WO2005109344A1 - 虹彩登録方法、虹彩登録装置および虹彩登録プログラム - Google Patents
虹彩登録方法、虹彩登録装置および虹彩登録プログラム Download PDFInfo
- Publication number
- WO2005109344A1 WO2005109344A1 PCT/JP2005/008219 JP2005008219W WO2005109344A1 WO 2005109344 A1 WO2005109344 A1 WO 2005109344A1 JP 2005008219 W JP2005008219 W JP 2005008219W WO 2005109344 A1 WO2005109344 A1 WO 2005109344A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- iris
- distribution
- authentication
- images
- image
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
Definitions
- the present invention relates to a personal authentication technology using an iris image, and particularly to a technology for improving the accuracy of iris authentication under various circumstances such as under external light such as sunlight or at night.
- Patent Document 1 discloses a basic iris authentication method in which iris image information obtained at the time of authentication is compared with stored iris image information to identify an individual.
- the pupil diameter is changed by illuminating the eyes, the illumination intensity is controlled to make the pupil a predetermined diameter, and then the iris images or feature amounts extracted from the iris images are compared.
- Patent Document 2 at the time of registration, a plurality of iris images having different pupil diameters are photographed by changing the illumination intensity, and a plurality of feature amounts respectively extracted from the photographed iris images are registered. Then, the feature amount extracted from the iris image captured at the time of authentication is compared with a plurality of registered feature amounts.
- Patent Document 3 at the time of registration, a large number of feature data is generated by giving various variations (pupil diameter, distortion, and cutout error), and a part of the feature data is selected and registered.
- Patent Document 1 Japanese Patent Publication No. 5-84166
- Patent Document 2 JP-A-2000-194855
- Patent Document 3 JP 2001-167279 A
- Patent Document 1 has a problem that it takes a certain amount of time to change the pupil diameter to a predetermined diameter, so that it takes a long time to perform authentication.
- Patent Document 2 at the time of registration, a plurality of iris images having different pupil diameters are photographed, so that the pupil diameter of the iris image at the time of authentication is any size. Can be compared with registered features having substantially the same pupil diameter. Therefore, it is not necessary to control the pupil diameter at the time of authentication, and the authentication time can be reduced as compared with Patent Document 1.
- Patent Document 2 it is described that a plurality of iris images are photographed by changing the illumination intensity, and the feature amounts extracted from the photographed images are registered, respectively. No particular mention is made of the quantity or the method of selection.
- the authentication performance is improved, but the capacity and the authentication time of the database holding the registered features are increased.
- the number of registered features is small, there is no problem with regard to the database capacity and authentication time, but depending on the selected registered features, the degree of pupil opening between registration and authentication is not significant. Due to the difference, the authentication performance may be reduced.
- the key to practical application of iris authentication is the ability to obtain an appropriate number of registered features in view of the database capacity / authentication time so that sufficient authentication accuracy can be obtained. It is considered to be one of
- an object of the present invention is to provide a technique for registering a feature amount so as to obtain stable authentication performance in personal authentication using an iris image.
- the first invention obtains a set of iris images in which the distribution of the degree of pupil opening is uniform with respect to the registrant, and evaluates the authentication performance from the set of iris images to obtain a predetermined number of iris images. It obtains the registration characteristics.
- a registered feature amount is selected from a set of iris images in which the distribution of the degree of pupil opening is uniform while evaluating the authentication performance. so Even for iris images with the degree of pupil opening, the ability to obtain stable authentication performance can be obtained.
- a set of iris images having a uniform pupil opening degree distribution is copied and deleted from the plurality of iris images so that the pupil opening degree distribution is uniform.
- a plurality of iris images may be obtained by shooting while controlling the illumination intensity so that the distribution of the degree of pupil opening becomes uniform.
- a plurality of iris images may be obtained by changing the illumination intensity and controlling the shooting interval so that the distribution of the degree of pupil opening becomes uniform.
- the second invention is to perform at least one of duplication and deletion of an iris image from a plurality of iris images of a registrant, so that the degree of pupil opening shows a predetermined distribution.
- a set is obtained, and a predetermined number of registered features are obtained from the set of iris images while evaluating authentication performance. Then, a distribution of the degree of pupil opening in a plurality of iris images obtained in an environment in which the registrant performs authentication is set as a predetermined distribution.
- a set of iris images whose pupil opening degree shows a predetermined distribution according to, for example, the life pattern of the registrant is obtained, and the authentication performance is evaluated from the set of iris images. Since a predetermined number of registered features can be obtained while paying a price, registered features that match the life pattern of the registrant can be obtained, and thus more stable authentication performance can be obtained.
- a feature amount is generated from a plurality of iris images of a registrant, and a predetermined number of registered feature amounts are selected from the feature amounts using authentication performance as an evaluation index.
- a predetermined evaluation value representing the authentication performance is calculated by weighting according to the number of features for each degree of pupil opening.
- the registered feature value is selected using the predetermined evaluation value representing the authentication performance, which is calculated by weighting according to the number of feature values for each pupil opening degree.
- the first or second invention can be performed from a plurality of iris images without previously acquiring a set of iris images having a uniform distribution of the degree of opening or a set of iris images having a predetermined degree of pupil opening. It is possible to obtain the same registered feature amount as. The invention's effect
- FIG. 1 is a flowchart showing an iris registration method according to a first embodiment of the present invention.
- FIG. 2 is a diagram showing an overall configuration of an iris authentication system in each embodiment of the present invention.
- FIG. 3 is a block diagram showing a configuration example of an iris registration device according to the first embodiment of the present invention.
- FIG. 4 is a diagram showing the appearance of a mobile phone with an authentication function as an example of an iris authentication device.
- FIG. 5 is a histogram showing an example of the distribution of the number of iris images with respect to the degree of pupil opening.
- FIG. 6 is a histogram showing a set of iris images in which the distribution of the degree of pupil opening is uniform.
- FIG. 7 is a schematic diagram showing positions of a pupil outer edge and an iris outer edge.
- FIG. 8 is a diagram expressing an iris region in an xy coordinate system.
- FIG. 9 is a diagram expressing an iris region in a polar coordinate system.
- FIG. 10 is a diagram showing an analysis band obtained by dividing an iris region into eight in the radial direction.
- FIG. 11 is a diagram showing a process of creating an iris feature amount.
- FIG. 12 is a diagram schematically showing a relationship between a Hamming distance and a difference between a pupil diameter and an iris diameter ratio.
- FIG. 13 is a diagram schematically showing an example of a distribution of pupil opening degrees in a registered image obtained by the first embodiment of the present invention.
- FIG. 14 is a diagram schematically showing another example of the distribution of the degree of pupil opening in the registered image obtained by the first embodiment of the present invention.
- FIG. 15 is a diagram showing a method of comparing feature amounts.
