WO2006006298A1 - 瞳孔検出装置および虹彩認証装置 - Google Patents
瞳孔検出装置および虹彩認証装置 Download PDFInfo
- Publication number
- WO2006006298A1 WO2006006298A1 PCT/JP2005/009045 JP2005009045W WO2006006298A1 WO 2006006298 A1 WO2006006298 A1 WO 2006006298A1 JP 2005009045 W JP2005009045 W JP 2005009045W WO 2006006298 A1 WO2006006298 A1 WO 2006006298A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- pupil
- candidate
- integration
- circle
- data
- Prior art date
Links
- 210000001747 pupil Anatomy 0.000 title claims abstract description 296
- 238000001514 detection method Methods 0.000 claims description 80
- 230000010354 integration Effects 0.000 claims description 80
- 238000011156 evaluation Methods 0.000 claims description 41
- 238000013075 data extraction Methods 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 22
- 238000000034 method Methods 0.000 description 12
- 230000015654 memory Effects 0.000 description 11
- 238000003384 imaging method Methods 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 5
- 239000000284 extract Substances 0.000 description 4
- 230000007423 decrease Effects 0.000 description 3
- 210000000720 eyelash Anatomy 0.000 description 3
- 238000011144 upstream manufacturing Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000000717 retained effect Effects 0.000 description 2
- 229930091051 Arenine Natural products 0.000 description 1
- 125000002066 L-histidyl group Chemical group [H]N1C([H])=NC(C([H])([H])[C@](C(=O)[*])([H])N([H])[H])=C1[H] 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 210000000744 eyelid Anatomy 0.000 description 1
- 208000016339 iris pattern Diseases 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B3/00—Apparatus for testing the eyes; Instruments for examining the eyes
- A61B3/10—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions
- A61B3/11—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions for measuring interpupillary distance or diameter of pupils
- A61B3/112—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions for measuring interpupillary distance or diameter of pupils for measuring diameter of pupils
-
- 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
- G06V40/18—Eye characteristics, e.g. of the iris
Definitions
- Pupil detection device and iris authentication device Pupil detection device and iris authentication device
- the present invention relates to an iris authentication device used for personal authentication and the like, and more particularly to a pupil detection device that detects the position of a middle-powered pupil image (hereinafter abbreviated as “eye image”).
- eye image a middle-powered pupil image
- the image data of the eye image (hereinafter abbreviated as “eye image data”) is binarized.
- There is known a method for calculating a partial derivative of this quantity with respect to r by calculating the force r to increase the radius r see, for example, Japanese Patent Publication No. 8-504 979.
- some methods have been proposed to improve the detection accuracy by eliminating the influence of eyelashes and external light reflection (for example, Japanese Patent Application Laid-Open No. 2002-119477).
- the present invention provides a pupil detection device and an iris authentication device capable of detecting a pupil position at high speed and with high accuracy.
- the pupil detection device of the present invention includes a pupil candidate detection unit that detects the position of a pupil candidate that can be a candidate for a pupil from an eye image, and a pupil that holds a plurality of pupil candidate positions detected by the pupil candidate detection unit.
- the center position force of the pupil candidate has a center position of another pupil candidate in a region within a predetermined distance. Pupil selection for selecting a pupil candidate as a pupil A part.
- FIG. 1 is a circuit block diagram of an iris authentication device using a pupil detection device according to a first embodiment of the present invention.
- FIG. 2A is a diagram showing an example of an image including a pupil.
- FIG. 2B is a diagram showing an integrated value with respect to the radius of the integrating circle.
- FIG. 2C is a diagram showing a value obtained by differentiating the integral value by the radius of the integral circle.
- FIG. 2D is a diagram showing an integration circle moving on the eye image.
- FIG. 3A is a diagram showing an example of an eye image when the integrating circle is located in the iris region and luminance at that time.
- FIG. 3B is a diagram showing an example of an eye image and luminance at that time when the integrating circle is located in the eyeglass frame.
- FIG. 4 is a circuit block diagram of the pupil detection device in the same embodiment.
- FIG. 5 is a circuit diagram of an image data extraction unit in the same embodiment.
- FIG. 6 is a circuit block diagram of a pupil candidate holding unit and a pupil selection unit in the same embodiment.
- FIG. 7 is a diagram for explaining the operation of the pupil selection unit in the embodiment.
- FIG. 8 is a flowchart showing an operation for one frame of an eye image of the pupil detection device in the same embodiment.
- FIG. 9 is a flowchart for selecting a middle-power pupil of a pupil candidate according to another embodiment of the present invention. Explanation of symbols
- the pupil detection device of the present invention includes a pupil candidate detection unit that detects the position of a pupil candidate that can be a candidate for a pupil from an eye image, and a pupil that holds a plurality of pupil candidate positions detected by the pupil candidate detection unit.
