CN108319939A - A kind of 3D four-dimension head face data discrimination apparatus - Google Patents
A kind of 3D four-dimension head face data discrimination apparatus Download PDFInfo
- Publication number
- CN108319939A CN108319939A CN201810302348.4A CN201810302348A CN108319939A CN 108319939 A CN108319939 A CN 108319939A CN 201810302348 A CN201810302348 A CN 201810302348A CN 108319939 A CN108319939 A CN 108319939A
- Authority
- CN
- China
- Prior art keywords
- data
- head
- head face
- camera
- dimension
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/145—Illumination specially adapted for pattern recognition, e.g. using gratings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/08—Indexing scheme for image data processing or generation, in general involving all processing steps from image acquisition to 3D model generation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
A kind of 3D four-dimension head face data discrimination apparatus, is acquired, handles and calculates to head face image data, generates the 3D four-dimension head face data of the collected object.The present invention is to identify that the identity information of target identifies 4 D data, the head face data of target person need not be compared one by one with the mass data in database, improve the efficiency of matching identification, greatly improve the speed of identification, characteristic point fitting is carried out using based on the directly matched temmoku point cloud matching identification method in spatial domain, the Fast Fitting for realizing head face feature point compares, and then realizes the identification of identity rapid authentication.The present invention is compared with traditional technology, in conjunction with digital image processing techniques, artificial intelligence control technology, provide it is a kind of it is easy to operate, speed is fast, the 3D four-dimension with high accuracy head face data discrimination apparatus.
Description
Technical field
The present invention relates to image reconstruction and identification technology field, a kind of especially 3D four-dimension head face data identification is set
It is standby.
Background technology
Head face is intrinsic one of the physiology or behavioural characteristic of biology as biological characteristic, have certain uniqueness and
Stability, i.e., the diversity ratio between certain head facial characteristics of any two biology is larger, and head facial characteristics generally will not
As the time changes a lot, this allows for head facial characteristics and is well suited for applying in authentication or identification harvester
In the scenes such as authentication information in.
Use single camera collection head portion facial feature data, single camera that can only acquire some specific angle at present,
Or need to adjust camera to acquire the head facial characteristics of different angle, actual use get up it is inconvenient, it is relatively complicated, therefore
This technical problem urgently to be resolved hurrily.
Invention content
In view of the above problems, it is proposed that the present invention overcoming the above problem in order to provide one kind or solves at least partly
State the 3D four-dimension head face data discrimination apparatus of problem.
The present invention provides a kind of 3D four-dimension head face data discrimination apparatus, including following device：
Head face feature information harvester, for acquiring several head face characteristic patterns of human body within given time
Picture, and according to four dimension modules of several head facial feature images structure head facial characteristics, to realize the head surface
The 4 D data of portion's feature acquires；
Head facial characteristics 4 D data storage device, for scanning or the identity information of typing human body (I1, I2 ... In)
Storage is associated to collected human body head facial characteristics 4 D data as distinguishing mark, formation includes a plurality of head surface
The database of portion's feature 4 D data (D1, D2 ... Dn)；
Target body identity recognition device, for identity information (I1, the I2 ... according to scanning or the target body of typing
In the head facial characteristics 4 D data (D1, D2 ... Dn) stored in the database) is found, and by the target body
Head facial characteristics 4 D data (T1, T2 ... Tn) respectively with the head facial characteristics four that is stored in the corresponding database
Dimension data (D1, D2 ... Dn) is compared, to identify the identity of target body.
Further, the head face feature information harvester, including：
Detection components, for determining head facial positions according to collected characteristics of objects information and head face directional information
Coordinate；
Image information collection assembly, the head face image data for obtaining the collected object, and by the head
Portion's face image data is transmitted to data handling component；
Supporting rack, for installing described image information gathering components；
Data handling component, information input terminal connects the information output of described image information gathering components, for connecing
Receive described image information gathering components transmission head face image data, to the head face image data carry out processing and
It calculates, generates the 3D four-dimension head face data of the collected object.
Further, the data handling component includes image processor GPU and central processor CPU, feature point extraction
The image information of several hand-characteristic images is assigned in the block block of GPU and carries out operation by unit, and combines CPU's
Centralized dispatching and distribution function calculate several described respective characteristic points of hand-characteristic image.
Further, described image information gathering components are the camera matrix that more Visible Light Cameras are formed, the support
Frame includes the support construction equipped with arc bearing structure, and the more Visible Light Cameras are arranged in the arc bearing structure.
Further, the arc bearing structure forms U-shaped, and the detection components are set at the curved arc of U-shaped, so as to
It is corresponding with the facial positions of gathered person when acquisition.
Further, described image information gathering components are one or more in light-field camera, laser, grating, described
Supporting rack is equipped with sliding rail, and described image information gathering components can be along the sliding rail more than the face slide half cycle of head.
Further, the head face feature information harvester further includes：
Light compensating lamp, the brightness for obtaining current environment are mended when according to the brightness of current environment determination
Light time, using light compensating lamp light filling, the light compensating lamp is fixedly connected with support frame as described above.
Further, the light compensating lamp is band-like light compensating lamp, is circumferentially uniformly distributed along head face.
Further, described image information gathering components include depth infrared camera and zoom color camera, the support
Frame is equipped with camera placement mechanism, and the detection components include human body sensing measurement module.
Further, the head face feature information harvester further includes connecting with the detection components information output
The seat connect, the data handling component include driver, which is used to drive based on the head facial positions coordinate
The seat rises or falls.
