CN106778470A - A kind of face identification method and device - Google Patents
A kind of face identification method and device Download PDFInfo
- Publication number
- CN106778470A CN106778470A CN201611007240.XA CN201611007240A CN106778470A CN 106778470 A CN106778470 A CN 106778470A CN 201611007240 A CN201611007240 A CN 201611007240A CN 106778470 A CN106778470 A CN 106778470A
- Authority
- CN
- China
- Prior art keywords
- face
- target
- target face
- image
- picture library
- 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
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
- G06V40/172—Classification, e.g. identification
- G06V40/173—Classification, e.g. identification face re-identification, e.g. recognising unknown faces across different face tracks
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of face identification method and device, methods described includes：Carry out Face datection in detection zone, and at least one target face to detecting is tracked；It is identified by the target face, determines whether the target face belongs to the face in face picture library；When the target face is not belonging to the face in the face picture library, the image of the target face obtained during using tracking, the target face is learnt, and the image of the target face is stored in the face picture library after study is finished, wherein, during the tracking it is the target face detection zone interior all or part of period during this from occurring to removing.The present invention can improve the identification range of recognition of face.
Description
Technical field
The present invention relates to biometrics identification technology field, more particularly to a kind of face identification method and device.
Background technology
Recognition of face has broad application prospects in fields such as security protection, authentications.Recognition of face is the face according to people
Portion's feature carries out the technology of identification, and in numerous biometrics identification technologies, face recognition technology is had because of it
Untouchable, intuitive, to be difficult counterfeit, recognition speed fast and be difficult the features such as being noticeable, obtained extensively in different field
Application.
Existing face recognition technology, it is necessary in advance to face picture library in intrinsic facial image learn, carrying out
During recognition of face, the intrinsic face belonged in the face picture library can only be identified, but can not be to the face picture library beyond
Strange face is identified.Such as, in real life, many people can transport when customs is crossed or carry some articles, but,
When some illegal passengers transport some illegal articles by customs, because the facial image of these illegal passengers may not exist
In the face picture library, i.e., the face not in advance to these illegal passengers learns, therefore existing face identification method is not
The face of these illegal passengers can be identified, therefore, the recognition of face scope of existing face identification method is relatively low.
The content of the invention
In view of this, the main purpose of the embodiment of the present invention is to provide a kind of face identification method and device, Neng Gouti
The identification range of recognition of face high.
A kind of face identification method is the embodiment of the invention provides, including：
Carry out Face datection in detection zone, and at least one target face to detecting is tracked；
It is identified by the target face, determines whether the target face belongs to the face in face picture library；
When the target face is not belonging to the face in the face picture library, using tracking during obtain the target
The image of face, learns to the target face, and is stored in the image of the target face after study is finished described
Face picture library, wherein, it is that target face detection zone from occurring to removing is interior during this during the tracking
All or part of period.
Optionally, methods described also includes：
When the target face belongs to the face in the face picture library, judge whether the target face is emphasis prison
Control face；
If the target face is the key monitoring face, alarm signal is sent.
Optionally, it is described to judge whether the target face is emphasis monitoring face, including：
Count the number of times that the target face is appeared in a FX within the setting period；
Whether the number of times that judgement is counted is more than preset threshold value, if it is, determining that the target face is key monitoring
Face, if it is not, then determining that the target face is not key monitoring face.
Optionally, methods described also includes：
Choose at least one image of key monitoring face from the face picture library, and facial image to selecting enters
Line flag；
Then, it is described to judge whether the target face is emphasis monitoring face, including：
Judge whether the target face belongs to the face in a labeled image in the face picture library, if it is,
Then determine that the target face is key monitoring face, if it is not, then determining that the target face is not key monitoring face.
Optionally, after the determination target face is key monitoring face, also include：
An image to appearing in the target face in the detection zone is intercepted；
Show the correspondence image of the target facial image and the target face of interception in the face picture library.
Optionally, after the determination target face is key monitoring face, also include：
Show the personal information of the target face.
