CN105554385B - A kind of remote multi-modal biological characteristic recognition methods and its system - Google Patents
A kind of remote multi-modal biological characteristic recognition methods and its system Download PDFInfo
- Publication number
- CN105554385B CN105554385B CN201510957176.0A CN201510957176A CN105554385B CN 105554385 B CN105554385 B CN 105554385B CN 201510957176 A CN201510957176 A CN 201510957176A CN 105554385 B CN105554385 B CN 105554385B
- Authority
- CN
- China
- Prior art keywords
- camera
- user
- iris
- video camera
- facial image
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000001815 facial effect Effects 0.000 claims abstract description 125
- 238000012545 processing Methods 0.000 claims abstract description 45
- 238000013500 data storage Methods 0.000 claims abstract description 13
- 238000012876 topography Methods 0.000 claims description 39
- 238000003384 imaging method Methods 0.000 claims description 19
- 230000011218 segmentation Effects 0.000 claims description 17
- 238000001514 detection method Methods 0.000 claims description 14
- 239000000284 extract Substances 0.000 claims description 11
- 230000003287 optical effect Effects 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 11
- 238000003860 storage Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 7
- 238000002366 time-of-flight method Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 3
- 238000002360 preparation method Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 2
- 230000001960 triggered effect Effects 0.000 claims description 2
- 230000003993 interaction Effects 0.000 abstract description 9
- 230000008901 benefit Effects 0.000 abstract description 8
- 230000000295 complement effect Effects 0.000 abstract description 4
- 230000002349 favourable effect Effects 0.000 abstract description 4
- 238000004422 calculation algorithm Methods 0.000 description 16
- 238000005516 engineering process Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 5
- 210000004709 eyebrow Anatomy 0.000 description 3
- 238000003909 pattern recognition Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000011478 gradient descent method Methods 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 230000004807 localization Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000035800 maturation Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 210000001938 protoplast Anatomy 0.000 description 2
- 238000013441 quality evaluation Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012827 research and development Methods 0.000 description 2
- 208000033748 Device issues Diseases 0.000 description 1
- 239000000571 coke Substances 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 210000003746 feather Anatomy 0.000 description 1
- 230000005021 gait Effects 0.000 description 1
- 210000004209 hair Anatomy 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000032258 transport Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/61—Control of cameras or camera modules based on recognised objects
- H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Collating Specific Patterns (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a kind of remote multi-modal biological characteristic identifying systems, recognition unit is stored including depth camera, central processing control module, Facial Image Capturing Camera, light source module, iris video camera and preset data, the central processing control module is connected respectively with the depth camera, central processing control module, Facial Image Capturing Camera, light source module, iris video camera and preset data storage recognition unit.In addition, the invention also discloses a kind of remote multi-modal biological characteristic recognition methods.A kind of remote multi-modal biological characteristic recognition methods disclosed by the invention and its system, it uses intelligent human-machine interaction mode, for comparing traditional single living things feature recognition, it can not only realize maximizing favourable factors and minimizing unfavourable ones, having complementary advantages between each feature, it and can be while remote identification, the accuracy of identification is further improved, remote, high-resolution, high speed multi-modal biological characteristic identification is realized, is of great practical significance.
Description
Technical field
The present invention relates to technical fields such as optics, image procossing and pattern-recognitions, more particularly to a kind of remote multimode
State biological feather recognition method and its system.
Background technology
At present, with the continuous development of human sciences' technology, biometrics identification technology is widely used.Biology
Feature mainly has including several mode：Face, fingerprint, iris, palmmprint, hand, gait, sound, signature etc..
Wherein, facial area is easier to obtain corresponding image feature information as minimum position is blocked suffered by human body, because
This face and iris become currently used biological characteristic mode.Face mode compared with iris mode there is image conveniently to obtain
The advantages of taking, but it is easily influenced by factors such as expression, age, illumination, and discrimination is significantly less than iris feature identification.Iris feature
Although the best biological mode of current accuracy highest, antifalsification, since iris dimensions are smaller, it is difficult to carry out iris
Image acquisition, iris image acquisition are links more difficult during iris recognition.
At present, the more mature iris of business application or face recognition device use low pixel and short focus fixed-focus mostly
Camera lens, shooting distance is near, generally completes iris recognition or recognition of face apart from (in 50cm) by limiting to stand.It is this near
The identification method of distance limits application of the iris recognition/recognition of face under a wide range of scene, therefore, carries out at present to long distance
Research from living creature characteristic recognition system has important application value.Since iris dimensions are smaller, so distant range iris is known
The research and development of other system face more challenges, and part research institution also actively develops correlative study in recent years, based on video camera
It does a lot of work in terms of array and distant range iris recognition system research and development based on rotary head both human-computer interaction forms,
The use distance of iris recognition is expanded, still, however it remains iris image resolution ratio is low, user's location response is relatively slow or positioning
Inaccurate, system delay causes iris image to be easier to the problems such as defocus blur occur, affects the quotient of distant range iris recognition system
Industry the process of the popularization.
Therefore, multi-modal biological characteristic identification can be carried out there is an urgent need to develop a kind of technology is gone out at present, compare biography
For single living things feature recognition of system, maximizing favourable factors and minimizing unfavourable ones, having complementary advantages, but also can be in long distance between each feature can be not only realized
While from identification, the accuracy of identification is further improved, realizes that remote, high-resolution, high speed multi-modal biological characteristic is known
Not.
Invention content
In view of this, the object of the present invention is to provide a kind of remote multi-modal biological characteristic recognition methods and its system,
Its multi-modal biological characteristic identification technology being combined using iris mode and face mode, structure high-precision optical system are put down
Platform using intelligent human-machine interaction mode, for more traditional single living things feature recognition, can not only realize raising between each feature
It is long keep away it is short, have complementary advantages, and the accuracy of identification while remote identification, can be further improved, realize it is remote,
The multi-modal biological characteristic identification of high-resolution, high speed is conducive to improve the product use feeling of user, has great production reality
Trample meaning.
For this purpose, the present invention provides a kind of remote multi-modal biological characteristic recognition methods, including step：
The first step：The depth image of shooting, collecting user obtains the depth information of user；
Second step：According to the depth information of the user obtained, the depth distance of user position is obtained；
Third walks：Judge whether the depth distance of user position is located within the distance range of user preset, if
It is then to issue the user with preset facial image shooting to start prompt message, and continue to execute four step of step the, if not, working as
When the depth distance is less than the minimum threshold values of user preset distance range or during more than maximum threshold values, respectively it is corresponding send out it is pre-
If facial image shooting prepare prompt message；
4th step：The direct picture of shooting, collecting user；
5th step：Face datection is carried out to the direct picture of the user of captured acquisition, then locating segmentation obtains user
Facial image in direct picture；
6th step：Whether the image quality parameter that judging obtained facial image has is located at preset facial image matter
In the numberical range for measuring parameter, if it is, the facial image is stored in real time, step the is performed if not, returning
Four steps；
7th step：Issue the user with the near infrared light needed for iris imaging, and the face subregion of shooting, collecting user
Image and from the image of the face subregion segmentation obtain human eye area image；8th step：To the user's that is obtained
Human eye area image carries out human eye detection, and then locating segmentation obtains the human eye topography in user's human eye area image；
9th step：Whether the image quality parameter that judging obtained human eye topography has is located at preset human eye figure
In the range of image quality amount parameter values, if it is, the human eye topography is stored in real time, performed if not, returning
Seven step of step the；
Tenth step：Iris region in human eye topography is positioned, then extracts stored active user's
Facial image with face characteristic and extract iris region in human eye topography with iris feature, and by the user
The face characteristic and iris feature that the face characteristic and iris feature having are respectively provided with pre-stored multiple validated users
Information is compared matching, completes identification process.
