first face characteristic of headend equipment collected first user equipment information and facial image is obtained
Information.Wherein, headend equipment can collect the first user equipment information and facial image, by the first user equipment information and face
Image is sent to management server.Management server is obtained front end and is set based on the first user equipment information from headend equipment
Standby collected first user equipment information.Management server obtains facial image based on the facial image from headend equipment
Corresponding first face characteristic information, the first face of the collected facial image of first face characteristic information, that is, headend equipment
Characteristic information.
Step 102, the incidence relation between second user facility information and the second face characteristic information is safeguarded in advance.
Wherein, the incidence relation between second user facility information and the second face characteristic information can specifically include: the
Pair between corresponding relationship and the second face characteristic information and personal information between two user equipment informations and personal information
It should be related to；In advance maintenance second user facility information and personal information between corresponding relationship, the second face characteristic information with
During corresponding relationship between personal information, second user facility information and personal information can be obtained, and tie up in advance
The corresponding relationship between second user facility information and the personal information currently obtained is stored in the facility information library of shield；Obtain people
The second face characteristic information and personal information of face image, and the second face characteristic is stored in the characteristic information library safeguarded in advance
Corresponding relationship between information and the personal information currently obtained.Alternatively, obtain second user facility information, facial image the
Two face characteristic informations and personal information, and second user facility information, second are stored in the characteristic information library safeguarded in advance
Corresponding relationship between face characteristic information and the personal information currently obtained.
Step 103, (headend equipment is adopted with the first face characteristic information period of acquisition for lookup from second user facility information
Collect the time interval of facial image) in multiple matched information of first user equipment information (i.e. second user equipment believe
Breath), finding associated second face characteristic information of multiple first user equipment informations, (multiple first user equipment informations are corresponding
Multiple associated second face characteristic informations of second user facility information).
Step 104, the first face is filtered out from associated second face characteristic information of multiple first user equipment informations
Corresponding second face characteristic information of characteristic information, determines face recognition result.Wherein, which is that front end is set
The standby corresponding face of collected facial image, and exportable corresponding personal information.
In the embodiment of the present invention, out of lookup in second user facility information with the first face characteristic information period of acquisition
Multiple matched information of first user equipment information, find multiple first user equipment informations associated second face characteristic letter
Before breath, can also judging the second all face characteristic informations, (the second all faces stored in characteristic information library are special
Reference breath, can include corresponding second face characteristic information of the first user equipment information) in, if exist and the first face spy
Similarity between reference breath meets the second face characteristic information of preset requirement；If it is, can directly by with it is the first
Similarity between face characteristic information meets the second face characteristic information of preset requirement as face recognition result；If not,
It then executes from multiple first user equipmenies searched in second user facility information and in the first face characteristic information period of acquisition
The information of information matches finds the process of associated second face characteristic information of multiple first user equipment informations.
In the embodiment of the present invention, from lookup in second user facility information and acquire in the first face characteristic information period
Multiple matched information of first user equipment information (i.e. second user facility information) are found multiple first user equipment informations and are closed
The process of second face characteristic information of connection, can specifically include but be not limited to such as under type: utilize the first face characteristic of acquisition
Multiple first user equipment informations in info period are inquired between the second user facility information safeguarded in advance and personal information
Corresponding relationship, find from second user facility information and set with this multiple matched second user of first user equipment information
Standby information, and obtain these corresponding personal informations of second user facility information；Dimension in advance is inquired using obtained personal information
Corresponding relationship between the second face characteristic information and personal information of shield, obtains corresponding multiple second face characteristic informations,
And the second obtained face characteristic information is associated second face characteristic information of multiple first user equipment informations.
In the embodiment of the present invention, the time interval of facial image is collected in headend equipment, headend equipment collects multiple
First user equipment information, and multiple first user equipment informations correspond to multiple second face characteristic informations.Based on this, from multiple
Corresponding second face of the first face characteristic information is filtered out in associated second face characteristic information of first user equipment information
Characteristic information determines the process of face recognition result, can specifically include but is not limited to such as under type: the first face characteristic is believed
It is special each of to cease associated by multiple first user equipment informations corresponding with the time interval for collecting facial image the second face
Reference breath is compared, and obtains this multiple associated each second face characteristic information of first user equipment information and the first face
The similarity of characteristic information；Highest second face characteristic information of similarity is selected, as face recognition result.
In the above process of the embodiment of the present invention, second user facility information can specifically include but be not limited to following one
Or any combination: body-worn information (such as bluetooth bracelet information, bluetooth headset information), the sequence number of mobile terminal, shifting
MAC (Media Access Control, media access control) address, the number of mobile terminal, SIM of dynamic terminal
(Subscriber Identity Module, client identification module) card sequence number etc.；First user equipment information includes interior
Hold identical as the content that second user facility information includes.