The embodiment of the present invention additionally provides a kind of face identification device, including：
Detecting and tracking unit, for carrying out Face datection, and at least one target person to detecting in detection zone
Face is tracked；
Face identification unit, for being identified by the target face, determines whether the target face belongs to
Face in face picture library；
Face unit, for be not belonging to when the target face in the face picture library face when, using tracking
The image of the target face that period obtains, learns to the target face, and by the target after study is finished
The image of face is stored in the face picture library, wherein, it is target face inspection from occurring to removing during the tracking
Survey region interior all or part of period during this.
Optionally, described device also includes：
Face judging unit, for belonging to when the target face during face in the face picture library, judges the mesh
Whether mark face is emphasis monitoring face；
Alarm transmitting element, if being the key monitoring face for the target face, sends alarm signal.
Optionally, the face judging unit includes：
Number of times count subelement, for count the target face setting the period in appear in a FX time
Number；
Whether face judgment sub-unit, the number of times for judging to count is more than preset threshold value, if it is, determining described
Target face is key monitoring face, if it is not, then determining that the target face is not key monitoring face.
Optionally, described device also includes：
Image tagged unit, it is for choosing at least one image of key monitoring face from the face picture library and right
The facial image for selecting is marked；
Then, the face judging unit, specifically for judging whether the target face belongs in the face picture library
The face in labeled image is opened, if it is, determine that the target face is key monitoring face, if it is not, then determining institute
It is not key monitoring face to state target face.
Optionally, described device also includes：
Image interception unit, for after it is determined that the target face is key monitoring face, to appearing in the inspection
One image of the target face surveyed in region is intercepted；
Image-display units, for showing the target facial image and the target face of interception in the face figure
Correspondence image in storehouse.
Optionally, described device also includes：
Information display unit, for after it is determined that the target face is key monitoring face, showing the target person
The personal information of face.
Face identification method provided in an embodiment of the present invention and device, are carried out to appearing in the face in detection zone in real time
Detection, for the every target face for detecting, the process of the detection zone is tracked from occurring to disappearing in；Meanwhile,
The image of the target face of interior acquisition during to tracking is identified, if recognition result shows that the target face is face figure
Strange face beyond storehouse, just using the image of the target face obtained during tracking, to the target face
Practise, and turn into a non-strange face in the target face is stored in into the face picture library after study is finished；So, institute is worked as
When stating target face and again appearing at the detection zone, based on the above-mentioned study to the target face, just can identify
The target face.It can be seen that, this mode that dynamic learning is carried out to the real-time face for occurring can constantly expand face study
Scope, such that it is able to effectively improve the scope of recognition of face.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
The accompanying drawing to be used needed for having technology description is briefly described, it should be apparent that, drawings in the following description are the present invention
Some embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, can also basis
These accompanying drawings obtain other accompanying drawings.
Fig. 1 is one of schematic flow sheet of face identification method provided in an embodiment of the present invention；
Fig. 2 is the two of the schematic flow sheet of face identification method provided in an embodiment of the present invention；
Fig. 3 is the composition schematic diagram of face identification device provided in an embodiment of the present invention.
Specific embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
A part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
Embodiment one
It is the schematic flow sheet of the face identification method that the embodiment of the present invention one is provided referring to Fig. 1, the method includes following
Step：
Step 101：Carry out Face datection in detection zone, and at least one target face to detecting carry out with
Track.
The purpose of Face datection is the position and size where finding each different face in the picture, when to video image
When carrying out Face datection, in addition it is also necessary to which the face in video image is tracked, the purpose is in the different two field pictures to video
Different faces carry out correspondence, i.e., same face is told from different frame image.
In the present embodiment, the detection zone can be shot using shooting first-class video capture instrument, to obtain
The video image of the detection zone is taken, so as to carry out the detection and tracking of face to video image.Specifically, the detection zone
Domain, can be the shooting area of a certain camera set in the different places such as customs, school, airport, cash dispenser or elevator.