Wherein, in the first step and second step, the depth image of shooting, collecting user is acquired by depth camera,
Obtain the depth distance of user position.
Wherein, in the 4th step, the direct picture of user is acquired by Facial Image Capturing Camera；
The Facial Image Capturing Camera is autozoom video camera or the digital lightfield camera focused again.
Wherein, it is near needed for iris imaging by being issued the user with by the light source that LED array forms in the 7th step
Infrared light and the face subregion image by iris video camera shooting, collecting user；
The iris video camera is autozoom video camera or the digital lightfield camera focused again.
In addition, the present invention also provides a kind of remote multi-modal biological characteristic identifying system, including：
Depth camera for the depth image of shooting, collecting user, obtains the depth information of user；
Central processing control module is connected with depth camera, and controlling depth video camera starts operation, is taken the photograph according to depth
The depth information for the user that camera is obtained, obtains the depth distance of user position, and judges the depth of user position
Whether degree distance is located within the distance range of user preset, is opened if it is, issuing the user with preset facial image shooting
Beginning prompt message, and operation Facial Image Capturing Camera is triggered, if not, when the depth distance is less than user preset distance range most
It is corresponding respectively to send out preset facial image shooting preparation prompt message when during small threshold values or more than maximum threshold values；
Facial Image Capturing Camera, for the direct picture of shooting, collecting user；
The central processing control module is also connected with Facial Image Capturing Camera, for being acquired captured by Facial Image Capturing Camera
The direct picture of user carries out Face datection, and then locating segmentation obtains the facial image in user's direct picture and judges
Whether the image quality parameter that the facial image obtained has is located in the numberical range of preset quality of human face image parameter,
If it is, by the facial image real-time storage to preset data store recognition unit and triggering operation light source module and
Iris video camera, if not, continuing the direct picture of control Facial Image Capturing Camera shooting, collecting user；
Light source module, for issuing the user with the near infrared light needed for iris imaging；
Iris video camera, for the face subregion image of shooting, collecting user and from the face subregion
Segmentation obtains human eye area image in image；
The central processing control module is also connected with iris video camera, for iris video camera to be controlled to start operation,
And the human eye area image that the user of acquisition is acquired to iris video camera carries out human eye detection, then locating segmentation obtains user
Human eye topography in human eye area image and the image quality parameter for judging obtained human eye topography and having are
It is no to be located in preset eye image mass parameter numberical range, if it is, human eye topography real-time storage is arrived
Preset data stores recognition unit, if not, continuing control operation light source module and iris video camera；
Preset data stores recognition unit, is connected with the central processing control module, used in described in real-time storage
The user's facial image and human eye topography that centre processing and control module is sent, and extract the face figure of stored active user
As with face characteristic and human eye topography iris region with iris feature and the face with the user it is special
The face characteristic and iris feature information that iris feature of seeking peace is respectively provided with pre-stored multiple validated users are compared
Identification process is completed in matching.
Wherein, including system shell, the positive lower end of the system shell has the central processing control module, described
Central processing control module is arranged above the light source module, and the light source module is arranged above display screen,
The both sides up and down of the display screen are respectively arranged with an iris video camera；
Described two iris video cameras, in distribution up and down, are respectively used to acquire the people of the user of different heights in vertical direction
Face part area image.
The Facial Image Capturing Camera is provided on the left of the display screen, the depth is provided on the right side of the display screen and is taken the photograph
Camera, the top of the depth camera have loud speaker.
Wherein, it is deep to include time-of-flight method TOF camera, structure light depth camera and laser scanning for the depth camera
Spend it is magazine any one；The Facial Image Capturing Camera is autozoom video camera or digital lightfield camera of focusing again；Institute
Iris video camera is stated as autozoom video camera or digital lightfield camera of focusing again.
Wherein, when the Facial Image Capturing Camera and iris video camera are autozoom video camera, the Facial Image Capturing Camera
The autozoom mode taken with iris video camera is specially：It is realized and become by the camera lens optical center of mobile autozoom video camera
Coke realizes zoom by the way that the sensor of autozoom video camera is controlled to move.
Wherein, it is cloud platform or remote server with data storage function that the preset data storage identification is single.
Wherein, the central processing control module includes autozoom control submodule and number focusing control submodule again
Block, wherein：
Autozoom control submodule is connected respectively with Facial Image Capturing Camera and iris video camera, for working as the face
When video camera and iris video camera use autozoom video camera, according to the depth for the user present position that depth camera obtains
Distance value determines the focusing position of the Facial Image Capturing Camera and iris video camera, and the Facial Image Capturing Camera and iris is controlled to image
Machine driving changes the camera lens of video camera and the relative position of sensor, realizes auto-focusing, obtains the clear of face or iris
Focus image.
Digital control submodule of focusing again, is connected respectively with Facial Image Capturing Camera and iris video camera, for working as the people
When face video camera and iris video camera use lightfield camera, control the Facial Image Capturing Camera and iris camera acquisition original
Face and eye image are transmitted to central processing control module, then, according to the user present position of depth camera acquisition
Depth distance determines the focusing position of the Facial Image Capturing Camera and iris video camera, weight Focusing parameter is then determined, to original
Face and face subregion image carry out number weight focus operation, obtain the shape library image of face or iris.
By above technical solution provided by the invention as it can be seen that compared with prior art, the present invention provides a kind of long distances
From multi-modal biological characteristic recognition methods and its system, the multi-modal biology being combined using iris mode and face mode is special
Levy identification technology, break through single mode feature the scope of application, accuracy of identification and safe-guarding and anti-counterfeiting etc. limitation, break through it is existing into
As technical bottleneck of the technology in terms of remote biometric image is obtained, high-precision optical system platform is built, using intelligence
Man-machine interaction mode for more traditional single living things feature recognition, can not only realize maximizing favourable factors and minimizing unfavourable ones between each feature, advantage
Complementation, and the accuracy of identification while remote identification, can be further improved, realize remote, high-resolution, high speed
Multi-modal biological characteristic identification, be conducive to improve user product use feeling, be of great practical significance.