- FIG. 16 is a block diagram showing a configuration example of an iris registration device according to a modification of the first embodiment of the present invention.
- FIG. 17 is a flowchart showing an iris registration method according to second and third embodiments of the present invention.
- FIG. 18 is a block diagram showing a configuration example of an iris registration device according to the second and third embodiments of the present invention.
- FIG. 19 is a flowchart showing an iris registration method according to a fourth embodiment of the present invention.
- FIG. 20 is a diagram schematically showing an example of distribution of a registered image obtained according to the fourth embodiment of the present invention with respect to a pupil diameter / iris diameter ratio.
- FIG. 21 is a schematic diagram of a daytime distribution.
- FIG. 22 is a schematic diagram of nighttime distribution.
- FIG. 23 is a schematic diagram of an outdoor type distribution.
- FIG. 24 is a schematic diagram of an indoor distribution.
- FIG. 25 is a diagram schematically showing an example of a distribution of a registered image with respect to a pupil diameter / iris diameter ratio.
- the first aspect of the present invention provides, as an iris registration method, a first step of obtaining a set of iris images having a uniform distribution of the degree of pupil opening with respect to a registered person; And a second step of obtaining a predetermined number of registered feature values while evaluating authentication performance from a set of iris images obtained as described above.
- the step of obtaining a plurality of iris images is performed so that the distribution of the degree of pupil opening becomes uniform with respect to the plurality of iris images. And / or performing at least one of duplication and deletion of an iris image.
- the first step includes a step of taking a plurality of iris images while controlling the illumination intensity so that the distribution of the degree of pupil opening becomes uniform. Provide one mode of iris registration method.
- the plurality of iris images are controlled while controlling the photographing interval so that the distribution of the degree of pupil opening becomes uniform.
- the iris registration method according to the first aspect comprising the steps of:
- a feature amount is generated from each iris image belonging to the set, and the authentication performance is used as an evaluation index based on each of the feature amounts. And a step of selecting a registration feature amount.
- a sixth aspect of the present invention as an iris registration method, a first step of obtaining a plurality of iris images for a registered person and a plurality of iris images obtained in an environment in which the registered person performs authentication.
- a fourth step of obtaining a predetermined number of registered features a predetermined number of registered features.
- a feature amount is generated from each iris image belonging to the set, and the authentication performance is evaluated by using an evaluation index from each of the feature amounts. And a step of selecting a registration feature amount.
- the iris region cutout position of the iris image is changed to the cutout position of the original iris image.
- X is an integer of 1 or more and M or less registered feature amounts is obtained from M (M is an integer of 2 or more) feature amounts.
- M is an integer of 2 or more
- An evaluation process for obtaining a predetermined evaluation value representing the following is repeatedly executed while changing the X feature amounts to be temporarily selected, and based on the predetermined evaluation value obtained based on each of the evaluation processes, X
- An iris registration method according to a fifth or seventh aspect for determining the number of registered features is provided.
- a tenth aspect of the present invention provides the iris registration method according to the ninth aspect, wherein the predetermined evaluation value is a statistical value of an individual rejection rate or a distance between features at the time of authentication.
- An eleventh aspect of the present invention is the sixth aspect of the sixth aspect, wherein in the second step, the distribution is set using the distribution of the degree of pupil opening obtained from the past authentication history of the registrant. Provides an iris registration method.
- a twelfth aspect of the present invention provides the iris registration method according to the sixth aspect, wherein the registrant sets the distribution in the second step.
- a thirteenth aspect of the present invention provides, as an iris registration method, a first step of obtaining a plurality of iris images for a registered person, and a feature amount from each iris image obtained in the first step.
- a predetermined evaluation value representing the authentication performance is calculated by weighting according to the number of features for each degree of pupil opening, and a registered feature is selected using the calculated evaluation value.
- a fourteenth aspect of the present invention is directed to a iris image obtained in an environment where the registrant performs authentication.
- the method further includes a fourth step of setting a distribution of the degree of pupil opening in the image, and calculating the predetermined evaluation value in consideration of the distribution set in the fourth step in the third step.
- An iris registration method according to a thirteenth aspect is provided.
- a fifteenth aspect of the present invention is the fourteenth aspect, wherein in the fourth step, a distribution is set using a distribution of pupil opening degrees obtained from a past authentication history of the registrant. Provides an iris registration method.
- a sixteenth aspect of the present invention provides the iris registration method of the fourteenth aspect, wherein, in the fourth step, the registrant sets a distribution.
- an image storage unit for storing a plurality of iris images of a registered person, and a pupil opening for the plurality of iris images stored in the image storage unit.
- the authentication performance is evaluated from a frequency conversion unit that performs at least one of duplication and deletion of an iris image and a plurality of iris images stored in the image storage unit so that the degree has a predetermined distribution.
- a registered feature generation unit for generating a registered number of registered features.
- an image storage unit that stores a set of iris images of a person to be registered, and a feature amount from each iris image stored in the image storage unit.
- a feature value extraction unit that generates a feature value selection unit that selects a predetermined number of registered feature values from each feature value generated by the feature value extraction unit using authentication performance as an evaluation index; Provides a method in which a predetermined evaluation value representing the authentication performance is calculated by weighting according to the number of features for each degree of pupil opening, and a registered feature is selected using the calculated evaluation value.
- an image acquisition unit that acquires a set of iris images of a registered person by photographing, and a set of iris images acquired by the image acquisition unit are stored.
- An image storage unit that performs a predetermined number of registered feature values while evaluating authentication performance from a set of iris images stored in the image storage unit.
- the illuminator includes an illuminating unit having a variable illumination intensity and a photographing unit capable of continuously photographing an image.
- the photographing unit converts a plurality of iris images into a predetermined distribution of the degree of pupil opening. Controlling the illumination intensity of the illumination unit so that provide.
- an image acquisition unit that acquires a set of iris images of a registrant by photographing, and a set of iris images acquired by the image acquisition unit are stored.
- An image storage unit that performs a predetermined number of registered feature values while evaluating authentication performance from a set of iris images stored in the image storage unit.
- Is provided with an illuminating unit having a variable illumination intensity, and a photographing unit capable of continuously photographing an image, and a plurality of illumination units are provided by the imaging unit while changing the illumination intensity of the illumination unit over time.
- an iris image that is photographed while controlling the photographing interval so that the degree of pupil opening has a predetermined distribution.
- a twenty-first aspect of the present invention is directed to a iris registration program in which a computer performs at least one of duplication and deletion of an iris image from a plurality of iris images so that a degree of pupil opening is predetermined.
- a first step of obtaining a set of iris images indicating a distribution, and a predetermined number of registered features are generated from the set of iris images obtained in the first step while evaluating authentication performance.
