CN109543633A - A kind of face identification method, device, robot and storage medium - Google Patents
A kind of face identification method, device, robot and storage medium Download PDFInfo
- Publication number
- CN109543633A CN109543633A CN201811442341.9A CN201811442341A CN109543633A CN 109543633 A CN109543633 A CN 109543633A CN 201811442341 A CN201811442341 A CN 201811442341A CN 109543633 A CN109543633 A CN 109543633A
- Authority
- CN
- China
- Prior art keywords
- characteristic information
- cloud
- face
- information
- default characteristic
- 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
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the present application discloses the embodiment of the present application and discloses a kind of face identification method, device, robot and storage medium, and this method includes by determining face characteristic information according to the face image in the pre-set user for facing angle acquisition；Optimization characteristic information is determined according to the face image in depression angle, the pre-set user for looking up angle and side view angle acquisition；Fusion feature information is determined according to the face characteristic information and the optimization characteristic information；Local default characteristic information is generated according to the fusion feature information and generates cloud default characteristic information；The facial image of user to be identified is obtained, and judges whether that cloud default characteristic information can be obtained from cloud.The embodiment of the present application can be able to achieve in networking or suspension carries out recognition of face to user, and determines fusion feature information by the face image of the pre-set user of multiple angle acquisitions, and the accuracy of recognition of face can be improved.
Description
Technical field
The invention relates to face recognition technology more particularly to a kind of face identification method, device, robot and deposit
Storage media.
Background technique
With the development of face recognition technology, face recognition application is into more and more fields；For example, medical care robot
The identity that recognition of face confirms patient can be carried out to patient by face recognition technology, and then user can be carried out corresponding
Medical treatment detection operation.
Existing robot, which generally requires just to be able to achieve from network-side acquisition identification information, carries out recognition of face to patient, and
If robot is disconnected with network-side and connect, the operation to patient's recognition of face may be cannot achieve.
Summary of the invention
The embodiment of the present application provides a kind of face identification method, device, robot and storage medium, can network or disconnected
It is able to achieve when net and recognition of face is carried out to user.
In a first aspect, the embodiment of the present application provides a kind of face identification method, comprising:
Face characteristic information is determined according to the face image in the pre-set user for facing angle acquisition；
Determine that optimization is special according to the face image in depression angle, the pre-set user for looking up angle and side view angle acquisition
Reference breath；
Fusion feature information is determined according to the face characteristic information and the optimization characteristic information；
Local default characteristic information is generated according to the fusion feature information and generates cloud default characteristic information；
The facial image of user to be identified is obtained, and judges whether that cloud default characteristic information can be obtained from cloud；
If it is the facial image is identified according to the cloud default characteristic information；
If otherwise obtaining local default characteristic information, and according to the local default characteristic information to the facial image
It is identified.
Further, cloud default characteristic information is generated according to the fusion feature information, comprising:
At least two fusion feature information are obtained, determine that feature is preset in cloud according at least two fusion features information
Information.
It is further, described that cloud default characteristic information is determined according at least two fusion features information, comprising:
Initial preset characteristic information is generated according to the fusion feature information of initial acquisition, and according to the fusion of subsequent acquisition spy
Reference breath optimizes the initial preset characteristic information, to determine cloud default characteristic information.
Second aspect, the embodiment of the present application also provides a kind of face identification devices, comprising:
Fusion feature module, for before the facial image for obtaining user to be identified, according to facing angle acquisition
The face image of pre-set user determines face characteristic information；According in depression angle, look up angle and side view angle acquisition
The face image of pre-set user determines optimization characteristic information, is determined according to the face characteristic information and the optimization characteristic information
Fusion feature information；
Characteristic module is preset, for pre- according to the local default characteristic information of fusion feature information generation and generation cloud
If characteristic information；
Judgment module for obtaining the facial image of user to be identified, and judges whether that can obtain cloud from cloud presets
Characteristic information if it is executes cloud identification module, if otherwise executing local identification module；
Cloud identification module, for being identified according to the cloud default characteristic information to the facial image；
Local identification module, for obtaining local default characteristic information, and according to the local default characteristic information to institute
Facial image is stated to be identified.
Further, the default characteristic module is used for:
At least two fusion feature information are obtained, determine that feature is preset in cloud according at least two fusion features information
Information.
Further, the default characteristic module is used for:
Initial preset characteristic information is generated according to the fusion feature information of initial acquisition, and according to the fusion of subsequent acquisition spy
Reference breath optimizes the initial preset characteristic information, to determine cloud default characteristic information.