Description of the drawings
Fig. 1 is a kind of flow chart of remote multi-modal biological characteristic recognition methods provided by the invention；
Fig. 2 is a kind of structure diagram of remote multi-modal biological characteristic identifying system provided by the invention；
Fig. 3 is a kind of appearance front schematic view of remote multi-modal biological characteristic identifying system provided by the invention；
Fig. 4 is face or iris camera shooting in a kind of remote multi-modal biological characteristic identifying system provided by the invention
When machine is autozoom video camera, the position relationship schematic diagram one that is imaged to remotely located subject；
Fig. 5 is face or iris camera shooting in a kind of remote multi-modal biological characteristic identifying system provided by the invention
When machine is autozoom video camera, the position relationship schematic diagram two that is imaged to remotely located subject；
Fig. 6 is face or iris camera shooting in a kind of remote multi-modal biological characteristic identifying system provided by the invention
When machine is autozoom video camera, the position relationship schematic diagram three that is imaged to remotely located subject.
Specific embodiment
In order to which those skilled in the art is made to more fully understand the present invention program, below in conjunction with the accompanying drawings with embodiment to this
Invention is described in further detail.
Fig. 1 is a kind of flow chart of remote multi-modal biological characteristic recognition methods provided by the invention；
Referring to Fig. 1, a kind of remote multi-modal biological characteristic recognition methods provided by the invention includes the following steps：
Step S101：The depth image of shooting, collecting user obtains depth information (the three-dimensional feature letter of user of user
Breath)；
Step S102：According to the depth information of the user obtained, depth distance (the i.e. user of user position is obtained
The distance between position and spot for photography)；
It,, can be by depth camera shooting, collecting user in specific implementation for step S101 and S102 for the present invention
Depth image, and the depth distance of user position is exported, particular by multiple view anaglyph, photometric stereo vision
Method, coloration forming process or defocus deduction method etc. it is existing based on the depth computing method of image come obtain user position with clap
Take the photograph the depth distance between place (such as depth camera infield).
Step S103：Judge whether the depth distance of user position is located within the distance range of user preset, such as
Fruit is then to issue the user with preset facial image shooting to start prompt message, and continue to execute step S104, if not, working as
When the depth distance is less than the minimum threshold values of user preset distance range or during more than maximum threshold values, respectively it is corresponding send out it is pre-
If facial image shooting prepare prompt message；
For the present invention, in step s 103, in specific implementation, the facial image shooting starts prompt message can root
Be configured in advance according to the needs of user, for example, can be played pre-recorded content for " please stop it is mobile, stand still simultaneously
One section of sound in head-up front ".
For the present invention, in step s 103, in specific implementation, when the depth distance is less than user preset distance range
Minimum threshold values when, it can be that the content prerecorded is that the corresponding default facial image shooting sent out, which prepares prompt message,
One section of sound of " please move backward "；When the depth distance is more than the maximum threshold values of user preset distance range, corresponding hair
It can be one section sound of the content prerecorded for " please move forward " that the preset facial image shooting gone out, which prepares prompt message,
Sound.
Step S104：The direct picture of shooting, collecting user；
It, can be by Facial Image Capturing Camera come the direct picture of shooting, collecting user, institute in step S104 for the present invention
State the video camera that COMS or ccd imaging sensor may be used in Facial Image Capturing Camera.The Facial Image Capturing Camera is preferably using automatic
Zoom camera can realize the lightfield camera that number is focused again.
Step S105：Face datection is carried out to the direct picture of the user of captured acquisition, then locating segmentation is used
Facial image in the direct picture of family；
For the present invention, it should be noted that Face datection and positioning belong to specific algorithm part, in specific implementation, this
Invention can be partitioned into facial image using the Face datection of existing maturation and the result of positioning scheduling algorithm.
In specific implementation, such as it may be used and Face datection is carried out based on haar (Ha Er) classifier algorithm, utilize SDM
(Supervised Descent Method (gradient descent method for having supervision) algorithm carries out face key point location.
Step S106：Whether the image quality parameter that judging obtained facial image has is located at preset facial image
(quality of human face image evaluation is carried out in the numberical range of mass parameter), if it is, the facial image is carried out in real time
Storage performs step S104 if not, returning；
For the present invention, in step s 106, described image mass parameter can include in resolution ratio, contrast and colour temperature
One or more.The numberical range of the preset quality of human face image parameter, can be pre- advanced according to the needs of user
Row setting.
For the present invention, in step s 106, the facial image is possibly stored to have the cloud of data storage function to put down
Platform, remote server or other devices.
Step S107：Issue the user with the near infrared light needed for iris imaging, and the face subregion of shooting, collecting user
Area image is (compared with facial image, around the figure of two acquisitions of user when the people face part area image is iris imaging
Picture only accounts for a part for facial image, and the ratio specifically accounted for and iris video camera etc. are between iris imagings equipment and user
Distance is related, and distance is nearer, then the ratio accounted in entire facial image is smaller, otherwise bigger) and from the face subregion
Image segmentation obtains human eye area image (one section of image including two and eyebrow, the bridge of the nose is laterally covered in face) in domain；
It should be noted that for the present invention, in step s 107, according to the facial image positioning result of step S105 with
And the nominal data between Facial Image Capturing Camera, iris video camera, digging window shape formula can be taken to divide from the image of face subregion
It cuts and obtains human eye area image, it is exactly that only region interested in the area image of protoplast face part (is referred in this step to dig window
It is human eye area) it splits.
The nominal data refers to the pixel correspondence that overlapped fov is interregional in different cameras image, step S105
The human eye key point position in facial image can be obtained, according to Facial Image Capturing Camera and the calibration relationship of iris video camera, and then
The corresponding position that face subregion image corresponds to human eye key point can be obtained, it can be by human eye area image point according to the position
It cuts out.
It, in step s 107, can be by issuing the user with iris imaging by the light source that LED array forms for the present invention
Required near infrared light.
For the present invention, in step s 107, the face of existing iris video camera shooting, collecting user can be passed through
Subregion area image.The iris video camera is preferably using autozoom video camera or can realize the digital light field focused again
Video camera.
Step S108：Human eye detection is carried out to the human eye area image of user obtained, then locating segmentation is used
(compared with human eye area image, which only has right and left eyes for human eye topography in the human eye area image of family
Eye circumference, without eyebrow, the bridge of the nose)；
For the present invention, it should be noted that human eye detection and positioning belong to specific algorithm part, in specific implementation, this
Invention can be partitioned into human eye topography using the result of this kind of algorithm such as existing human eye detection and positioning.
In specific implementation, such as the Ada-Boosting based on haar-like (class Ha Er) feature may be used (adaptively
Enhancing study) human eye detection localization method obtains position of human eye, and then is partitioned into human eye topography.It should be noted that
The Haar features that Haar-like features, i.e. existing technical staff are often said are a kind of common feature descriptions of computer vision field
Operator.Currently used Haar-like features can be divided into three classes：Linear character, edge feature, point feature (central feature),
Diagonal feature.
Step S109：Whether the image quality parameter that judging obtained human eye topography has is located at preset human eye
(eye image quality evaluation is carried out in image quality parameter numberical range), if it is, by human eye topography reality
Shi Jinhang is stored, and step S107 is performed if not, returning；
For the present invention, in step S109, the human eye topography is possibly stored to have data storage function
Cloud platform, remote server or other devices.