- the center position force of the pupil candidate has a center position of another pupil candidate in a region within a predetermined distance. Pupil selection for selecting a pupil candidate as a pupil A part. With this configuration, it is possible to provide a pupil detection device that can detect the pupil position with high accuracy and high speed.
- the pupil detection device of the present invention sets a plurality of concentric circles as integral circles on the eye image, and extracts image data of an eye image located on the circumference of the integral circle.
- a change circle detection unit that detects an integration circle that changes stepwise with respect to the radius of the pupil
- a pupil candidate holding unit that holds the center coordinates of the integration circle detected by the change circle detection unit as the coordinate position of the pupil candidate
- a pupil selection unit that selects a pupil candidate having a center position of another pupil candidate in a region within a predetermined distance from the center coordinate of the pupil candidate among the pupil candidates held by the pupil candidate holding unit.
- the change circle detection unit of the pupil detection device of the present invention outputs, as an evaluation value, the magnitude of change in which the integration value of the circular integration unit changes stepwise with respect to the radius of the integration circle.
- the holding unit is configured by connecting multiple maximum value detectors that detect data having the maximum value among the input data in series, and by inputting the evaluation value to the pupil candidate holding unit, the evaluation value is large! / In order, pupil candidates are held. With this configuration, it is possible to arrange pupil candidates in large and river pages using evaluation values.
- the maximum value detector of the pupil detection device of the present invention includes a register for holding input data, A comparator that compares the data held in the register with the input data, and a selector that selects and outputs either the data held in the register or the input data. Based on the output of the comparator, the register holds the input data if the input data is larger than the stored data. The input data is larger than the data! In this case, the data held by the register may be selected, and the input data may be smaller than the data held by the register. In this case, the input data may be selected. With this configuration, the maximum value detector can be realized with a relatively simple circuit.
- the pupil selection unit of the pupil detection device of the present invention groups a plurality of pupil candidates that are close to each other as one group! ⁇ ⁇ ⁇ ⁇ , and pupil candidates from each group In other words, the sum of the evaluation values of the group or the pupil candidates is the highest, and the pupil position may be determined from the selected group.
- the pupil selection unit can be realized using a relatively simple algorithm.
- the iris authentication apparatus of the present invention includes the pupil detection apparatus of the present invention. With this configuration, it is possible to provide an iris authentication device equipped with a pupil detection device capable of detecting the pupil position with high accuracy and high speed.
- FIG. 1 is a circuit block diagram of an iris authentication device 100 using the pupil detection device 200 according to the first embodiment of the present invention.
- FIG. 1 also shows an imaging unit 120, an illumination unit 130, and an authentication processing unit 140 that are necessary for configuring the iris authentication device 100 in addition to the pupil detection device 200.
- An iris authentication device 100 includes an imaging unit 120 that captures a user's eye image, a pupil detection device 200 that detects a pupil position and its radius from the eye image, and an eye image force acquisition.
- the authentication processing unit 140 which performs personal authentication by comparing the iris code with the registered iris code, emits near-infrared light with a light intensity suitable for eye image acquisition and its surroundings An illumination unit 130 for illuminating the part is provided.
- the imaging unit 120 includes a guide mirror 121, a visible light cut filter 122, a lens 123, an imaging device 124, and a preprocessing unit 125.
- the optical system can be reduced in size, weight, and cost.
- the guiding mirror 121 guides the eyes to the correct imaging position by the user reflecting his / her eyes.
- the pre-processing unit 125 extracts an image data component from the output signal of the image sensor 124, performs necessary processing as image data such as gain adjustment, and outputs it as user's eye image data.
- the pupil detection device 200 includes a pupil candidate detection unit 210, a pupil candidate holding unit 280, and a pupil selection unit 290.
- the pupil detection device 200 detects the pupil position and its radius from the center of the eye image, and sends it to the authentication processing unit 140. Output.
- the authentication processing unit 140 cuts out an iris image from the eye image data based on the pupil center coordinates and the pupil radius detected by the pupil detection device 200. Then, the authentication operation is executed by converting the iris image into a unique iris code indicating an iris pattern and comparing it with a registered iris code.
- FIGS. 2A to 2D are diagrams for explaining a pupil detection method of the pupil detection device 200 according to the first embodiment of the present invention.
- 2A is a diagram showing an example of an image including a pupil
- FIG. 2B is a diagram showing an integrated value with respect to the radius of the integrating circle
- FIG. 2C is a diagram showing a value obtained by differentiating the integrated value with the radius of the integrating circle
- FIG. 2D is an eye image. It is a figure which shows the integrating circle which moves up.
