CN109711287A - Face acquisition method and Related product - Google Patents
Face acquisition method and Related product Download PDFInfo
- Publication number
- CN109711287A CN109711287A CN201811517472.9A CN201811517472A CN109711287A CN 109711287 A CN109711287 A CN 109711287A CN 201811517472 A CN201811517472 A CN 201811517472A CN 109711287 A CN109711287 A CN 109711287A
- Authority
- CN
- China
- Prior art keywords
- face
- facial image
- image
- mac address
- address list
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 105
- 230000001815 facial effect Effects 0.000 claims abstract description 195
- 238000012545 processing Methods 0.000 claims abstract description 46
- 239000000523 sample Substances 0.000 claims abstract description 36
- 230000008569 process Effects 0.000 claims description 26
- 238000004590 computer program Methods 0.000 claims description 16
- 238000013441 quality evaluation Methods 0.000 claims description 16
- 238000003860 storage Methods 0.000 claims description 13
- 238000012790 confirmation Methods 0.000 claims description 11
- 230000008859 change Effects 0.000 claims description 10
- 238000003709 image segmentation Methods 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 238000013497 data interchange Methods 0.000 claims 1
- 238000005303 weighing Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 16
- 238000004422 calculation algorithm Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 9
- 230000004048 modification Effects 0.000 description 6
- 238000012986 modification Methods 0.000 description 6
- 239000012141 concentrate Substances 0.000 description 4
- 230000001419 dependent effect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000000571 coke Substances 0.000 description 1
- 238000005314 correlation function Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/08—Testing, supervising or monitoring using real traffic
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the present application provides a kind of face acquisition method and Related product, wherein, method includes: using Wi-Fi probe technique at the first moment to progress Wi-Fi scanning in specified range, obtain the first Wi-Fi MAC Address list, face acquisition is carried out to specified range, obtain the first face image set, at the second moment using Wi-Fi probe technique to progress Wi-Fi scanning in specified range, obtain the 2nd Wi-Fi MAC Address list, 2nd Wi-Fi MAC Address list is compared with the first Wi-Fi MAC Address list, if comparison result is when there is preset increments variation in the first Wi-Fi MAC Address list, again face acquisition is carried out to specified range, obtain the second face image set, according to the first face image set pair Second face image set carries out duplicate removal processing, at least one target facial image is obtained, any facial image that target facial image is not concentrated with the first facial image matches, so, the unnecessary face duplicate removal processing bring wasting of resources is avoided, the efficiency of recognition of face is improved.
Description
Technical field
This application involves technical field of face recognition, and in particular to a kind of face acquisition method and Related product.
Background technique
It is an important problem in the repeatability in short-term of technical field of face recognition, facial recognition data acquisition.In short-term
The human face data of repeated acquisition is meaningless data, will cause more storage resource wave without human face data duplicate removal in short-term
Take, when data are presented, effect can also have a greatly reduced quality, currently, most of cached based on human face data in short-term, recognize people
By, to human face data duplicate removal in short-term is completed, reducing the efficiency of recognition of face with human face data calculating ratio in caching when face,
Also, duplicate removal process is the process for relatively expending computing resource to the face in short-term, can bring cost in actual scene application
Increase.
Summary of the invention
The embodiment of the present application provides a kind of face acquisition method and device, and the efficiency of recognition of face can be improved, also,
Avoid the unnecessary face duplicate removal processing bring wasting of resources.
The embodiment of the present application first aspect provides a kind of face acquisition method, comprising:
The first Wi-Fi is obtained to Wi-Fi scanning is carried out in specified range using Wi-Fi probe technique at the first moment
MAC Address list, the first Wi-Fi MAC Address list includes at least one MAC Address；
Face acquisition is carried out to the specified range, obtains the first face image set, first face image set includes
At least one facial image；
Second is obtained to Wi-Fi scanning is carried out in the specified range using the Wi-Fi probe technique at the second moment
Wi-Fi MAC Address list, the 2nd Wi-Fi MAC Address list includes at least one MAC Address；
The 2nd Wi-Fi MAC Address list is compared with the first Wi-Fi MAC Address list；
If comparison result is when there is preset increments variation in the first Wi-Fi MAC Address list, again to described
Specified range carries out face acquisition, the second face image set is obtained, according to first face image set to second face
Image set carries out duplicate removal processing, obtains at least one target facial image, target facial image not with first facial image
Any facial image matching concentrated.
Optionally, the corresponding electronic equipment of each MAC Address, it is described that face acquisition is carried out to the specified range,
Obtain the first face image set, it may include following steps:
Determine at least one camera in the specified range；
With determining in the first Wi-Fi MAC Address list every MAC by the first Wi-Fi MAC Address list
The corresponding position in location, obtains multiple positions；
It controls at least one described camera the multiple position is focused and shot, obtains multiple images；
Image segmentation is carried out to multiple described images, obtains multiple facial images；
Duplicate removal processing is carried out to the multiple facial image, obtains first face image set.
The embodiment of the present application second aspect provides a kind of face acquisition device, comprising:
Scanning element is obtained for using Wi-Fi probe technique to Wi-Fi scanning is carried out in specified range at the first moment
To the first Wi-Fi MAC Address list, the first Wi-Fi MAC Address list includes at least one MAC Address；
Acquisition unit, it is described the first for obtaining the first face image set to specified range progress face acquisition
Face image collection includes at least one facial image；
The scanning element, be also used to the second moment using the Wi-Fi probe technique in the specified range into
Row Wi-Fi scanning, obtains the 2nd Wi-Fi MAC Address list, the 2nd Wi-Fi MAC Address list includes at least one
MAC Address；
Comparing unit, for will the 2nd Wi-Fi MAC Address list and the first Wi-Fi MAC Address list into
Row compares；
Processing unit, if being preset increments variation occur in the first Wi-Fi MAC Address list for comparison result
When, face acquisition is carried out to the specified range again, the second face image set is obtained, according to first face image set pair
Second face image set carries out duplicate removal processing, obtains at least one target facial image, target facial image not with it is described
Any facial image matching that first facial image is concentrated.
The application third aspect provides a kind of face acquisition device, comprising: processor and memory；And one or more
A program, one or more of programs are stored in the memory, and are configured to be executed by the processor, institute
Stating program includes the instruction for the step some or all of as described in first aspect.
Fourth aspect, the embodiment of the present application provide a kind of computer readable storage medium, wherein described computer-readable
Storage medium is for storing computer program, wherein the computer program executes computer such as the embodiment of the present application the
The instruction of step some or all of described in one side.
5th aspect, the embodiment of the present application provide a kind of computer program product, wherein the computer program product
Non-transient computer readable storage medium including storing computer program, the computer program are operable to make to calculate
Machine executes the step some or all of as described in the embodiment of the present application first aspect.The computer program product can be one
A software installation packet.
