Summary of the invention
The disclosure technical problem to be solved is to provide a kind of face identification method, device and system, can be improvedThe accuracy of recognition of face.
On the one hand according to the disclosure, a kind of face identification method is proposed, comprising: receive the video that video monitoring equipment is sentImage and monitoring period information；If in video image including facial image to be identified, video monitoring is searched according to monitoring periodThe customer equipment identification information that equipment obtains；Corresponding complete facial image is determined according to customer equipment identification information；It will be completeFacial image is matched with facial image to be identified, identifies the overall face feature of facial image to be identified.
Optionally, face identification method further include: carry out the corresponding complete facial image of customer equipment identification informationClustering；The key facial feature of every a kind of whole person's face image is weighted；By the pass of facial image to be identifiedKey facial characteristics is weighted；By the weighted value of the key facial feature of facial image to be identified and complete facial imageThe weighted value of key facial feature is matched；The weighted value of key facial feature with facial image to be identified is most matchedOverall face feature of the overall face feature of complete facial image as facial image to be identified.
Optionally, the face identification method further include: the overall face feature for the facial image to be identified that will identify that withThe overall face feature of facial image in database is compared, and determines the corresponding personnel identity information of people's image to be identified；Wherein, the overall face feature of facial image and the corresponding relationship of personnel identity information are preserved in database.
Optionally, face identification method further include: the people to be identified that will be identified in video image by video-splicingFace image is synthesized, and the complete facial image of facial image to be identified is dynamically presented.
Optionally, customer equipment identification information is the MAC Address of user equipment.
According to another aspect of the present disclosure, it is also proposed that a kind of face identification device, comprising: information receiving unit, for connecingReceive the video image and monitoring period information that video monitoring equipment is sent；Face determination unit to be identified, for determining video figureIt whether include facial image to be identified as in；Equipment identification information acquiring unit, if for including people to be identified in video imageFace image then searches the customer equipment identification information that video monitoring equipment obtains according to monitoring period；Complete facial image determinesUnit, for determining corresponding complete facial image according to customer equipment identification information；Face matching unit is used for whole personFace image is matched with facial image to be identified, identifies the overall face feature of facial image to be identified.
Optionally, the face identification device further include: cluster analysis unit, for customer equipment identification information is correspondingComplete facial image carries out clustering；Facial characteristics weight calculation unit, for by the key of every a kind of whole person's face imageFacial characteristics is weighted, and the key facial feature of facial image to be identified is weighted；Wherein, faceMatching unit is used for the weighted value of the key facial feature of facial image to be identified and the key facial of complete facial image is specialThe weighted value of sign is matched, by the most matched complete face figure of the weighted value of the key facial feature with facial image to be identifiedOverall face feature of the overall face feature of picture as facial image to be identified.
Optionally, face identification device further include: personnel identity determination unit, the face to be identified for will identify thatThe overall face feature of image is compared with the overall face feature of the facial image in database, determines people's image to be identifiedCorresponding personnel identity information；Wherein, the overall face feature and personnel identity information of facial image are preserved in databaseCorresponding relationship.
Optionally, the face identification device further include: face image synthesis unit, for passing through video-splicing for video figureThe facial image to be identified identified as in is synthesized, and the complete facial image of facial image to be identified is dynamically presented.
Optionally, customer equipment identification information is the MAC Address of user equipment.
According to another aspect of the present disclosure, it is also proposed that a kind of face identification system, comprising: video monitoring equipment and above-mentionedFace identification device；Wherein, video monitoring equipment has the function of wireless exploration.
According to another aspect of the present disclosure, it is also proposed that a kind of face identification device, comprising: memory；And it is coupled to and depositsThe processor of reservoir, processor are configured as the face identification method for example above-mentioned based on the instruction execution for being stored in memory.
According to another aspect of the present disclosure, it is also proposed that a kind of computer readable storage medium is stored thereon with computer journeyThe step of sequence instruction, which realizes above-mentioned face identification method when being executed by processor.
If in disclosure video image including facial image to be identified, video monitoring equipment is searched according to monitoring period and is obtainedThe customer equipment identification information obtained, and corresponding complete facial image is determined according to customer equipment identification information, by complete faceImage is matched with facial image to be identified, identifies the overall face feature of facial image to be identified, being capable of dynamic optimizationFacial image improves the accuracy of recognition of face.
By the detailed description referring to the drawings to the exemplary embodiment of the disclosure, the other feature of the disclosure and itsAdvantage will become apparent.
Specific embodiment
The various exemplary embodiments of the disclosure are described in detail now with reference to attached drawing.It should also be noted that unless in addition havingBody explanation, the unlimited system of component and the positioned opposite of step, numerical expression and the numerical value otherwise illustrated in these embodiments is originallyScope of disclosure.
