CN101499129A - Distant range iris recognition system and method - Google Patents
Distant range iris recognition system and method Download PDFInfo
- Publication number
- CN101499129A CN101499129A CNA200810057184XA CN200810057184A CN101499129A CN 101499129 A CN101499129 A CN 101499129A CN A200810057184X A CNA200810057184X A CN A200810057184XA CN 200810057184 A CN200810057184 A CN 200810057184A CN 101499129 A CN101499129 A CN 101499129A
- Authority
- CN
- China
- Prior art keywords
- main control
- image
- control computer
- camera
- height
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000012360 testing method Methods 0.000 claims abstract description 28
- 238000000605 extraction Methods 0.000 claims description 15
- 239000004744 fabric Substances 0.000 claims description 13
- 238000001514 detection method Methods 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 239000000284 extract Substances 0.000 claims description 7
- 238000003491 array Methods 0.000 claims description 4
- 230000002950 deficient Effects 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 238000012546 transfer Methods 0.000 claims description 4
- 230000008447 perception Effects 0.000 claims description 3
- 230000004304 visual acuity Effects 0.000 claims description 3
- 210000000554 iris Anatomy 0.000 description 81
- 238000005516 engineering process Methods 0.000 description 14
- 230000008569 process Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 3
- 239000011121 hardwood Substances 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 240000000015 Iris germanica Species 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 208000016339 iris pattern Diseases 0.000 description 1
- 230000013011 mating Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 210000000162 simple eye Anatomy 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Abstract
The invention discloses a distant range iris identifying system and a method thereof. The system includes: a camera/long focus lens for shooting eye image; a collecting card; a main control computer for collecting image by controlling the camera/long focus lens through the collecting card; a controllable clouds terrace for controlling the camera/long focus lens raising falling or left and righ rotary set on computer under controlled by the computer; a display/clew device for displaying the image collected by the camera/long focus lens or clewing under controlled by the main control computer; a height test sensor set on an identifying channel top for testing human height; an infrared source set on two sides of the channel door front for supplying light to image shoot; a singlechip control circuit for controlling the height testing sensor and the infrared source working. The system can shoot clear iris image continuously in distant range (beyond three meters) and identify which can increase practicability and enlarge application range for identifying iris.
Description
Technical field
The present invention relates to a kind ofly carrying out iris authentication system and method at a distance.The present invention combines technology such as Flame Image Process, pattern-recognition, optical technology and automatic control, is applied to the iris recognition direction in living things feature recognition field.
Background technology
Iris recognition technology is that accuracy is the highest in the present biometrics identification technology, one of antifalsification best techniques, has market application foreground widely.Steps such as the step of iris recognition generally comprises that iris image obtains, live body detection, pre-service, feature extraction and characteristic matching.
Present iris technology can realize identification fast and accurately.The patent of China national Department of Intellectual Property for example: 1. Tan's car pusher, Wang Yunhong, horsepower, " based on the personal identification method of living body iris ", application number: 01144524.6; And 2. Tan's car pushers, Wang Yunhong, Sun Zhenan, " robust features of iris image extract with recognition methods ", application number: 200410081184.5 etc.; And be desirably in the identification in the large-scale crowd and be applied.
Wherein, to obtain be the prerequisite of carrying out iris recognition to iris image; Yet because the diameter of iris is very little, and the iris image of gathering requires that abundant pixel must be arranged, and also is a very difficult link so iris image obtains.
Iris image acquiring device and method in the technology all is in-plant or hand-held at present, and these Technology Needs people is very near from the iris capturing device, even eyes is pressed close to camera lens tightly come images acquired, uses very inconvenient in real life.Main cause is owing to common iris camera target surface all very little (typical camera is as 640 * 480), and iris recognition requires the diameter all very big (more than 150 pixels) of iris portion, so the scope of camera and the depth of field are all very little.So people's eyes must first be fixed among a small circle apart from shooting, just can discern; Depart from this point a little, all can not obtain distinct image.
In order to address this problem, people have done a lot of improvement, a kind of is to utilize range sensor to record people's distance, utilize sound or pilot lamp prompter to advance then or retreat, thereby a kind of method is to utilize mirror or display to allow the people see that the image of oneself adjusts the position automatically.The problem of these equipment is that the user must positive cooperation just can collect suitable image, uses very inconvenient.
Also having a kind of method is the method that adopts from motion tracking or autozoom: the position that method that detects by people's face or service range sensor are determined people's eyes; Then control up and down the The Cloud Terrace of rotation rotate the position that the iris video camera removes initiatively to seek people's eyes, and the image of people's eyes is caught in autozoom.This mode can significantly reduce people's cooperate degree, yet often speed is slower, and cost is higher, and system is complicated more, and just running is more unstable.
Yet to be the people just can carry out iris recognition at remote (beyond 3 meters even farther) to optimal method, even when the very natural place of passing by of people, just can discern rapidly.Carry out iris image acquiring at a distance, just requiring camera lens that very narrow visual angle must be arranged; In addition, the people stands at a distance with regard to more difficult aligning, and this just requires camera to aim at automatically, and simultaneously, camera has the enough big coverage and the depth of field.
Summary of the invention
(1) technical matters that will solve
In view of this, fundamental purpose of the present invention is to provide the iris image gathering system and the method for a kind of remote (beyond 3 meters), carries out iris recognition to make things convenient for the user.
(2) technical scheme
For achieving the above object, the invention provides a kind of distant range iris recognition system, this system comprises:
One takes the camera/long focal length lens of eye image, and this camera/long focal length lens is connected in main control computer by capture card;
One connects the capture card of camera/long focal length lens and main control computer;
One main control computer by capture card control camera/long focal length lens images acquired;
One under the control of main control computer the control setting controlled The Cloud Terrace of camera/long focal length lens lifting or left rotation and right rotation thereon;
One shows camera/long focal length lens institute's images acquired or the display/prompt facility of pointing out under the control of main control computer; And
One is arranged at the height testing sensor that is used for the testing human height on identification passage top;
One is arranged at the both sides, access door the place ahead of identification passage, and the infrared light supply of light is provided for photographic images;
The single chip machine controlling circuit of one control height testing sensor and infrared source working;
Described main control computer is connected in capture card, controlled The Cloud Terrace and single chip machine controlling circuit by serial ports RS-232 or RS-485 bus respectively, and is connected with display/prompt facility by the VGA data line.