Implement the embodiment of the present application, has the following beneficial effects:
As can be seen that being adopted by face acquisition method and Related product described in the embodiment of the present application at the first moment
With Wi-Fi probe technique to Wi-Fi scanning is carried out in specified range, the first Wi-Fi MAC Address list, the first Wi-Fi are obtained
MAC Address list includes at least one MAC Address, carries out face acquisition to specified range, obtains the first face image set, and first
Face image set includes at least one facial image, at the second moment using Wi-Fi probe technique to carrying out Wi- in specified range
Fi scanning, obtains the 2nd Wi-Fi MAC Address list, and the 2nd Wi-Fi MAC Address list includes at least one MAC Address, will
2nd Wi-Fi MAC Address list is compared with the first Wi-Fi MAC Address list, if comparison result is the first Wi-Fi
When occurring preset increments variation in MAC Address list, face acquisition is carried out to specified range again, obtains the second facial image
Collection carries out duplicate removal processing to the second face image set according to the first face image set, obtains at least one target facial image, mesh
Any facial image that mark facial image is not concentrated with the first facial image matches, in this way, can be judged by Wi-Fi probe technique
Personnel's variation in specified region, to judge whether to need to carry out duplicate removal processing, therefore, avoids unnecessary face duplicate removal processing
The bring wasting of resources improves the efficiency of recognition of face.
Detailed description of the invention
In order to more clearly explain the technical solutions in the embodiments of the present application, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, the accompanying drawings in the following description is some embodiments of the present application, for ability
For the those of ordinary skill of domain, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Figure 1A is a kind of system architecture schematic diagram of face acquisition method provided by the embodiments of the present application；
Figure 1B is a kind of embodiment flow diagram of face acquisition method provided by the embodiments of the present application；
Fig. 2 is a kind of embodiment flow diagram of face acquisition method provided by the embodiments of the present application；
Fig. 3 A is a kind of structural schematic diagram of face acquisition device provided by the embodiments of the present application；
Fig. 3 B is the structural representation of the modification structures of face acquisition device described in Fig. 3 A provided by the embodiments of the present application
Figure；
Fig. 3 C is the structural representation of the acquisition unit of face acquisition device described in Fig. 3 A provided by the embodiments of the present application
Figure；
Fig. 4 is a kind of example structure schematic diagram of face acquisition device provided by the embodiments of the present application.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiment is some embodiments of the present application, instead of all the embodiments.Based on this Shen
Please in embodiment, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall in the protection scope of this application.
The description and claims of this application and term " first ", " second ", " third " and " in the attached drawing
Four " etc. are not use to describe a particular order for distinguishing different objects.In addition, term " includes " and " having " and it
Any deformation, it is intended that cover and non-exclusive include.Such as it contains the process, method of a series of steps or units, be
System, product or equipment are not limited to listed step or unit, but optionally further comprising the step of not listing or list
Member, or optionally further comprising other step or units intrinsic for these process, methods, product or equipment.
Referenced herein " embodiment " is it is meant that a particular feature, structure, or characteristic described can wrap in conjunction with the embodiments
It is contained at least one embodiment of the application.It is identical that each position in the description shows that the phrase might not be each meant
Embodiment, nor the independent or alternative embodiment with other embodiments mutual exclusion.Those skilled in the art explicitly and
Implicitly understand, embodiment described herein can be combined with other embodiments.
In order to better understand a kind of face acquisition method and Related product provided by the embodiments of the present application, below first to this
The system architecture of the applicable face acquisition method of application embodiment is described.A refering to fig. 1, Figure 1A are that the embodiment of the present application mentions
The system architecture schematic diagram of the face acquisition method of confession.As shown in Figure 1A, system architecture may include one or more servers
And multiple electronic equipments, in which:
Server can include but is not limited to background server, component server, face acquisition system server or face
Acquisition software server etc., server can be communicated by internet with multiple electronic equipments.Server acquires face
As a result it is sent to electronic equipment.
Electronic equipment in the embodiment of the present application can include but is not limited to any hand based on intelligent operating system
Formula electronic product is held, the input equipments such as keyboard, dummy keyboard, touch tablet, touch screen and voice-operated device can be passed through with user
To carry out human-computer interaction, smart phone, tablet computer, PC etc..Wherein, intelligent operating system includes but is not limited to
It is any to enrich the operating system of functions of the equipments by providing various mobile applications to mobile device, such as Android (Android),
iOSTM, Windows Phone etc..
Face acquisition device or electronic equipment described by the embodiment of the present application may include smart phone (such as Android
Mobile phone, iOS mobile phone, Windows Phone mobile phone etc.), tablet computer, palm PC, laptop, mobile internet device
(MID, Mobile Internet Devices) or wearable device etc., above-mentioned is only citing, and non exhaustive, includes but unlimited
In above-mentioned apparatus, certainly, above-mentioned face acquisition device can also be server, in face acquisition device it is mountable at least one
Wi-Fi probe.
It should be noted that the system architecture of face acquisition method provided by the present application is not limited to shown in Figure 1A.
Figure 1B is please referred to, is a kind of flow diagram of the embodiment of face acquisition method provided by the embodiments of the present application.
Face acquisition method as described in this embodiment, comprising the following steps:
101, it uses Wi-Fi probe technique to Wi-Fi scanning is carried out in specified range at the first moment, obtains the first Wi-
Fi MAC Address list, the first Wi-Fi MAC Address list includes at least one MAC Address.
Wherein, specified range can be specified by user, alternatively, some specific spatial dimension can be defaulted as, the first moment can
For a certain moment in the short time, it can specifically be specified by user or system default, face acquisition device can be adopted at the first moment
With Wi-Fi probe technique to Wi-Fi scanning is carried out in specified range, if there is at least one other equipment to open Wi-Fi function,
The Wi-Fi MAC Address of at least one equipment then can be obtained, thus, the MAC Address of the equipment obtained by scanning obtains the first Wi-
Fi MAC Address list includes at least one MAC Address in the first Wi-Fi MAC Address list.
102, face acquisition is carried out to the specified range, obtains the first face image set, first face image set
Including at least one facial image.
Wherein, face acquisition device carries out face acquisition by personnel of the camera to specified range, thus, included
First face image set of multiple facial images of specified range personnel, specified range can be specified by user, alternatively, can default
For some specific range (for example, in coverage of camera).
Optionally, described that face acquisition is carried out to the specified range in above-mentioned steps 102, obtain the first facial image
Collection, it may include following steps:
21, the specified range is shot, obtains target image；
22, image segmentation is carried out to the target image, obtains P character image, P is positive integer；
23, recognition of face is carried out to the P character image, obtains Q facial image and P-Q inhuman face images, Q is
Positive integer no more than P；
24, target following and recognition of face are carried out to the P-Q inhuman face images, obtains P-Q facial image；
25, using the Q facial image and the P-Q facial image as first face image set.
Wherein, the camera of face acquisition device can obtain more in the specified range to shooting in specified range
Target image is opened, it may be comprising multiple facial images or character image or scene image, therefore in multiple target images
Image dividing processing can be carried out for multiple target images, obtain P character image, P is positive integer.It specifically, can be for every
(one or more) the personage's prospect for opening target image is confined, can if personage's foreground image is not present in target image
Directly reject the target image；If there are personage's foreground images in target image, personage's prospect and background can be carried out respectively
Modeling, each of target image pixel can all be connect with personage's prospect or background node, if two adjacent nodes
It is not belonging to same personage's prospect or background, then the side between two nodes can be cut off, thus, distinguish personage's foreground image
And background image, P character image is obtained, in this way, can be used to reject the letter of the background in target image using image partition method
The interference of breath, to improve the efficiency of recognition of face.