For example, when second user facility information is body-worn information (such as bluetooth bracelet information, bluetooth headset information)
When, then collected first user equipment information of headend equipment is that body-worn information (believe by such as bluetooth bracelet information, bluetooth headset
Breath etc.).When second user facility information is the MAC Address of mobile terminal, then collected first user equipment of headend equipment
When information is the MAC Address of mobile terminal.
Certainly, in practical applications, the first user equipment information and second user facility information are not limited to above-mentioned
User equipment information, for other user equipment informations, details are not described herein.
Based on the above-mentioned technical proposal, in the embodiment of the present invention, the collected user equipment information of headend equipment can be based on
With the face characteristic information of facial image, face recognition result is determined, rather than be based only on the collected face figure of headend equipment
The face characteristic information of picture, determines face recognition result, is not entirely dependent on the face characteristic information of facial image, to pass through
Various dimensions information determines face recognition result, promotes face recognition accuracy rate, reduces face leakage discrimination and False Rate, promotes people
The reliability of face identification.
Below in conjunction with specific embodiment, the above process is further detailed.
A kind of method that recognition of face is proposed in the embodiment of the present invention, this method can be applied in video monitoring system,
The video monitoring system at least may include headend equipment (such as video camera) and management server (such as VM server), such as Fig. 2 institute
Show, the method for the recognition of face can specifically include following steps:
Step 201, management server obtains second user facility information and personal information, and in the equipment letter safeguarded in advance
The corresponding relationship between the second user facility information and the personal information is stored in breath library.
Wherein, second user facility information includes but is not limited to following one or any combination: the body-worn of personnel
Information (such as bluetooth bracelet information, bluetooth headset information), personnel information of mobile terminal (sequence number of such as mobile terminal moves
The dynamic MAC Address of terminal, the number of mobile terminal, SIM card sequence number etc.).
Wherein, management server can store the body-worn information of personnel, personnel in the same facility information library
Corresponding relationship between information of mobile terminal and personal information, for example, storing the body-worn letter of personnel in facility information library 1
It ceases, the corresponding relationship between the information of mobile terminal and personal information of personnel.Management server can also be believed in different equipment
The information of mobile terminal of corresponding relationship, personnel in breath library between the body-worn information and personal information of storage personnel and personnel
Corresponding relationship between information, for example, between the body-worn information and personal information for storing personnel in facility information library 1
Corresponding relationship, the corresponding relationship between the information of mobile terminal and personal information for storing personnel in facility information library 2.
Step 202, management server obtains the second face characteristic information and personal information of facial image, and ties up in advance
The corresponding relationship between second face characteristic information and the personal information is stored in the characteristic information library of shield.Wherein, the face
Image can specifically refer to the video image comprising face.
Wherein, it may include the facial image in the second face characteristic information, can also include the other information of face, such as
The distance between two, the distance between eyebrow, shape of face feature etc. repeats no more this.
Under concrete application scene, second user facility information, the second face characteristic letter can be obtained using corresponding manner
Breath and personal information.For example, being directed to certain garden, personnel in garden can be required to provide itself personal information (such as name, identity
Card, gender, age etc.) and second user facility information, and acquire the facial image of the personnel (this acquisition is in alignment with personnel's
Acquisition, clarity, accuracy are very high).
For step 201 and step 202, management server is to store respectively in characteristic information library and facility information library
Corresponding relationship, second user facility information between two face characteristic informations and personal information and the corresponding pass between personal information
System, in practical applications, management server storage second user can also set in the same information bank (such as characteristic information library)
Standby corresponding relationship between information, the second face characteristic information and the personal information currently obtained, the process is herein no longer in detail
It repeats.
Step 203, management server obtains the of collected first user equipment information of headend equipment and facial image
One face characteristic information.Wherein, headend equipment can collect the first user equipment information and facial image, and this first is used
Family facility information and the facial image are sent to management server.Further, management server can be based on setting from front end
The first standby user equipment information obtains collected first user equipment information of headend equipment.Management server can be with base
In the facial image from headend equipment, corresponding first face characteristic information of the facial image, and first face are obtained
Characteristic information is corresponding first face characteristic information of the collected facial image of headend equipment.
In the embodiment of the present invention, in order to distinguish conveniently, the face characteristic information stored in characteristic information library is known as the
The corresponding face characteristic information of the collected facial image of headend equipment is known as the first face characteristic letter by two face characteristic informations
Breath.The user equipment information stored in facility information library is known as second user facility information, headend equipment is collected
User equipment information is known as the first user equipment information.
