CN106682620A - Human face image acquisition method and device - Google Patents
Human face image acquisition method and device Download PDFInfo
- Publication number
- CN106682620A CN106682620A CN201611235227.XA CN201611235227A CN106682620A CN 106682620 A CN106682620 A CN 106682620A CN 201611235227 A CN201611235227 A CN 201611235227A CN 106682620 A CN106682620 A CN 106682620A
- Authority
- CN
- China
- Prior art keywords
- image
- humanoid
- destination object
- exposure
- head
- 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
- 238000000034 method Methods 0.000 title claims abstract description 67
- 230000011218 segmentation Effects 0.000 claims abstract description 59
- 238000001514 detection method Methods 0.000 claims description 54
- 238000004422 calculation algorithm Methods 0.000 claims description 20
- 230000001815 facial effect Effects 0.000 claims description 19
- 230000005540 biological transmission Effects 0.000 claims description 3
- 241000406668 Loxodonta cyclotis Species 0.000 claims 1
- 235000013399 edible fruits Nutrition 0.000 claims 1
- 230000008901 benefit Effects 0.000 abstract description 3
- 210000003128 head Anatomy 0.000 description 121
- 238000004891 communication Methods 0.000 description 15
- 238000004590 computer program Methods 0.000 description 9
- 238000012549 training Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 7
- 238000000605 extraction Methods 0.000 description 6
- 238000007796 conventional method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 241000208340 Araliaceae Species 0.000 description 4
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 4
- 235000003140 Panax quinquefolius Nutrition 0.000 description 4
- 230000033228 biological regulation Effects 0.000 description 4
- 210000004709 eyebrow Anatomy 0.000 description 4
- 235000008434 ginseng Nutrition 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 240000006409 Acacia auriculiformis Species 0.000 description 1
- 208000003351 Melanosis Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000000712 assembly Effects 0.000 description 1
- 238000000429 assembly Methods 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 210000005069 ears Anatomy 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 210000000887 face Anatomy 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 231100000241 scar Toxicity 0.000 description 1
- 238000006748 scratching Methods 0.000 description 1
- 230000002393 scratching effect Effects 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- 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
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Image Processing (AREA)
- Studio Devices (AREA)
Abstract
The invention discloses a human face image acquisition method and device. The human face image acquisition method includes the steps that a first image, acquired by an image sensor, of a target object is acquired; human shape segmentation is carried out based on the first image of the target object, so that at least the head of the target object is segmented out; a coordinate region, in the first image, of the head of the target object is acquired based on the human shape segmentation result; the image sensor is controlled to locally expose the target object based on the coordinate region to enable exposure of the head region of the target object to meet preset requirements; a second image of the locally exposed target object is acquired. By means of the human face image acquisition method, the problem that ideal human face recognition pictures are not easily acquired in the dark light or backlight environment is effectively solved. The device has the similar advantages.
Description
Technical field
The present invention relates to acquisition technology field, more particularly to one kind can improve half-light environment servant's face image acquiring
The man face image acquiring method and device of performance.
Background technology
With expanding economy, advancing by leaps and bounds for the quickening of city-building speed, and internet causes population in city close
Collection, floating population increases, and has caused the traffic in urban construction, social security, key area strick precaution, the network crime to become increasingly conspicuous
Deng city management problem, therefore video monitoring system is increasingly widely applied, and how to make collection image include high-quality
Facial image become research emphasis.
In current IMAQ, it is a security protection industry difficult problem that the portrait under low-illumination scene or backlighting condition is captured, and is grabbed
The portrait that photographed is dark or completely black cause can not be for carrying out recognition of face.Now generally by using support wide dynamic range
Camera solves the problems, such as that portrait is more black under low-illumination scene or backlighting condition using face partial exposure.However, supporting wide
The camera of dynamic range is generally relatively costly, and under strong backlight or dark environment portrait capture effect nor
It is highly desirable.And the premise of face partial exposure to be video camera will first detect face, the position for being then based on face is done local and is exposed
Light, obtains preferable portrait picture；But in the case of strong backlight or dark, man face image acquiring algorithm can't detect
Face, therefore cannot just carry out next step action.
Accordingly, it is desirable to provide a kind of man face image acquiring method and device, to solve above-mentioned asking at least in part
Topic.
The content of the invention
A series of concept of reduced forms is introduced in Summary, this will enter one in specific embodiment part
Step is described in detail.The Summary of the present invention is not meant to the pass for attempting to limit technical scheme required for protection
Key feature and essential features, more do not mean that the protection domain for attempting to determine technical scheme required for protection.
In order to solve the above problems at least in part, the invention provides a kind of man face image acquiring method, including：
Obtain the first image of the destination object of imageing sensor collection；
Humanoid segmentation is carried out based on the first image of the destination object, to be at least partitioned into the head of the destination object
Portion；
Result based on the humanoid segmentation obtains the coordinates regional of the head of destination object described in described first image；
Partial exposure is carried out so that described to the destination object based on coordinates regional control described image sensor
The exposure of the head zone of destination object meets pre-provisioning request；
Second image of the destination object of collection Jing partial exposures.
Exemplarily, also included before the image of the destination object of the acquisition imageing sensor collection：
The image of target area is obtained in real time；
Humanoid detection is carried out to the image of acquired target area, to judge the target area with the presence or absence of humanoid；
If the target area exists humanoid, subsequent step is continued executing with, if the target area does not have people
Shape, then do not perform subsequent step.
Exemplarily, the head of destination object described in described image is obtained in the result based on the humanoid segmentation
Coordinates regional before, also include：
Whether the quantity for judging the pixel in the head zone of the destination object is more than given threshold,
If the quantity of the pixel in the head zone of the destination object is more than given threshold, continue executing with follow-up
Step, on the contrary then do not perform subsequent step.
Exemplarily, it is described that local is carried out to the destination object based on coordinates regional control described image sensor
Exposure is so that the exposure of the head zone of the destination object meets pre-provisioning request includes：Adjust the exposure of described image sensor
Parameter, so that the head zone of the destination object in second image for being gathered is exposed to predetermined facial image and adopts
Standard required for collection.
Exemplarily, the exposure parameter includes at least one in time for exposure, aperture size and exposure ISO.
Exemplarily, it is the step of first image based on the destination object carries out humanoid segmentation, described based on institute
The step of result for stating humanoid segmentation obtains the coordinates regional of the head of destination object described in described first image is by server
Realize, it is described that partial exposure is carried out so that described to the destination object based on coordinates regional control described image sensor
The step of exposure of the head zone of destination object meets pre-provisioning request is realized by the processor of camera internal；Or,
It is the step of first image based on the destination object carries out humanoid segmentation, described based on the humanoid segmentation
Result obtain described first image described in destination object head coordinates regional the step of and it is described based on the seat
Mark Region control described image sensor carries out partial exposure so that the head zone of the destination object to the destination object
Exposure realized by the processor of camera internal the step of meet pre-provisioning request.
Exemplarily, the humanoid detection with the humanoid segmentation by the Human detection algorithm based on SVM, or based on LBP
The real-time Human detection algorithm of innovatory algorithm is realized.
The embodiment of the present invention also provides a kind of human face image collecting device, including：
Image collection module, described image acquisition module is used for the first figure of the destination object for obtaining imageing sensor collection
Picture；
Humanoid segmentation module, the humanoid segmentation module is used to carry out humanoid point to the destination object in described first image
Cut, to be at least partitioned into the head of the destination object, and obtain the coordinates regional of the destination object head；
Partial exposure module, the partial exposure module is used for the control of the coordinates regional based on destination object head institute
State imageing sensor carries out partial exposure so that the exposure of the head zone of the destination object meets pre- to the destination object
Provisioning request；
Wherein, described image acquisition module is additionally operable to based on the partial exposure results acquisition of the partial exposure module
Second image of the destination object of Jing partial exposures.
Exemplarily, the human face image collecting device also includes humanoid detection module, and it is right that the humanoid detection module is used for
The image of the target area that described image acquisition module is obtained carries out humanoid detection, to judge that the target area whether there is people
Shape, if the target area exists humanoid, the humanoid detection module is by detected humanoid transmission to described humanoid
Segmentation module, on the contrary then continue to carry out humanoid detection to the image of the next target area.
Exemplarily, the humanoid segmentation module is additionally operable to judge the pixel in the head zone of the destination object
Whether quantity is more than given threshold, if the quantity of the pixel in the head zone of the destination object is more than given threshold,
Then the humanoid segmentation module obtains the coordinates regional of the head of the destination object, and the coordinates regional is sent to described
Partial exposure module；Otherwise then do not obtain the coordinates regional of the head of the destination object.
Exemplarily, the partial exposure module adjusts the exposure ginseng of described image sensor based on the coordinates regional
Number, so that the head zone of the destination object in second image for being gathered is exposed to predetermined man face image acquiring
Required standard.
Exemplarily, the exposure parameter includes at least one in time for exposure, aperture size and exposure ISO.