Preferably, described main control computer is behind the eye image that receives camera/long focal length lens shooting, this image is handled in real time, eye image is clearly carried out iris image location and feature extraction, the iris feature of image in the iris feature that extracts and the database is compared, judge this person's identity, and control display/prompt facility carries out auditory tone cues or light prompt after iris recognition is finished, and carry out the operation of switch door.
Preferably, in described camera/long focal length lens, camera adopts at least 400 ten thousand pixels and the high frame speed of the high resolving power of at least 15 frame/seconds camera, and long focal length lens adopts focal length in the long focal length lens more than 300 millimeters.
Preferably, described capture card adopts the CameraLink capture card, and main control computer is by the transfer rate of control capture card configuration image, and time shutter, video standard and conversion figure place that camera is set.
Preferably, described controlled The Cloud Terrace is provided with 5 presetting bits at least, makes camera aim at the zone of 1.4 meters, 1.5 meters, 1.6 meters, 1.7 meters, 1.8 meters height respectively, and the speed that wherein controlled The Cloud Terrace rotates up and down was 6 degree/seconds.
Preferably, described infrared light supply adopts at least 6 infrared LED arrays, is installed in identification passage both sides respectively, and light intensity is evenly distributed on 2 milliwatt/square centimeters in the camera field depth.
Preferably, described single chip machine controlling circuit adopts the AVR single-chip microcomputer, and utilizes MOSFET to control the opening and closing of described infrared light supply;
Single chip machine controlling circuit constantly reads the height number of height testing sensor, this height number is zero under the situation that nobody passes through, as the people by the time will become 1 meter more than 4, single chip machine controlling circuit will inform that main control computer has the people to pass through by serial ports this moment, and from a plurality of height numbers of perception, get a maximal value, export to main control computer as people's height values.
Preferably, described display, camera/long focal length lens, controlled The Cloud Terrace and main control computer from top to bottom are disposed in the rack successively, and this rack is positioned at outside 3 meters in access door the place ahead at least.
For achieving the above object, the present invention also provides a kind of distant range iris recognition methods, and this method comprises:
When the people entered the identification passage, height testing sensor estimated people's general height, and this height number is exported to main control computer by single chip machine controlling circuit, and main control computer is adjusted camera/long focal length lens lifting and the rotation on the controlled The Cloud Terrace;
Camera/the long focal length lens that is arranged on the controlled The Cloud Terrace outside 3 meters in the passage of identification is taken eye image continuously to the people by the identification passage, and is transferred to main control computer;
Main control computer is handled in real time to eye image, constantly detects this eye image, and judges whether this eye image is picture rich in detail;
When picture rich in detail occurred, main control computer carried out iris image location and feature extraction, and the iris feature of extraction and the image in the database are compared, and judges this person's identity.
Preferably, this method further comprises in advance to be registered eye image, specifically comprise: the image of registering left and right sides eyes simultaneously, every eyes are registered continuously when 3 width of cloth images and 3 width of cloth images all mate just succeed in registration at least, after the image registration success iris feature of 6 width of cloth images altogether of two eyes is deposited in the iris characteristic data storehouse of main control computer at least, each iris feature comprises 1024 bytes.
Preferably, described main control computer is adjusted camera/long focal length lens lifting and the rotation on the controlled The Cloud Terrace, specifically comprises:
Single chip machine controlling circuit constantly reads the height number of height testing sensor, when height number suddenly when zero becomes more than 1.4 meters, the notice main control computer has the people by discerning passage;
The people is being arranged when discerning passage, single chip machine controlling circuit reads a plurality of human body height numbers continuously, gets maximal value and exports to main control computer for people's height estimated value;
Main control computer is according to people's height estimation people's eye position, and rotary platform makes the position of 3 meters of camera alignment eye height; Wherein, described The Cloud Terrace has 5 presetting bits at least, makes camera aim at 1.4 meters, 1.5 meters, 1.6 meters, 1.7 meters and 1.8 meters respectively, and main control computer can rotate controlled The Cloud Terrace and reach wherein any position within 1 second.
Preferably, described main control computer detects eye image and adopts monocular to detect, as long as there is an eye image to be detected, just carries out ensuing processing, judges whether this eye image is picture rich in detail.
Preferably, described monocular detection method is based on open software OpenCV, and the human eye sorter that adopts Harr-like feature and Boosting to train out detects; At first image is carried out down-sampledly during detection, and then handle.
Preferably, described main control computer judges whether eye image is picture rich in detail, adopts the method for computed image edge energy, thinks that picture quality is qualified when energy value surpasses threshold value.The method of described employing computed image edge energy is to adopt the TenenGrad of computed image to assess, and promptly utilizes the Sobel operator edge calculation of both direction, asks for edge energy then, thinks that picture quality is qualified when energy value surpasses threshold value.
Preferably, the TenenGrad of described employing computed image assesses, and specifically comprises: utilize the single order differential on the Sobel boundary operator computed image both direction, ask for the energy of edge image then:
Wherein G (i, j)
xAnd G (i, j)
yBe respectively the convolution of image and Sobel operator, the Sobel operator respectively has one at x and y direction:
Define a threshold value then,, think that picture quality is defective during less than this threshold value when the TenenGrad of image thinks that picture quality is qualified during more than or equal to this threshold value.
Preferably, this method further comprises after judging this person's identity at main control computer: main control computer control display/prompt facility carries out auditory tone cues or light prompt, and carries out the operation of switch door.
(3) beneficial effect
The present invention has used image processing techniques, mode identification technology, optical technology and automatic control technology, can from remote (beyond 3 meters) continuously shooting clear iris image and discern, make and just can finish authentication through an access door time when the people does to stop slightly, thereby improved the practicality of iris recognition greatly, expanded the range of application of iris recognition.