Wherein, by being mounted on the imaging sensor of the headend equipment (such as video camera) of the specific region of crucial entrance,
Facial image can be captured, and the facial image is sent to management server by headend equipment, before being obtained by management server
First face characteristic information of the collected facial image of end equipment.
Wherein, by being mounted on the sensing detecting module of the headend equipment (such as video camera) of the specific region of crucial entrance
(may be mounted on headend equipment, such as WIFI (Wireless Fidelity, Wireless Fidelity) wireless module, bluetooth module etc.),
The first user equipment information can be collected, and first user equipment information is sent to management server by headend equipment, by
Management server obtains collected first user equipment information of headend equipment, and the first user equipment information content for including with
The content that second user facility information includes is identical.For example, when second user facility information is body-worn information (such as bluetooth hand
Ring information, bluetooth headset information etc.) when, then collected first user equipment information of headend equipment be body-worn information (such as
Bluetooth bracelet information, bluetooth headset information etc.).When second user facility information is the MAC Address of mobile terminal, then front end is set
When standby collected first user equipment information is the MAC Address of mobile terminal.Certainly, in practical applications, the first user sets
Standby information and second user facility information are not limited to above-mentioned user equipment information, for other user equipment informations,
This is repeated no more.
Wherein, due to be located at the same area user may be it is multiple, at each acquisition moment, headend equipment acquisition
To the first user equipment information may each be multiple first user equipment informations.
Wherein, headend equipment is when sending collected facial image to management server, also by the acquisition of facial image
Moment is sent to management server, by the first face characteristic information and pair at acquisition moment of record management server facial image
It should be related to.Headend equipment, can also be by the first user when sending collected first user equipment information to management server
The acquisition moment of facility information is sent to management server, by the first user equipment information of record management server and acquisition moment
Corresponding relationship.
Wherein, for acquiring the first user equipment information by the WIFI wireless module of headend equipment, WIFI is wireless mould
Transmission Beacon (detection) message of block period is then moved when mobile terminal is located at the investigative range of WIFI wireless module
Terminal can be obtained to WIFI wireless module returning response message, WIFI wireless module from the response message that mobile terminal returns
The first user equipment information is obtained, and obtains the acquisition moment of the first user equipment information.Alternatively, mobile terminal active period is sent out
The probe requests message is sent, when mobile terminal is located at the investigative range of WIFI wireless module, then the detection that mobile terminal is sent is asked
Ask message that can be received by WIFI wireless module, WIFI wireless module can be obtained from from the probe requests message of mobile terminal
The first user equipment information is obtained, and obtains the acquisition moment of the first user equipment information.
Wherein, when headend equipment sends collected first user equipment information to management server, settable
In period T, headend equipment only sends first user equipment information to management server.
Step 204, management server is searched and the first face characteristic information period of acquisition from second user facility information
Multiple matched information of first user equipment information in (i.e. headend equipment collect facial image time interval), find more
A associated second face characteristic information of first user equipment information (use by multiple first user equipment informations corresponding multiple second
Associated second face characteristic information of family facility information).
In the embodiment of the present invention, management server is searched and acquisition the first face characteristic letter from second user facility information
Multiple matched information of first user equipment information (i.e. second user facility information) in the period are ceased, multiple first users are found
The process of associated second face characteristic information of facility information, can specifically include but be not limited to such as under type: management server
It is set using the second user that multiple first user equipment informations inquiry in the first face characteristic information period of acquisition is safeguarded in advance
Corresponding relationship between standby information and personal information, management server found from second user facility information with this multiple the
The matched second user facility information of one user equipment information, and obtain the corresponding personnel's letter of these second user facility informations
Breath；Management server is using between obtained personal information inquiry the second face characteristic information safeguarded in advance and personal information
Corresponding relationship obtains corresponding multiple second face characteristic informations, and the second face characteristic information that management server obtains is
Multiple associated second face characteristic informations of first user equipment information.
Step 205, management server is screened from associated second face characteristic information of multiple first user equipment informations
Corresponding second face characteristic information of first face characteristic information out, determines face recognition result.Wherein, the face recognition result
As the corresponding face of the collected facial image of headend equipment, management server may be used also after obtaining face recognition result
To export the corresponding personal information of face recognition result.
