CN206322194U - A kind of anti-fraud face identification system based on 3-D scanning - Google Patents
A kind of anti-fraud face identification system based on 3-D scanning Download PDFInfo
- Publication number
- CN206322194U CN206322194U CN201621161959.4U CN201621161959U CN206322194U CN 206322194 U CN206322194 U CN 206322194U CN 201621161959 U CN201621161959 U CN 201621161959U CN 206322194 U CN206322194 U CN 206322194U
- Authority
- CN
- China
- Prior art keywords
- module
- dimensional information
- dimensional
- face
- scanning
- 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.)
- Expired - Fee Related
Links
Abstract
The utility model discloses a kind of anti-fraud face identification system based on 3-D scanning, system, three-dimensional information storage system and three-dimensional information comparison system are obtained including three-dimensional information, the three-dimensional information storage system obtains system, three-dimensional information comparison system with three-dimensional information respectively and is connected.The utility model provides a kind of anti-fraud face identification system based on 3-D scanning, and the system has simple in construction, reasonable in design, efficient, safe and reliable advantage.
Description
Technical field
The utility model belongs to technical field of mapping, and in particular to a kind of anti-fraud recognition of face system based on 3-D scanning
System.
Background technology
Face identification system, using face recognition technology as core, is an emerging biological identification technology, is the current world
The high-quality precision and sophisticated technology of sciemtifec and technical sphere tackling key problem, its widely used regional characteristics analysis algorithm has merged computer image processing technology
With biostatistics principle in one, portrait characteristic point is extracted from video using computer image processing technology, biology is utilized
Statistical principle carries out analysis founding mathematical models, with vast potential for future development.
The principle of face identification system is that system input is usually one or a series of contains the face for not determining identity
The facial image recognition of some known identities in image, and face database or corresponding coding, and its output is then one to be
Row similarity score, shows the identity of face to be identified.
Face identification system is widely used in recognition of face access management system, recognition of face access control and attendance system, face
Recognize monitoring management, the strick precaution of recognition of face computer security, the search of recognition of face photo, the visiting registration of recognition of face, recognition of face
The intelligent clearance system of ATM intelligent video warning system, recognition of face prison intelligent alarm system, recognition of face RFID, face
Identification public security criminal pursue and capture an escaped prisoner intelligent alarm system etc., it is adaptable to park, factory, supermarket, cell square, conference centre, physical culture
The significant points of the public activities such as venue, school, hospital, residential quarter, commercial street, the large-scale market of farm produce and gathering place, hotel
（Hotel）, food and drink, public place of entertainment, the hall gateway of office building, a variety of occasions such as elevator and other main thoroughfares.
Present face identification system be based on two dimension image analyzed, including man face image acquiring, Face detection,
The technologies such as recognition of face contrast identity validation, separate people in a frame of a sub-picture or video flowing from background, will
The a certain object contrast registered in the portrait and database that capture；It is general to be known according to the set feature of face and PCA face
Not, after a series of training algorithms lifting precision, realized based on gradation of image.
But, two-dimentional facial image obtains the 3D models fraud that system is easily generated by photo, passes through open
Photo build dummy model can cheat most face identification system to crack the mode of face detection, it is only necessary to it is three low
The photo of resolution ratio is just enough to reappear 3D models to cheat authentication system, and the duplicity based on VR fundamentally refers to
To the leak of the identification system based on two dimension, in the case where photographic quality is good enough, VR, which is built, can break through more than 80% two dimension
Face identification system.
Utility model content
In view of the shortcomings of the prior art, the utility model provides a kind of anti-fraud recognition of face system based on 3-D scanning
System, the system has simple in construction, reasonable in design, efficient, safe and reliable advantage.
To realize utility model purpose, the utility model uses following technical scheme：
A kind of anti-fraud face identification system based on 3-D scanning, including three-dimensional information obtain system, three-dimensional information and deposited
Storage system and three-dimensional information comparison system, the three-dimensional information storage system obtain system, three-dimensional information with three-dimensional information respectively
Comparison system is connected.
Preferably, the three-dimensional information obtain system include power supply module and connected projecting apparatus module, video camera,
Projecting apparatus ray machine is provided with face tracking and depth transducer, light filling module and communication module group, the projecting apparatus module.