Description of drawings
Fig. 1 is the appearance assumption diagram of distant range iris recognition system provided by the invention;
Fig. 2 is a distant range iris recognition system hardware device connection diagram provided by the invention;
Fig. 3 is the method flow diagram of distant range iris identification provided by the invention;
Fig. 4 is the software realization flow figure according to the identification of embodiment of the invention distant range iris;
Fig. 5 is for adjusting the software realization flow figure of video camera shooting height automatically according to the embodiment of the invention;
Fig. 6 is the scope synoptic diagram according to embodiment of the invention video camera;
Among the figure, main element and label declaration are as follows:
(1) is computing machine; (2) be camera and telephoto lens; (3) be controlled The Cloud Terrace; (4) be display and prompt facility; (5) be height testing sensor; (6) be access door; (7) be infrared light supply; (8) be control circuit; (9) be power supply; (10) be rack;
P0 is camera and image acquisition card initialization
P1 is an images acquired
P2-1 is simple eye detection (identification process)
P2-2 is that eyes detect (register flow path)
Whether P3-1 for there being eyes (identification process)
P3-1 is not for there being two eyes (register flow path)
P4 is for extracting the eye areas image
P5 is that out of focus is judged
P6 is whether picture quality is good
P7-1 is for extracting feature (identification process)
P7-2 is for extracting feature and registering database (register flow path)
P8 is the iris characteristic data storehouse
P9 is an aspect ratio to, identification people's identity
S1 is for constantly reading height testing sensor
It is big highly whether S2 for become suddenly
S3 is for reading height value several times continuously
S4 is for estimating the approximate region of human eye
S5 is that rotary head arrives human eye area
(R1) be the image acquisition scope and the depth of field of single camera;
(R2) be the general image acquisition range under the The Cloud Terrace cooperation
Embodiment
For making the purpose, technical solutions and advantages of the present invention clearer, below in conjunction with specific embodiment, and with reference to accompanying drawing, the present invention is described in more detail.
(1) the whole step of distant range iris system operation is as follows:
(1) camera is installed beyond 3 meters, when the people enters the identification passage, is estimated people's general height by height testing sensor, and by main control computer control with the camera rotation, and people's face scope at 3 meters of rough alignment;
(2) people's identification passage slow-down or temporarily paused for 1,2 seconds of passing by, camera is with the continuous photographic images of very fast speed;
(3) main control computer is handled in real time to image, constantly detects the image of people's two or one eyes, and judges whether image is picture rich in detail;
(4) when picture rich in detail occurs, main control computer carries out iris image location and feature extraction;
(5) main control computer is compared the iris feature of extraction and the image in the database, judges this person's identity.
(2) the outward appearance mounting structure (as Fig. 1) of system's operation
This distant range iris recognition system provided by the invention comprises:
One takes the camera/long focal length lens of eye image, and this camera/long focal length lens is connected in main control computer by capture card;
One connects the capture card of camera/long focal length lens and main control computer;
One main control computer by capture card control camera/long focal length lens images acquired;
One under the control of main control computer the control setting controlled The Cloud Terrace of camera/long focal length lens lifting or left rotation and right rotation thereon;
One shows camera/long focal length lens institute's images acquired or the display/prompt facility of pointing out under the control of main control computer; And
One is arranged at the height testing sensor that is used for the testing human height on identification passage top;
One is arranged at the both sides, access door the place ahead of identification passage, and the infrared light supply of light is provided for photographic images;
The single chip machine controlling circuit of one control height testing sensor and infrared source working;
Described main control computer is connected in capture card, controlled The Cloud Terrace and single chip machine controlling circuit by serial ports RS-232 or RS-485 bus respectively, and is connected with display/prompt facility by the VGA data line.
Described main control computer is behind the eye image that receives camera/long focal length lens shooting, this image is handled in real time, eye image is clearly carried out iris image location and feature extraction, the iris feature of image in the iris feature that extracts and the database is compared, judge this person's identity, and control display/prompt facility carries out auditory tone cues or light prompt after iris recognition is finished, and carry out the operation of switch door.
In described camera/long focal length lens, camera adopts at least 400 ten thousand pixels and the high frame speed of the high resolving power of at least 15 frame/seconds camera, and long focal length lens adopts focal length in the long focal length lens more than 300 millimeters.
Described capture card adopts the CameraLink capture card, and main control computer is by the transfer rate of control capture card configuration image, and time shutter, video standard and conversion figure place that camera is set.
Described controlled The Cloud Terrace is provided with 5 presetting bits at least, makes camera aim at the zone of 1.4 meters, 1.5 meters, 1.6 meters, 1.7 meters, 1.8 meters height respectively, and the speed that wherein controlled The Cloud Terrace rotates up and down was 6 degree/seconds.
Described infrared light supply adopts at least 6 infrared LED arrays, is installed in identification passage both sides respectively, and light intensity is evenly distributed on 2 milliwatt/square centimeters in the camera field depth.
Described single chip machine controlling circuit adopts the AVR single-chip microcomputer, and utilizes MOSFET to control the opening and closing of described infrared light supply; Single chip machine controlling circuit constantly reads the height number of height testing sensor, this height number is zero under the situation that nobody passes through, as the people by the time will become 1 meter more than 4, single chip machine controlling circuit will inform that main control computer has the people to pass through by serial ports this moment, and from a plurality of height numbers of perception, get a maximal value, export to main control computer as people's height values.
Described display, camera/long focal length lens, controlled The Cloud Terrace and main control computer from top to bottom are disposed in the rack successively, and this rack is positioned at outside 3 meters in access door the place ahead at least.
Refer again to Fig. 1, rack (10) is placed in the position about 3 meters on the opposite of the access door (6) of discerning passage; Rack is installed main control computer (1), controlled The Cloud Terrace (3), video camera/telephoto lens (2), display/prompt facility (4) from the bottom up respectively; The people is through top, the about 1 meter setting height(from bottom) testing sensor (5) before the access door, when the people walks the out-of-date general height that can measure the people; Infrared light supply (7) is installed in both sides, access door the place ahead.
Wherein camera is selected the high-performance camera for use, resolution (adopts 2352 * 1728 among the embodiment more than 4,000,000 pixels, among other embodiment, also can select 2000 * 2000,3000 * 2208 etc. for use), image transmission speed 15 hardwood/seconds (based on CameraLink image pick-up card and 32 PCI computing machines).
Wherein camera lens is selected long focal length lens (adopt 300 millimeters focal length lenses among the embodiment, the size of focal length can determine the distance of gathering) for use, and lens aperture is adjusted into F=11, (also can allow aperture littler or bigger among other embodiment, aperture is more little, and the depth of field is big more, and light-inletting quantity is also more little).
Wherein infrared light supply uses 6 infrared LED arrays, is contained in the passage both sides respectively, and light intensity is evenly distributed on 2 milliwatt/square centimeters in the camera field depth, and light intensity is in strict conformity with national laser safety standard.