Wherein, the time interval of facial image is collected in headend equipment, headend equipment collects multiple first users and sets
Standby information, management server inquire the second user facility information safeguarded in advance and personnel using multiple first user equipment informations
Corresponding relationship between information is obtained multiple personal informations, and is inquired the second face safeguarded in advance using multiple personal informations
Corresponding relationship between characteristic information and personal information obtains multiple second face characteristic informations, i.e., multiple first user equipmenies
Information corresponds to multiple second face characteristic informations.
Based on this, in the embodiment of the present invention, management server is from associated second face of multiple first user equipment informations
Corresponding second face characteristic information of the first face characteristic information is filtered out in characteristic information (multiple second face characteristic informations),
The process for determining face recognition result can specifically include but be not limited to such as under type: management server is by the first face characteristic
Second face each of associated by information multiple first user equipment informations corresponding with the time interval for collecting facial image
Characteristic information is compared, obtain this multiple associated each second face characteristic information of first user equipment information with it is the first
The similarity of face characteristic information；Management server selects highest second face characteristic information of similarity, as recognition of face knot
Fruit.
Wherein, management server determines the facial image after the first face characteristic information for obtaining facial image
Acquire the moment, it is contemplated that the influence of the factors such as error can also determine the time interval for collecting facial image (i.e. comprising face
The time interval at the acquisition moment of image), moreover, management server can determine in the time interval for collecting facial image
Multiple first user equipment informations out.
In the embodiment of the present invention, management server is being searched and the first face characteristic of acquisition from second user facility information
Multiple matched information of first user equipment information in info period, find multiple first user equipment informations associated second
Before face characteristic information, management server can also judge that the second all face characteristic informations (is deposited in characteristic information library
The second all face characteristic informations of storage, can include corresponding second face characteristic information of the first user equipment information) in,
Meet the second face characteristic information of preset requirement with the presence or absence of the similarity between the first face characteristic information.If so,
The second face that then similarity between the first face characteristic information directly can be met preset requirement by management server is special
Reference breath is used as face recognition result, no longer execution above-mentioned steps 204 and step 205.If it is not, then management server execute from
It searches in second user facility information and is matched with multiple first user equipment informations in the first face characteristic information period of acquisition
Information, find the process of associated second face characteristic information of multiple first user equipment informations.
Based on aforesaid way, in the embodiment of the present invention, management server is first to judge the second all face characteristic informations
In, if there is the second face characteristic information that the similarity between the first face characteristic information meets preset requirement.Work as view
First face characteristic information of frequency image than it is more visible when, then the second all face characteristic informations can exist and the first face is special
Similarity between reference breath meets the second face characteristic information of preset requirement, in this way can directly by with the first face characteristic
Similarity between information meets the second face characteristic information of preset requirement as face recognition result, to accurately obtain people
Face recognition result.For example, when obtaining clearly the first face characteristic information 1, even if the first user equipment information corresponding
Two face characteristic informations are the second face characteristic information 1, the second face characteristic information 2, the second face characteristic information 3, then manage
Server is also first to judge the second all face characteristic informations (such as second the second face characteristic information of face characteristic information 1-
1000) in, if there is the second face characteristic letter that the similarity between the first face characteristic information 1 meets preset requirement
Breath, it is assumed that the similarity between the second face characteristic information 100 and the first face characteristic information meets preset requirement, then by second
Face characteristic information 100 is used as face recognition result, which can be an accurate face recognition result, this
When, management server is not needed from the second face characteristic information 1, the second face characteristic information 2, the second face characteristic information 3
Select the corresponding face recognition result of the first face characteristic information 1, it can obtain accurate face recognition result.
Wherein, management server, can also be to the face figure after the first face characteristic information for obtaining facial image
As being analyzed, to detect whether the facial image meets recognition of face requirement, as whether the light of facial image conforms to
Ask, whether angle meets the requirements, whether two eye distances from meeting the requirements, the inspection of Adaboost classifier can be used in management server
Survey whether facial image meets recognition of face requirement, specific detection process no longer repeats in detail.If facial image is unsatisfactory for
Recognition of face requirement, then the first face characteristic information is compared management server with each second face characteristic information, obtains
To the similarity of each second face characteristic information and the first face characteristic information, and select highest second face of similarity special
Reference breath, as face recognition result.Alternatively, management server is known directly by each second face characteristic information as face
Not as a result, having multiple face recognition results at this time.In management server by the first face characteristic information and each second face
When characteristic information is compared, it is possible to reduce the characteristic point quantity of comparison, for example, being needed when normal face characteristic information compares
100 characteristic points are wanted, when facial image is unsatisfactory for recognition of face requirement, when face characteristic information compares, only use 20
Characteristic point.
