CN107977613A - Improve the method and face identification system of recognition of face efficiency - Google Patents
Improve the method and face identification system of recognition of face efficiency Download PDFInfo
- Publication number
- CN107977613A CN107977613A CN201711183034.9A CN201711183034A CN107977613A CN 107977613 A CN107977613 A CN 107977613A CN 201711183034 A CN201711183034 A CN 201711183034A CN 107977613 A CN107977613 A CN 107977613A
- Authority
- CN
- China
- Prior art keywords
- face
- recognition
- identification
- filing
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 230000001815 facial effect Effects 0.000 claims abstract description 44
- 238000012545 processing Methods 0.000 claims abstract description 28
- 230000003068 static effect Effects 0.000 claims description 16
- 230000007613 environmental effect Effects 0.000 claims description 15
- 238000012163 sequencing technique Methods 0.000 claims description 9
- 238000012795 verification Methods 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 4
- 238000003032 molecular docking Methods 0.000 claims description 3
- 238000011835 investigation Methods 0.000 description 12
- 230000000694 effects Effects 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 6
- 238000013459 approach Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 238000013524 data verification Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 239000000284 extract Substances 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000005286 illumination Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000013136 deep learning model Methods 0.000 description 2
- 238000012876 topography Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 210000000216 zygoma Anatomy 0.000 description 1
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
Disclose a kind of method and face identification system for improving recognition of face efficiency, in different identification location arrangements face recognition devices, multiple face recognition device collections and identification facial image, it is more than one or more of face recognition devices of predetermined accuracy rate to recognition accuracy to identify that object carries out facial image filing processing as target, wherein, the identification object refers to that specific identity is not required and is only through the object that face recognition device recognizes.
Description
Technical field
The invention belongs to technical field of face recognition, more particularly to a kind of method and face for improving recognition of face efficiency
Identifying system.
Background technology
At present, face recognition technology is increasingly becoming one kind with the maturation of camera, algorithm, data volume etc. condition
Bottom application tool class technology, is constantly popularized.
Realize that the designs such as attendance management, security protection verification are no longer rare using face recognition technology.Its basic principle is such as
Under, the face data of the crowd passed through is gathered by being arranged on the picture pick-up device of appropriate area, which is prestored with system
Human face data be compared, so as to fulfill authentication with identification judge.
Swipe the card, for brush finger line, brush face compared to traditional, the difficulty of present face recognition technology is not to being swept
Retouch that object is any to bother sense, do not require the special cooperation of scanned object.It is traditional swipe the card, brush finger line, brush face, especially brush
Face, although and authentication is realized by face recognition, its require object specific location keep given pose, this
The application scenarios of sample, for high flow capacity, the application scenarios of interruption-free are perfect not enough.However, in the case of non-intervention, it is natural
The crowd of flowing, in fact it could happen that glasses, mask, side face, bow, the interference of many factors such as cap, causes recognition accuracy big
It is big to reduce.
Although recognition accuracy can be continuously improved, setting can also be passed through by modes such as deep learning, data training
Stronger picture pick-up device, improves the face data amount collected, or even increase three-dimensional modeling reduces the technologies such as true face mask
To realize the further lifting of recognition accuracy, but in the case of current computing capability and device hardware ability, only from
The angle of single lens identification, which is set out, does improvement, the raising efficiency of recognition accuracy, as recognition accuracy becomes increasingly
Height, then it is increasing to lift difficulty.
Patent document CN104899579A discloses face identification method, and method includes:
According to the face characteristic of default deep learning model extraction facial image to be identified and facial image sample to
Amount;
The phase of the facial image to be identified and the facial image sample is calculated based on the face feature vector extracted
Like degree value;
Recognition of face is carried out to the facial image to be identified according to the similarity value calculated.The patent passes through
According to the face feature vector of default deep learning model extraction facial image to be identified and facial image sample, and it is based on
The face feature vector extracted calculates the similarity value of the facial image to be identified and the facial image sample, then
Recognition of face is carried out to the facial image to be identified according to the similarity value calculated.But the patent is still single
Recognition of face, can not break through equipment local environment, the equipment performance etc. limitation, can not be based on identification object be filed, make
Recognition of face efficiency it is low, utilizing status is poor.
Face identification method based on deep learning and key point feature extraction disclosed in patent document CN106355138A
Comprise the following steps,
Step 1, obtain video image, extracts the class Lis Hartel sign in video image;
Step 2, levy according to class Lis Hartel, builds the strong classifier of cascade, recycles strong classifier to detect video image
In human eye area image;
Step 3, set human eye area image symmetrical at least seven key point, then region division is carried out to it, obtains local
Image block;
Step 4, obtain the pretreatment topography block that identical key point is provided with face database, is matched local
Image block obtains the image block pair of corresponding key point, recycle depth convolutional neural networks extract the feature of image block pair to
Amount;
Step 5, the grader decision-making point for calculating feature vector, judge the highest image block pair of grader decision-making point, its
In belong to the pretreatment topography block in face database where facial image as the output result identified.The patent reduces
The error rate of recognition of face under the conditions of non-limiting, but the patent is still single recognition of face, can not be broken through residing for the equipment
Environment, equipment performance etc. are limited to, and can not be based on identification object and be filed so that recognition of face efficiency is low, and utilizing status is poor.