In addition, face acquisition device after obtaining P character image, may include face figure in the P character image
Picture can carry out recognition of face to the P character image, obtain Q facial image and P-Q inhuman face images, and Q is no more than P
Positive integer, then, face acquisition device can continue to P-Q inhuman face images based on the algorithm of target following carry out target with
Track, after target following, the facial image of P-Q inhuman face image is can be obtained in face acquisition device, for the facial image,
Recognition of face can be used, obtain the corresponding facial image of P-Q personnel, and by above-mentioned Q facial image and P-Q face figure
As being used as the first face image set, thus, it as much as possible can obtain the face of all personnel in specified range.
Wherein, the algorithm of target following may include following at least one: tracking-by-detection track algorithm,
Tracking-Learning-Detection track algorithm, Struck algorithm etc., are not limited thereto.
Optionally, the corresponding electronic equipment of each MAC Address, above-mentioned steps 102 carry out people to the specified range
Face acquisition, obtains the first face image set, it may include following steps:
26, at least one camera in the specified range is determined；
27, it is determined by the first Wi-Fi MAC Address list each in the first Wi-Fi MAC Address list
The corresponding position of MAC Address, obtains multiple positions；
28, it controls at least one described camera the multiple position is focused and shot, obtains multiple images；
29, image segmentation is carried out to multiple described images, obtains multiple facial images, and to the multiple facial image into
Row duplicate removal processing obtains first face image set.
Wherein, due to the corresponding electronic equipment of a MAC Address, electronic equipment may then be carried by user, because
This includes multiple MAC Address in the first Wi-Fi MAC Address list, and Wi-Fi probe technique is to carrying out Wi-Fi in specified range
When scanning, the position of the electronic equipment of each MAC Address also can recorde, alternatively, signal strength can be oriented every in turn
The position of a electronic equipment obtains multiple positions, in turn, can control at least one above-mentioned camera and carries out pair to multiple positions
Coke is simultaneously shot, and obtains multiple images, specifically, can be to control at least one camera shooting every prefixed time interval in preset time period
Head is focused and is shot to multiple positions, multiple images are obtained, and carries out image segmentation to multiple images, obtains multiple face figures
Picture is matched these facial images two-by-two, removes repeater's face image, obtains the first face image set, in this way, can be with
Clearly and accurately collect facial image.
103, it uses the Wi-Fi probe technique to Wi-Fi scanning is carried out in the specified range at the second moment, obtains
2nd Wi-Fi MAC Address list, the 2nd Wi-Fi MAC Address list includes at least one MAC Address.
Wherein, specified range can be specified by user, alternatively, some specific range can be defaulted as, specified range can with it is upper
It is consistent to state step 101, Wi-Fi probe technique can be used to Wi-Fi scanning is carried out in specified range at the second moment, if having at least
One other equipment opens Wi-Fi function, then the Wi-Fi MAC Address of at least one equipment can be obtained, thus, obtain second
Wi-Fi MAC Address list includes at least one MAC Address in the 2nd Wi-Fi MAC Address list, wherein the second moment can
For the predetermined time for being later than first moment user's self-setting, specifically, Wi-Fi probe technique pair is can be used in face acquisition device
Wi-Fi scanning is carried out in specified range, obtains the 2nd Wi-Fi MAC Address list, wherein the 2nd Wi-Fi MAC Address list
In MAC Address can with the first Wi-Fi MAC Address can be consistent or inconsistent.
104, the 2nd Wi-Fi MAC Address list is compared with the first Wi-Fi MAC Address list.
Wherein, the MAC Address in the 2nd Wi-Fi MAC Address list and the first Wi-Fi MAC Address list may be consistent
Or it is inconsistent, for example, the 2nd Wi-Fi MAC Address list is than the MAC Address in the first Wi-Fi MAC Address list compared to can
It can increase, that is to say, that may have new MAC Address, alternatively, MAC Address may be reduced, alternatively, the 2nd Wi-Fi
MAC Address in MAC Address list and the first Wi-Fi MAC Address list, which does not increase, not to be subtracted, that is to say, that may be unchanged, tool
Body, can the 2nd Wi-Fi MAC Address list be compared with the first Wi-Fi MAC Address list, obtain increment variation or
Decrement variation or unconverted comparison result, because the MAC Address of each equipment may be unique, and every equipment
MAC Address is different from, and therefore, the increase and decrease of personnel in specified range can be judged by the variation of MAC Address.
It is again right 105, if comparison result is preset increments variation occurs in the first Wi-Fi MAC Address list
The specified range carries out face acquisition, the second face image set is obtained, according to first face image set to described second
Face image set carries out duplicate removal processing, obtains at least one target facial image, target facial image not with first face
Any facial image matching in image set.
Wherein, preset increments variation can be by user's sets itself or system default, for example, it is new to increase at least one
MAC Address, specifically, preset increments variation can be the 2nd Wi-Fi MAC Address list than in the first Wi-Fi MAC Address list
MAC Address compare, increase a MAC Address, a is positive integer, alternatively, preset increments variation can be the second Wi-Fi MAC
Occur being not present in the MAC Address of the first Wi-Fi MAC Address list in address list.Specifically, by the 2nd Wi-Fi
After MAC Address list is compared with the MAC Address in the first Wi-Fi MAC Address list, face acquisition device can be again
For specified range personnel carry out face acquisition, obtain the second face image set, can by the second face image set with it is the first
The algorithm of face image centralized procurement duplicate removal processing carries out duplicate removal processing, obtains any facial image that do not concentrate with the first facial image
The facial image of personnel at least one matched specified region, thus, weed out the first face image set and the second face figure
The facial image to match in image set improves the efficiency of duplicate removal processing in face acquisition.
Wherein, the algorithm of duplicate removal processing may include following one kind: OpenCV image processing algorithm, based on the fast of motion match
Algorithm of duplicate removal etc. is compared based on color histogram and LBP histogram feature in fast Duplicate Removal Algorithm, it is not limited here.
Optionally, above-mentioned steps 105, it is described that second face image set is carried out according to first face image set
Duplicate removal processing obtains at least one target facial image, it may include following steps:
51, each people that each facial image and second facial image concentrated first facial image are concentrated
Face image is matched, and multiple matching values are obtained；
52, the matching value for being greater than preset threshold is chosen from the multiple matching value, obtains at least one object matching value；
53, at least one described corresponding facial image of object matching value is determined；
54, at least one described corresponding facial image of object matching value is excluded from second facial image concentration,
Obtain at least one described target facial image.
Wherein, each facial image and the second facial image that face acquisition device can concentrate the first facial image are concentrated
Each facial image carry out matching duplicate removal, specifically, can by determined using similarity measurement the first facial image concentrate
Each facial image and each facial image for concentrating of the second facial image in corresponding relationship, for example, pixel-by-pixel the
The gray matrix of one realtime graphic window with a certain size of each facial image that two facial images are concentrated, and it is the first
All window gray scale arrays for each facial image that face image is concentrated, are scanned for matching, be obtained by method for measuring similarity
Into each image, the probability value of matched window gray scale array is as matching value, to obtain multiple matching values.
