CN107679504A - Face identification method, device, equipment and storage medium based on camera scene - Google Patents
Face identification method, device, equipment and storage medium based on camera scene Download PDFInfo
- Publication number
- CN107679504A CN107679504A CN201710954276.7A CN201710954276A CN107679504A CN 107679504 A CN107679504 A CN 107679504A CN 201710954276 A CN201710954276 A CN 201710954276A CN 107679504 A CN107679504 A CN 107679504A
- Authority
- CN
- China
- Prior art keywords
- face
- face recognition
- facial image
- recognition result
- key point
- 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
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
- G06V40/168—Feature extraction; Face representation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of face identification method based on camera scene, including：Obtain the image of camera shooting；The face in described image is detected, obtains facial image；The key point in the facial image is detected, extracts key point information；According to the key point information, face characteristic is extracted；The face characteristic is inputted into face recognition module, obtains face recognition result.By handling the facial image that camera is got, face recognition process is optimized, the accuracy rate of camera scene human face recognition result can be improved, the generation of error detection can be reduced, and can avoid because facial angle is improper or facial image is unintelligible and caused by identify mistake, and face recognition result can be fed back into monitor terminal to remind user in time.
Description
Technical field
The present invention relates to field of face identification, and in particular to a kind of face identification method based on camera scene, device,
Computing device and computer-readable storage medium.
Background technology
Recognition of face is a kind of biological identification technology that the facial feature information based on people carries out identification.Use video camera
Or image or video flowing of the camera collection containing face, and automatic detect and track face, and then to detecting in the picture
Face carry out face a series of correlation techniques.At present, camera is widely used in monitoring, tele-medicine and video in real time
Meeting etc., there is an urgent need to the quick identity knowledge under a kind of remote, non-mated condition of user for numerous video surveillance applications
Other technology, in the hope of remote quick confirmation personnel identity, realize intelligent early-warning.In the prior art, by camera is collected
Image or video flowing it is of low quality, the recognition of face based on camera scene is more prone to error detection than general scene,
And can not be solved in time for error detection, additionally, due to facial angle in image not just or face it is unintelligible cause identification tie
Fruit accuracy rate is not high.
The content of the invention
In view of the above problems, it is proposed that the present invention so as to provide one kind overcome above mentioned problem or at least in part solve on
State the face identification method based on camera scene, device, computing device and the computer-readable storage medium of problem.
According to an aspect of the invention, there is provided a kind of face identification method based on camera scene, including：
Obtain the image of camera shooting；
The face in described image is detected, obtains facial image；
The key point in the facial image is detected, extracts key point information；
According to the key point information, face characteristic is extracted；
The face characteristic is inputted into face recognition module, obtains face recognition result.
Alternatively, the face characteristic is inputted into face recognition module described, after obtaining face recognition result,
Methods described also includes：
Judge whether the face recognition result is error detection result, know if it is not, then feeding back the face to monitor terminal
Other result.
Alternatively, it is described to judge whether face recognition result is that error detection result further comprises：
Determine whether face recognition result is error detection result by manually marking；
Or the face characteristic by the error detection marked in advance in face characteristic and face recognition result and database
And face recognition result is compared, determine whether face recognition result is error detection result according to comparison result.
Alternatively, determine whether face recognition result is the side after error detection result by manually marking described
Method also includes：
If determine that face recognition result is error detection result by manually marking, by face characteristic and recognition of face knot
The annotation results of fruit are stored into database.
Alternatively, the key point in the detection facial image, before extracting key point information, methods described is also wrapped
Include：Face quality evaluation processing is carried out to the facial image, judges whether the facial image is not recognizable facial image；
Key point in the detection facial image is specially：If the facial image is not not recognizable face figure
Picture, then detect the key point in facial image.
Alternatively, the not recognizable facial image includes：Deflection angle be more than predetermined angle threshold value side face image and/
Or definition is less than the facial image of default clarity threshold.
Alternatively, described according to the key point information, after extracting face characteristic, methods described further comprises：
According to face characteristic, clustering processing is carried out to facial image；
The result of clustering processing is fed back into monitor terminal, so that the user of monitor terminal is labeled processing.
Alternatively, it is described to input the face characteristic into face recognition module, it is further to obtain face recognition result
Including：
Judge whether the face recognition result is recognition of face corresponding to the first user marked in advance in database
As a result, if it is not, then to monitor terminal feedback alarm signal.
Alternatively, corresponding to the first user marked in advance in judging that the face recognition result is not database
In the case of face recognition result, methods described also includes：
Shooting instruction is sent to the camera, so that the camera instructs recorded video data according to the shooting；
The video data transmitting of the cam feedback is delivered into monitor terminal.
According to another aspect of the present invention, there is provided a kind of face identification device based on camera scene, including：
Image collection module, suitable for obtaining the image of camera shooting；
Face detection module, the face being adapted to detect in described image, obtains facial image；
Key point extraction module, the facial key point being adapted to detect in the facial image, extract key point information；
Face characteristic extraction module, the face being adapted to detect in described image, extract face characteristic；
Face recognition module, suitable for using the face characteristic as input, obtaining face recognition result.
Alternatively, described device also includes：
Error detection identification module, suitable for judging whether the face recognition result is error detection result；
First data feedback module, if determining that the face recognition result is not flase drop suitable for the error detection identification module
Result is surveyed, feeds back the face recognition result to monitor terminal.
Alternatively, the error detection identification module is further adapted for：
Determine whether face recognition result is error detection result by manually marking；
Or the face characteristic by the error detection marked in advance in face characteristic and face recognition result and database
And face recognition result is compared, determine whether face recognition result is error detection result according to comparison result.
Alternatively, the error detection identification module is further adapted for：
If determine that face recognition result is error detection result by manually marking, by face characteristic and recognition of face knot
The annotation results of fruit are stored into database.
Alternatively, described device also includes：Face quality assessment modules, suitable for carrying out face quality to the facial image
Assessment is handled, and judges whether the facial image is not recognizable facial image；
The key point extraction module is further adapted for：If the facial image is not not recognizable facial image, examine
The key point surveyed in facial image.
Alternatively, the not recognizable facial image includes：Deflection angle be more than predetermined angle threshold value side face image and/
Or definition is less than the facial image of default clarity threshold.
Alternatively, described device also includes：
Cluster module, suitable for according to face characteristic, clustering processing is carried out to facial image；
Second data feedback module, suitable for the result of clustering processing is fed back into monitor terminal, for the use of monitor terminal
Family is labeled processing.