(3) system hardware equipment connects (as Fig. 2)
The view data of main control computer (1) and camera (2) exchanges by the CameraLink image pick-up card, can come the transfer rate of configuration image by the control capture card, and time shutter, video standard, conversion figure place etc. that camera (2) are set.(it is 60ms that the time shutter for example is set, standard 2352 * 1728, the conversion figure place is 10,15 hardwood/seconds of transmission speed)
Main control computer (1) directly is connected by the VGA line with display.The human-computer interaction interface that software in the main control computer adopts shows the image of collection and the eye image in image segmentation, and points out the user by sounding, show that name waits.When the people can directly can see the image of collection through out-of-date from display, and see the prompting that system provides.(also can remove display in other embodiments, and use semi-transparent semi-reflecting mirror instead or point out with pilot lamp etc.)
Main control computer (1) is connected by serial ports (RS-232 or RS-485 bus) with controlled The Cloud Terrace (3) by serial ports.Controlled The Cloud Terrace is provided with 5 presetting bits (or a plurality of presetting bit) at least, makes camera (2) aim at 1.4 meters, 1.5 meters, 1.6 meters, 1.7 meters, 1.8 meters approximate region respectively.Wherein controlled The Cloud Terrace velocity of rotation up and down was 6 degree/seconds, distance outside 3 meters, and main control computer can be controlled controlled The Cloud Terrace and turn to any one zone about 1 second.
Main control computer (1) is connected by serial ports with single chip machine controlling circuit (8), and single chip machine controlling circuit is used for controlling infrared light supply (7) and reads the numerical value of height testing sensor (5).
Single chip machine controlling circuit (8) adopts the AVR single-chip microcomputer, and utilizes the opening and closing of MOSFET control infrared light supply (7); Single chip machine controlling circuit constantly reads the height number of height testing sensor (5); This numerical value is zero under the situation that nobody passes through, as the people by the time can become 1 meter more than 4, at this moment single chip machine controlling circuit (8) can inform that main control computer (1) someone passes through by serial ports, and following height value several times got a maximal value, give main control computer as people's height values.
(4) distant range iris identification process
Existing iris recognition technology all is to use common industrial camera or monitoring camera, is based upon on 640 * 480 the image processing method; The camera (usually more than 4,000,000 pixels) of high pixel is adopted in distant range iris identification provided by the invention, at aspects such as Flame Image Process, location eyes a great difference is arranged; But there is no essential distinction aspect feature extraction and the comparison.
Fig. 3 is the method flow diagram of distant range iris identification provided by the invention, and this method comprises:
Step 301: when the people entered the identification passage, height testing sensor estimated people's general height, and this height number is exported to main control computer by single chip machine controlling circuit;
Step 302: main control computer is adjusted camera/long focal length lens lifting and the rotation on the controlled The Cloud Terrace;
Step 303: the camera/long focal length lens that is arranged on the controlled The Cloud Terrace outside 3 meters in the passage of identification is taken eye image continuously to the people by the identification passage, and is transferred to main control computer;
Step 304: main control computer is handled in real time to eye image, constantly detects this eye image, and judges whether this eye image is picture rich in detail;
Step 305: when picture rich in detail occurred, main control computer carried out iris image location and feature extraction, and the iris feature of extraction and the image in the database are compared, and judges this person's identity.
This method further comprises in advance to be registered eye image, specifically comprise: the image of registering left and right sides eyes simultaneously, every eyes are registered continuously when 3 width of cloth images and 3 width of cloth images all mate just succeed in registration at least, after the image registration success iris feature of 6 width of cloth images altogether of two eyes is deposited in the iris characteristic data storehouse of main control computer at least, each iris feature comprises 1024 bytes.
Described main control computer is adjusted camera/long focal length lens lifting and the rotation on the controlled The Cloud Terrace, specifically comprises:
Single chip machine controlling circuit constantly reads the height number of height testing sensor, when height number suddenly when zero becomes more than 1.3 meters, the notice main control computer has the people by discerning passage;
The people is being arranged when discerning passage, single chip machine controlling circuit reads a plurality of human body height numbers continuously, gets maximal value and exports to main control computer for people's height estimated value;
Main control computer is according to people's height estimation people's eye position, and rotary platform makes the position of 3 meters of camera alignment eye height; Wherein, described The Cloud Terrace has 5 presetting bits at least, makes camera aim at 1.4 meters, 1.5 meters, 1.6 meters, 1.7 meters and 1.8 meters respectively, and main control computer can rotate controlled The Cloud Terrace and reach wherein any position within 1 second.
Described main control computer detects eye image and adopts monocular to detect, as long as there is an eye image to be detected, just carries out ensuing processing, judges whether this eye image is picture rich in detail.
Described monocular detection method is based on open software OpenCV, and the human eye sorter that adopts Harr-like feature and Boosting to train out detects; At first image is carried out down-sampledly during detection, and then handle.
Described main control computer judges whether eye image is picture rich in detail, adopt the TenenGrad of computed image to assess, promptly utilize the Sobel operator edge calculation of both direction, ask for edge energy then, when energy value surpasses threshold value, think that picture quality is qualified.Define a threshold value then,, think that picture quality is defective during less than this threshold value when the TenenGrad of image thinks that picture quality is qualified during more than or equal to this threshold value.
This method further comprises after judging this person's identity at main control computer: main control computer control display/prompt facility carries out auditory tone cues or light prompt, and carries out the operation of switch door.
Further describe below in conjunction with the method for accompanying drawing distant range iris identification:
1. distant range iris identification software flow process is as shown in Figure 4:
P0: initialization camera and capture card when system start-up are provided with time shutter, video standard, conversion figure place of camera (2) etc.(it is 60ms that the time shutter for example is set, standard 2352 * 1728, the conversion figure place is 10,15 hardwood/seconds of transmission speed)
P1: system begins constantly to read the image of camera collection, and image is shown.
P2, P3: image is handled, and detected the position of eyes.
Wherein, when at register flow path, need two eyes of people all to be detected Shi Caineng and carry out location registration process (P2-2, P2-3), right and left eyes that like this can the underwriter is registered simultaneously; When at identification process, as long as there are eyes to be detected, just can handle, like this can be so that use convenient.
Wherein, the method for human eye detection is based on open software OpenCV, and the human eye sorter that adopts Harr-like feature and Boosting to train out detects; At first image is carried out down-sampledly when detecting, and then handle.
P4: after determining the position of human eye, extract the image of eyes part.At existing iris recognition technology, all be to use 640 * 480 images.
P5, P6: the image to the eyes part carries out the picture quality judgement.
