CN107844744A - With reference to the face identification method, device and storage medium of depth information - Google Patents
With reference to the face identification method, device and storage medium of depth information Download PDFInfo
- Publication number
- CN107844744A CN107844744A CN201710930240.5A CN201710930240A CN107844744A CN 107844744 A CN107844744 A CN 107844744A CN 201710930240 A CN201710930240 A CN 201710930240A CN 107844744 A CN107844744 A CN 107844744A
- Authority
- CN
- China
- Prior art keywords
- face
- image
- facial image
- identified
- target
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Library & Information Science (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of face identification method of combination depth information, this method includes:Establish the facial image Sample Storehouse that face ID, face coloured image and face depth image match each other;Build and train face Classification and Identification model, obtain the characteristic vector of face sample image;Obtain target facial image to be identified, including target face coloured image to be identified and target face depth image to be identified;The target facial image to be identified is inputted into the face classification identification model, extracts the characteristic vector of the target facial image to be identified, the face ID according to corresponding to this feature vector determines the target facial image to be identified.The present invention combines the depth information of face, by calculating the vector distance of the characteristic vector of target face coloured image and depth image to be identified and the characteristic vector of face sample image, realizes the accurate identification to face.The present invention also provides a kind of electronic installation and a kind of computer-readable recording medium.
Description
Technical field
The present invention relates to technical field of face recognition, more particularly to a kind of face identification method of combination depth information, dress
Put and storage medium.
Background technology
Recognition of face is a kind of contactless biometric identification that the facial feature information based on people carries out authentication
Technology.With the rapid development of computer and network technologies, face recognition technology has been widely used in intelligent entrance guard, public peace
Entirely, all more important industries such as amusement, military affairs and field.
Current face's identification generally uses convolutional neural networks (the Convolutional Neural based on 2D images
Networks, abbreviation CNN) returned, due to not having depth information in 2D images, therefore existing face identification system is for phase
Separating capacity like face is generally insufficient, and (such as face's colored drawing, is tatooed or illumination variation for the texture variations of same face
Deng) adaptability it is bad.
The content of the invention
The present invention provides a kind of face identification method, device and the storage medium of combination depth information, and its main purpose exists
In combining face coloured image and depth image, the accurate identification to face is realized.
To achieve the above object, the present invention provides a kind of face identification method, and this method includes:
Sample Storehouse establishment step:Obtain 2N facial images, including N face coloured images and corresponding N faces depths
Image is spent, the facial image is pre-processed, using pretreated facial image as face sample image, establishes face
The facial image Sample Storehouse that ID, face coloured image and face depth image match each other, wherein, N is integer more than 2, people
Range information comprising each point of character face with image acquisition unit in face depth image;
Model training step:Convolutional neural networks are trained with the face sample image to match each other, obtained
The characteristic vector of face classification identification model and the face sample image;
Target facial image obtaining step:Obtain target facial image to be identified, including face coloured image and corresponding
Face depth image;
Target identification step:The target facial image to be identified is inputted into the face classification identification model, extraction should
The characteristic vector of target facial image to be identified, searched according to this feature vector in the facial image Sample Storehouse and wait to know with this
The face sample image that other target facial image matches, the target face figure to be identified is determined according to the face sample image
The face ID of picture.
Preferably, the pretreatment in the Sample Storehouse establishment step includes being removed picture noise to the facial image
With the processing of correction human face posture, and face ID is marked to the facial image.
Preferably, in the target identification step according to the characteristic vector of the target facial image to be identified in the people
The face sample image matched with the target facial image to be identified is searched in face image Sample Storehouse to be included:
Calculate between the characteristic vector of the target facial image to be identified and the characteristic vector of the face sample image
Vector distance;
Using gained vector distance is minimum or face sample image less than threshold value as with the target face figure to be identified
As the face sample image to match.
Alternatively, the vector distance is COS distance or Euclidean distance.
Preferably, the 2N in the Sample Storehouse establishment step facial images obtain according to following methods:
First shooting step:The coloured image of the personage occurred using shooting area in video camera shooting preset time range
And corresponding depth image;
First face detecting step:Face figure is extracted from the coloured image and depth image using Face datection algorithm
Picture, obtain N face coloured images and corresponding N face depth images.
The target facial image obtains according to following methods:
Second shooting step:Using the target to be identified occurred in video camera shooting current shooting region coloured image and
Depth image;
Second Face datection step:Using Face datection algorithm from the coloured image and depth image of the target to be identified
Facial image is extracted, obtains the face coloured image and face depth image of the target to be identified.
Alternatively, the recognition of face detection algorithm is the algorithm based on geometric properties, Local Features Analysis algorithm, feature
Face algorithm, the algorithm based on elastic model, the one or more in neural network algorithm.
In addition, to achieve the above object, the present invention also provides a kind of electronic installation, the electronic installation includes image and obtains list
Member, memory and processor, described image acquiring unit include the video camera with depth camera function, wrapped in the memory
Recognition of face program is included, following steps are realized when the recognition of face program is by the computing device:
Sample Storehouse establishment step:Obtain 2N facial images, including N face coloured images and corresponding N faces depths
Image is spent, the facial image is pre-processed, using pretreated facial image as face sample image, establishes face
The facial image Sample Storehouse that ID, face coloured image and face depth image match each other, wherein, N is integer more than 2, people
Range information comprising each point of character face with image acquisition unit in face depth image;
Model training step:Convolutional neural networks are trained with the face sample image to match each other, obtained
The characteristic vector of face classification identification model and the face sample image;
Target facial image obtaining step:Obtain target facial image to be identified, including face coloured image and corresponding
Face depth image;
Target identification step:The target facial image to be identified is inputted into the face classification identification model, extraction should
The characteristic vector of target facial image to be identified, searched according to this feature vector in the facial image Sample Storehouse and wait to know with this
The face sample image that other target facial image matches, the target face figure to be identified is determined according to the face sample image
The face ID of picture.
Preferably, the pretreatment in the Sample Storehouse establishment step includes being removed picture noise to the facial image
With the processing of correction human face posture, and face ID is marked to the facial image.