Preferably, the face tracking and depth transducer include control unit and respectively connected image unit,
Face tracking module, sensing unit, display unit, driver element, the driver element connecting power device.
Preferably, the three-dimensional information storage system include integrated edge extracting module on circuit boards, noise reduction module,
Eliminate expression weight module, texture and remove splicing and reset module, three-dimensional feature and quantify module and time storage module.
The utility model, come gathered data information, uses deep by optical camera and projecting apparatus ray machine in the moment of collection
Degree sensor builds the coordinate system of three dimensions with high-definition camera camera lens and passed with obtaining texture model, then by the data of acquisition
Enter and rebuild and analyzed into information system, repeat shoot multiple image, then by three-dimensional algorithm go calculate face space
Position（Coordinate is constructed in scanning process with depth transducer and optical lens）, it can be spliced in real time afterwards,
Obtain complete three-dimensional data.
Preferably, the three-dimensional information, which obtains system, includes power supply module and connected laser module, HDR industry
Laser is provided with camera, color cmos camera, light filling module and communication module group, the laser module.
Preferably, the three-dimensional information storage system includes integrated discrete point cloud processing module, secondary on circuit boards
Surface interpolation module, edge extracting module, noise reduction module, elimination expression weight module, texture remove splicing and replacement module, three
Dimensional feature quantifies module and time storage module.
The utility model is adopted by high resolution camera, laser module, red flashing light lamp and two HDR industrial cameras
Collect data message, laser rays is irradiated to human face, two cameras catch this flashy 3 d scan data, due to people
The curvature in body surface face is different, and light, which is radiated on object, can reflect and reflect, and now scanner will obtain object under test
Spatial information, depth information, for determining each point position in space of body surface, 3D scanners in different angles,
Some width positional informations of object can be recorded, software compares these positional informations（align）, to obtain overall position letter
Breath, software integration（fuse）All positional informations are combined into a complete object, at this moment can be by these information with soft
Part is converted to 3D point cloud, and cloud data only includes the geometric coordinate and Reflection intensity information of object, by being carried out to camera
After inside and outside parameter demarcation, image and point cloud are merged by photogrammetric mode, passed in the moment of collection with depth
Sensor builds the coordinate system of three dimensions with industrial camera camera lens, and the principle spread again with a cloud obtains texture mapping data,
The data of acquisition are passed in information system again and is rebuild and is analyzed, repeat to shoot multiple image, then pass through three-dimensional algorithm
Go to the locus of calculating face（Locus is determined in scanning process with laser sensor）, can carry out afterwards in real time
Splicing, obtain complete three-dimensional data.
Preferably, the three-dimensional information, which obtains system, includes power supply module and connected optical camera, RGB color
Video camera, 3D depth inductor, two dimensional character tracker module, light filling module and communication module group, the 3D depth inductor bag
Include RF transmitter and infrared C MOS video cameras.
Preferably, the three-dimensional information storage system include integrated demarcation module on circuit boards, edge extracting module,
Noise reduction module, elimination expression weight module, texture remove splicing and quantify module and time storage mould with replacement module, three-dimensional feature
Group.
Preferably, the three-dimensional information comparison system includes the main control server of 1 internal database, pair for information
Than, feedback, preserve.
Preferably, the Aunar that the optical camera includes being sequentially connected in order draws chip, autozoom module, focal length
And aperture.
Preferably, the light filling module includes circuit board, metallic support, pad and light compensating lamp, the metallic support two ends
Circuit board and pad are connected respectively, and the light compensating lamp is fixed in pad.