In a kind of concrete application, if facial image meets recognition of face requirement, management server is by the first face
All second face characteristic informations (such as second the second face characteristic of face characteristic information 1- in characteristic information and characteristic information library
Information 1000) it is compared, obtain the second face characteristic information of each of characteristic information library and the first face characteristic information
Similarity, if there is similarity be more than given threshold (illustrate corresponding second face characteristic information of the similarity be with it is the first
Similarity between face characteristic information meets the second face characteristic information of preset requirement), then select similarity highest second
Face characteristic information, as face recognition result, no longer execution above-mentioned steps 204 and step 205；If being more than without similarity
Given threshold, then (such as by the first face characteristic information each second face characteristic information corresponding with the first user equipment information
Second face characteristic information 1, the second face characteristic information 2, the second face characteristic information 3) it is compared, it obtains the first user and sets
The similarity of standby information corresponding each second face characteristic information and the first face characteristic information, and select similarity highest
Second face characteristic information, as face recognition result.
Wherein, it is compared by two face characteristic informations, it, can be with when obtaining the similarity of two face characteristic informations
It is handled using similarity algorithm, for example, similarity algorithm can be with perceptual hash algorithm, SIM (Structural
SIMilarity, structural similarity) algorithm etc., it no longer repeats in detail herein.
Based on the above-mentioned technical proposal, in the embodiment of the present invention, the collected user equipment information of headend equipment can be based on
With the face characteristic information of facial image, face recognition result is determined, rather than be based only on the collected face figure of headend equipment
The face characteristic information of picture, determines face recognition result, is not entirely dependent on the face characteristic information of facial image, to pass through
Various dimensions information determines face recognition result, promotes face recognition accuracy rate, reduces face leakage discrimination and False Rate, promotes people
The reliability of face identification.
Based on inventive concept same as the above method, a kind of dress of recognition of face is additionally provided in the embodiment of the present invention
It sets, the device application of the recognition of face is on the management server.Wherein, the device of the recognition of face can by software realization,
It can also be realized by way of hardware or software and hardware combining.Taking software implementation as an example, as the dress on a logical meaning
It sets, is to be read computer program instructions corresponding in nonvolatile memory by the processor of the management server where it
Get what operation in memory was formed.For hardware view, as shown in figure 3, for the device institute of recognition of face proposed by the present invention
Management server a kind of hardware structure diagram, in addition to processor shown in Fig. 3, network interface, memory and non-volatile
Outside memory, management server can also include other hardware, such as be responsible for the forwarding chip of processing message；From hardware configuration
For, which is also possible to be distributed apparatus, may include multiple interface cards, to carry out message in hardware view
The extension of processing.
As shown in figure 4, the structure chart of the device for recognition of face proposed by the present invention, described device specifically include: obtaining
Module 11 for obtaining collected first user equipment information of headend equipment, and obtains the collected people of the headend equipment
First face characteristic information corresponding to face image；Maintenance module 12, for safeguarding second user facility information and second in advance
Incidence relation between face characteristic information；Enquiry module 13, for being searched from second user facility information and acquisition first
Multiple matched information of first user equipment information in the face characteristic information period find multiple first user equipment informations and close
Second face characteristic information of connection；Determining module 14, for from associated second people of multiple first user equipment informations
Corresponding second face characteristic information of first face characteristic information is filtered out in face characteristic information, determines recognition of face knot
Fruit.
The enquiry module 13 is also used to searching from second user facility information and the first face characteristic information of acquisition
Multiple matched information of first user equipment information in period, find associated second face of multiple first user equipment informations
Before characteristic information, judge in the second all face characteristic informations with the presence or absence of between first face characteristic information
Similarity meets the second face characteristic information of preset requirement；If it is not, then execute from second user facility information search with
Multiple matched information of first user equipment information in the first face characteristic information period are acquired, multiple first users is found and sets
The process of second face characteristic information of standby information association；The determining module 14 is also used to when query result, which is, is, will be with
Similarity between first face characteristic information meets the second face characteristic information of preset requirement as recognition of face knot
Fruit.
The determining module 14, specifically for special from associated second face of multiple first user equipment informations
Corresponding second face characteristic information of first face characteristic information is filtered out in reference breath, determines the mistake of face recognition result
Cheng Zhong, by first face characteristic information and associated each second face characteristic of multiple first user equipment informations
Information is compared, and obtains associated each second face characteristic information of multiple first user equipment informations and described the
The similarity of one face characteristic information；
Highest second face characteristic information of similarity is selected, as face recognition result.
In the embodiment of the present invention, the second user facility information includes following one or any combination: body-worn letter
Breath, the sequence number of mobile terminal, the MAC address of mobile terminal, the number of mobile terminal, client identification module
SIM card sequence number；The content phase that the content that first user equipment information includes includes with the second user facility information
Together.