The content of the invention
For problems of the prior art, the present invention provides a kind of method for improving recognition of face efficiency and face is known
Other system, face identification system are more than recognition accuracy one or more of face recognition devices of predetermined accuracy rate to know
Other object carries out facial image filing processing for target, is lifted in single incident, by forming face identification system, based on knowledge
Other object is filed so that recognition of face is efficient and utilizing status is good.
The purpose of the present invention is be achieved by the following technical programs:
An aspect of of the present present invention, a kind of method for improving recognition of face efficiency include the following steps:
In different identification location arrangements face recognition devices, multiple face recognition device collections and identification facial image are right
Recognition accuracy is more than one or more of face recognition devices of predetermined accuracy rate to identify that object carries out face as target
Image filing is handled, wherein, the identification object refers to that specific identity is not required and is only through face recognition device identification
The object arrived.
In a kind of method of raising recognition of face efficiency, face identification system gathers each face recognition device
Identification parameter, identification parameter include shooting the performance parameter of the face recognition device of the facial image, environmental parameter and/or
Take the resource parameters of face identification system, face identification system recognition accuracy is more than predetermined accuracy rate one or
Multiple face recognition devices are to identify that object carries out facial image as target and corresponding identification parameter filing is handled.Wherein, shadow
The parameter for ringing identification is roughly divided into three aspects, when the performance parameter of face recognition device, second, residing for face recognition device
Environmental parameter, third, system processing recognition of face resource parameters, therefore, the present invention in, identification parameter include shooting described in
Performance parameter, environmental parameter and/or the resource parameters for taking face identification system of the face recognition device of facial image.
In a kind of method of raising recognition of face efficiency, the performance parameter includes point of face recognition device
Resolution, clarity, signal-to-noise ratio and/or white balance parameter, the environmental parameter include the identification position of face recognition device, identification
Angle, recognition of face integrity degree and/or environmental light intensity, the resource parameters for taking face identification system include taking identification system
CPU usage, the memory usage of system.
In a kind of method of raising recognition of face efficiency, set based on identification parameter to each face recognition device
Weight coefficient is put, each face recognition device identifies that the view data in the recognition result and database of facial image compares acquisition
Recognition accuracy, recognition accuracy are multiplied by weight coefficient and obtain the weight recognition accuracy of each face recognition device, and face is known
Other system is more than the weight recognition accuracy one or more of face recognition devices of predetermined accuracy rate to identify pair
As carrying out facial image filing processing for target.
In a kind of method of raising recognition of face efficiency, the weight coefficient is adjusted by data verification
Recognition accuracy approaches maximum probability value to obtain the optimal weight coefficient of each face recognition device.
In a kind of method of raising recognition of face efficiency, the weight coefficient is weighting weight parameter, described
Weight coefficient is weighted to pass through to performance parameter weight coefficient, environmental parameter weight coefficient and/or the money for taking face identification system
Source parameters weighting coefficient weighting obtains.
In a kind of method of raising recognition of face efficiency, when being identified to predetermined facial image, by the identification
Accuracy rate sorts from big to small, when recognition accuracy is located at one or more face recognition devices of predefined procedure to identify object
The filing processing of facial image and relevant identification parameter is carried out for target.
In a kind of method of raising recognition of face efficiency, based on identification position and/or recognition time section to returning
The filing data that shelves processing is drawn are marked, and the filing data include interim increased interim filing data, described interim
Filing data can be with the filing data filing processing.
In a kind of method of raising recognition of face efficiency, filing data and the static data with identity archives
Storehouse verifies and docking, periodically verifies the true identity in filing data by the verification with the static database, meets body
The filing data of part condition change into the data of static database.
In a kind of method of raising recognition of face efficiency, the identification parameter includes recognition time and identifies standby
Note information, motion track of the face identification system based on identification object and its identification parameter structure identification object.
According to another aspect of the present invention, a kind of face identification system for the method for implementing to improve recognition of face efficiency includes
Multiple face recognition devices and processor for being arranged in different identification positions, the processor include whether judging recognition accuracy
More than the determining device of predetermined accuracy rate and for filing the archiver handled to identify that object carries out facial image as target.
In the face identification system, face identification system includes being used for the data acquisition dress for gathering identification parameter
Put, processor connects the face recognition device and data acquisition device, and processor is further included for setting face recognition device
View data in recognition result and database, is compared the comparing unit for obtaining probable value, company by the weight unit of weight coefficient
The sequencing unit of the weight unit and comparing unit is connect, probable value is multiplied by weight coefficient and obtains each face knowledge by sequencing unit
The recognition accuracy of other equipment sorts from big to small.