The utility model is by optical camera, RGB color video camera, RF transmitter and infrared C MOS video cameras
The 3D depth inductors constituted carry out gathered data information, and 3D depth inductor perceives environment by way of black and white spectrum：
Black represents infinity, and pure white to represent infinitely near, the gray zone correspondence object between black and white arrives the physical distance of sensor, its receipts
Collect every bit within the vision, and form the depth image that a width represents surrounding environment, generated with the speed of 10-30 frames per second
Depth image stream, reproduces surrounding environment, software can carry out Pixel-level assessment to depth image, to distinguish human body not real-time 3D
Same position, meanwhile, this process must shorten the response time with the pretreatment of optimization, and the flight time is based in the moment of collection
The principle of the depth calculation imaging of TOF camera, collocation depth transducer builds the coordinate of three dimensions with high definition camera camera lens
The data of acquisition then are passed in information system with obtaining texture model and are rebuild and analyzed by system, with acquired many
Frame video flowing, then by three-dimensional algorithm go calculate face locus（Depth transducer and light are used in scanning process
Learn camera lens and construct coordinate）, can in real time be spliced afterwards, obtain complete three-dimensional data, reused Active
Apperance Model are used as two dimensional character tracker, the depth data of the model extension that then calculating is obtained to the system
On, carry out three-dimensional face identification.
3D depth inductor will be distinguished from background environment human body using segmentation strategy, i.e., extracted from noise
Go out useful signal.Can be with face's skeleton of Proactive traceback user, in this stage, we are the object being each tracked in the depth of field
So-called segmentation shade is created in image, this is a kind of by background object（Such as chair and pet etc.）Depth map after rejecting
Picture, only the part of shade is split in transmission in handling process below, to mitigate body-sensing amount of calculation, obtains the image of multiframe
Afterwards, the work next exactly recognized, the simply basic image data obtained through LightCoding technologies, weight
Point still will recognize image, be converted to effective instruction.
The beneficial effects of the utility model are：The utility model, which provides a kind of anti-fraud face based on 3-D scanning, to be known
Other system, the system has simple in construction, reasonable in design, efficient, safe and reliable advantage.
1st, relative to plane geometry principle, for face is identified, the system uses space geometry principle, lead to
The acquisition of information of depth dimension is crossed, fraud will not be caused to recognition of face by making the structure of VR models, it is necessary to be the three-dimensional in space
Object could be by the checking of recognition of face；
2nd, for feature based PCA/LDA face identification method, the system need not carry out the change of image,
But be compared directly against the threedimensional model in database, success rate is more than more than 80%；
3rd, the system can obtain texture mapping, exclude after illumination, skin color, human face expression influence, can be by eyeball, wound
A series of indexs such as scar, cheekbone height are added to recognition of face, and on the basis of anti-fraud, 3-D scanning would is that elasticity
The face matching of model, the true and false is judged by the information of multiple dimensions.
Brief description of the drawings
Fig. 1 is structured flowchart of the present utility model；
Fig. 2 is the structural representation of three-dimensional information acquisition system in embodiment 1；
Fig. 3 is the structural representation of three-dimensional information acquisition system in embodiment 2；
Fig. 4 is the structural representation of three-dimensional information acquisition system in embodiment 3；
Fig. 5 is the structural representation of the utility model three-dimensional information storage system；
Fig. 6 is the structural representation of the utility model three-dimensional information comparison system；
Fig. 7 is the structured flowchart of the utility model face tracking and depth transducer；
Fig. 8 is the structural representation of the utility model light filling module；
Fig. 9 is the structural representation of the utility model optical camera；
In the figures above：1st, power supply module；2nd, projecting apparatus module；3rd, face tracking and depth transducer；4th, light filling module；
5th, communication module group；6th, video camera；7th, HDR industrial cameras；8th, color cmos camera；9th, RGB color video camera；10th, infrared ray
CMOS video cameras；11st, circuit board；12nd, metallic support；13rd, pad；14th, light compensating lamp；15th, Aunar draws chip；16th, autozoom
Module；17th, focal length；18th, aperture.
Embodiment
The utility model is further described by embodiment below in conjunction with the accompanying drawings.