Exemplarily, the human face image collecting device is camera,
Or, the human face image collecting device includes camera and server, and the camera is obtained including described image
Delivery block and the partial exposure module, the server includes the humanoid segmentation module.
Man face image acquiring method and device of the invention, by splitting to the portrait in image, with least
The head being partitioned in portrait, for example, be divided into head, trunk and four limbs by portrait, then according to the result of portrait segmentation, obtains
The coordinates regional of head in image is taken, being then based on the exposure parameter of coordinates regional regulation imageing sensor is carried out for head
The partial exposure of (face), exposure area has specific aim and position is precisely, due to the figure for same camera to gathering
It is more easily implemented so as to locating human face region ratio directly carries out Face datection in collection image as carrying out humanoid detection, it is possible to
Obtain face exposure image more more preferable than conventional method.That is, by doing partial exposure to the head that portrait is partitioned into, mesh is solved
Can't detect face and a difficult problem for desirable photograph cannot be obtained under front half-light or backlight environment.
Further, man face image acquiring method and device of the invention portrait segmentation before, first to image
It is humanoid to be detected subsequently to carry out humanoid segmentation, and for the relative man face image acquiring of humanoid detection, universality is higher, adopts
It is humanoid in can easily detecting low-light (level) environment or strong backlight environment with starlight level imageing sensor, greatly reduce cost
With the requirement to imageing sensor.
Description of the drawings
The drawings below of the embodiment of the present invention is used to understand the present invention in this as the part of the present invention.Illustrate in accompanying drawing
Embodiments of the invention and its description, for explaining the principle of the present invention.In the accompanying drawings,
Fig. 1 is the exemplary electronic device for realizing man face image acquiring method and device according to embodiments of the present invention
Schematic block diagram；
Fig. 2 is the indicative flowchart of the man face image acquiring method according to the embodiment of the present invention；
Fig. 3 is the more detailed indicative flowchart of the man face image acquiring method according to the embodiment of the present invention；
Fig. 4 is the schematic block diagram of the human face image collecting device according to the embodiment of the present invention；
Fig. 5 is the schematic block diagram of the image detecting apparatus according to the embodiment of the present invention.
Specific embodiment
In the following description, a large amount of concrete details are given to provide more thorough understanding of the invention.So
And, it will be apparent to one skilled in the art that the embodiment of the present invention can be without the need for one or more of these details
And be carried out.In other examples, in order to avoid obscuring with the embodiment of the present invention, for more well known in the art
Technical characteristic is not described.
It should be appreciated that the present invention can be implemented in different forms, and should not be construed as being limited to what is proposed here
Embodiment.On the contrary, providing these embodiments disclosure will be made thoroughly and complete, and be will fully convey the scope of the invention to
Those skilled in the art.In the accompanying drawings, in order to clear, the size and relative size of part, element etc. may be exaggerated.Ad initio
Identical element is represented to whole same reference numerals.
In order that the object, technical solutions and advantages of the present invention become apparent from, root is described in detail below with reference to accompanying drawings
According to the example embodiment of the present invention.Obviously, described embodiment is only a part of embodiment of the present invention, rather than this
Bright whole embodiments, it should be appreciated that the present invention is not limited by example embodiment described herein.Described in the present invention
The embodiment of the present invention, those skilled in the art's all other embodiment resulting in the case where creative work is not paid
All should fall under the scope of the present invention.
First, with reference to Fig. 1 describing for realizing man face image acquiring method and apparatus according to embodiments of the present invention
Exemplary electronic device 100.
As shown in figure 1, electronic equipment 100 includes one or more processors 102, one or more storage devices 104, defeated
Enter/output device 106, communication interface 108 and one or more image-signal processors (ISP) 110, imageing sensor 114,
Bindiny mechanism's (not shown) interconnection that these components pass through bus system 112 and/or other forms.It should be noted that shown in Fig. 1
The component and structure of electronic equipment 100 is illustrative, and not restrictive, and as needed, the electronic equipment can also
With other assemblies and structure, it is also possible to not including aforesaid members, for example, can include communication interface 108, it is also possible to
Not packet communication interface 108.
The processor 102 typically represent any types or form can processing data or explain and execute instruction place
Reason unit.In general, processor can be CPU (CPU) or hold with data-handling capacity and/or instruction
The processing unit of the other forms of row ability, and other components in the electronic equipment 100 can be controlled to perform expectation
Function.In a particular embodiment, processor 102 can receive the instruction from software application or module.These instructions can be with
Cause the function of one or more example embodiments that processor 102 completes to be described herein and/or illustrate.
The storage device 104 can include one or more computer programs, and the computer program can
With including various forms of computer-readable recording mediums, such as volatile memory and/or nonvolatile memory.It is described easy
The property lost memory can for example include random access memory (RAM) and/or cache memory (cache) etc..It is described non-
Volatile memory can for example include read-only storage (ROM), hard disk, flash memory etc..In the computer-readable recording medium
On can store one or more computer program instructions, processor 102 can run described program instruction, to realize hereafter institute
The client functionality (realized by processor) in the embodiment of the present invention stated and/or other desired functions.In the meter
Various application programs and various data can also be stored in calculation machine readable storage medium storing program for executing, such as application program use and/or
Various data for producing etc..
The input/output device 106 can be that user exports the device of various information for input instruction and to outside,
For example input unit can include one or more in keyboard, mouse, microphone and touch-screen etc..Output device can include
One or more in display, loudspeaker etc..
Communication interface 108 widely represent any types or form can promote exemplary electronic device 100 and one or
The adapter or communication equipment of the communication between multiple optional equipments.For example, communication interface 108 can promote electronic equipment 100
With the communication in front end or accessory electronic device and back-end server or high in the clouds.The example of communication interface 108 is included but is not limited to
Wired network interface (such as NIC), radio network interface (such as wireless network interface card), modem and appoint
What his suitable interface.In one embodiment, communication interface 108 by with the direct-connected offer of the network of such as internet to remote
Journey server/remote front-end equipment it is direct-connected.In a particular embodiment, communication interface 108 by with dedicated network, such as video
The direct-connected offer of the networks such as monitoring network, Skynet system network is to the direct-connected of remote server/remote front-end equipment.Communication interface
108 can also indirectly provide this connection by any other suitable connection.
Image-signal processor (ISP) 110 carries out IMAQ for controlling imageing sensor 114, and adjusts AE (automatically
Exposure) the image matter such as parameter and brightness, contrast, time for exposure such as digital gain, analog gain, BLC, wide dynamic
Amount parameter and other specification, with adjusting image quality, and the output signal based on imageing sensor 114 generates corresponding exposure
Image, and transmitted to processor 102 by the connection unit of such as bus system 112 and carry out subsequent treatment.Meanwhile, picture signal
Processor (ISP) 110 can also receive the order or instruction from processor 102, to be adjusted control to imageing sensor 114
System.Image-signal processor (ISP) 110 can as needed and the quantity of imageing sensor 114 arranges one or more, and
And image-signal processor (ISP) 110 can be integrated with processor 102 etc., on-chip system (SOC) is embodied as, it is also possible to set up
Arrange, and be attached by the such as connection unit of bus system 112 and processor 102.
Imageing sensor 114 can gather or shoot image (such as photo, video of the desired visible light exposure of user
Deng), and captured image is stored in the storage device 104 so that other components are used.Imageing sensor 114
One example is RGB sensors, or RGBW sensors or black and white sensor (can only gather black white image) etc., and it passes through sense
Visible ray is answered to form colour or black white image/video.
Exemplarily, set for realizing the exemplary electron of man face image acquiring method and apparatus according to embodiments of the present invention
Adopt for may be implemented as such as smart mobile phone, panel computer, the IMAQ end of gate control system, the image of preventing road monitoring system
The rear end control process end at collection end, the IMAQ end of safety-protection system and various monitoring, safety-security area etc. or server end or
High in the clouds etc..
Fig. 2 is the indicative flowchart of the man face image acquiring method according to the embodiment of the present invention.Below in conjunction with Fig. 2 pair
Man face image acquiring method according to embodiments of the present invention is described.
As shown in Fig. 2 man face image acquiring method includes disclosed in the embodiment of the present invention：
First, in step s 201, the image of the destination object of imageing sensor collection is obtained, the first image is denoted as.
The image of the destination object of imageing sensor collection, the target pair are obtained by communication unit or connection unit
As being, for example, pedestrian or people to be identified.
In step S202, the image based on the destination object carries out humanoid detection and humanoid segmentation, at least to split
Go out the head of the destination object.
Exemplarily, for example can be using the good humanoid detector of training in advance come in imageing sensor acquired image
In portrait is carried out it is humanoid detection and humanoid segmentation, to be at least partitioned into the head of the destination object, for example, portrait is split
For regions such as head, trunk and four limbs.