In the face identification system, processor include be used for will filing data periodically with the quiet of identity archives
The checker of state database verification, the filing data that processor transmission verification passes through to the static database.In the people
In face identifying system, face identification system includes being used for the data acquisition device for gathering identification parameter, and processor connects the people
Face identification equipment and data acquisition device, processor further include for face recognition device weight coefficient is set weight unit,
View data in recognition result and database is compared to the comparing unit for obtaining probable value, the connection weight unit and is compared
Probable value is multiplied by weight coefficient and obtains each face recognition device by the sequencing unit and self study unit of unit, sequencing unit
Recognition accuracy sorts from big to small, and the self study unit adjusts the weight coefficient by data verification and identifies accurately
Rate approaches maximum probability value to obtain the optimal weight coefficient of each face recognition device.
Compared with prior art, the present invention has technique effect beneficial below:
In the prior art, for recognition result, handling result is often just provided at that time, such as security access control system,
, to provide subsequent treatment, it will either let pass or sent someone to be investigated according to recognition result at that time.But know completing
After the subsequent treatment of other result, the recognition result is not filed usually, causes the utilization rate of recognition result than relatively low,
The recognition result for each face recognition device that present system is disposed does filing analysis, and each face recognition device is known
The object being clipped to, is filed according to different attributes such as region, properties, and face identification system of the present invention is more than recognition accuracy
One or more of face recognition devices of predetermined accuracy rate are led to using identifying that object carries out facial image filing processing as target
Cross to form face identification system, filed based on identification object so that recognition of face is efficient and utilizing status is good, further
Weight analysis judgement can be carried out by the recognition result of the different face recognition devices for system deployment, it is preferable for condition
The recognition result of equipment give the weight of higher, improve the accuracy rate of recognition of face on the whole.
Described above is only the general introduction of technical solution of the present invention, in order to cause the technological means of the present invention clearer
Understand, reach the degree that those skilled in the art can be practiced according to the content of specification, and in order to allow the present invention
Above and other objects, features and advantages can become apparent, below with the present invention embodiment illustrate
Explanation.
Brief description of the drawings
By reading the detailed description hereafter in preferred embodiment, the advantages of present invention is various other and benefit
It will be clear understanding for those of ordinary skill in the art.Figure of description is only used for showing the purpose of preferred embodiment,
And it is not considered as limitation of the present invention.It should be evident that drawings discussed below is only some embodiments of the present invention,
For those of ordinary skill in the art, without creative efforts, can also be obtained according to these attached drawings
Other attached drawings.
In the accompanying drawings:
Fig. 1 is the step schematic diagram of the method for the raising recognition of face efficiency of one embodiment of the present of invention;
Fig. 2 is the structure diagram of the face identification system of one embodiment of the present of invention.
The present invention is further explained below in conjunction with drawings and examples.
Embodiment
The specific embodiment of the present invention is more fully described below with reference to accompanying drawings.Although show the present invention's in attached drawing
Specific embodiment, it being understood, however, that may be realized in various forms the present invention without should be limited by embodiments set forth here
System.Conversely, there is provided these embodiments are to be able to be best understood from the present invention, and can be complete by the scope of the present invention
Be communicated to those skilled in the art.
It should be noted that some vocabulary has been used to censure specific components among specification and claim.Ability
Field technique personnel it would be appreciated that, technical staff may call same component with different nouns.This specification and right
It is required that not in a manner of the difference of noun is used as and distinguishes component, but differentiation is used as with the difference of component functionally
Criterion."comprising" or " comprising " as mentioned in working as in specification in the whole text and claim are an open language, therefore should be solved
It is interpreted into " including but not limited to ".Specification subsequent descriptions for implement the present invention better embodiment, so it is described description be with
For the purpose of the rule of specification, the scope of the present invention is not limited to.Protection scope of the present invention, which is worked as, regards appended right
It is required that subject to institute's defender.
For ease of the understanding to the embodiment of the present invention, done further by taking several specific embodiments as an example below in conjunction with attached drawing
Explanation, and each attached drawing does not form the restriction to the embodiment of the present invention.
Fig. 1 is the step schematic diagram of the method for the raising recognition of face efficiency of one embodiment of the present of invention, and one kind improves
The method of recognition of face efficiency includes the following steps:
In different identification location arrangements face recognition devices, multiple face recognition device collections and identification facial image are right
Recognition accuracy is more than one or more of face recognition devices of predetermined accuracy rate to identify that object carries out face as target
Image filing is handled, wherein, the identification object refers to that specific identity is not required and is only through face recognition device identification
The object arrived.
Present recognition of face is all based on the extraction to some characteristic points on facial image in fact, then forms one specially
Archives of door form, for example extract some and will not usually change, and everyone characteristic point for having differences, interpupillary distance,
Ear is high, cheekbone is wide etc., so in the prior art, identification is exactly quickly to extract face in picture to be identified, Ran Houti in fact
The corresponding archives of characteristic point of the face are taken, are then compared with the target data being collected in static database, root
According to the similarity degree of comparison result, judge to make result.Processing for recognition result in the prior art is instant, with peace
Anti- investigation or it is online pursue and capture an escaped prisoner exemplified by, each recognition result, is just handled at once, the handling result of security protection be typically let pass or
Person blocks, and the handling result pursued and captured an escaped prisoner is typically to let pass or arrest.But the utilization of this recognition result is insufficient.Citing
For, a convict may not have any identification possibility before criminal offence is implemented;A market conversely speaking,
Or the VIP client of a service location, may not have yet any subsequent treatment may, although from market or the service
For place, have a mind to obtain very much the identity identification information of the client in advance.
