Specific embodiment
Below in conjunction with attached drawing in the embodiment of the present invention, technical solution in the embodiment of the present invention carries out clear, completeGround description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Usually existThe component of the embodiment of the present invention described and illustrated in attached drawing can be arranged and be designed with a variety of different configurations herein.
Therefore, the detailed description of the embodiment of the present invention provided in the accompanying drawings is not intended to limit below claimedThe scope of the present invention, but be merely representative of selected embodiment of the invention.Based on the embodiment of the present invention, those skilled in the artMember's every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
It should be noted that term " first " and " second " etc. relational terms be used merely to an entity or behaviourMake with another entity or operate distinguish, without necessarily requiring or implying between these entities or operation there are it is any thisThe actual relationship of kind or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to nonexcludabilityInclude so that include a series of elements process, method, article or equipment not only include those elements, but alsoIncluding other elements that are not explicitly listed, or further include for this process, method, article or equipment intrinsic wantElement.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including described wantThere is also other identical elements in the process, method, article or equipment of element.
Fig. 1 is please referred to, is the block diagram of server 100.The server 100 includes that recognition of face training sample obtainsTake device 200, memory 111, processor 112 and communication unit 113.
The memory 111, processor 112 and each element of communication unit 113 are directly or indirectly electrical between each otherConnection, to realize the transmission or interaction of data.For example, these elements can pass through one or more communication bus or letter between each otherNumber line, which is realized, to be electrically connected.The recognition of face training sample acquisition device 200 includes at least one can be with software or firmware(Firmware) form is stored in the memory 111 or is solidificated in the operating system of the server 100Software function module in (Operating System, OS).The processor 112 is deposited in the memory 111 for executingThe executable module of storage, such as software function module and calculating included by the recognition of face training sample acquisition device 200Machine program etc..
Wherein, the memory 111 may be, but not limited to, random access memory (Random AccessMemory, RAM), read-only memory (Read Only Memory, ROM), programmable read only memory (ProgrammableRead-Only Memory, PROM), erasable read-only memory (Erasable Programmable Read-OnlyMemory, EPROM), electricallyerasable ROM (EEROM) (Electric Erasable Programmable Read-OnlyMemory, EEPROM) etc..Wherein, memory 111 is for storing program or data.The communication unit 113 is for passing through instituteThe communication connection that network is established between the server 100 and other communication terminals is stated, and for receiving and dispatching number by the networkAccording to.
It should be understood that structure shown in FIG. 1 is only the structural schematic diagram of server 100, the server 100 may be used alsoIncluding component more perhaps more less than shown in Fig. 1 or with the configuration different from shown in Fig. 1.Each group shown in Fig. 1Part can be realized using hardware, software, or its combination.
First embodiment
The embodiment of the invention provides a kind of recognition of face training sample acquisition methods, know for on-line automatic acquisition faceOther training sample, is distinguished without using manpower, is demarcated.Referring to Fig. 2, being instructed for recognition of face provided in an embodiment of the present inventionPractice the flow chart of sample acquiring method.The face recognition training sample acquiring method includes:
Step S201: the first biometric information of user is obtained.
In an alternative embodiment, the first biometric information is finger print information.Accordingly, acquisition finger print information is answeredWhen for fingerprint identification device.Correspondingly, when the first biometric information is other types, corresponding acquisition equipment can beOther.
Step S202: judge to believe in the first pre-established biometric information database with the presence or absence of with the first bio-identificationMatched biometric information is ceased, if so, thening follow the steps S203；If it is not, then re-executeing the steps S201.
Wherein, the first pre-established biometric information database includes the biometric information of a large number of users.Meanwhile it shouldIn the memory 111 of server 100, be also stored with the facial image of a large number of users, and the facial image of each user and its fromThe biometric information of body is associated.
By judging to whether there is and the first biometric information in the first pre-established biometric information databaseThe biometric information matched actually judges in the memory 111 of server 100, if is stored with and possesses the first biology knowledgeThe facial image of the user of other information.