Alternatively, described device also includes：
Judge module, suitable for judging whether the face recognition result is advance the first user couple marked in database
The face recognition result answered；
Alarm module, if judging that the face recognition result has been marked in advance in database suitable for the judge module
Face recognition result corresponding to first user of note, then to monitor terminal feedback alarm information.
Alternatively, described device also includes：
Sending module, suitable for judging that the face recognition result has been marked in advance in database in the judge module
In the case of face recognition result corresponding to first user of note, shooting instruction is sent to the camera, for the shooting
Head instructs recorded video data according to the shooting；
3rd data feedback module, suitable for the video data transmitting of the cam feedback is delivered into monitor terminal.
According to another aspect of the invention, there is provided a kind of computing device, including：Processor, memory, communication interface and
Communication bus, the processor, the memory and the communication interface complete mutual communication by the communication bus；
The memory is used to deposit an at least executable instruction, and the executable instruction makes the computing device above-mentioned
Operation corresponding to face identification method based on camera scene.
In accordance with a further aspect of the present invention, there is provided a kind of computer-readable storage medium, be stored with the storage medium to
A few executable instruction, the executable instruction make the computing device face identification method pair based on camera scene as described above
The operation answered.
According to the face identification method based on camera scene, device, equipment and storage medium disclosed by the invention, obtaining
After the image for getting camera shooting, the face in detection image, face characteristic is extracted；Detect the key in facial image
Point, key point information is extracted, face characteristic is extracted according to key point information, face characteristic is inputted into face recognition module,
Obtain face recognition result.By handling the facial image that camera is got, face recognition process is optimized,
On the one hand the accuracy rate of camera scene human face identification can be improved；On the other hand, recognition of face knot can be quickly obtained
Fruit, continuous processing in real time can be carried out to the image that camera is shot, meets that remote camera rapidly and accurately identifies identity
Demand.
Described above is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention,
And can be practiced according to the content of specification, and in order to allow above and other objects of the present invention, feature and advantage can
Become apparent, below especially exemplified by the embodiment of the present invention.
Brief description of the drawings
By reading the detailed description of hereafter preferred embodiment, it is various other the advantages of and benefit it is common for this area
Technical staff will be clear understanding.Accompanying drawing is only used for showing the purpose of preferred embodiment, and is not considered as to the present invention
Limitation.And in whole accompanying drawing, identical part is denoted by the same reference numerals.In the accompanying drawings：
Fig. 1 shows the face identification method flow chart according to an embodiment of the invention based on camera scene；
Fig. 2 shows the face identification method flow chart in accordance with another embodiment of the present invention based on camera scene；
Fig. 3 shows the face identification method flow chart based on camera scene according to further embodiment of the present invention；
Fig. 4 shows the functional block of the face identification device based on camera scene according to another embodiment of the invention
Figure；
Fig. 5 shows the functional block of the face identification device based on camera scene according to another embodiment of the invention
Figure；
Fig. 6 shows a kind of structural representation of computing device according to embodiments of the present invention.
Embodiment
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although the disclosure is shown in accompanying drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
Limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
Completely it is communicated to those skilled in the art.
It is very universal that camera, which is applied to monitoring in real time, such as is stayed at home, the place installation camera such as company, can be with
It is very convenient to check real-time condition, but image due to camera shooting or video flowing is of low quality, based on shooting first show
The accuracy rate of the recognition of face of scape is low.Face identification method of the kind based on camera scene that the present embodiment provides, by taking the photograph
As head shoot image handled, can quickly and accurately identify the face in image.
Fig. 1 shows the face identification method flow chart according to an embodiment of the invention based on camera scene.This
The method that embodiment provides is applied to server side, as shown in figure 1, this method comprises the following steps：
Step S101, obtain the image of camera shooting.
Server obtains the image that long-range shooting head end will photograph, be the characteristics of the image continuity by force, image matter
Amount is not high, this require follow-up processing will rapidly and efficiently, discrimination it is high.
Step S102, the face in detection image, obtains facial image.
Human face region is detected in the image photographed from above-mentioned camera, isolates human face region among image
Come, obtain facial image.By the way that facial image is separated, it is easy to reduce the amount of calculation of subsequent treatment, improves subsequent treatment
Efficiency.
Step S103, the key point in facial image is detected, extract key point information.
The key point of locating human face in facial image, such as eyes, nose, mouth, chin etc., are extracted including key point
Position and the key point information such as the distance between key point characteristic, because the key point information of face varies with each individual, face
Key point information can characterize a person's identity, the selection of key point and the number of key point can influence Object identifying knot
The accuracy rate of fruit.
Step S104, according to key point information, extract face characteristic.
The process that face characteristic extraction process is modeled aiming at some features of face, the shape according to human face
Shape describe and they the distance between characteristic contribute to the characteristic of face classification to obtain, extracted according to step S103
The key point information come, the geometric description of the distance between these key points and key point characteristic is established, as recognition of face
Feature.
Step S105, face characteristic is inputted into face recognition module, obtains face recognition result.
The face characteristic that above-mentioned S104 steps extract is inputted into face recognition module, for different people, because
Face characteristic is different, and it is different to characterize the recognition result of this person's identity information, and face characteristic is input into recognition of face
Calculated in module, obtain face recognition result.
The face identification method based on camera scene provided according to the present embodiment, getting the figure of camera shooting
As after, the face in detection image, face characteristic is extracted；The key point in facial image is detected, extracts key point information, root
Face characteristic is extracted according to key point information, face characteristic is inputted into face recognition module, obtains face recognition result.Pass through
The facial image that camera is got is handled, face recognition process is optimized, on the one hand can improve camera
The accuracy rate of scene human face identification；On the other hand, face recognition result can be quickly obtained, camera can be shot
Image carries out continuous processing in real time, meets the needs of remote camera rapidly and accurately identifies identity.
Due to the image of camera shooting or the of low quality of video flowing, the big side face that photographs and unintelligible it can influence people
The accuracy rate of face recognition result, and if be identified as face by non-face, and its result is fed back into user, user can be influenceed
Usage experience, the face identification method based on camera scene that the following embodiments of the present invention provide can avoid error detection people
Face recognition result, and reduce big side face and the not high influence to Face datection result of definition.
Fig. 2 shows the face identification method flow chart in accordance with another embodiment of the present invention based on camera scene,
As shown in Fig. 2 this method includes：
Step S201, obtain the image of camera shooting.
Step S202, the face in detection image, obtains facial image.
Human face region is detected in the image photographed from above-mentioned camera, isolates human face region among image
Come, obtain facial image.By the way that facial image is separated, it is easy to reduce the amount of calculation of subsequent treatment, improves subsequent treatment
Efficiency.