The third aspect the embodiment of the present application also provides a kind of robot, including memory, processor and is stored in storage
On device and the computer program that can run on a processor, the processor realize that the application is arbitrarily implemented when executing described program
A kind of face identification method described in example.
Fourth aspect, the embodiment of the present application also provides a kind of computer readable storage mediums, are stored thereon with computer
Program, the program realize a kind of face identification method described in the application any embodiment when being executed by processor.
The embodiment of the present application discloses a kind of face recognition scheme, by according in the pre-set user for facing angle acquisition
Face image determines face characteristic information；According in depression angle, the pre-set user of looking up angle and side view angle acquisition
Face image determines optimization characteristic information；Determine that fusion feature is believed according to the face characteristic information and the optimization characteristic information
Breath；Local default characteristic information is generated according to the fusion feature information and generates cloud default characteristic information；It obtains to be identified
The facial image of user, and judge whether that cloud default characteristic information can be obtained from cloud；If it is pre- according to the cloud
If characteristic information identifies the facial image；If otherwise obtaining local default characteristic information, and according to the local
Default characteristic information identifies the facial image.The embodiment of the present application can be able to achieve in networking or suspension to
Family carries out recognition of face, and determines fusion feature information, Ke Yiti by the face image of the pre-set user of multiple angle acquisitions
The accuracy of high recognition of face.
Detailed description of the invention
Fig. 1 is a kind of flow chart for face identification method that the embodiment of the present application one provides；
Fig. 2 is a kind of flow chart for face identification method that the embodiment of the present application two provides；
Fig. 3 is the flow chart for another face identification method that the embodiment of the present application two provides；
Fig. 4 is the structural schematic diagram for the face identification device that the embodiment of the present application three provides；
Fig. 5 is a kind of hardware structural diagram for robot that the embodiment of the present application four provides.
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the application, rather than the restriction to the application.It also should be noted that in order to just
Part relevant to the application is illustrated only in description, attached drawing rather than entire infrastructure.
Embodiment one
Fig. 1 is a kind of flow chart for face identification method that the embodiment of the present application one provides, and this method can be known by face
Other device executes, wherein the device can generally can integrate in robot by software and or hardware realization, specific to wrap
Include following steps:
S110, the facial image for obtaining user to be identified, and judge whether that cloud default characteristic information can be obtained from cloud；
If it is operation S111 is executed, if otherwise executing operation S112.
Wherein, the embodiment of the present application, which can be, applies in robot, and the user to be identified is robot execution
The user of interaction.Illustratively, the artificial medical care robot of machine, medical care robot can execute the behaviour of medical care detection to patient
Make, correspondingly, user to be identified can be the patient that medical care robot executes medical care detection operation.It is configured in the robot
Camera can obtain the facial image of user to be identified by the camera of robot.It can also be through external image
Acquisition device acquires the facial image of user to be identified, and the people of user to be identified is obtained from the image collecting device of the outside
Face image.
The cloud can be the corresponding cloud server of robot.Network module is configured in robot, robot can
To access internet by network module, and cloud default characteristic information is obtained from cloud.It can be by judging the net of robot
Whether network module accesses internet to determine whether cloud default characteristic information can be obtained from cloud, if the network module of robot
Internet is not accessed, then can not get cloud default characteristic information from cloud.It can also be passed by the network of network module
Defeated rate to determine whether can from cloud obtain cloud default characteristic information, if network transmission speed is slow, network delay compared with
Seriously, then can determination can not get cloud default characteristic information from cloud, and then according to local default characteristic information come pair
Facial image is identified.
S111, if it is according to the cloud default characteristic information facial image is identified.
The cloud default characteristic information is the facial feature information of user gathered in advance, and cloud default characteristic information is made
Facial image identified for identification reference information.Illustratively, the characteristic information in the facial image can be extracted,
And match the characteristic information of facial image with cloud default characteristic information, if matching degree is higher, can determine described
The corresponding user to be identified of facial image can be made robot carry out subsequent interaction to user to be identified and be grasped by verifying
Make.
It illustratively, include the facial feature information of multiple and different users in the cloud default characteristic information, it can be with
It is matched by the facial image for the user to be identified that will acquire with multiple and different facial feature informations, chooses matching rate
Highest facial feature information is determined as recognition result.
It is alternatively possible to be carried out according to the cloud default characteristic information to the facial image by cloud server
Identification.
If S112, otherwise obtaining local default characteristic information, and according to the local default characteristic information to the people
Face image is identified.