When in the first pre-established biometric information database be not present and the matched biology of the first biometric informationWhen identification information, just show the facial image that the user is not stored in the memory 111 of server 100, to can not obtainRecognition of face training sample is taken, needs to reacquire the first biometric information, re-starts judgement.
In an alternative embodiment, include by the first biometric information and the first biometric information databaseAll biometric informations are compared one by one, once comparing successfully, just can obtain the first pre-established biometric information numberAccording to the result existed in library with the matched biometric information of the first biometric information.
Furthermore, it is to be understood that ground, the first biometric information and believe with the matched bio-identification of the first biometric informationBreath, as same user, current collected biometric information and the biometric information for acquiring and storing in the past.
Step S203: it obtains pre-stored with associated first facial image of the first biometric information.
Know when existing in the first pre-established biometric information database with the matched biology of the first biometric informationWhen other information, just directly acquire it is pre-stored with associated first facial image of the first biometric information, to constitute face knowledgeOther training sample.
Step S204: the second facial image of control one image capture device acquisition user.
Meanwhile determining exist in the first pre-established biometric information database and the first biometric informationWhen the biometric information matched, the second facial image of control one image capture device acquisition user, to be instructed as recognition of facePractice another part of sample.
Step S205: the first facial image and the second facial image are determined as recognition of face training sample.
It is to be appreciated that recognition of face training sample should belong to the facial image of same user comprising at least two.AndWhen there is biometric information matched with the first biometric information in the first pre-established biometric information database,Just it using with associated first facial image of the first biometric information as one of the facial image compareed, while acquiring at onceThe second facial image of user, using as another person's face image, to constitute complete recognition of face training sample.
Step S206: the second biometric information associated with the first biometric information is obtained.
Know when existing in the first pre-established biometric information database with the matched biology of the first biometric informationOther information and then acquisition the second biometric information associated with first biometric information.
It should be noted that in the present embodiment, which is that collection in worksite possesses the first biologyThe biometric information of the user of identification information.And second the type of biometric information and the first biometric information can phaseIt is same to can also be different.In an alternative embodiment, the second biometric information is voiceprint.Voiceprint is relative to fingerLine information is easier to acquire, and fingerprint collecting equipment is actively put his hand into without user, as long as but user speak, just can utilize vocal printAcquisition equipment just can collect voiceprint.Certainly, in other embodiments, the second biometric information can also be other classesType, such as finger print information, iris information etc..
It should also be noted that, the second biometric information database, which can also be, to be deposited in an alternative embodimentIt is stored in the second biometric information database pre-established, is not necessarily to collection in worksite, the first bio-identification of direct basisInformation searching is simultaneously read.
To sum up, the first biometric information and the first face picture of the second biometric information and user itself are equalIt is associated.
Step S207: judge whether to receive the abnormal signal that image capture device generates and sends, if it is, stepS208；If not, thening follow the steps S212.
It should be noted that when image capture device due to photographic subjects turn round, be blocked or other factors withoutWhen can take the facial image of photographic subjects, abnormal signal is just generated, abnormal signal is just transmitted to server 100.
When not receiving the abnormal signal that image capture device generates and sends, show that Image Acquisition is set under current stateThe standby third facial image that can acquire user, therefore step S212 is executed at this time, it can continue to obtain more training samples.
Step S208: control image capture device stops shooting.
After image capture device generates abnormal signal, show that image capture device can not currently acquire facial image, becauseThis server 100 controls image capture device and stops shooting, to avoid excessive unrelated images are taken.
Step S209: judging whether to receive the recovery normal signal that image capture device generates and sends, if it is,Step S210；If it is not, then terminating process.
When receiving the recovery normal signal that image capture device generates and sends, show image capture device energy at this timeThe facial image of photographic subjects is enough taken, but can not be determined during image capture device loses photographic subjects with the presence or absence of peopleThe case where member's replacement, therefore subsequent process is also needed further to judge；And image capture device ought not be received and is generated concurrentlyWhen the recovery normal signal sent, then facial image can not be further obtained, therefore directly terminate process.
Step S210: the third biometric information of user is obtained.
Third biometric information is image capture device collected biometric information in real time.
Step S211: judging whether third biometric information matches with the second biometric information, if it is, executingStep S212；If it is not, then terminating process.