Wherein, the modules of apparatus of the present invention can integrate in one, can also be deployed separately.Above-mentioned module can close
And be a module, multiple submodule can also be further split into.
Through the above description of the embodiments, those skilled in the art can be understood that the present invention can be by
Software adds the mode of required general hardware platform to realize, naturally it is also possible to which by hardware, but in many cases, the former is more
Good embodiment.Based on this understanding, technical solution of the present invention substantially in other words contributes to the prior art
Part can be embodied in the form of software products, which is stored in a storage medium, if including
Dry instruction is used so that a computer equipment (can be personal computer, server or the network equipment etc.) executes this hair
Method described in bright each embodiment.It will be appreciated by those skilled in the art that attached drawing is the schematic diagram of a preferred embodiment,
Module or process in attached drawing are not necessarily implemented necessary to the present invention.
It will be appreciated by those skilled in the art that the module in device in embodiment can describe be divided according to embodiment
It is distributed in the device of embodiment, corresponding change can also be carried out and be located in one or more devices different from the present embodiment.On
The module for stating embodiment can be merged into a module, can also be further split into multiple submodule.The embodiments of the present invention
Serial number is for illustration only, does not represent the advantages or disadvantages of the embodiments.
Disclosed above is only several specific embodiments of the invention, and still, the present invention is not limited to this, any ability
What the technical staff in domain can think variation should all fall into protection scope of the present invention.
Claims (8)
1. a kind of method of recognition of face is applied in management server, which is characterized in that the described method comprises the following steps:
Obtain the first face characteristic information of headend equipment collected first user equipment information and facial image；
Incidence relation between maintenance second user facility information and the second face characteristic information in advance；
Believe from being searched in second user facility information with multiple first user equipmenies in the first face characteristic information period of acquisition
Matched information is ceased, associated second face characteristic information of multiple first user equipment informations is found；
It is special that first face is filtered out from associated second face characteristic information of multiple first user equipment informations
Reference ceases corresponding second face characteristic information, determines face recognition result.
2. the method according to claim 1, wherein described search and acquisition the from second user facility information
Multiple matched information of first user equipment information in one face characteristic information period, find multiple first user equipment informations
Before associated second face characteristic information, the method also includes:
Judge to meet in advance in the second all face characteristic informations with the presence or absence of the similarity between the first face characteristic information
If it is required that the second face characteristic information；If so, the similarity between the first face characteristic information is met preset requirement
The second face characteristic information as face recognition result；It searches and acquires from second user facility information if not, executing
Multiple matched information of first user equipment information in first face characteristic information period find multiple first user equipment letters
Cease the process of associated second face characteristic information.
3. the method according to claim 1, wherein described be associated with from multiple first user equipment informations
The second face characteristic information in filter out corresponding second face characteristic information of first face characteristic information, determine face
The process of recognition result, specifically includes:
By first face characteristic information and associated each second face characteristic of multiple first user equipment informations
Information is compared, and obtains associated each second face characteristic information of multiple first user equipment informations and described the
The similarity of one face characteristic information；
Highest second face characteristic information of similarity is selected, as face recognition result.
4. method according to claim 1-3, which is characterized in that the second user facility information includes following
One of or any combination: body-worn information, the sequence number of mobile terminal, mobile terminal MAC address, move
Number, the client identification module SIM card sequence number of dynamic terminal；The content and described second that first user equipment information includes
The content that user equipment information includes is identical.
5. a kind of device of recognition of face is applied in management server, which is characterized in that described device specifically includes:
Module is obtained, for obtaining collected first user equipment information of headend equipment, and obtains the headend equipment acquisition
First face characteristic information corresponding to the facial image arrived；
Maintenance module, for safeguarding the incidence relation between second user facility information and the second face characteristic information in advance；
Enquiry module, for from being searched in second user facility information and multiple the in the first face characteristic information period of acquisition
The matched information of one user equipment information finds associated second face characteristic information of multiple first user equipment informations；
Determining module, for filtering out institute from associated second face characteristic information of multiple first user equipment informations
Corresponding second face characteristic information of the first face characteristic information is stated, determines face recognition result.
6. device according to claim 5, which is characterized in that
The enquiry module is also used to out of lookup in second user facility information with the first face characteristic information period of acquisition
Multiple matched information of first user equipment information, find multiple first user equipment informations associated second face characteristic letter
Before breath, judge in the second all face characteristic informations with the presence or absence of the similarity between first face characteristic information
Meet the second face characteristic information of preset requirement；It is searched from second user facility information and acquisition the if it is not, then executing
Multiple matched information of first user equipment information in one face characteristic information period, find multiple first user equipment informations
The process of associated second face characteristic information；
The determining module is also used to when query result, which is, is, then will be similar between first face characteristic information
Degree meets the second face characteristic information of preset requirement as face recognition result.