In addition, preset threshold can be user's sets itself or system default, after obtaining multiple matching values, can with it is pre-
If threshold value is compared, if more than preset threshold, then it is assumed that the matching value is object matching value, to obtain multiple object matchings
Value, then, it is determined that the corresponding facial image of object matching value is target facial image, to obtain multiple target face figures
Therefore picture weeds out the first face image set and the second facial image concentrates the facial image to match, improve face acquisition
The efficiency of duplicate removal processing in the process.
Wherein, similarity measurement may include following one kind: correlation function, covariance function, poor quadratic sum, poor absolute value and
Etc. extreme value is estimated, it is not limited thereto.
Optionally, above-mentioned steps 51, each facial image and described second that first facial image is concentrated
Each facial image that facial image is concentrated is matched, and obtains multiple matching values, it may include following steps:
A1, the image quality evaluation values i, the facial image i of facial image i is obtained as first facial image concentration
Any facial image；
A2, according to the mapping relations between preset image quality evaluation values and matching threshold, determine described image quality
The corresponding object matching threshold value of evaluation of estimate i；
A3, contours extract is carried out to the facial image i, obtains the first circumference；
A4, feature point extraction is carried out to the facial image i, obtains fisrt feature point set；
A5, first circumference is matched with the second circumference of facial image j, obtains the first matching
Value, the facial image j are any facial image that second facial image is concentrated；
A6, the fisrt feature point set is matched with the second feature point set of the facial image j, obtains second
With value；
A7, object matching value is determined according to first matching value, second matching value.
Wherein, in face recognition process, success or not is heavily dependent on the picture quality of facial image, therefore,
Image quality evaluation can be carried out to any facial image that the first facial image is concentrated, obtain multiple images quality evaluation value, and
With the memory of face identification device specifically, image quality evaluation index can be used to collected first face in storage
Multiple facial images in image set carry out image quality evaluation, obtain multiple images quality evaluation value, image quality evaluation refers to
Mark may include, but are not limited to: average gray, mean square deviation, entropy, edge conservation degree, signal-to-noise ratio etc., the figure that may be defined as
Image quality amount evaluation of estimate is bigger, then picture quality is better.
In addition, the mapping that can store between preset image quality evaluation values and matching threshold in face acquisition device is closed
System, in turn, determines that the corresponding object matching threshold value of objective image quality evaluation of estimate i on this basis can according to the mapping relations
Contours extract is carried out to target facial image i, obtains the first circumference, feature point extraction is carried out to target facial image i, is obtained
To fisrt feature point set, by the second circumference of the first circumference and the second any facial image j of facial image kind heat into
Row matching, obtains the first matching value, fisrt feature point set is matched with the second feature point set of facial image j, obtains the
Two matching values determine object matching value according to the first matching value, the second matching value in turn, for example, can be in face identification device
The mapping relations between matching value and weighted value pair are stored in advance, obtain corresponding first weight coefficient of the first matching value, and
Corresponding second weight coefficient of second matching value, object matching value=first matching value * the+the second matching value of the first weight coefficient *
Second weight coefficient, in this way, dynamic regulation face matching process, is conducive to promote recognition of face efficiency.
In addition, the algorithm of contours extract can be following at least one: Hough transformation, canny operator etc. are not done herein
Limit, the algorithm of feature point extraction can be following at least one: Harris angle point, scale invariant feature extract transformation (scale
Invariant feature transform, SIFT) etc., it is not limited here.
Optionally, it after above-mentioned steps 104, can comprise the further steps of:
If the comparison result is that the default decrement of appearance changes or is unchanged in the Wi-Fi MAC Address list,
Duplicate removal process is skipped, face collection process is completed in confirmation.
Wherein, presetting decrement variation can be by user's self-setting or system default, for example, reducing at least one MAC
Address, if the 2nd Wi-Fi MAC Address list is compared with the first Wi-Fi MAC Address list, obtained comparing result
For decrement variation or it is unchanged when, that is to say, that the personnel in specified region reduce, and do not subtract alternatively, not increasing, can be without
Face collection process is completed in duplicate removal processing, confirmation, since the MAC Address of every equipment is different from and uniquely, can pass through
The variation of MAC Address judges the increasing of personnel in specified range or subtracts or unchanged, thus, improve the efficiency of recognition of face.
As can be seen that being carried out using Wi-Fi probe technique in specified range by the embodiment of the present application at the first moment
Wi-Fi scanning, obtains the first Wi-Fi MAC Address list, and the first Wi-Fi MAC Address list includes at least one MAC Address,
Face acquisition is carried out to specified range, obtains the first face image set, the first face image set includes at least one facial image,
At the second moment using Wi-Fi probe technique to Wi-Fi scanning is carried out in specified range, the 2nd Wi-Fi MAC Address column are obtained
Table, the 2nd Wi-Fi MAC Address list includes at least one MAC Address, by the 2nd Wi-Fi MAC Address list and the first Wi-
Fi MAC Address list is compared, if is there is preset increments variation in the first Wi-Fi MAC Address list in comparison result,
Again face acquisition is carried out to specified range, obtains the second face image set, according to the first face image set to the second face figure
Image set carries out duplicate removal processing, obtains at least one target facial image, what target facial image was not concentrated with the first facial image
Any facial image matching, in this way, can judge that the personnel in specified region change by Wi-Fi probe technique, to judge whether
It needs to carry out duplicate removal processing, with this, avoids the unnecessary face duplicate removal processing bring wasting of resources, improve recognition of face
Efficiency.
Consistent with the abovely, referring to Fig. 2, being a kind of embodiment stream of face acquisition method provided by the embodiments of the present application
Journey schematic diagram.Face acquisition method as described in this embodiment, comprising the following steps:
201, it uses Wi-Fi probe technique to Wi-Fi scanning is carried out in specified range at the first moment, obtains the first Wi-
Fi MAC Address list, the first Wi-Fi MAC Address list includes at least one MAC Address.
202, face acquisition is carried out to the specified range, obtains the first face image set, first face image set
Including at least one facial image.
203, it uses the Wi-Fi probe technique to Wi-Fi scanning is carried out in the specified range at the second moment, obtains
2nd Wi-Fi MAC Address list, the 2nd Wi-Fi MAC Address list includes at least one MAC Address.
204, the 2nd Wi-Fi MAC Address list is compared with the first Wi-Fi MAC Address list.
It is again right 205, if comparison result is preset increments variation occurs in the first Wi-Fi MAC Address list
The specified range carries out face acquisition, the second face image set is obtained, according to first face image set to described second
Face image set carries out duplicate removal processing, obtains at least one target facial image, target facial image not with first face
Any facial image matching in image set.
If 206, the comparison result is to occur default decrement variation or unchanged in the Wi-Fi MAC Address list
When, duplicate removal process is skipped, face collection process is completed in confirmation.
Optionally, the specific descriptions of above-mentioned steps 201- step 206 can refer to face acquisition method described in Figure 1B
The correspondence step of step 101- step 105, details are not described herein.