It is to be appreciated that since user can be movement, but the position of image capture device is fixed, thus in realityIn the application process of border, be constantly present image capture device can not photographic subjects user facial image the case where.To by sentencingWhether disconnected third biometric information matches with the second biometric information, can determine that image capture device loses photographic subjectsAgain the face picture that can be shot afterwards, if the face possessed with the user of the second biometric information shot for beforePicture leads to the face sample captured so as to avoid personnel's replacement occurs during image capture device loses photographic subjectsThe problem of mistake ensure that the reliability of face sample.
When third biometric information and the second biometric information mismatch, show to lose bat in image capture devicePersonnel's replacement occurs during taking the photograph target, training sample can not be obtained again, therefore directly terminate process.
Step S212: control image capture device resurveys the third facial image of user.
When third biometric information is matched with the second biometric information, show the photographic subjects of image capture deviceIt does not replace, as possesses the user of the first biometric information and the second biometric information, resurvey third again at this timeFacial image, using as new recognition of face training sample.
Step S213: third facial image and the first facial image are determined as recognition of face training sample.
Specifically, by police and judicial remotely help and educate meet with scene for be unfolded discuss, the present invention will be described in detail provideThe application process of recognition of face training sample acquisition methods.
The first biometric information, i.e. finger print information are first acquired in inlet, then inquires pre-established fingerprint databaseIn whether there is the finger print information, if it is present control inlet video camera carry out face snap to obtain the second face figurePicture, while the certificate photo of the user is obtained, as the first facial image, and in conjunction with the second facial image that entrance camera is capturedRecognition of face training subsystem is given together as recognition of face training sample carries out model training.
After entering audience chamber, start the continuous collecting of vocal print, it will collected second biometric information, i.e. sound for the first timeLine information is stored in database, the baseline as subsequent Application on Voiceprint Recognition.Then paying special attention to face cannot be by the different of video captureReason condition: it once face leaves the candid photograph region of video camera, for example turns one's head or moves, video camera can not then be normally carried out face and grabIt claps.When abnormal conditions recovery, need to suspend the face snap function of video camera.It at this time will be in collected vocal print and databaseThe voice print database of typing for the first time is compared, and after only vocal print compares successfully, system just starts the normal face snap of video cameraTo obtain third facial image, and recognition of face training is given together as recognition of face training sample in conjunction with the first face imageSubsystem carries out model training.
Second embodiment
Referring to Fig. 3, Fig. 3 is a kind of recognition of face training sample acquisition device 200 that present pre-ferred embodiments provideFunctional block diagram.It should be noted that recognition of face training sample acquisition device 200 provided by the present embodiment, basicPrinciple and the technical effect of generation are identical with above-described embodiment, and to briefly describe, the present embodiment part does not refer to place, can refer toCorresponding contents in the above embodiments.The face recognition training sample acquiring device 200 includes biometric information acquiring unit210, judging unit 220, facial image acquiring unit 230, control unit 240 and recognition of face training sample determination unit250。
Wherein, biometric information acquiring unit 210 is used to obtain the first biometric information of user.
It is to be appreciated that the biometric information acquiring unit 210 can be used for executing step in a kind of preferred embodimentRapid S201.
Judging unit 220 whether there is and the first biology for judging in the first pre-established biometric information databaseThe matched biometric information of identification information.
It is to be appreciated that the judging unit 220 can be used for executing step S202 in a kind of preferred embodiment.
Facial image acquiring unit 230 is used to exist in the first pre-established biometric information database and first is rawWhen the matched biometric information of object identification information, obtain pre-stored with the associated first face figure of the first biometric informationPicture.
It is to be appreciated that the facial image acquiring unit 230 can be used for executing step in a kind of preferred embodimentS203。
Control unit 240 is used to control the second facial image of image capture device acquisition user.
It is to be appreciated that the control unit 240 can be used for executing step S204 in a kind of preferred embodiment.
Recognition of face training sample determination unit 250 is used to the first facial image and the second facial image being determined as faceRecognition training sample.