The local default characteristic information is the facial feature information of the user of default acquisition, and local default characteristic information is deposited
It stores up in being locally stored of robot, when cloud default characteristic information can not be obtained from cloud, passes through the sheet for obtaining robot
Local default characteristic information in ground storage identifies facial image.Illustratively, the facial image can be extracted
In characteristic information, and the characteristic information of facial image is matched with local default characteristic information, if matching degree is higher,
It can determine that the corresponding user to be identified of the facial image passes through verifying, and then robot can be made to carry out user to be identified
Subsequent interactive operation.Wherein it is possible to be by robot according to the local default characteristic information to the facial image into
Row identification.
The embodiment of the present application discloses a kind of face identification method, by obtaining the facial image of user to be identified, and sentences
It is disconnected whether to obtain cloud default characteristic information from cloud；If it is according to the cloud default characteristic information to the face
Image is identified；If otherwise obtaining local default characteristic information, and according to the local default characteristic information to the people
Face image is identified, can be able to achieve in networking or suspension and be carried out recognition of face to user.
Embodiment two
Fig. 2 is a kind of flow chart for face identification method that the embodiment of the present application two provides, and this method can be known by face
Other device executes, wherein the device can generally can integrate on a hardware platform, specifically by software and or hardware realization
Include the following steps:
S120, fusion feature information is generated according to the face image of the pre-set user in the acquisition of at least two predetermined angles.
The face of people be it is three-dimensional, face's piece only may can only be presented by the face image of the user of an angle shot
The feature in face, so by the face image for acquiring pre-set user at least two predetermined angles, according to pre- at least two
If the face image of the pre-set user of angle acquisition fusion feature information generated, can embody more fully face feature.
Optionally, the predetermined angle includes positive angle, depression angle, looks up angle and side view angle.
Wherein, it by facing the positive face of the i.e. user of face image of the pre-set user of angle acquisition, is adopted by depression angle
The face image of collection is to overlook face, and the face image by looking up angle acquisition is to look up face, passes through the face of side view angle acquisition
Portion's image is side face image.The side view angle can be the corresponding side view angle of left face of user, be also possible to the right side of user
The side view angle of face, because there are certain symmetry for the left and right face of people, it is possible to from the side of any one side view angle acquisition
Face image.Furthermore it is also possible to be the right face image for both having passed through right side angle acquisition user, further through left side angle acquisition user's
Left face image can so obtain more facial feature informations.
Illustratively, the face image of the user of different predetermined angles can be acquired by the first acquisition device, described
One acquisition device includes four cameras, and the first camera is arranged in the position of face user face on the first acquisition device, is used
In the face image of acquisition user；Positioned at the second camera of the top of the first camera on the first acquisition device, for adopting
Collect the vertical view face image of user；Positioned at the third camera of the lower section of the first camera on the first acquisition device, for acquiring
User's looks up face image；Positioned at the 4th camera of the left or right side of the first camera on the first acquisition device, it is used for
Acquire the right side face image or left side face image of user.First acquisition device can also include five cameras, that is, include
Above-mentioned the first camera, second camera and third camera, further includes being respectively set at left and right sides of the first camera
The 4th camera and the 5th camera, so as to acquire the left face and right face of user simultaneously.It is acquired in the first acquisition device
To after the face image of the user of different predetermined angles, the data of face image can be transmitted to robot and/or transmission
To cloud server.
Optionally, as shown in figure 3, the face image life for the pre-set user that the basis is acquired at least two predetermined angles
It can be implemented by following manner at the operation of fusion feature information:
S1201, face characteristic information is determined according to the face image in the pre-set user for facing angle acquisition.
Wherein, the basis according to determined by the face image for the pre-set user for facing angle acquisition is facing angle acquisition
The face image of pre-set user is the face image of user, and face image generally comprises the position distribution letter of face's organ of user
Breath includes the position of face's organ according to the face characteristic information that the face image in the pre-set user for facing angle acquisition determines
Set distributed intelligence.It does not include user's chin to the area of neck but not including that feature of the side face of user to the region of ear yet
Feature in domain etc., so needing further to determine other features according to the face image of the pre-set user of other angles acquisition
Information.
S1202, it is determined according to the face image in depression angle, the pre-set user for looking up angle and side view angle acquisition
Optimize characteristic information.
The optimization characteristic information is the characteristic information not acquired from the face image for face angle shot；It is exemplary
Ground, optimization characteristic information includes the shape information of ear and the shape information of chin etc..Use can be collected by depression angle
The shape of face information of the vertical view at family, the shape information for collecting the chin of user by looking up angle, is arrived by side view angle acquisition
The shape information of the ear of user, and then fusion feature information can be determined according to optimization characteristic information and face characteristic information.
S1203, fusion feature information is determined according to the face characteristic information and the optimization characteristic information.