7. device according to claim 5, which is characterized in that
The determining module, specifically for from associated second face characteristic information of multiple first user equipment informations
In filter out corresponding second face characteristic information of first face characteristic information, during determining face recognition result,
By first face characteristic information and associated each second face characteristic information of multiple first user equipment informations
Be compared, obtain associated each second face characteristic information of multiple first user equipment informations with it is described the first
The similarity of face characteristic information；
Highest second face characteristic information of similarity is selected, as face recognition result.
8. according to any device of claim 5-7, which is characterized in that the second user facility information include it is following it
One or any combination: body-worn information, the sequence number of mobile terminal, the MAC address of mobile terminal, movement
Number, the client identification module SIM card sequence number of terminal；The content and described second that first user equipment information includes are used
The content that family facility information includes is identical.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510703783.4A CN105279496B (en) | 2015-10-26 | 2015-10-26 | A kind of method and apparatus of recognition of face |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510703783.4A CN105279496B (en) | 2015-10-26 | 2015-10-26 | A kind of method and apparatus of recognition of face |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105279496A CN105279496A (en) | 2016-01-27 |
| CN105279496B true CN105279496B (en) | 2019-10-18 |
Family
ID=55148480
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510703783.4A Active CN105279496B (en) | 2015-10-26 | 2015-10-26 | A kind of method and apparatus of recognition of face |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105279496B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105872979B (en) * | 2016-05-31 | 2019-11-26 | 王方松 | A kind of method and device obtaining crowd's information in setting place |
| CN106408013A (en) * | 2016-09-12 | 2017-02-15 | 湖南数据魔方信息科技有限公司 | Method for applying video-based human body characteristic identification technology in wireless positioning |
| CN106548148A (en) * | 2016-10-26 | 2017-03-29 | 北京意泰物联软件科技有限公司 | The recognition methodss of unknown face and system in video |
| CN108540760B (en) * | 2017-03-01 | 2021-02-26 | 中国电信股份有限公司 | Video monitoring identification method, device and system |
| CN109766736A (en) * | 2017-11-09 | 2019-05-17 | 中国电信股份有限公司 | Face identification method, device and system |
| CN108271069A (en) * | 2017-12-11 | 2018-07-10 | 北京奇艺世纪科技有限公司 | The segment filter method and device of a kind of video frequency program |
| CN109963113B (en) * | 2017-12-14 | 2021-06-22 | 浙江宇视科技有限公司 | Method and device for monitoring interested target |
| CN108228742B (en) * | 2017-12-15 | 2021-10-22 | 深圳市商汤科技有限公司 | Face duplicate checking method and device, electronic equipment, medium and program |
| CN110825765B (en) * | 2019-10-23 | 2022-10-04 | 中国建设银行股份有限公司 | Face recognition method and device |
| CN113158823B (en) * | 2021-03-30 | 2023-05-12 | 浙江大华技术股份有限公司 | Face recognition method and device |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102184391A (en) * | 2011-05-19 | 2011-09-14 | 汉王科技股份有限公司 | Distributed type face recognition method and system as well as face recognition terminal |
| CN102360421A (en) * | 2011-10-19 | 2012-02-22 | 苏州大学 | Face identification method and system based on video streaming |
| US8244002B2 (en) * | 2009-03-18 | 2012-08-14 | Industrial Technology Research Institute | System and method for performing rapid facial recognition |
| CN103824058A (en) * | 2014-02-26 | 2014-05-28 | 杨勇 | Face recognition system and method based on locally distributed linear embedding algorithm |
| CN103995818A (en) * | 2013-02-15 | 2014-08-20 | 三星电子株式会社 | Electronic device and object recognition method in electronic device |
| CN104318217A (en) * | 2014-10-28 | 2015-01-28 | 吴建忠 | Face recognition information analysis method and system based on distributed cloud computing |
| CN104765739A (en) * | 2014-01-06 | 2015-07-08 | 南京宜开数据分析技术有限公司 | Large-scale face database searching method based on shape space |
| CN105205457A (en) * | 2015-09-10 | 2015-12-30 | 上海卓易科技股份有限公司 | Information acquisition system and method based on face recognition |
| CN106611151A (en) * | 2015-10-23 | 2017-05-03 | 杭州海康威视数字技术股份有限公司 | A human face identification method and apparatus |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102073859A (en) * | 2011-02-14 | 2011-05-25 | 汉王科技股份有限公司 | Child picking and sending system on basis of face identification and control method thereof |