The face identification system of the present invention has the ability to carry out filing processing for identification data.Known with the vehicle of highway
Exemplified by not, in expressway access, crucial current mouth, each outlet, the current data of a certain particular vehicle can be accurately obtained,
The current data include the time that vehicle passes through the locality, profile vehicle photo etc..If will every time it can identify
As a result, once confirm it is errorless after, all classification put in order with the relevant recognition result of the Vehicle Object, then being capable of fast reaction one
The account of the history of a object.
In the prior art, do not regarded completely based on one generally only using identifying that object does filing processing as target
Frequency record is preserved, and the holding time is often a shorter time.So a common example is, it is multiple when needing
When interrogating and examining the situation for asking some object, a feasible method, often goes to infer that the object may be at which according to existing clue
Which position a period appears in, and then goes to look back this section of video content by way of manually investigating.Such mode was both held
Object easily is can not find, and it is neither possible to realizing instantaneity, is often taken very long.
In application scheme, independent of above-mentioned existing static database, for the face being presently processing
Data, similarly complete the work such as face recognition, feature extraction, archives foundation, then by the currently processed human face data
As archive processing, although this archives does not have personnel's name, gender, the household register usually having in static database
Deng the data collected by other means, but by uniquely identifying the face recognition of object as a result, also can be by the user
Leave to come as the information that can file, in case the later stage uses, it might even be possible to established according to the archive information of the user merely complete
New static database.
Due to this filing be based on higher identification weight may or there is provided the feelings compared with high-accuracy threshold value
Just implement under condition, so the recognition result that filing obtains is relatively believable, more can really react the identification object
Situation.
At this time, being capable of the easily anti-trace for looking into the identification object when needing to identification object into when line search.
If still being illustrated with the embodiment of above-mentioned recognition of face deployment system, in the museum of a large-scale activity,
There may be 40 open entrances, each entrance deploys the picture pick-up device of high configuration, then disposed in most of passage
Passage picture pick-up device at 120, finally in each venue, deploys 40 wide-angle imaging equipment.Wherein, only entrance is imaged
Equipment and the face recognition result of passage picture pick-up device carry out filing processing, and only to those recognition accuracies more than 90%
Recognition result carry out filing processing.It so, it is possible reliably to obtain the filing data largely based on identifying object.
This filing data, can realize that substantial amounts of derivative purposes, such as the movable floor manager need searching activity
When certain live welcome guest, which may be in the bad dressing room of certain signal of communication, at this time, can transfer base rapidly
In the recognition result archive information of the welcome guest, historical activity information of the welcome guest in museum is judged, according to its event trace
It is inferred to the position at the most possible place of the welcome guest.
In above-mentioned example, director, welcome guest etc. are the objects for having in advance authentication information, and system has body according to these
The certification object of part, to do 1 comparison than N, then files its recognition result into system, in case follow-up use.
In fact, can also be by way of newly-built archives, to implement to file for the object without clear and definite identity.For example it is
System is put in order the user's identification object in new customer data base, so when shooting obtains a new user to entrance for the first time
Afterwards in whole active procedure, the recognition result of the user is constantly photographed, and the history for the identification object of enriching constantly is lived
Dynamic information.It is useful in that, effectively help system user can do scene investigation.So-called scene investigation, for example guess including identity
Survey.Object of one frequent activities near activity working space, it may be possible to a site activity support staff for not arranging identity;
Object of one frequent activities near entrance a, it may be possible to ox;There are more believable identification object filing shelves
In the case of case, many scene investigations and analysis, and this scene investigation and the result of analysis can be made based on the archives
Feedback is close to instantaneity.
In a kind of preferred embodiment for the method for improving recognition of face efficiency of the present invention, face identification system is adopted
Collect the identification parameter of each face recognition device, identification parameter includes shooting the performance of the face recognition device of the facial image
Parameter, environmental parameter and/or the resource parameters for taking face identification system, face identification system are more than recognition accuracy predetermined
One or more of face recognition devices of accuracy rate are to identify that object carries out facial image as target and corresponding identification is joined
Number filing processing.
The identification parameter of the present invention includes many aspects, such as ambient light, illumination light, shooting angle, indoor and outdoor surroundings etc..