Simultaneously, it should be appreciated that for ease of description, the size of various pieces shown in attached drawing is not according to realityProportionate relationship draw.
Be to the description only actually of at least one exemplary embodiment below it is illustrative, never as to the disclosureAnd its application or any restrictions used.
Technology, method and apparatus known to person of ordinary skill in the relevant may be not discussed in detail, but suitableIn the case of, the technology, method and apparatus should be considered as authorizing part of specification.
It is shown here and discuss all examples in, any occurrence should be construed as merely illustratively, withoutIt is as limitation.Therefore, the other examples of exemplary embodiment can have different values.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang YiIt is defined in a attached drawing, then in subsequent attached drawing does not need that it is further discussed.
For the purposes, technical schemes and advantages of the disclosure are more clearly understood, below in conjunction with specific embodiment, and referenceThe disclosure is further described in attached drawing.
Fig. 1 is the flow diagram of one embodiment of disclosure face identification method.
In step 110, the video image and monitoring period information that video monitoring equipment is sent are received.Wherein, the video figureThe local faces images such as side face, half of face may be included as in, it is also possible to include complete facial image.
In step 120, if in video image including facial image to be identified, video monitoring is searched according to monitoring period and is setThe standby customer equipment identification information obtained.Wherein, video monitoring equipment has the function of wireless exploration, and customer equipment identification information isThe MAC Address of user equipment.For example, can be searched according to monitoring period if video image includes side face image and pass through WIFIProbe obtains user terminal MAC Address, which can be set in video monitoring equipment.
In step 130, corresponding complete facial image is determined according to customer equipment identification information.For example, passing through the regionOther video monitoring equipments can obtain the corresponding complete facial image of customer equipment identification information.
In step 140, complete facial image is matched with facial image to be identified, identifies facial image to be identifiedOverall face feature.For example, have corresponding complete facial image in other monitor videos in region in the same time,And the corresponding user terminal MAC Address of the complete facial image is obtained also by WIFI probe, if facial image pair to be identifiedThe user terminal MAC Address answered user terminal MAC Address corresponding with complete facial image is identical, then it is assumed that the complete face figureThe facial characteristics of picture is the overall face feature of facial image to be identified.
In this embodiment, if in video image including facial image to be identified, video prison is searched according to monitoring periodThe customer equipment identification information that equipment obtains is controlled, and corresponding complete facial image is determined according to customer equipment identification information, it willComplete facial image is matched with facial image to be identified, identifies the overall face feature of facial image to be identified, canDynamic optimization facial image improves the accuracy of recognition of face.
Fig. 2 is the flow diagram of another embodiment of disclosure face identification method.
In step 210, the video image and monitoring period information that video monitoring equipment is sent are received.
In step 220, if in video image including facial image to be identified, video monitoring is searched according to monitoring period and is setThe standby customer equipment identification information obtained.
In step 230, corresponding complete facial image is determined according to customer equipment identification information.Wherein, due to same viewThe case where may including multiple faces in frequency picture, therefore, match the customer equipment identification information face may for it is multiple notSame people.
In step 240, the corresponding complete facial image of customer equipment identification information is subjected to clustering.By to completeFacial image carries out clustering, can determine in video pictures and correspond to the complete facial image of how many class, i.e., corresponding how many personal.
In step 250, the key facial feature of every a kind of whole person's face image is weighted.
In step 260, the key facial feature of facial image to be identified is weighted.
Wherein, step 250 and step 260 may be performed simultaneously, can also execution in no particular order.
In step 270, by the key of the weighted value of the key facial feature of facial image to be identified and complete facial imageThe weighted value of facial characteristics is matched.
In step 280, by the most matched complete face figure of the weighted value of the key facial feature with facial image to be identifiedOverall face feature of the overall face feature of picture as facial image to be identified.Wherein, feature vector is carried out to face informationComparison analysis after, can carry out intelligent compensation etc. pretreatment, complete pretreatment after, the available face figure compared with comprehensive characterPicture, the most suitable facial image of optimization, so that image detail feature is apparent.
It in this embodiment, can be first to complete face for having the case where multiple face informations in same video imageImage carries out clustering, the key facial feature of every a kind of whole person's face image is weighted, while to be identifiedThe key facial feature of facial image is weighted, then by the weighted value of the key facial feature of facial image to be identifiedIt is matched with the weighted value of the key facial feature of complete facial image, by the overall face of most matched complete facial imageOverall face feature of the feature as facial image to be identified, can improve the local face image in video, optimization videoIn face to be identified complete appearance, realize more monitoring area dynamic acquisitions tracking targets, and improve the sense of facial imageOfficial's effect.