Step S203, face quality evaluation processing is carried out to facial image, judges whether facial image is not recognizable people
Face image, if it is not, then performing step S204；If so, then not doing subsequent treatment to this facial image, this method terminates.
Wherein, not recognizable facial image includes：Deflection angle is more than the side face image of predetermined angle threshold value and/or clear
Facial image of the degree less than clarity threshold.
In the application of reality, due to that in the image of camera shooting, may there is big side face (the i.e. deflection of face of people
Angle changing rate is big, such as larger than predetermined angle threshold value), and the face that definition is not high, can cause can not identify the face or
There is mistake in recognition result, influences the accuracy rate of face recognition result, the face figure that the present embodiment extracts according to step S202
The relevant information of picture and face, quality evaluation processing is carried out to facial image, judges that this goes out whether facial image is big side face
And whether be fuzzy face etc., exclude not can recognize that facial image with this.
Step S204, detect the key point in facial image.
If facial image is not unrecognizable facial image, the key point of locating human face on this basis, such as eyes,
Nose, mouth, chin etc., the key point informations such as the distance between position and key point including key point characteristic are extracted, by
Varied with each individual in the key point information of face, the key point information of face can characterize a person's identity, the selection of key point
And the number of key point can influence the accuracy rate of Object identifying result.
Step S205, according to key point information, extract face characteristic.
Face characteristic extraction process is carried out aiming at some features of face, the mistake being modeled to face characteristic
Journey, according to the shape description of human face and they the distance between characteristic contribute to the characteristic of face classification to obtain
According to the key point information extracted according to step S204, establishing the distance between these key points and key point characteristic
Geometric description, the feature as recognition of face.
Alternatively, in step S205 according to key point information, after extracting face characteristic, in addition to：According to face characteristic,
Clustering processing is carried out to facial image；The result of clustering processing is fed back into monitor terminal, carried out for the user of monitor terminal
Mark processing.
For example, in a face recognition process, face characteristic is extracted, according to the face characteristic, to facial image
Clustering processing is carried out, the result of clustering processing is fed back into monitor terminal, the cluster result is labeled as Zhang San by user, by face
Feature is inputted to face recognition module, then user corresponding to obtained face recognition result is Zhang San.User can repeatedly be carried out
Mark because same person on the same day at different moments, the state that is presented of Various Seasonal face be different, server
Deep learning is carried out according to user's face characteristic and face recognition result, updates face recognition module, improves recognition of face knot
The accuracy rate of fruit.
Step S206, face characteristic is inputted into face recognition module, obtains face recognition result.
The face characteristic extracted is inputted into face recognition module, because face characteristic is different, this can be characterized
The recognition result of people's identity information represents different, and face characteristic is inputted to face recognition module and calculated, obtains face
Recognition result.
Step S207, judge whether face recognition result is error detection result, if so, not processing then, this method terminates；
If it is not, then perform step S208.
In face recognition process, face, such as the portrait mould that camera is photographed may be identified as by non-face
Type is identified as face, if this kind of face recognition result is fed back into monitor terminal, can influence the usage experience of user, therefore,
Need to judge whether face recognition result is error detection result, so as to which error detection result is excluded.
Specifically, it may determine that whether face recognition result is error detection by following two modes：
Mode one：Determine whether face recognition result is error detection by manually marking.The method needs manually to enter rower
Note, and the error detection judges to come into force.If in addition, determine that face recognition result is error detection by manually marking, also
The annotation results of face characteristic and face recognition result need to be stored into database, subsequently to enter pedestrian to facial image
When face identifies, by face characteristic and face recognition result by the characteristics of objects of the error detection marked in database and people
Face recognition result is compared, and determines whether face recognition result is error detection result according to comparison result.
Mode two：The face of the error detection of face characteristic and face recognition result with having been marked in advance in database is special
Sign and face recognition result are compared, and determine whether face recognition result is error detection result according to comparison result.For example,
In a face recognition process, dummy is identified as face, by mark, then the face recognition result of dummy is
Error detection result, the face characteristic of dummy and face recognition result storage are arrived into database, when next time camera is clapped
Dummy is taken the photograph, the face recognition result that face recognition result and error detection in database are corresponded to from dummy is compared
It is right, then can be true by comparison because annotation results corresponding to face recognition result corresponding to dummy are error detection result
The face recognition result of the fixed dummy is error detection result.
User can carry out error detection mark to non-face recognition result, and server passes through the face characteristic to error detection and people
Face recognition result carries out deep learning, updates the face recognition module of error detection.
Step S208, feed back face recognition result to monitor terminal.
Specifically, if judging, face recognition result is not error detection result, feeds back recognition of face knot to monitor terminal
Fruit, to prompt user.
Face recognition result is fed back to monitor terminal by server, wherein, face recognition result is not error detection result, no
The influence to Consumer's Experience can be caused.
The face identification method based on camera scene provided according to the present embodiment, the figure shot by obtaining camera
Picture；Face in detection image, obtains facial image；Face quality evaluation processing is carried out to facial image, judges facial image
Whether it is not recognizable facial image；If facial image is not not recognizable facial image, the face in facial image is detected
Key point；According to key point information, face characteristic is extracted；Face characteristic is inputted into face recognition module, obtains face knowledge
Other result；Judge whether face recognition result is error detection result, if it is not, then feeding back face recognition result to monitor terminal.It is logical
Cross and the facial image that camera is got is handled, face recognition process is optimized, camera scene can be improved
The accuracy rate and real-time of human face recognition result, while the generation of error detection can be reduced, and can avoid because of face angle
Spend improper or facial image it is unintelligible and cause identify mistake, and can in time by face recognition result feed back to monitoring eventually
Hold to remind user.
Video monitoring is quickly popularized, and there is an urgent need to a kind of remote, non-cooperation of user for numerous video surveillance applications
Quick identity recognizing technology under state, in the hope of remote quick confirmation personnel identity, realize intelligent early-warning.Because user can not
The picture captured by camera can be observed always, and user may miss the situation that stranger enters monitored site.The present invention
Following embodiments provide a kind of face identification method based on camera scene, pass through the image that is shot to camera and carry out
Processing, can identify the face of the stranger in image, and report is sent to user according to the face recognition result of stranger
It is alert to remind.
Fig. 3 shows the face identification method flow chart based on camera scene according to further embodiment of the present invention,
As shown in figure 3, this method includes：
Step S301, obtain the image of camera shooting.
Step S302, the face in detection image, obtains facial image.
Step S303, detect the key point in facial image.
Step S304, according to key point information, extract face characteristic.
The implementation procedure of above step can be found in the description of above example, will not be repeated here.