In the present embodiment, for ease of description, for detecting one or more face in the detection zone, will examine
The every face for measuring referred to as target face.
Step 102：It is identified by the target face, in determining whether the target face belongs to face picture library
Face.
In the present embodiment, it is identified by appearing in every in the detection zone different target face,
Can determine whether the target face is strange face.That is, if described target face is the face in the face picture library,
Due to being learnt to the face in the face picture library in advance, therefore, by recognition of face, it may be determined that the mesh
Mark face belongs to the existing face in face picture library, and otherwise, the target face is the strange face beyond the face picture library.
Specifically, the present embodiment can be known using following any one face identification method to the target face
Not：
The face identification method of geometric properties；
The face identification method of feature based face (PCA)；
The face identification method of neutral net；
The face identification method of elastic graph matching；
The face identification method of line segment Hausdorff distance (LHD)；
The face identification method of SVMs (SVM).
It is, of course, also possible to using other face identification methods, the present embodiment is not restricted to this.
Step 103：When the target face is not belonging to the face in the face picture library, using tracking during obtain
The image of the target face, learns to the target face, and by the image of the target face after study is finished
Be stored in the face picture library, wherein, be during the tracking target face from occurring to removing the detection zone this
All or part of period in period.
In the present embodiment, every facial image in the face picture library can carry out area using different image identifications
Point.After being identified to every target face for appearing in the detection zone using face identification method, such as, for it
In a target face A, if recognition result shows that target face A is not the people in certain image in the face picture library
Face, then it is assumed that target face A is a strange face, at this point it is possible to carry out face to target face A using an image identification
Name, for being made a distinction with the existing face in other strange faces or the face picture library, meanwhile, by tracking the target
Processes of the face A in cam lens from occurring to disappearing, using the image of target face A interior appearance during tracking,
Automatically the face feature of target face A is learnt, and after study terminates, by the facial image of target face A and corresponding
Image identification is stored in the face picture library.
For appearing in every strange face in the detection zone, by said process, can be in real time to strange
Face is learnt and strange facial image is stored, and so, will constantly have new facial image in the face picture library
Renewal is entered, and when these faces again appear at the detection zone and are detected, the face study based on before
And image storing process, the present embodiment is possible to identify these faces.
Embodiment two
It is the schematic flow sheet of the face identification method that the embodiment of the present invention two is provided, with reality in this implementation two referring to Fig. 2
The related introduction for applying same steps in example one refers to above-described embodiment one, and the method is comprised the following steps：
Step 201:Carry out Face datection in detection zone, and at least one target face to detecting carry out with
Track.
Step 202:It is identified by the target face, in determining whether the target face belongs to face picture library
Face, if it is, perform step 203, if it is not, then perform step 205.
Step 203：Judge whether the target face is emphasis monitoring face.
In the present embodiment, the key monitoring face can be the people of offender or country's limitation People Going Abroad
Face, etc..
In the present embodiment, step 203 can use following any one implementation method.
In the first embodiment, step 203 can include：
Step A1：Count the number of times that the target face is appeared in a FX within the setting period.
For example, in real life, there is such class crowd, i.e. " boatman ", " boatman " refers to using the atural object of border two
Product price and the difference of restraint of trade, for the purpose of earning " band expenses of labour ", escape customs supervision, and " a small amount of multiple " is carried by country
Control or dutiable goods, the special group of article immigration.Because " boatman " this kind of illegal crowd can frequently appear in customs, so
Can be by counting every target face in a FX (such as, certain of all of monitoring area of customs or customs
One fixation monitor area) occurrence number determine if that doubtful is " boatman ".
Step A2：Whether the number of times that judgement is counted is more than preset threshold value, if it is, determining that the target face is weight
Point monitoring face, if it is not, then determining that the target face is not key monitoring face.
Based on the citing in step A1, it is assumed that the detection zone is a certain area to be monitored of customs, as a passenger
Face appear in first when in the detection zone, by above-mentioned steps, this passenger can be carried out face study and by its
Facial image is stored in the face picture library, and the number of times that the face occurs is designated as 1 time, when this passenger again appears at institute
State when in detection zone, the face of the passenger is can recognize that by recognition of face, and it is 2 times to add up the occurrence number of the face.