As can be seen that being carried out using Wi-Fi probe technique in specified range by the embodiment of the present application at the first moment
Wi-Fi scanning, obtains the first Wi-Fi MAC Address list, and the first Wi-Fi MAC Address list includes at least one MAC Address,
Face acquisition is carried out to specified range, obtains the first face image set, the first face image set includes at least one facial image,
At the second moment using Wi-Fi probe technique to Wi-Fi scanning is carried out in specified range, the 2nd Wi-Fi MAC Address column are obtained
Table, the 2nd Wi-Fi MAC Address list includes at least one MAC Address, by the 2nd Wi-Fi MAC Address list and the first Wi-
Fi MAC Address list is compared, if is there is preset increments variation in the first Wi-Fi MAC Address list in comparison result,
Again face acquisition is carried out to specified range, obtains the second face image set, according to the first face image set to the second face figure
Image set carries out duplicate removal processing, obtains at least one target facial image, what target facial image was not concentrated with the first facial image
Any facial image matching, if comparison result is to occur default decrement variation in the Wi-Fi MAC Address list or without change
When change, duplicate removal process is skipped, face collection process is completed in confirmation, in this way, can judge specified region by Wi-Fi probe technique
Personnel's variation, without carrying out duplicate removal processing, with this, avoids unnecessary when decrement, which occur, in personnel to change or is unchanged
The face duplicate removal processing bring wasting of resources, improves the efficiency of recognition of face.
Consistent with the abovely, specific as follows the following are the device for implementing above-mentioned face acquisition method:
Fig. 3 A is please referred to, is a kind of example structure schematic diagram of face acquisition device provided by the embodiments of the present application.This
Face acquisition device described in embodiment, comprising: scanning element 301, acquisition unit 302, comparing unit 303 and processing are single
Member 304, specific as follows:
Scanning element 301, for the first moment using Wi-Fi probe technique in specified range carry out Wi-Fi scanning,
The first Wi-Fi MAC Address list is obtained, the first Wi-Fi MAC Address list includes at least one MAC Address, second
Moment obtains the 2nd Wi-Fi MAC Address to Wi-Fi scanning is carried out in the specified range using the Wi-Fi probe technique
List, the 2nd Wi-Fi MAC Address list includes at least one MAC Address；
Acquisition unit 302 obtains the first face image set for carrying out face acquisition to the specified range, and described the
One face image set includes at least one facial image；
The scanning element 301 is also used at the second moment using the Wi-Fi probe technique in the specified range
Wi-Fi scanning is carried out, obtains the 2nd Wi-Fi MAC Address list, the 2nd Wi-Fi MAC Address list includes at least one
MAC Address；
Comparing unit 303, for arranging the 2nd Wi-Fi MAC Address list and the first Wi-Fi MAC Address
Table is compared；
Processing unit 304, if being preset increments change occur in the first Wi-Fi MAC Address list for comparison result
When change, face acquisition is carried out to the specified range again, the second face image set is obtained, according to first face image set
Duplicate removal processing is carried out to second face image set, obtains at least one target facial image, target facial image not with institute
State any facial image matching of the first facial image concentration.
Wherein, above-mentioned scanning element 301 can be used for realizing method described in above-mentioned steps 101,103, acquisition unit 302
It can be used for realizing method described in above-mentioned steps 102, above-mentioned comparing unit 303 can be used for realizing described by above-mentioned steps 104
Method, above-mentioned processing unit 304 can be used for realizing method described in above-mentioned steps 105, so analogizes below.
Optionally, such as Fig. 3 B, Fig. 3 B is the modification structures of face acquisition device described in Fig. 3 A, compared with Fig. 3 A
Compared with can also include: confirmation unit 305, wherein
Confirmation unit 305, if being to occur default decrement in the Wi-Fi MAC Address list to become for the comparison result
When changing or is unchanged, duplicate removal process is skipped, face collection process is completed in confirmation.
Optionally, if Fig. 3 C, Fig. 3 C are the specific thin of the acquisition unit 302 in face acquisition device described in Fig. 3 A
Change structure, the acquisition unit 302 can include: shooting module 3021, segmentation module 3022, identification module 3023, tracking module
3024 and determining module 3025, specific as follows:
Shooting module 3021 obtains target image for shooting to the specified range；
Divide module 3022, for carrying out image segmentation to the target image, obtains P character image, P is positive whole
Number；
Identification module 3023 obtains Q facial image and P-Q for carrying out recognition of face to the P character image
Inhuman face image, Q are the positive integer no more than P；
Tracking module 3024 obtains P- for carrying out target following and recognition of face to the P-Q inhuman face images
Q facial image；
Determining module 3025, for using the Q facial image and the P-Q facial image as first face
Image set.
As can be seen that using Wi-Fi probe at the first moment by face acquisition device described in the embodiment of the present application
Technology obtains the first Wi-Fi MAC Address list, the first Wi-Fi MAC Address list to Wi-Fi scanning is carried out in specified range
Including at least one MAC Address, face acquisition is carried out to specified range, obtains the first face image set, the first face image set
Including at least one facial image, obtained using Wi-Fi probe technique to Wi-Fi scanning is carried out in specified range at the second moment
To the 2nd Wi-Fi MAC Address list, the 2nd Wi-Fi MAC Address list includes at least one MAC Address, by the 2nd Wi-Fi
MAC Address list is compared with the first Wi-Fi MAC Address list, if comparison result is the first Wi-Fi MAC Address list
In when there is preset increments variation, face acquisition is carried out to specified range again, the second face image set is obtained, according to the first
Face image collection carries out duplicate removal processing to the second face image set, obtains at least one target facial image, target facial image is not
Any facial image concentrated with the first facial image matches, in this way, can judge the people in specified region by Wi-Fi probe technique
Member's variation, with this, avoids unnecessary face duplicate removal processing bring resource wave to judge whether to need to carry out duplicate removal processing
Take, improves the efficiency of recognition of face.
It is understood that the function of each program module of the face acquisition device of the present embodiment can be according to above method reality
The method specific implementation in example is applied, specific implementation process is referred to the associated description of above method embodiment, herein no longer
It repeats.
Consistent with the abovely, referring to Fig. 4, being a kind of embodiment knot of face identification device provided by the embodiments of the present application
Structure schematic diagram.Face acquisition device as described in this embodiment, comprising: at least one input equipment 1000；At least one is defeated
Equipment 2000 out；At least one processor 3000, such as CPU；With memory 4000, above-mentioned input equipment 1000, output equipment
2000, processor 3000 and memory 4000 are connected by bus 5000.
Wherein, above-mentioned input equipment 1000 concretely touch panel, physical button or mouse.
Above-mentioned output equipment 2000 concretely display screen.