- the image including the pupil includes a disk-shaped low luminance region indicating the pupil and an annular medium luminance region indicating the iris on the outer side. Therefore, if the image data is circularly integrated along the circumference of the integration circle C of radius R around the pupil center position coordinate (Xo, Yo), the integration value I is stepped at the pupil radius Ro as shown in Fig. 2 (b). Will change. Therefore, the pupil radius Ro can be obtained by finding the radius of the integral circle when the value dlZdR obtained by differentiating the integral value I with the radius R exceeds a threshold (hereinafter referred to as “difference threshold”) Alth.
- difference threshold hereinafter referred to as “difference threshold” Alth.
- the pupil detection device 200 detects the position coordinates (Xo, Yo) of the pupil and the pupil radius Ro.
- the average value of the image data of the pixels located on the circumference of each integral circle ⁇ is calculated, or a medium constant number (m) of pixels located on the circumference is selected and selected. Add image data.
- the integral value I of the circular integration is assumed.
- the integration value I for each integration circle ⁇ changes in a step shape, so that the radius R of the integration value I
- a large maximum value is shown where it is equal to the pupil radius Ro.
- the position of the pupil and its radius can be obtained by obtaining the integral circle C in which the difference value ⁇ is larger than the difference threshold value A lth.
- the difference value ⁇ may show a large value accidentally.
- the number of integration circles n and the number of pixels m selected on each integration circle are reduced, the amount of calculation can be reduced and high-speed pupil detection is possible, but on the other hand, the difference value ⁇ is increased accidentally.
- the possibility of showing a high value increases, and the pupil detection accuracy decreases. Therefore, a luminance difference calculation unit 240 is provided in the pupil detection device 200, and for each integration circle C, a difference B between the maximum value and the minimum value on the circumference of the circle is obtained, and the difference ⁇ This is referred to as the “brightness difference threshold”.
- FIGS. 3A and 3B are diagrams for explaining the operation of the luminance difference calculation unit 240.
- Fig. 3A is a diagram showing an example of an eye image when the integration circle is located in the iris region and an example of luminance at that time
- Fig. 3B is an example of an eye image when the integration circle is located in the eyeglass frame and an example of luminance at that time.
- each integration circle C is located in a relatively uniform region such as the inside of the pupil region or the iris region.
- the brightness variation of the image data on the circumference is small.
- Fig. 3A shows the integration circle located in the iris region, which is the middle luminance region of the ring.
- the difference B between the maximum luminance value and the minimum luminance value on the circumference is smaller than the smaller luminance difference threshold Bth.
- the luminance difference threshold Bth is desirably set to be larger than the expected variation in luminance data on the circumference. Empirically, it should be set smaller than the difference between the average brightness of the skin and the average brightness of the pupil, which is larger than the difference between the average brightness of the iris and the average brightness of the pupil. For example, in the case of an image signal with 256 gradations, the average brightness of the pupil is about 40 gradations, the average brightness of the iris is about 100 gradations, and the average brightness of the skin is about 200 gradations. Set between 60 and 160! /.
- the integral value I when the integral circle is on the pupil is approximately 40.
- FIG. 4 is a circuit block diagram of pupil detection device 200 according to the first embodiment of the present invention.
- the pupil detection device 200 includes a pupil candidate detection unit 210, a pupil candidate holding unit 280, a pupil selection The selector 290 is provided.
- the pupil candidate detection unit 210 sets an integration circle to on the eye image and extracts image data on the circumference of each integration circle ⁇ , and extracts the extracted image data for each integration circle C.
- Circulatory integration unit 230 that circulates and integrates, luminance difference calculation unit 240 that calculates the difference B between the maximum and minimum values of the image data for each integration circle, and the difference value ⁇ I that determines the difference value ⁇ I of the integral value I relative to the radius R
- the maximum value of ⁇ I is larger than the difference threshold ⁇ Ith.
- the change circle detector 250 outputs the difference value ⁇ I and the radius R of the integration circle, and shows the center coordinates (X, Y) of the integration circles C to C
- a pointer portion 260 is provided.
- the pupil candidate holding unit 280 is configured such that the change circle detection unit 250 has a difference value larger than the difference threshold A lth.
- ⁇ When ⁇ is output, it is considered that the pupil candidate has been detected, and the position coordinates (X, Y) and radius R of the plurality of pupil candidates are stored, and the pupil selection unit 290 selects one pupil from among the plurality of pupil candidates. Pick out.
- FIG. 5 is a circuit diagram of the image data extraction unit 220.