Embodiment 1
As shown in Figure 1, Figure 2, shown in Fig. 5, Fig. 6, Fig. 7, Fig. 8, a kind of anti-fraud face identification system based on 3-D scanning, bag
Include three-dimensional information and obtain system, three-dimensional information storage system and three-dimensional information comparison system, the three-dimensional information storage system point
System, three-dimensional information comparison system is not obtained with three-dimensional information be connected, the three-dimensional information obtain system include powering module 1 and
Connected projecting apparatus module 2, video camera, face tracking and depth transducer 3, light filling module 4 and communication module group 5, it is described
Projecting apparatus ray machine is provided with projecting apparatus module 2, the face tracking connects with depth transducer 3 including control unit and respectively with it
The image unit that connects, face tracking module, sensing unit, display unit, driver element, the driver element connection power dress
Put, the light filling module 4 includes circuit board 11, metallic support 12, pad 13 and light compensating lamp 14, the two ends of metallic support 12 point
Not Lian Jie circuit board 11 and pad 13, the light compensating lamp 14 is fixed in pad 13, and the three-dimensional information storage system includes collection
Into edge extracting module on circuit boards, noise reduction module, eliminate expression weight module, texture remove splicing with reset module,
Three-dimensional feature quantifies module and time storage module, and the three-dimensional information comparison system includes the master control clothes of 1 internal database
Business device, for the contrast of information, feedback, is preserved.
Operation principle：
User will carry out the recognition of face of three-dimensional before camera lens when using the system, and three-dimensional three-dimensional information obtains system
System first use light filling module, to experiencer face carry out light filling, with realize remove shade effect, by control projecting apparatus module and
Video camera obtains the three-dimensional light of user along data and texture mapping, and the acquisition of information that progress is more than 3 times, face tracking is passed with depth
Sensor will be tracked and obtain the distance of curved surface of face part in face moving process to object, be communicated with TCP/IP
Acquired data are uploaded to three-dimensional information storage system by module, and face surface data carries out edge line extraction, object noise reduction,
The spatial warping that face is brought because of expression is removed, by three-dimensional characteristic quantification, texture is removed and is spliced, weighed afterwards
Put, will texture mapping be mapped in threedimensional model, can be locked for time for uploading, such as without knowledge within 5min
Not, alarm feedback will be carried out, main control server obtains the final data uploaded, with three-dimensional face number reserved in database
According to being contrasted, after multiple index contrasts such as face depth, scar, cheekbone height, human eye, by feedback simultaneously to original
Database file is modified.
Embodiment 2
As shown in Fig. 1, Fig. 3, Fig. 5, Fig. 6, Fig. 8, a kind of anti-fraud face identification system based on 3-D scanning, including three
Tie up Information Acquisition System, three-dimensional information storage system and three-dimensional information comparison system, the three-dimensional information storage system respectively with
Three-dimensional information obtains system, the connection of three-dimensional information comparison system, the three-dimensional information obtain system include power supply module 1 and and its
Laser module, HDR industrial cameras 7, color cmos camera 8, light filling module 4 and the communication module group 5 of connection, the laser die
Laser is provided with group, the light filling module includes circuit board 11, metallic support 12, pad 13 and light compensating lamp 14, the metal
The two ends of support 12 connect circuit board 11 and pad 13 respectively, and the light compensating lamp 14 is fixed in pad 13, and the three-dimensional information is deposited
Storage system includes integrated discrete point cloud on circuit boards and handles module, quadratic surface interpolation module, edge extracting module, noise reduction
Module, elimination expression weight module, texture remove splicing and quantify module and time storage module with replacement module, three-dimensional feature,
The three-dimensional information comparison system includes the main control server of 1 internal database, for the contrast of information, feedback, preserves.