When this passenger sets one, the period (such as one month) frequently appears in customs and occurrence number exceedes certain predetermined threshold value (ratio
Such as 10 times) when, then, this passenger is likely to " boatman ", therefore, the face of this passenger will be considered as key monitoring face.
In second implementation method, to realize step 203, the face identification method that the present embodiment two is provided can also be wrapped
A pre-treatment step is included, i.e.,：Choose at least one image of key monitoring face from the face picture library, and to selecting
Facial image is marked.In the pre-treatment step, due to the facial image in the face picture library, except can include from
The target facial image detected in the detection zone, can also include the facial image that other approach are obtained, such as, and can be with
The offender of public security intraoffice network (such as networking is obtained) or the facial image of suspect are derived from, can in advance by this
The facial image of a little offenders or suspect carries out emphasis mark, and these labeled image faces are key monitoring
Face.
Based on the pre-treatment step, then step 203 can include：Judge whether the target face belongs to the face figure
Face in storehouse in a labeled image, if it is, determine that the target face is key monitoring face, if it is not, then
Determine that the target face is not key monitoring face.In this step, after being identified to the target face, if known
Other result shows that the target face belongs to the face picture library and is a labeled image in the face picture library, then
Can determine that the target face is key monitoring face.
Step 204:If the target face is the key monitoring face, alarm signal is sent.
In the present embodiment, once it is determined that the target face is the key monitoring face, alarm signal is just sent, than
Such as, alarm signal is sent to the monitoring device of the warning personnel such as customs, notifies that related personnel is found that key monitoring face, customs
Personnel can be taken immediate steps and the personnel are controlled, and examine its identity or interrogate and examine its carrying article it is whether illegal.
Further, the present embodiment can also be after it is determined that the target face be key monitoring face, to appearing in
One image of the target face in the detection zone is intercepted；And show interception target facial image and
Correspondence image of the target face in the face picture library.In the present embodiment, attach most importance to when identifying the target face
After the face of point monitoring personnel, occur to during disappearing in the detection zone for tracking it, for can tracing into
Comparing clearly front face image is intercepted, and by the key monitoring personnel in interception image and the face picture library
Facial image carry out contrast and show, so that whether monitoring personnel can contrast determine whether two facial images by picture
The same people of correspondence.
Further, the present embodiment can also show described after it is determined that the target face is key monitoring face
The personal information of target face.In the present embodiment, the personal information of the target face, such as, institute can also be prestored
The head portrait that target face is the offender obtained from public security intraoffice network is stated, while also obtaining the name of the offender, body
High personal information, because the face of the offender is key monitoring face, can show the facial image of the offender
While (including the correspondence image stored from the facial image and the face picture library of detection zone interception), the criminal is shown
The personal information of guilty molecule.
Step 205:The image of the target face obtained during using tracking, learns to the target face,
And the image of the target face is stored in the face picture library after study is finished, wherein, it is the mesh during the tracking
The mark face detection zone interior all or part of period during this from occurring to removing.
Face identification method provided in an embodiment of the present invention, the face to appearing in real time in detection zone detects,
For the every target face for detecting, the process of the detection zone is tracked from occurring to disappearing in；Meanwhile, to tracking
The image of the target face obtained in period is identified, if recognition result shows that the target face is beyond face picture library
Strange face, just using tracking during obtain the target face image, the target face is learnt, and
Be stored in the target face in the face picture library after finishing by study turns into a non-strange face；So, when the target
When face again appears at the detection zone, based on the above-mentioned study to the target face, the mesh just can be identified
Mark face.It can be seen that, this mode that dynamic learning is carried out to the real-time face for occurring can constantly expand the model of face study
Enclose, such that it is able to effectively improve the scope of recognition of face.