Fig. 3 is the flow diagram of the further embodiment of disclosure face identification method.Wherein video monitoring equipment canThink the video camera with WIFI detecting function, be able to carry out video capture, while the MAC of user terminal can be detectedLocation.
In step 310, video camera obtains a unrecognized side face video, which is sent to recognition of face dressIt sets, wherein carry temporal information in the video.
In step 320, face identification device analyzes side face personnel's video clip, and to be identified in monitored pictureFace carries out screenshot, while acquisition time information.
In step 330, face identification device sends the request for obtaining user terminal MAC Address to video camera.
In step 340, video camera is based on temporal information and sends user terminal MAC Address to face identification device.
In step 350, face identification device obtains one or more complete facial images by user terminal MAC Address.
In step 360, complete facial image is matched with facial image to be identified.Wherein it is possible to according to crucial specialSign similarity etc. confirms the overall face feature of face to be identified.
In step 370, the overall face feature for the facial image to be identified that will identify that and the facial image in databaseOverall face feature be compared, determine the corresponding personnel identity information of people's image to be identified.Wherein, it is preserved in databaseThe overall face feature of facial image and the corresponding relationship of personnel identity information.
In this embodiment, by carrying out MAC Address comparison, the complete looks of optimization face to be identified, dynamic optimizationThe mode of facial image, then face discriminance analysis is done, to obtain the facial image that minutia is more clear, improves face and knowOther accuracy and integrality.
In addition, the facial image to be identified that the disclosure can also be will identify that by video-splicing is synthesized, dynamically it is inThe complete facial image of existing facial image to be identified realizes comprehensive recognition of face, and then carries out more monitoring area dynamics and obtainTake tracking target.User can check face recognition result by client and video is played and recorded a video in real time.
Fig. 4 is the structural schematic diagram of one embodiment of disclosure face identification device.The face identification device includes letterReceiving unit 410, face determination unit 420 to be identified, equipment identification information acquiring unit 430, complete facial image is ceased to determineUnit 440 and face matching unit 450, in which:
Information receiving unit 410 is used to receive the video image and monitoring period information of video monitoring equipment transmission.Wherein,The local faces images such as side face, half of face may be included in the video image, it is also possible to include complete facial image.
Whether face determination unit 420 to be identified is for determining in video image comprising facial image to be identified.
If equipment identification information acquiring unit 430 is for including facial image to be identified in video image, according to monitoringTime searches the customer equipment identification information that video monitoring equipment obtains.Wherein, video monitoring equipment has the function of wireless exploration,Customer equipment identification information is the MAC Address of user equipment.
Complete facial image determination unit 440 is used to determine corresponding complete face figure according to customer equipment identification informationPicture.
Face matching unit 450 is identified for matching complete facial image with facial image to be identified wait knowThe overall face feature of others' face image.
In this embodiment, if in video image including facial image to be identified, video prison is searched according to monitoring periodThe customer equipment identification information that equipment obtains is controlled, and corresponding complete facial image is determined according to customer equipment identification information, it willComplete facial image is matched with facial image to be identified, identifies the overall face feature of facial image to be identified, canDynamic optimization facial image improves the accuracy of recognition of face.
Fig. 5 is the structural schematic diagram of another embodiment of disclosure face identification device.The face identification device includesInformation receiving unit 510, face determination unit 520 to be identified, equipment identification information acquiring unit 530, complete facial image are trueOrder member 540, cluster analysis unit 550, facial characteristics weight calculation unit 560 and face matching unit 570, in which:
Information receiving unit 510 is used to receive the video image and monitoring period information of video monitoring equipment transmission.Wait knowWhether others' face determination unit 520 is used to determine in video image comprising facial image to be identified.Equipment identification information obtains singleIf member 530 searches what video monitoring equipment obtained for including facial image to be identified in video image, according to monitoring periodCustomer equipment identification information.Complete facial image determination unit 540 is corresponding complete for being determined according to customer equipment identification informationWhole facial image.Cluster analysis unit 550 is used to carrying out the corresponding complete facial image of customer equipment identification information into cluster pointAnalysis.By carrying out clustering to complete facial image, it can determine in video pictures and correspond to the complete facial image of how many class, i.e.,It is corresponding how many personal.Facial characteristics weight calculation unit 560 be used for by the key facial feature of every a kind of whole person's face image intoRow weighted calculation, and the key facial feature of facial image to be identified is weighted.Face matching unit 570 is used forBy the weighted value of the weighted value of the key facial feature of facial image to be identified and the key facial feature of complete facial image intoRow matching, by the overall face of the most matched complete facial image of the weighted value of the key facial feature with facial image to be identifiedOverall face feature of the feature as facial image to be identified.