Preferably, in the target identification step according to the characteristic vector of the target facial image to be identified in the people
The face sample image matched with the target facial image to be identified is searched in face image Sample Storehouse to be included:
Calculate between the characteristic vector of the target facial image to be identified and the characteristic vector of the face sample image
Vector distance;
Using gained vector distance is minimum or face sample image less than threshold value as with the target face figure to be identified
As the face sample image to match.
Alternatively, the vector distance is COS distance or Euclidean distance.
Preferably, the 2N in the Sample Storehouse establishment step facial images obtain according to following methods:
First shooting step:The coloured image of the personage occurred using shooting area in video camera shooting preset time range
And corresponding depth image;
First face detecting step:Face figure is extracted from the coloured image and depth image using Face datection algorithm
Picture, obtain N face coloured images and corresponding N face depth images.
The target facial image obtains according to following methods:
Second shooting step:Using the target to be identified occurred in video camera shooting current shooting region coloured image and
Depth image;
Second Face datection step:Using Face datection algorithm from the coloured image and depth image of the target to be identified
Facial image is extracted, obtains the face coloured image and face depth image of the target to be identified.
Alternatively, the recognition of face detection algorithm is the algorithm based on geometric properties, Local Features Analysis algorithm, feature
Face algorithm, the algorithm based on elastic model, the one or more in neural network algorithm.
In addition, to achieve the above object, the present invention also provides a kind of computer-readable recording medium, described computer-readable
Storage medium includes facial image Sample Storehouse, face classification identification model and recognition of face program, the recognition of face program quilt
Realized during the computing device as described above with reference to the arbitrary steps in the face identification method of depth information.
Face identification method, electronic installation and the computer-readable recording medium of combination depth information proposed by the present invention,
Pass through the face point that the face coloured image of the target to be identified obtained in real time and the input of face depth image are built and trained
Class identification model, the characteristic vector of the target facial image to be identified is extracted, calculates the target facial image to be identified
The vector distance of characteristic vector and the characteristic vector of face sample image, is searched according to vector distance in facial image Sample Storehouse
The face sample image matched with the target facial image to be identified.Due to training face Classification and Identification model, extraction face
The characteristic vector of image applies face depth image, and comprising character face, each point obtains with image in face depth image
The range information of unit, the present invention can realize more accurately to be identified to face, especially the plane characteristic height phase when face
Seemingly, in the case of stereoscopic features, such as bridge of the nose height, eye socket depth, cheekbone height difference, recognition of face can be significantly improved
Precision.
Brief description of the drawings
Fig. 1 is the running environment schematic diagram of electronic installation preferred embodiment of the present invention;
Fig. 2 is the functional block diagram of recognition of face program in Fig. 1;
Fig. 3 is the flow chart for the face identification method that the present invention combines depth information;
Fig. 4 is the flow chart for the face identification method preferred embodiment that the present invention combines depth information.
The realization, functional characteristics and advantage of the object of the invention will be described further referring to the drawings in conjunction with the embodiments.
Embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
It is the running environment schematic diagram of electronic installation preferred embodiment of the present invention shown in reference picture 1.
The electronic installation 1 can be the tool such as server, smart mobile phone, tablet personal computer, pocket computer, desktop PC
There is the terminal device of shooting and calculation function.
Shown in reference picture 1, the electronic installation 1 includes image acquisition unit 11, memory 12, processor 13, network interface
14 and communication bus 15.Described image acquiring unit 11 is mountable to particular place, such as office space, monitor area, to entering
The target captured in real-time of the particular place obtains realtime graphic, is transmitted by network by obtained realtime graphic is shot to processor
13.Network interface 14 can alternatively include wireline interface, the wave point (such as WI-FI interfaces) of standard.Communication bus 15 is used
Connection communication between these components are realized.
Memory 12 includes the readable storage medium storing program for executing of at least one type.The readable storage medium storing program for executing of at least one type
Can be such as flash memory, hard disk, multimedia card, the non-volatile memory medium of card-type memory.In certain embodiments, it is described can
Read the internal storage unit that storage medium can be the electronic installation 1, such as the hard disk of the electronic installation 1.In other realities
Apply in example, the readable storage medium storing program for executing can also be the external memory storage 11 of the electronic installation 1, such as the electronic installation 1
The plug-in type hard disk of upper outfit, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital,
SD) block, flash card (Flash Card) etc..
In the present embodiment, the readable storage medium storing program for executing of the memory 12 is generally used for storage and is installed on the electronic installation
1 recognition of face program 10, facial image Sample Storehouse and structure and the face classification identification model that trains etc..The memory
12 can be also used for temporarily storing the data that has exported or will export.
Processor 13, can be in certain embodiments a central processing unit (Central Processing Unit,
CPU), microprocessor or other data processing chips, for the program code or processing data stored in run memory 12, example
Such as perform face recognizer 10.
Fig. 1 illustrate only with component 11-15 and the electronic installation of recognition of face program 10 1, it should be understood that
It is not required for implementing all components shown, the more or less component of the implementation that can be substituted.
Alternatively, the electronic installation 1 can also include user interface, and user interface can include input block such as keyboard
(Keyboard), speech input device such as microphone (microphone) etc. has the equipment of speech identifying function, voice defeated
Go out device such as sound equipment, earphone etc., alternatively user interface can also include wireline interface, the wave point of standard.
The electronic installation 1 can also include display, and what display can also be suitably is referred to as display screen or display unit.
Can be light-emitting diode display, liquid crystal display, touch-control liquid crystal display and Organic Light Emitting Diode in some embodiments
(Organic Light-Emitting Diode, OLED) display etc..Display is used to show what is handled in the electronic apparatus 1
Information and for showing visual user interface.
The electronic installation 1 also includes touch sensor.What the touch sensor was provided carries out touch operation for user
Region be referred to as touch area.In addition, touch sensor described here can be resistive touch sensor, capacitance touch
Sensor etc..Moreover, the touch sensor not only includes the touch sensor of contact, the touch that may also comprise proximity passes
Sensor etc..In addition, the touch sensor can be single sensor, or such as multiple sensors of array arrangement.