Step S110：Iris region in human eye topography is positioned, then extracts stored active user
Facial image with face characteristic and extract iris region in human eye topography with iris feature, and this is used
The people that the face characteristic and iris feature that family has are respectively provided with pre-stored multiple validated users (such as registered users)
Face feature and iris feature information are compared matching, complete identification process.
In the present invention, it should be noted that in specific implementation, in step s 110, Iris Location side specifically may be used
Method, such as rubber sheet model (rubber Slab) algorithm of Daugman (name), to the rainbow in human eye topography
Diaphragm area is positioned.
In the present invention, it should be noted that existing Feature Extraction Technology can be utilized to extract the face figure of active user
As with face characteristic and extract iris region in human eye topography with iris feature.Feature Extraction Technology is figure
As processing and the basic conception of area of pattern recognition, the present invention does not illustrate technical principle at this.Feature Extraction Technology
Suitable feature can be selected according to image property, in favor of carrying out match cognization.
For the present invention, in step s 110, the comparison match step is specially：If the face that the user has is special
The face characteristic and iris feature information match that iris feature of seeking peace has with one of validated user, then judge current use
Family is validated user, if the face characteristic and iris feature information match that do not have with any one validated user, sentence
Disconnected active user is disabled user, completes identification process.
For the present invention, in step s 110, it should be noted that pre-stored multiple validated users are (as
Registered user) face characteristic that is respectively provided with and iris feature information, can multiple validated users be separately operable with the present invention's
Step 101 is obtained to step S109, by registered in advance to multiple validated users, and stores face characteristic and rainbow that they have
Film characteristic information.
Therefore, based on above technical solution it is found that a kind of remote multi-modal biological characteristic identification provided by the invention
Method, using the advantage of face mode and iris mode in living things feature recognition, by building active light source and polynary camera shooting
Machine imaging system merges intelligent human-machine interaction mode and biological characteristic detection method, breaches existing living creature characteristic recognition system
Technical bottleneck in terms of remote living things feature recognition is carried out, to pushing popularization of the living things feature recognition in a wide range of scene
Using with important practical significance.
Referring to Fig. 2, in specific implementation, in order to which a kind of remote multi-modal biological characteristic for running the invention described above offer is known
Other method, the present invention also provides a kind of remote multi-modal biological characteristic identifying system, which includes：
Depth camera 101 for the depth image of shooting, collecting user, obtains depth information (the three of user of user
Dimensional feature information)；
, can be by the depth image of depth camera shooting, collecting user in specific implementation for the present invention, and export use
The depth distance of family position particular by multiple view anaglyph, photometric stereo, coloration forming process or defocuses
Deduction method etc. is existing, and based on the depth computing method of image, to obtain user position, (such as depth camera is pacified with spot for photography
Fill place) between depth distance.
For the present invention, in specific implementation, the depth camera 101 can select TOF (time-of-flight method) video camera,
Any one in structure light depth camera and laser scanning depth camera.
Central processing control module 102 is connected with depth camera 101, starts for controlling depth video camera 101 and transports
Row according to the depth information for the user that depth camera is obtained, obtains the depth distance of user position (i.e. where user
The distance between position and spot for photography), and judge whether the depth distance of user position is located at the distance of user preset
Within the scope of, if it is, issuing the user with preset facial image shooting starts prompt message, and trigger operation face camera shooting
Machine 103, if not, when minimum threshold values of the depth distance less than user preset distance range or more than maximum threshold values
When, it is corresponding respectively to send out preset facial image shooting preparation prompt message；
For the present invention, in specific implementation, the central processing control module 102 can pass through loud speaker and/or display
Device issues the user with preset facial image shooting and starts prompt message.
For the present invention, in specific implementation, the central processing control module 102 can with keyboard, mouse, touch screen,
The user instructions such as tablet input equipment (human-computer interaction module) is connected, and user can not only be facilitated to input identification and start to refer to
It enables, so as to control central processing control module 102, user can also be facilitated to pre-set present system, such as in advance
Distance range, default numberical range for setting quality of human face image parameter etc. are first set.
In the present invention, in specific implementation, the central processing control module can be by defeated with loud speaker, display screen etc.
Go out equipment to be connected (human-computer interaction module), issue the user with preset facial image shooting and start prompt message.
For the present invention, for the central processing control module 102, in specific implementation, the facial image shooting is opened
Beginning prompt message can be in advance configured according to the needs of user, such as can be the content of played pre-recorded " please to stop
Only move, stand still and look squarely front " one section of sound.
For the present invention, for the central processing control module 102, in specific implementation, when the depth distance is less than
During the minimum threshold values of user preset distance range, the corresponding default facial image shooting sent out, which prepares prompt message, to be
The content prerecorded is one section of sound of " please move backward "；When the depth distance is more than user preset distance range most
During big threshold values, the corresponding preset facial image shooting sent out prepare prompt message can be the content prerecorded for " please to
One section of sound of preceding movement ".
Facial Image Capturing Camera 103, for the direct picture of shooting, collecting user；
It, can be by Facial Image Capturing Camera come the direct picture of shooting, collecting user, the Facial Image Capturing Camera for the present invention
The video camera of COMS or ccd imaging sensor may be used.
In the present invention, in specific implementation, the Facial Image Capturing Camera 103 is preferably using autozoom video camera or energy
Enough lightfield cameras realized number and focused again.
Central processing control module 102 is also connected with Facial Image Capturing Camera 103, for captured by Facial Image Capturing Camera 103
The direct picture of the user of acquisition carries out Face datection, and then locating segmentation obtains the facial image in user's direct picture, with
And whether the image quality parameter for judging obtained facial image and having is located at the numerical value of preset quality of human face image parameter
In the range of (carry out quality of human face image evaluation), if it is, by the facial image real-time storage to preset data storage
Recognition unit 106 and triggering operation light source module 104 and iris video camera 105, if not, continuing to control Facial Image Capturing Camera
The direct picture of shooting, collecting user；
For the present invention, it should be noted that Face datection and positioning belong to specific algorithm part, can in specific implementation
To be partitioned into facial image using the result of the Face datection of existing maturation and positioning scheduling algorithm.
In specific implementation, such as it may be used and Face datection is carried out based on haar (Ha Er) classifier algorithm, utilize SDM
(Supervised Descent Method) (gradient descent method for having supervision) algorithm carries out face key point location.
For the present invention, described image mass parameter can include a kind of or more in resolution ratio, contrast and colour temperature
Kind.The numberical range of the preset quality of human face image parameter can be in advance configured according to the needs of user.
For the present invention, preset data storage recognition unit can be the cloud platform with data storage function, remote
Journey server or other devices.
Light source module 104, for issuing the user with the near infrared light needed for iris imaging；
Iris video camera 105, for the face subregion image of shooting, collecting user and from the face subregion
Area image segmentation obtains human eye area image (one section of image including two and eyebrow, the bridge of the nose is laterally covered in face)；
It should be noted that for the present invention, iris video camera 105 can be obtained according to central processing control module 102
Facial image testing result and Facial Image Capturing Camera, iris video camera between nominal data, can take dig window shape formula from
Segmentation obtains human eye area image in the image of face subregion, and it is exactly only interested in the area image of protoplast face part to dig window
Region (referring to human eye area) split.