Specifically, the key point in facial image is detected, extracts key point information；According to key point information, face is extracted
Feature.
Preferably, after step S304 extracts face characteristic, in addition to：According to face characteristic, facial image is entered
Row clustering processing；The result of clustering processing is fed back into monitor terminal, so that the user of monitor terminal is labeled processing.
For example, in a face recognition process, face characteristic is extracted, according to the face characteristic, to facial image
Clustering processing is carried out, the result of clustering processing is fed back into monitor terminal, the cluster result is labeled as Zhang San by user, by face
Feature is inputted to face recognition module and calculated, then it is Zhang San to obtain user corresponding to face recognition result.User can be more
It is secondary to be labeled because same person on the same day at different moments, the state that is presented of Various Seasonal face be it is different,
Server carries out deep learning according to the face characteristic and face recognition result of user annotation, updates face recognition module, carries
The accuracy rate of high face recognition result.
Step S305, face recognition features are inputted into face recognition module, obtain face recognition result.
Step S306, judge whether face recognition result is face corresponding to the first user marked in advance in database
Recognition result, if so, then performing step S307；If it is not, then perform step S308.
Face identification method provided in an embodiment of the present invention depends on the first user marked in advance in database corresponding
Face recognition result, user is labeled to face recognition result in advance by above-mentioned steps, such as camera photographs use
The facial image at family, key point extraction, face characteristic extraction and clustering processing are carried out to facial image, will by monitor terminal
This clustering processing result is labeled as Zhang San, then is labeled as Zhang San corresponding to the face recognition result of the user, by face characteristic with
And face recognition result storage is into database.When camera photographs the facial image again, face recognition result is calculated,
By being compared with the face recognition result in database, judge that the face recognition result is known with the face to be prestored in database
Other result whether matching, you can judge the face recognition result whether know by the face of the user marked in advance in database
Other result.
Step S307, face recognition result is fed back to monitor terminal, this method terminates.
Step S308, to monitor terminal feedback alarm signal.
If it is not face recognition result corresponding to the user marked in advance in database to judge face recognition result, right
It is stranger corresponding to the face recognition result for server, then to monitor terminal feedback alarm signal, so that monitoring is whole
User is prompted at end.
Step S309, shooting instruction is sent to camera, so that camera instructs recorded video data according to shooting.
If it is not recognition of face knot corresponding to the first user marked in advance in database to judge face recognition result
Fruit, then shooting instruction is sent to camera, so that camera records the video data for including this face according to shooting instruction.
Step S310, the video of cam feedback is sent to monitor terminal, this method and terminated.
Such as user carries out remote monitoring to family, camera shooting image, be have identified by the above method in image
People be the user not marked, it indicates that camera recorded video data, and the video of cam feedback is sent to prison
Control terminal, accordingly even when user can not monitor in real time, user, and instruction are prompted to monitor terminal by sending alarm signal
Camera records the situation of lower family, and user can observe situation to home in time.
The face identification method based on camera scene provided according to the present embodiment, the figure shot by obtaining camera
Picture；Face in detection image, obtains facial image；The facial key point in facial image is detected, extracts key point information；Root
According to key point information, face characteristic is extracted；Face characteristic is inputted into human face recognition model, obtains face recognition result, is sentenced
Whether disconnected face recognition result is recognition result corresponding to the first user marked in advance in database, if it is not, then to prison
Control terminal feedback alarm signal, shooting instruction is sent to camera, so that camera instructs recorded video data according to shooting, and
The video data transmitting of cam feedback is delivered into monitor terminal.It is right by handling the facial image that camera is got
Face recognition process optimizes, and can improve the accuracy rate of camera scene human face identification, can reduce the hair of error detection
It is raw, also warning reminding can be carried out to user according to face recognition result in addition and record associated video.
Fig. 4 shows the functional block of the face identification device based on camera scene according to another embodiment of the invention
Figure, as shown in figure 4, the device includes：
Image collection module 401, suitable for obtaining the image of camera shooting.
Face detection module 402, the face being adapted to detect in image, obtains facial image.
Key point extraction module 403, the facial key point being adapted to detect in facial image, extract key point information.
Face characteristic extraction module 404, suitable for according to key point information, extracting face characteristic.
Face recognition module 405, suitable for using face characteristic as input, obtaining face recognition result.
The face identification device based on camera scene provided according to the present embodiment, passes through the people got to camera
Face image is handled, and face recognition process is optimized, and on the one hand can improve the standard of camera scene human face identification
True rate；On the other hand, face recognition result can be quickly obtained, the image that camera is shot can be carried out continuous real-time
Processing, meets the needs of remote camera rapidly and accurately identifies identity.
Fig. 5 shows the functional block of the face identification device based on camera scene according to another embodiment of the invention
Figure, as shown in figure 5, the device further comprises on the basis of the device shown in Fig. 4：
Error detection identification module 501, suitable for judging whether face recognition result is error detection result.
First data feedback module 502, if determining that face recognition result is not error detection suitable for error detection identification module 501
As a result, face recognition result is fed back to monitor terminal.
Error detection identification module 501 is further adapted for：
Determine whether face recognition result is error detection result by manually marking；
Or the face characteristic by the error detection marked in advance in face characteristic and face recognition result and database
And face recognition result is compared, determine whether face recognition result is error detection result according to comparison result.
Error detection identification module 501 is further adapted for：If determine that face recognition result is error detection knot by manually marking
Fruit, then by the storage of the annotation results of face characteristic and face recognition result into database.
Further, the device also includes：Face quality assessment modules 503, suitable for carrying out face quality to facial image
Assessment is handled, and judges whether facial image is not recognizable facial image.
Key point extraction module 403 is further adapted for：If facial image is not not recognizable facial image, face is detected
Facial key point in image.
Preferably, not recognizable facial image includes：Deflection angle is more than the side face image of predetermined angle threshold value and/or clear
Facial image of the clear degree less than default clarity threshold.
Further, in another embodiment of the invention, the above-mentioned face identification device based on camera scene also wraps
Include：
Cluster module 504, suitable for according to face characteristic, clustering processing is carried out to facial image.
Second data feedback module 505, suitable for the result of clustering processing is fed back into monitor terminal, for monitor terminal
User is labeled processing.
Further, in another embodiment of the invention, the above-mentioned face identification device based on camera scene also wraps
Include：
Judge module 506, suitable for judging whether face recognition result is advance the first user couple marked in database
The face recognition result answered.
Alarm module 507, if judging that face recognition result has been marked in advance in database suitable for judge module 506
The first user corresponding to face recognition result, then to monitor terminal feedback alarm information.