Above-mentioned memory 4000 can be high speed RAM memory, can also be nonvolatile storage (non-volatile
), such as magnetic disk storage memory.Above-mentioned memory 4000 is used to store a set of program code, above-mentioned input equipment 1000, defeated
Equipment 2000 and processor 3000 are used to call the program code stored in memory 4000 out, perform the following operations:
Above-mentioned processor 3000, is used for:
The first Wi-Fi is obtained to Wi-Fi scanning is carried out in specified range using Wi-Fi probe technique at the first moment
MAC Address list, the first Wi-Fi MAC Address list includes at least one MAC Address；
Face acquisition is carried out to the specified range, obtains the first face image set, first face image set includes
At least one facial image；
Second is obtained to Wi-Fi scanning is carried out in the specified range using the Wi-Fi probe technique at the second moment
Wi-Fi MAC Address list, the 2nd Wi-Fi MAC Address list includes at least one MAC Address；
The 2nd Wi-Fi MAC Address list is compared with the first Wi-Fi MAC Address list；
If comparison result is when there is preset increments variation in the first Wi-Fi MAC Address list, again to described
Specified range carries out face acquisition, the second face image set is obtained, according to first face image set to second face
Image set carries out duplicate removal processing, obtains at least one target facial image, target facial image not with first facial image
Any facial image matching concentrated.
In a possible example, above-mentioned processor 3000 is also used to:
If the comparison result is that the default decrement of appearance changes or is unchanged in the Wi-Fi MAC Address list,
Duplicate removal process is skipped, face collection process is completed in confirmation.
In a possible example, face acquisition is carried out to the specified range described, obtains the first facial image
Collection aspect, above-mentioned processor 3000 are specifically used for:
The specified range is shot, target image is obtained；
Image segmentation is carried out to the target image, obtains P character image, P is positive integer；
Recognition of face is carried out to the P character image, obtains Q facial image and P-Q inhuman face images, Q is not
Positive integer greater than P；
Target following and recognition of face are carried out to the P-Q inhuman face images, obtain P-Q facial image；
Using the Q facial image and the P-Q facial image as first face image set.
In a possible example, it is described according to first face image set to second face image set into
Row duplicate removal processing, in terms of obtaining at least one target facial image, above-mentioned processor 3000 is specifically used for:
Each face that each facial image and second facial image that first facial image is concentrated are concentrated
Image is matched, and multiple matching values are obtained；
The matching value for being greater than preset threshold is chosen from the multiple matching value, obtains at least one object matching value；
Determine at least one described corresponding facial image of object matching value；
At least one described corresponding facial image of object matching value is excluded from second facial image concentration, is obtained
At least one described target facial image.
In a possible example, in each facial image and second people for concentrating first facial image
Each facial image that face image is concentrated is matched, and in terms of obtaining multiple matching values, above-mentioned processor 3000 is specifically used for:
The image quality evaluation values i, the facial image i for obtaining facial image i are what first facial image was concentrated
Any facial image；
According to the mapping relations between preset image quality evaluation values and matching threshold, described image quality evaluation is determined
The corresponding object matching threshold value of value i；
Contours extract is carried out to the facial image i, obtains the first circumference；
Feature point extraction is carried out to the facial image i, obtains fisrt feature point set；
First circumference is matched with the second circumference of facial image j, obtains the first matching value, institute
Stating facial image j is any facial image that second facial image is concentrated；
The fisrt feature point set is matched with the second feature point set of the facial image j, obtains the second matching
Value；
Object matching value is determined according to first matching value, second matching value.
The embodiment of the present application also provides a kind of computer storage medium, wherein the computer storage medium can be stored with journey
Sequence, the program include some or all of any face acquisition method recorded in above method embodiment step when executing
Suddenly.
Although the application is described in conjunction with each embodiment herein, however, implementing the application claimed
In the process, those skilled in the art are by checking the attached drawing, disclosure and the appended claims, it will be appreciated that and it is real
Other variations of the existing open embodiment.In the claims, " comprising " (comprising) word is not excluded for other compositions
Part or step, "a" or "an" are not excluded for multiple situations.Claim may be implemented in single processor or other units
In several functions enumerating.Mutually different has been recited in mutually different dependent certain measures, it is not intended that these are arranged
It applies to combine and generates good effect.
It will be understood by those skilled in the art that embodiments herein can provide as method, apparatus (equipment) or computer journey
Sequence product.Therefore, complete hardware embodiment, complete software embodiment or combining software and hardware aspects can be used in the application
The form of embodiment.Moreover, it wherein includes the calculating of computer usable program code that the application, which can be used in one or more,
The computer program implemented in machine usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.Computer program is stored/distributed in suitable medium, is provided together with other hardware or as the one of hardware
Part can also use other distribution forms, such as pass through the wired or wireless telecommunication system of Internet or other.
The application be referring to the embodiment of the present application method, apparatus (equipment) and computer program product flow chart with/
Or block diagram describes.It should be understood that each process that can be realized by computer program instructions in flowchart and/or the block diagram and/
Or the combination of the process and/or box in box and flowchart and/or the block diagram.It can provide these computer program instructions
To general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices processor to generate one
A machine so that by the instruction that the processor of computer or other programmable data processing devices executes generate for realizing
The 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 spy
Determine 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 or
The 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 counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Although the application is described in conjunction with specific features and embodiment, it is clear that, do not departing from this Shen
In the case where spirit and scope please, it can be carry out various modifications and is combined.Correspondingly, the specification and drawings are only institute
The exemplary illustration for the application that attached claim is defined, and be considered as covered within the scope of the application any and all and repair
Change, change, combining or equivalent.Obviously, those skilled in the art the application can be carried out various modification and variations without
It is detached from spirit and scope.If in this way, these modifications and variations of the application belong to the claim of this application and its
Within the scope of equivalent technologies, then the application is also intended to include these modifications and variations.
Claims (10)
1. a kind of face acquisition method characterized by comprising
At the first moment using Wi-Fi probe technique to Wi-Fi scanning is carried out in specified range, with obtaining the first Wi-Fi MAC
Location list, the first Wi-Fi MAC Address list includes at least one MAC Address；
Face acquisition is carried out to the specified range, obtains the first face image set, first face image set includes at least
One facial image；
The 2nd Wi- is obtained to Wi-Fi scanning is carried out in the specified range using the Wi-Fi probe technique at the second moment
Fi MAC Address list, the 2nd Wi-Fi MAC Address list includes at least one MAC Address；
The 2nd Wi-Fi MAC Address list is compared with the first Wi-Fi MAC Address list；
If comparison result is when there is preset increments variation in the first Wi-Fi MAC Address list, again to described specified
Range carries out face acquisition, the second face image set is obtained, according to first face image set to second facial image
Collection carries out duplicate removal processing, obtains at least one target facial image, and target facial image is not concentrated with first facial image
Any facial image matching.
2. the method according to claim 1, wherein the method also includes:
If the comparison result is when occurring default decrement in the Wi-Fi MAC Address list to change or is unchanged, to skip
Face collection process is completed in duplicate removal process, confirmation.
3. weighing method described in wanting 1 or 2 according to right, which is characterized in that it is described that face acquisition is carried out to the specified range, it obtains
To the first face image set, comprising:
The specified range is shot, target image is obtained；
Image segmentation is carried out to the target image, obtains P character image, P is positive integer；
Recognition of face is carried out to the P character image, obtains Q facial image and P-Q inhuman face images, Q is no more than P
Positive integer；
Target following and recognition of face are carried out to the P-Q inhuman face images, obtain P-Q facial image；
Using the Q facial image and the P-Q facial image as first face image set.