Relatively good identification parameter, the access to elevators being typically include in the market under normal illumination environment, or normal illumination environment
Under exhibition detector gate at.Under such environment, due to being indoor, so usually identified object there is higher probability to uncap,
The cover materials such as mask;Since ambient light is normal, so both can guarantee that brightness when taking pictures, while object extracts outdoor wearing
Sunglasses possibility it is higher;Due in channel position, so higher by the possibility of the passage;Since passage is more narrow
It is narrow, so the identification object passed through at the same time will not be too many;Due to similar elevator or the passage of detector gate, thus object have it is higher
May positive face towards front direction of travel.In short, combining above-mentioned all conditions, the shooting that appropriate location is set here fills
Put, be capable of the view data for obtaining being very suitable for implementing recognition of face of higher probability, also, it is preferable to be also due to position,
Higher costs, the device of higher performance may also be used in the camera device that such location is disposed, so as to further be lifted most
Whole Object identifying rate.
In a kind of preferred embodiment for the method for improving recognition of face efficiency of the present invention, given based on identification parameter
Each face recognition device sets weight coefficient, and each face recognition device is identified in the recognition result and database of facial image
View data compare acquisition recognition accuracy, recognition accuracy is multiplied by weight coefficient and obtains the weight of each face recognition device
Recognition accuracy, face identification system are more than the weight recognition accuracy one or more of faces of predetermined accuracy rate
Identification equipment is to identify that object carries out facial image filing processing as target.In the present invention, pass through the identification knot to identifying object
The analysis of fruit, will wherein identify that weight is higher or recognition accuracy threshold value sets higher recognition result, as credible identification
As a result achieve, and will identify that information all filings such as position, recognition time, identification remarks are handled accordingly.The present invention's
In a kind of preferred embodiment of the method for raising recognition of face efficiency, adjusting the weight coefficient by data verification makes
Obtain recognition accuracy and approach maximum probability value to obtain the optimal weight coefficient of each face recognition device.
In a kind of preferred embodiment of the method for raising recognition of face efficiency of the present invention, the weight coefficient
To weight weight parameter, the weighting weight coefficient is by performance parameter weight coefficient, environmental parameter weight coefficient and/or accounting for
Weighted and obtained with the resource parameters weight coefficient of face identification system.
Based on this, multiple face recognition devices such as camera devices are deployed with a face identification system, can be with
, can be according to the performance of camera device, camera device local environment just in the case of carrying out recognition of face or image recognition
The difference identification condition such as profit, the system resources in computation distributed to camera device, to the obtained identification of the camera device
As a result weight identification is given.For example, in optimal location as described above, optimal picture pick-up device is configured with, and system is given
In the case of giving the computing resource that highest is supported, the judging result obtained at this should give highest weighting.That is,
It is again seen that in the case of identification object, the recognition result under the conditions of the identification is most believable.Next, for overall identification
Some aspects then further reduce it not as the recognition result that is obtained of those camera points of above-mentioned optimum condition to condition wherein
The credible weight of judging result.For those worst recognition results of identification conditions, for example, flow of the people it is huge, greatly disperseed meter
Resource is calculated, and ambient light is complicated, the large channel for having situations such as various hot spot shades, typically, such as old-fashioned customs building
Reach a standard passage, and due to lacking environmental reconstruction basis, huge plus flow of the people, personnel wear various masks, cap, scarf, personnel
Face's posture is different, the adverse circumstances of personnel's action speed, and the recognition result obtained here is relatively low with regard to relative weighting.
Under the prior art, the output result of recognition of face is often a possibility, and either 1 to 1,1 compares N than N or N
Comparison condition under, the recognition result of recognition of face often provides a possibility.The raising recognition of face efficiency of the present invention
Method passes through in different identification location arrangements face recognition devices, multiple face recognition device collections and identification facial image, people
Face identifying system gathers the identification parameter of each face recognition device, and power is set to each face recognition device based on identification parameter
Weight coefficient, the recognition result based on weight coefficient adjustment output.The preferably identification of higher weights identification parameter identification condition is set
For being identified as a result, giving higher weight, this significantly improves the accuracy rate of recognition of face.
In addition, above-mentioned weight analysis, the threshold value that may also be combined with recognition result is set.For example, join for above-mentioned identification
For the best system deployment point of number, when implementing 1 alignments than N at this, for example for the system of pursuing and capturing an escaped prisoner, collect
The face data of one object, is compared, which is judged by system with runaway convict's face data storehouse built in system
The probability identical with some runaway convict's first in database necessarily in some number range, due at this identification parameter compared with
It is good, when identifying that probability is in more than 90%, it must notify that policeman goes to be interrogated and examined, but when identification probability is less than
When 70%, then it may not necessarily be interrogated and examined.Certainly, above-mentioned investigation strategy is only illustrative, the threshold value in the investigation strategy, should
This is adjusted according to actual environment, it will be understood that takes precautions against desired occasion for high-risk, this judgment threshold can be further
Lower, for the occasion of low hazard prevention requirement, this judgment threshold can be dialled further up.The result of this adjustment is exactly, right
In environment as airport security, even if the system of pursuing and capturing an escaped prisoner judges that identical possibility is relatively low, but implementation should be also reminded
Investigation, for general public arena environment, even if the system of pursuing and capturing an escaped prisoner judges that identical possibility is of a relatively high, but can also abandon
Investigation.