It is to be appreciated that the face recognition training sample determination unit 250 can be used for holding in a kind of preferred embodimentRow step S205.
Biometric information acquiring unit 210 is also used to obtain the second biology associated with the first biometric information and knowsOther information.
It is to be appreciated that the biometric information acquiring unit 210 can be used for executing step in a kind of preferred embodimentRapid S206.
Judging unit 220 is also used to judge whether to receive the abnormal signal that image capture device generates and sends.
It is to be appreciated that the judging unit 220 can be used for executing step S207 in a kind of preferred embodiment.
Control unit 240 is also used to when not receiving the abnormal signal that image capture device generates and sends, control figureAs acquisition equipment stops shooting.
It is to be appreciated that the control unit 240 can be used for executing step S208 in a kind of preferred embodiment.
Judging unit 220 is also used to judge whether to receive the recovery normal signal that image capture device generates and sends.
It is to be appreciated that the judging unit 220 can be used for executing step S209 in a kind of preferred embodiment.
Biometric information acquiring unit 210 is also used to normal when receiving the recovery that image capture device generates and sendsWhen signal, the third biometric information of user is obtained.
It is to be appreciated that the biometric information acquiring unit 210 can be used for executing step in a kind of preferred embodimentRapid S210.
Judging unit 220 is also used to judge whether third biometric information matches with the second biometric information.
It is to be appreciated that the judging unit 220 can be used for executing step S211 in a kind of preferred embodiment.
Control unit 240 is also used to when third biometric information is matched with the second biometric information, controls imageAcquisition equipment resurveys the third facial image of user.
It is to be appreciated that the control unit 240 can be used for executing step S212 in a kind of preferred embodiment.
Recognition of face training sample determination unit 250 is also used to third facial image and the first facial image being determined as peopleFace recognition training sample.
It is to be appreciated that the face recognition training sample determination unit 250 can be used for holding in a kind of preferred embodimentRow step S213.
In conclusion recognition of face training sample acquisition methods provided in an embodiment of the present invention and device, are used by obtainingFirst biometric information at family, when in the first biometric information database exist and the matched life of the first biometric informationIt when object identification information, obtains pre-stored with associated first facial image of the first biometric information, while controlling an imageThe second facial image for acquiring equipment acquisition user, so that the first facial image and the second facial image are determined as recognition of faceTraining sample.Due to being associated with the first facial image and the second facial image using the first biometric information, to realizeIn the case where prosthetic participates in, recognition of face training sample is reliably obtained, efficiency and accuracy rate had both been improved, and had also savedHuman cost.
In several embodiments provided herein, it should be understood that disclosed device and method can also pass throughOther modes are realized.The apparatus embodiments described above are merely exemplary, for example, flow chart and block diagram in attached drawingShow the device of multiple embodiments according to the present invention, the architectural framework in the cards of method and computer program product,Function and operation.In this regard, each box in flowchart or block diagram can represent the one of a module, section or codePart, a part of the module, section or code, which includes that one or more is for implementing the specified logical function, to be heldRow instruction.It should also be noted that function marked in the box can also be with difference in the implementation that some are determined as replacementThe sequence marked in attached drawing occurs.For example, two continuous boxes can actually be basically executed in parallel, they are sometimesIt can also execute in the opposite order, this depends on the function involved.It is also noted that in block diagram and or flow chartThe combination of box in each box and block diagram and or flow chart, can function or movement as defined in executing it is dedicatedHardware based system is realized, or can be realized using a combination of dedicated hardware and computer instructions.
In addition, each functional module in each embodiment of the present invention can integrate one independent portion of formation togetherPoint, it is also possible to modules individualism, an independent part can also be integrated to form with two or more modules.
If the function is realized in the form of software function module and determination is independent product when selling or using, canTo be stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention substantially orSay that the part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, it shouldComputer software product is stored in a storage medium, including some instructions are used so that a computer equipment (can bePersonal computer, server or network equipment etc.) execute all or part of step of each embodiment the method for the present inventionSuddenly.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), deposits at randomThe various media that can store program code such as access to memory (RAM, Random Access Memory), magnetic or disk.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this fieldFor art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repairChange, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.