- Fig. 5 also shows an adder 230 and a luminance difference calculator 240 corresponding to one integral circle C.
- the image data extraction unit 220 is composed of a partial frame memory 222 and a lead line for extracting image data.
- the partial frame memory 222 is formed by connecting a plurality of first-in-first-out type (FIFO type) line memories 224 in series. Then, image data is extracted from m pixels corresponding to the integration circle C on the image by the extraction line L.
- FIG. 5 shows only one integration circle C and a drawing line L for extracting four pixel data on the circumference. In the first embodiment, there are 20 forces. From the integration circles C to C, eight data lines are drawn for each i 1 20.
- the circular integrator 230 includes adders 230 to 230 that are independent of each of the integration circles C to C, and adds m pieces of image data positioned on the circumference of each integration circle C, The result of addition is output as integral value I to change circle detector 250.
- the luminance difference calculation unit 240 includes independent luminance difference calculators 240 to 240 for each of the integration circles C to C, and each luminance difference calculator 240 is m positioned on the circumference of the integration circle C.
- Maximum value detector 241 that detects the maximum value of each pixel data
- minimum value detector 242 that detects the minimum value
- subtractor 243 that calculates the difference B between the maximum value and minimum value
- difference B and luminance difference threshold Bth Comparator 24 is provided. Then, n comparison results are output to the change circle detection unit 250.
- the odd circle detection pole 250 includes subtractors 252 to 252, a selector 253, and a con- verter 254.
- the subtractor 252 calculates a difference with respect to the radius R of the integral value I for each integral circle C. That is, among the integration circles C to C, the difference value ⁇ I between the integration values I and I with respect to the integration circle C with a different radius is obtained. However, if the difference B between the maximum value and the minimum value of the image data for the integration circle C is larger than the luminance difference threshold Bth, the difference value is forcibly set to 0.
- the selector 253 and the comparator 254 output the radius R of the integration circle C in which the difference value ⁇ is larger than the difference threshold A lth to the pupil candidate holding unit 280, and the difference value ⁇ I is also evaluated as an evaluation ⁇ . Output to pupil candidate holding unit 280. At this time, the image for the integration circle C
- the subtractor 252i When the difference B between the maximum value and the minimum value of the data is larger than the luminance difference threshold Bth, the subtractor 252i forcibly sets the difference value ⁇ I to 0, so that the difference B is larger than the luminance difference threshold Bth. In this case, the radius R is not output to the pupil candidate holding unit 280.
- the difference B between the maximum value and the minimum value of the pixel data is limited. Or less.
- the difference B increases if it does not coincide with the center of the pupil. Therefore, the possibility of false detection can be reduced by excluding information when the difference B is greater than the luminance difference threshold Bth.
- the pupil detection accuracy can be increased.
- FIG. 6 is a circuit block diagram of pupil candidate holding unit 280 and pupil selection unit 290.
- a plurality of maximum value detectors 280 to 280 are connected in series.
- Each of the maximum value detectors 280 is held in registers 282, 283, 284 and 285 which hold the maximum X and Y coordinates, radius R and evaluation value of the candidate pupil, and the input evaluation value and register 285.
- Comparator 281 for comparing with the evaluation city that has been input, selector X for selecting the offset force of the input X coordinate, Y coordinate, radius R and evaluation ⁇ and the held X coordinate, Y coordinate, radius R and evaluation ffi , 287, 288, and 289!
- the maximum value detector 280 at the top receives the outputs X and Y of the X counter 262 and Y counter 264 indicating the coordinates of the integral circle, The output R of the change circle detector 250 is also input.
- the X coordinate X, Y coordinate Y, radius R, and evaluation ⁇ ⁇ that were previously held in the registers 282 to 285 are input to the second maximum value detector 280 via the selectors 286 to 289. And the newly entered X coordinate X, Y coordinate Y, radius R, evaluation value
- evaluation city 0 is less than or equal to evaluation city 1, newly entered X coordinates X, Y
- the second maximum value detector 280 is an evaluation output from the first maximum value detector 280.
- the entered X coordinate X, Y coordinate Y, radius R, and evaluation value are output to the third maximum value detector 280.
- the i-th maximum value detector 280 holds the maximum output value 280 on the upstream side as well. The data that has been held until then is output to the maximum value detector 280 on the downstream side and the upstream side i + 1
- the first maximum value detector SSC ⁇ retains the X-coordinate X, Y-coordinate Y, radius R, and evaluation value for the pupil candidate that has a large evaluation value
- the second maximum value detector 28 0 contains the X coordinate X, Y coordinate Y, radius R, and rating for the second largest candidate pupil.
- the city is retained, and the i-th maximum detector 280 has the i-th largest pupil value.