Embodiment three
It is the composition schematic diagram of the face identification device that the embodiment of the present invention three is provided referring to Fig. 3, the device includes：
Detecting and tracking unit 301, for carrying out Face datection, and at least one target to detecting in detection zone
Face is tracked；
Face identification unit 302, for being identified by the target face, determines whether the target face belongs to
Face in face picture library；
Face unit 303, for be not belonging to when the target face in the face picture library face when, using with
The image of the target face obtained during track, learns to the target face, and by the mesh after study is finished
The image for marking face is stored in the face picture library, wherein, it is the target face described from occurring to removing during the tracking
Detection zone interior all or part of period during this.
In some embodiments, described device also includes face judging unit and alarm transmitting element, wherein：
Face judging unit, for belonging to when the target face during face in the face picture library, judges the mesh
Whether mark face is emphasis monitoring face；
Alarm transmitting element, if being the key monitoring face for the target face, sends alarm signal.
In some embodiments, the face judging unit includes that number of times counts subelement and face judgment sub-unit,
Wherein：
Number of times count subelement, for count the target face setting the period in appear in a FX time
Number；
Whether face judgment sub-unit, the number of times for judging to count is more than preset threshold value, if it is, determining described
Target face is key monitoring face, if it is not, then determining that the target face is not key monitoring face.
In some embodiments, described device also includes：Image tagged unit, for being chosen from the face picture library
At least one image of key monitoring face, and facial image to selecting is marked；Then, the face judging unit,
Specifically for judging whether the target face belongs to the face in a labeled image in the face picture library, if it is,
Then determine that the target face is key monitoring face, if it is not, then determining that the target face is not key monitoring face.
In some embodiments, described device also includes image interception unit and image-display units, wherein：
Image interception unit, for after it is determined that the target face is key monitoring face, to appearing in the inspection
One image of the target face surveyed in region is intercepted；
Image-display units, for showing the target facial image and the target face of interception in the face figure
Correspondence image in storehouse.
In some embodiments, described device also includes：
Information display unit, for after it is determined that the target face is key monitoring face, showing the target person
The personal information of face.
The face identification device includes processor and memory, above-mentioned detecting and tracking unit 301, face identification unit
302nd, face unit 303 etc. is stored in memory as program unit, by computing device storage in memory
Said procedure unit realize corresponding function.
Kernel is included in processor, is gone in memory to transfer corresponding program unit by kernel.Kernel can set one
Or more, the identification range of recognition of face is improved by adjusting kernel parameter.
Memory potentially includes the volatile memory in computer-readable medium, random access memory (RAM) and/
Or the form, such as read-only storage (ROM) or flash memory (flash RAM) such as Nonvolatile memory, memory is deposited including at least one
Storage chip.
Face identification device provided in an embodiment of the present invention, the face to appearing in real time in detection zone detects,
For the every target face for detecting, the process of the detection zone is tracked from occurring to disappearing in；Meanwhile, to tracking
The image of the target face obtained in period is identified, if recognition result shows that the target face is beyond face picture library
Strange face, just using tracking during obtain the target face image, the target face is learnt, and
Be stored in the target face in the face picture library after finishing by study turns into a non-strange face；So, when the target
When face again appears at the detection zone, based on the above-mentioned study to the target face, the mesh just can be identified
Mark face.It can be seen that, this mode that dynamic learning is carried out to the real-time face for occurring can constantly expand the model of face study
Enclose, such that it is able to effectively improve the scope of recognition of face.
Present invention also provides a kind of computer program product, when being performed on data processing equipment, it is adapted for carrying out just
The program code of beginningization there are as below methods step：
Carry out Face datection in detection zone, and at least one target face to detecting is tracked；
It is identified by the target face, determines whether the target face belongs to the face in face picture library；
When the target face is not belonging to the face in the face picture library, using tracking during obtain the target
The image of face, learns to the target face, and is stored in the image of the target face after study is finished described
Face picture library, wherein, it is that target face detection zone from occurring to removing is interior during this during the tracking
All or part of period.