- a computer performs a first step of generating feature values from a plurality of iris images, and each feature value generated in the first step. And performing a second step of selecting a predetermined number of registered feature amounts using the authentication performance as an evaluation index, wherein the second step includes the steps of: A feature is provided in which weighting is calculated according to the number of features for each degree of opening, and a registration feature is selected using the calculated evaluation value.
- FIG. 1 is a flowchart showing an iris registration method according to the first embodiment of the present invention. The process of FIG. 1 is executed in the iris registration device 14 described later. Steps SA0 and SA1 correspond to the first step, and steps SA2 and SA3 correspond to the second step.
- FIG. 2 is a diagram showing the overall configuration of the iris authentication system according to the present embodiment.
- the iris authentication server 11 has an iris database 12 for storing iris features of at least one registrant. Network 13. Also, the iris registration device 14 and the iris authentication device 15 are connected to the network 13 in the same manner.
- the iris registration device 14 transmits the iris feature generated at the time of registration to the iris database 12.
- the iris authentication device 15 performs personal authentication by comparing the iris feature amount generated at the time of authentication with the iris feature amount at the time of registration acquired from the iris database 12.
- FIG. 3 is a block diagram showing a configuration example of the iris registration device 14 according to the present embodiment.
- the iris registration device 14 in FIG. 3 includes an image storage unit 31 that stores a plurality of iris images photographed by a photographing device (not shown), a feature amount extraction unit 32 that performs a feature amount extraction step SA2, and a feature amount extraction unit 32.
- a part 36 is provided.
- the feature extracting unit 32, the feature storing unit 33, and the feature selecting unit 34 constitute a registered feature generating unit.
- a plurality of iris authentication servers 11 may be provided for each region or institution used, or a plurality of servers including a mirror server for distributing a load. Also, the iris database 12 is connected to the iris authentication server 11 via the network 13,
- the iris registration device 14 only captures the iris image, transmits the captured iris image to the iris authentication server 11, and generates the registration feature amount on the iris authentication server 11 side. Is also good. Further, all functions of the iris registration device 14 may be built in the iris authentication server 11.
- the iris authentication device 15 only captures the iris image for authentication, transmits the captured iris image to the iris authentication server 11, and generates the authentication feature amount in the iris authentication server 11. Is also good. The comparison with the registered feature amount is also performed in the iris server 11, and the iris authentication device 15 may receive only the authentication result. Also, the iris authentication device 15 has all the functions of the iris authentication server 11, the iris database 12, and the iris registration device 14, and the registration, the maintenance of the feature amount, and the authentication are performed by one device. What? FIG. 4 is a diagram showing the appearance of a mobile phone with an authentication function as an example of the iris authentication device 15 in the present embodiment. The mobile phone with authentication function 20 in FIG.
- a camera 21 for capturing an iris image and a lighting 22 for capturing an iris is obtained by adding a camera 21 for capturing an iris image and a lighting 22 for capturing an iris to the mobile phone.
- a monitor 23, operation buttons 24, a speaker 25, a microphone 26, an antenna 27, and the like are provided.
- the lighting 22 is constituted by one or several near-infrared LEDs.
- the monitor 23 displays the iris image being captured and the authentication result.
- the person to be authenticated performs iris authentication under various environments regardless of outdoors or indoors or day and night using a mobile phone with an authentication function as shown in FIG. And
- the registrant captures a plurality (N) of iris images in advance (SA0).
- SA0 a plurality of iris images having different pupil diameters / iris diameter ratios (indexes indicating the degree of pupil opening) are photographed.
- the photographing of the iris image may be performed by the iris registration device 14, or an image photographed by another device may be transferred to the iris registration device 14.
- the distribution of the degree of pupil opening may not be uniform.
- the obtained plurality of iris images are stored in the image storage unit 31.
- the frequency equalization step SA1 by duplicating or deleting the iris image from the plurality of iris images acquired in step SA0, the frequency is uniform, that is, the number of pupils relative to the pupil diameter / iris diameter ratio. Obtain a set of iris images having a uniform distribution of. It can be said that this set of iris images has a uniform distribution of the degree of pupil opening.
- This processing is executed by the frequency conversion unit 36.
- FIG. 5 is a histogram showing an example of the distribution of the number of iris images with respect to the pupil diameter / iris diameter ratio.
- about 300 iris images were continuously taken before and after changing the visible light intensity from “strong” to “weak” in two steps using an imaging device with a fixed number of images per hour.
- C1 to C15 on the horizontal axis indicate pupil diameter and iris diameter ratio classes, respectively, and the width of each class is 0.01.
- the vertical axis is the frequency of appearance (the number of images).
- the following method can be considered.
- a reference frequency is set, and an iris image is duplicated or deleted so that the frequency of each class matches the reference frequency. That is, for the class whose frequency is lower than the reference frequency, the iris image is copied to increase the frequency, and for the class whose frequency is higher than the reference frequency, the iris image is deleted and the frequency is reduced.
- FIG. 6 is a histogram showing a set of iris images obtained from the distribution in FIG. 5 and having a uniform distribution of the degree of pupil opening. As shown in Fig. 6, it is necessary to make the frequencies exactly the same in all the divisions.
- the feature amount extraction step SA2 the feature amount is calculated from each iris image (here, M (M is a natural number)) belonging to the iris image set having a uniform frequency obtained in step SA1. Are extracted respectively.
- This process is executed by the feature amount extraction unit 32.
- Ability to use any method for extracting the feature amount here, the method described in Japanese Patent No. 3307936 shall be used. The outline of the method is as follows.
- the outer edge of the pupil (the boundary between the pupil and the iris) and the outer edge of the iris (the boundary between the iris and the sclera) are determined, and the iris region is cut out.
- the analysis band is determined (the radial direction is divided into eight rings).
- FIG. 7 is a schematic diagram showing the positions of the pupil outer edge E1 and the iris outer edge E2
- FIG. FIG. 9 is a diagram in which an area surrounded by an iris outer edge E2 is cut out as an iris area and is expressed in an xy coordinate system.
- Fig. 9 is a diagram expressing the iris region in the r ⁇ polar coordinate system with the center of the pupil as the origin (transformation of (2)).
- the outer edge of the actual pupil and the outer edge of the iris are not exactly perfect circles. When both are approximated by a circle, the center of the pupil and the center of the iris are not concentric (they are eccentric). Thus, the effects of eccentricity, differences in the degree of pupil opening, and the effects of scaling can be absorbed.
- FIG. 10 is a diagram showing the 8-ring analysis band determined in (3)
- FIG. 11 is a diagram showing the creation of the iris feature amount in (4).
- the (b) binarization (c) is shown by applying a Gabor filter to the luminance signal (a). Although it is actually a two-dimensional signal, it is shown here in one dimension for simplicity of explanation.