- the X coordinate X, Y coordinate Y, radius R, and evaluation city for the complement are retained.
- the pupil selection unit 290 has the center position of another pupil candidate in a region within a predetermined distance from the plurality of pupil candidates held in the pupil candidate holding unit 280.
- One pupil candidate is selected, and its position coordinates and radius are output to the authentication processing unit 140 as the position coordinates and radius of the pupil.
- the predetermined distance is 1.5 pixels. Therefore, the pupil selection unit 290, for each of the pupil candidates, includes pupil candidates included in a total of eight pixel positions corresponding to four pixels vertically and horizontally adjacent to the position coordinates (X, Y) of the pupil candidate and four pixels in the diagonal direction. The number of pupils is counted, and a pupil candidate including a large number of pupil candidates is selected as a true pupil.
- the pupil selection unit 290 can be configured using a dedicated circuit that performs the above operations. In this embodiment, the above-described processing is performed using a CPU (not shown) provided in the authentication processing unit 140. Go and go.
- FIG. 7 is a diagram for explaining the operation of the pupil selection unit 290. Pupil candidates P, P
- the erroneously detected pupil candidates are hardly clustered, but the pupil candidates tend to be clustered around the true pupil. This depends on the detection accuracy of the pupil candidates. The better the detection accuracy, the smaller the number of pupil candidates that are dense.
- the number k of pupil candidates detected by the pupil candidate holding unit 280 and the number of pixel positions for counting the number of pupil candidates existing around by the pupil selection unit 290 are the detection accuracy of the pupil candidates, It is desirable to determine by estimation of the number of erroneously detected pupil candidates.
- the number of pixel positions for counting the number of pupil candidates is 4 pixels vertically, horizontally, and diagonally 4
- the area was set to include a total of 8 pixels. It is also assumed that there are nine pupil candidates at the true pupil position (one true pupil, one each vertically and horizontally, one each diagonally) and a maximum of six erroneously detected pupil candidates. Then, set the number of pupil candidates to be detected to 15 and 7 pieces.
- a plurality of pupil candidates are detected from the eye image, and the center position of another pupil candidate exists at a pixel position adjacent to the center position of the pupil candidate from the plurality of pupil candidates.
- FIG. 8 is a flowchart showing the operation for one frame of the eye image of the pupil detection device 200 in the first embodiment of the present invention.
- the pupil detection device 200 captures image data for one pixel (S51). If the captured image data is the first data of one frame (S52), the Y counter 264 is reset and the registers 282 to 285 of the pupil candidate holding unit 280 are reset (S53). If the fetched data is the first data of one line (S54), the X counter 262 is reset and the Y counter 264 is incremented (S55). Then, the X counter 262 is incremented (S56).
- the captured image data is captured into the partial frame memory 222.
- n ⁇ m image data are extracted for each of the integration circles C force m out of the pixels corresponding to the n integration circles C to C on the eye image.
- the adder 230 corresponding to each integration circle C is The integral value Ii of the image data is calculated, and the luminance difference calculator 240i calculates the difference B between the maximum value and the minimum value of the image data.
- the change circle detection unit 250 calculates a difference value ⁇ I of each integral value I. However, at this time, if the difference B is larger than the luminance difference threshold Bth, the difference value ⁇ is forcibly set to 0 (S57).
- the comparator 254 compares the difference value ⁇ I with the difference threshold value ⁇ Ith (S58), and the difference value
- the pupil candidate holding unit 280 holds the X counter 262, the Y counter 264, and the radius of the integrating circle Ro at this time as pupil candidates, and also the difference value ⁇ I thereof. Hold as evaluation ⁇ o. At this time, the pupil candidate holding unit 280 rearranges the pupil candidates in descending order of evaluation value and holds a maximum of k pupil candidates (S 59). Next, it is determined whether or not the captured data is the last data of one frame (S60). If not, the process returns to step S51.
- the pupil selection unit 290 for each pupil candidate, another pupil candidate that exists at a pixel position adjacent to the center coordinate.
- the X-coordinate, Y-coordinate, and radius values of the pupil candidate with the largest value are output to the iris recognition processing unit 140 as the true pupil X-coordinate Xo, Y-coordinate Yo, and pupil radius Ro. (S61).
- step S 51 to step S 60 described above are executed each time image data for one pixel is input to the partial frame memory 222.
- the frame frequency is 30 Hz and the eye image power is 40 to 480 pixels
- the above-described series of operations are executed in a time of 1Z (30 X 640 X 480) or less.
- the integration circle moves by one pixel on the image, so the integration circle scans the image once while inputting one frame image. In this way, pupil detection can be performed in real time on image data captured by the imaging unit 120 using a relatively small circuit.