Further, the data handling component further includes：
Image processor, for the head face image data optimization processing, including it is automatic exposure, automatic white flat
Weighing apparatus, auto-focusing and/or image deformity correction；
Central processing unit carries out registration and calculates for the head face image data to be inputted registration Algorithm model
To registration data, the 3D four-dimension head face data of the collected object is generated based on the registration data.
The head face feature information harvester further includes：
Display in the arc bearing structure is set, and the display is connect with the data handling component；
The data handling component is built after obtaining the 3D models of head face, shows head by visual means on the display
Portion's face 3D data；Or after the data handling component builds to obtain the 3D models of the face of the head with time dimension,
On the display head face 4 D data is shown by visual means.
Further, the target body identity recognition device gives birth to the target using temmoku point cloud matching identification method
Biological characteristic 4 D data (D1, the D2 ... stored in the biological characteristic 4 D data (T1, T2 ... Tn) of object and the database
Dn it) is compared；The temmoku point cloud matching identification method includes the following steps：
S301. characteristic point is fitted；
S302. curved surface entirety best fit；
S303. similarity calculation；
Further, the temmoku point cloud matching identification method comprises the following specific steps that：
Characteristic point fitting is carried out using based on spatial domain directly matched method, in the corresponding rigid region of two clouds,
It chooses three and features above point is used as fitting key point, pass through coordinate transform, directly carry out characteristic point Corresponding matching；
After characteristic point Corresponding matching, the alignment of data of the point cloud after whole curved surface best fit；
Similarity calculation is carried out using least square method.
The beneficial effects of the present invention are：A kind of 3D four-dimension head face data discrimination apparatus is provided, passes through 3D first
4 D data harvester, including detection components, for determining head according to characteristics of human body's information and head face directional information
Facial positions coordinate；Image information collection assembly, the head face image data for obtaining the collected object, and by institute
It states head face image data and is transmitted to data handling component；Supporting rack, for installing described image information gathering components；Data
Processing component, information input terminal connect the information output of described image information gathering components, for receiving described image letter
The head face image data for ceasing collection assembly transmission, is handled and is calculated to the head face image data, and institute is generated
State the 3D four-dimension head face data of collected object.Meanwhile the present invention with identify target identity information identify 4 D data,
Mass data in the data and database of target person need not be compared one by one, improve the efficiency of matching identification, significantly
The speed for improving identification carries out characteristic point fitting using based on the directly matched temmoku point cloud matching identification method in spatial domain,
The Fast Fitting for realizing hand-characteristic point compares, and then realizes the identification of identity rapid authentication.The present invention and traditional technology phase
Than, in conjunction with digital image processing techniques, artificial intelligence control technology, provide it is a kind of it is easy to operate, speed is fast, head with high accuracy
Facial 3D 4 D datas identification equipment.In addition, the face of people and hand are combinations rigid and flexible, flexible portion is because dynamic
Make variation and have different forms, such as expression shape change, facial muscle can change correspondingly state, and hand carries out different actions, hand
Portion's state can also change correspondingly.Therefore different 3D renderings can be formed, if being identified with individual data characteristics, can exists and miss
Difference.Therefore several biometric images of Visible Light Camera acquisition organism within given time, it is special according to several described biologies
Four dimension modules of picture construction biological characteristic are levied, realizes and the 4 D data of organism is acquired, store and be associated with to organism afterwards
Identity information, when whether again identify that target organism is the organism identity, even if there is table in target organism such as face
Feelings or hand have action, and also the identity of recognizable object organism, further improves accuracy of identification.
Above description is only the general introduction of technical solution of the present invention, in order to better understand the technical means of the present invention,
And can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can
It is clearer and more comprehensible, below the special specific implementation mode for lifting the present invention.
According to the following detailed description of specific embodiments of the present invention in conjunction with the accompanying drawings, those skilled in the art will be brighter
The above and other objects, advantages and features of the present invention.
Description of the drawings
By reading the detailed description of hereafter preferred embodiment, various other advantages and benefit are common for this field
Technical staff will become clear.Attached drawing only for the purpose of illustrating preferred embodiments, and is not considered as to the present invention
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings：
Fig. 1 shows the 3D four-dimension according to an embodiment of the invention head face data discrimination apparatus structural schematic diagram；
Fig. 2 is the structural schematic diagram of the first specific implementation mode of data acquisition device provided by the present invention；
Fig. 3 is the schematic device in the embodiment of the present invention；
The work flow diagram of specific embodiment shown in Fig. 4 Fig. 2；
Fig. 5 is the structural schematic diagram of second of specific implementation mode of data acquisition device provided by the present invention；
Fig. 6 is the fundamental diagram of 3D 4 D data harvesters shown in Fig. 5；
Fig. 7 is the structural schematic diagram of the third specific implementation mode of data acquisition device provided by the present invention；And
Fig. 8 is the structural schematic diagram of 4th kind of specific implementation mode of data acquisition device provided by the present invention.
Reference numeral
Pedestal 100, seat 200, supporting rack 300, display 400, bearing structure 500,600 and of image information collection assembly
Light compensating lamp 700.
Specific implementation mode
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although showing the disclosure in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
It is limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
Completely it is communicated to those skilled in the art.
It should be noted that the 3D 4 D datas in the present invention refer to three-dimensional space data binding time dimension data institute shape
At data, three dimensions binding time dimension refers to：Multiple same time intervals or different time intervals, different angle, no
With the data acquisition system of image or image formation situations such as orientation or different conditions.In other words, 4 D data can be multiple
The 3D data acquisition systems of same time interval or different time intervals, different angle, different direction, different expression forms etc..It is described
Head, refer to all organs of human body neck (cervical vertebra) or more；Described face refers to face and ear.