It in this embodiment, can be first to complete face for having the case where multiple face informations in same video imageImage carries out clustering, the key facial feature of every a kind of whole person's face image is weighted, while to be identifiedThe key facial feature of facial image is weighted, then by the weighted value of the key facial feature of facial image to be identifiedIt is matched with the weighted value of the key facial feature of complete facial image, by the overall face of most matched complete facial imageOverall face feature of the feature as facial image to be identified, can improve the local face image in video, optimization videoIn face to be identified complete appearance, realize more monitoring area dynamic acquisition target followings, and improve the sense of facial imageOfficial's effect.
In another embodiment of the disclosure, which can also include personnel identity determination unit 580,The overall face feature of facial image to be identified for will identify that and the overall face feature of the facial image in databaseIt is compared, determines the corresponding personnel identity information of people's image to be identified；Wherein, the entirety of facial image is preserved in databaseThe corresponding relationship of facial characteristics and personnel identity information.
In another embodiment of the disclosure, which can also include face image synthesis unit 590,For synthesizing the facial image to be identified identified in video image by video-splicing, face to be identified is dynamically presentedThe complete facial image of image.
Through the foregoing embodiment, the disclosure can be realized comprehensive recognition of face, and then carry out more monitoring area dynamicsObtain tracking target.
Fig. 6 is the structural schematic diagram of one embodiment of disclosure face identification system.The face identification system includes viewFrequency monitoring device 610 and face identification device 620, wherein face identification device 620 has carried out in detail in the above-described embodimentsIt introduces, video monitoring equipment 610 has the function of that wireless exploration is able to carry out for example, with the video camera of WIFI detecting functionVideo capture, while the MAC Address of user terminal can be detected.
The effect that multiple video monitoring equipments realize the covering of monitoring scene many places can be arranged in the disclosure in monitoring area,Many places key feature facial image is matched through the above way, realizes comprehensive recognition of face, improves the whole of recognition of faceBody efficiency.
Fig. 7 is the structural schematic diagram of the further embodiment of disclosure face identification device.The face identification device includesMemory 710 and processor 720.Wherein: memory 710 can be disk, flash memory or other any non-volatile memory mediums.Memory 710 is used to store the instruction in embodiment corresponding to Fig. 1-3.Processor 720 is coupled to memory 710, can be used asOne or more integrated circuits are implemented, such as microprocessor or microcontroller.The processor 720 is deposited for executing in memoryThe instruction of storage.
It in one embodiment, can be as shown in figure 8, the face identification device 800 includes memory 810 and processor820.Processor 820 is coupled to memory 810 by BUS bus 830.The face identification device 800 can also be connect by storageMouthfuls 840 are connected to external memory 850 to call external data, can also be connected to by network interface 860 network orThe other computer system (not shown) of person, no longer describes in detail herein.
In this embodiment, it is instructed by memory stores data, then above-metioned instruction is handled by processor, it being capable of dynamicOptimize facial image, improves the accuracy of recognition of face.
In another embodiment, a kind of computer readable storage medium, is stored thereon with computer program instructions, this refers toThe step of order realizes the method in embodiment corresponding to Fig. 1-3 when being executed by processor.It should be understood by those skilled in the art that,Embodiment of the disclosure can provide as method, apparatus or computer program product.Therefore, complete hardware reality can be used in the disclosureApply the form of example, complete software embodiment or embodiment combining software and hardware aspects.Moreover, the disclosure can be used oneIt is a or it is multiple wherein include computer usable program code computer can with non-transient storage medium (including but not limited toMagnetic disk storage, CD-ROM, optical memory etc.) on the form of computer program product implemented.
The disclosure is reference according to the method for the embodiment of the present disclosure, the flow chart of equipment (system) and computer program productAnd/or block diagram describes.It should be understood that each process in flowchart and/or the block diagram can be realized by computer program instructionsAnd/or the combination of the process and/or box in box and flowchart and/or the block diagram.It can provide these computer programs to refer toEnable the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to generateOne machine so that by the instruction that the processor of computer or other programmable data processing devices executes generate for realizingThe device for the function of being specified in one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spyDetermine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram orThe function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that countingSeries of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer orThe instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram oneThe step of function of being specified in a box or multiple boxes.
So far, the disclosure is described in detail.In order to avoid covering the design of the disclosure, it is public that this field institute is not describedThe some details known.Those skilled in the art as described above, completely it can be appreciated how implementing technology disclosed hereinScheme.
Although being described in detail by some specific embodiments of the example to the disclosure, the skill of this fieldArt personnel it should be understood that above example merely to be illustrated, rather than in order to limit the scope of the present disclosure.The skill of this fieldArt personnel are it should be understood that can modify to above embodiments in the case where not departing from the scope of the present disclosure and spirit.This public affairsThe range opened is defined by the following claims.