- the method of selecting a pupil candidate having a center position force within the predetermined distance near the center position of another pupil candidate from the plurality of pupil candidates is not limited to the above-described method.
- multiple pupil candidates that are close to each other are grouped as a single loop, and the number of pupil candidates included in each group is large! The total of the evaluation values of the pupil candidates included or included is high!
- a configuration may be adopted in which a true pupil is selected based on a clue.
- Fig. 9 is a flowchart for selecting a candidate pupil of the pupil candidate based on this concept.
- the pupil selection unit 290 takes in one pupil candidate.
- the difference between the pupil candidate values Xi, Yi, and Ri and the average value Xgj, Ygj, and Rgj (j is 0 or a positive integer) is predetermined.
- step S71 the candidate pupil captured in step S71 is added to the group (S73). If it does not exist, a new group including only the pupil candidates taken in step S71 is created (S74). Next, for the group to which pupil candidates are added in step S73, the average values Xgj, Ygj, and Rgj are recalculated for the group newly created in step S74 (S75).
- step S71 the process returns to step S71 (S76).
- the total ⁇ J of the evaluation values of the pupil candidates included in the group is obtained for each group (S77).
- the average value Xgj, Ygj, and Rgj of the group having the largest total evaluation value ⁇ J is output to the iris authentication processing unit 140 as the X coordinate, Y coordinate, and radius of the pupil ( S 78).
- the selector 253 of the change circle detection unit 250 of the present embodiment has a function of selecting the maximum value of the difference value ⁇ ⁇ and the radius R of the integration circle C at that time.
- pupil candidate protection The holding unit 280 originally has a function of detecting the maximum value. Therefore, the selector 253 can be configured to simply output the outputs of the subtracters 252 to 252 and the radius of the integrating circle in a time division manner.
- the number of concentric integration circles is 20, and the number of image data to be extracted from one integration circle is 8. These numbers are detection accuracy, processing time, circuit It is desirable to decide on the balance with the scale, etc.
- the present invention it is possible to provide a pupil detection device and an iris authentication device capable of detecting the pupil position with high accuracy and high speed.
- the present invention can provide a pupil detection device capable of detecting the pupil position with high accuracy and high speed, it is useful as an iris authentication device used for personal authentication and the like.
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Ophthalmology & Optometry (AREA)
- Biomedical Technology (AREA)
- Human Computer Interaction (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Biophysics (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Heart & Thoracic Surgery (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Eye Examination Apparatus (AREA)
- Image Input (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US10/555,232 US20070036396A1 (en) | 2004-07-14 | 2005-05-18 | Pupil detection device and iris authentication apparatus |
EP05741518A EP1767141A4 (en) | 2004-07-14 | 2005-05-18 | PUPIL MEASUREMENT DEVICE AND DEVICE FOR IRISIDENTIFICATION |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2004206932A JP3966309B2 (ja) | 2004-07-14 | 2004-07-14 | 瞳孔検出装置および虹彩認証装置 |
JP2004-206932 | 2004-07-14 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2006006298A1 true WO2006006298A1 (ja) | 2006-01-19 |
Family
ID=35783655
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2005/009045 WO2006006298A1 (ja) | 2004-07-14 | 2005-05-18 | 瞳孔検出装置および虹彩認証装置 |
Country Status (5)
Country | Link |
---|---|
US (1) | US20070036396A1 (ja) |
EP (1) | EP1767141A4 (ja) |
JP (1) | JP3966309B2 (ja) |
CN (1) | CN100403973C (ja) |
WO (1) | WO2006006298A1 (ja) |