In fact, the selection of this threshold value, can also do further adjustment according to the property of identification object database.Such as
It for the runaway convict of high-risk, can strengthen investigating, even if probability may be relatively low, can also notify to investigate, for common runaway convict, then
Investigation can be loosened, improve the operational efficiency of whole system.
In addition, above-mentioned weights can also be integrated with investigation result, so as to improve the data of highest weighting rank
Reliability, for the situation by recognition of face, and by actual identity investigation confirmation identity, such data are obvious
With highest weight, the identity of the explanation object that can be beyond all doubt.
In a kind of preferred embodiment of the method for raising recognition of face efficiency of the present invention, each recognition of face
View data in the recognition result and database of equipment identification facial image compares acquisition probable value, and probable value is multiplied by weight system
Number obtains the recognition accuracy of each face recognition device, and the recognition accuracy is sorted from big to small.
In a kind of preferred embodiment of the method for raising recognition of face efficiency of the present invention, pass through data verification
The weight coefficient is adjusted so that recognition accuracy approaches maximum probability value to obtain the optimal weight of each face recognition device
Coefficient.For example, in certain circumstances, gather the remarkable situation of distance, collect certain sample, then this sample is in itself
Situation be clear, so verification result is removed by this sample, so as to infer whether the setting of weight coefficient reasonable, if not
It can rationally be adjusted.For example 100 people are looked for, it is threaded back through going under multiple picture pick-up devices repeatedly, then counts this 100
The actual passage situation of people, is compared with the result that system is identified, is in the light of actual conditions compared with system results
Hit rate, to judge the weight coefficient of multiple picture pick-up devices.Adjusted in another example big data training can be carried out by self study device
The whole weight coefficient causes recognition accuracy to approach maximum probability value to obtain the optimal weight system of each face recognition device
Number.
In a kind of preferred embodiment of the method for raising recognition of face efficiency of the present invention, the performance parameter
Resolution ratio, clarity, signal-to-noise ratio and/or white balance parameter including face recognition device, the environmental parameter are known including face
Identification position, identification angle, recognition of face integrity degree and/or the environmental light intensity of other equipment.
In a kind of preferred embodiment of the method for raising recognition of face efficiency of the present invention, the occupancy face
The resource parameters of identifying system include CPU usage, the memory usage for taking identifying system.For example, it is arranged on critical positions
Face recognition device CPU usage and/or memory usage may be configured as higher, or the recognition of face when critical positions
The CPU usage and/or memory usage of equipment than it is relatively low when, can improve CPU usage and/or memory usage causes weight
The face recognition device of position is wanted to play more preferable recognition performance.In a kind of raising recognition of face efficiency of the invention
In the preferred embodiment of method, the weight coefficient is weighting weight parameter, and the weighting weight coefficient passes through to performance parameter
Weight coefficient, environmental parameter weight coefficient and/or the resource parameters weight coefficient weighting acquisition for taking face identification system.
In a kind of preferred embodiment of the method for raising recognition of face efficiency of the present invention, based on identification position
And/or the filing data that recognition time section draws filing processing are marked, the filing data include temporarily increased face
When file data, the interim filing data can be with the filing data filing processing.
In a kind of preferred embodiment of the method for raising recognition of face efficiency of the present invention, filing data and tool
The static database for having identity archives verifies and docking, periodically verifies filing data by the verification with the static database
In true identity, the filing data for meeting identity condition change into the data of static database.In described one of the present invention
Kind is improved in the preferred embodiment of the method for recognition of face efficiency, when being identified to predetermined facial image, by the recognition accuracy
Sort from big to small, when recognition accuracy is located at one or more face recognition devices of predefined procedure to identify object as target
Carry out the filing processing of facial image and relevant identification parameter.
In a kind of preferred embodiment of the method for raising recognition of face efficiency of the present invention, the identification parameter
Including recognition time and identification remark information, face identification system identifies object based on identification object and its identification parameter structure
Motion track.
Fig. 2 is the structure diagram of the face identification system of one embodiment of the present of invention, and one kind is implemented to improve face knowledge
The face identification system of the method for other efficiency includes multiple face recognition devices 1 and processor 3 for being arranged in different identification positions,
The processor includes judging whether recognition accuracy is more than the determining device 8 of predetermined accuracy rate and for identify object as target
Carry out the archiver 9 of facial image filing processing.
In the preferred embodiment of the face identification system of the present invention, face identification system includes being used to gather identification parameter
Data acquisition device 2, processor 3 connects the face recognition device 1 and data acquisition device 2, and processor 3, which further includes, to be used for
The weight unit 4 of face recognition device weight coefficient is set, the view data in recognition result and database is compared into acquisition generally
Probable value is multiplied by by the comparing unit 5 of rate value, the sequencing unit 6 for connecting the weight unit 4 and comparing unit 5, sequencing unit 6
The recognition accuracy that weight coefficient obtains each face recognition device 1 sorts from big to small.