4. method according to claim 1-3, which is characterized in that described according to first face image set pair
Second face image set carries out duplicate removal processing, obtains at least one target facial image, comprising:
Each facial image that each facial image and second facial image that first facial image is concentrated are concentrated
It is matched, obtains multiple matching values；
The matching value for being greater than preset threshold is chosen from the multiple matching value, obtains at least one object matching value；
Determine at least one described corresponding facial image of object matching value；
At least one described corresponding facial image of object matching value is excluded from second facial image concentration, is obtained described
At least one target facial image.
5. according to the method described in claim 4, it is characterized in that, each face that first facial image is concentrated
Image is matched with each facial image that second facial image is concentrated, and obtains multiple matching values, comprising:
The image quality evaluation values i, the facial image i for obtaining facial image i are any that first facial image is concentrated
Facial image；
According to the mapping relations between preset image quality evaluation values and matching threshold, described image quality evaluation value i is determined
Corresponding object matching threshold value；
Contours extract is carried out to the facial image i, obtains the first circumference；
Feature point extraction is carried out to the facial image i, obtains fisrt feature point set；
First circumference is matched with the second circumference of facial image j, obtains the first matching value, the people
Face image j is any facial image that second facial image is concentrated；
The fisrt feature point set is matched with the second feature point set of the facial image j, obtains the second matching value；
Object matching value is determined according to first matching value, second matching value.
6. a kind of face acquisition device characterized by comprising
Scanning element, at the first moment using Wi-Fi probe technique to Wi-Fi scanning is carried out in specified range, obtain the
One Wi-Fi MAC Address list, the first Wi-Fi MAC Address list includes at least one MAC Address；
Acquisition unit obtains the first face image set, the first face figure for carrying out face acquisition to the specified range
Image set includes at least one facial image；
The scanning element is also used at the second moment using the Wi-Fi probe technique to carrying out Wi- in the specified range
Fi scanning, obtain the 2nd Wi-Fi MAC Address list, and the 2nd Wi-Fi MAC Address list includes at least one MAC
Location；
Comparing unit, for comparing the 2nd Wi-Fi MAC Address list with the first Wi-Fi MAC Address list
It is right；
Processing unit, if being weight when there is preset increments variation in the first Wi-Fi MAC Address list for comparison result
Face acquisition newly is carried out to the specified range, the second face image set is obtained, according to first face image set to described
Second face image set carries out duplicate removal processing, obtains at least one target facial image, and target facial image is not with described first
Any facial image matching that facial image is concentrated.
7. device according to claim 6, which is characterized in that described device further include:
Confirmation unit, if for the comparison result be occur in the Wi-Fi MAC Address list default decrement variation or
When unchanged, duplicate removal process is skipped, face collection process is completed in confirmation.
8. device according to claim 6 or 7, which is characterized in that face acquisition is carried out to the specified range described,
In terms of obtaining the first face image set, the acquisition unit is specifically used for:
The specified range is shot, target image is obtained；
Image segmentation is carried out to the target image, obtains P character image, P is positive integer；
Recognition of face is carried out to the P character image, obtains Q facial image and P-Q inhuman face images, Q is no more than P
Positive integer；
Target following and recognition of face are carried out to the P-Q inhuman face images, obtain P-Q facial image；
Using the Q facial image and the P-Q facial image as first face image set.
9. a kind of face acquisition device, which is characterized in that including processor, memory, the memory for store one or
Multiple programs, and be configured to be executed by the processor, described program includes for executing such as any one of claim 1-5 institute
The instruction for the step in method stated.
10. a kind of computer readable storage medium, which is characterized in that storage is used for the computer program of electronic data interchange,
In, the computer program makes computer execute the method according to claim 1 to 5.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811517472.9A CN109711287B (en) | 2018-12-12 | 2018-12-12 | Face acquisition method and related product |
| PCT/CN2019/114729 WO2020119315A1 (en) | 2018-12-12 | 2019-10-31 | Face acquisition method and related product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811517472.9A CN109711287B (en) | 2018-12-12 | 2018-12-12 | Face acquisition method and related product |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109711287A true CN109711287A (en) | 2019-05-03 |
| CN109711287B CN109711287B (en) | 2020-11-24 |
Family
ID=66255670
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811517472.9A Active CN109711287B (en) | 2018-12-12 | 2018-12-12 | Face acquisition method and related product |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109711287B (en) |
| WO (1) | WO2020119315A1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020119315A1 (en) * | 2018-12-12 | 2020-06-18 | 深圳云天励飞技术有限公司 | Face acquisition method and related product |
| CN111476105A (en) * | 2020-03-17 | 2020-07-31 | 深圳力维智联技术有限公司 | Face data cleaning method, device and equipment |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112733647A (en) * | 2020-12-30 | 2021-04-30 | 浙江大华技术股份有限公司 | Method, analysis server and system based on MAC address and face information binding |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100141794A1 (en) * | 2008-12-04 | 2010-06-10 | Nintendo Co., Ltd. | Program and information processing device allowing storage of information for identifying user |
| WO2011021259A1 (en) * | 2009-08-21 | 2011-02-24 | Sony Ericsson Mobile Communications Ab | Information terminal, information control method for an information terminal, and information control program |
| CN104992075A (en) * | 2015-07-30 | 2015-10-21 | 浙江宇视科技有限公司 | Multi-source information correlation method based on big data |
| CN105243373A (en) * | 2015-10-27 | 2016-01-13 | 北京奇虎科技有限公司 | Method for filtering facial images to prevent repeated snapshot, server, intelligent monitoring device and system |
| CN105790955A (en) * | 2016-04-06 | 2016-07-20 | 深圳市博康智能信息技术有限公司 | Method and system for associating MAC addresses with face information |
| CN105844903A (en) * | 2016-03-22 | 2016-08-10 | 乐卡汽车智能科技（北京）有限公司 | Vehicle positioning method and device |
| CN106303397A (en) * | 2015-05-12 | 2017-01-04 | 杭州海康威视数字技术股份有限公司 | Image-pickup method and system, video frequency monitoring method and system |
| CN106548164A (en) * | 2016-11-28 | 2017-03-29 | 中通服公众信息产业股份有限公司 | The relevance recognition methods of facial image and mobile device |