In addition, the area of the display of the electronic installation 1 can be identical with the area of the touch sensor, can also not
Together.Alternatively, display and touch sensor stacking are set, to form touch display screen.The device, which is based on touching, to be shown
The touch control operation of display screen detecting user's triggering.
The electronic installation 1 can also include radio frequency (Radio Frequency, RF) circuit, sensor and voicefrequency circuit etc.
Deng will not be repeated here.
In the running environment schematic diagram of the preferred embodiment of electronic installation 1 shown in Fig. 1, as a kind of readable storage medium storing program for executing
Memory 12 in can include operating system, recognition of face program 10, facial image Sample Storehouse and structure and the people that trains
Face Classification and Identification model.Processor 13 realizes following steps when performing the recognition of face program 10 stored in memory 12:
Sample Storehouse establishment step:Obtain 2N facial images, including N face coloured images and corresponding N faces depths
Image is spent, the facial image is pre-processed, using pretreated facial image as face sample image, establishes face
The facial image Sample Storehouse that ID, face coloured image and face depth image match each other, wherein, N is integer more than 2, people
Range information comprising each point of character face with image acquisition unit 11 in face depth image;
Model training step:Convolutional neural networks are trained with the face sample image to match each other, obtained
The characteristic vector of face classification identification model and the face sample image;
Target facial image obtaining step:Obtain target facial image to be identified, including face coloured image and corresponding
Face depth image;
Target identification step:The target facial image to be identified is inputted into the face classification identification model, extraction should
The characteristic vector of target facial image to be identified, searched according to this feature vector in the facial image Sample Storehouse and wait to know with this
The face sample image that other target facial image matches, the target face figure to be identified is determined according to the face sample image
The face ID of picture.It is deep on combining on the functional block diagram and Fig. 3 of recognition of face program 10 that concrete principle refer to following Fig. 2
Spend the introduction of the flow chart of the face identification method of information.
It is the functional block diagram of recognition of face program 10 in Fig. 1 shown in reference picture 2.In the present embodiment, recognition of face journey
Sequence 10 is divided into multiple modules, and the plurality of module is stored in memory 12, and is performed by processor 13, to complete this hair
It is bright.Module alleged by the present invention is the series of computation machine programmed instruction section for referring to complete specific function.
The recognition of face program 10 can be divided into:Acquisition module 110, study module 120, extraction module 130 and
Identification module 140.
Acquisition module 110, the coloured image and depth image of the personage for obtaining the shooting of image acquisition unit 11, is utilized
Face datection algorithm therefrom extracts facial image and the facial image to extraction pre-processes.For example, as shown in figure 3, can be with
Facial image Sample Storehouse is established by acquisition module 110, obtains target face coloured image and depth image to be identified.
Described image acquiring unit 11 can be a video camera for integrating common camera function and depth camera function,
Two video cameras can be included:The common camera of one shoot coloured image, the depth camera of a shooting depth image
(such as Time of Flight Camera).The coloured image can be described by multiple color space, including RGB,
HSV, HIS, CMY etc..Each pixel value in the depth image represent in scene between certain point and video camera away from
From, in the present embodiment, expression the distance between face certain point and image acquisition unit 11.Described image acquiring unit 11 is clapped
When taking the photograph coloured image and depth image, shooting angle is consistent with set of frequency.For example, image acquisition unit 11 is adjusted to just
To the direction (shooting personage direct picture) of monitor area entrance, set every set time (such as 2 seconds) while shooting one
Coloured image and depth image, the coloured image and depth image of synchronization shooting can establish one by marking shooting time
Matching relationship corresponding to one.The pretreatment includes removing picture noise, correction human face posture and to every face coloured image
With depth image mark face ID.Described image noise may be caused by many reasons, such as, because device there may be in itself
Some shortcomings, some points on face possibly can not obtain depth information by image acquisition unit 11, can not know depth
Part can replace output with 0 value, can regard these 0 values as noise.In the present embodiment, first can be filled out with bilinear interpolation algorithm
This partial pixel of depth information can not be obtained by image acquisition unit 11 by mending, then remove noise jamming with Gaussian filter.
Study module 120, for the facial image to be matched each other with face ID, face coloured image and face depth image
Sample Storehouse is trained to convolutional neural networks, obtain the feature of face classification identification model and the face sample image to
Amount.
During being trained with the facial image Sample Storehouse to convolutional neural networks, each group is matched each other
Face coloured image and depth image input convolutional neural networks, extract corresponding to this group of face coloured image and depth image
Personage facial eigenvectors, sample size that training pattern is used is more, differences between samples are bigger, obtained face classification mould
Type is more accurate.As shown in figure 3, the characteristic vector that each group face coloured image and depth image extract through convolutional neural networks is
T1、T2、T3、…、Tn。
Extraction module 130, for the target face coloured image to be identified and depth image to be inputted into the face point
Class identification model, the characteristic vector of the target facial image to be identified is extracted using the face classification identification model, such as
Characteristic vector T.
Identification module 140, for being searched according to this feature vector in the facial image Sample Storehouse and the mesh to be identified
The face sample image that mark facial image matches, the target facial image to be identified is determined according to the face sample image
Face ID.
In the present embodiment, identification module 140 calculates characteristic vector and the people of the target face sample image to be identified
The vector distance of the characteristic vector of face sample image, using gained vector distance is minimum or face sample image less than threshold value as
The face sample image to match with the target facial image to be identified, determined according to the face sample image described to be identified
The face ID of target facial image.
For example, as shown in figure 3, identification module 140 is by calculating the characteristic vector T and face of target facial image to be identified
Characteristic vector T1, T2 of sample image, T3 ..., Tn distance D1, D2, D3 ..., Dn, from distance D1, D2, D3 ..., sieve in Dn
Minimum value is selected, or filters out all distance values less than predetermined threshold value, face sample graph corresponding to the distance value filtered out
As the face sample image as to match with the target facial image to be identified, the face ID of the face sample image is
The face ID of the target facial image to be identified.The vector distance can be COS distance or Euclidean distance.