Operation principle：
User will carry out the recognition of face of three-dimensional before camera lens when using the system, and it is first that three-dimensional information obtains system
Light filling module is used, light filling is carried out to experiencer's face, to realize the effect for removing shade, by controlling laser module（It is built-in
Laser）, 2 HDR industrial cameras obtain the three-dimensional space data of user, obtain texture with the color cmos camera of low noise and paste
Figure, spatial digitizer will obtain the spatial information of object under test, depth information and be used for determining each point of body surface in space
In the different angle in position, some width positional informations of object can be recorded, software compares these positional informations（align）, come
Obtain overall positional information, software integration（fuse）All positional informations are combined into a complete object, at this moment can be with
3D point cloud is converted to software by these information, and cloud data only believe by geometric coordinate and reflected intensity comprising object
Breath, image and point cloud by being carried out to camera after inside and outside parameter demarcation, merged by photogrammetric mode, carried out 3
Acquisition of information more than secondary, the face tracking module of high frequency will be tracked in face moving process to object, and depth is passed
Sensor obtains the distance of curved surface of face part, and by under point cloud registering to control net coordinate system, the point cloud lacked for target also may be used
Registration two-by-two is carried out to it to find same place using public domain, in order to there is a cloud to be transformed into unified control net coordinate
System is lower to obtain a cloud with together with the registering method in control point, requires that a wherein station is necessary for being fitted on control net with punctual two-by-two
Point cloud under coordinate system, can set up big when the data of point cloud field data acquisition are directed into software according to coordinate points automatic Mosaic
After the discrete spatial point cloud data of amount, construct the threedimensional model of human body on this basis, put the leak reparation of cloud due to a cloud
The discreteness of itself, can cause model to there is certain defect, it is necessary to carry out the behaviour such as auto-mending, adjustment to it in the polygon stage
After work, accurate mathematical model can just be obtained by carrying out quadratic surface interpolation module, will be acquired with TCP/IP communication module groups
Data upload to three-dimensional information storage system, and face surface data carries out edge line extraction, object noise reduction, remove face because table
Feelings and the spatial warping brought, by three-dimensional characteristic quantification, remove texture and are spliced, reset afterwards, a cloud is spread again
Into three dimensions, the textures of required texture are mapped in three-dimensional point cloud, can be locked for the time uploaded, such as
Without identification within 5min, alarm feedback will be carried out, main control server obtains the final data uploaded, with having been protected in database
The three-dimensional face data stayed are contrasted, after multiple index contrasts such as face depth, scar, cheekbone height, human eye, by anti-
Feedback is modified to original database file simultaneously.
Embodiment 3
As shown in Fig. 1, Fig. 4, Fig. 5, Fig. 6, Fig. 8, Fig. 9, a kind of anti-fraud face identification system based on 3-D scanning, bag
Include three-dimensional information and obtain system, three-dimensional information storage system and three-dimensional information comparison system, the three-dimensional information storage system point
System, three-dimensional information comparison system is not obtained with three-dimensional information be connected, the three-dimensional information obtain system include powering module 1 and
Connected optical camera, RGB color video camera 9,3D depth inductor, two dimensional character tracker module, light filling module 4
With communication module group 5, the 3D depth inductor includes RF transmitter and infrared C MOS video cameras 10, the optical camera
The Aunar that head includes being sequentially connected in order draws chip 15, autozoom module 16, focal length 17 and aperture 18, the light filling module
4 include circuit board 11, metallic support 12, pad 13 and light compensating lamp 14, and the two ends of metallic support 12 connect circuit board 11 respectively
With pad 13, the light compensating lamp 14 is fixed in pad 13, the three-dimensional information storage system include it is integrated on circuit boards
Demarcate module, edge extracting module, noise reduction module, elimination expression weight module, texture removal splicing and replacement module, three-dimensional spy
Quantization module and time storage module are levied, the three-dimensional information comparison system includes the main control server of 1 internal database, used
In the contrast of information, feedback, preserve.
Operation principle：
User will carry out the recognition of face of three-dimensional before camera lens when using the system, and it is first that three-dimensional information obtains system
Light filling is carried out to experiencer's face with light filling module, to realize the effect for removing shade, height is obtained with RGB color video camera
The problem of quality textures, the 3D depth perceptions that GB colour cameras and RF transmitter and infrared C MOS video cameras are constituted should
Device generate depth image stream with the speed of 10-30 frames per second to arrange in pairs or groups, and reproduces surrounding environment, two dimensional character tracker real-time 3D
Module will be distinguished from background environment face using segmentation strategy, i.e., useful signal is extracted from noise, can be with
Face's skeleton of Proactive traceback user, in this stage, the system is that the object being each tracked is created in depth image
So-called segmentation shade, this is a kind of by background object（Such as chair and pet etc.）Depth image after rejecting, below
Only the part of shade is split in transmission in handling process, and to mitigate body-sensing amount of calculation, software can carry out Pixel-level to depth image
Assess, to distinguish the face different parts of human body, meanwhile, this process must shorten the response time with the pretreatment of optimization,
In the principle of depth calculation imaging of the moment based on flight time TOF camera of collection, collocation 3D depth transducers and high definition phase
Coordinate system of the machine camera lens to build three dimensions repeatedly obtains video flowing, obtained with 3D depth transducers with obtaining texture model
The distance of curved surface of face part is taken to use Active Apperance Model as two dimensional character tracker, then calculating
Obtained model extension is to our depth data, and face tracking module will be chased after in face moving process to object
Next it is exactly the work recognized after track, the image for obtaining multiframe, is through what LightCoding technologies were obtained
Basic image data, emphasis still will recognize image, be converted to effective instruction, obtain high-quality three-dimensional data, use
Acquired data are uploaded to three-dimensional information storage system by TCP/IP communication module groups, and face surface data carries out edge line and carried
Take, object noise reduction, remove face because expression and the spatial warping that brings, by three-dimensional characteristic quantification, remove texture and spelled
Connect, reset afterwards, texture mapping is mapped in threedimensional model, can be locked, such as existed for the time uploaded
Without identification within 5min, alarm feedback will be carried out, main control server obtains the final data uploaded, and reserved in database
Three-dimensional face data contrasted, after the contrast of the multiple indexs such as face depth, scar, cheekbone height, human eye, pass through feedback
Original database file is modified simultaneously.