Wherein, the face characteristic information includes facing the characteristic information of face's key point of angle shot, the optimization
It include the characteristic information not acquired from the face image for face angle shot in characteristic information, by face characteristic information and excellent
Change characteristic information as fusion feature information, fusion feature information can embody more fully face characteristic information, and fusion is special
Reference breath identifies facial image as identification reference information, and the accuracy of recognition of face can be improved.
Fusion feature information is generated into local default characteristic information and generates cloud default characteristic information and is used to carry out face
Identification, can be when getting the facial image of user to be identified, because including that comprehensive face is special in fusion feature information
Reference breath, so the shooting angle of the facial image regardless of user to be identified, can accurately identify the user to be identified
Facial image.
S121, local default characteristic information is generated according to the fusion feature information and generates cloud default characteristic information.
Wherein it is possible to fusion feature information is stored in being locally stored of robot, as local default characteristic information,
When carrying out recognition of face, the fusion feature information prestored is called to identify facial image as local default characteristic information.
It is stored in addition, fusion feature information is sent in cloud server by network module, it, can when carrying out recognition of face
To call the fusion feature information of cloud server storage as cloud default characteristic information.
It is alternatively possible to obtain at least two fusion feature information, and true according at least two fusion features information
Determine cloud default characteristic information.
Wherein, at least two fusion feature information include the fusion feature information that front and back repeatedly obtains, and be can be to same
The fusion feature information repeatedly obtained before and after a pre-set user.According at least two fusion feature information, can advanced optimize
The accuracy of cloud default characteristic information.
Optionally, described to determine that cloud default characteristic information be under according at least two fusion features information
The mode of stating is implemented:
Initial preset characteristic information is generated according to the fusion feature information of initial acquisition, and according to the fusion of subsequent acquisition spy
Reference breath optimizes the initial preset characteristic information, to determine cloud default characteristic information.
Wherein, the fusion feature information of initial acquisition most starts the pre-set user acquired at least two predetermined angles
Face image determined by fusion feature information, the fusion feature information of subsequent acquisition is the fusion obtained in the follow-up process
Characteristic information can be corrected optimization to the fusion feature information initially obtained according to the fusion feature information of subsequent acquisition,
To obtain cloud default characteristic information.
Illustratively, if at least two fusion feature information are special to the fusion repeatedly obtained before and after the same pre-set user
The fusion feature information of subsequent acquisition, then can be increased the identification reference information of the pre-set user by reference breath, so can be excellent
Change cloud default characteristic information, the identification accuracy to the pre-set user can be improved.
S122, the facial image for obtaining user to be identified, and judge whether that cloud default characteristic information can be obtained from cloud.
S123, if it is according to the cloud default characteristic information facial image is identified.
If S124, otherwise obtaining local default characteristic information, and according to the local default characteristic information to the people
Face image is identified.
The specific embodiment of aforesaid operations can refer to associated description above, and details are not described herein.
The embodiment of the present application passes through melts according to the face image generation of the pre-set user in the acquisition of at least two predetermined angles
It closes characteristic information, face characteristic information is determined according to the face image in the pre-set user for facing angle acquisition, and according to institute
It states fusion feature information to generate local default characteristic information and generate cloud default characteristic information, passes through fusion feature information conduct
It identifies reference information, the accuracy of recognition of face can be improved.
Embodiment three
Fig. 4 is the structural schematic diagram of face identification device that the embodiment of the present application three provides, the device can by software and/
Or hardware realization, it generally can integrate on a hardware platform.As shown in figure 4, the face identification device includes:
Judgment module 210, for obtaining the facial image of user to be identified, and judging whether can be pre- from cloud acquisition cloud
If characteristic information, cloud identification module 211 is if it is executed, if otherwise executing local identification module 212；
Cloud identification module 211, for being identified according to the cloud default characteristic information to the facial image；
Local identification module 212, for obtaining local default characteristic information, and according to the local default characteristic information pair
The facial image is identified.
The embodiment of the present application discloses a kind of face identification device, by obtaining the facial image of user to be identified, and sentences
It is disconnected whether to obtain cloud default characteristic information from cloud；If it is according to the cloud default characteristic information to the face
Image is identified；If otherwise obtaining local default characteristic information, and according to the local default characteristic information to the people
Face image is identified.The embodiment of the present application can be able to achieve in networking or suspension carries out recognition of face to user.
Optionally, further includes:
Fusion feature module, for before the facial image for obtaining user to be identified, according at least two preset angles
The face image for spending the pre-set user of acquisition generates fusion feature information；
Characteristic module is preset, for pre- according to the local default characteristic information of fusion feature information generation and generation cloud
If characteristic information.
Optionally, the predetermined angle includes positive angle, depression angle, looks up angle and side view angle.