Shown in reference picture 4, the flow chart of the preferred embodiment of the face identification method of depth information is combined for the present invention.Electricity
The processor 13 of sub-device 1 realizes the following step of face identification method when performing the recognition of face program 10 stored in memory 12
Suddenly:
Step S10, face ID, face coloured image and face depth image are established by acquisition module 110 and matched each other
Facial image Sample Storehouse.Acquisition module 110 obtains shooting area in preset time range and the coloured image of personage and depth occurs
Image is spent, facial image is therefrom extracted using Face datection algorithm, obtains face coloured image and corresponding face depth image,
The facial image is pre-processed, using pretreated facial image as face sample image, it is color to establish face ID, face
The facial image Sample Storehouse that color image and face depth image match each other.The pretreatment is included to the 2N facial images
It is removed picture noise and corrects the processing of human face posture, and face ID is marked to described facial image.
Step S20, built by study module 120 and train face Classification and Identification model, obtain face sample image
Characteristic vector.Study module 120 is trained with the face sample image to match each other to convolutional neural networks, obtains people
The characteristic vector of face Classification and Identification model and the face sample image.When training the face classification identification model, use
The quantity of face sample image is more, difference is bigger, and obtained face classification model is more accurate.
Step S30, target facial image to be identified, including target face to be identified colour are obtained by acquisition module 110
Image and face depth image.Acquisition module 110 obtain in current shooting region the coloured image of the target to be identified of appearance and
Depth image, facial image is extracted from the coloured image and depth image of the target to be identified using Face datection algorithm, is obtained
To the face coloured image and face depth image of target to be identified.In the present embodiment, the recognition of face detection algorithm is
Algorithm based on geometric properties, Local Features Analysis algorithm, Eigenface, the algorithm based on elastic model, neutral net are calculated
One or more in method.
Step S40, the target facial image to be identified is inputted into the face classification identification model, extraction module 130
Extract the characteristic vector of target facial image to be identified.
Step S50, identification module 140 is according to the characteristic vector of the target facial image to be identified in the facial image sample
The face sample image to match with the target facial image to be identified is searched in this storehouse, institute is determined according to the face sample image
State the face ID of target facial image to be identified.Identification module 140 is by calculating the feature of the target facial image to be identified
The vectorial vector distance between the characteristic vector of the face sample image, by gained vector distance minimum or less than threshold value
Face sample image as the face sample image to match with the target facial image to be identified, the face sample image
Face ID is the face ID of the target facial image to be identified.The vector distance can be COS distance or Euclidean away from
From.
The face identification method that the present embodiment proposes, combines face plane information and depth information, utilizes face classification
Identification model extracts the face coloured image of target to be identified and the characteristic vector of face depth image, according to this feature vector
The face sample image to match with the target facial image to be identified is searched in the facial image Sample Storehouse.Due to training
Face classification identification model, the characteristic vector of extraction facial image apply face depth image, and are wrapped in face depth image
The range information with image acquisition unit 11 is each put containing character face, the present invention can realize more accurately to be identified to face,
Especially when the plane characteristic of face is highly similar, and stereoscopic features, such as bridge of the nose height, eye socket depth, cheekbone height are different
In the case of, recognition of face precision can be significantly improved.
In addition, the embodiment of the present invention also proposes a kind of computer-readable recording medium, the computer-readable recording medium
Can be hard disk, multimedia card, SD card, flash card, SMC, read-only storage (ROM), Erasable Programmable Read Only Memory EPROM
(EPROM), any one in portable compact disc read-only storage (CD-ROM), USB storage etc. or several timess
Meaning combination.The computer-readable recording medium includes facial image Sample Storehouse, the face classification for building and training identification
Model and recognition of face program 10 etc., following operation is realized when the recognition of face program 10 is performed by the processor 13:
Sample Storehouse establishment step:Obtain 2N facial images, including N face coloured images and corresponding N faces depths
Image is spent, the facial image is pre-processed, using pretreated facial image as face sample image, establishes face
The facial image Sample Storehouse that ID, face coloured image and face depth image match each other, wherein, N is integer more than 2, people
Range information comprising each point of character face with image acquisition unit 11 in face depth image;
Model training step:Convolutional neural networks are trained with the face sample image to match each other, obtained
The characteristic vector of face classification identification model and the face sample image;
Target facial image obtaining step:Target facial image to be identified is obtained, includes the face colour of target to be identified
Image and corresponding face depth image;
Target identification step:The target facial image to be identified is inputted into the face classification identification model, extraction should
The characteristic vector of target facial image to be identified, searched according to this feature vector in the facial image Sample Storehouse and wait to know with this
The face sample image that other target facial image matches, the target face figure to be identified is determined according to the face sample image
The face ID of picture.
The embodiment of the computer-readable recording medium of the present invention and the recognition of face of above-mentioned combination depth information
Method and the embodiment of electronic installation 1 are roughly the same, will not be repeated here.
It should be noted that herein, term " comprising ", "comprising" or its any other variant are intended to non-row
His property includes, so that process, device, article or method including a series of elements not only include those key elements, and
And also include the other element being not expressly set out, or also include for this process, device, article or method institute inherently
Key element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that including this
Other identical element also be present in the process of key element, device, article or method.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on such understanding, technical scheme is substantially done to prior art in other words
Going out the part of contribution can be embodied in the form of software product, and the computer software product is stored in one as described above
In storage medium, including some instructions are make it that a station terminal equipment (can be mobile phone, computer, server, or network
Equipment etc.) perform method described in each embodiment of the present invention.
The preferred embodiments of the present invention are these are only, are not intended to limit the scope of the invention, it is every to utilize this hair
The equivalent structure or equivalent flow conversion that bright specification and accompanying drawing content are made, or directly or indirectly it is used in other related skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of face identification method of combination depth information, it is characterised in that this method includes:
Sample Storehouse establishment step:Obtain 2N facial images, including N face coloured images and corresponding N face depth maps
Picture, the facial image is pre-processed, using pretreated facial image as face sample image, establish face ID, people
The facial image Sample Storehouse that face coloured image and face depth image match each other, wherein, N is the integer more than 2;
Model training step:Convolutional neural networks are trained with the face sample image to match each other, obtain face
The characteristic vector of Classification and Identification model and the face sample image;
Target facial image obtaining step:Obtain target facial image to be identified, including face coloured image and corresponding face
Depth image;
Target identification step:The target facial image to be identified is inputted into the face classification identification model, this is extracted and waits to know
The characteristic vector of other target facial image, searched and the mesh to be identified in the facial image Sample Storehouse according to this feature vector
The face sample image that mark facial image matches, the target facial image to be identified is determined according to the face sample image
Face ID.