In the preferred embodiment of the face identification system of the present invention, face identification system includes being used to gather identification parameter
Data acquisition device 2, processor 3 connects the face recognition device 1 and data acquisition device 2, and processor 3, which further includes, to be used for
The weight unit 4 of face recognition device weight coefficient is set, the view data in recognition result and database is compared into acquisition generally
The comparing unit 5 of rate value, the sequencing unit 6 and self study unit 7 for connecting the weight unit 4 and comparing unit 5, sequencing unit
Probable value is multiplied by weight coefficient by 6 to be obtained the recognition accuracy of each face recognition device 1 and sorts from big to small, the self study
Unit 7 by data verification adjusts the weight coefficient recognition accuracy and approaches maximum probability value to be known with obtaining each face
The optimal weight coefficient of other equipment 1.
In the preferred embodiment of the face identification system of the present invention, the identifying system is cloud server, the clothes
Business device includes processor, hard disk, memory, bus and the communication port for being interacted with face recognition device 1.
In one embodiment, processor 3 includes general processor, digital signal processor, application-specific integrated circuit ASIC
Or on-site programmable gate array FPGA.
In one embodiment, the processor 3 includes memory, and the memory includes one or more read-only storages
Device ROM, random access memory ram, flash memory or Electrical Erasable programmable read only memory EEPROM.
Although embodiment of the present invention is described above in association with attached drawing, the invention is not limited in above-mentioned
Specific embodiments and applications field, above-mentioned specific embodiment are only schematical, directiveness, rather than restricted
's.Those of ordinary skill in the art are under the enlightenment of this specification and in the scope for not departing from the claims in the present invention and being protected
In the case of, the form of many kinds can also be made, these belong to the row of protection of the invention.
Claims (10)
1. a kind of method for improving recognition of face efficiency, it includes the following steps:
In different identification location arrangements face recognition devices, multiple face recognition device collections and identification facial image, to identification
Accuracy rate is more than one or more of face recognition devices of predetermined accuracy rate to identify that object carries out facial image as target
Filing is handled, wherein, the identification object refers to that specific identity is not required and is only through what face recognition device recognized
Object.
A kind of 2. method for improving recognition of face efficiency according to claim 1, it is characterised in that:File data with having
The static database verification and docking of identity archives, are periodically verified in filing data by the verification with the static database
True identity, the filing data for meeting identity condition change into the data of static database.
A kind of 3. method for improving recognition of face efficiency according to claim 1, it is characterised in that:Based on identification position
And/or the filing data that recognition time section draws filing processing are marked, the filing data include temporarily increased face
When file data, the interim filing data can be with the filing data filing processing.
A kind of 4. method for improving recognition of face efficiency according to claim 1, it is characterised in that:Face identification system is adopted
Collect the identification parameter of each face recognition device, identification parameter includes shooting the performance of the face recognition device of the facial image
Parameter, environmental parameter and/or the resource parameters for taking face identification system, face identification system are more than recognition accuracy predetermined
One or more of face recognition devices of accuracy rate are to identify that object carries out facial image as target and corresponding identification is joined
Number filing processing.
A kind of 5. method for improving recognition of face efficiency according to claim 4, it is characterised in that:The performance parameter bag
Resolution ratio, clarity, signal-to-noise ratio and/or the white balance parameter of face recognition device are included, the environmental parameter includes recognition of face
Identification position, identification angle, recognition of face integrity degree and/or the environmental light intensity of equipment, the money for taking face identification system
Source parameter includes taking CPU usage, the memory usage of identifying system.
A kind of 6. method for improving recognition of face efficiency according to claim 4, it is characterised in that:Given based on identification parameter
Each face recognition device sets weight coefficient, and each face recognition device is identified in the recognition result and database of facial image
View data compare acquisition recognition accuracy, recognition accuracy is multiplied by weight coefficient and obtains the weight of each face recognition device
Recognition accuracy, face identification system are more than the weight recognition accuracy one or more of faces of predetermined accuracy rate
Identification equipment is to identify that object carries out facial image filing processing as target.
A kind of 7. method for improving recognition of face efficiency according to claim 1, it is characterised in that:The identification is accurate
Rate sorts from big to small, when recognition accuracy is located at one or more face recognition devices of predefined procedure to identify object as mark
The filing for carrying out facial image and relevant identification parameter processing.
8. a kind of face identification system implemented any one of claim 1-7 and improve the method for recognition of face efficiency, its feature
It is, face identification system includes multiple face recognition devices (1) and processor (3) for being arranged in different identification positions, described
Processor include judge recognition accuracy whether more than predetermined accuracy rate determining device (8) and for using identify object as target into
The archiver (9) of pedestrian's face image filing processing.
9. a kind of face identification system as claimed in claim 8, it is characterised in that face identification system includes being used to gather knowing
The data acquisition device (2) of other parameter, processor (3) connect the face recognition device (1) and data acquisition device (2), place
Reason device (3) further include for face recognition device weight coefficient is set weight unit (4), by recognition result and database
View data compares the sequence list of the comparing unit (5) for obtaining probable value, the connection weight unit (4) and comparing unit (5)
Probable value is multiplied by weight coefficient and obtains the recognition accuracy of each face recognition device (1) from big by first (6), sequencing unit (6)
To small sequence.