Optionally, fusion feature module is specifically used for: true according to the face image in the pre-set user for facing angle acquisition
Determine face characteristic information；It is true according to the face image in depression angle, the pre-set user for looking up angle and side view angle acquisition
Surely optimize characteristic information, fusion feature information is determined according to the face characteristic information and the optimization characteristic information.
Optionally, default characteristic module is specifically used for: at least two fusion feature information is obtained, according to described at least two
Fusion feature information determines cloud default characteristic information.
Optionally, default characteristic module is specifically used for: it is special to generate initial preset according to the fusion feature information of initial acquisition
Reference breath, and the initial preset characteristic information is optimized according to the fusion feature information of subsequent acquisition, to determine cloud
Default characteristic information.
Example IV
The embodiment of the present application also provides a kind of storage medium comprising computer executable instructions, and the computer is executable
Instruction is used to execute a kind of face identification method when being executed by computer processor, this method comprises:
The facial image of user to be identified is obtained, and judges whether that cloud default characteristic information can be obtained from cloud；
If it is the facial image is identified according to the cloud default characteristic information；
If otherwise obtaining local default characteristic information, and according to the local default characteristic information to the facial image
It is identified.
Optionally, which can be also used for executing the application times when being executed by computer processor
A kind of face identification method provided by embodiment of anticipating.
By the description above with respect to embodiment, it is apparent to those skilled in the art that, the application
It can be realized by software and required common hardware, naturally it is also possible to which by hardware realization, but in many cases, the former is more
Good embodiment.Based on this understanding, the technical solution of the application substantially in other words contributes to the prior art
Part can be embodied in the form of software products, which can store in computer readable storage medium
In, floppy disk, read-only memory (Read-Only Memory, ROM), random access memory (Random such as computer
Access Memory, RAM), flash memory (FLASH), hard disk or CD etc., including some instructions are with so that a computer is set
Standby (can be personal computer, server or the network equipment etc.) executes method described in each embodiment of the application.
Embodiment five
As shown in figure 5, a kind of hardware structural diagram of the robot provided for the embodiment of the present application five, as shown in figure 5,
The robot includes:
One or more processors 410, in Fig. 5 by taking a processor 410 as an example；
Memory 420；
The robot can also include: input unit 430 and output device 440.
Processor 410, memory 420, input unit 430 and output device 440 in the robot can be by total
Line or other modes connect, in Fig. 5 for being connected by bus.
Memory 420 be used as a kind of non-transient computer readable storage medium, can be used for storing software program, computer can
Execute program and module, as the corresponding program instruction/module of one of the embodiment of the present application face identification method (for example,
Attached judgment module shown in Fig. 4 210, cloud identification module 211 and local identification module 212).Processor 410 is deposited by operation
Software program, instruction and module in memory 420 are stored up, at the various function application and data of robot
Reason realizes a kind of face identification method of above method embodiment.
Memory 420 may include storing program area and storage data area, wherein storing program area can store operation system
Application program required for system, at least one function；Storage data area, which can be stored, uses created data according to robot
Deng.In addition, memory 420 may include high-speed random access memory, it can also include non-transitory memory, for example, at least
One disk memory, flush memory device or other non-transitory solid-state memories.In some embodiments, memory 420
Optional includes the memory remotely located relative to processor 410, these remote memories can pass through network connection to terminal
Equipment.The example of above-mentioned network includes but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
Input unit 430 can be used for receiving the number or character information of input, and generate the user setting with robot
And the related key signals input of function control.Output device 440 may include that display screen etc. shows equipment.
Note that above are only the preferred embodiment and institute's application technology principle of the application.It will be appreciated by those skilled in the art that
The application is not limited to specific embodiment described here, be able to carry out for a person skilled in the art it is various it is apparent variation,
The protection scope readjusted and substituted without departing from the application.Therefore, although being carried out by above embodiments to the application
It is described in further detail, but the application is not limited only to above embodiments, in the case where not departing from the application design, also
It may include more other equivalent embodiments, and scope of the present application is determined by the scope of the appended claims.
Claims (8)
1. a kind of face identification method characterized by comprising
Face characteristic information is determined according to the face image in the pre-set user for facing angle acquisition；
Optimization feature letter is determined according to the face image in depression angle, the pre-set user for looking up angle and side view angle acquisition
Breath；
Fusion feature information is determined according to the face characteristic information and the optimization characteristic information；
Local default characteristic information is generated according to the fusion feature information and generates cloud default characteristic information；
The facial image of user to be identified is obtained, and judges whether that cloud default characteristic information can be obtained from cloud；
If it is the facial image is identified according to the cloud default characteristic information；
If otherwise obtaining local default characteristic information, and the facial image is carried out according to the local default characteristic information
Identification.