2. face identification method according to claim 1, it is characterised in that the pretreatment is included to the facial image
It is removed picture noise and corrects the processing of human face posture, and face ID is marked to the facial image.
3. face identification method according to claim 1, it is characterised in that 2N people in the Sample Storehouse establishment step
Face image obtains according to following methods:
First shooting step:The coloured image of personage that occurs using shooting area in video camera shooting preset time range and right
The depth image answered;
First face detecting step:Facial image is extracted from the coloured image and depth image using Face datection algorithm,
Obtain N face coloured images and corresponding N face depth images.
4. face identification method according to claim 1, it is characterised in that the target facial image obtaining step bag
Include:
Second shooting step:Utilize the coloured image and depth of the target to be identified occurred in video camera shooting current shooting region
Image;
Second Face datection step:Extracted using Face datection algorithm from the coloured image and depth image of the target to be identified
Facial image, obtain the face coloured image and face depth image of the target to be identified.
5. the face identification method according to claim 3 or 4, it is characterised in that the recognition of face detection algorithm is base
Algorithm, Local Features Analysis algorithm, Eigenface, the algorithm based on elastic model, neural network algorithm in geometric properties
In one or more.
6. face identification method according to claim 1, it is characterised in that treated in the target identification step according to
The characteristic vector of identification target facial image is searched and the target facial image to be identified in the facial image Sample Storehouse
The face sample image matched somebody with somebody includes:
Calculate between the characteristic vector of the target facial image to be identified and the characteristic vector of the face sample image to
Span from;
Using gained vector distance is minimum or face sample image less than threshold value as with the target facial image phase to be identified
The face sample image of matching.
7. face identification method according to claim 6, it is characterised in that the vector distance is COS distance or Euclidean
Distance.
8. a kind of electronic installation, including image acquisition unit, memory and processor, it is characterised in that described image obtains single
Member includes the video camera with depth camera function, and the memory includes recognition of face program, the recognition of face program quilt
Following steps are realized during the computing device:
Sample Storehouse establishment step:Obtain 2N facial images, including N face coloured images and corresponding N face depth maps
Picture, the facial image is pre-processed, using pretreated facial image as face sample image, establish face ID, people
The facial image Sample Storehouse that face coloured image and face depth image match each other, wherein, N is the integer more than 2;
Model training step:Convolutional neural networks are trained with the face sample image to match each other, obtain face
The characteristic vector of Classification and Identification model and the face sample image;
Target facial image obtaining step:Obtain target facial image to be identified, including face coloured image and corresponding face
Depth image;
Target identification step:The target facial image to be identified is inputted into the face classification identification model, this is extracted and waits to know
The characteristic vector of other target facial image, searched and the mesh to be identified in the facial image Sample Storehouse according to this feature vector
The face sample image that mark facial image matches, the target facial image to be identified is determined according to the face sample image
Face ID.
9. electronic installation according to claim 8, it is characterised in that every comprising character face in the face depth image
Individual point and the range information of described image acquiring unit.
10. a kind of computer-readable recording medium, it is characterised in that the computer-readable recording medium includes recognition of face
Program, facial image Sample Storehouse and face classification identification model, when the recognition of face program is executed by processor, realize as weighed
Profit requires the step of face identification method any one of 1 to 7.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710930240.5A CN107844744A (en) | 2017-10-09 | 2017-10-09 | With reference to the face identification method, device and storage medium of depth information |
PCT/CN2017/108804 WO2019071664A1 (en) | 2017-10-09 | 2017-10-31 | Human face recognition method and apparatus combined with depth information, and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710930240.5A CN107844744A (en) | 2017-10-09 | 2017-10-09 | With reference to the face identification method, device and storage medium of depth information |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107844744A true CN107844744A (en) | 2018-03-27 |
Family
ID=61662330
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710930240.5A Pending CN107844744A (en) | 2017-10-09 | 2017-10-09 | With reference to the face identification method, device and storage medium of depth information |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN107844744A (en) |
WO (1) | WO2019071664A1 (en) |
Cited By (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108764031A (en) * | 2018-04-17 | 2018-11-06 | 平安科技(深圳)有限公司 | Identify method, apparatus, computer equipment and the storage medium of face |
CN108763903A (en) * | 2018-05-29 | 2018-11-06 | Oppo广东移动通信有限公司 | Verify device and electronic equipment |