- (A) is the angular direction luminance signal in one of the eight rings. Actually, a multi-scale Gabor filter is applied, and a single-scale Gabor filter has a real part and an imaginary part, but (b) and (c) show the results of applying the real part of a certain scale Gabor filter. It is.
- the position of each bit in the iris feature (c) after binarization by the sign of the Gabor filter output can be associated with a certain position on the iris image.
- a feature amount selecting step SA3 X feature amounts are selected as registered feature amounts to be finally registered from the M iris feature amounts obtained in step SA2.
- the number X of registered features is determined in advance in consideration of the capacity of the database and the permissible authentication performance for the purpose of authentication. This process is executed by the feature amount selection unit 34.
- the selection method here is as follows.
- X pieces are provisionally selected from the M feature amounts. Then, assuming that the X feature amounts temporarily selected have been registered, the remaining (M ⁇ X) feature amounts are authenticated, and a predetermined value representing the authentication performance is obtained. Find the evaluation value. Such an evaluation process is repeatedly performed while changing the X feature amounts to be temporarily selected. Then, X registered feature amounts are determined based on the evaluation values obtained in each of the repeatedly executed evaluation processes. For example, X feature values that give the highest authentication performance, that is, a predetermined evaluation value indicating the highest authentication performance, are finally selected as registered feature values.
- the predetermined evaluation value representing the authentication performance for example, the value of the personal rejection rate at the time of performing authentication (if the number of personal rejections among (M ⁇ X) feature amounts is Y, ⁇ / (Represented by (MX)) can be used. Also, statistical values of the no and mining distances as the distances between feature values at the time of authentication may be used. As the statistical value, for example, an average value, an intermediate value, a minimum value, or the like may be used. When the rejection rate or the distance between feature values is used as the evaluation value, the smaller the value, the higher the authentication performance.
- steps SA2 and SA3 a registered feature amount is obtained from the uniform-frequency iris image set obtained in step SA1 while evaluating the authentication performance.
- a registration step SA4 the registration feature amount selected in step SA3 is registered.
- the registration unit 35 transmits the registered feature amount to the iris authentication server 11 via the network 13.
- the transmitted registered features are stored in the iris database 12.
- the iris pattern changes accordingly. Therefore, when performing authentication based on a registered image, as shown in Fig. 12, when the pupil diameter and the iris diameter ratio of the iris image to be authenticated are the same as the registered image, the registered image with the smallest Hamming distance is determined. As the difference between the pupil diameter and the iris diameter ratio increases, the hamming distance increases. The degree of the increase in the hamming distance differs depending on individual differences between eyes. Strictly, even the same individual (eye) differs depending on the pupil diameter / iris diameter ratio of the registered image.
- the original iris image of the registered feature amount obtained according to the present embodiment is as shown in FIG. Pupil diameter and iris diameter ratio are almost equally spaced. This is because, when feature values are registered at equal intervals as shown in FIG. 13, the average authentication performance is the highest.
- the degree of increase in the hamming distance differs depending on the pupil diameter / iris diameter ratio of the registered image
- the original iris image of the registered feature amount obtained according to the present embodiment is, as shown in FIG.
- the diameter * iris diameter ratio is not always equal.
- a predetermined number of registered features are obtained from a set of iris images with uniform pupil opening distribution while evaluating authentication performance, as shown in FIG. In this case, or in the case shown in FIG. 14, the authentication accuracy can be maximized by the limited number of features.
- step SA1 when the iris image is duplicated in order to make the number distribution of the iris image set uniform, in step SA2, the duplicated iris image and the original iris image are copied. The exact same feature amount is extracted from the iris image.
- step SA3 for example, when the feature amount obtained from the duplicated iris image is temporarily selected, the evaluation value representing the authentication performance becomes a value that is too better than the performance actually expected. It can happen. As a result, there is a possibility that the feature amount selection may not be properly performed.
- the cutout position of the iris region (pupil outer edge and iris outer edge) is set to a very small distance from the cutout position of the original iris image. It is preferable to generate the feature amount by shifting only the amount. Specifically, for example, a part or all of a total of six parameters including a center coordinate (X, y) and a radius r representing a circle fitted to the outer edge of the pupil and the outer edge of the iris, respectively, may be shifted by a small amount. Les ,. As a result, a feature amount different from that of the original iris image can be generated from the duplicated iris image.
- the person to be authenticated captures an iris image using the iris authentication device 15.
- a portable device such as the mobile phone 20 with an authentication function in FIG. 4 is used as the iris authentication device 15
- authentication can be performed regardless of location and time. In the daytime outdoors, an iris image in a miotic state is taken, and at night or in a place with dark lighting, an iris image in a mydriatic state is taken.
- step SA2 a feature amount is extracted from the captured iris image. Since the processing here is the same as step SA2 at the time of registration, the description is omitted here.
- the comparison is performed while the feature amounts are relatively shifted in the angular direction as shown in FIG. Then, the hamming distance at the time of the shift when the hamming distance is minimized is output as a comparison result.
- the iris authentication device 15 executes processing up to feature extraction, and extracts the extracted feature amount from the iris authentication server. 11, and the iris authentication server 11 may perform the feature data acquisition and authentication.
- a predetermined number of registered feature amounts is obtained from a set of iris images in which the distribution of the degree of pupil opening is uniform while evaluating authentication performance.
- stable authentication performance can be obtained regardless of the degree of pupil opening of the iris image to be authenticated.
- the distribution of the degree of pupil opening is made uniform by duplicating or deleting an iris image, even if the distribution of the degree of pupil opening in a plurality of captured iris images is not necessarily uniform, The effects described above can be obtained.
- the distribution of the degree of pupil opening is not always uniform, and the set of iris images indicates that the authentication performance is high on average.
- N feature amounts have been extracted.
- the authentication performance of the remaining (N ⁇ X) features is calculated by assuming that X features are provisionally selected from the N features and the X features that have been temporarily selected have been registered. .
- C is the number of classes obtained by dividing the pupil diameter * iris diameter ratio
- Ni is the number of feature values belonging to class Ci
- X is a temporary rejection of the user belonging to class Ci when the feature values are temporarily registered and authenticated.
- the number is FRi
- the mining distance is HDij.
- the true rejection rate of the class Ci can be expressed as FRiZN i, and this is normalized by the number of features belonging to the class, that is, weighted by the reciprocal of the frequency. Going and calculating the rejection rate FRR, it becomes (Equation 2)
- the average value HD of the whole Hamming distance is obtained by normalizing with the quantity number, it is as shown in (Equation 3).
- FIG. 16 is a block diagram showing a configuration example of an iris registration device 14A according to the present modification.
- the same reference numerals as in FIG. 3 denote the same components as in FIG. 3, and a detailed description thereof will be omitted.
- the frequency conversion unit 36 is omitted.
- the feature amount selecting unit 34 # executes the above-described registration feature amount selection processing.