Exemplarily, the humanoid detection algorithm such as full convolutional neural networks can be advanced with to instruct on the basis of a large amount of pictures
Humanoid detector is practised, for the single-frame images of input, the good humanoid segmentation of the training in advance can rapidly to right in image
Portrait is split, for example, portrait is divided into into the regions such as head, trunk and four limbs.Additionally, continuous for imageing sensor
The multiple image of collection, after head zone is partitioned in first two field picture, can be based on the previous frame image of current frame image
In head zone position following the trail of the position of the head zone in current frame image in real time.Wherein, the humanoid detection
Can be by the Human detection algorithm based on SVM, or the real-time Human detection algorithm reality based on LBP innovatory algorithms with humanoid segmentation
It is existing.
In step S203, the coordinates regional of the head of destination object described in described image is obtained.
After completing to portrait segmentation in step 202., the position of coordinate and head zone based on image obtains figure
The coordinates regional of the head of destination object as described in.
In step S204, header area of the described image sensor to the destination object is controlled based on the coordinates regional
Domain carries out partial exposure, so that the exposure of the head zone of the destination object meets pre-provisioning request, such as man face image acquiring
The standard of needs.
Wherein, based on the coordinates regional control described image sensor partial exposure is carried out to the destination object so that
The exposure of the head zone of the destination object meets pre-provisioning request and includes：The exposure parameter of described image sensor is adjusted, with
The head zone for making the destination object in second image for being gathered is exposed to needed for predetermined man face image acquiring
The standard wanted.Wherein, the exposure parameter can include at least one in time for exposure, aperture size and exposure ISO.
In one example, the exposure parameter captures shutter speed and candid photograph gain to adjust by adjustment, wherein, institute
State candid photograph shutter speed and the candid photograph gain is calculated according to the following formula：
Shut_cap=shut_video*shut_set/ (shut_video+shut_set) (1)
Gain_cap=gain_video*shut_video/shut_cap (2)
Wherein, to capture shutter speed, gain_cap is candid photograph gain to shut_cap；Shut_video is video recording mould
Shutter speed under formula, gain_video is video gain；Shut_set captures most slow shutter speed for default.
Because when ambient light is weaker or in backlight, the image that optical image sensor is gathered is dark or complete due to portrait
Unlicensed tour guide causes to cannot be used for recognition of face, or causes the increase of man face image acquiring difficulty, man face image acquiring efficiency and hydraulic performance decline,
In order to improve half-light or backlight servant's face image acquiring performance, the coordinate based on the destination object head for being extracted in the present invention
Region control visible light image sensor carries out partial exposure to the head zone of the destination object, so that the destination object
Head zone the standard that needs to man face image acquiring of image exposure.
Exemplary, such as based on destination object head coordinates regional, judges the brightness of the image in the coordinates regional, so
The brightness range that afterwards brightness and recognition of face based on the image in the coordinates regional needs, adjusts the exposure ginseng of imageing sensor
Number, so that the brightness of the image of head zone meets the standard of recognition of face in the image of imageing sensor collection, so as to realize
Preferably recognition of face.
In an example of the invention, when ambient light is weaker or in backlight, the figure that can be based in the coordinates regional
The brightness range that the brightness of picture and recognition of face need, adjusts the exposure parameter of imageing sensor, is adopted with increasing imageing sensor
The brightness of the image of head zone in the image of collection, complies with the standard of recognition of face.
In another example of the present invention, when ambient light is very strong, the image of imageing sensor collection is entirely white, also unfavorable
In recognition of face, the brightness range that now can be needed based on the brightness of the image in the coordinates regional and recognition of face, adjust
The exposure parameter of imageing sensor, with the brightness of the image of head zone in the image for reducing imageing sensor collection, so that its
Meet the standard of recognition of face.
In step S205, the image (being denoted as the second image) of the destination object of Jing partial exposures is gathered, i.e. collection
The image of partial exposure is carried out to obtain the facial image for meeting demand to the head zone of the destination object.
The image of described image sensor collection can also be able to be video for picture.
In one example, when the image of imageing sensor collection is video, can also be for constituting the every of the video
One frame picture carries out Face datection and facial image is extracted.Further, it is also possible to being based on the image of collection carries out recognition of face, face
Attributive analysis etc. is operated.
Exemplarily, can be deployed at man face image acquiring end according to the man face image acquiring method of the present embodiment, example
Such as, in security protection application, the IMAQ end of gate control system can be deployed in；In financial application field, can be deployed in individual
People's end, smart phone, panel computer, personal computer etc..
Alternatively, man face image acquiring method according to embodiments of the present invention is deployed in server end with can also being distributed
At (or high in the clouds) and personal terminal.For example, in financial application field, IMAQ can be carried out in personal terminal, then in clothes
Business device end (or high in the clouds) carries out humanoid detection, humanoid segmentation, coordinates regional acquisition to the image for gathering, and then enters in personal terminal
Row partial exposure and local exposure image are gathered, and finally carry out man face image acquiring extraction and knowledge in server end (or high in the clouds)
Not etc..
According to the man face image acquiring method of the present embodiment, humanoid detection and humanoid point are carried out by the image to gathering
Cut, so as to obtain the coordinates regional of destination object head, being then based on the exposure parameter of coordinates regional regulation sensor is carried out
Partial exposure, so that head image meets the standard of man face image acquiring in the image of destination object.Because exposure area has
Specific aim and position is accurate, it is possible to obtain face exposure image more more preferable than conventional method.That is, by carrying out humanoid detection
So as to be partitioned into head, then partial exposure is done to the head that portrait is partitioned into, solve and examined under current half-light or backlight environment
Do not detect face and a difficult problem for desirable photograph cannot be obtained, and may be equally applicable for solving under intense light conditions, photo turns white
And it is unfavorable for the problem of recognition of face.
Fig. 3 is the more detailed indicative flowchart of the man face image acquiring method according to the embodiment of the present invention.Tie below
Close Fig. 3 to be described in detail man face image acquiring method according to embodiments of the present invention.
As shown in figure 3, man face image acquiring method includes disclosed in the embodiment of the present invention：
First, in step S301, the image of Real-time Collection target area.
Target area is monitored by imageing sensor or video camera, to obtain the image of target area in real time.
The target area can be monitor area, or for carrying out the region of recognition of face, or other regions.
In step s 302, carry out humanoid detection, to judge the target area in the presence or absence of humanoid.
For the image that every width target area is gathered in step S301, humanoid detection is carried out, to judge the target area
With the presence or absence of humanoid in domain.
Exemplarily, for example can be using the good humanoid detector of training in advance come the figure to gathered every width target area
As carrying out humanoid detection, to judge the target area in the presence or absence of humanoid.
Exemplarily, the humanoid detection algorithm such as fast RCNN can be advanced with to train on the basis of a large amount of pictures
Humanoid detector, for the single-frame images of input, the good humanoid detection of the training in advance can be detected rapidly from image
It is humanoid.Additionally, for the multiple image of imageing sensor continuous acquisition, detect in first two field picture it is humanoid after, can be with base
Humanoid position in the previous frame image of current frame image is following the trail of in real time humanoid position in current frame image.
If in step 302, being not detected by humanoid, then return to step S301, continue the image for gathering target area,
And then carry out humanoid detection.That is, humanoid detection is carried out to the next image of target area, to judge target area in whether
Exist humanoid.
If detecting in step 302 humanoid, in step S303, portrait segmentation is carried out.
In step 303, to described image in it is humanoid split, to be at least partitioned into the humanoid head.
That is, to detect in step 302 it is humanoid carry out humanoid segmentation, to be at least partitioned into the humanoid head, example
Such as humanoid it is divided into head, trunk and four limbs region by what is detected in step 302.
Exemplarily, for example can be using the good humanoid dispenser of training in advance come in imageing sensor acquired image
In portrait is split.The humanoid partitioning algorithm such as full convolutional neural networks can be advanced with to instruct on the basis of a large amount of pictures
Humanoid dispenser is practised, for the single-frame images of input, the good humanoid segmentation of the training in advance can rapidly to right in image
Portrait is split, for example, portrait is divided into into the regions such as head, trunk and four limbs.Additionally, continuous for imageing sensor
The multiple image of collection, after head zone is partitioned in first two field picture, can be based on the previous frame image of current frame image
In head zone position following the trail of the position of the head zone in current frame image in real time.
In step s 304, judge the pixel of head zone in described image whether more than given threshold.
Due to realize that recognition of face generally requires the pixel with 100x100 in facial image, so if face
Image pixel is unfavorable for very little, then recognition of face.If the image few to these pixels is also carried out recognition of face, can wave
Take a large amount of computing resources, and affect whole recognition of face efficiency.Therefore, when in step S303, being partitioned into head zone
Afterwards, that is, the quantity of the pixel in the region is obtained or calculates, to judge it whether more than given threshold.The given threshold is used
Recognition of face is may adapt in the expression head image.For example, in an example of the invention, the given threshold is 50.
I.e. when the pixel count of head zone in image is more than 50, the head image is just adapted for recognition of face, if less than 50, then
Represent that head or portrait are too little in image, are not suitable for carrying out face.