Wherein, picture quality judges that the TenenGrad of employing computed image assesses: promptly utilize the single order differential on the Sobel boundary operator computed image both direction, ask for the energy of edge image then:
Wherein G (i, j)
xAnd G (i, j)
yBe respectively the convolution of image and Sobel operator, the Sobel operator respectively has one at x and y direction:
In P6, we define a threshold value, think that picture quality is qualified when the TenenGrad of image is worth more than or equal to this, think that picture quality is defective during less than this value.
P7: when capturing the picture rich in detail of eyes, carry out Iris Location and feature extraction.
Wherein, during registered images (P7-1), must register right and left eyes two width of cloth images simultaneously; Every continuously behind registration 3 width of cloth images and 3 width of cloth images succeed in registration when all mating; During recognition image (P7-2), order is carried out feature extraction to two eyes.
P8, P9: the iris feature of totally 6 width of cloth images (each 1024 byte) with two eyes after the image registration success deposits the iris characteristic data storehouse in.During recognition image, feature and the image in the database that recognition image extracts are done coupling (adopting the Hamming distance comparison), the coupling mark surpasses a preset threshold (being 0.33 among the embodiment), thinks the identity of matching stencil correspondence.
Wherein related Iris Location and feature extracting method all are based on prior art (Chinese patent: 1. Tan's car pusher, Wang Yunhong, horsepower, " based on the personal identification method of living body iris ", application number: 01144524.6 among P7, P8, the P9; And 2. Tan's car pushers, Wang Yunhong, Sun Zhenan, " robust features of iris image extract with recognition methods ", application number: 200410081184.5)
2, the method for adjusting the video camera shooting height automatically is shown in software flow Fig. 5
S1: single chip machine controlling circuit constantly reads height value by height testing sensor.This height value is zero under the situation that nobody passes through; When passing through, the people can increase suddenly.
S2: whether the single chip machine controlling circuit decision height increases to suddenly more than 1.3 meters, if then notify main control computer to have the people to pass through; Otherwise continue to judge.
S3: single chip machine controlling circuit reads height value several times continuously when having the people to pass through, and asks its maximal value, is transferred to main control computer as people's height values.
S4: main control computer is judged people's height values, and the position of guestimate human eye is at the fixedly multiple (for example human eye height ≈ people height * 0.95) of people's height.If position of human eye is at 1.35 meters to 1.45 meters then forward controlled The Cloud Terrace to presetting bit 1; If at 1.45 meters to 1.55 meters then forward controlled The Cloud Terrace to presetting bit 2; If at 1.55 meters to 1.65 meters then forward controlled The Cloud Terrace to presetting bit 3; If at 1.65 meters to 1.75 meters then forward controlled The Cloud Terrace to presetting bit 4; If at 1.75 meters to 1.85 meters then forward controlled The Cloud Terrace to presetting bit 5.(can with reference to figure 5)
S5: control controlled The Cloud Terrace rotation.Controlled The Cloud Terrace Spin Control is controlled by international Pelco agreement.Wherein controlled The Cloud Terrace velocity of rotation up and down was 6 degree/seconds, distance outside 3 meters, and main control computer can be controlled controlled The Cloud Terrace and turn to any one zone about 1 second.
(5) system diagram illustrates as acquisition range
System has been owing to adopted the video camera of high pixel (embodiment is 2352 * 1728), and rotates with controlled The Cloud Terrace and to cooperate, and can obtain very big image acquisition scope.
In addition owing to adopted long focal length lens (300 millimeters of focal lengths, aperture is got F=11), can be the 3 meters far away image acquisition that realize irises, and very big and the image acquisition depth of field are arranged.
The acquisition range of single camera is shown in R1 among Fig. 6.In an embodiment, beyond 3 meters, we can obtain wide 0.2 meter * high 0.15 meter * dark 0.15 meter acquisition range.
And cooperate the camera rotation with controlled The Cloud Terrace, just can obtain bigger acquisition range, shown in R2 among Fig. 6.The acquisition range of five presetting bits (even more) associating can reach wide 0.2 meter * high 0.7 meter * dark 0.15 meter acquisition range.
The invention provides a kind of in the method for carrying out iris recognition at a distance.This method can obtain the image acquisition scope of wide 0.2 meter * high 0.7 meter * dark 0.15 3 meters distance, adapt to height 1.50 to 1.90 meters user, and when the user passes by access door, only need do 1 to 2 second pause, just can finish iris image acquiring and identification.
The present invention has realized remote iris recognition, and greatly facilitates user's use, is the significant improvement of current iris recognition technology, thereby has improved the range of application of iris authentication system widely, has very big range of application and market potential.
Embodiment 1: the clearance system that is applied to large-scale consumer
The present invention can be applied to the clearance system of large-scale consumer.Example is as follows: used distant range iris recognition system to carry out people's identity verification at certain port of being open to the custom.The user shows the certificate indicate identification of oneself before an access door, or adopts card reader to allow computing machine read the passport NO. of oneself; The early gate of passage is opened then, people's admission passage; When admission passage, the user eyes to the front, and slows down step, the at this moment positive remote people's iris image clearly that just collects automatically; If identification is passed through, and is the people on the certificate really, then open the late gate of passage, people normally leg speed passes passage; If identification is not passed through, show that then people's identity has problem, the Security Personnel need carefully check affirmation.
This mode greatly facilitates being open to the custom of large-scale crowd, has not only increased security, has also saved the managerial personnel's that are open to the custom energy simultaneously.And with respect to the clearance system of other biological feature identification, distant range iris identification both can guarantee accuracy, used also very convenient.
Embodiment 2: the iris authentication system that is applied to the honored guest
The present invention can be used for honored guest's iris authentication system.Use is as follows: at certain senior guild hall inlet, need carry out the iris recognition identity verification to visiting personnel, but because the guest is more honorable, in order not cause guest's dislike, be inconvenient to allow instrument aim at the guest and operate, so guild hall's inlet has adopted the distant range iris pattern recognition device.After the guest enters guild hall, by the gate time, stopped for 3 times in second in fixing position, eye to the front, in this process, the remote capture device outside 3 meters photographs iris image clearly, and identifies guest's identity, and send the sound of this " so-and-so Mr., welcome ".This allows the guest experience the safety practice of guild hall, allows the guest be with very convenient and satisfied simultaneously.