- FIG. 17 is a flowchart showing an iris registration method according to the second embodiment of the present invention. 17, the steps common to FIG. 1 are denoted by the same reference numerals as in FIG. This embodiment is also realized in an iris authentication system as shown in FIG. 2, for example. Step SB1 corresponds to the first step.
- FIG. 18 is a block diagram showing a configuration example of the iris registration device 14 B according to the present embodiment.
- components common to FIG. 3 are denoted by the same reference numerals as in FIG. Compared to Fig. 3, the frequency conversion unit 36 is omitted, and instead, an illumination unit 37 configured to illuminate visible light and control the illumination intensity enables continuous imaging.
- a photographing section 38 and a control section 39 for controlling the lighting section 37 and the photographing section 28 are provided.
- the illumination unit 37, the imaging unit 38, and the control unit 39 constitute an image acquisition unit, and an imaging step SB1 is executed.
- the registrant photographs a plurality of iris images.
- the illumination intensity is controlled so that the distribution of the degree of pupil opening becomes uniform.
- the illumination unit 37 can set the illumination intensity in a plurality of levels ( ⁇ types) L1 to LP. Let's say.
- the pupil diameter / iris diameter ratio is divided into P classes Cl to CP according to the illumination intensities L1 to LP in advance, and the number of iris images per class is determined in advance. Then, continuous photographing is started with the first illumination intensity L1, and the pupil diameter / iris diameter ratio is calculated for each photographed image.
- the iris images whose pupil diameter and iris diameter ratio are included in the class C1 are stored in the image storage unit 31, and the iris images not included are discarded without saving.
- the illumination intensity is changed to L2, and shooting is performed in the same manner.
- a predetermined number of iris images are stored in the image storage unit 31 for all the classes C1 to CP, the photographing ends.
- a set of iris images having a uniform distribution of the degree of pupil opening can be obtained by imaging.
- a feature amount extraction step SA2 a feature amount selection step SA3, and a registration step SA4 are executed on the obtained set of iris images.
- the processing in steps SA2 to SA4 is the same as in the first embodiment, and a description thereof will not be repeated.
- the distribution of the degree of pupil opening can be made uniform at the stage of capturing an iris image, so that the frequency equalization processing shown in the first embodiment can be performed. Is no longer necessary.
- a set of iris images having a uniform distribution of the degree of pupil opening is obtained by imaging by controlling the imaging interval instead of controlling the illumination intensity. is there.
- the iris registration method and the iris registration device according to the present embodiment are the same as those shown in FIGS. 17 and 18.
- the registrant photographs a plurality of iris images.
- the imaging interval is controlled so that the distribution of the degree of pupil opening becomes uniform.
- the photographing unit 38 is configured so that the number of photographed images per time can be controlled.
- the illumination unit 37 is configured so that the illumination intensity can be controlled, as in the second embodiment.
- FIG. 5 The histogram in Fig. 5 shown above shows that approximately 300 shots were taken continuously before and after changing the illumination intensity from two levels to "weak” from "high” to “low” using a shooting device with a fixed shooting interval. Sheets It is obtained from an iris image.
- the reason why the ratio of the pupil diameter to the iris diameter is relatively large is that the number of images is large because imaging was continued even after the subject's pupil completely adjusted to the ⁇ weak '' visible light intensity. . Also, the number is not constant even when the pupil diameter / iris diameter ratio is relatively small or in the middle range. This seems to be because the degree of pupil opening does not necessarily change linearly with time.
- the pupil diameter / iris diameter ratio is divided into a plurality of (P) classes C1 to CP, and the number of iris images per class is determined in advance.
- the temporal change of the average pupil diameter of each person or a plurality of persons is measured in advance in accordance with the illumination control used for photographing.
- the number of shots per time is calculated from the time change of the pupil diameter and the classes C1 to CP, and by controlling the shooting interval of the shooting unit 38, the distribution of the degree of pupil opening is uniform.
- a collection of images can be obtained by photography.
- a feature amount extraction step SA2 a feature amount selection step SA3, and a registration step SA4 are performed on the obtained set of iris images.
- the processing in steps SA2 to SA4 is the same as in the first embodiment, and a description thereof will not be repeated.
- the distribution of the degree of pupil opening can be made uniform at the stage of capturing an iris image. Is no longer necessary.
- FIG. 19 is a flowchart of the iris registration method according to the fourth embodiment of the present invention.
- steps common to FIG. 1 are denoted by the same reference numerals as in FIG.
- This embodiment is also realized in an iris authentication system as shown in FIG. 2, for example. It is executed by the iris registration device 14 as shown in FIG. Step SA0 corresponds to the first step, step SC1 corresponds to the second and third steps, and steps SA2 and SA3 correspond to the fourth step.
- the registrant previously captures a plurality (N) of iris images having different pupil diameter * iris diameter ratios. (SA0).
- the photographing of the iris image may be performed by the iris registration device 14, or an image captured by another device may be transferred to the iris registration device 14.
- the distribution of the degree of pupil opening may or may not be substantially uniform. That is, any of the photographing methods described in the first to third embodiments can be used.
- the obtained plural iris images are stored in the image storage unit 31.
- step SC1 the distribution of the degree of pupil opening in a plurality of iris images obtained in an environment where the registrant performs authentication is set. Then, by duplicating or deleting the iris images from the plurality of iris images acquired in step SA0, a set of iris images in which the distribution of the number of pupils with respect to the iris diameter ratio is a predetermined distribution is obtained. . It can be said that this set of iris images indicates that the degree of pupil opening shows a predetermined distribution. This processing is executed by the frequency conversion unit 36A.
- FIG. 20 is a histogram showing an example of the distribution of the number of iris images with respect to the pupil diameter / iris diameter ratio after execution of step SC1.
- the number of images having a small pupil diameter / iris diameter ratio is relatively large toward a person who frequently performs iris authentication outdoors.
- the conversion method here is the same as in the first embodiment.For example, for a class whose number is less than the target, the iris image is duplicated to increase the number, while a class whose number is larger than the target is used. Deletes the iris image to reduce the number.
- various distributions can be considered as the predetermined distribution.
- distributions such as daytime Z night type, outdoor type Z indoor type, etc. may be created in advance, assuming the user's life pattern.
- a distribution having a large frequency of a class having a small pupil diameter / iris diameter ratio as shown in FIG. 21 can be used.
- a distribution having a large frequency in a class having a large pupil diameter / iris diameter ratio as shown in FIG. 22 can be used.
- a distribution with a large frequency in both the class with a small pupil diameter / iris diameter ratio and the class with a large iris diameter ratio as shown in Fig. it can.
- the user can select an arbitrary distribution from the distributions created in advance such as day / night type, outdoor type / Z indoor type, and uniform distribution. An interface may be used.
- the registrant who simply selects from the distribution shapes created in advance may input the distribution shape itself.