In order to solve the above technical problems, an embodiment of the present invention provides a kind of 3D four-dimension head face data discrimination apparatus.
Fig. 1 shows the 3D four-dimension according to an embodiment of the invention head face data discrimination apparatus structural schematic diagram, packet
It includes：Head face feature information harvester, for acquiring several head facial feature images of human body within given time, and
Four dimension modules that head facial characteristics is built according to several described head facial feature images, to realize the head facial characteristics
4 D data acquisition；
Head facial characteristics 4 D data storage device, for scanning or the identity information of typing human body (I1, I2 ... In)
Storage is associated to collected human body head facial characteristics 4 D data as distinguishing mark, formation includes a plurality of head surface
The database of portion's feature 4 D data (D1, D2 ... Dn)；
Target body identity recognition device, for identity information (I1, the I2 ... according to scanning or the target body of typing
In the head facial characteristics 4 D data (D1, D2 ... Dn) stored in the database) is found, and by the target body
Head facial characteristics 4 D data (T1, T2 ... Tn) respectively with the head facial characteristics four that is stored in the corresponding database
Dimension data (D1, D2 ... Dn) is compared, to identify the identity of target body.
Fig. 2 is the structural schematic diagram of the first specific implementation mode of data acquisition device provided by the present invention；Fig. 3 is this
Schematic device in inventive embodiments；Fig. 4 is the work flow diagram of specific embodiment shown in Fig. 2.
As shown in Fig. 2, the head face information collecting device that Fig. 2 is provided for the first specific implementation mode of the invention,
The device includes：Pedestal 100, seat 200, supporting rack 300, display 400, bearing structure 500, image information collection assembly
600, light compensating lamp 700, seat 200 are connect with pedestal 100,300 connect base 100 of supporting rack and annular bearing structure 500, display
Device 400 is located at 500 outside of annular bearing structure, and display 400 is connect with annular bearing structure 500 and supporting rack 300, light compensating lamp
Control module 600, light compensating lamp 700 are fixed in bearing structure 500.
In Fig. 2, image information collection assembly 600 is specially the camera matrix of Visible Light Camera composition.
As shown in figure 4, a kind of workflow of head face 3D 4 D data harvesters is：
Step 1) parameter setting：Camera parameter, the communication of detection components and image information collection assembly is arranged in starter
Module connects, and receives feedback information.
Step 2) data acquire：Data handling component control camera is taken pictures, gathered data, is surveyed component and is collected with image information
The communication module of component connects, and control camera is taken pictures, and receives feedback information.
Step 3) data transmission：Transmit the image data of image information collection assembly acquisition.
Step 4) Data Format Transform：Image data is received, and is decoded, JPG formatted datas and video format are generated
Data.
Step 5) guiding display：One output end of data handling component is connect with guiding display screen 400, transmission video letter
It number display screen 400 and is shown to guiding.
Step 6) Face detection identifies：Face detection identification is carried out, and then seat is controlled by chair control module.
Step 7) chair control：PLC module is connect with chair control module in seat receives control command, passes through motor mould
Block controls seat lifting.
Step 8) data validity judges：If data invalid, repetitive operation step 2) 3) 4) 5) 6) 7), if data effectively into
Enter in next step.
The multifocal dot image data conversion of step 9)：Image data format conversion module carries out multifocal point sampling to light field data
And be converted to JPG data formats.
Step 10) fusing image data：Multiple JPG data are handled, a JPG formatted data is fused into.
Step 11) generates point cloud：Multiple JPG data are handled, point cloud data is generated.
Step 12) point cloud is demarcated：Cloud information is handled, dimension data is generated.
Step 13) threedimensional model synthesizes：Calibrated point cloud data is handled, threedimensional model is generated.
Step 14) threedimensional model renders：Three-dimensional modeling data is rendered.
Step 15) threedimensional model is shown：Display screen shows threedimensional model.
The operation principle of the present invention, the present invention for traditional camera take pictures only there are one focal plane, data before and after focal plane
Fuzzy, apart from focal plane, remoter picture is fuzzyyer, and first to focus before shooting, even if focusing is clearly for certain depth of field
Object can not also photograph the front and back depth of field all clearly images, and the characteristic point of fuzzy data can not be extracted in 3D Data Synthesis,
The case where causing synthetic effect difference even to synthesize failure.
If it is camera matrix, supporting rack 300 includes the support construction equipped with arc bearing structure 500, can be by more
Visible Light Camera is arranged in arc bearing structure 500, can be uniformly distributed, can also non-uniform Distribution, can be same from multi-angle
When obtain head facial information.
In a kind of specific embodiment, image information collecting component 600 provided by the invention further includes light compensating lamp
700, which is fixedly connected with support frame as described above 300.When the brightness determination of current environment needs to carry out light filling, utilize
Light compensating lamp light filling, to improve head face data precision.
In a kind of specific embodiment, image information collection assembly 600 can also be depth infrared camera, laser,
It is one or more in grating or light-field camera.When image information collection assembly 600 be depth infrared camera, laser, grating, or
When one or more in light-field camera, sliding rail can be designed on supporting rack, image information collection assembly 600 can along sliding rail around
It is more than head face slide half cycle.