2. the method according to claim 1, wherein generating cloud according to the fusion feature information presets feature
Information, comprising:
At least two fusion feature information are obtained, determine that feature letter is preset in cloud according at least two fusion features information
Breath.
3. according to the method described in claim 2, it is characterized in that, described determine according at least two fusion features information
Cloud default characteristic information, comprising:
Initial preset characteristic information is generated according to the fusion feature information of initial acquisition, and is believed according to the fusion feature of subsequent acquisition
Breath optimizes the initial preset characteristic information, to determine cloud default characteristic information.
4. a kind of face identification device characterized by comprising
Fusion feature module, for before the facial image for obtaining user to be identified, according to facing the default of angle acquisition
The face image of user determines face characteristic information；According in depression angle, look up the default of angle and side view angle acquisition
The face image of user determines optimization characteristic information, determines fusion according to the face characteristic information and the optimization characteristic information
Characteristic information；
Default characteristic module, for generating local default characteristic information according to the fusion feature information and generating the default spy in cloud
Reference breath；
Judgment module for obtaining the facial image of user to be identified, and judges whether that can obtain cloud from cloud presets feature
Information if it is executes cloud identification module, if otherwise executing local identification module；
Cloud identification module, for being identified according to the cloud default characteristic information to the facial image；
Local identification module, for obtaining local default characteristic information, and according to the local default characteristic information to the people
Face image is identified.
5. according to the method described in claim 4, it is characterized in that, the default characteristic module is used for:
At least two fusion feature information are obtained, determine that feature letter is preset in cloud according at least two fusion features information
Breath.
6. according to the method described in claim 5, it is characterized in that, the default characteristic module is used for:
Initial preset characteristic information is generated according to the fusion feature information of initial acquisition, and is believed according to the fusion feature of subsequent acquisition
Breath optimizes the initial preset characteristic information, to determine cloud default characteristic information.
7. a kind of robot including memory, processor and stores the computer that can be run on a memory and on a processor
Program, which is characterized in that the processor realizes the method according to claim 1 when executing described program.
8. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is held by processor
The method according to claim 1 is realized when row.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811442341.9A CN109543633A (en) | 2018-11-29 | 2018-11-29 | A kind of face identification method, device, robot and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811442341.9A CN109543633A (en) | 2018-11-29 | 2018-11-29 | A kind of face identification method, device, robot and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109543633A true CN109543633A (en) | 2019-03-29 |
Family
ID=65851023
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811442341.9A Pending CN109543633A (en) | 2018-11-29 | 2018-11-29 | A kind of face identification method, device, robot and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109543633A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110598565A (en) * | 2019-08-16 | 2019-12-20 | 信利光电股份有限公司 | Far and near face recognition method and device and automatic door |
| CN111781993A (en) * | 2020-06-28 | 2020-10-16 | 联想(北京)有限公司 | Information processing method, system and computer readable storage medium |
| CN111814701A (en) * | 2020-07-13 | 2020-10-23 | 安徽兰臣信息科技有限公司 | Children face recognition algorithm for feature migration learning based on double-layer heterogeneous network |
| CN111950325A (en) * | 2019-05-15 | 2020-11-17 | 杭州海康威视数字技术股份有限公司 | Target identification method and device and electronic equipment |
| CN112560669A (en) * | 2020-12-14 | 2021-03-26 | 杭州趣链科技有限公司 | Face posture estimation method and device and electronic equipment |
| CN112819106A (en) * | 2021-04-16 | 2021-05-18 | 江西博微新技术有限公司 | IFC component type identification method, device, storage medium and equipment |