Further, in another embodiment of the invention, the above-mentioned face identification device based on camera scene also wraps
Include：
Sending module 508, suitable for judging that face recognition result has been marked in advance in database in judge module 506
The first user corresponding in the case of face recognition result, shooting instruction is sent to camera, so that camera is according to shooting
Instruct recorded video data；
3rd data feedback module 509, suitable for the video data transmitting of cam feedback is delivered into monitor terminal.
The face identification device based on camera scene provided according to the present embodiment, passes through what camera was got
Facial image is handled, and face recognition process is optimized, and can improve the standard of camera scene human face recognition result
True rate and real-time, while the generation of error detection can be reduced, and can avoid because facial angle is improper or facial image
It is unintelligible and cause to identify mistake, and face recognition result can be fed back into monitor terminal to remind user in time.In addition
Also warning reminding can be carried out to user according to face recognition result and record associated video.
The embodiments of the invention provide a kind of nonvolatile computer storage media, the computer-readable storage medium is stored with
An at least executable instruction, the computer executable instructions can perform in above-mentioned any means embodiment based on camera scene
Face identification method.
Fig. 6 shows a kind of structural representation of computing device according to embodiments of the present invention, the specific embodiment of the invention
The specific implementation to computing device does not limit.
As shown in fig. 6, the computing device can include：Processor (processor) 602, communication interface
(Communications Interface) 604, memory (memory) 606 and communication bus 608.
Wherein：
Processor 602, communication interface 604 and memory 606 complete mutual communication by communication bus 608.
Communication interface 604, for being communicated with the network element of miscellaneous equipment such as client or other servers etc..
Processor 602, for configuration processor 610, it can specifically perform the above-mentioned recognition of face side based on camera scene
Correlation step in method embodiment.
Specifically, program 610 can include program code, and the program code includes computer-managed instruction.
Processor 602 is probably central processor CPU, or specific integrated circuit ASIC (Application
Specific Integrated Circuit), or it is arranged to implement the integrated electricity of one or more of the embodiment of the present invention
Road.The one or more processors that computing device includes, can be same type of processor, such as one or more CPU；Also may be used
To be different types of processor, such as one or more CPU and one or more ASIC.
Memory 606, for depositing program 610.Memory 606 may include high-speed RAM memory, it is also possible to also include
Nonvolatile memory (non-volatile memory), for example, at least a magnetic disk storage.
Program 610 specifically can be used for so that processor 602 performs following operation：
Obtain the image of camera shooting；
Face in detection image, obtains facial image；
The key point in facial image is detected, extracts key point information；
According to key point information, face characteristic is extracted；
Face characteristic is inputted into face recognition module, obtains face recognition result.
Program 610 specifically can be also used for so that processor 602 performs following operation：
Judge whether face recognition result is error detection result, if it is not, then feeding back face recognition result to monitor terminal.
Program 610 specifically can be also used for so that processor 602 performs following operation：
Determine whether face recognition result is error detection result by manually marking；
Or the face characteristic by the error detection marked in advance in face characteristic and face recognition result and database
And face recognition result is compared, determine whether face recognition result is error detection result according to comparison result.
Program 610 specifically can be also used for so that processor 602 performs following operation：
If determine that face recognition result is error detection result by manually marking, by face characteristic and recognition of face knot
The annotation results of fruit are stored into database.
Program 610 specifically can be also used for so that processor 602 performs following operation：
Before the facial key point in detecting facial image, face quality evaluation processing is carried out to facial image, judged
Whether facial image is not recognizable facial image；
Detection facial image in facial key point be specially：If facial image is not not recognizable facial image, examine
The facial key point surveyed in facial image.
Not recognizable facial image includes：Deflection angle is low more than the side face image and/or definition of predetermined angle threshold value
In the facial image of default clarity threshold.
Program 610 specifically can be also used for so that processor 602 performs following operation：
According to key point information, after extracting face characteristic, according to face characteristic, clustering processing is carried out to facial image；
The result of clustering processing is fed back into monitor terminal, so that the user of monitor terminal is labeled processing.
Program 610 specifically can be also used for so that processor 602 performs following operation：
Judge whether output result is face recognition result corresponding to the first user marked in advance in database, if
It is no, then to monitor terminal feedback alarm signal.
Program 610 specifically can be also used for so that processor 602 performs following operation：
Face recognition result corresponding to the first user marked in advance in judging that output result is not database
In the case of, shooting instruction is sent to camera, so that camera instructs recorded video data according to shooting；
The video data transmitting of cam feedback is delivered into monitor terminal.
Algorithm and display be not inherently related to any certain computer, virtual system or miscellaneous equipment provided herein.
Various general-purpose systems can also be used together with teaching based on this.As described above, required by constructing this kind of system
Structure be obvious.In addition, the present invention is not also directed to any certain programmed language.It should be understood that it can utilize various
Programming language realizes the content of invention described herein, and the description done above to language-specific is to disclose this hair
Bright preferred forms.
In the specification that this place provides, numerous specific details are set forth.It is to be appreciated, however, that the implementation of the present invention
Example can be put into practice in the case of these no details.In some instances, known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this description.
Similarly, it will be appreciated that in order to simplify the disclosure and help to understand one or more of each inventive aspect,
Above in the description to the exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the method for the disclosure should be construed to reflect following intention：I.e. required guarantor
The application claims of shield features more more than the feature being expressly recited in each claim.It is more precisely, such as following
Claims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following embodiment are expressly incorporated in the embodiment, wherein each claim is in itself
Separate embodiments all as the present invention.
Those skilled in the art, which are appreciated that, to be carried out adaptively to the module in the equipment in embodiment
Change and they are arranged in one or more equipment different from the embodiment.Can be the module or list in embodiment
Member or component be combined into a module or unit or component, and can be divided into addition multiple submodule or subelement or
Sub-component.In addition at least some in such feature and/or process or unit exclude each other, it can use any
Combination is disclosed to all features disclosed in this specification (including adjoint claim, summary and accompanying drawing) and so to appoint
Where all processes or unit of method or equipment are combined.Unless expressly stated otherwise, this specification (including adjoint power
Profit requires, summary and accompanying drawing) disclosed in each feature can be by providing the alternative features of identical, equivalent or similar purpose come generation
Replace.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included some features rather than further feature, but the combination of the feature of different embodiments means in of the invention
Within the scope of and form different embodiments.For example, in the following claims, embodiment claimed is appointed
One of meaning mode can use in any combination.