Fig. 7 and Fig. 8 are please referred to, Fig. 7 is the knot of the third specific implementation mode of data acquisition device provided by the present invention
Structure schematic diagram；Fig. 8 is the structural schematic diagram of 4th kind of specific implementation mode of data acquisition device provided by the present invention.In Fig. 7
Image information collection assembly 600 is specially laser camera, and image information collection assembly 600 is specially light-field camera in Fig. 8.
As shown in fig. 7, when image information collection assembly is the camera matrix that more Visible Light Cameras are formed, support frame as described above
Include the support construction equipped with arc bearing structure 500, formed the camera matrix more Visible Light Cameras be arranged in it is described
In arc bearing structure.Wherein, arc bearing structure forms U-shaped, and the detection components are set at the curved arc of U-shaped, so as to
It is corresponding with the facial positions of gathered person when acquisition.
In a kind of specific embodiment, data acquisition device provided by the present invention includes believing with the detection components
The seat 200 of output end connection is ceased, the data handling component includes：Driver is used to drive based on head facial positions coordinate
The seat 200 rises or falls；When biology is located on the seat 200, described image information gathering components are to head surface
Portion's information is acquired.Taking human as example, the height of people is had nothing in common with each other, when the head face position of people and image information are collected
Component camera lens position can control the height of seat 200, make image not in a plane according to the information of detection components
Information gathering components camera lens in head face, to improve the applicability of harvester, promotes the experience sense of user just.
It in the above-described embodiments, then can be by counting after getting the complete head face image data of collected object
Head face image data is handled and calculated according to processing component, generates the 3D four-dimension head face number for being collected object
According to.
Preferably, data handling component includes image processor GPU and central processor CPU, by several biological characteristic figures
The image information of picture, which is assigned in the block block of GPU, carries out operation, and combines centralized dispatching and the distribution function of CPU, calculates more
The respective characteristic point of width biometric image.It can be seen that the embodiment of the present invention is carried out using more photographing camera control technologies
The acquisition of biological information can significantly improve the collecting efficiency of biological information.Also, during the embodiment of the present invention is based on
The parallel computation of central processor and graphics processor can efficiently realize the processing of characteristic information.
Preferably, GPU is double GPU, and every GPU has a multiple block, such as 56 block, the embodiment of the present invention to this not
It is restricted.
In another preferred embodiment of the present invention, data handling component can also include：Display 400；Data processing group
Part, which is additionally operable to 3D four-dimension head face data being sent to display 400, to be shown.
Referring to FIG. 5, Fig. 5 is the structural representation of second of specific implementation mode of data acquisition device provided by the present invention
Scheme, image information collection assembly 600 is specially infrared depth camera in Fig. 5.
In 3D four-dimension head face data acquisition harvester shown in Fig. 5, image information collection assembly includes depth
Infrared camera, zoom color camera, depth infrared camera, zoom color camera can be fixed on supporting rack 500.Data
Processing component, including image processor, central processing unit and driver.Central processing module, depth infrared camera, zoom are color
Form and aspect machine, light module, camera rotating mechanism, human body sensing measurement module, camera data transmission module, display interface, operation
Interface, pedestal, seat 200.
The real-time that the present invention is rebuild around the head face stereoscopic three-dimensional of depth infrared camera, high-precision, high efficiency are adopted
With a kind of combination of depth infrared camera and zoom color camera, the high-resolution depth image of real time fusion and high-resolution
The coloured image of rate, automatically detects human body and measures human height, and automatic identification face quickly adjusts people by seat 200
Height and sitting posture, and scan and realize full-automatic head face 3D data acquisition devices.
During the work time, human body sensing test module is fixed on understructure, display interface and operation interface and bottom
Holder structure connects, and central processing module is fixed on chassis interior, and camera data transmission module is located inside understructure, pedestal knot
Structure is connect with camera rotating mechanism, and camera rotating mechanism connects zoom color camera, depth infrared camera and light module, camera
Rotating mechanism includes adjustable angle camera fixed frame, tumbler, and tumbler contains servo motor, with fast case, transmission device,
Zoom color camera, depth infrared camera, light module are fixed on adjustable angle fixed frame, and adjustable angle fixed frame is solid
It being scheduled on camera rotating mechanism, the camera rotating module of central processing module connects servo motor,
It adjusts seat 200 and is fixed on pedestal 100, adjust about 200 adjustable height of seat and left and right angle rotatable, adjust
Section seat 200 includes horizontally rotating servo motor, is vertically moved up or down servo motor, level horizontally rotates gear with fast case, vertical to rise
Transmission gear screw rod drops, and the chair control module connection of body weight inductor, wherein central processing module adjusts seat 200,
Wherein central processing module includes image quality processing chip, infrared distance measurement processing chip, puts cloud generation unit, and three
Tie up registration Algorithm processing module, 3D Data Synthesis modules, video display module, microprocessor control module, the control mould of seat 200
Block, camera rotate control module, lighting control module.
Referring to FIG. 6, Fig. 6 is the fundamental diagram of 3D 4 D data harvesters shown in Fig. 5.
Application method and step, such as Fig. 6：
1) start setting：After startup, the input unit relevant parameter on display interface includes the weight and height of people, skin
Color is arranged, the colour temperature and luminance parameter of Auto-matching light, operating mode：Automatic operation mode and manual work pattern.
2) human body sensing measurement module：According to human body sensing measurement module, whether in place detection people, and measures people's sitting posture
Height value, zoom color camera detect face automatically, judge the angle value that people sits.
3) seat is adjusted：According to the present level value and angle value of people's sitting posture, adjusting seat is automatically adjusted to face and is suitble to
The state that color camera is taken pictures with depth infrared camera scanning.