| CN106899827A (en) * | 2015-12-17 | 2017-06-27 | 杭州海康威视数字技术股份有限公司 | Image data acquiring, inquiry, video frequency monitoring method, equipment and system |
| CN107273833A (en) * | 2017-06-06 | 2017-10-20 | 深圳市至壹科技开发有限公司 | Method and its system for monitoring floating population |
| CN108090430A (en) * | 2017-12-08 | 2018-05-29 | 杭州魔点科技有限公司 | The method and its device of Face datection |
| CN108228872A (en) * | 2017-07-21 | 2018-06-29 | 北京市商汤科技开发有限公司 | Facial image De-weight method and device, electronic equipment, storage medium, program |
| CN108282784A (en) * | 2018-01-24 | 2018-07-13 | 深圳捷豹电波科技有限公司 | Wireless network access method, MiFi terminals, mobile terminal and storage medium |
| CN108491822A (en) * | 2018-04-02 | 2018-09-04 | 杭州高创电子科技有限公司 | A kind of Face datection De-weight method based on the limited caching of embedded device |
| CN108665584A (en) * | 2018-03-08 | 2018-10-16 | 常州工学院 | A kind of entrance pedestrian disengaging judges system and method |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006197516A (en) * | 2005-01-17 | 2006-07-27 | Ricoh Co Ltd | Image processing system |
| CN106303401B (en) * | 2015-05-12 | 2019-12-06 | 杭州海康威视数字技术股份有限公司 | Video monitoring method, equipment and system thereof and video monitoring method based on shopping mall |
| CN106303400B (en) * | 2015-05-12 | 2019-06-18 | 杭州海康威视数字技术股份有限公司 | The monitoring method and device of vehicle-mounted vidicon |
| CN108985845A (en) * | 2018-07-18 | 2018-12-11 | 北京旷视科技有限公司 | Broadcast monitoring method, apparatus and system |
| CN109711287B (en) * | 2018-12-12 | 2020-11-24 | 深圳云天励飞技术有限公司 | Face acquisition method and related product |
-
2018
- 2018-12-12 CN CN201811517472.9A patent/CN109711287B/en active Active
-
2019
- 2019-10-31 WO PCT/CN2019/114729 patent/WO2020119315A1/en active Application Filing
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100141794A1 (en) * | 2008-12-04 | 2010-06-10 | Nintendo Co., Ltd. | Program and information processing device allowing storage of information for identifying user |
| WO2011021259A1 (en) * | 2009-08-21 | 2011-02-24 | Sony Ericsson Mobile Communications Ab | Information terminal, information control method for an information terminal, and information control program |
| CN106303397A (en) * | 2015-05-12 | 2017-01-04 | 杭州海康威视数字技术股份有限公司 | Image-pickup method and system, video frequency monitoring method and system |
| CN104992075A (en) * | 2015-07-30 | 2015-10-21 | 浙江宇视科技有限公司 | Multi-source information correlation method based on big data |
| CN105243373A (en) * | 2015-10-27 | 2016-01-13 | 北京奇虎科技有限公司 | Method for filtering facial images to prevent repeated snapshot, server, intelligent monitoring device and system |
| CN106899827A (en) * | 2015-12-17 | 2017-06-27 | 杭州海康威视数字技术股份有限公司 | Image data acquiring, inquiry, video frequency monitoring method, equipment and system |
| CN105844903A (en) * | 2016-03-22 | 2016-08-10 | 乐卡汽车智能科技（北京）有限公司 | Vehicle positioning method and device |
| CN105790955A (en) * | 2016-04-06 | 2016-07-20 | 深圳市博康智能信息技术有限公司 | Method and system for associating MAC addresses with face information |
| CN106548164A (en) * | 2016-11-28 | 2017-03-29 | 中通服公众信息产业股份有限公司 | The relevance recognition methods of facial image and mobile device |
| CN107273833A (en) * | 2017-06-06 | 2017-10-20 | 深圳市至壹科技开发有限公司 | Method and its system for monitoring floating population |
| CN108228872A (en) * | 2017-07-21 | 2018-06-29 | 北京市商汤科技开发有限公司 | Facial image De-weight method and device, electronic equipment, storage medium, program |
| CN108090430A (en) * | 2017-12-08 | 2018-05-29 | 杭州魔点科技有限公司 | The method and its device of Face datection |
| CN108282784A (en) * | 2018-01-24 | 2018-07-13 | 深圳捷豹电波科技有限公司 | Wireless network access method, MiFi terminals, mobile terminal and storage medium |
| CN108665584A (en) * | 2018-03-08 | 2018-10-16 | 常州工学院 | A kind of entrance pedestrian disengaging judges system and method |
| CN108491822A (en) * | 2018-04-02 | 2018-09-04 | 杭州高创电子科技有限公司 | A kind of Face datection De-weight method based on the limited caching of embedded device |
Non-Patent Citations (1)
| Title |
|---|
| 李凯雷 等: "基于wifi探针的人流量异常自动预警***设计", 《电子测量技术》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020119315A1 (en) * | 2018-12-12 | 2020-06-18 | 深圳云天励飞技术有限公司 | Face acquisition method and related product |
| CN111476105A (en) * | 2020-03-17 | 2020-07-31 | 深圳力维智联技术有限公司 | Face data cleaning method, device and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109711287B (en) | 2020-11-24 |
| WO2020119315A1 (en) | 2020-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108229369B (en) | Image shooting method and device, storage medium and electronic equipment | |
| US11403874B2 (en) | Virtual avatar generation method and apparatus for generating virtual avatar including user selected face property, and storage medium | |
| EP3739502A1 (en) | Image processing method, apparatus, storage medium, and electronic device | |
| CN109583449A (en) | Character identifying method and Related product | |
| CN110276308B (en) | Image processing method and device | |
| CN108200334B (en) | Image shooting method and device, storage medium and electronic equipment | |
| CN108198130B (en) | Image processing method, image processing device, storage medium and electronic equipment | |
| CN106874826A (en) | Face key point-tracking method and device | |
| CN104049760B (en) | The acquisition methods and system of a kind of man-machine interaction order | |
| KR101612605B1 (en) | Method for extracting face feature and apparatus for perforimg the method | |
| CN106101540B (en) | Focus point determines method and device | |
| CN109711287A (en) | Face acquisition method and Related product | |
| JP6071002B2 (en) | Reliability acquisition device, reliability acquisition method, and reliability acquisition program | |
| WO2019041660A1 (en) | Face deblurring method and device | |
| CN111382791B (en) | Deep learning task processing method, image recognition task processing method and device | |
| CN115620398A (en) | Target action detection method and device | |
| JP5746550B2 (en) | Image processing apparatus and image processing method | |
| CN111563490A (en) | Face key point tracking method and device and electronic equipment | |
| WO2015176502A1 (en) | Image feature estimation method and device | |
| CN105229700B (en) | Device and method for extracting peak figure picture from multiple continuously shot images | |
| WO2024022301A1 (en) | Visual angle path acquisition method and apparatus, and electronic device and medium | |
| CN110956131B (en) | Single-target tracking method, device and system | |
| US11361467B2 (en) | Pose selection and animation of characters using video data and training techniques | |
| Han et al. | Connecting the complementary-view videos: joint camera identification and subject association | |
| CN113569594A (en) | Method and device for labeling key points of human face |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 518000 Longgang road 8288, Yuen Shan Street, Longgang District, Shenzhen, Guangdong, 1 floor, 17 Town, Shenzhen Dayun software town Patentee after: Shenzhen Yuntian lifeI Technology Co., Ltd Address before: 518000 Longgang road 8288, Yuen Shan Street, Longgang District, Shenzhen, Guangdong, 1 floor, 17 Town, Shenzhen Dayun software town Patentee before: SHENZHEN INTELLIFUSION TECHNOLOGIES Co.,Ltd. |
|
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Peng Cheng Inventor after: Deng Haoran Inventor before: Peng Cheng |