| CN113561908A (en) * | 2021-07-27 | 2021-10-29 | 奇瑞新能源汽车股份有限公司 | Control method and device of vehicle-mounted face recognition equipment |
| CN114007101A (en) * | 2021-10-29 | 2022-02-01 | 中国联合网络通信集团有限公司 | Processing method and device for fusion display device and storage medium |
| CN114445951A (en) * | 2020-10-30 | 2022-05-06 | 许沁沁 | Campus intelligent management system and method |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100828412B1 (en) * | 2006-11-06 | 2008-05-09 | 연세대학교 산학협력단 | 3d face recognition method using multiple point signature |
| US20100150409A1 (en) * | 2008-12-12 | 2010-06-17 | Tektronix, Inc. | Method and apparatus for automatic illuminant compensation in video surveillance |
| US20130111337A1 (en) * | 2011-11-02 | 2013-05-02 | Arcsoft Inc. | One-click makeover |
| CN104636725A (en) * | 2015-02-04 | 2015-05-20 | 华中科技大学 | Gesture recognition method based on depth image and gesture recognition system based on depth images |
| CN104751144A (en) * | 2015-04-02 | 2015-07-01 | 山东大学 | Frontal face quick evaluation method for video surveillance |
| CN106503687A (en) * | 2016-11-09 | 2017-03-15 | 合肥工业大学 | The monitor video system for identifying figures of fusion face multi-angle feature and its method |
| CN106991403A (en) * | 2017-04-07 | 2017-07-28 | 移康智能科技（上海）股份有限公司 | A kind of method and apparatus of recognition of face |
| WO2017183038A1 (en) * | 2016-04-20 | 2017-10-26 | Wishelf Ltd. | System and method for monitoring stocking shelves |
| CN107622227A (en) * | 2017-08-25 | 2018-01-23 | 深圳依偎控股有限公司 | A kind of method, terminal device and the readable storage medium storing program for executing of 3D recognitions of face |
| CN107705248A (en) * | 2017-10-31 | 2018-02-16 | 广东欧珀移动通信有限公司 | Image processing method, device, electronic equipment and computer-readable recording medium |
| CN107958244A (en) * | 2018-01-12 | 2018-04-24 | 成都视观天下科技有限公司 | A kind of face identification method and device based on the fusion of video multiframe face characteristic |
| CN108447143A (en) * | 2018-05-15 | 2018-08-24 | 兰州工业学院 | A kind of Intelligent roll calling system |
| CN108509828A (en) * | 2017-02-28 | 2018-09-07 | 深圳市朗驰欣创科技股份有限公司 | A kind of face identification method and face identification device |
| CN108537135A (en) * | 2018-03-16 | 2018-09-14 | 北京市商汤科技开发有限公司 | The training method and device of Object identifying and Object identifying network, electronic equipment |
| US10091412B1 (en) * | 2017-06-30 | 2018-10-02 | Polycom, Inc. | Optimal view selection method in a video conference |
| CN108875516A (en) * | 2017-12-12 | 2018-11-23 | 北京旷视科技有限公司 | Face identification method, device, system, storage medium and electronic equipment |
-
2018
- 2018-11-29 CN CN201811442341.9A patent/CN109543633A/en active Pending
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100828412B1 (en) * | 2006-11-06 | 2008-05-09 | 연세대학교 산학협력단 | 3d face recognition method using multiple point signature |
| US20100150409A1 (en) * | 2008-12-12 | 2010-06-17 | Tektronix, Inc. | Method and apparatus for automatic illuminant compensation in video surveillance |
| US20130111337A1 (en) * | 2011-11-02 | 2013-05-02 | Arcsoft Inc. | One-click makeover |
| CN104636725A (en) * | 2015-02-04 | 2015-05-20 | 华中科技大学 | Gesture recognition method based on depth image and gesture recognition system based on depth images |
| CN104751144A (en) * | 2015-04-02 | 2015-07-01 | 山东大学 | Frontal face quick evaluation method for video surveillance |
| WO2017183038A1 (en) * | 2016-04-20 | 2017-10-26 | Wishelf Ltd. | System and method for monitoring stocking shelves |
| CN106503687A (en) * | 2016-11-09 | 2017-03-15 | 合肥工业大学 | The monitor video system for identifying figures of fusion face multi-angle feature and its method |
| CN108509828A (en) * | 2017-02-28 | 2018-09-07 | 深圳市朗驰欣创科技股份有限公司 | A kind of face identification method and face identification device |
| CN106991403A (en) * | 2017-04-07 | 2017-07-28 | 移康智能科技（上海）股份有限公司 | A kind of method and apparatus of recognition of face |
| US10091412B1 (en) * | 2017-06-30 | 2018-10-02 | Polycom, Inc. | Optimal view selection method in a video conference |
| CN107622227A (en) * | 2017-08-25 | 2018-01-23 | 深圳依偎控股有限公司 | A kind of method, terminal device and the readable storage medium storing program for executing of 3D recognitions of face |
| CN107705248A (en) * | 2017-10-31 | 2018-02-16 | 广东欧珀移动通信有限公司 | Image processing method, device, electronic equipment and computer-readable recording medium |
| CN108875516A (en) * | 2017-12-12 | 2018-11-23 | 北京旷视科技有限公司 | Face identification method, device, system, storage medium and electronic equipment |
| CN107958244A (en) * | 2018-01-12 | 2018-04-24 | 成都视观天下科技有限公司 | A kind of face identification method and device based on the fusion of video multiframe face characteristic |