CN108763911A (en) * | 2018-06-06 | 2018-11-06 | Oppo广东移动通信有限公司 | Verification method, verification device, electronic equipment and computer readable storage medium |
CN108765014A (en) * | 2018-05-30 | 2018-11-06 | 中海云智慧(北京)物联网科技有限公司 | A kind of intelligent advertisement put-on method based on access control system |
CN108932505A (en) * | 2018-07-25 | 2018-12-04 | 维沃移动通信有限公司 | A kind of image processing method and electronic equipment |
CN109241890A (en) * | 2018-08-24 | 2019-01-18 | 北京字节跳动网络技术有限公司 | Face image correction method, apparatus and storage medium |
CN109472280A (en) * | 2018-09-10 | 2019-03-15 | 广东数相智能科技有限公司 | A kind of method, storage medium and electronic equipment updating species identification model library |
CN109948467A (en) * | 2019-02-28 | 2019-06-28 | 中国科学院深圳先进技术研究院 | Method, apparatus, computer equipment and the storage medium of recognition of face |
CN110188616A (en) * | 2019-05-05 | 2019-08-30 | 盎锐(上海)信息科技有限公司 | Space modeling method and device based on 2D and 3D image |
CN110378209A (en) * | 2019-06-11 | 2019-10-25 | 深圳市锐明技术股份有限公司 | A kind of driver identification verification method and device |
WO2019214557A1 (en) * | 2018-05-08 | 2019-11-14 | 深圳大学 | Method and system for detecting face image generated by deep network |
CN110458025A (en) * | 2019-07-11 | 2019-11-15 | 南京邮电大学 | A kind of personal identification and localization method based on binocular camera |
CN110532979A (en) * | 2019-09-03 | 2019-12-03 | 深圳市华芯技研科技有限公司 | A kind of 3-D image face identification method and system |
CN110533426A (en) * | 2019-08-02 | 2019-12-03 | 深圳蚂里奥技术有限公司 | A kind of method of payment and system |
CN110619200A (en) * | 2018-06-19 | 2019-12-27 | Oppo广东移动通信有限公司 | Verification system and electronic device |
CN111144298A (en) * | 2019-12-26 | 2020-05-12 | 北京华捷艾米科技有限公司 | Pedestrian identification method and device |
CN111553191A (en) * | 2020-03-30 | 2020-08-18 | 深圳壹账通智能科技有限公司 | Video classification method and device based on face recognition and storage medium |
CN111753658A (en) * | 2020-05-20 | 2020-10-09 | 高新兴科技集团股份有限公司 | Post sleep warning method and device and computer equipment |
CN111832535A (en) * | 2018-08-24 | 2020-10-27 | 创新先进技术有限公司 | Face recognition method and device |
CN112036284A (en) * | 2020-08-25 | 2020-12-04 | 腾讯科技(深圳)有限公司 | Image processing method, device, equipment and storage medium |
CN112598836A (en) * | 2020-12-14 | 2021-04-02 | 天时地理(深圳)智能科技有限公司 | Face recognition comparison system and method based on deep learning |
CN112801013A (en) * | 2021-02-08 | 2021-05-14 | 的卢技术有限公司 | Face recognition method, system and device based on key point recognition and verification |
CN113642415A (en) * | 2021-07-19 | 2021-11-12 | 南京南瑞信息通信科技有限公司 | Face feature expression method and face recognition method |
CN113837105A (en) * | 2021-09-26 | 2021-12-24 | 北京的卢深视科技有限公司 | Face recognition method, face recognition system, electronic equipment and storage medium |
US11580779B2 (en) | 2018-05-29 | 2023-02-14 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Verification system, electronic device, and verification method |
Families Citing this family (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112949362B (en) * | 2019-12-11 | 2023-10-17 | 杭州海康威视数字技术股份有限公司 | Personnel information labeling method and device and electronic equipment |
CN110210307B (en) | 2019-04-30 | 2023-11-28 | 中国银联股份有限公司 | Face sample library deployment method, face-recognition-based service processing method and device |
CN112052709B (en) * | 2019-06-06 | 2024-04-19 | 北京搜狗科技发展有限公司 | Face attribute identification method and device |
CN112115740B (en) * | 2019-06-19 | 2024-04-09 | 京东科技信息技术有限公司 | Method and apparatus for processing image |
CN110472480A (en) * | 2019-06-28 | 2019-11-19 | 深圳数马电子技术有限公司 | Item identification method, device and computer readable storage medium |
CN110502986A (en) * | 2019-07-12 | 2019-11-26 | 平安科技(深圳)有限公司 | Identify character positions method, apparatus, computer equipment and storage medium in image |
CN111325156B (en) * | 2020-02-24 | 2023-08-11 | 北京沃东天骏信息技术有限公司 | Face recognition method, device, equipment and storage medium |
CN111462227A (en) * | 2020-03-27 | 2020-07-28 | 海信集团有限公司 | Indoor personnel positioning device and method |
CN111368803A (en) * | 2020-03-28 | 2020-07-03 | 河南工业职业技术学院 | Face recognition method and system |
CN111583317B (en) * | 2020-04-29 | 2024-02-09 | 深圳市优必选科技股份有限公司 | Image alignment method and device and terminal equipment |
CN111639545B (en) * | 2020-05-08 | 2023-08-08 | 浙江大华技术股份有限公司 | Face recognition method, device, equipment and medium |
CN111709303A (en) * | 2020-05-21 | 2020-09-25 | 北京明略软件系统有限公司 | Face image recognition method and device |
CN111899281B (en) * | 2020-07-15 | 2023-10-31 | 北京和利时系统工程有限公司 | Method and system for realizing control strategy of auxiliary monitoring system based on behavior tree |
CN112052727B (en) * | 2020-07-30 | 2024-04-02 | 广州市标准化研究院 | Portrait recognition analysis system and method based on big data |
CN114698399A (en) * | 2020-10-12 | 2022-07-01 | 鸿富锦精密工业(武汉)有限公司 | Face recognition method and device and readable storage medium |
CN112329661B (en) * | 2020-11-10 | 2022-06-03 | 广东博通科技服务有限公司 | Face recognition device based on deep volume neural network and use method |
CN112380965B (en) * | 2020-11-11 | 2024-04-09 | 浙江大华技术股份有限公司 | Face recognition method and multi-camera |
CN112651306A (en) * | 2020-12-10 | 2021-04-13 | 深兰人工智能(四川)有限公司 | Tool taking monitoring method and device |
CN112766049A (en) * | 2020-12-29 | 2021-05-07 | 清华大学 | Large-scale face recognition test set construction method and device based on difficult sample mining |
CN113378715B (en) * | 2021-06-10 | 2024-01-05 | 北京华捷艾米科技有限公司 | Living body detection method based on color face image and related equipment |
CN113536966A (en) * | 2021-06-25 | 2021-10-22 | 佛山君兰智能科技有限公司 | Face recognition system and method based on Internet of things |
CN114530033A (en) * | 2022-02-18 | 2022-05-24 | 平安国际智慧城市科技股份有限公司 | Eye screen distance warning method, device, equipment and storage medium based on face recognition |