Above-described specific embodiment; purpose of the present invention, technical scheme and beneficial effect are further described; institute is understood that; the above only is specific embodiments of the invention; be not limited to the present invention; within the spirit and principles in the present invention all, any modification of being made, be equal to replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (16)
1, a kind of distant range iris recognition system is characterized in that, this system comprises:
One takes the camera/long focal length lens of eye image, and this camera/long focal length lens is connected in main control computer by capture card;
One connects the capture card of camera/long focal length lens and main control computer;
One main control computer by capture card control camera/long focal length lens images acquired;
One under the control of main control computer the control setting controlled The Cloud Terrace of camera/long focal length lens lifting or left rotation and right rotation thereon;
One shows camera/long focal length lens institute's images acquired or the display/prompt facility of pointing out under the control of main control computer; And
One is arranged at the height testing sensor that is used for the testing human height on identification passage top;
One is arranged at the both sides, access door the place ahead of identification passage, and the infrared light supply of light is provided for photographic images;
The single chip machine controlling circuit of one control height testing sensor and infrared source working;
Described main control computer is connected in capture card, controlled The Cloud Terrace and single chip machine controlling circuit by serial ports RS-232 or RS-485 bus respectively, and is connected with display/prompt facility by the VGA data line.
2, distant range iris recognition system according to claim 1, it is characterized in that, described main control computer is behind the eye image that receives camera/long focal length lens shooting, this image is handled in real time, eye image is clearly carried out iris image location and feature extraction, the iris feature of image in the iris feature that extracts and the database is compared, judge this person's identity, and control display/prompt facility carries out auditory tone cues or light prompt after iris recognition is finished, and carry out the operation of switch door.
3, distant range iris recognition system according to claim 1, it is characterized in that, in described camera/long focal length lens, camera adopts at least 400 ten thousand pixels and the high frame speed of the high resolving power of at least 15 frame/seconds camera, and long focal length lens adopts focal length in the long focal length lens more than 300 millimeters.
4, distant range iris recognition system according to claim 1, it is characterized in that, described capture card adopts the CameraLink capture card, and main control computer is by the transfer rate of control capture card configuration image, and time shutter, video standard and conversion figure place that camera is set.
5, distant range iris recognition system according to claim 1, it is characterized in that, described controlled The Cloud Terrace is provided with 5 presetting bits at least, make camera aim at the zone of 1.4 meters, 1.5 meters, 1.6 meters, 1.7 meters, 1.8 meters height respectively, the speed that wherein controlled The Cloud Terrace rotates up and down was at least 6 degree/seconds.
6, distant range iris recognition system according to claim 1 is characterized in that, described infrared light supply adopts at least 6 infrared LED arrays, is installed in identification passage both sides respectively, and light intensity is evenly distributed on 2 milliwatt/square centimeters in the camera field depth.
7, distant range iris recognition system according to claim 1 is characterized in that, described single chip machine controlling circuit adopts the AVR single-chip microcomputer, and utilizes MOSFET to control the opening and closing of described infrared light supply;
Single chip machine controlling circuit constantly reads the height number of height testing sensor, this height number is zero under the situation that nobody passes through, as the people by the time will become 1 meter more than 4, single chip machine controlling circuit will inform that main control computer has the people to pass through by serial ports this moment, and from a plurality of height numbers of perception, get a maximal value, export to main control computer as people's height values.
8, distant range iris recognition system according to claim 1, it is characterized in that, described display, camera/long focal length lens, controlled The Cloud Terrace and main control computer from top to bottom are disposed in the rack successively, and this rack is positioned at outside 3 meters in access door the place ahead at least.
9, a kind of distant range iris recognition methods is characterized in that, this method comprises:
When the people entered the identification passage, height testing sensor estimated people's general height, and this height number is exported to main control computer by single chip machine controlling circuit, and main control computer is adjusted camera/long focal length lens lifting and the rotation on the controlled The Cloud Terrace;
Camera/the long focal length lens that is arranged on the controlled The Cloud Terrace outside 3 meters in the passage of identification is taken eye image continuously to the people by the identification passage, and is transferred to main control computer;
Main control computer is handled in real time to eye image, constantly detects this eye image, and judges whether this eye image is picture rich in detail;
When picture rich in detail occurred, main control computer carried out iris image location and feature extraction, and the iris feature of extraction and the image in the database are compared, and judges this person's identity.
10, distant range iris recognition methods according to claim 9 is characterized in that, this method further comprises in advance to be registered eye image, specifically comprises:
Register the image of left and right sides eyes simultaneously, every eyes are registered continuously when 3 width of cloth images and 3 width of cloth images all mate just succeed in registration at least, after the image registration success iris feature of 6 width of cloth images altogether of two eyes is deposited in the iris characteristic data storehouse of main control computer at least, each iris feature comprises 1024 bytes.
11, distant range iris recognition methods according to claim 9 is characterized in that, described main control computer is adjusted camera/long focal length lens lifting and the rotation on the controlled The Cloud Terrace, specifically comprises:
Single chip machine controlling circuit constantly reads the height number of height testing sensor, when height number suddenly when zero becomes more than 1.4 meters, the notice main control computer has the people by discerning passage;
The people is being arranged when discerning passage, single chip machine controlling circuit reads a plurality of human body height numbers continuously, gets maximal value and exports to main control computer for people's height estimated value;
Main control computer is according to people's height estimation people's eye position, and rotary platform makes the position of 3 meters of camera alignment eye height; Wherein, described The Cloud Terrace has 5 presetting bits at least, makes camera aim at 1.4 meters, 1.5 meters, 1.6 meters, 1.7 meters and 1.8 meters respectively, and main control computer can rotate controlled The Cloud Terrace and reach wherein any position within 1 second.
12, distant range iris recognition methods according to claim 9, it is characterized in that, when discerning, described main control computer detects eye image and adopts monocular to detect, as long as there is an eye image to be detected, just carry out ensuing processing, judge whether this eye image is picture rich in detail.
13, distant range iris recognition methods according to claim 12 is characterized in that, described monocular detection method is based on open software OpenCV, and the human eye sorter that adopts Harr-like feature and Boosting to train out detects; At first image is carried out down-sampledly during detection, and then carry out human eye detection.
14, distant range iris recognition methods according to claim 9 is characterized in that, described main control computer judges whether eye image is picture rich in detail, adopts the method for computed image edge energy, thinks that picture quality is qualified when energy value surpasses threshold value.