The nominal data refers to the pixel correspondence that overlapped fov is interregional in different cameras image, passes through center
Processing and control module 102 can obtain the human eye key point position in facial image, according to Facial Image Capturing Camera and iris video camera
Calibration relationship, and then the corresponding position that face subregion image corresponds to human eye key point can be obtained, can according to the position
Human eye area image is split.
It, can be by issuing the user with the near-infrared needed for iris imaging by the light source that LED array forms for the present invention
Light.
For the present invention, the face subregion image of existing iris video camera shooting, collecting user can be passed through.
In the present invention, in specific implementation, the iris video camera preferably uses autozoom video camera or can
Realize the lightfield camera that number is focused again.
Central processing control module 102 is also connected with iris video camera 105, for iris video camera 105 to be controlled to start
It runs, and the human eye area image that the user obtained is acquired to iris video camera 105 carries out human eye detection, then locating segmentation
It obtains the human eye topography in user's human eye area image and judges the image matter that obtained human eye topography has
Parameter is measured whether to be located in preset eye image mass parameter numberical range and (carry out eye image quality evaluation), if
It is that human eye topography real-time storage to preset data is then stored into recognition unit 106, if not, continuing control operation
Light source module 104 and iris video camera 105；
For the present invention, it should be noted that human eye detection and positioning belong to specific algorithm part, in specific implementation, this
Invention can be partitioned into human eye topography using the result of this kind of algorithm such as existing human eye detection and positioning.
In specific implementation, such as the Ada-Boosting based on haar-like (class Ha Er) feature may be used (adaptively
Enhancing study) human eye detection localization method obtains position of human eye, and then is partitioned into human eye topography.It should be noted that
The Haar features that Haar-like features, i.e. existing technical staff are often said are a kind of common feature descriptions of computer vision field
Operator.Currently used Haar-like features can be divided into three classes：Linear character, edge feature, point feature (central feature),
Diagonal feature.Preset data stores recognition unit 106, is connected with the central processing control module 102, for depositing in real time
User's facial image and the human eye topography that the central processing control module 102 is sent are stored up, and in human eye topography
Iris region positioned, extract face characteristic and extract human eye office that the facial image of stored active user has
Iris region has in portion's image iris feature and the face characteristic with the user and iris feature are with prestoring
The face characteristic that is respectively provided with of multiple validated users (such as registered users) and iris feature information be compared matching, complete
Identification process.
In the present invention, it should be noted that in specific implementation, the preset data storage recognition unit can specifically be run
Iris locating method, such as rubber sheet model (rubber Slab) algorithm of Daugman (name), to human eye part
Iris region in image is positioned.
The present invention, the preset data storage recognition unit can be the cloud platform with data storage function, long-range clothes
Business device or other devices.
In the present invention, it should be noted that existing Feature Extraction Technology can be utilized to extract the face figure of active user
As with face characteristic and human eye topography in iris region with iris feature.Feature Extraction Technology is image procossing
With the basic conception of area of pattern recognition, the present invention does not illustrate technical principle at this.Feature Extraction Technology can root
Suitable feature is selected according to image property, in favor of carrying out match cognization.
For the present invention, for face characteristic and iris feature and pre-stored multiple legal use with the user
The face characteristic and iris feature information that family (such as registered users) is respectively provided with are compared matching, the preset data storage
The concrete processing procedure of recognition unit 106 is：If the face characteristic and iris feature that have for the user and one of them
The face characteristic and iris feature information match that validated user has, then judge active user for validated user, if not with
The face characteristic and iris feature information match that any one validated user has, then judge active user for disabled user,
Complete identification process.
For the present invention, it should be noted that pre-stored multiple validated users (such as registered users) are respectively
The face characteristic and iris feature information having, can according to the technique and scheme of the present invention distinguish multiple validated users in advance
Run depth camera 101 of the invention, central processing control module 102, Facial Image Capturing Camera 103, light source module 104, iris
105 grade of video camera obtains, can be by registered in advance to multiple validated users, and stores face characteristic and iris that they have
Characteristic information.
For the present invention, in specific implementation, the central processing control module 102 can include multiple central processing units
CPU or digital signal processor DSP.
For a kind of remote multi-modal biological characteristic identifying system provided by the invention, the distance of user can be identified
Range can be 1 meter to 3 meters under normal circumstances.
Fig. 3 is a kind of appearance diagram of remote multi-modal biological characteristic identifying system provided by the invention.It is specific real
On now, referring to Fig. 3, the remote multi-modal biological characteristic identifying system includes system shell 100, the system shell 110
Positive lower end there is central processing control module 102, the central processing control module 102 is arranged above light source die
Block 104, the light source module 104 are arranged above display screen 200, and the both sides up and down of the display screen 200 are set respectively
There are one iris video camera 105, described two iris video cameras 105 are distributed in vertical direction in upper and lower, to meet different heights
User face subregion image acquisition.
It should be noted that for remote multi-modal biological characteristic identifying system provided by the invention, if including hanging down
Nogata is in two iris video cameras 105 being distributed up and down, then the central processing control module 102 is additionally operable to by people
The direct picture of the captured user acquired of face video camera 103 carries out Face datection, judges the height of user, and according to height
Numerical values recited, the corresponding iris video camera 105 opened positioned at display screen either above or below.
It, can be in the original front that Facial Image Capturing Camera is shot according to Face datection result in specific implementation for the present invention
Locating human face's image-region on image, according to present position of the facial image region on original direct picture, by setting in advance
Correspondence of the user's height and facial image region put on original direct picture between present position, it can be determined that obtain
The height of user.
The left side of the display screen 200 is provided with Facial Image Capturing Camera 103, and the right side of the display screen 200 is provided with depth
Video camera 101, the top of the depth camera 101 have loud speaker 300.
It should be noted that in the present invention, the field range of Facial Image Capturing Camera 103 and depth camera 101 compares iris
Video camera 105 is big, and position is not limited to shown in figure, need to only ensure regardless of user's height and present position, Facial Image Capturing Camera
103 and depth camera 101 can take user position interested.
In the present invention, referring to Fig. 3, the display screen 200 is used for the position to user and the last identification knot of the present invention
Fruit carries out image instruction, and one kind that the mode of touch display screen is inputted as system can also be used；
In the present invention, referring to Fig. 3, the loud speaker 300 refers to for making voice to the position of user and recognition result
Show.
In the present invention, in specific implementation, the Facial Image Capturing Camera 103, iris video camera 105, depth camera 101 are divided
It can not be connected by any one connection mode such as USB 3.0 or CameraLink with central processing control module 102
It connects.
Referring to fig. 4 to fig. 6, when the Facial Image Capturing Camera 103 and iris video camera 105 are using autozoom video camera,
There are two types of autozoom modes, and a kind of is to realize zoom (as shown in Figure 5) by the camera lens optical center of mobile autozoom video camera,
Another is to realize zoom (as shown in Figure 6) by the way that the sensor of autozoom video camera is controlled to move.