If the pixel in step s 304, determining head zone in described image is not more than given threshold, then it is back to
In step S301, and repeat execution step S301~S304, the pixel of head zone no more than sets threshold in described image
Till value.The filtration of the image to partly not being suitable for carrying out recognition of face can be so realized, computing resource is saved, people is improved
The whole efficiency of face image acquiring.
If in step s 304, determining the pixel of head zone in described image more than given threshold, then into step
In S305.
In step S305, the coordinates regional of head in described image is obtained.
After the pixel in step s 304, determining head zone in described image is more than given threshold, then based on image
Coordinate and step S303 in the described humanoid head that is partitioned into, to obtain described image in head coordinates regional.
Within step 306, partial exposure is carried out based on coordinates regional control imageing sensor, so that the header area
The standard that the image exposure in domain needs to man face image acquiring.
Exemplary, such as based on destination object head coordinates regional, judges the brightness of the image in the coordinates regional, so
The brightness range that afterwards brightness and recognition of face based on the image in the coordinates regional needs, adjusts the exposure ginseng of imageing sensor
Number, so that the brightness of head image meets the standard of recognition of face in the image of imageing sensor collection, so as to realize preferably
Recognition of face.The exposure parameter for example includes the parameters such as time for exposure, digital gain, analog gain, BLC, wide dynamic
With the parameter such as brightness, contrast.
In an example of the invention, when ambient light is weaker or in backlight, the figure that can be based in the coordinates regional
The brightness range that the brightness of picture and recognition of face need, adjusts the exposure parameter of imageing sensor, for example, increase the time for exposure, with
Increase the brightness of head image in the image of imageing sensor collection, comply with the standard of recognition of face.The present invention's
In another example, when ambient light is very strong, the image of imageing sensor collection is entirely white, is also unfavorable for recognition of face, now may be used
With the brightness range that the brightness and recognition of face based on the image in the coordinates regional needs, the exposure ginseng of imageing sensor is adjusted
Number, for example, reduce the time for exposure, with the brightness of head image in the image for reducing imageing sensor collection, complies with face
The standard of identification.
Further, it is to be understood that in the present invention so-called partial exposure refers to the head in image is obtained
After coordinates regional, the brightness range that the brightness and recognition of face based on the image in the coordinates regional needs adjusts image sensing
The exposure parameter of device, is exposed to gather image using the exposure parameter when partial exposure is carried out to whole target area,
So that head image meets the standard of recognition of face in the image of collection, the brightness for for example making head image in the image of collection is accorded with
Close the standard of recognition of face.That is, in the present invention partial exposure is referred to based on regional area (such as head zone) in image
Picture quality (such as brightness) adjusting the exposure parameter of imageing sensor, then figure is resurveyed with the exposure parameter
Picture, so that the picture quality of regional area meets the requirements, rather than only localized region exposes or to adjusting imageing sensor
The exposure parameter of regional area.Although other regions are likely to be at overexposure using this local exposure method, but as long as head figure
As the recognition of face that can be used for that meets the requirements, it has simple and fast and the less advantage of amount of calculation.
In step S307, gathering the head zone to the destination object carries out the image of partial exposure.
Further, after the partial exposure image of imageing sensor is obtained, the image of partial exposure can also be entered
Row Face datection, face character analysis, recognition of face etc. are operated.
Exemplary property, for example, can be gathered using the good human-face detector of training in advance in visible light image sensor
Image in locating human face region.For example, can advance with the Face datections such as Ha Er (Haar) algorithm, Adaboost algorithm with
Recognizer trains human-face detector on the basis of a large amount of pictures, and for the single-frame images of input, the training in advance is good
Human-face detector can quickly locate out human face region.Additionally, for the multiframe figure of visible light image sensor continuous acquisition
Picture, after human face region is oriented in first two field picture, can be based on human face region in the previous frame image of current frame image
Position is following the trail of in real time the position of the human face region in current frame image.
After detecting facial image in the image of imageing sensor collection and providing corresponding coordinate, then can be by coordinate
Facial image is plucked out (be commonly called as scratching figure), to obtain facial image.
Exemplarily, the people can be detected from the image of visible light image sensor collection in step S307
The coordinate data of face image position；According to the coordinate data of the destination object, adopt from the visible light image sensor
Take in the image of collection only including the image of the face.As an example, when it is determined that the coordinate of facial image position
After data, can be marked at these coordinates, for example, be labeled as 1, and the position mark outside these coordinates is 0, so as to true
Determine region, profile and pixel of facial image etc., then can use existing figure cutting techniques (for example, Graph Cut algorithms)
The region for being labeled as 1 is taken out, so as to obtain the only image comprising face.
Further, in embodiments of the present invention, the characteristic information of face can be detected/extracted by the Face datection.
So-called characteristic information, the letter that can be used for face or distinguished face to be identified and other faces for referring to
Breath.By taking facial image as an example, so-called characteristic information can exemplarily include such as face overall information, such as shape of face, face
Layout etc., can also include local feature information, and such as mole, freckle, scar etc. can also include face characteristic information, for example
Left ear information (size, shape etc.), auris dextra information (size, shape etc.), left eyebrow information (such as shape, position, length and width etc.),
Right eyebrow information (such as shape, position, length and width etc.), and left eye information (such as shape, position, length and width etc.), right eye information
(such as shape, position, length and width etc.) etc..
Exemplarily, in one embodiment, Sobel operator extractions characteristics algorithm or Gabor characteristic algorithm etc. can be passed through
The characteristic information of facial image is extracted in the image that feature extraction algorithm is obtained from step 307.In another embodiment, can be with
Using the good crucial spot locator of training in advance come locating human face's key point in human face region (such as in eyes, canthus, eyes
The heart, eyebrow, nose, nose, face, the corners of the mouth and face mask etc.).For example, cascade homing method can be advanced with a large amount of
Crucial spot locator is trained on the basis of the face picture of artificial mark.Alternatively, it would however also be possible to employ traditional face is crucial
Independent positioning method, it is based on parametric shape model, according to the appearance features near key point, learns a parameter model,
Iteratively optimize the position of key point when using, finally obtain crucial point coordinates, after crucial point coordinates is obtained, can be based on should
Coordinate carries out a step and obtains key point (such as eyes, canthus, eye center, eyebrow, nose, nose, face, the corners of the mouth and face
Profile etc.) other information, such as size, shape etc. information.
Should be appreciated that the present invention is not limited by the concrete facial image extracting method for adopting and characteristics information extraction method, nothing
By be existing facial image extracting method and characteristics information extraction method or in the future the facial image extracting method of exploitation and
Feature extracting method, in being applied to man face image acquiring method according to embodiments of the present invention, and also should be included in
In protection scope of the present invention.
Exemplarily, can be deployed at man face image acquiring end according to the man face image acquiring method of the present embodiment, example
Such as, in security protection application, the IMAQ end of gate control system can be deployed in；In financial application field, can be deployed in individual
People's end, smart phone, panel computer, personal computer etc..
Alternatively, man face image acquiring method according to embodiments of the present invention is deployed in server end with can also being distributed
At (or high in the clouds) and personal terminal.For example, in financial application field, IMAQ can be carried out in personal terminal, then in clothes
Business device end (or high in the clouds) carries out humanoid detection, humanoid segmentation, coordinates regional acquisition to the image for gathering, and then enters in personal terminal
Row partial exposure and local exposure image are gathered, and finally carry out man face image acquiring extraction and knowledge in server end (or high in the clouds)
Not etc..
According to the man face image acquiring method of the present embodiment, humanoid detection and humanoid point are carried out by the image to gathering
Cut, so as to obtain the coordinates regional of destination object head, being then based on the exposure parameter of coordinates regional regulation sensor is carried out
Partial exposure, so that head image meets the standard of man face image acquiring in the image of destination object.Because exposure area has
Specific aim and position is accurate, it is possible to obtain face exposure image more more preferable than conventional method.That is, by being partitioned into portrait
Head do partial exposure, solve and can't detect face and the difficulty of desirable photograph cannot be obtained under current half-light or backlight environment
Topic, and may be equally applicable for solving under intense light conditions, photo turns white and is unfavorable for the problem of recognition of face.
Further, can also part be unsuitable for carrying out recognition of face according to the man face image acquiring method of the present embodiment
Image filtered, to save computing resource, improve the whole efficiency of man face image acquiring.
In one example, it is above-mentioned the step of carrying out humanoid segmentation based on the first image of the destination object, be based on
The step of result of the humanoid segmentation obtains the coordinates regional of the head of destination object described in described first image is by servicing
Device realizes that control described image sensor based on the coordinates regional carries out partial exposure so that the mesh to the destination object
The step of exposure of the head zone of mark object meets pre-provisioning request is realized by the processor of camera internal.Due to image segmentation,
The steps such as coordinate determination can save the calculation resources of camera itself in server end realization, it is ensured that camera has the computing of abundance
Resource goes to carry out IMAQ.