The all parts embodiment of the present invention can be realized with hardware, or to be run on one or more processor
Software module realize, or realized with combinations thereof.It will be understood by those of skill in the art that it can use in practice
Microprocessor either digital signal processor (DSP) come realize in computing device according to embodiments of the present invention some or it is complete
The some or all functions of portion's part.The present invention be also implemented as a part for performing method as described herein or
Person whole equipment or program of device (for example, computer program and computer program product).It is such to realize the present invention's
Program can store on a computer-readable medium, or can have the form of one or more signal.Such signal
It can download and obtain from internet website, either provide on carrier signal or provided in the form of any other.
It should be noted that the present invention will be described rather than limits the invention for above-described embodiment, and ability
Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference symbol between bracket should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" before element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of some different elements and being come by means of properly programmed computer real
It is existing.In if the unit claim of equipment for drying is listed, several in these devices can be by same hardware branch
To embody.The use of word first, second, and third does not indicate that any order.These words can be explained and run after fame
Claim.
Claims (10)
1. a kind of face identification method based on camera scene, including：
Obtain the image of camera shooting；
The face in described image is detected, obtains facial image；
The key point in the facial image is detected, extracts key point information；
According to the key point information, face characteristic is extracted；
The face characteristic is inputted into face recognition module, obtains face recognition result.
2. according to the method for claim 1, the face characteristic is inputted into face recognition module described, obtains people
After face recognition result, methods described also includes：
Judge whether the face recognition result is error detection result, if it is not, then feeding back the recognition of face knot to monitor terminal
Fruit.
It is 3. according to the method for claim 2, described to judge whether face recognition result is that error detection result further comprises：
Determine whether face recognition result is error detection result by manually marking；
Or by face characteristic and face recognition result and the face characteristic of error detection that has been marked in advance in database and
Face recognition result is compared, and determines whether face recognition result is error detection result according to comparison result.
4. according to the method for claim 3, determine whether face recognition result is error detection by manually marking described
As a result after, methods described also includes：
If determining that face recognition result is error detection result by manually marking, by face characteristic and face recognition result
Annotation results are stored into database.
It is 5. crucial according to the method any one of claim 1-4, the key point in the detection facial image, extraction
Before point information, methods described also includes：Face quality evaluation processing is carried out to the facial image, judges the facial image
Whether it is not recognizable facial image；
Key point in the detection facial image is specially：If the facial image is not not recognizable facial image,
Then detect the key point in facial image.
6. according to the method for claim 5, the not recognizable facial image includes：Deflection angle is more than predetermined angle threshold
The side face image and/or definition of value are less than the facial image of default clarity threshold.
7. according to the method any one of claim 1-6, described according to the key point information, face characteristic is extracted
Afterwards, methods described further comprises：
According to face characteristic, clustering processing is carried out to facial image；
The result of clustering processing is fed back into monitor terminal, so that the user of monitor terminal is labeled processing.
8. a kind of face identification device based on camera scene, including：
Image collection module, suitable for obtaining the image of camera shooting；
Face detection module, the face being adapted to detect in described image, obtains facial image；
Key point extraction module, the facial key point being adapted to detect in the facial image, extract key point information；
Face characteristic extraction module, suitable for according to the key point information, extracting face characteristic；
Face recognition module, suitable for using the face characteristic as input, obtaining face recognition result.
9. a kind of computing device, including：Processor, memory, communication interface and communication bus, the processor, the storage
Device and the communication interface complete mutual communication by the communication bus；
The memory is used to deposit an at least executable instruction, and the executable instruction makes the computing device such as right will
Ask operation corresponding to the face identification method based on camera scene any one of 1-7.
10. a kind of computer-readable storage medium, an at least executable instruction, the executable instruction are stored with the storage medium
Make behaviour corresponding to the face identification method based on camera scene of the computing device as any one of claim 1-7
Make.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710954276.7A CN107679504A (en) | 2017-10-13 | 2017-10-13 | Face identification method, device, equipment and storage medium based on camera scene |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710954276.7A CN107679504A (en) | 2017-10-13 | 2017-10-13 | Face identification method, device, equipment and storage medium based on camera scene |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107679504A true CN107679504A (en) | 2018-02-09 |
Family
ID=61141463
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710954276.7A Pending CN107679504A (en) | 2017-10-13 | 2017-10-13 | Face identification method, device, equipment and storage medium based on camera scene |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107679504A (en) |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108573227A (en) * | 2018-04-09 | 2018-09-25 | 深圳竹信科技有限公司 | ECG data quality evaluating method and device |
| CN108664920A (en) * | 2018-05-10 | 2018-10-16 | 深圳市深网视界科技有限公司 | A kind of cascade face cluster method and apparatus extensive in real time |