It should be noted that in fig. 4 to fig. 6,501 be subject, and 502 be the light of the camera lens of autozoom video camera
The heart, 503 be camera sensor, and 504 be sensor imaging.Autozoom video camera when Fig. 4 is non-zoom is to being located at
The subject 501 of distant place is imaged；When 502 present position of camera lens optical center for changing autozoom video camera, such as Fig. 5 institutes
Show, the camera lens optical center 502 of autozoom video camera moves forward, the situation that subject 501 and camera sensor 503 do not move
Under, the focal length f of camera lens becomes larger, and view angle theta becomes smaller, then the picture for being on camera sensor 503 is as shown in figure 5, realize change
Burnt function.When changing the location of camera sensor 503, as shown in fig. 6, being moved after camera sensor 503, subject
In the case that the camera lens optical center 502 of body 501 and autozoom video camera does not move, lens focus f becomes larger, and view angle theta becomes smaller, camera shooting
The picture that is on machine sensor 503 equally realizes zoom function as shown in fig. 6, consistent with Fig. 5 imagings.
For the present invention, as described above, in specific implementation, the Facial Image Capturing Camera and iris video camera are preferably using certainly
Dynamic Zoom camera can realize the lightfield camera that number is focused again.
For the central processing control module 102, in order to which Facial Image Capturing Camera 103 and iris video camera 105 is controlled to start
Operation, respectively acquisition obtain the face of user or the shape library image of iris.The central processing control module 102 includes
Autozoom control submodule and digital control submodule of focusing again, wherein：
Autozoom control submodule is connected respectively with Facial Image Capturing Camera and iris video camera, for working as the face
When video camera and iris video camera use autozoom video camera, according to the depth for the user present position that depth camera obtains
Distance value determines the focusing position of the Facial Image Capturing Camera and iris video camera, and the Facial Image Capturing Camera and iris is controlled to image
Machine driving changes the camera lens of video camera and the relative position of sensor, realizes auto-focusing, obtains the clear of face or iris
Focus image.
For the present invention, it should be noted that in specific implementation, according to the image that depth camera is shot, can obtain
Residing for user apart from depth value, which is face and the position focused of iris video camera needs.
For the present invention, it is also necessary to which explanation in specific implementation, can pass through Facial Image Capturing Camera and iris video camera etc.
Video camera internal mechanical structure changes the distance between camera lens optical center and sensor, this relative distance is exactly camera lens
Focal length if the object distance of shooting is farther out, increases focal length, both increases relative distance, if the object distance of shooting compared with
Closely, then reduce focal length, reduce the two relative distance.
Digital control submodule of focusing again, is connected respectively with Facial Image Capturing Camera and iris video camera, for working as the people
When face video camera and iris video camera use lightfield camera, control the Facial Image Capturing Camera and iris camera acquisition original
Face and eye image are transmitted to central processing control module, then, according to the user present position of depth camera acquisition
Depth distance determines the focusing position of the Facial Image Capturing Camera and iris video camera, weight Focusing parameter is then determined, to original
Face and face subregion image carry out number weight focus operation, obtain the shape library image of face or iris.
For the present invention, it should be noted that in specific implementation, according to the image that depth camera is shot, can obtain
Residing for user apart from depth value, which is face and the position focused of iris video camera needs.
It should be noted that weight Focusing parameter, this is the parameter that optical field imaging number is focused again, if it is determined that mesh
Distance between mark and camera, then the distance just corresponds to a weight Focusing parameter, using the parameter, passes through number weight focus algorithm
It can be obtained by the shape library image of target location.A kind of number weight focus algorithm also known technology at last at present, this
In do not introduce specifically.
Therefore, based on above technical solution it is found that a kind of remote multi-modal biological characteristic identification provided by the invention
System, using the advantage of face mode and iris mode in living things feature recognition, by building active light source and polynary camera shooting
Machine imaging system merges intelligent human-machine interaction mode and biological characteristic detection method, breaches existing living creature characteristic recognition system
Technical bottleneck in terms of remote living things feature recognition is carried out, to pushing popularization of the living things feature recognition in a wide range of scene
Using with important practical significance.
In conclusion compared with prior art, the present invention provides a kind of remote multi-modal biological characteristic identification sides
Method and its system, the multi-modal biological characteristic identification technology being combined using iris mode and face mode, structure high-precision
Optical system platform using intelligent human-machine interaction mode, for more traditional single living things feature recognition, can not only be realized each
Maximizing favourable factors and minimizing unfavourable ones, having complementary advantages between feature, and the accuracy of identification while remote identification, can be further improved,
It realizes remote, high-resolution, high speed multi-modal biological characteristic identification, is conducive to improve the product use feeling of user, has
Great production practices meaning.
The above is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications also should
It is considered as protection scope of the present invention.
Claims (10)
1. a kind of remote multi-modal biological characteristic recognition methods, which is characterized in that including step：
The first step：The depth image of shooting, collecting user obtains the depth information of user；
Second step：According to the depth information of the user obtained, the depth distance of user position is obtained；
Third walks：Judge whether the depth distance of user position is located within the distance range of user preset, if it is,
It issues the user with preset facial image shooting and starts prompt message, and continue to execute four step of step the, if not, when the depth
When degree is apart from the minimum threshold values for being less than user preset distance range or more than maximum threshold values, correspondence sends out preset people respectively
Face image shooting prepares prompt message；
4th step：The direct picture of shooting, collecting user；
5th step：Face datection is carried out to the direct picture of the user of captured acquisition, then locating segmentation obtains user front
Facial image in image；
6th step：Whether the image quality parameter that judging obtained facial image has, which is located at preset quality of human face image, is joined
In several numberical ranges, if it is, the facial image is stored in real time, four step of step the is performed if not, returning；
7th step：The near infrared light needed for iris imaging, and the face subregion image of shooting, collecting user are issued the user with,
And segmentation obtains human eye area image from the image of the face subregion；
8th step：Human eye detection is carried out to the human eye area image of user obtained, then locating segmentation obtains user's human eye
Human eye topography in area image；
9th step：Whether the image quality parameter that judging obtained human eye topography has is located at preset eye image matter
It measures in the range of parameter values, if it is, the human eye topography is stored in real time, step is performed if not, returning
7th step；
Tenth step：Iris region in human eye topography is positioned, then extracts the face of stored active user
Image with face characteristic and extract iris region in human eye topography with iris feature, and the user is had
Face characteristic and the face characteristic that is respectively provided with of human eye feature and pre-stored multiple validated users and iris feature information
Matching is compared, completes identification process.
2. the method as described in claim 1, which is characterized in that in the first step and second step, pass through depth camera
The depth image of shooting, collecting user is acquired, obtains the depth distance of user position.
3. the method as described in claim 1, which is characterized in that in the 4th step, use is acquired by Facial Image Capturing Camera
The direct picture at family；
The Facial Image Capturing Camera is autozoom video camera or the digital lightfield camera focused again.
4. the method as described in claim 1, which is characterized in that in the 7th step, pass through the light source being made of LED array
Issue the user with the near infrared light needed for iris imaging and the face subregion by iris video camera shooting, collecting user
Image；
The iris video camera is autozoom video camera or the digital lightfield camera focused again.