- a feature value extraction step SA2 a feature value selection step SA3, and a registration step SA4 are performed on the obtained set of iris images.
- the processing in steps SA2 to SA4 is the same as in the first embodiment, and a description thereof will not be repeated.
- the pupil diameter * iris is used as the feature value to be registered. Those having a small diameter ratio are easily selected. Therefore, for a person who frequently performs iris authentication outdoors, iris authentication performance particularly outdoors is improved.
- the operation at the time of authentication is the same as that of the first embodiment, and a description thereof will be omitted.
- the present embodiment while evaluating the authentication performance from the set of iris images in which the distribution of the degree of pupil opening has a predetermined distribution, for example, in accordance with the life pattern of the registrant, A predetermined number of registered features are obtained.
- a stable authentication performance can be obtained for an iris image captured by the registrant in his or her own life pattern.
- the distribution of the degree of pupil opening is made to be a predetermined distribution by duplicating or deleting the iris image, the distribution of the degree of pupil opening in a plurality of captured iris images can be determined as described above. The effect obtained can be obtained.
- the accumulated authentication history can be used for the next and subsequent registrations.
- a number distribution as shown in FIG. 20 may be used. That is, the degree of pupil opening is calculated for an iris image captured at the time of authentication, and the calculated degree is stored in a plurality of authentication operations, whereby a number distribution as shown in FIG. 20 can be obtained. For example, in the case of a user who frequently performs authentication in a bright environment such as the daytime, as shown in FIG. On the other hand, in the case of a user who frequently performs authentication in a dark environment such as at night, the frequency of a class having a large ratio of pupil diameter to iris diameter increases.
- the difference between the distribution shape used at the time of registration and the distribution shape obtained from the authentication history becomes larger than a predetermined threshold, re-registration is automatically performed using the distribution shape with the obtained authentication history power. It may be performed.
- only the distribution shape data obtained from the authentication history is transmitted to the iris registration device, and is stored in the image storage unit 31 at the time of the first registration.
- the registered feature amount may be re-acquired using the iris image set or the feature amount set stored in the feature amount storage unit 33 and the distribution shape obtained from the authentication history.
- the registered feature amount may be extracted from the iris image used for the authentication using only the number distribution, or the feature amount used at the time of the authentication itself may be used as the registered feature amount.
- the desired distribution is evaluated with respect to the evaluation value for each class.
- weighting may be performed in accordance with the number of features belonging to the class, and the overall evaluation value may be calculated. Specifically, for example, the following processing is performed.
- N feature values have been extracted.
- X features are temporarily selected from the N features, and the X features that are temporarily selected have been registered, the authentication performance of the remaining (N-X) features is calculated. .
- C is the number of classes obtained by dividing the pupil diameter * iris diameter ratio
- Ni is the number of feature values belonging to class Ci
- rejection of individuals belonging to class Ci is performed when temporarily registering X feature values and authenticating
- the number is FRi
- the mining distance is HDij.
- the rejection rate of class Ci can be expressed as FRiZN i. This is weighted by the number of features Ni belonging to class Ci in the iris image acquired in step SAO and the weight Wi for class Ci in the desired distribution, and the rejection rate FRR is obtained as shown in (Equation 4). Become.
- the desired distribution is a discrete distribution as shown in FIG. 20, class Ci is used as weight Wi. Can be used.
- the weight Wi is, for example, the pupil diameter representing the class Ci.
- the function value f (Ri) at the representative value Ri of the iris diameter ratio Can be used.
- the value (Equation 5) obtained by integrating the continuous function f (r) within the range of the pupil diameter and the iris diameter ratio corresponding to the class Ci can be used.
- the frequency is not affected by the bias of the frequency for each class.
- an evaluation value corresponding to a desired distribution can be calculated. Therefore, regardless of the degree of pupil opening of the iris image to be authenticated, it is possible to obtain a predetermined number of registered feature amounts that can provide stable authentication performance in an assumed environment.
- Each step of the iris registration method according to the present invention may be realized in whole or in part using dedicated hardware, or may be realized in software by a computer program. Absent. That is, the iris registration method according to the present invention The present invention can be realized by an apparatus including a computer that executes a program for realizing the method, and a program for realizing the method is recorded on a computer-readable recording medium, and recorded on the recording medium. It can be realized by running a program on a computer.
- the present invention provides a registration method for enabling personal authentication with a low rejection rate under various brightness, so that, for example, a mobile phone 'PDA or the like is equipped with an iris authentication function, It is effective when performing mopile authentication for e-commerce.