As seen through the above description of the embodiments, those skilled in the art can be understood that above-mentioned implementation
All or part of step in example method can add the mode of required general hardware platform to realize by software.Based on such
Understand, the part that technical scheme substantially contributes to prior art in other words can be in the form of software product
Embody, the computer software product can be stored in storage medium, such as ROM/RAM, magnetic disc, CD, including it is some
Instruction is used to so that a computer equipment (can be the network services such as personal computer, server, or WMG
Equipment, etc.) perform method described in some parts of each embodiment of the invention or embodiment.
It should be noted that each embodiment is described by the way of progressive in this specification, each embodiment emphasis is said
Bright is all the difference with other embodiment, between each embodiment identical similar portion mutually referring to.For reality
For applying device disclosed in example, because it is corresponded to the method disclosed in Example, so description is fairly simple, related part
Referring to method part illustration.
Also, it should be noted that herein, term " including ", "comprising" or its any other variant be intended to it is non-
It is exclusive to include, so that process, method, article or equipment including a series of key elements not only include those key elements,
But also other key elements including being not expressly set out, or also include by this process, method, article or equipment are solid
Some key elements.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that including
Also there is other identical element in the process of the key element, method, article or equipment.
The foregoing description of the disclosed embodiments, enables professional and technical personnel in the field to realize or uses the present invention.
Various modifications to these embodiments will be apparent for those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, the present invention
The embodiments shown herein is not intended to be limited to, and is to fit to and principles disclosed herein and features of novelty phase one
The scope most wide for causing.
Claims (10)
1. a kind of face identification method, it is characterised in that including：
Carry out Face datection in detection zone, and at least one target face to detecting is tracked；
It is identified by the target face, determines whether the target face belongs to the face in face picture library；
When the target face is not belonging to the face in the face picture library, using tracking during obtain the target face
Image, the target face is learnt, and study finish after the image of the target face is stored in the face
Picture library, wherein, it is the target face interior whole during this of the detection zone from occurring to removing during the tracking
Or partial period.
2. method according to claim 1, it is characterised in that methods described also includes：
When the target face belongs to the face in the face picture library, judge whether the target face is emphasis monitor
Face；
If the target face is the key monitoring face, alarm signal is sent.
3. the method stated according to claim 2, it is characterised in that described to judge whether the target face is emphasis monitor
Face, including：
Count the number of times that the target face is appeared in a FX within the setting period；
Whether the number of times that judgement is counted is more than preset threshold value, if it is, determine that the target face is key monitoring face,
If it is not, then determining that the target face is not key monitoring face.
4. method according to claim 2, it is characterised in that methods described also includes：
Choose at least one image of key monitoring face from the face picture library, and facial image to selecting enters rower
Note；
Then, it is described to judge whether the target face is emphasis monitoring face, including：
Judge whether the target face belongs to the face in a labeled image in the face picture library, if it is, really
The fixed target face is key monitoring face, if it is not, then determining that the target face is not key monitoring face.
5. according to the methods described of claim 3 or 4, it is characterised in that the determination target face is key monitoring face
Afterwards, also include：
An image to appearing in the target face in the detection zone is intercepted；
Show the correspondence image of the target facial image and the target face of interception in the face picture library.
6. according to the methods described of claim 3 or 4, it is characterised in that the determination target face is key monitoring face
Afterwards, also include：
Show the personal information of the target face.
7. a kind of face identification device, it is characterised in that including：
Detecting and tracking unit, for carrying out Face datection in detection zone, and at least one target face to detecting enters
Line trace；
Face identification unit, for being identified by the target face, determines whether the target face belongs to face
Face in picture library；
Face unit, for be not belonging to when the target face in the face picture library face when, during tracking
The image of the target face for obtaining, learns to the target face, and by the target face after study is finished
Image be stored in the face picture library, wherein, be target face detection zone from occurring to removing during the tracking
Domain interior all or part of period during this.