4) zoom color camera：According to face size, camera lens automatic telescopic to suitable visual angle and clarity.
5) light modules：According to the colour of skin and ambient light of face, the brightness of light adjust automatically and colour temperature, zoom color camera
Reach the picture of high-resolution and high contrast with depth infrared camera.
6) depth infrared camera：After the sitting posture of people reaches suitable position and light Matching and modification, depth infrared camera is in people
One side position of face starts to collect depth distance information.
7) camera rotating mechanism：After the start-up operation of a side position of face, camera rotation
Mechanism is turned with fixed speed, and dynamic and simultaneous transmission camera picture and Range finder data arrive
The image quality processing chip and Range finder processing chip of central processing module.
8) cloud generation module is put：The point cloud of the data of depth infrared to central processing module produces module, produces 3D point cloud
Information.
9) three-dimensional registration algoritic module：The information input of the high definition picture binding site cloud of zoom color camera is to three-dimensional registration
Algoritic module carries out registration and registration data is calculated.
10) 3D Data Synthesis module：Registration data generates 3D data models to 3D Data Synthesis modules.
11) video display module：After 3D data models generate, finally it is shown on display interface and is grasped by operation interface
Make 3D data.
Detection device obtains the characteristic information and directional information for being collected object, and passes through detection group based on above- mentioned information
Part determines head facial positions, and then obtains complete head face image data, then according to collected head face figure
As data establish 3D four-dimension head face data.Based on the characteristic information for being collected object, group is collected by image information
Part is accurate and completely obtains the head face image data for being collected object, to carry out the 3D four-dimensional reconstructions of human body biological characteristics.
The embodiment of the present invention can improve the efficiency of 3D reconstructions while effectively collecting head face image data.
The specific implementation mode of the present invention is illustrated above, but the present invention is not limited thereto, without departing from
Spirit of the invention, the present invention can also have various change.
In embodiments of the present invention, in the facial characteristics 4 D data storage device of head, storage is adopted by above step
The head facial characteristics 4 D data collected, and using the identity information of organism (I1, I2 ... In) as distinguishing mark to acquisition
To head facial characteristics 4 D data stored, formation include a plurality of head facial characteristics 4 D data (D1, D2 ... Dn)
Database, such as：4 D data D1 and the identity information I1 of the organism are associated storage, four dimensions of another organism
It is associated storage according to the identity information I2 of D2 and the organism, and so on, formation includes the number of n organism 4 D data
According to library.
Wherein, when acquisition target, that is, organism is human body, then identity information I includes but not limited to people's：Name, property
, not one or more in age and certificate number, certificate number may include people in life commonly used such as identification card number,
It is one or more in passport No., license number, social security number or officer's identity card number.
Preferably, the identity information is obtained by scanning identity card, passport, driving license, social security card or officer's identity card, alternatively,
Manually or automatically the mode of typing obtains identity information from identity card, passport, driving license, social security card or officer's identity card.
Preferably, in target body identity recognition device, when to the identification of target organism, using temmoku point cloud
Head facial characteristics 4 D data (T1, T2 ... Tn) of the matching identification method to target organism (organism of identity i.e. to be identified)
It is compared with the head facial characteristics 4 D data (D1, D2 ... Dn) stored in database, to identify the body of target organism
Part.First, it can be quickly found out deposited in this way such as the identification card number of human body by inputting the identity information of target organism
Storage in the database using the identification card number as the 4 D data (D1, D2 ... Dn) of filename, without by the data of target person with
Mass data in database is compared one by one, improves the efficiency of matching identification, greatly improves the speed of identification,
Then again taking out in the head face-image 4 D data (T1, T2 ... Tn) of the current collected human body and data
4 D data is compared, and finally identifies whether the identity of the human body meets, and then realizes authentication, specifically, using day
Mesh point cloud matching identification method includes the following steps：
S301. characteristic point is fitted；
S302. curved surface entirety best fit；
S303. similarity calculation.
Preferably, temmoku point cloud matching identification method further includes following specific steps：
Characteristic point fitting is carried out using based on spatial domain directly matched method, in the corresponding rigid region of two clouds,
It chooses three and features above point is used as fitting key point, pass through coordinate transform, directly carry out characteristic point Corresponding matching；
After characteristic point Corresponding matching, the alignment of data of the point cloud after whole curved surface best fit；
Similarity calculation is carried out using least square method.
Temmoku point cloud matching identification method (Yare Eyes point cloud match recognition method) is known
Other process and operation principle are as follows：First, point cloud at a time is the basic element for forming four dimension modules, it includes space
Coordinate information (XYZ) and colouring information (RGB).The attribute of point cloud includes spatial resolution, positional accuracy, surface normal etc..
Its feature is not influenced by external condition, will not all be changed for translating and rotating.Reverse software can carry out a cloud
Editor and processing, such as：Imageware, geomagic, catia, copycad and rapidform etc..Temmoku point cloud, which compares, to be known
Other method is distinctive to include based on the directly matched method in spatial domain：Iteration closest approach method ICP (Iterative closest
Point), ICP methods are generally divided into two steps, the fitting of first step characteristic point, second step curved surface entirety best fit.First fitting alignment
The purpose of characteristic point is in order to which the shortest time is found and is aligned two clouds of fitting to be compared.But not limited to this.Such as it can be with
It is：
The first step chooses three and features above point is used as fitting key point in the corresponding rigid region of two clouds,
By coordinate transform, characteristic point Corresponding matching is directly carried out.