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Ophthalmology & Optometry (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Collating Specific Patterns (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
Description
Claims
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2006512984A JP3940759B2 (ja) | 2004-05-10 | 2005-04-28 | 虹彩登録方法、虹彩登録装置および虹彩登録プログラム |
US11/172,640 US7623686B2 (en) | 2004-05-10 | 2005-07-01 | Techniques and apparatus for increasing accuracy of iris authentication by utilizing a plurality of iris images |
US12/536,754 US8064649B2 (en) | 2004-05-10 | 2009-08-06 | Techniques and apparatus for increasing accuracy of iris authentication by utilizing a plurality of iris images having different pupil diameter/iris diameter ratios |
US13/230,900 US8208693B2 (en) | 2004-05-10 | 2011-09-13 | Techniques and apparatus for increasing accuracy of iris authentication by utilizing a plurality of iris images having different pupil diameter/iris diameter ratios |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2004139778 | 2004-05-10 | ||
JP2004-139778 | 2004-05-10 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US11/172,640 Continuation US7623686B2 (en) | 2004-05-10 | 2005-07-01 | Techniques and apparatus for increasing accuracy of iris authentication by utilizing a plurality of iris images |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2005109344A1 true WO2005109344A1 (ja) | 2005-11-17 |
Family
ID=35239479
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2005/008219 WO2005109344A1 (ja) | 2004-05-10 | 2005-04-28 | 虹彩登録方法、虹彩登録装置および虹彩登録プログラム |
Country Status (4)
Country | Link |
---|---|
US (3) | US7623686B2 (ja) |
JP (1) | JP3940759B2 (ja) |
CN (1) | CN100498837C (ja) |
WO (1) | WO2005109344A1 (ja) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2018206239A (ja) * | 2017-06-08 | 2018-12-27 | シャープ株式会社 | 認証装置および認証方法 |
Families Citing this family (49)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2004042658A1 (ja) * | 2002-11-07 | 2004-05-21 | Matsushita Electric Industrial Co., Ltd. | 個人認証方法、虹彩登録装置、虹彩認証装置および個人認証プログラム |
US8090157B2 (en) | 2005-01-26 | 2012-01-03 | Honeywell International Inc. | Approaches and apparatus for eye detection in a digital image |
US7593550B2 (en) | 2005-01-26 | 2009-09-22 | Honeywell International Inc. | Distance iris recognition |
US7761453B2 (en) | 2005-01-26 | 2010-07-20 | Honeywell International Inc. | Method and system for indexing and searching an iris image database |
US8705808B2 (en) | 2003-09-05 | 2014-04-22 | Honeywell International Inc. | Combined face and iris recognition system |
US8442276B2 (en) | 2006-03-03 | 2013-05-14 | Honeywell International Inc. | Invariant radial iris segmentation |
US8064647B2 (en) | 2006-03-03 | 2011-11-22 | Honeywell International Inc. | System for iris detection tracking and recognition at a distance |
US8098901B2 (en) | 2005-01-26 | 2012-01-17 | Honeywell International Inc. | Standoff iris recognition system |
US9020854B2 (en) | 2004-03-08 | 2015-04-28 | Proxense, Llc | Linked account system using personal digital key (PDK-LAS) |
US9113464B2 (en) | 2006-01-06 | 2015-08-18 | Proxense, Llc | Dynamic cell size variation via wireless link parameter adjustment |
US11206664B2 (en) | 2006-01-06 | 2021-12-21 | Proxense, Llc | Wireless network synchronization of cells and client devices on a network |
WO2007101275A1 (en) | 2006-03-03 | 2007-09-07 | Honeywell International, Inc. | Camera with auto-focus capability |
JP2009529197A (ja) | 2006-03-03 | 2009-08-13 | ハネウェル・インターナショナル・インコーポレーテッド | モジュールバイオメトリクス収集システムアーキテクチャ |
KR101299074B1 (ko) | 2006-03-03 | 2013-08-30 | 허니웰 인터내셔널 인코포레이티드 | 홍채 인코딩 시스템 |
GB2448653B (en) | 2006-03-03 | 2011-03-23 | Honeywell Int Inc | Single lens splitter camera |
JP4738488B2 (ja) | 2006-03-03 | 2011-08-03 | ハネウェル・インターナショナル・インコーポレーテッド | 画像品質メトリックを有する虹彩認識システム |
US7904718B2 (en) | 2006-05-05 | 2011-03-08 | Proxense, Llc | Personal digital key differentiation for secure transactions |
PL380581A1 (pl) * | 2006-09-07 | 2008-03-17 | Naukowa I Akademicka Sieć Komputerowa | Sposób testowania żywotności oka i urządzenie do testowania żywotności oka |
US20100104182A1 (en) * | 2007-02-28 | 2010-04-29 | Gondek Jay S | Restoring and synthesizing glint within digital image eye features |
JP5012092B2 (ja) * | 2007-03-02 | 2012-08-29 | 富士通株式会社 | 生体認証装置、生体認証プログラムおよび複合型生体認証方法 |
US8063889B2 (en) | 2007-04-25 | 2011-11-22 | Honeywell International Inc. | Biometric data collection system |
US20090060286A1 (en) * | 2007-09-04 | 2009-03-05 | General Electric Company | Identification system and method utilizing iris imaging |
WO2009062194A1 (en) | 2007-11-09 | 2009-05-14 | 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 |
US20090216092A1 (en) * | 2008-02-26 | 2009-08-27 | Acunetx, Inc. | System for analyzing eye responses to accurately detect deception |
WO2009126732A2 (en) | 2008-04-08 | 2009-10-15 | Proxense, Llc | Automated service-based order processing |
US8436907B2 (en) | 2008-05-09 | 2013-05-07 | Honeywell International Inc. | Heterogeneous video capturing system |
US8213782B2 (en) | 2008-08-07 | 2012-07-03 | Honeywell International Inc. | Predictive autofocusing system |
US8090246B2 (en) | 2008-08-08 | 2012-01-03 | Honeywell International Inc. | Image acquisition system |
CN101727574A (zh) * | 2008-10-17 | 2010-06-09 | 深圳富泰宏精密工业有限公司 | 虹膜识别系统及方法 |
US8280119B2 (en) | 2008-12-05 | 2012-10-02 | Honeywell International Inc. | Iris recognition system using quality metrics |
JP2010286937A (ja) * | 2009-06-10 | 2010-12-24 | Hitachi Ltd | 生体認証方法、及び、生体認証に用いるクライアント端末、認証サーバ |
US8472681B2 (en) | 2009-06-15 | 2013-06-25 | Honeywell International Inc. | Iris and ocular recognition system using trace transforms |
US8630464B2 (en) | 2009-06-15 | 2014-01-14 | Honeywell International Inc. | Adaptive iris matching using database indexing |
JP2013518319A (ja) * | 2010-01-22 | 2013-05-20 | イリテック インコーポレイテッド | 虹彩サイズの異なる複数の虹彩イメージを用いた虹彩認識装置及び方法 |
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 |
US8742887B2 (en) | 2010-09-03 | 2014-06-03 | Honeywell International Inc. | Biometric visitor check system |
US9265450B1 (en) | 2011-02-21 | 2016-02-23 | Proxense, Llc | Proximity-based system for object tracking and automatic application initialization |
US9405898B2 (en) | 2013-05-10 | 2016-08-02 | Proxense, Llc | Secure element as a digital pocket |