8. device according to claim 7, it is characterised in that described device also includes：
Face judging unit, for belonging to when the target face during face in the face picture library, judges the target person
Whether face is emphasis monitoring face；
Alarm transmitting element, if being the key monitoring face for the target face, sends alarm signal.
9. the device stated according to claim 8, it is characterised in that the face judging unit includes：
Number of times counts subelement, and the number of times appeared in the period in a FX is being set for counting the target face；
Whether face judgment sub-unit, the number of times for judging to count is more than preset threshold value, if it is, determining the target
Face is key monitoring face, if it is not, then determining that the target face is not key monitoring face.
10. device according to claim 8, it is characterised in that described device also includes：
Image tagged unit, for choosing at least one image of key monitoring face from the face picture library, and to choosing
The facial image for going out is marked；
Then, the face judging unit, specifically for judging whether the target face belongs to a quilt in the face picture library
Face in mark image, if it is, determine that the target face is key monitoring face, if it is not, then determining the mesh
Mark face is not key monitoring face.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611007240.XA CN106778470A (en) | 2016-11-15 | 2016-11-15 | A kind of face identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611007240.XA CN106778470A (en) | 2016-11-15 | 2016-11-15 | A kind of face identification method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106778470A true CN106778470A (en) | 2017-05-31 |
Family
ID=58968805
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611007240.XA Pending CN106778470A (en) | 2016-11-15 | 2016-11-15 | A kind of face identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106778470A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107992834A (en) * | 2017-12-11 | 2018-05-04 | 成都西华升腾科技有限公司 | For limiting the warning device of People Going Abroad |
| CN109658572A (en) * | 2018-12-21 | 2019-04-19 | 上海商汤智能科技有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN109670451A (en) * | 2018-12-20 | 2019-04-23 | 天津天地伟业信息系统集成有限公司 | Automatic face recognition tracking |
| CN109871767A (en) * | 2019-01-17 | 2019-06-11 | 平安科技（深圳）有限公司 | Face identification method, device, electronic equipment and computer readable storage medium |
| CN110147461A (en) * | 2019-04-30 | 2019-08-20 | 维沃移动通信有限公司 | Image display method, device, terminal device and computer readable storage medium |
| CN110995989A (en) * | 2019-11-25 | 2020-04-10 | 陈颖 | Lens capturing method based on human body feature positioning |
| WO2020088136A1 (en) * | 2018-10-29 | 2020-05-07 | 苏宁云计算有限公司 | Customer path tracking method and system |
| CN112926353A (en) * | 2019-12-05 | 2021-06-08 | 王体 | Distributed cloud processing method for field data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102201061A (en) * | 2011-06-24 | 2011-09-28 | 常州锐驰电子科技有限公司 | Intelligent safety monitoring system and method based on multilevel filtering face recognition |
| CN102572388A (en) * | 2011-10-31 | 2012-07-11 | 东莞市中控电子技术有限公司 | Face-recognition-based network video monitoring device and monitoring recognition method |
| CN102867173A (en) * | 2012-08-28 | 2013-01-09 | 华南理工大学 | Human face recognition method and system thereof |
| CN104732210A (en) * | 2015-03-17 | 2015-06-24 | 深圳超多维光电子有限公司 | Target human face tracking method and electronic equipment |
| CN105117463A (en) * | 2015-08-24 | 2015-12-02 | 北京旷视科技有限公司 | Information processing method and information processing device |
-
2016
- 2016-11-15 CN CN201611007240.XA patent/CN106778470A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102201061A (en) * | 2011-06-24 | 2011-09-28 | 常州锐驰电子科技有限公司 | Intelligent safety monitoring system and method based on multilevel filtering face recognition |
| CN102572388A (en) * | 2011-10-31 | 2012-07-11 | 东莞市中控电子技术有限公司 | Face-recognition-based network video monitoring device and monitoring recognition method |
| CN102867173A (en) * | 2012-08-28 | 2013-01-09 | 华南理工大学 | Human face recognition method and system thereof |