ICP is a very effective tool in 3D data reconstruction process, at certain for curve or the registration of curved surface segment
One moment gave the rough initial alignment condition of two 3D models, and ICP iteratively seeks rigid transformation between the two with minimum
Change alignment error, realizes the registration of the space geometry relationship of the two.
Given setWithSet element two model surfaces of expression
Coordinate points, ICP registration techniques iteratively solve apart from nearest corresponding points, establish transformation matrix, and implement transformation to one of,
Until reaching some condition of convergence, its coding of iteration stopping is as follows：
1.1 ICP algorithm
Input .P1, P2.
P2 after output is transformed
P2(0)=P2, l=0；
Do
For P2(l) each point in
A nearest point y is looked in P1i；
End For
It calculatesRegistration error E；
IfE is more than a certain threshold value
Calculate P2(l) the transformation matrix T (l) between Y (l)；
P2(l+1)=T (l) P2(l), l=l+1；
Else
Stop；
End If
While||P2(l+l)-P2(l)||>threshold；
Wherein registration error
1.2 matchings based on local feature region：
Since head face is broadly divided into rigid model part and plasticity model part, plasticity model influences the accurate of alignment
Property, and then influence similarity.Second of gathered data has local difference to plasticity model for the first time, and a kind of solution route is only to exist
Rigid model region selected characteristic point, characteristic point be extracted from an object, to have holding to stablize under certain condition constant
Attribute, iteration closest approach method ICP characteristic points can be used and be fitted alignment.Requirement to characteristic point：
1) completeness contains object information as much as possible, is allowed to be different from the object of other classifications；2) compactedness tables
It is as few as possible up to required data volume；3) feature is also required preferably to be remained unchanged under model rotation, translation, mirror transformation.
In 3D living things feature recognitions, using two 3D biological characteristic model point clouds of alignment, the similar of input model is calculated
Degree, wherein registration error is as difference measure.
Second step：After characteristic point best fit, the alignment of data of the point cloud after whole curved surface best fit.
Third walks, similarity calculation.Least square method
Least square method (also known as least squares method) is a kind of mathematical optimization techniques.It by minimize error quadratic sum
Find the optimal function matching of data.Unknown data can be easily acquired using least square method, and these are acquired
Data and real data between error quadratic sum be minimum.Least square method can also be used for curve matching.It is some other excellent
Change problem can also be expressed by minimizing energy or maximizing entropy with least square method.It is usually used in solving curve fit problem,
And then solve the complete fitting of curved surface.It can accelerate Data Convergence by iterative algorithm, quickly acquire optimal solution.
If 3D data models at a time are inputted with stl file format, pass through calculating point cloud and triangle
The distance of piece determines its deviation.Therefore, this method needs to establish plane equation to each tri patch, and deviation arrives flat for point
The distance in face.And be IGES or STEP models for 3D data models at a time, since free form surface expression-form is
The faces NURBS, so the distance calculating in point to face needs the method for using numerical optimization to be calculated.By in iterative calculation point cloud
Each point expresses deviation to the minimum range of nurbs surface, or that nurbs surface carried out specified scale is discrete, with point and point
Apart from approximate expression point deviation, or it is converted into STL formats and carries out deviation calculating.Different coordinate alignment and deviation calculating side
The testing result of method, acquisition is also different.The size of alignment error will directly affect the confidence level of accuracy of detection and assessment report.
Best fit alignment is that detection error averagely arrives entirety, is terminated in terms of iteration by ensureing the whole minimum condition of deviation
The alignment procedure of calculation carries out 3D analyses to registration result, generates result object in the form of the root mean square of error between two figures
Output, root mean square is bigger, and difference of two models of reflection at this is bigger.Vice versa.Judge according to registration ratio is compared
Whether it is to compare subject matter.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that the implementation of the present invention
Example can be put into practice without these specific details.In some instances, well known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this description.
Similarly, it should be understood that in order to simplify the disclosure and help to understand one or more of each inventive aspect,
Above in the description of exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the method for the disclosure should be construed to reflect following intention：It is i.e. required to protect
Shield the present invention claims the more features of feature than being expressly recited in each claim.More precisely, as following
Claims reflect as, inventive aspect is all features less than single embodiment disclosed above.Therefore,
Thus the claims for following specific implementation mode are expressly incorporated in the specific implementation mode, wherein each claim itself
All as a separate embodiment of the present invention.
Those skilled in the art, which are appreciated that, to carry out adaptively the module in the component in embodiment
Change and they are arranged in the one or more components different from the embodiment.It can be the module or list in embodiment
Member or component be combined into a module or unit or component, and can be divided into addition multiple submodule or subelement or
Sub-component.Other than such feature and/or at least some of process or unit exclude each other, it may be used any
Combination is disclosed to all features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so to appoint
Where all processes or unit of method or component are combined.Unless expressly stated otherwise, this specification (including adjoint power
Profit requires, abstract and attached drawing) disclosed in each feature can be by providing the alternative features of identical, equivalent or similar purpose come generation
It replaces.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included certain features rather than other 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 claimed it is one of arbitrary
It mode can use in any combination.
It should be noted that the present invention will be described rather than limits the invention for above-described embodiment, and ability
Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference mark between bracket should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" before element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of several different elements and being come by means of properly programmed computer real
It is existing.In the unit claims listing several devices, several in these devices can be by the same hardware branch
To embody.The use of word first, second, and third does not indicate that any sequence.These words can be explained and be run after fame
Claim.