CN103544420B (zh) * | 2013-08-15 | 2016-05-11 | 马建 | 用于智能眼镜的防伪虹膜身份认证方法 |
CN105260698B (zh) * | 2015-09-08 | 2019-01-25 | 山东眼神智能科技有限公司 | 对虹膜图像进行定位的方法和装置 |
US10820840B2 (en) * | 2016-04-28 | 2020-11-03 | Joshua Noel Hogan | Optical coherence tomography for identity verification |
IL251596A0 (en) * | 2017-04-05 | 2017-06-29 | Robin Koch | System and method for photographing a user's iris |
US11475446B2 (en) | 2018-12-28 | 2022-10-18 | Mastercard International Incorporated | System, methods and computer program products for identity authentication for electronic payment transactions |
US11494769B2 (en) * | 2019-01-10 | 2022-11-08 | Mastercard International Incorporated | System, methods and computer program products for identity authentication for electronic payment transactions |
CN110688951B (zh) * | 2019-09-26 | 2022-05-31 | 上海商汤智能科技有限公司 | 图像处理方法及装置、电子设备和存储介质 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH08504979A (ja) * | 1991-07-15 | 1996-05-28 | ドーグマン、ジョン・ジー | 虹彩解析に基づく生体測定学的人物識別システム |
JP2000194855A (ja) * | 1998-12-25 | 2000-07-14 | Oki Electric Ind Co Ltd | 個体識別システム |
JP2001167279A (ja) * | 1999-12-14 | 2001-06-22 | Oki Electric Ind Co Ltd | 個体識別装置 |
JP2004167227A (ja) * | 2002-11-07 | 2004-06-17 | Matsushita Electric Ind Co Ltd | 個人認証方法、虹彩登録装置、虹彩認証装置および個人認証プログラム |
JP5084166B2 (ja) * | 2006-03-29 | 2012-11-28 | 中国電力株式会社 | 水素製造装置 |
Family Cites Families (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4641349A (en) | 1985-02-20 | 1987-02-03 | Leonard Flom | Iris recognition system |
US5130667A (en) | 1991-04-11 | 1992-07-14 | Bell Communications Research Inc. | Differential transimpedance amplifier |
JP3047555B2 (ja) | 1991-09-30 | 2000-05-29 | 松下電器産業株式会社 | 掃除機の床ノズル及び自走式掃除機 |
EP0944875B1 (en) * | 1997-09-16 | 2003-02-19 | Invisitech Corporation | Personal identification system using multiple parameters having low cross-correlation |
US6289113B1 (en) * | 1998-11-25 | 2001-09-11 | Iridian Technologies, Inc. | Handheld iris imaging apparatus and method |
JP2001034754A (ja) * | 1999-07-19 | 2001-02-09 | Sony Corp | 虹彩認証装置 |
US7277561B2 (en) * | 2000-10-07 | 2007-10-02 | Qritek Co., Ltd. | Iris identification |
JP3586431B2 (ja) * | 2001-02-28 | 2004-11-10 | 松下電器産業株式会社 | 個人認証方法および装置 |
KR100456619B1 (ko) * | 2001-12-05 | 2004-11-10 | 한국전자통신연구원 | 에스.브이.엠(svm)을 이용한 얼굴 등록/인증 시스템 및방법 |
EP1600898B1 (en) * | 2002-02-05 | 2018-10-17 | Panasonic Intellectual Property Management Co., Ltd. | Personal authentication method, personal authentication apparatus and image capturing device |
WO2004042658A1 (ja) | 2002-11-07 | 2004-05-21 | Matsushita Electric Industrial Co., Ltd. | 個人認証方法、虹彩登録装置、虹彩認証装置および個人認証プログラム |
-
2005
- 2005-04-28 JP JP2006512984A patent/JP3940759B2/ja active Active
- 2005-04-28 CN CNB2005800049638A patent/CN100498837C/zh active Active
- 2005-04-28 WO PCT/JP2005/008219 patent/WO2005109344A1/ja active Application Filing
- 2005-07-01 US US11/172,640 patent/US7623686B2/en active Active
-
2009
- 2009-08-06 US US12/536,754 patent/US8064649B2/en active Active
-
2011
- 2011-09-13 US US13/230,900 patent/US8208693B2/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH08504979A (ja) * | 1991-07-15 | 1996-05-28 | ドーグマン、ジョン・ジー | 虹彩解析に基づく生体測定学的人物識別システム |
JP2000194855A (ja) * | 1998-12-25 | 2000-07-14 | Oki Electric Ind Co Ltd | 個体識別システム |
JP2001167279A (ja) * | 1999-12-14 | 2001-06-22 | Oki Electric Ind Co Ltd | 個体識別装置 |
JP2004167227A (ja) * | 2002-11-07 | 2004-06-17 | Matsushita Electric Ind Co Ltd | 個人認証方法、虹彩登録装置、虹彩認証装置および個人認証プログラム |
JP5084166B2 (ja) * | 2006-03-29 | 2012-11-28 | 中国電力株式会社 | 水素製造装置 |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2018206239A (ja) * | 2017-06-08 | 2018-12-27 | シャープ株式会社 | 認証装置および認証方法 |
Also Published As
Publication number | Publication date |
---|---|
US20050249385A1 (en) | 2005-11-10 |
US20110317883A1 (en) | 2011-12-29 |
JPWO2005109344A1 (ja) | 2008-03-21 |
US8208693B2 (en) | 2012-06-26 |
JP3940759B2 (ja) | 2007-07-04 |
US8064649B2 (en) | 2011-11-22 |
CN1947150A (zh) | 2007-04-11 |
CN100498837C (zh) | 2009-06-10 |
US7623686B2 (en) | 2009-11-24 |
US20090296996A1 (en) | 2009-12-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2005109344A1 (ja) | 虹彩登録方法、虹彩登録装置および虹彩登録プログラム | |
US10445574B2 (en) | Method and apparatus for iris recognition | |
KR101051848B1 (ko) | 개인인증방법, 홍채등록장치 및 홍채인증장치 | |
CN103383723B (zh) | 用于生物特征验证的电子欺骗检测的方法和系统 | |
WO2014084249A1 (ja) | 顔認証装置、認証方法とそのプログラム、情報機器 | |
CN104504408A (zh) | 一种人脸识别比对方法和实现该方法的系统 | |
US20220189206A1 (en) | Iris authentication device, iris authentication method, and recording medium | |
CN109871845A (zh) | 证件图像提取方法及终端设备 | |
CN106815803B (zh) | 图片的处理方法及装置 | |
CN208351494U (zh) | 人脸识别系统 | |
CN105049710B (zh) | 一种大视角摄像头控制方法及用户终端 | |
CN112199530A (zh) | 多维度脸库图片自动更新方法、系统、设备及介质 | |
CN106156739B (zh) | 一种基于脸部轮廓分析的证件照耳朵检测与提取方法 | |
CN114898402A (zh) | 一种融合人脸和人体特征的行人重识别方法、装置及介质 | |
CN110321378A (zh) | 一种移动监控图像识别系统及方法 | |
Masaoud et al. | A review paper on ear recognition techniques: models, algorithms and methods | |
Benlamoudi | Multi-modal and anti-spoofing person identification | |
JP3639291B2 (ja) | 個人認証方法、虹彩登録装置、虹彩認証装置および個人認証プログラム | |
CN109213889A (zh) | 一种客户信息合并的方法及装置 | |
CN114299569A (zh) | 一种基于眼球运动的安全人脸认证方法 | |
Jing et al. | An overview of multimode biometric recognition technology | |
JP2004362619A (ja) | 虹彩登録装置 | |
JP3574653B2 (ja) | 虹彩コード化方法、個人認証方法、虹彩コード登録装置、虹彩認証装置、および虹彩認証プログラム | |
CN116311395B (zh) | 指纹识别的方法和装置 | |
Mohammed et al. | Performance Evolution Ear Biometrics Based on Features from Accelerated Segment Test |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 11172640 Country of ref document: US |
|
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 JP KE KG KM KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NA 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 | ||
DPEN | Request for preliminary examination filed prior to expiration of 19th month from priority date (pct application filed from 20040101) | ||
WWE | Wipo information: entry into national phase |
Ref document number: 2006512984 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 200580004963.8 Country of ref document: CN |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
WWW | Wipo information: withdrawn in national office |
Country of ref document: DE |
|
122 | Ep: pct application non-entry in european phase |