15, distant range iris recognition methods according to claim 14 is characterized in that, the method for described employing computed image edge energy is to adopt the TenenGrad of computed image to assess, and specifically comprises:
Utilize the single order differential on the Sobel boundary operator computed image both direction, ask for the energy of edge image then:
Wherein G (i, j)
xAnd G (i, j)
yBe respectively the convolution of image and Sobel operator, the Sobel operator respectively has one at x and y direction:
Define a threshold value then,, think that picture quality is defective during less than this threshold value when the TenenGrad of image thinks that picture quality is qualified during more than or equal to this threshold value.
16, distant range iris recognition methods according to claim 9 is characterized in that, this method further comprises after judging this person's identity at main control computer:
Main control computer control display/prompt facility carries out auditory tone cues or light prompt, and carries out the operation of switch door.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200810057184XA CN101499129B (en) | 2008-01-30 | 2008-01-30 | Distant range iris recognition system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200810057184XA CN101499129B (en) | 2008-01-30 | 2008-01-30 | Distant range iris recognition system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101499129A true CN101499129A (en) | 2009-08-05 |
| CN101499129B CN101499129B (en) | 2010-12-22 |
Family
ID=40946198
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200810057184XA Active CN101499129B (en) | 2008-01-30 | 2008-01-30 | Distant range iris recognition system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101499129B (en) |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102567737A (en) * | 2011-12-28 | 2012-07-11 | 华南理工大学 | Method for locating eyeball cornea |
| CN102750768A (en) * | 2012-07-24 | 2012-10-24 | 苏州工业园区七星电子有限公司 | Access control system based on iris identification |
| CN102831392A (en) * | 2012-07-09 | 2012-12-19 | 哈尔滨工业大学 | Device for remote iris tracking and acquisition, and method thereof |
| CN102982325A (en) * | 2012-02-16 | 2013-03-20 | 郑吉洙 | Iris image capture device and iris identification device |
| CN104021382A (en) * | 2014-06-20 | 2014-09-03 | 北京释码大华科技有限公司 | Eye image collection method and system |
| CN105426874A (en) * | 2015-12-18 | 2016-03-23 | 深圳前海达闼云端智能科技有限公司 | Processing method and device for iris identification |
| CN105447405A (en) * | 2015-11-09 | 2016-03-30 | 南京以太安全技术有限公司 | Document encryption/decryption method and apparatus based on iris recognition and authentication |
| CN106295536A (en) * | 2016-08-02 | 2017-01-04 | 北京无线电计量测试研究所 | A kind of self-adapting type iris identification device and utilize the method that this device carries out iris identification |
| CN107038783A (en) * | 2017-04-14 | 2017-08-11 | 安徽省沃瑞网络科技有限公司 | One kind is applied to building receptionist's system |
| CN107918730A (en) * | 2017-12-26 | 2018-04-17 | 北京无线电计量测试研究所 | A kind of application program login method based on iris recognition identification certification |
| CN107944364A (en) * | 2017-11-15 | 2018-04-20 | 北京亿兆云生物科技有限公司 | A kind of identity authentication platform and iris camera based on iris recognition |
| CN108280390A (en) * | 2017-01-06 | 2018-07-13 | 望墨科技（武汉）有限公司 | A kind of method and system of iris recognition |
| CN108345862A (en) * | 2018-03-02 | 2018-07-31 | 中控智慧科技股份有限公司 | A kind of iris authentication system and its iris identification method |
| CN108346216A (en) * | 2018-04-27 | 2018-07-31 | 珠海亨天宇网络科技有限公司 | A kind of intellectual analysis display instrument |
| CN108470152A (en) * | 2018-02-14 | 2018-08-31 | 天目爱视（北京）科技有限公司 | Based on infrared 3D four-dimension iris data acquisition methods and system |
| CN109117692A (en) * | 2017-06-23 | 2019-01-01 | 上海荆虹电子科技有限公司 | A kind of iris identification device, system and method |
| CN111556306A (en) * | 2019-11-21 | 2020-08-18 | 苏州思源科安信息技术有限公司 | Device and method for long-distance large-field iris optical imaging |
| CN111563437A (en) * | 2020-04-28 | 2020-08-21 | 德施曼机电（中国）有限公司 | Iris detection method of door lock device |
| CN111583459A (en) * | 2020-04-28 | 2020-08-25 | 德施曼机电（中国）有限公司 | Intelligent door lock system based on iris detection |
| CN111583456A (en) * | 2020-04-28 | 2020-08-25 | 德施曼机电（中国）有限公司 | Door lock device based on iris recognition |
| CN112578905A (en) * | 2020-11-17 | 2021-03-30 | 北京津发科技股份有限公司 | Man-machine interaction testing method and system for mobile terminal |
| CN116582644A (en) * | 2023-05-04 | 2023-08-11 | 深圳市联深科技发展有限公司 | Personnel track tracing method and system based on BIM video monitoring |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105550673B (en) * | 2016-02-01 | 2019-07-05 | 北京眼神智能科技有限公司 | A kind of iris identification device and control method |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1545057A (en) * | 2003-11-14 | 2004-11-10 | 清华大学 | Open type iris image automatic collecting device |
| CN1760887A (en) * | 2004-10-11 | 2006-04-19 | 中国科学院自动化研究所 | The robust features of iris image extracts and recognition methods |
| CN1924886A (en) * | 2005-08-31 | 2007-03-07 | 上海乐金广电电子有限公司 | Iris recognition system using visible light and identification method thereof |
| KR100804798B1 (en) * | 2006-03-16 | 2008-02-20 | 주식회사 에스원 | Iris scan system and the method thereof, security system and the method thereof using the same |
-
2008
- 2008-01-30 CN CN200810057184XA patent/CN101499129B/en active Active
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102567737A (en) * | 2011-12-28 | 2012-07-11 | 华南理工大学 | Method for locating eyeball cornea |
| CN102982325A (en) * | 2012-02-16 | 2013-03-20 | 郑吉洙 | Iris image capture device and iris identification device |
| CN102831392A (en) * | 2012-07-09 | 2012-12-19 | 哈尔滨工业大学 | Device for remote iris tracking and acquisition, and method thereof |
| CN102831392B (en) * | 2012-07-09 | 2015-06-24 | 哈尔滨工业大学 | Device for remote iris tracking and acquisition, and method thereof |
| CN102750768A (en) * | 2012-07-24 | 2012-10-24 | 苏州工业园区七星电子有限公司 | Access control system based on iris identification |