| CN108960216A (en) * | 2018-09-21 | 2018-12-07 | 浙江中正智能科技有限公司 | A kind of detection of dynamic human face and recognition methods |
| CN109242045A (en) * | 2018-09-30 | 2019-01-18 | 北京达佳互联信息技术有限公司 | Image clustering processing method, device, electronic equipment and storage medium |
| CN109359508A (en) * | 2018-08-27 | 2019-02-19 | 贵阳朗玛信息技术股份有限公司 | A kind of head portrait processing method and processing device |
| CN109461003A (en) * | 2018-11-30 | 2019-03-12 | 阿里巴巴集团控股有限公司 | Plurality of human faces scene brush face payment risk preventing control method and equipment based on multi-angle of view |
| CN109472269A (en) * | 2018-10-17 | 2019-03-15 | 深圳壹账通智能科技有限公司 | Characteristics of image configuration and method of calibration, device, computer equipment and medium |
| CN109648573A (en) * | 2018-12-20 | 2019-04-19 | 达闼科技（北京）有限公司 | A kind of robot conversation switching method, device and calculate equipment |
| CN110032921A (en) * | 2018-12-03 | 2019-07-19 | 阿里巴巴集团控股有限公司 | A kind of adjustment device and method of face recognition device |
| CN110110669A (en) * | 2019-05-08 | 2019-08-09 | 广东赛翼智能科技有限公司 | A kind of wisdom scenic spot tourist's localization method and system based on face recognition technology |
| CN110263772A (en) * | 2019-07-30 | 2019-09-20 | 天津艾思科尔科技有限公司 | A kind of face characteristic identifying system based on face key point |
| CN110263521A (en) * | 2019-06-24 | 2019-09-20 | 深圳市商汤科技有限公司 | Login guard method and device, system, electronic equipment and storage medium |
| CN110288705A (en) * | 2019-07-02 | 2019-09-27 | 北京字节跳动网络技术有限公司 | The method and apparatus for generating threedimensional model |
| CN110321767A (en) * | 2018-03-30 | 2019-10-11 | 株式会社日立制作所 | Image acquiring apparatus and method, behavior analysis system and storage medium |
| CN110909568A (en) * | 2018-09-17 | 2020-03-24 | 北京京东尚科信息技术有限公司 | Image detection method, apparatus, electronic device, and medium for face recognition |
| CN110929546A (en) * | 2018-09-19 | 2020-03-27 | 传线网络科技（上海）有限公司 | Face comparison method and device |
| CN110929545A (en) * | 2018-09-19 | 2020-03-27 | 传线网络科技（上海）有限公司 | Human face image sorting method and device |
| CN111008564A (en) * | 2019-11-01 | 2020-04-14 | 南京航空航天大学 | Uncooperative human face image recognition method and system |
| CN111126163A (en) * | 2019-11-28 | 2020-05-08 | 星络智能科技有限公司 | Intelligent panel, interaction method based on face angle detection and storage medium |
| CN111339811A (en) * | 2019-08-27 | 2020-06-26 | 杭州海康威视系统技术有限公司 | Image processing method, device, equipment and storage medium |
| CN111539295A (en) * | 2020-04-17 | 2020-08-14 | 中移（杭州）信息技术有限公司 | Face recognition method, device, system, network equipment and storage medium |
| CN111541867A (en) * | 2020-03-18 | 2020-08-14 | 北京中科医信科技有限公司 | Face recognition system suitable for medical institution and working method thereof |
| CN111784163A (en) * | 2020-07-01 | 2020-10-16 | 深圳前海微众银行股份有限公司 | Data evaluation method, device, equipment and storage medium |
| CN111931675A (en) * | 2020-08-18 | 2020-11-13 | 熵基科技股份有限公司 | Coercion alarm method, device, equipment and storage medium based on face recognition |
| CN112036262A (en) * | 2020-08-11 | 2020-12-04 | 海尔优家智能科技（北京）有限公司 | Face recognition processing method and device |
| CN112052706A (en) * | 2019-06-06 | 2020-12-08 | 鸿富锦精密工业(武汉)有限公司 | Electronic device and face recognition method |
| CN112950674A (en) * | 2021-03-09 | 2021-06-11 | 厦门市公安局 | Cross-camera track tracking method and device based on cooperation of multiple identification technologies and storage medium |
| CN113447128A (en) * | 2020-03-10 | 2021-09-28 | 百度在线网络技术（北京）有限公司 | Multi-person body temperature detection method and device, electronic equipment and storage medium |
| CN114038109A (en) * | 2021-10-27 | 2022-02-11 | 金陵科技学院 | Special access control system for school classroom epidemic situation |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102799871A (en) * | 2012-07-13 | 2012-11-28 | Tcl集团股份有限公司 | Method for tracking and recognizing face |
| CN104050449A (en) * | 2014-06-13 | 2014-09-17 | 无锡天脉聚源传媒科技有限公司 | Face recognition method and device |
| CN105701464A (en) * | 2016-01-13 | 2016-06-22 | 杭州奇客科技有限公司 | Method of determining face detection false detection and key point positioning accuracy |
| CN106228137A (en) * | 2016-07-26 | 2016-12-14 | 广州市维安科技股份有限公司 | A kind of ATM abnormal human face detection based on key point location |
-
2017
- 2017-10-13 CN CN201710954276.7A patent/CN107679504A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102799871A (en) * | 2012-07-13 | 2012-11-28 | Tcl集团股份有限公司 | Method for tracking and recognizing face |
| CN104050449A (en) * | 2014-06-13 | 2014-09-17 | 无锡天脉聚源传媒科技有限公司 | Face recognition method and device |
| CN105701464A (en) * | 2016-01-13 | 2016-06-22 | 杭州奇客科技有限公司 | Method of determining face detection false detection and key point positioning accuracy |
| CN106228137A (en) * | 2016-07-26 | 2016-12-14 | 广州市维安科技股份有限公司 | A kind of ATM abnormal human face detection based on key point location |
Non-Patent Citations (1)
| Title |
|---|
| 李勇: "智能视频之人脸识别技术的分析和应用", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (41)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110321767A (en) * | 2018-03-30 | 2019-10-11 | 株式会社日立制作所 | Image acquiring apparatus and method, behavior analysis system and storage medium |
| CN110321767B (en) * | 2018-03-30 | 2023-01-31 | 株式会社日立制作所 | Image extraction device and method, behavior analysis system, and storage medium |
| CN108573227A (en) * | 2018-04-09 | 2018-09-25 | 深圳竹信科技有限公司 | ECG data quality evaluating method and device |
| CN108573227B (en) * | 2018-04-09 | 2022-04-29 | 深圳竹信科技有限公司 | Electrocardiogram data quality evaluation method and device |
| CN108664920A (en) * | 2018-05-10 | 2018-10-16 | 深圳市深网视界科技有限公司 | A kind of cascade face cluster method and apparatus extensive in real time |
| CN108664920B (en) * | 2018-05-10 | 2022-12-20 | 东方网力科技股份有限公司 | Real-time large-scale cascading face clustering method and device |
| CN109359508A (en) * | 2018-08-27 | 2019-02-19 | 贵阳朗玛信息技术股份有限公司 | A kind of head portrait processing method and processing device |
| CN110909568A (en) * | 2018-09-17 | 2020-03-24 | 北京京东尚科信息技术有限公司 | Image detection method, apparatus, electronic device, and medium for face recognition |
| CN110929546A (en) * | 2018-09-19 | 2020-03-27 | 传线网络科技（上海）有限公司 | Face comparison method and device |
| CN110929545A (en) * | 2018-09-19 | 2020-03-27 | 传线网络科技（上海）有限公司 | Human face image sorting method and device |
| CN108960216A (en) * | 2018-09-21 | 2018-12-07 | 浙江中正智能科技有限公司 | A kind of detection of dynamic human face and recognition methods |
| CN109242045A (en) * | 2018-09-30 | 2019-01-18 | 北京达佳互联信息技术有限公司 | Image clustering processing method, device, electronic equipment and storage medium |
| CN109472269A (en) * | 2018-10-17 | 2019-03-15 | 深圳壹账通智能科技有限公司 | Characteristics of image configuration and method of calibration, device, computer equipment and medium |