Specific embodiment of the utility model is the foregoing is only, but architectural feature of the present utility model is not limited to
This, the utility model can be used on similar product, and any those skilled in the art is in field of the present utility model, institute
The change or modification of work are all covered among the scope of the claims of the present utility model.
Claims (4)
1. a kind of anti-fraud face identification system based on 3-D scanning, it is characterised in that：System, three are obtained including three-dimensional information
Tie up information storage system and three-dimensional information comparison system, the three-dimensional information storage system obtained respectively with three-dimensional information system,
Three-dimensional information comparison system is connected, the three-dimensional information obtain system include power supply module and connected laser module,
Laser is provided with HDR industrial cameras, color cmos camera, light filling module and communication module group, the laser module.
2. the anti-fraud face identification system as claimed in claim 1 based on 3-D scanning, it is characterised in that：The three-dimensional letter
Cease storage system include it is integrated on circuit boards discrete point cloud processing module, quadratic surface interpolation module, edge extracting module,
Noise reduction module, elimination expression weight module, texture remove splicing and quantify module and time storage mould with replacement module, three-dimensional feature
Group.
3. the anti-fraud face identification system as claimed in claim 1 or 2 based on 3-D scanning, it is characterised in that：Described three
Tieing up information comparison system includes the main control server of 1 internal database, for the contrast of information, feedback, preserves.
4. the anti-fraud face identification system as claimed in claim 3 based on 3-D scanning, it is characterised in that：The light filling mould
Group includes circuit board, metallic support, pad and light compensating lamp, and the metallic support two ends connect circuit board and pad respectively, described
Light compensating lamp is fixed in pad.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201621161959.4U CN206322194U (en) | 2016-10-24 | 2016-10-24 | A kind of anti-fraud face identification system based on 3-D scanning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201621161959.4U CN206322194U (en) | 2016-10-24 | 2016-10-24 | A kind of anti-fraud face identification system based on 3-D scanning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN206322194U true CN206322194U (en) | 2017-07-11 |
Family
ID=59263378
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201621161959.4U Expired - Fee Related CN206322194U (en) | 2016-10-24 | 2016-10-24 | A kind of anti-fraud face identification system based on 3-D scanning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN206322194U (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106384106A (en) * | 2016-10-24 | 2017-02-08 | 杭州非白三维科技有限公司 | Anti-fraud face recognition system based on 3D scanning |
| CN107509045A (en) * | 2017-09-11 | 2017-12-22 | 广东欧珀移动通信有限公司 | Image processing method and device, electronic installation and computer-readable recording medium |
| CN107509043A (en) * | 2017-09-11 | 2017-12-22 | 广东欧珀移动通信有限公司 | Image processing method and device |
| CN107707831A (en) * | 2017-09-11 | 2018-02-16 | 广东欧珀移动通信有限公司 | Image processing method and device, electronic installation and computer-readable recording medium |
| CN108171185A (en) * | 2018-01-03 | 2018-06-15 | 阿里巴巴集团控股有限公司 | The method, apparatus and system of identification |
| CN110223297A (en) * | 2019-04-16 | 2019-09-10 | 广东康云科技有限公司 | Segmentation and recognition methods, system and storage medium based on scanning point cloud data |
| US11503228B2 (en) | 2017-09-11 | 2022-11-15 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Image processing method, image processing apparatus and computer readable storage medium |
-
2016
- 2016-10-24 CN CN201621161959.4U patent/CN206322194U/en not_active Expired - Fee Related