In another example, the step of first image based on the destination object carries out humanoid segmentation, described
Based on the humanoid segmentation result obtain described first image described in destination object head coordinates regional the step of, with
And it is described based on the coordinates regional control described image sensor partial exposure is carried out to the destination object so that the mesh
The step of exposure of the head zone of mark object meets pre-provisioning request is realized by the processor of camera internal.Due to each step
Realize in camera internal, thus the localization of man face image acquiring can be realized, and then be advantageously implemented the sheet of recognition of face
Groundization.
Fig. 4 is the schematic block diagram of the human face image collecting device according to the embodiment of the present invention.With reference to Fig. 5 pair
Human face image collecting device according to embodiments of the present invention is described.
As shown in figure 4, human face image collecting device 400 according to embodiments of the present invention includes image collection module 410, people
Shape detection module 420, humanoid segmentation module 430, partial exposure module 440 and face detection module 450.In some examples,
Face detection module 450 can not also be included.
Image collection module 410 is used to gather the image of target area by imageing sensor.Image collection module 410 can
With what is stored in the processor 102 in electronic equipment as shown in Figure 1 or the Running storage device 104 of image-signal processor 110
Programmed instruction can perform step S201 and step in man face image acquiring method according to embodiments of the present invention realizing
Rapid S301.In an example of the invention, the operation of processor 102 in the electronic equipment as shown in Figure 1 of image collection module 410 is deposited
The programmed instruction stored in storage device 104 obtains the image of the collection of imageing sensor 114 by communication unit or connection unit.
The image of target area of the humanoid detection module 420 for obtaining to described image acquisition module 410 carries out humanoid
Detection, to judge the target area with the presence or absence of humanoid, if the target area has humanoid, the humanoid detection mould
Block 420 by detected humanoid transmission to it is described it is humanoid segmentation module 430, otherwise then continue to the next target area
Image carry out humanoid detection.Humanoid detection module 420 can be as shown in Figure 1 electronic equipment in processor 102/ or image
The programmed instruction stored in the Running storage device 104 of signalling means 110 can be performed according to embodiments of the present invention realizing
Step S302 in man face image acquiring method.
Humanoid segmentation module 430 is used to carry out humanoid segmentation to the destination object in described image, to be at least partitioned into institute
The head of destination object is stated, and obtains the coordinates regional of the head of the destination object.That is, humanoid segmentation module 430 is to humanoid
Detection module 420 detect it is humanoid split, be for example divided into head, trunk and four limbs region by humanoid, then judge
Whether the quantity of the pixel in the head zone of the destination object is more than given threshold, if the head of the destination object
The quantity of the pixel in region is more than given threshold, then obtain the coordinates regional of the head of the destination object, and will be described
Coordinates regional is sent to the partial exposure module 440；Otherwise then do not obtain the coordinates regional of the head of the destination object.People
Shape splits the processor 102 and/or picture signal device 110 operation storage dress in the electronic equipment that module 430 can be as shown in Figure 1
The programmed instruction stored in 104 is put realizing, and can be performed in man face image acquiring method according to embodiments of the present invention
The step of S202~S203, and step S303~S305.
Partial exposure module 440 is used for the coordinates regional based on the head of the destination object and controls imageing sensor to institute
Stating the head of destination object carries out partial exposure, so that the image exposure of the head zone of the destination object is adopted to facial image
The standard that collection needs.That is, coordinates regional of the partial exposure module 440 based on the head of the destination object adjusts described image and passes
The exposure parameter of sensor, so that the standard that the image exposure of the head zone of the destination object needs to man face image acquiring.
For example, partial exposure control module 440 adjusts the exposure parameter of described image sensor, to increase the head of the destination object
The brightness of the image in region.Again for example, partial exposure control module 440 adjusts the exposure parameter of described image sensor, to drop
The brightness of the image of the head zone of the low destination object.Partial exposure control module 440 can be as shown in Figure 1 electronics set
The programmed instruction stored in processor 102 and/or the Running storage device 104 of picture signal device 110 in standby, and can realizing
Step S204 and S306 in perform man face image acquiring method according to embodiments of the present invention.
Face detection module 450 carries out the image of partial exposure based on the acquired head zone to the destination object
Carry out Face datection man face image acquiring.The head zone to the destination object i.e. from imageing sensor collection carries out local
Face is detected and extracted in the image of exposure, and Face datection man face image acquiring and extracting method are for example described above, and here is no longer
Repeat.
In one example, the human face image collecting device is camera.In another example, the facial image
Harvester includes camera and server, and the camera includes described image acquisition module and the partial exposure module,
The server includes the humanoid segmentation module.
Human face image collecting device of the invention, by the image to gathering humanoid detection and humanoid segmentation are carried out,
So as to obtain the coordinates regional of destination object head, being then based on the exposure parameter of coordinates regional regulation sensor carries out local
Exposure, so that head image meets the standard of man face image acquiring in the image of destination object.It is directed to because exposure area has
Property and position is accurate, it is possible to obtain face exposure image more more preferable than conventional method.That is, the head by being partitioned into portrait
Partial exposure is done in portion, solves and can't detect face and cannot obtain a difficult problem for desirable photograph under current half-light or backlight environment,
And may be equally applicable for solving under intense light conditions, photo turns white and is unfavorable for the problem of recognition of face.
Further, can also part be unsuitable for carrying out recognition of face according to the human face image collecting device of the present embodiment
Image filtered, to save computing resource, improve the whole efficiency of the man face image acquiring for recognition of face.
Fig. 5 is the schematic block diagram of the man face image acquiring equipment according to the embodiment of the present invention.With reference to Fig. 5 pair
Man face image acquiring device systems according to embodiments of the present invention are described.
As shown in figure 5, image detecting apparatus 500 according to embodiments of the present invention include imageing sensor 510, picture signal
Processor 520, storage device 530 and processor 540.
Imageing sensor 510 is used to gather the image of target area.Imageing sensor 510 can be RGB sensors, also may be used
Think black and white sensor.Imageing sensor 510 can gather picture and can also gather video.
Image-signal processor 520 is controlled for imageing sensor 510, and to the letter of the collection of imageing sensor 510
Number processed, to obtain the image or video data of target area.That is, the data of the collection of imageing sensor 510 can be by scheming
Realize as the programmed instruction stored in the Running storage device 540 of signal processor 520, to obtain the picture of target area or regard
Frequency evidence.In an embodiment of the present invention, image-signal processor 520 is additionally operable to run what is stored in the storage device 530
Program code, to perform man face image acquiring method according to embodiments of the present invention in local exposure method corresponding steps,
Or the partial exposure module 440 for realizing in human face image collecting device according to embodiments of the present invention.
The storage device 530 store for realizing man face image acquiring method according to embodiments of the present invention in it is corresponding
The program code of step.
The processor 540 is used to run the program code stored in the storage device 530, to perform according to the present invention
The corresponding steps of the man face image acquiring method of embodiment, and for realizing man face image acquiring according to embodiments of the present invention
Image collection module 410, humanoid detection module 420, humanoid segmentation module 430 and face detection module 450 in device.
In one embodiment, following steps are performed when described program code is run by the processor 540：
Obtain the image of the destination object of imageing sensor collection；
Image based on the destination object carries out humanoid segmentation, to be at least partitioned into the head of the destination object；
Obtain the coordinates regional of the head of destination object described in described image；
Partial exposure is carried out to the head of the destination object based on coordinates regional control imageing sensor, so that institute
The head image for stating destination object is exposed to the standard of man face image acquiring needs；
Gather the image of the partial exposure.
In one example, the man face image acquiring equipment is camera.In another example, the facial image
Collecting device includes camera and server, and the camera includes described image acquisition module and the partial exposure module,
The server includes the humanoid segmentation module.
In one embodiment, processor 540 can be implemented as central processing unit (CPU), wherein, central processing unit
(CPU) image of target area is obtained by imageing sensor 510, then by corresponding program in execution storage device 530
Code, humanoid detection, humanoid segmentation are carried out to described image, to obtain described image in destination object head coordinate area
Domain, then sends the coordinates regional of the head of the destination object to image-signal processor (ISP) 520, picture signal process
Device 520 controls imageing sensor 510 and carries out partial exposure by corresponding program code in execution storage device 530, so that figure
As the head image of destination object in the image of the collection of sensor 510 meets the standard of recognition of face.Subsequently, central processing unit
(CPU) corresponding program in being also based on the partial exposure image of the collection of imageing sensor 510 by performing storage device 530
Code carries out human face detection and recognition.
Exemplarily, image detecting apparatus 500 according to embodiments of the present invention can be implemented with imageing sensor, deposit
The unit or system of reservoir, communication interface/unit and processor.
Image detecting apparatus 500 according to embodiments of the present invention can be deployed in man face image acquiring identifying system, example
Such as, in security protection application, gate control system or preventing road monitoring system can be deployed in；In financial application field, can be with bank, friendship
Easily etc. identity authorization system in.