CN115471902B (en) * | 2022-11-14 | 2023-03-24 | 广州市威士丹利智能科技有限公司 | Face recognition protection method and system based on smart campus |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130300939A1 (en) * | 2012-05-11 | 2013-11-14 | Cisco Technology, Inc. | System and method for joint speaker and scene recognition in a video/audio processing environment |
CN104751140A (en) * | 2015-03-30 | 2015-07-01 | 常州大学 | Three-dimensional face recognition algorithm based on deep learning SDAE theory and application thereof in field of finance |
CN104778441A (en) * | 2015-01-07 | 2015-07-15 | 深圳市唯特视科技有限公司 | Multi-mode face identification device and method fusing grey information and depth information |
CN104899579A (en) * | 2015-06-29 | 2015-09-09 | 小米科技有限责任公司 | Face recognition method and face recognition device |
CN105513221A (en) * | 2015-12-30 | 2016-04-20 | 四川川大智胜软件股份有限公司 | ATM (Automatic Teller Machine) cheat-proof device and system based on three-dimensional human face identification |
CN205318544U (en) * | 2015-12-30 | 2016-06-15 | 四川川大智胜软件股份有限公司 | Device and system are prevented cheaing by ATM based on three dimensional face identification |
CN105847684A (en) * | 2016-03-31 | 2016-08-10 | 深圳奥比中光科技有限公司 | Unmanned aerial vehicle |
CN106022317A (en) * | 2016-06-27 | 2016-10-12 | 北京小米移动软件有限公司 | Face identification method and apparatus |
CN106650656A (en) * | 2016-12-16 | 2017-05-10 | 中新智擎有限公司 | User identification device and robot |
CN106778615A (en) * | 2016-12-16 | 2017-05-31 | 中新智擎有限公司 | A kind of method of identifying user identity, device and service for infrastructure robot |
CN106909905A (en) * | 2017-03-02 | 2017-06-30 | 中科视拓(北京)科技有限公司 | A kind of multi-modal face identification method based on deep learning |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101385599B1 (en) * | 2012-09-26 | 2014-04-16 | 한국과학기술연구원 | Method and apparatus for interfering montage |
CN105354543A (en) * | 2015-10-29 | 2016-02-24 | 小米科技有限责任公司 | Video processing method and apparatus |
CN105844635B (en) * | 2016-03-21 | 2018-10-12 | 北京工业大学 | A kind of rarefaction representation depth image method for reconstructing based on structure dictionary |
CN106919251A (en) * | 2017-01-09 | 2017-07-04 | 重庆邮电大学 | A kind of collaborative virtual learning environment natural interactive method based on multi-modal emotion recognition |
CN106991377B (en) * | 2017-03-09 | 2020-06-05 | Oppo广东移动通信有限公司 | Face recognition method, face recognition device and electronic device combined with depth information |
CN106934377B (en) * | 2017-03-14 | 2020-03-17 | 新疆智辰天林信息科技有限公司 | Improved human face detection system |
-
2017
- 2017-10-09 CN CN201710930240.5A patent/CN107844744A/en active Pending
- 2017-10-31 WO PCT/CN2017/108804 patent/WO2019071664A1/en active Application Filing
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130300939A1 (en) * | 2012-05-11 | 2013-11-14 | Cisco Technology, Inc. | System and method for joint speaker and scene recognition in a video/audio processing environment |
CN104778441A (en) * | 2015-01-07 | 2015-07-15 | 深圳市唯特视科技有限公司 | Multi-mode face identification device and method fusing grey information and depth information |
CN104751140A (en) * | 2015-03-30 | 2015-07-01 | 常州大学 | Three-dimensional face recognition algorithm based on deep learning SDAE theory and application thereof in field of finance |
CN104899579A (en) * | 2015-06-29 | 2015-09-09 | 小米科技有限责任公司 | Face recognition method and face recognition device |
CN105513221A (en) * | 2015-12-30 | 2016-04-20 | 四川川大智胜软件股份有限公司 | ATM (Automatic Teller Machine) cheat-proof device and system based on three-dimensional human face identification |
CN205318544U (en) * | 2015-12-30 | 2016-06-15 | 四川川大智胜软件股份有限公司 | Device and system are prevented cheaing by ATM based on three dimensional face identification |
CN105847684A (en) * | 2016-03-31 | 2016-08-10 | 深圳奥比中光科技有限公司 | Unmanned aerial vehicle |
CN106022317A (en) * | 2016-06-27 | 2016-10-12 | 北京小米移动软件有限公司 | Face identification method and apparatus |
CN106650656A (en) * | 2016-12-16 | 2017-05-10 | 中新智擎有限公司 | User identification device and robot |
CN106778615A (en) * | 2016-12-16 | 2017-05-31 | 中新智擎有限公司 | A kind of method of identifying user identity, device and service for infrastructure robot |
CN106909905A (en) * | 2017-03-02 | 2017-06-30 | 中科视拓(北京)科技有限公司 | A kind of multi-modal face identification method based on deep learning |
Cited By (35)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108764031A (en) * | 2018-04-17 | 2018-11-06 | 平安科技(深圳)有限公司 | Identify method, apparatus, computer equipment and the storage medium of face |
CN108764031B (en) * | 2018-04-17 | 2023-04-18 | 平安科技(深圳)有限公司 | Method, device, computer equipment and storage medium for recognizing human face |
WO2019200749A1 (en) * | 2018-04-17 | 2019-10-24 | 平安科技(深圳)有限公司 | Facial recognition method, apparatus, computing device and storage medium |
WO2019214557A1 (en) * | 2018-05-08 | 2019-11-14 | 深圳大学 | Method and system for detecting face image generated by deep network |
US11580779B2 (en) | 2018-05-29 | 2023-02-14 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Verification system, electronic device, and verification method |
CN108763903A (en) * | 2018-05-29 | 2018-11-06 | Oppo广东移动通信有限公司 | Verify device and electronic equipment |
CN108765014A (en) * | 2018-05-30 | 2018-11-06 | 中海云智慧(北京)物联网科技有限公司 | A kind of intelligent advertisement put-on method based on access control system |
CN108763911A (en) * | 2018-06-06 | 2018-11-06 | Oppo广东移动通信有限公司 | Verification method, verification device, electronic equipment and computer readable storage medium |
US10834303B2 (en) | 2018-06-06 | 2020-11-10 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Verification method, verification device, electronic device and computer readable storage medium |