5. a kind of remote multi-modal biological characteristic identifying system, which is characterized in that including：
Depth camera for the depth image of shooting, collecting user, obtains the depth information of user；
Central processing control module is connected with depth camera, starts for controlling depth video camera and runs, is taken the photograph according to depth
The depth information for the user that camera is obtained, obtains the depth distance of user position, and judges the depth of user position
Whether degree distance is located within the distance range of user preset, is opened if it is, issuing the user with preset facial image shooting
Beginning prompt message, and operation Facial Image Capturing Camera is triggered, if not, when the depth distance is less than user preset distance range most
It is corresponding respectively to send out preset facial image shooting preparation prompt message when during small threshold values or more than maximum threshold values；
Facial Image Capturing Camera, for the direct picture of shooting, collecting user；
The central processing control module is also connected with Facial Image Capturing Camera, for the user acquired captured by Facial Image Capturing Camera
Direct picture carry out Face datection, then locating segmentation obtain user's direct picture in facial image and judge obtained
Whether the image quality parameter that the facial image obtained has is located in the numberical range of preset quality of human face image parameter, if
It is that the facial image real-time storage to preset data is then stored into recognition unit and triggering operation light source module and iris
Video camera, if not, continuing the direct picture of control Facial Image Capturing Camera shooting, collecting user；
Light source module, for issuing the user with the near infrared light needed for iris imaging；
Iris video camera, for the face subregion image of shooting, collecting user and from face subregion image
Middle segmentation obtains human eye area image；
The central processing control module is also connected with iris video camera, for iris video camera to be controlled to start operation, and it is right
The human eye area image that iris video camera acquires the user of acquisition carries out human eye detection, and then locating segmentation obtains user's human eye
Human eye topography in area image and judge image quality parameter that obtained human eye topography has whether position
In in preset eye image mass parameter numberical range, if it is, by human eye topography real-time storage to default
Data store recognition unit, if not, continuing control operation light source module and iris video camera；
Preset data stores recognition unit, is connected with the central processing control module, for centre described in real-time storage
The user's facial image and human eye topography that reason control module is sent, and the iris region in human eye topography is determined
Position, the face characteristic and extract iris in human eye topography that then the facial image of the stored active user of extraction has
Iris feature that region has and the face characteristic with the user and iris feature and pre-stored multiple legal use
The face characteristic and iris feature information that family is respectively provided with are compared matching, complete identification process.
6. system as claimed in claim 5, which is characterized in that including system shell, the positive lower end tool of the system shell
There is the central processing control module, the central processing control module is arranged above the light source module, the light
Source module is arranged above display screen, and the both sides up and down of the display screen are respectively arranged with an iris video camera；
Two iris video cameras, in distribution up and down, are respectively used to acquire the face subregion of the user of different heights in vertical direction
Area image；
The Facial Image Capturing Camera is provided on the left of the display screen, the depth camera is provided on the right side of the display screen
Machine, the top of the depth camera have loud speaker.
7. such as system described in claim 5 or 6, which is characterized in that the depth camera is imaged including time-of-flight method TOF
Any one in machine, structure light depth camera and laser scanning depth camera；
The Facial Image Capturing Camera is autozoom video camera or digital lightfield camera of focusing again；The iris video camera is certainly
Dynamic Zoom camera or digital lightfield camera of focusing again.
8. system as claimed in claim 5, which is characterized in that when the Facial Image Capturing Camera and iris video camera are automatic change
During focus video camera, the autozoom mode that the Facial Image Capturing Camera and iris video camera are taken is specially：Pass through mobile automatic change
The camera lens optical center of focus video camera realizes zoom or realizes zoom by the way that the sensor of autozoom video camera is controlled to move.
9. such as system described in claim 5 or 6, which is characterized in that the preset data storage recognition unit is with data
The cloud platform or remote server of store function.
10. system as claimed in claim 5, which is characterized in that the central processing control module is controlled including autozoom
Submodule and digital control submodule of focusing again, wherein：
Autozoom control submodule is connected respectively with Facial Image Capturing Camera and iris video camera, for working as the face camera shooting
When machine and iris video camera use autozoom video camera, according to the depth distance for the user present position that depth camera obtains
Value determines the focusing position of the Facial Image Capturing Camera and iris video camera, and the Facial Image Capturing Camera and iris video camera is controlled to drive
The relative position of the dynamic camera lens and sensor for changing video camera, realizes auto-focusing, obtains the shape library of face or iris
Image；
Digital control submodule of focusing again, is connected with Facial Image Capturing Camera and iris video camera, is taken the photograph for working as the face respectively
When camera and iris video camera use lightfield camera, the Facial Image Capturing Camera and the original face of iris camera acquisition are controlled
Central processing control module is transmitted to eye image, then, according to the depth for the user present position that depth camera obtains
Distance determines the focusing position of the Facial Image Capturing Camera and iris video camera, weight Focusing parameter is then determined, to original face
Number weight focus operation is carried out with face subregion image, obtains the shape library image of face or iris.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510957176.0A CN105554385B (en) | 2015-12-18 | 2015-12-18 | A kind of remote multi-modal biological characteristic recognition methods and its system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510957176.0A CN105554385B (en) | 2015-12-18 | 2015-12-18 | A kind of remote multi-modal biological characteristic recognition methods and its system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105554385A CN105554385A (en) | 2016-05-04 |
| CN105554385B true CN105554385B (en) | 2018-07-10 |
Family
ID=55833303
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510957176.0A Active CN105554385B (en) | 2015-12-18 | 2015-12-18 | A kind of remote multi-modal biological characteristic recognition methods and its system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105554385B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255282A (en) * | 2017-07-14 | 2019-01-22 | 上海荆虹电子科技有限公司 | A kind of biometric discrimination method, device and system |