Additionally, according to embodiments of the present invention, additionally providing a kind of storage medium, program is stored on said storage
Instruction, when described program is instructed and run by computer or processor for performing the man face image acquiring side of the embodiment of the present invention
Method, the corresponding steps of local exposure method, and for realizing human face image collecting device according to embodiments of the present invention, local
Corresponding module/the submodule of exposure module.The storage medium can for example include the storage card of smart phone, panel computer
It is memory unit, the hard disk of personal computer, read-only storage (ROM), Erasable Programmable Read Only Memory EPROM (EPROM), portable
Any combination of formula aacompactadisk read onlyamemory (CD-ROM), USB storage or above-mentioned storage medium.The computer can
Read any combination that storage medium can be one or more computer-readable recording mediums, such as one computer-readable storage
Medium includes the computer-readable program code generated for target object information, another computer-readable recording medium bag
Containing the computer-readable program code for target object information identification.
In one embodiment, the computer program instructions can be realized according to of the invention real when being run by computer
Each functional module in the man face image acquiring square law device of example is applied, and/or can be performed according to embodiments of the present invention
Man face image acquiring method.
In one embodiment, the computer program instructions perform following steps when being run by computer：Obtain figure
As the image of the destination object of sensor collection；Image based on the destination object carries out humanoid segmentation, to be at least partitioned into
The head of the destination object；Obtain the coordinates regional of the head of destination object described in described image；Based on the coordinate area
Domain control imageing sensor carries out partial exposure to the head of the destination object, so that the head image of the destination object exposes
The standard that light needs to man face image acquiring；Gather the image of the partial exposure.
Each module in human face image collecting device according to embodiments of the present invention can be by according to embodiments of the present invention
Man face image acquiring electronic equipment the processor computer program instructions that store in memory of operation realizing, or
The computer instruction that can be stored in the computer-readable recording medium of computer program according to embodiments of the present invention
Realize when being run by computer.
Man face image acquiring method and apparatus according to embodiments of the present invention, image detecting apparatus and storage medium, pass through
Image to gathering carries out humanoid detection and humanoid segmentation, so as to obtain the coordinates regional of destination object head, is then based on this
Coordinates regional adjusts the exposure parameter of sensor and carries out partial exposure, so that head image meets face in the image of destination object
The standard of IMAQ.Because exposure area has specific aim and position is accurate, it is possible to obtain more more preferable than conventional method
Face exposure image.That is, by doing partial exposure to the head that portrait is partitioned into, solve and examined under current half-light or backlight environment
Do not detect face and a difficult problem for desirable photograph cannot be obtained, and may be equally applicable for solving under intense light conditions, photo turns white
And it is unfavorable for the problem of recognition of face.
Although the example embodiment by reference to Description of Drawings here, it should be understood that above-mentioned example embodiment is merely exemplary
, and be not intended to limit the scope of the invention to this.Those of ordinary skill in the art can wherein carry out various changes
And modification, it is made without departing from the scope of the present invention and spirit.All such changes and modifications are intended to be included in claims
Within required the scope of the present invention.
Those of ordinary skill in the art are it is to be appreciated that the list of each example with reference to the embodiments described herein description
Unit and algorithm steps, being capable of being implemented in combination in electronic hardware or computer software and electronic hardware.These functions are actually
Performed with hardware or software mode, depending on the application-specific and design constraint of technical scheme.Professional and technical personnel
Each specific application can be used different methods to realize described function, but this realization it is not considered that exceeding
The scope of the present invention.
In several embodiments provided herein, it should be understood that disclosed apparatus and method, it can be passed through
Its mode is realized.For example, apparatus embodiments described above are only schematic, for example, the division of the unit, and only
Only a kind of division of logic function, can there is other dividing mode when actually realizing, such as multiple units or component can be tied
Close or be desirably integrated into another equipment, or some features can be ignored, or do not perform.
In specification mentioned herein, a large amount of details are illustrated.It is to be appreciated, however, that the enforcement of the present invention
Example can be put into practice in the case of without these details.In some instances, known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this description.
Similarly, it will be appreciated that in order to simplify the present invention and help understand one or more in each inventive aspect, exist
To the present invention exemplary embodiment description in, the present invention each feature be grouped together into sometimes single embodiment, figure,
Or in descriptions thereof.However, the method for the invention should be construed to reflect following intention：It is i.e. claimed
The more features of feature that are expressly recited in each claim of application claims ratio.More precisely, as accordingly
As claims reflect, its inventive point is can be with all features less than certain disclosed single embodiment
Feature is solving corresponding technical problem.Therefore, it then follows thus claims of specific embodiment are expressly incorporated in the tool
Separate embodiments of the body embodiment, wherein each claim as the present invention itself.
It will be understood to those skilled in the art that in addition to mutually exclusive between feature, any combinations pair can be adopted
All features and so disclosed any method disclosed in this specification (including adjoint claim, summary and accompanying drawing)
Or all processes or unit of equipment are combined.Unless expressly stated otherwise, this specification (will including adjoint right
Ask, make a summary and accompanying drawing) disclosed in each feature can, equivalent identical by offer or similar purpose alternative features replacing.
Although additionally, it will be appreciated by those of skill in the art that some embodiments described herein include other embodiments
In included some features rather than further feature, but the combination of the feature of different embodiments means in of the invention
Within the scope of and form different embodiments.For example, in detail in the claims, embodiment required for protection one of arbitrarily
Can in any combination mode using.
The present invention all parts embodiment can be realized with hardware, or with one or more processor operation
Software module realize, or with combinations thereof realization.It will be understood by those of skill in the art that can use in practice
Microprocessor or digital signal processor (DSP) to realize article analytical equipment according to embodiments of the present invention in some moulds
The some or all functions of block.The present invention is also implemented as the part for performing method as described herein or complete
The program of device (for example, computer program and computer program) in portion.Such program for realizing the present invention can be stored
On a computer-readable medium, or can have one or more signal form.Such signal can be from internet
Download on website and obtain, or provide on carrier signal, or provide in any other form.
It should be noted that above-described embodiment the present invention will be described rather than limits the invention, and ability
Field technique personnel can design without departing from the scope of the appended claims alternative embodiment.In the claims,
Any reference symbol between bracket should not be configured to limitations on claims.Word "comprising" is not excluded the presence of not
Element listed in the claims or step.Word "a" or "an" before element does not exclude the presence of multiple such
Element.The present invention can come real by means of the hardware for including some different elements and by means of properly programmed computer
It is existing.If in the unit claim for listing equipment for drying, several in these devices can be by same hardware branch
To embody.The use of word first, second, and third does not indicate that any order.These words can be explained and be run after fame
Claim.
The above, the only specific embodiment of the present invention or the explanation to specific embodiment, the protection of the present invention
Scope is not limited thereto, any those familiar with the art the invention discloses technical scope in, can be easily
Expect change or replacement, all should be included within the scope of the present invention.Protection scope of the present invention should be with claim
Protection domain is defined.
Claims (13)
1. a kind of man face image acquiring method, it is characterised in that include：
Obtain the first image of the destination object of imageing sensor collection；
Humanoid segmentation is carried out based on the first image of the destination object, to be at least partitioned into the head of the destination object；
Result based on the humanoid segmentation obtains the coordinates regional of the head of destination object described in described first image；
Partial exposure is carried out so that the target to the destination object based on coordinates regional control described image sensor
The exposure of the head zone of object meets pre-provisioning request；
Second image of the destination object of collection Jing partial exposures.
2. man face image acquiring method according to claim 1, it is characterised in that in the acquisition imageing sensor collection
Destination object image before also include：
The image of target area is obtained in real time；
Humanoid detection is carried out to the image of acquired target area, to judge the target area with the presence or absence of humanoid；
If the target area exists humanoid, continue executing with subsequent step, if the target area do not exist it is humanoid,
Subsequent step is not performed.
3. man face image acquiring method according to claim 1 and 2, it is characterised in that described based on described humanoid point
Described in the result acquisition described image cut before the coordinates regional of the head of destination object, also include：
Whether the quantity for judging the pixel in the head zone of the destination object is more than given threshold,
If the quantity of the pixel in the head zone of the destination object is more than given threshold, follow-up step is continued executing with
Suddenly, subsequent step otherwise is not then performed.
4. man face image acquiring method according to claim 1 and 2, it is characterised in that described based on the coordinates regional
Control described image sensor carries out partial exposure so that the exposure of the head zone of the destination object to the destination object
Meeting pre-provisioning request includes：The exposure parameter of described image sensor is adjusted, so that the institute in second image for being gathered
The head zone for stating destination object is exposed to standard required for predetermined man face image acquiring.
5. the man face image acquiring method according to right wants 4, it is characterised in that the exposure parameter include the time for exposure,
At least one in aperture size and exposure ISO.