EP3579142A1 (en) * | 2018-06-06 | 2019-12-11 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Verification method, verification device, electronic device and computer readable storage medium |
CN110619200A (en) * | 2018-06-19 | 2019-12-27 | Oppo广东移动通信有限公司 | Verification system and electronic device |
CN108932505A (en) * | 2018-07-25 | 2018-12-04 | 维沃移动通信有限公司 | A kind of image processing method and electronic equipment |
CN109241890A (en) * | 2018-08-24 | 2019-01-18 | 北京字节跳动网络技术有限公司 | Face image correction method, apparatus and storage medium |
CN111832535A (en) * | 2018-08-24 | 2020-10-27 | 创新先进技术有限公司 | Face recognition method and device |
CN109472280A (en) * | 2018-09-10 | 2019-03-15 | 广东数相智能科技有限公司 | A kind of method, storage medium and electronic equipment updating species identification model library |
CN109948467A (en) * | 2019-02-28 | 2019-06-28 | 中国科学院深圳先进技术研究院 | Method, apparatus, computer equipment and the storage medium of recognition of face |
CN110188616A (en) * | 2019-05-05 | 2019-08-30 | 盎锐(上海)信息科技有限公司 | Space modeling method and device based on 2D and 3D image |
CN110188616B (en) * | 2019-05-05 | 2023-02-28 | 上海盎维信息技术有限公司 | Space modeling method and device based on 2D and 3D images |
CN110378209B (en) * | 2019-06-11 | 2021-12-17 | 深圳市锐明技术股份有限公司 | Driver identity verification method and device |
CN110378209A (en) * | 2019-06-11 | 2019-10-25 | 深圳市锐明技术股份有限公司 | A kind of driver identification verification method and device |
CN110458025A (en) * | 2019-07-11 | 2019-11-15 | 南京邮电大学 | A kind of personal identification and localization method based on binocular camera |
CN110458025B (en) * | 2019-07-11 | 2022-10-14 | 南京邮电大学 | Target identification and positioning method based on binocular camera |
CN110533426A (en) * | 2019-08-02 | 2019-12-03 | 深圳蚂里奥技术有限公司 | A kind of method of payment and system |
CN110532979A (en) * | 2019-09-03 | 2019-12-03 | 深圳市华芯技研科技有限公司 | A kind of 3-D image face identification method and system |
CN111144298A (en) * | 2019-12-26 | 2020-05-12 | 北京华捷艾米科技有限公司 | Pedestrian identification method and device |
CN111553191A (en) * | 2020-03-30 | 2020-08-18 | 深圳壹账通智能科技有限公司 | Video classification method and device based on face recognition and storage medium |
CN111753658A (en) * | 2020-05-20 | 2020-10-09 | 高新兴科技集团股份有限公司 | Post sleep warning method and device and computer equipment |
CN112036284A (en) * | 2020-08-25 | 2020-12-04 | 腾讯科技(深圳)有限公司 | Image processing method, device, equipment and storage medium |
CN112036284B (en) * | 2020-08-25 | 2024-04-19 | 腾讯科技(深圳)有限公司 | Image processing method, device, equipment and storage medium |
CN112598836A (en) * | 2020-12-14 | 2021-04-02 | 天时地理(深圳)智能科技有限公司 | Face recognition comparison system and method based on deep learning |
CN112801013A (en) * | 2021-02-08 | 2021-05-14 | 的卢技术有限公司 | Face recognition method, system and device based on key point recognition and verification |
CN112801013B (en) * | 2021-02-08 | 2024-04-09 | 的卢技术有限公司 | Face recognition method, system and device based on key point recognition verification |
CN113642415A (en) * | 2021-07-19 | 2021-11-12 | 南京南瑞信息通信科技有限公司 | Face feature expression method and face recognition method |
CN113642415B (en) * | 2021-07-19 | 2024-06-04 | 南京南瑞信息通信科技有限公司 | Face feature expression method and face recognition method |
CN113837105A (en) * | 2021-09-26 | 2021-12-24 | 北京的卢深视科技有限公司 | Face recognition method, face recognition system, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
WO2019071664A1 (en) | 2019-04-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107844744A (en) | With reference to the face identification method, device and storage medium of depth information | |
CN109711243B (en) | Static three-dimensional face in-vivo detection method based on deep learning | |
CN107633204B (en) | Face occlusion detection method, apparatus and storage medium | |
CN105426857B (en) | Human face recognition model training method and device | |
CN110059661A (en) | Action identification method, man-machine interaction method, device and storage medium | |
CN110111418A (en) | Create the method, apparatus and electronic equipment of facial model | |
CN105590097B (en) | Dual camera collaboration real-time face identification security system and method under the conditions of noctovision | |
CN109190470B (en) | Pedestrian re-identification method and device | |
CN107633207A (en) | AU characteristic recognition methods, device and storage medium | |
US10489636B2 (en) | Lip movement capturing method and device, and storage medium | |
CN107679447A (en) | Facial characteristics point detecting method, device and storage medium | |
JP2018508888A (en) | System and method for performing fingerprint-based user authentication using an image captured using a mobile device | |
CN107316029B (en) | A kind of living body verification method and equipment | |
CN109559362B (en) | Image subject face replacing method and device | |
CN109685713B (en) | Cosmetic simulation control method, device, computer equipment and storage medium | |
CN110796100B (en) | Gait recognition method and device, terminal and storage device | |
CN105654033A (en) | Face image verification method and device | |
CN105117399B (en) | Image searching method and device | |
CN106485186A (en) | Image characteristic extracting method, device, terminal device and system | |
CN109410211A (en) | The dividing method and device of target object in a kind of image | |
CN111104833A (en) | Method and apparatus for in vivo examination, storage medium, and electronic device | |
CN112651333B (en) | Silence living body detection method, silence living body detection device, terminal equipment and storage medium | |
CN109670517A (en) | Object detection method, device, electronic equipment and target detection model | |
CN108108711A (en) | Face supervision method, electronic equipment and storage medium | |
CN112633221A (en) | Face direction detection method and related 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: 20180327 |
|
RJ01 | Rejection of invention patent application after publication |