Families Citing this family (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8090157B2 (en) * | 2005-01-26 | 2012-01-03 | Honeywell International Inc. | Approaches and apparatus for eye detection in a digital image |
US9020854B2 (en) | 2004-03-08 | 2015-04-28 | Proxense, Llc | Linked account system using personal digital key (PDK-LAS) |
US8433919B2 (en) | 2005-11-30 | 2013-04-30 | Proxense, Llc | Two-level authentication for secure transactions |
US8036152B2 (en) | 2006-01-06 | 2011-10-11 | Proxense, Llc | Integrated power management of a client device via system time slot assignment |
US11206664B2 (en) | 2006-01-06 | 2021-12-21 | Proxense, Llc | Wireless network synchronization of cells and client devices on a network |
US8659427B2 (en) | 2007-11-09 | 2014-02-25 | Proxense, Llc | Proximity-sensor supporting multiple application services |
US8171528B1 (en) | 2007-12-06 | 2012-05-01 | Proxense, Llc | Hybrid device having a personal digital key and receiver-decoder circuit and methods of use |
WO2009079666A1 (en) | 2007-12-19 | 2009-06-25 | Proxense, Llc | Security system and method for controlling access to computing resources |
US8508336B2 (en) | 2008-02-14 | 2013-08-13 | Proxense, Llc | Proximity-based healthcare management system with automatic access to private information |
WO2009126732A2 (en) | 2008-04-08 | 2009-10-15 | Proxense, Llc | Automated service-based order processing |
JP5365214B2 (ja) * | 2009-01-22 | 2013-12-11 | 日本電気株式会社 | 画像処理装置、生体認証装置、画像処理方法及びプログラム |
US9418205B2 (en) | 2010-03-15 | 2016-08-16 | Proxense, Llc | Proximity-based system for automatic application or data access and item tracking |
US9322974B1 (en) | 2010-07-15 | 2016-04-26 | Proxense, Llc. | Proximity-based system for object tracking |
US9265450B1 (en) | 2011-02-21 | 2016-02-23 | Proxense, Llc | Proximity-based system for object tracking and automatic application initialization |
IL215883A0 (en) * | 2011-10-24 | 2012-03-01 | Iriss Medical Technologies Ltd | System and method for indentifying eye conditions |
JP2013215549A (ja) * | 2012-03-16 | 2013-10-24 | Fujitsu Ltd | 画像処理装置、画像処理プログラムおよび画像処理方法 |
US9405898B2 (en) | 2013-05-10 | 2016-08-02 | Proxense, Llc | Secure element as a digital pocket |
JP6751324B2 (ja) * | 2016-09-14 | 2020-09-02 | 株式会社デンソーアイティーラボラトリ | 虹彩検出装置、虹彩検出方法、およびプログラム |
KR102369412B1 (ko) | 2017-02-02 | 2022-03-03 | 삼성전자주식회사 | 홍채 인식 장치 및 방법 |
US11003936B2 (en) * | 2019-06-14 | 2021-05-11 | Tobii Ab | Method and system for controlling an eye tracking system |
WO2021171396A1 (ja) * | 2020-02-26 | 2021-09-02 | 三菱電機株式会社 | 瞳孔位置検出装置、視線検出装置、及び瞳孔位置検出方法 |
WO2021171395A1 (ja) * | 2020-02-26 | 2021-09-02 | 三菱電機株式会社 | 瞳孔位置検出装置、視線検出装置、及び瞳孔位置検出方法 |
CN112464829B (zh) * | 2020-12-01 | 2024-04-09 | 中航航空电子有限公司 | 一种瞳孔定位方法、设备、存储介质及视线追踪系统 |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001167252A (ja) * | 1999-12-10 | 2001-06-22 | Oki Electric Ind Co Ltd | 眼画像作成方法、アイリス認証方法及びアイリス認証装置 |
Family Cites Families (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4641349A (en) * | 1985-02-20 | 1987-02-03 | Leonard Flom | Iris recognition system |
US5291560A (en) * | 1991-07-15 | 1994-03-01 | Iri Scan Incorporated | Biometric personal identification system based on iris analysis |
US6419638B1 (en) * | 1993-07-20 | 2002-07-16 | Sam H. Hay | Optical recognition methods for locating eyes |
US6095989A (en) * | 1993-07-20 | 2000-08-01 | Hay; Sam H. | Optical recognition methods for locating eyes |
US5481622A (en) * | 1994-03-01 | 1996-01-02 | Rensselaer Polytechnic Institute | Eye tracking apparatus and method employing grayscale threshold values |
US5805745A (en) * | 1995-06-26 | 1998-09-08 | Lucent Technologies Inc. | Method for locating a subject's lips in a facial image |
US6144754A (en) * | 1997-03-28 | 2000-11-07 | Oki Electric Industry Co., Ltd. | Method and apparatus for identifying individuals |
CN1144152C (zh) * | 1999-07-22 | 2004-03-31 | 中国科学院自动化研究所 | 基于虹膜识别的身份鉴定方法 |
JP4469476B2 (ja) * | 2000-08-09 | 2010-05-26 | パナソニック株式会社 | 眼位置検出方法および眼位置検出装置 |
US7277561B2 (en) * | 2000-10-07 | 2007-10-02 | Qritek Co., Ltd. | Iris identification |
JP2004021406A (ja) * | 2002-06-13 | 2004-01-22 | Matsushita Electric Ind Co Ltd | 目位置特定方法及び認証装置 |