| CN109461003B (en) * | 2018-11-30 | 2021-06-22 | 创新先进技术有限公司 | Multi-view-angle-based multi-face scene face brushing payment risk prevention and control method and device |
| CN109461003A (en) * | 2018-11-30 | 2019-03-12 | 阿里巴巴集团控股有限公司 | Plurality of human faces scene brush face payment risk preventing control method and equipment based on multi-angle of view |
| CN110032921A (en) * | 2018-12-03 | 2019-07-19 | 阿里巴巴集团控股有限公司 | A kind of adjustment device and method of face recognition device |
| CN109648573A (en) * | 2018-12-20 | 2019-04-19 | 达闼科技（北京）有限公司 | A kind of robot conversation switching method, device and calculate equipment |
| CN109648573B (en) * | 2018-12-20 | 2020-11-10 | 达闼科技（北京）有限公司 | Robot session switching method and device and computing equipment |
| CN110110669A (en) * | 2019-05-08 | 2019-08-09 | 广东赛翼智能科技有限公司 | A kind of wisdom scenic spot tourist's localization method and system based on face recognition technology |
| CN112052706B (en) * | 2019-06-06 | 2022-07-29 | 鸿富锦精密工业(武汉)有限公司 | Electronic device and face recognition method |
| CN112052706A (en) * | 2019-06-06 | 2020-12-08 | 鸿富锦精密工业(武汉)有限公司 | Electronic device and face recognition method |
| CN110263521A (en) * | 2019-06-24 | 2019-09-20 | 深圳市商汤科技有限公司 | Login guard method and device, system, electronic equipment and storage medium |
| CN110288705B (en) * | 2019-07-02 | 2023-08-04 | 北京字节跳动网络技术有限公司 | Method and device for generating three-dimensional model |
| CN110288705A (en) * | 2019-07-02 | 2019-09-27 | 北京字节跳动网络技术有限公司 | The method and apparatus for generating threedimensional model |
| CN110263772A (en) * | 2019-07-30 | 2019-09-20 | 天津艾思科尔科技有限公司 | A kind of face characteristic identifying system based on face key point |
| CN110263772B (en) * | 2019-07-30 | 2024-05-10 | 天津艾思科尔科技有限公司 | Face feature recognition system based on face key points |
| CN111339811B (en) * | 2019-08-27 | 2024-02-20 | 杭州海康威视系统技术有限公司 | Image processing method, device, equipment and storage medium |
| CN111339811A (en) * | 2019-08-27 | 2020-06-26 | 杭州海康威视系统技术有限公司 | Image processing method, device, equipment and storage medium |
| CN111008564A (en) * | 2019-11-01 | 2020-04-14 | 南京航空航天大学 | Uncooperative human face image recognition method and system |
| CN111126163A (en) * | 2019-11-28 | 2020-05-08 | 星络智能科技有限公司 | Intelligent panel, interaction method based on face angle detection and storage medium |
| CN113447128B (en) * | 2020-03-10 | 2023-06-23 | 百度在线网络技术（北京）有限公司 | Multi-human-body-temperature detection method and device, electronic equipment and storage medium |
| CN113447128A (en) * | 2020-03-10 | 2021-09-28 | 百度在线网络技术（北京）有限公司 | Multi-person body temperature detection method and device, electronic equipment and storage medium |
| US11521422B2 (en) | 2020-03-10 | 2022-12-06 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and device for detecting body temperature, electronic apparatus and storage medium |
| CN111541867A (en) * | 2020-03-18 | 2020-08-14 | 北京中科医信科技有限公司 | Face recognition system suitable for medical institution and working method thereof |
| CN111539295A (en) * | 2020-04-17 | 2020-08-14 | 中移（杭州）信息技术有限公司 | Face recognition method, device, system, network equipment and storage medium |
| CN111784163A (en) * | 2020-07-01 | 2020-10-16 | 深圳前海微众银行股份有限公司 | Data evaluation method, device, equipment and storage medium |
| CN112036262A (en) * | 2020-08-11 | 2020-12-04 | 海尔优家智能科技（北京）有限公司 | Face recognition processing method and device |
| CN111931675A (en) * | 2020-08-18 | 2020-11-13 | 熵基科技股份有限公司 | Coercion alarm method, device, equipment and storage medium based on face recognition |
| CN112950674A (en) * | 2021-03-09 | 2021-06-11 | 厦门市公安局 | Cross-camera track tracking method and device based on cooperation of multiple identification technologies and storage medium |
| CN112950674B (en) * | 2021-03-09 | 2024-03-05 | 厦门市公安局 | Cross-camera track tracking method and device based on cooperation of multiple recognition technologies and storage medium |
| CN114038109A (en) * | 2021-10-27 | 2022-02-11 | 金陵科技学院 | Special access control system for school classroom epidemic situation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107679504A (en) | Face identification method, device, equipment and storage medium based on camera scene | |
| CN105590097B (en) | Dual camera collaboration real-time face identification security system and method under the conditions of noctovision | |
| CN110378314A (en) | A kind of human face region image archiving method, device, electronic equipment and storage medium | |
| CN109426785B (en) | Human body target identity recognition method and device | |
| CN109325429B (en) | Method, device, storage medium and terminal for associating feature data | |
| CN113052029A (en) | Abnormal behavior supervision method and device based on action recognition and storage medium | |
| CN109766755B (en) | Face recognition method and related product | |
| US9633272B2 (en) | Real time object scanning using a mobile phone and cloud-based visual search engine | |
| CN105096223A (en) | Double-induction safety monitoring system of RFID technology and application method of system | |
| CN110418204B (en) | Video recommendation method, device, equipment and storage medium based on micro expression | |
| JP5785667B1 (en) | Person identification system | |
| CN110956118B (en) | Target object detection method and device, storage medium and electronic device | |
| CN111753594A (en) | Danger identification method, device and system | |
| CN111177469A (en) | Face retrieval method and face retrieval device | |
| CN114821282A (en) | Image detection model and method based on domain confrontation neural network | |
| CN111126411B (en) | Abnormal behavior identification method and device | |
| CN109558773A (en) | Information identifying method, device and electronic equipment | |
| CN110895663B (en) | Two-wheel vehicle identification method and device, electronic equipment and monitoring system | |
| CN113469137A (en) | Abnormal behavior recognition method and device, storage medium and electronic device | |
| CN111310844B (en) | Vehicle identification model construction method and device and identification method and device | |
| CN107666573A (en) | The method for recording of object video and device, computing device under camera scene | |
| CN112990156B (en) | Optimal target capturing method and device based on video and related equipment | |
| CN112380951B (en) | Method and device for identifying abnormal behavior, computer equipment and storage medium | |
| CN111291597B (en) | Crowd situation analysis method, device, equipment and system based on image | |
| CN113505733A (en) | Behavior recognition method, behavior recognition device, storage medium and electronic device |
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 |
Application publication date: 20180209 |
|
| RJ01 | Rejection of invention patent application after publication |