Families Citing this family (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106054278B (en) * | 2016-07-07 | 2018-06-12 | 王飞 | A kind of head three dimensional data collection and the detector gate and method of identification |
| CN106250851B (en) * | 2016-08-01 | 2020-03-17 | 徐鹤菲 | Identity authentication method, identity authentication equipment and mobile terminal |
| CN106524909B (en) * | 2016-10-20 | 2020-10-16 | 北京旷视科技有限公司 | Three-dimensional image acquisition method and device |
| CN106569330B (en) * | 2016-10-28 | 2019-07-12 | 深圳奥比中光科技有限公司 | A kind of design method of optical design, area array projection device and a kind of depth camera |
| CN106599779A (en) * | 2016-10-28 | 2017-04-26 | 黑龙江省科学院自动化研究所 | Human ear recognition method |
| CN108206929A (en) * | 2016-12-16 | 2018-06-26 | 北京华泰科捷信息技术股份有限公司 | A kind of contactless personnel information acquisition device and its acquisition method |
| US10867161B2 (en) * | 2017-09-06 | 2020-12-15 | Pixart Imaging Inc. | Auxiliary filtering device for face recognition and starting method for electronic device |
| CN107766834B (en) * | 2017-11-01 | 2023-09-26 | 北京蓝海华业工程技术有限公司 | Face recognition method and system |
| CN110008786A (en) * | 2018-01-04 | 2019-07-12 | 浙江湖州先牛信息科技有限公司 | A kind of more camera lens iris authentication systems |
| CN108229399A (en) * | 2018-01-05 | 2018-06-29 | 北京红马传媒文化发展有限公司 | Image-recognizing method, pattern recognition device and verification equipment |
| CN109145856A (en) * | 2018-09-03 | 2019-01-04 | 武汉虹识技术有限公司 | Iris image acquiring method, iris image acquiring device and computing device |
| CN109360310A (en) * | 2018-10-11 | 2019-02-19 | 中控智慧科技股份有限公司 | Biometric discrimination method, systems-on-a-chip and channel unit |
| CN113452926B (en) * | 2018-10-26 | 2023-01-13 | 创新先进技术有限公司 | Image acquisition device, system and method |
| CN109753926A (en) * | 2018-12-29 | 2019-05-14 | 深圳三人行在线科技有限公司 | A kind of method and apparatus of iris recognition |
| CN109726694B (en) * | 2019-01-02 | 2023-08-25 | 上海百豪新材料有限公司 | Iris image acquisition method and device |
| CN110225249B (en) * | 2019-05-30 | 2021-04-06 | 深圳市道通智能航空技术有限公司 | Focusing method and device, aerial camera and unmanned aerial vehicle |
| WO2021098132A1 (en) * | 2019-11-21 | 2021-05-27 | 苏州思源科安信息技术有限公司 | Far-distance large-field-of-viewiris optical imaging device and method |
| CN111207690B (en) * | 2020-02-17 | 2021-03-12 | 天目爱视（北京）科技有限公司 | Adjustable iris 3D information acquisition measuring equipment |
| CN111563245A (en) * | 2020-05-15 | 2020-08-21 | 支付宝(杭州)信息技术有限公司 | User identification method, device, equipment and medium |
| CN111743524A (en) * | 2020-06-19 | 2020-10-09 | 联想(北京)有限公司 | Information processing method, terminal and computer readable storage medium |
| CN112507781B (en) * | 2020-10-21 | 2023-11-21 | 天津中科智能识别产业技术研究院有限公司 | Multi-dimensional multi-mode group biological feature recognition system and method |
| CN113645403B (en) * | 2021-07-29 | 2022-08-19 | 深圳市芯成像科技有限公司 | Self-photographing method and system based on holder, computer readable storage medium and intelligent holder |
| CN117880630B (en) * | 2024-03-13 | 2024-06-07 | 杭州星犀科技有限公司 | Focusing depth acquisition method, focusing depth acquisition system and terminal |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101027678A (en) * | 2004-06-21 | 2007-08-29 | 谷歌公司 | Single image based multi-biometric system and method |
| CN104618643A (en) * | 2015-01-20 | 2015-05-13 | 广东欧珀移动通信有限公司 | Shooting method and device |
| CN105138950A (en) * | 2015-07-03 | 2015-12-09 | 广东欧珀移动通信有限公司 | Photographing method and user terminal |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007504562A (en) * | 2003-09-04 | 2007-03-01 | サーノフ コーポレーション | Method and apparatus for performing iris authentication from a single image |
| US8254768B2 (en) * | 2010-12-22 | 2012-08-28 | Michael Braithwaite | System and method for illuminating and imaging the iris of a person |
-
2015
- 2015-12-18 CN CN201510957176.0A patent/CN105554385B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101027678A (en) * | 2004-06-21 | 2007-08-29 | 谷歌公司 | Single image based multi-biometric system and method |
| CN104618643A (en) * | 2015-01-20 | 2015-05-13 | 广东欧珀移动通信有限公司 | Shooting method and device |
| CN105138950A (en) * | 2015-07-03 | 2015-12-09 | 广东欧珀移动通信有限公司 | Photographing method and user terminal |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255282A (en) * | 2017-07-14 | 2019-01-22 | 上海荆虹电子科技有限公司 | A kind of biometric discrimination method, device and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105554385A (en) | 2016-05-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105554385B (en) | A kind of remote multi-modal biological characteristic recognition methods and its system | |
| CN105809144B (en) | A gesture recognition system and method using motion segmentation | |
| CN103106401B (en) | Mobile terminal iris recognition device with human-computer interaction mechanism | |
| CN105335722B (en) | Detection system and method based on depth image information | |
| CN105659200B (en) | For showing the method, apparatus and system of graphic user interface | |
| US10007336B2 (en) | Apparatus, system, and method for mobile, low-cost headset for 3D point of gaze estimation | |
| WO2019179441A1 (en) | Focus tracking method and device of smart apparatus, smart apparatus, and storage medium | |
| US9432593B2 (en) | Target object information acquisition method and electronic device | |
| EP3156754A1 (en) | Dart game device having multiple cameras and computer program stored in computer-readable medium | |
| WO2020078440A1 (en) | Apparatus for collecting high-definition facial images and method for automatic pitch adjustment of camera gimbal | |
| CN102855471B (en) | Remote iris intelligent imaging device and method | |
| US20140037135A1 (en) | Context-driven adjustment of camera parameters | |
| CN103353935A (en) | 3D dynamic gesture identification method for intelligent home system | |
| CN105654048A (en) | Multi-visual-angle face comparison method | |
| CN104364733A (en) | Position-of-interest detection device, position-of-interest detection method, and position-of-interest detection program | |
| JP7192872B2 (en) | Iris authentication device, iris authentication method, iris authentication program and recording medium | |
| CN106464793B (en) | Photographic device and camera shooting householder method | |
| JP5438601B2 (en) | Human motion determination device and program thereof | |
| KR101640014B1 (en) | Iris recognition apparatus for detecting false face image | |
| CN109753925A (en) | A kind of method and apparatus that iris feature extracts | |
| US11882354B2 (en) | System for acquisiting iris image for enlarging iris acquisition range | |
| CN109634407A (en) | It is a kind of based on control method multimode man-machine heat transfer agent synchronous acquisition and merged | |
| CN106599779A (en) | Human ear recognition method | |
| KR101961266B1 (en) | Gaze Tracking Apparatus and Method | |
| KR101480816B1 (en) | Visual speech recognition system using multiple lip movement features extracted from lip image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20190110 Address after: Unit 1005, Block MSD-G1, Teda, 57 Second Avenue, Tianjin Economic and Technological Development Zone, 300457 Patentee after: TIANJIN ZHONGKE HONGXING TECHNOLOGY CO.,LTD. Address before: 300457 No. 57, Second Avenue, Economic and Technological Development Zone, Binhai New Area, Tianjin Patentee before: TIANJIN ZHONGKE INTELLIGENT IDENTIFICATION INDUSTRY TECHNOLOGY RESEARCH INSTITUTE Co.,Ltd. |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A Long Range Multimodal Biometric Feature Recognition Method and Its System Granted publication date: 20180710 Pledgee: Bohai Bank Co.,Ltd. Tianjin Branch Pledgor: TIANJIN ZHONGKE HONGXING TECHNOLOGY CO.,LTD. Registration number: Y2024120000040 |