JP2004240583A (ja) * | 2003-02-04 | 2004-08-26 | Brother Ind Ltd | 画像処理装置およびそれを備えた画像読み取り装置 |
US7599524B2 (en) * | 2003-04-04 | 2009-10-06 | Sarnoff Corporation | Method and apparatus for providing a robust object finder |
US20050031173A1 (en) * | 2003-06-20 | 2005-02-10 | Kyungtae Hwang | Systems and methods for detecting skin, eye region, and pupils |
US7756301B2 (en) * | 2005-01-26 | 2010-07-13 | Honeywell International Inc. | Iris recognition system and method |
-
2004
- 2004-07-14 JP JP2004206932A patent/JP3966309B2/ja not_active Expired - Fee Related
-
2005
- 2005-05-18 EP EP05741518A patent/EP1767141A4/en not_active Withdrawn
- 2005-05-18 US US10/555,232 patent/US20070036396A1/en not_active Abandoned
- 2005-05-18 WO PCT/JP2005/009045 patent/WO2006006298A1/ja not_active Application Discontinuation
- 2005-05-18 CN CNB2005800005451A patent/CN100403973C/zh not_active Expired - Fee Related
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001167252A (ja) * | 1999-12-10 | 2001-06-22 | Oki Electric Ind Co Ltd | 眼画像作成方法、アイリス認証方法及びアイリス認証装置 |
Also Published As
Publication number | Publication date |
---|---|
US20070036396A1 (en) | 2007-02-15 |
JP3966309B2 (ja) | 2007-08-29 |
EP1767141A4 (en) | 2009-08-05 |
JP2006025969A (ja) | 2006-02-02 |
CN100403973C (zh) | 2008-07-23 |
CN1805702A (zh) | 2006-07-19 |
EP1767141A1 (en) | 2007-03-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2006006298A1 (ja) | 瞳孔検出装置および虹彩認証装置 | |
WO2006013668A1 (ja) | 瞳孔検出装置および虹彩認証装置 | |
US7347547B2 (en) | Pupil detection device and iris authentication apparatus | |
WO2006013669A1 (ja) | 瞳孔検出装置および虹彩認証装置 | |
JP6778247B2 (ja) | 眼球血管および顔認識のための画像および特徴品質、画像強化および特徴抽出、ならびにバイオメトリックシステムのための眼球血管と顔領域および/またはサブ顔領域との融合 | |
CN111507994B (zh) | 一种人像提取方法、人像提取装置及移动终端 | |
US8879847B2 (en) | Image processing device, method of controlling image processing device, and program for enabling computer to execute same method | |
US8401247B2 (en) | Image processing apparatus, biometric authentication apparatus, image processing method and recording medium | |
KR102393298B1 (ko) | 홍채 인식 방법 및 장치 | |
JP5995217B2 (ja) | 瞳孔部分を近似する楕円の検出を行う方法 | |
US20060262965A1 (en) | Pupil detection device and iris authentication apparatus | |
CN108932498A (zh) | 办公场所指纹识别鉴权机构 | |
CN111444817A (zh) | 一种人物图像识别方法、装置、电子设备和存储介质 | |
JP2008021121A (ja) | 瞳孔検出装置および虹彩認証装置ならびに瞳孔検出方法 | |
KR20180072517A (ko) | 홍채와 공막의 경계선 검출 방법 | |
KR19980020738A (ko) | 얼굴 구성요소 추출시스템 및 그 추출방법 | |
JP2006260351A (ja) | 眼鏡反射検出機能つき瞳孔検出装置および虹彩認証装置 | |
Mazur | Fast algorithm for iris detection | |
Karasek et al. | Genetic programming based classifier in viola-jones rapidminer image mining extension | |
Mohammadi et al. | Comparative Study of Skeletonization and Radial Distance Methods for Automated Finger Enumeration |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 200580000545.1 Country of ref document: CN |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2007036396 Country of ref document: US Ref document number: 10555232 Country of ref document: US |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2005741518 Country of ref document: EP |
|
AK | Designated states |
Kind code of ref document: A1 Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BW BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE EG ES FI GB GD GE GH GM HR HU ID IL IN IS KE KG KM KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NA NG NI NO NZ OM PG PH PL PT RO RU SC SD SE SG SK SL SM SY TJ TM TN TR TT TZ UA UG US UZ VC VN YU ZA ZM ZW |
|
AL | Designated countries for regional patents |
Kind code of ref document: A1 Designated state(s): BW GH GM KE LS MW MZ NA SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IS IT LT LU MC NL PL PT RO SE SI SK TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
NENP | Non-entry into the national phase |
Ref country code: DE |
|
WWW | Wipo information: withdrawn in national office |
Ref document number: DE |
|
WWP | Wipo information: published in national office |
Ref document number: 10555232 Country of ref document: US |
|
WWP | Wipo information: published in national office |
Ref document number: 2005741518 Country of ref document: EP |