So far, although those skilled in the art will appreciate that present invention has been shown and described in detail herein multiple shows
Example property embodiment still without departing from the spirit and scope of the present invention, still can according to the present disclosure directly
Determine or derive many other variations or modifications consistent with the principles of the invention.Therefore, the scope of the present invention is understood that and recognizes
It is set to and covers other all these variations or modifications.
Claims (10)
1. a kind of 3D four-dimension head face data discrimination apparatus, which is characterized in that including following device：
Head face feature information harvester, for acquiring several head facial feature images of human body within given time,
And four dimension modules of head facial characteristics are built according to several described head facial feature images, to realize that the head face is special
The 4 D data of sign acquires；
Head facial characteristics 4 D data storage device, for scanning or the identity information of typing human body (I1, I2 ... In) conduct
Distinguishing mark is associated storage to collected human body head facial characteristics 4 D data, and formation includes that a plurality of head face is special
Levy the database of 4 D data (D1, D2 ... Dn)；
Target body identity recognition device, for being looked for according to the identity information (I1, I2 ... In) of scanning or the target body of typing
To the head facial characteristics 4 D data (D1, D2 ... Dn) stored in the database, and by the head surface of the target body
Portion's feature 4 D data (T1, T2 ... Tn) respectively with the head facial characteristics 4 D data that is stored in the corresponding database
(D1, D2 ... Dn) is compared, to identify the identity of target body.
2. equipment according to claim 1, which is characterized in that the head face feature information harvester, including：
Detection components, for determining that head facial positions are sat according to collected characteristics of objects information and head face directional information
Mark；
Image information collection assembly, the head face image data for obtaining the collected object, and by the head surface
Portion's image data is transmitted to data handling component；
Supporting rack, for installing described image information gathering components；
Data handling component, information input terminal connects the information output of described image information gathering components, for receiving
The head face image data for stating the transmission of image information collection assembly, is handled and is counted to the head face image data
It calculates, generates the 3D four-dimension head face data of the collected object.
3. equipment according to claim 2, which is characterized in that the data handling component include image processor GPU and
The image information of several hand-characteristic images is assigned to the block of GPU by central processor CPU, feature point extraction unit
Operation is carried out in block, and combines centralized dispatching and the distribution function of CPU, and it is respective to calculate several described hand-characteristic images
Characteristic point.
4. equipment according to claim 3, which is characterized in that described image information gathering components are more Visible Light Cameras
The camera matrix of formation, support frame as described above include the support construction equipped with arc bearing structure, the more Visible Light Camera cloth
It sets in the arc bearing structure.
5. equipment according to claim 4, which is characterized in that the arc bearing structure forms U-shaped, the detection group
Part is set at the curved arc of U-shaped, corresponding with the facial positions of gathered person when to acquire.
6. equipment according to claim 3, which is characterized in that described image information gathering components be light-field camera, laser,
One or more in grating, support frame as described above is equipped with sliding rail, and described image information gathering components can be along the sliding rail around head
It is more than portion's face slide half cycle.
7. according to claim 2-6 any one of them equipment, which is characterized in that the head face feature information harvester
Further include：Light compensating lamp, the brightness for obtaining current environment need to carry out light filling when according to the brightness of current environment determination
When, using light compensating lamp light filling, the light compensating lamp is fixedly connected with support frame as described above；The light compensating lamp is band-like light compensating lamp, along institute
Head face is stated circumferentially to be uniformly distributed；Described image information gathering components include depth infrared camera and zoom color camera, institute
It states supporting rack and is equipped with camera placement mechanism, the detection components include human body sensing measurement module.
8. equipment according to claim 3, which is characterized in that the head face feature information harvester further include with
The seat of the detection components information output connection, the data handling component includes driver, and the driver is for being based on
The head facial positions coordinate drives the seat to rise or fall.
9. equipment according to claim 3, which is characterized in that the data handling component further includes：
Image processor, for the head face image data optimization processing, including automatic exposure, automatic white balance, from
Dynamic focusing and/or image deformity correction；
Central processing unit carries out being registrated to be calculated matching for the head face image data to be inputted registration Algorithm model
Quasi- data generate the 3D four-dimension head face data of the collected object based on the registration data.