| CN108537135A (en) * | 2018-03-16 | 2018-09-14 | 北京市商汤科技开发有限公司 | The training method and device of Object identifying and Object identifying network, electronic equipment |
| CN108447143A (en) * | 2018-05-15 | 2018-08-24 | 兰州工业学院 | A kind of Intelligent roll calling system |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111950325A (en) * | 2019-05-15 | 2020-11-17 | 杭州海康威视数字技术股份有限公司 | Target identification method and device and electronic equipment |
| CN111950325B (en) * | 2019-05-15 | 2024-03-08 | 杭州海康威视数字技术股份有限公司 | Target identification method and device and electronic equipment |
| CN110598565A (en) * | 2019-08-16 | 2019-12-20 | 信利光电股份有限公司 | Far and near face recognition method and device and automatic door |
| CN111781993B (en) * | 2020-06-28 | 2022-04-22 | 联想(北京)有限公司 | Information processing method, system and computer readable storage medium |
| CN111781993A (en) * | 2020-06-28 | 2020-10-16 | 联想(北京)有限公司 | Information processing method, system and computer readable storage medium |
| CN111814701A (en) * | 2020-07-13 | 2020-10-23 | 安徽兰臣信息科技有限公司 | Children face recognition algorithm for feature migration learning based on double-layer heterogeneous network |
| CN114445951A (en) * | 2020-10-30 | 2022-05-06 | 许沁沁 | Campus intelligent management system and method |
| CN112560669A (en) * | 2020-12-14 | 2021-03-26 | 杭州趣链科技有限公司 | Face posture estimation method and device and electronic equipment |
| CN112819106A (en) * | 2021-04-16 | 2021-05-18 | 江西博微新技术有限公司 | IFC component type identification method, device, storage medium and equipment |
| CN112819106B (en) * | 2021-04-16 | 2021-07-13 | 江西博微新技术有限公司 | IFC component type identification method, device, storage medium and equipment |
| CN113561908A (en) * | 2021-07-27 | 2021-10-29 | 奇瑞新能源汽车股份有限公司 | Control method and device of vehicle-mounted face recognition equipment |
| CN113561908B (en) * | 2021-07-27 | 2023-06-23 | 奇瑞新能源汽车股份有限公司 | Control method and device of vehicle-mounted face recognition equipment |
| CN114007101A (en) * | 2021-10-29 | 2022-02-01 | 中国联合网络通信集团有限公司 | Processing method and device for fusion display device and storage medium |
| CN114007101B (en) * | 2021-10-29 | 2023-05-16 | 中国联合网络通信集团有限公司 | Processing method, device and storage medium of fusion display device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109543633A (en) | A kind of face identification method, device, robot and storage medium | |
| KR101803081B1 (en) | Robot for store management | |
| TWI751161B (en) | Terminal equipment, smart phone, authentication method and system based on face recognition | |
| US20200380279A1 (en) | Method and apparatus for liveness detection, electronic device, and storage medium | |
| US9323912B2 (en) | Method and system for multi-factor biometric authentication | |
| WO2021143266A1 (en) | Method and apparatus for detecting living body, electronic device and storage medium | |
| CN110458154A (en) | Face identification method, device and computer readable storage medium | |
| CN108307037A (en) | Terminal control method, terminal and computer readable storage medium | |
| CN107590430A (en) | Biopsy method, device, equipment and storage medium | |
| WO2021232985A1 (en) | Facial recognition method and apparatus, computer device, and storage medium | |
| US11675883B2 (en) | Passive identification of a kiosk user | |
| CN110866454B (en) | Face living body detection method and system and computer readable storage medium | |
| CN108875468A (en) | Biopsy method, In vivo detection system and storage medium | |
| CN109600336A (en) | Store equipment, identifying code application method and device | |
| US11277358B2 (en) | Chatbot enhanced augmented reality device guidance | |
| CN110058677A (en) | Electrical interface devices between avionics system and sensor | |
| CN109803109A (en) | A kind of wearable augmented reality remote video system and video call method | |
| CN110765924A (en) | Living body detection method and device and computer-readable storage medium | |
| CN106920039A (en) | A kind of taxation risk managing and control system | |
| CN112818733B (en) | Information processing method, device, storage medium and terminal | |
| US11829460B2 (en) | Systems and methods for biometric authentication via face covering | |
| CN114626036B (en) | Information processing method and device based on face recognition, storage medium and terminal | |
| CN115171196B (en) | Face image processing method, related device and storage medium | |
| CN104866745B (en) | A kind of electronic equipment and information processing method | |
| CN107730483A (en) | The methods, devices and systems of mobile device, processing face biological characteristic |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190329 |