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106384106A (en) * | 2016-10-24 | 2017-02-08 | 杭州非白三维科技有限公司 | Anti-fraud face recognition system based on 3D scanning |
| CN107509045A (en) * | 2017-09-11 | 2017-12-22 | 广东欧珀移动通信有限公司 | Image processing method and device, electronic installation and computer-readable recording medium |
| CN107509043A (en) * | 2017-09-11 | 2017-12-22 | 广东欧珀移动通信有限公司 | Image processing method and device |
| CN107707831A (en) * | 2017-09-11 | 2018-02-16 | 广东欧珀移动通信有限公司 | Image processing method and device, electronic installation and computer-readable recording medium |
| CN107509043B (en) * | 2017-09-11 | 2020-06-05 | Oppo广东移动通信有限公司 | Image processing method, image processing apparatus, electronic apparatus, and computer-readable storage medium |
| US11503228B2 (en) | 2017-09-11 | 2022-11-15 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Image processing method, image processing apparatus and computer readable storage medium |
| US11516412B2 (en) | 2017-09-11 | 2022-11-29 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Image processing method, image processing apparatus and electronic device |
| CN108171185A (en) * | 2018-01-03 | 2018-06-15 | 阿里巴巴集团控股有限公司 | The method, apparatus and system of identification |
| CN110223297A (en) * | 2019-04-16 | 2019-09-10 | 广东康云科技有限公司 | Segmentation and recognition methods, system and storage medium based on scanning point cloud data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN206322194U (en) | A kind of anti-fraud face identification system based on 3-D scanning | |
| CN106384106A (en) | Anti-fraud face recognition system based on 3D scanning | |
| WO2021088300A1 (en) | Rgb-d multi-mode fusion personnel detection method based on asymmetric double-stream network | |
| CN104166841B (en) | The quick detection recognition methods of pedestrian or vehicle is specified in a kind of video surveillance network | |
| CN104851099B (en) | A kind of image interfusion method based on expression study | |
| CN109819208A (en) | A kind of dense population security monitoring management method based on artificial intelligence dynamic monitoring | |
| CN109657581B (en) | Urban rail transit gate traffic control method based on binocular camera behavior detection | |
| CN106778506A (en) | A kind of expression recognition method for merging depth image and multi-channel feature | |
| CN106446873A (en) | Face detection method and device | |
| CN105843386A (en) | Virtual fitting system in shopping mall | |
| KR20150021526A (en) | Self learning face recognition using depth based tracking for database generation and update | |
| CN106056053A (en) | Human posture recognition method based on skeleton feature point extraction | |
| CN110390308B (en) | Video behavior identification method based on space-time confrontation generation network | |
| CN111462128A (en) | Pixel-level image segmentation system and method based on multi-modal spectral image | |
| CN107247920A (en) | Interaction control method, device and computer-readable recording medium | |
| CN113378649A (en) | Identity, position and action recognition method, system, electronic equipment and storage medium | |
| CN107704851A (en) | Character recognition method, Public Media exhibiting device, server and system | |
| CN107147877A (en) | FX night fog day condition all-weather colorful video imaging system and its construction method | |
| CN106970709A (en) | A kind of 3D exchange methods and device based on holographic imaging | |
| CN113762009B (en) | Crowd counting method based on multi-scale feature fusion and double-attention mechanism | |
| CN103235943A (en) | Principal component analysis-based (PCA-based) three-dimensional (3D) face recognition system | |
| CN112488165A (en) | Infrared pedestrian identification method and system based on deep learning model | |
| Liu et al. | STCN-Net: A novel multi-feature stream fusion visibility estimation approach | |
| CN109033999B (en) | Subway charge platform based on face recognition | |
| CN111199184A (en) | Portable three-dimensional imaging equipment for intelligent community patrol and use method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170711 Termination date: 20191024 |