| CN104021382A (en) * | 2014-06-20 | 2014-09-03 | 北京释码大华科技有限公司 | Eye image collection method and system |
| CN105447405A (en) * | 2015-11-09 | 2016-03-30 | 南京以太安全技术有限公司 | Document encryption/decryption method and apparatus based on iris recognition and authentication |
| WO2017101778A1 (en) * | 2015-12-18 | 2017-06-22 | 深圳前海达闼云端智能科技有限公司 | Iris information obtaining method and apparatus, storage medium, electronic device, and system |
| CN105426874A (en) * | 2015-12-18 | 2016-03-23 | 深圳前海达闼云端智能科技有限公司 | Processing method and device for iris identification |
| CN106295536A (en) * | 2016-08-02 | 2017-01-04 | 北京无线电计量测试研究所 | A kind of self-adapting type iris identification device and utilize the method that this device carries out iris identification |
| CN106295536B (en) * | 2016-08-02 | 2019-05-03 | 北京无线电计量测试研究所 | Self-adapting type iris identification device and the method for carrying out iris recognition using the device |
| CN108280390A (en) * | 2017-01-06 | 2018-07-13 | 望墨科技（武汉）有限公司 | A kind of method and system of iris recognition |
| CN107038783A (en) * | 2017-04-14 | 2017-08-11 | 安徽省沃瑞网络科技有限公司 | One kind is applied to building receptionist's system |
| CN109117692B (en) * | 2017-06-23 | 2024-03-29 | 深圳荆虹科技有限公司 | Iris recognition device, system and method |
| CN109117692A (en) * | 2017-06-23 | 2019-01-01 | 上海荆虹电子科技有限公司 | A kind of iris identification device, system and method |
| CN107944364A (en) * | 2017-11-15 | 2018-04-20 | 北京亿兆云生物科技有限公司 | A kind of identity authentication platform and iris camera based on iris recognition |
| CN107918730A (en) * | 2017-12-26 | 2018-04-17 | 北京无线电计量测试研究所 | A kind of application program login method based on iris recognition identification certification |
| CN108470152A (en) * | 2018-02-14 | 2018-08-31 | 天目爱视（北京）科技有限公司 | Based on infrared 3D four-dimension iris data acquisition methods and system |
| CN108345862A (en) * | 2018-03-02 | 2018-07-31 | 中控智慧科技股份有限公司 | A kind of iris authentication system and its iris identification method |
| CN108346216A (en) * | 2018-04-27 | 2018-07-31 | 珠海亨天宇网络科技有限公司 | A kind of intellectual analysis display instrument |
| CN111556306A (en) * | 2019-11-21 | 2020-08-18 | 苏州思源科安信息技术有限公司 | Device and method for long-distance large-field iris optical imaging |
| CN111556306B (en) * | 2019-11-21 | 2022-03-01 | 苏州思源科安信息技术有限公司 | Device and method for long-distance large-field iris optical imaging |
| CN111563437A (en) * | 2020-04-28 | 2020-08-21 | 德施曼机电（中国）有限公司 | Iris detection method of door lock device |
| CN111583459A (en) * | 2020-04-28 | 2020-08-25 | 德施曼机电（中国）有限公司 | Intelligent door lock system based on iris detection |
| CN111583456A (en) * | 2020-04-28 | 2020-08-25 | 德施曼机电（中国）有限公司 | Door lock device based on iris recognition |
| CN111583456B (en) * | 2020-04-28 | 2022-05-27 | 德施曼机电（中国）有限公司 | Door lock device based on iris recognition |
| CN112578905A (en) * | 2020-11-17 | 2021-03-30 | 北京津发科技股份有限公司 | Man-machine interaction testing method and system for mobile terminal |
| CN116582644A (en) * | 2023-05-04 | 2023-08-11 | 深圳市联深科技发展有限公司 | Personnel track tracing method and system based on BIM video monitoring |
| CN116582644B (en) * | 2023-05-04 | 2024-01-26 | 深圳市联深科技发展有限公司 | Personnel track tracing method and system based on BIM video monitoring |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101499129B (en) | 2010-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101499129B (en) | Distant range iris recognition system and method | |
| CN100361135C (en) | Method for acquiring human-face image, human-face discrimination and discriminating system | |
| US10395097B2 (en) | Method and system for biometric recognition | |
| CN102622588B (en) | Dual-certification face anti-counterfeit method and device | |
| CN109389719B (en) | Community door access control system and door opening method | |
| CN102841354B (en) | Vision protection implementation method of electronic equipment with display screen | |
| CN103106397B (en) | Human face in-vivo detection method based on bright pupil effect | |
| KR101968101B1 (en) | Object recognition camera module and object recognition system thereof | |
| CN107862299A (en) | A kind of living body faces detection method based on near-infrared Yu visible ray binocular camera | |
| CN109101871A (en) | A kind of living body detection device based on depth and Near Infrared Information, detection method and its application | |
| CN101520838A (en) | Automatic-tracking and automatic-zooming method for acquiring iris images | |
| US20020131622A1 (en) | Apparatus and method for adjusting focus position in iris recognition system | |
| CN102262727A (en) | Method for monitoring face image quality at client acquisition terminal in real time | |
| CN108876968A (en) | Recognition of face gate and its anti-trailing method | |
| CN105095893A (en) | Image acquisition device and method | |
| CN108960068A (en) | For acquiring the light source brightness adjusting device and method of finger venous image | |
| CN106778713A (en) | The iris identification device and method of a kind of dynamic human eye tracking | |
| JP2000105830A (en) | Individual identifying device | |
| CN102622614B (en) | Knife switch closing reliability judging method based on distance between knife switch arm feature point and fixing end | |
| CN103996033B (en) | Human identification method based on tracking of human face five-sense-organ coordinates | |
| CN110414381A (en) | Tracing type face identification system | |
| KR101596363B1 (en) | Access Control Apparatus and Method by Facial Recognition | |
| CN206489590U (en) | A kind of iris identification device of dynamic human eye tracking | |
| Hanna et al. | A System for Non-Intrusive Human Iris Acquisition and Identification. | |
| CN111145416A (en) | Face recognition gate and anti-trailing method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20181112 Address after: Unit 1005, Block MSD-G1, Teda, 57 Second Avenue, Tianjin Economic and Technological Development Zone, 300457 Patentee after: Tianjin Zhongke Rainbow Star Technology Co., Ltd. Address before: 100080 No. 95 East Zhongguancun Road, Beijing, Haidian District Patentee before: Institute of Automation, Chinese Academy of Sciences |