| JP5975293B2 (en) * | 2013-02-22 | 2016-08-23 | 富士ゼロックス株式会社 | Authentication apparatus and program |
| CN104021398A (en) * | 2014-06-16 | 2014-09-03 | 北京云视智通科技有限公司 | Wearable intelligent device and method for assisting identity recognition |
-
2015
- 2015-10-26 CN CN201510703783.4A patent/CN105279496B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8244002B2 (en) * | 2009-03-18 | 2012-08-14 | Industrial Technology Research Institute | System and method for performing rapid facial recognition |
| CN102184391A (en) * | 2011-05-19 | 2011-09-14 | 汉王科技股份有限公司 | Distributed type face recognition method and system as well as face recognition terminal |
| CN102360421A (en) * | 2011-10-19 | 2012-02-22 | 苏州大学 | Face identification method and system based on video streaming |
| CN102360421B (en) * | 2011-10-19 | 2014-05-28 | 苏州大学 | Face identification method and system based on video streaming |
| CN103995818A (en) * | 2013-02-15 | 2014-08-20 | 三星电子株式会社 | Electronic device and object recognition method in electronic device |
| CN104765739A (en) * | 2014-01-06 | 2015-07-08 | 南京宜开数据分析技术有限公司 | Large-scale face database searching method based on shape space |
| CN103824058A (en) * | 2014-02-26 | 2014-05-28 | 杨勇 | Face recognition system and method based on locally distributed linear embedding algorithm |
| CN104318217A (en) * | 2014-10-28 | 2015-01-28 | 吴建忠 | Face recognition information analysis method and system based on distributed cloud computing |
| CN105205457A (en) * | 2015-09-10 | 2015-12-30 | 上海卓易科技股份有限公司 | Information acquisition system and method based on face recognition |
| CN106611151A (en) * | 2015-10-23 | 2017-05-03 | 杭州海康威视数字技术股份有限公司 | A human face identification method and apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105279496A (en) | 2016-01-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105279496B (en) | A kind of method and apparatus of recognition of face | |
| KR102215041B1 (en) | Method and system for tracking an object in a defined area | |
| US9323979B2 (en) | Face recognition performance using additional image features | |
| CN107506684B (en) | Gait recognition method and device | |
| EP3100227B1 (en) | Detection of unauthorized devices on atms | |
| US20170345181A1 (en) | Video monitoring method and video monitoring system | |
| US9754630B2 (en) | System to distinguish between visually identical objects | |
| JP6516832B2 (en) | Image retrieval apparatus, system and method | |
| US9947105B2 (en) | Information processing apparatus, recording medium, and information processing method | |
| CN105335750A (en) | Client identity identification system and identification method | |
| JP2015106300A (en) | Image search device, control method for image search device, and program | |
| CN105488486B (en) | The face identification method and device for preventing photo from attacking | |
| EP3893192A1 (en) | Information processing system, information processing device, information processing method, and program | |
| JP2016181159A (en) | System, retrieval method and program | |
| JP6645655B2 (en) | Image processing apparatus, image processing method, and program | |
| CN110211251A (en) | A kind of face identification method, device, storage medium and recognition of face terminal | |
| CN110717428A (en) | Identity recognition method, device, system, medium and equipment fusing multiple features | |
| CN104980695A (en) | Coordination of object location data with video data | |
| CN109583296A (en) | One kind preventing error detection method, apparatus, system and computer storage medium | |
| KR100434907B1 (en) | Monitoring system including function of figure acknowledgement and method using this system | |
| WO2018080547A1 (en) | Video monitoring | |
| WO2020115910A1 (en) | Information processing system, information processing device, information processing method, and program | |
| CN110866418A (en) | Image base generation method, device, equipment, system and storage medium | |
| JP2002208011A (en) | Image collation processing system and its method | |
| CN110991316B (en) | Method for automatically acquiring shape and identity information applied to open environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20200602 Address after: 250001 whole floor, building 3, Aosheng building, 1166 Xinluo street, Jinan area, Jinan pilot Free Trade Zone, Shandong Province Patentee after: Jinan boguan Intelligent Technology Co., Ltd Address before: Hangzhou City, Zhejiang province 310051 Binjiang District West Street Jiangling Road No. 88 building 10 South Block 1-11 Patentee before: ZHEJIANG UNIVIEW TECHNOLOGIES Co.,Ltd. |
|
| TR01 | Transfer of patent right |