6. the man face image acquiring method according to right wants 1 or 2, it is characterised in that described based on the destination object
The step of first image carries out humanoid segmentation, the result based on the humanoid segmentation obtain mesh described in described first image
The step of coordinates regional of the head of mark object, is realized by server, described based on coordinates regional control described image sensing
Device carries out partial exposure to the destination object so that the exposure of the head zone of the destination object meets the step of pre-provisioning request
The rapid processor by camera internal is realized；Or,
The step of first image based on the destination object carries out humanoid segmentation, the knot based on the humanoid segmentation
It is the step of the coordinates regional of the head of destination object and described based on the coordinate area described in fruit acquisition described first image
Domain control described image sensor carries out partial exposure so that the exposure of the head zone of the destination object to the destination object
The step of light meets pre-provisioning request is realized by the processor of camera internal.
7. the man face image acquiring method according to right wants 1 or 2, it is characterised in that the humanoid detection is humanoid with described
Split by the Human detection algorithm based on SVM, or the real-time Human detection algorithm based on LBP innovatory algorithms is realized.
8. a kind of human face image collecting device, it is characterised in that include：
Image collection module, described image acquisition module is used for the first image of the destination object for obtaining imageing sensor collection；
Humanoid segmentation module, the humanoid segmentation module is used to carry out humanoid segmentation to the destination object in described first image,
To be at least partitioned into the head of the destination object, and obtain the coordinates regional of the destination object head；
Partial exposure module, the partial exposure module is used for the coordinates regional based on the destination object head and controls the figure
As sensor partial exposure is carried out to the destination object so that the destination object head zone exposure meet it is predetermined will
Ask；
Wherein, described image acquisition module is additionally operable to based on the partial exposure results acquisition Jing office of the partial exposure module
Second image of the destination object of portion's exposure.
9. human face image collecting device according to claim 8, it is characterised in that described also including humanoid detection module
Humanoid detection module is used for the image of the target area obtained to described image acquisition module carries out humanoid detection, described to judge
Target area with the presence or absence of humanoid,
If the target area exists humanoid, the humanoid detection module is by detected humanoid transmission to described humanoid
Segmentation module, on the contrary then continue to carry out humanoid detection to the image of the next target area.
10. human face image collecting device according to claim 8, it is characterised in that the humanoid segmentation module is additionally operable to
Whether the quantity for judging the pixel in the head zone of the destination object is more than given threshold,
If the quantity of the pixel in the head zone of the destination object is more than given threshold, the humanoid segmentation module
The coordinates regional of the head of the destination object is obtained, and the coordinates regional is sent to the partial exposure module；Otherwise
The coordinates regional of the head of the destination object is not then obtained.
11. human face image collecting devices according to claim 8, it is characterised in that the partial exposure module is based on institute
The exposure parameter that coordinates regional adjusts described image sensor is stated, so that the target pair in second image for being gathered
The head zone of elephant is exposed to the standard required for predetermined man face image acquiring.
12. human face image collecting devices according to claim 10, it is characterised in that when the exposure parameter includes exposure
Between, at least one in aperture size and exposure ISO.
13. human face image collecting devices according to any one of claim 8 to 12, it is characterised in that the facial image
Harvester is camera,
Or, the human face image collecting device includes camera and server, and the camera includes that described image obtains mould
Block and the partial exposure module, the server includes the humanoid segmentation module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611235227.XA CN106682620A (en) | 2016-12-28 | 2016-12-28 | Human face image acquisition method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611235227.XA CN106682620A (en) | 2016-12-28 | 2016-12-28 | Human face image acquisition method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106682620A true CN106682620A (en) | 2017-05-17 |
Family
ID=58872786
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611235227.XA Pending CN106682620A (en) | 2016-12-28 | 2016-12-28 | Human face image acquisition method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106682620A (en) |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107091800A (en) * | 2017-06-06 | 2017-08-25 | 深圳小孚医疗科技有限公司 | Focusing system and focus method for micro-imaging particle analysis |
| CN107155063A (en) * | 2017-06-19 | 2017-09-12 | 深圳市泰衡诺科技有限公司上海分公司 | Night scene filming control method, system and equipment |
| CN107241558A (en) * | 2017-06-16 | 2017-10-10 | 广东欧珀移动通信有限公司 | Exposure processing method, device and terminal device |
| CN107317977A (en) * | 2017-06-23 | 2017-11-03 | 北京小米移动软件有限公司 | Image pickup method and device |
| CN107492074A (en) * | 2017-07-21 | 2017-12-19 | 触景无限科技（北京）有限公司 | Image acquisition and processing method, device and terminal device |
| CN107734129A (en) * | 2017-09-27 | 2018-02-23 | 广东欧珀移动通信有限公司 | Solve lock control method and Related product |
| CN108197601A (en) * | 2018-01-29 | 2018-06-22 | 深圳市巨龙创视科技有限公司 | A kind of Intelligent human-face tracks exposure system |
| CN108416265A (en) * | 2018-01-30 | 2018-08-17 | 深圳大学 | A kind of method for detecting human face, device, equipment and storage medium |
| CN108881710A (en) * | 2017-12-28 | 2018-11-23 | 北京旷视科技有限公司 | Image processing method, device and system and storage medium |
| CN109145734A (en) * | 2018-07-17 | 2019-01-04 | 深圳市巨龙创视科技有限公司 | Algorithm is captured in IPC Intelligent human-face identification based on 4K platform |
| CN109948500A (en) * | 2019-03-13 | 2019-06-28 | 西安科技大学 | A method of the accurate monitoring personnel for coal mine passes in and out |
| CN110620881A (en) * | 2019-10-31 | 2019-12-27 | 北京猎户智芯科技有限公司 | License plate exposure compensation method and device, computer equipment and storage medium |
| CN110705336A (en) * | 2018-07-10 | 2020-01-17 | 福州瑞芯微电子股份有限公司 | Image processing method, system, electronic device and readable storage medium |
| CN110852934A (en) * | 2018-08-21 | 2020-02-28 | 北京市商汤科技开发有限公司 | Image processing method and apparatus, image device, and storage medium |
| CN110942421A (en) * | 2018-09-21 | 2020-03-31 | 北京市商汤科技开发有限公司 | Image processing method and apparatus, image processing device, and storage medium |
| CN111084632A (en) * | 2019-12-09 | 2020-05-01 | 深圳圣诺医疗设备股份有限公司 | Automatic exposure control method and device based on mask, storage medium and electronic equipment |
| CN111274886A (en) * | 2020-01-13 | 2020-06-12 | 天地伟业技术有限公司 | Deep learning-based pedestrian red light violation analysis method and system |
| CN111670457A (en) * | 2017-12-03 | 2020-09-15 | 脸谱公司 | Optimization of dynamic object instance detection, segmentation and structure mapping |
| CN112511749A (en) * | 2020-11-30 | 2021-03-16 | 上海摩象网络科技有限公司 | Automatic exposure control method and device for target object and electronic equipment |
| CN113163101A (en) * | 2020-01-22 | 2021-07-23 | 浙江宇视科技有限公司 | Image exposure adjusting method, device, equipment and medium |
| CN113179375A (en) * | 2021-06-09 | 2021-07-27 | 北京澎思科技有限公司 | Exposure processing method, exposure processing apparatus, electronic device, storage medium, and program product |
| CN113422908A (en) * | 2021-07-01 | 2021-09-21 | 联想(北京)有限公司 | Data processing method and device |
| US11205071B2 (en) | 2018-07-16 | 2021-12-21 | Advanced New Technologies Co., Ltd. | Image acquisition method, apparatus, system, and electronic device |
| WO2022160638A1 (en) * | 2021-01-29 | 2022-08-04 | 深圳市商汤科技有限公司 | Target object exposure method and apparatus, and storage medium, device and program |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101216885A (en) * | 2008-01-04 | 2008-07-09 | 中山大学 | Passerby face detection and tracing algorithm based on video |
| CN101866425A (en) * | 2010-06-02 | 2010-10-20 | 北京交通大学 | Human body detection method based on fish-eye camera |
| US20120300052A1 (en) * | 2005-11-11 | 2012-11-29 | Eyelock Inc. | Methods for performing biometric recognition of a human eye and corroboration of same |