| CN104732210A (en) * | 2015-03-17 | 2015-06-24 | 深圳超多维光电子有限公司 | Target human face tracking method and electronic equipment |
| CN105117463A (en) * | 2015-08-24 | 2015-12-02 | 北京旷视科技有限公司 | Information processing method and information processing device |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107992834A (en) * | 2017-12-11 | 2018-05-04 | 成都西华升腾科技有限公司 | For limiting the warning device of People Going Abroad |
| WO2020088136A1 (en) * | 2018-10-29 | 2020-05-07 | 苏宁云计算有限公司 | Customer path tracking method and system |
| CN109670451A (en) * | 2018-12-20 | 2019-04-23 | 天津天地伟业信息系统集成有限公司 | Automatic face recognition tracking |
| CN109658572A (en) * | 2018-12-21 | 2019-04-19 | 上海商汤智能科技有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN109658572B (en) * | 2018-12-21 | 2020-09-15 | 上海商汤智能科技有限公司 | Image processing method and device, electronic equipment and storage medium |
| US11410001B2 (en) | 2018-12-21 | 2022-08-09 | Shanghai Sensetime Intelligent Technology Co., Ltd | Method and apparatus for object authentication using images, electronic device, and storage medium |
| CN109871767A (en) * | 2019-01-17 | 2019-06-11 | 平安科技（深圳）有限公司 | Face identification method, device, electronic equipment and computer readable storage medium |
| CN110147461A (en) * | 2019-04-30 | 2019-08-20 | 维沃移动通信有限公司 | Image display method, device, terminal device and computer readable storage medium |
| CN110995989A (en) * | 2019-11-25 | 2020-04-10 | 陈颖 | Lens capturing method based on human body feature positioning |
| CN112926353A (en) * | 2019-12-05 | 2021-06-08 | 王体 | Distributed cloud processing method for field data |
| CN112926353B (en) * | 2019-12-05 | 2024-03-19 | 上海岽利信息科技有限公司 | Site data distributed cloud processing method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106778470A (en) | A kind of face identification method and device | |
| CN107527009B (en) | Remnant detection method based on YOLO target detection | |
| Braunegg et al. | Apricot: A dataset of physical adversarial attacks on object detection | |
| CN108229335A (en) | It is associated with face identification method and device, electronic equipment, storage medium, program | |
| CN105893510A (en) | Video structurization system and target search method thereof | |
| CN109446936A (en) | A kind of personal identification method and device for monitoring scene | |
| CN108564069A (en) | A kind of industry safe wearing cap video detecting method | |
| CN107818573A (en) | A kind of method for tracking target and device | |
| US20210082217A1 (en) | Method for provisioning a device with an information element allowing to identify unauthorized users in a restricted area | |
| CN108021846A (en) | A kind of face identification method and device | |
| CN108694399A (en) | Licence plate recognition method, apparatus and system | |
| CN105893957A (en) | Method for recognizing and tracking ships on lake surface on the basis of vision | |
| CN109934098A (en) | A kind of video camera intelligence system and its implementation with secret protection | |
| JP2020154808A (en) | Information processor, information processing system, information processing method, and program | |
| CN108229411A (en) | Human body hand-held knife behavioral value system and method based on RGB color image | |
| CN108280388A (en) | The method and apparatus and type of face detection method and device of training face detection model | |
| Nam | Loitering detection using an associating pedestrian tracker in crowded scenes | |
| CN111985331A (en) | Detection method and device for preventing secret of business from being stolen | |
| CN112399049A (en) | Gas station illegal gas filling identification method, system and equipment based on intelligent box | |
| CN112287760A (en) | Behavior monitoring-based airport figure risk quantification method | |
| CN109460714B (en) | Method, system and device for identifying object | |
| Zhang et al. | Face occlusion detection using cascaded convolutional neural network | |
| Shen et al. | IriTrack: Liveness detection using irises tracking for preventing face spoofing attacks | |
| CN106127233A (en) | A kind of eyes open detection method and the system of closed state | |
| CN115861919A (en) | Passage control method for preventing trailing passage behavior |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170531 |