10. a kind of face identification system as claimed in claim 8, it is characterised in that processor (3) includes being used to that number will to be filed
According to the checker periodically verified with the static database with identity archives, processor (3) sends the filing data that verification passes through
To the static database.A kind of method and face identification system for improving recognition of face efficiency is disclosed, improves recognition of face
The method of efficiency includes the following steps:In different identification location arrangements face recognition devices, the collection of multiple face recognition devices and
Identify facial image, people is more than recognition accuracy one or more of face recognition devices of predetermined accuracy rate to identify pair
As carrying out facial image filing processing for target, wherein, the identification object refers to that specific identity is not required and is only through
The object that face recognition device recognizes.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711183034.9A CN107977613A (en) | 2017-11-23 | 2017-11-23 | Improve the method and face identification system of recognition of face efficiency |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711183034.9A CN107977613A (en) | 2017-11-23 | 2017-11-23 | Improve the method and face identification system of recognition of face efficiency |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107977613A true CN107977613A (en) | 2018-05-01 |
Family
ID=62011131
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711183034.9A Pending CN107977613A (en) | 2017-11-23 | 2017-11-23 | Improve the method and face identification system of recognition of face efficiency |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107977613A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109783663A (en) * | 2018-12-28 | 2019-05-21 | 上海依图网络科技有限公司 | A kind of archiving method and device |
CN110532965A (en) * | 2019-08-30 | 2019-12-03 | 京东方科技集团股份有限公司 | Age recognition methods, storage medium and electronic equipment |
CN111710424A (en) * | 2020-06-19 | 2020-09-25 | 浙江新芮信息科技有限公司 | Catering personnel health monitoring method and equipment and computer readable storage medium |
CN113671589A (en) * | 2021-09-14 | 2021-11-19 | 清华大学 | Safety detection match physical system |
-
2017
- 2017-11-23 CN CN201711183034.9A patent/CN107977613A/en active Pending
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109783663A (en) * | 2018-12-28 | 2019-05-21 | 上海依图网络科技有限公司 | A kind of archiving method and device |
CN110532965A (en) * | 2019-08-30 | 2019-12-03 | 京东方科技集团股份有限公司 | Age recognition methods, storage medium and electronic equipment |
US11361587B2 (en) | 2019-08-30 | 2022-06-14 | Boe Technology Group Co., Ltd. | Age recognition method, storage medium and electronic device |
CN110532965B (en) * | 2019-08-30 | 2022-07-26 | 京东方科技集团股份有限公司 | Age identification method, storage medium and electronic device |
CN111710424A (en) * | 2020-06-19 | 2020-09-25 | 浙江新芮信息科技有限公司 | Catering personnel health monitoring method and equipment and computer readable storage medium |
CN113671589A (en) * | 2021-09-14 | 2021-11-19 | 清华大学 | Safety detection match physical system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9875392B2 (en) | System and method for face capture and matching | |
CN107808152A (en) | Lift the method and face identification system of face recognition accuracy rate | |
CN106997629B (en) | Access control method, apparatus and system | |
CN104091176B (en) | Portrait comparison application technology in video | |
CN108256459B (en) | Security check door face recognition and face automatic library building algorithm based on multi-camera fusion | |
CN107358146B (en) | Method for processing video frequency, device and storage medium | |
CN105868689B (en) | A kind of face occlusion detection method based on concatenated convolutional neural network | |
US20070174272A1 (en) | Facial Recognition in Groups | |
CN108229335A (en) | It is associated with face identification method and device, electronic equipment, storage medium, program | |
US8600121B2 (en) | Face recognition system and method | |
CN107977613A (en) | Improve the method and face identification system of recognition of face efficiency | |
US8798327B2 (en) | Method and system for people flow statistics | |
WO2017122258A1 (en) | Congestion-state-monitoring system | |
CN107832730A (en) | Improve the method and face identification system of face recognition accuracy rate | |
CN104036236B (en) | A kind of face gender identification method based on multiparameter exponential weighting | |
CN108564052A (en) | Multi-cam dynamic human face recognition system based on MTCNN and method | |
CN108009482A (en) | One kind improves recognition of face efficiency method | |
US20230368559A1 (en) | Information processing apparatus, information processing method, and non-transitory computer-readable storage medium | |
CN107230267A (en) | Intelligence In Baogang Kindergarten based on face recognition algorithms is registered method | |
CN106296879A (en) | The methods, devices and systems that flow of the people based on wireless exploration obtains | |
CN106791706A (en) | Object lock method and system | |
CN108701211A (en) | For detecting, tracking, estimating and identifying the system based on depth sense occupied in real time | |
CN207233038U (en) | Face is called the roll and number system | |
CN109637123A (en) | A kind of complexity traffic environment downlink people living things feature recognition and traffic control system | |
CN108009530A (en) | A kind of identity calibration system and method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180501 |
|
WD01 | Invention patent application deemed withdrawn after publication |