| CN103136899A (en) * | 2013-01-23 | 2013-06-05 | 宁凯 | Intelligent alarming monitoring method based on Kinect somatosensory equipment |
| CN103984915A (en) * | 2014-02-28 | 2014-08-13 | 中国计量学院 | Pedestrian re-recognition method in monitoring video |
| CN105389549A (en) * | 2015-10-28 | 2016-03-09 | 北京旷视科技有限公司 | Object recognition method and device based on human body action characteristic |
| CN105407276A (en) * | 2015-11-03 | 2016-03-16 | 北京旷视科技有限公司 | Photographing method and equipment |
-
2016
- 2016-12-28 CN CN201611235227.XA patent/CN106682620A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120300052A1 (en) * | 2005-11-11 | 2012-11-29 | Eyelock Inc. | Methods for performing biometric recognition of a human eye and corroboration of same |
| CN101216885A (en) * | 2008-01-04 | 2008-07-09 | 中山大学 | Passerby face detection and tracing algorithm based on video |
| CN101866425A (en) * | 2010-06-02 | 2010-10-20 | 北京交通大学 | Human body detection method based on fish-eye camera |
| CN103136899A (en) * | 2013-01-23 | 2013-06-05 | 宁凯 | Intelligent alarming monitoring method based on Kinect somatosensory equipment |
| CN103984915A (en) * | 2014-02-28 | 2014-08-13 | 中国计量学院 | Pedestrian re-recognition method in monitoring video |
| CN105389549A (en) * | 2015-10-28 | 2016-03-09 | 北京旷视科技有限公司 | Object recognition method and device based on human body action characteristic |
| CN105407276A (en) * | 2015-11-03 | 2016-03-16 | 北京旷视科技有限公司 | Photographing method and equipment |
Non-Patent Citations (1)
| Title |
|---|
| 陈慧岩等: "《无人驾驶汽车概论》", 31 July 2014, 北京理工大学出版社 * |
Cited By (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107091800A (en) * | 2017-06-06 | 2017-08-25 | 深圳小孚医疗科技有限公司 | Focusing system and focus method for micro-imaging particle analysis |
| CN107241558B (en) * | 2017-06-16 | 2019-07-19 | Oppo广东移动通信有限公司 | Exposure processing method, device and terminal device |
| CN107241558A (en) * | 2017-06-16 | 2017-10-10 | 广东欧珀移动通信有限公司 | Exposure processing method, device and terminal device |
| CN107155063A (en) * | 2017-06-19 | 2017-09-12 | 深圳市泰衡诺科技有限公司上海分公司 | Night scene filming control method, system and equipment |
| CN107317977A (en) * | 2017-06-23 | 2017-11-03 | 北京小米移动软件有限公司 | Image pickup method and device |
| CN107492074A (en) * | 2017-07-21 | 2017-12-19 | 触景无限科技（北京）有限公司 | Image acquisition and processing method, device and terminal device |
| CN107734129A (en) * | 2017-09-27 | 2018-02-23 | 广东欧珀移动通信有限公司 | Solve lock control method and Related product |
| CN111670457B (en) * | 2017-12-03 | 2023-12-01 | 元平台公司 | Optimization of dynamic object instance detection, segmentation and structure mapping |
| CN111670457A (en) * | 2017-12-03 | 2020-09-15 | 脸谱公司 | Optimization of dynamic object instance detection, segmentation and structure mapping |
| CN108881710A (en) * | 2017-12-28 | 2018-11-23 | 北京旷视科技有限公司 | Image processing method, device and system and storage medium |
| CN108197601A (en) * | 2018-01-29 | 2018-06-22 | 深圳市巨龙创视科技有限公司 | A kind of Intelligent human-face tracks exposure system |
| CN108416265A (en) * | 2018-01-30 | 2018-08-17 | 深圳大学 | A kind of method for detecting human face, device, equipment and storage medium |
| CN110705336B (en) * | 2018-07-10 | 2022-09-09 | 福州瑞芯微电子股份有限公司 | Image processing method, system, electronic device and readable storage medium |
| CN110705336A (en) * | 2018-07-10 | 2020-01-17 | 福州瑞芯微电子股份有限公司 | Image processing method, system, electronic device and readable storage medium |
| US11205071B2 (en) | 2018-07-16 | 2021-12-21 | Advanced New Technologies Co., Ltd. | Image acquisition method, apparatus, system, and electronic device |
| US11244158B2 (en) | 2018-07-16 | 2022-02-08 | Advanced New Technologies Co., Ltd. | Image acquisition method, apparatus, system, and electronic device |
| CN109145734A (en) * | 2018-07-17 | 2019-01-04 | 深圳市巨龙创视科技有限公司 | Algorithm is captured in IPC Intelligent human-face identification based on 4K platform |
| CN110852934A (en) * | 2018-08-21 | 2020-02-28 | 北京市商汤科技开发有限公司 | Image processing method and apparatus, image device, and storage medium |
| CN110942421A (en) * | 2018-09-21 | 2020-03-31 | 北京市商汤科技开发有限公司 | Image processing method and apparatus, image processing device, and storage medium |
| CN109948500B (en) * | 2019-03-13 | 2022-12-27 | 西安科技大学 | Method for accurately monitoring personnel entering and exiting of coal mine |
| CN109948500A (en) * | 2019-03-13 | 2019-06-28 | 西安科技大学 | A method of the accurate monitoring personnel for coal mine passes in and out |
| CN110620881A (en) * | 2019-10-31 | 2019-12-27 | 北京猎户智芯科技有限公司 | License plate exposure compensation method and device, computer equipment and storage medium |
| CN111084632A (en) * | 2019-12-09 | 2020-05-01 | 深圳圣诺医疗设备股份有限公司 | Automatic exposure control method and device based on mask, storage medium and electronic equipment |
| CN111274886A (en) * | 2020-01-13 | 2020-06-12 | 天地伟业技术有限公司 | Deep learning-based pedestrian red light violation analysis method and system |
| CN111274886B (en) * | 2020-01-13 | 2023-09-19 | 天地伟业技术有限公司 | Deep learning-based pedestrian red light running illegal behavior analysis method and system |
| CN113163101A (en) * | 2020-01-22 | 2021-07-23 | 浙江宇视科技有限公司 | Image exposure adjusting method, device, equipment and medium |
| WO2021147364A1 (en) * | 2020-01-22 | 2021-07-29 | 浙江宇视科技有限公司 | Image exposure adjustment method and apparatus, device, and storage medium |
| CN113163101B (en) * | 2020-01-22 | 2023-02-28 | 浙江宇视科技有限公司 | Image exposure adjusting method, device, equipment and medium |
| CN112511749A (en) * | 2020-11-30 | 2021-03-16 | 上海摩象网络科技有限公司 | Automatic exposure control method and device for target object and electronic equipment |
| WO2022160638A1 (en) * | 2021-01-29 | 2022-08-04 | 深圳市商汤科技有限公司 | Target object exposure method and apparatus, and storage medium, device and program |
| CN113179375A (en) * | 2021-06-09 | 2021-07-27 | 北京澎思科技有限公司 | Exposure processing method, exposure processing apparatus, electronic device, storage medium, and program product |
| CN113422908A (en) * | 2021-07-01 | 2021-09-21 | 联想(北京)有限公司 | Data processing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106682620A (en) | Human face image acquisition method and device | |
| WO2019233262A1 (en) | Video processing method, electronic device, and computer readable storage medium | |
| US10949952B2 (en) | Performing detail enhancement on a target in a denoised image | |
| CN111402135B (en) | Image processing method, device, electronic equipment and computer readable storage medium | |
| US9104914B1 (en) | Object detection with false positive filtering | |
| CN107358241B (en) | Image processing method, image processing device, storage medium and electronic equipment | |
| CN106446873A (en) | Face detection method and device | |
| EP2709062B1 (en) | Image processing device, image processing method, and computer readable medium | |
| CN108875619B (en) | Video processing method and device, electronic equipment and computer readable storage medium | |
| CN106161980A (en) | Photographic method and system based on dual camera | |
| WO2017112140A1 (en) | Identity obfuscation | |
| CN107808136A (en) | Image processing method, device, readable storage medium storing program for executing and computer equipment | |
| CN108108415B (en) | Image processing method, image processing apparatus, storage medium, and electronic device | |
| CN110334635A (en) | Main body method for tracing, device, electronic equipment and computer readable storage medium | |
| CN109712177B (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium | |
| CN109299658B (en) | Face detection method, face image rendering device and storage medium | |
| WO2021078001A1 (en) | Image enhancement method and apparatus | |
| CN108875540A (en) | Image processing method, device and system and storage medium | |
| CN110738116B (en) | Living body detection method and device and electronic equipment | |
| CN111626163B (en) | Human face living body detection method and device and computer equipment | |
| CN107911625A (en) | Light measuring method, device, readable storage medium storing program for executing and computer equipment | |
| CN107743200A (en) | Method, apparatus, computer-readable recording medium and the electronic equipment taken pictures | |
| CN106951833A (en) | Human face image collecting device and man face image acquiring method | |
| CN107705279B (en) | Image data real-time processing method and device for realizing double exposure and computing equipment | |
| CN114387548A (en) | Video and liveness detection method, system, device, storage medium and program product |
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 | ||
| CB02 | Change of applicant information |
Address after: 100190 Beijing, Haidian District Academy of Sciences, South Road, No. 2, block A, No. 313 Applicant after: BEIJING KUANGSHI TECHNOLOGY Co.,Ltd. Applicant after: MEGVII (BEIJING) TECHNOLOGY Co.,Ltd. Address before: 100190 Beijing, Haidian District Academy of Sciences, South Road, No. 2, block A, No. 313 Applicant before: BEIJING KUANGSHI TECHNOLOGY Co.,Ltd. Applicant before: PINHOLE (BEIJING) TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170517 |