10. equipment according to claim 9, which is characterized in that the head face feature information harvester further includes：
Display in the arc bearing structure is set, and the display is connect with the data handling component；Described
Data handling component is built after obtaining the 3D models of head face, shows head surface by visual means on the display
Portion's 3D data；Or after the data handling component builds to obtain the 3D models of the face of the head with time dimension, in institute
It states and shows head face 4 D data by visual means on display；
The target body identity recognition device, using temmoku point cloud matching identification method to the biological characteristic of the target organism
The biological characteristic 4 D data (D1, D2 ... Dn) stored in 4 D data (T1, T2 ... Tn) and the database is compared；Institute
Temmoku point cloud matching identification method is stated to include the following steps：
S301. characteristic point is fitted；
S302. curved surface entirety best fit；
S303. similarity calculation；
The temmoku point cloud matching identification method comprises the following specific steps that：
Characteristic point fitting is carried out using based on the directly matched method in spatial domain, in the corresponding rigid region of two clouds, is chosen
Three and features above point conduct fitting key point, pass through coordinate transform, directly carry out characteristic point Corresponding matching；
After characteristic point Corresponding matching, the alignment of data of the point cloud after whole curved surface best fit；
Similarity calculation is carried out using least square method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810302348.4A CN108319939A (en) | 2018-04-04 | 2018-04-04 | A kind of 3D four-dimension head face data discrimination apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810302348.4A CN108319939A (en) | 2018-04-04 | 2018-04-04 | A kind of 3D four-dimension head face data discrimination apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108319939A true CN108319939A (en) | 2018-07-24 |
Family
ID=62897634
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810302348.4A Withdrawn CN108319939A (en) | 2018-04-04 | 2018-04-04 | A kind of 3D four-dimension head face data discrimination apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108319939A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109146961A (en) * | 2018-09-05 | 2019-01-04 | 天目爱视（北京）科技有限公司 | A kind of 3D measurement and acquisition device based on virtual matrix |
| CN109671143A (en) * | 2018-12-23 | 2019-04-23 | 广东腾晟信息科技有限公司 | Human body intelligent modeling method |
| CN109854893A (en) * | 2018-12-06 | 2019-06-07 | 东南大学 | A kind of adjustable multiple views three-dimensional reconstruction acquisition system |
| CN111046704A (en) * | 2018-10-12 | 2020-04-21 | 杭州海康威视数字技术股份有限公司 | Method and device for storing identity identification information |
| CN112016570A (en) * | 2019-12-12 | 2020-12-01 | 天目爱视（北京）科技有限公司 | Three-dimensional model generation method used in background plate synchronous rotation acquisition |
| CN114267068A (en) * | 2021-12-24 | 2022-04-01 | 北京的卢深视科技有限公司 | Face recognition method based on continuous frame information, electronic equipment and storage medium |
-
2018
- 2018-04-04 CN CN201810302348.4A patent/CN108319939A/en not_active Withdrawn
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109146961A (en) * | 2018-09-05 | 2019-01-04 | 天目爱视（北京）科技有限公司 | A kind of 3D measurement and acquisition device based on virtual matrix |
| CN109146961B (en) * | 2018-09-05 | 2019-12-31 | 天目爱视（北京）科技有限公司 | 3D measures and acquisition device based on virtual matrix |
| CN111046704A (en) * | 2018-10-12 | 2020-04-21 | 杭州海康威视数字技术股份有限公司 | Method and device for storing identity identification information |
| CN111046704B (en) * | 2018-10-12 | 2023-05-09 | 杭州海康威视数字技术股份有限公司 | Method and device for storing identity identification information |
| CN109854893A (en) * | 2018-12-06 | 2019-06-07 | 东南大学 | A kind of adjustable multiple views three-dimensional reconstruction acquisition system |
| CN109671143A (en) * | 2018-12-23 | 2019-04-23 | 广东腾晟信息科技有限公司 | Human body intelligent modeling method |
| CN112016570A (en) * | 2019-12-12 | 2020-12-01 | 天目爱视（北京）科技有限公司 | Three-dimensional model generation method used in background plate synchronous rotation acquisition |
| CN112016570B (en) * | 2019-12-12 | 2023-12-26 | 天目爱视（北京）科技有限公司 | Three-dimensional model generation method for background plate synchronous rotation acquisition |
| CN114267068A (en) * | 2021-12-24 | 2022-04-01 | 北京的卢深视科技有限公司 | Face recognition method based on continuous frame information, electronic equipment and storage medium |
| CN114267068B (en) * | 2021-12-24 | 2022-11-01 | 合肥的卢深视科技有限公司 | Face recognition method based on continuous frame information, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108319939A (en) | A kind of 3D four-dimension head face data discrimination apparatus | |
| CN109269405B (en) | A kind of quick 3D measurement and comparison method | |
| CN108564018A (en) | A kind of biological characteristic 3D 4 D datas recognition methods and system based on infrared photography | |
| CN109766876A (en) | Contactless fingerprint acquisition device and method | |
| CN110570503B (en) | Method for acquiring normal vector, geometry and material of three-dimensional object based on neural network | |
| CN108334853A (en) | A kind of head face 3D 4 D data harvesters | |
| CN112304222B (en) | Background board synchronous revolution's 3D information acquisition equipment | |
| CN111028341B (en) | Three-dimensional model generation method | |
| Omari et al. | Virtual anthropology? Reliability of three-dimensional photogrammetry as a forensic anthropology measurement and documentation technique | |
| CN108446596A (en) | Iris 3D 4 D datas acquisition system based on Visible Light Camera matrix and method | |
| CN109377551A (en) | A kind of three-dimensional facial reconstruction method, device and its storage medium | |
| CN108334874A (en) | A kind of 3D four-dimension iris image identification equipment | |
| KR101792541B1 (en) | Smart Device Skin care service system using Skin Diagnostic Information | |
| US11769320B2 (en) | Systems and methods for dynamic identification of a surgical tray and the items contained thereon | |
| CN1655193A (en) | Method and image processing system for segmentation of section image data | |
| CN108470166A (en) | A kind of biological characteristic 3D 4 D datas recognition methods and system based on laser scanning | |
| CN108416312A (en) | A kind of biological characteristic 3D data identification methods and system taken pictures based on visible light | |
| CN111160136A (en) | Standardized 3D information acquisition and measurement method and system | |
| CN108550184A (en) | A kind of biological characteristic 3D 4 D datas recognition methods and system based on light-field camera | |
| CN108470152A (en) | Based on infrared 3D four-dimension iris data acquisition methods and system | |
| CN108470149A (en) | A kind of 3D 4 D datas acquisition method and device based on light-field camera | |
| CN108520230A (en) | A kind of 3D four-dimension hand images data identification method and equipment | |
| CN108446597A (en) | A kind of biological characteristic 3D collecting methods and device based on Visible Light Camera | |
| CN209401042U (en) | Contactless fingerprint acquisition device | |
| CN108334873A (en) | A kind of 3D four-dimension hand data discrimination apparatus |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180724 |