KR20200079989A - Apparatus and Method for Recognizing Fake Iris By Using Minutia Data Variation - Google Patents

Abstract

Disclosed are an apparatus for discriminating a fake iris using a feature point variation and a method thereof. The apparatus for discriminating a fake iris requests at least one operation to change a position of the iris or prevent the iris from being seen by a user attempting iris authentication, and then determines whether the iris is a fake iris being authenticated based on whether a variation exists in a feature point extracted from a photographed image.

Description

Apparatus and Method for Recognizing Fake Iris By Using Minutia Data Variation}

The present invention relates to a iris discrimination apparatus and method for discriminating a counterfeit iris from a technique related to biometrics using an iris.

Iris Recognition is one of the things that has attracted attention as a means of personal authentication. The iris is the tissue that forms the pupil of the animal by surrounding the pupil, and is the most complex and sophisticated fiber tissue in the human body. Each person has a different iris pattern, and the iris of the same person's left and right eyes is also different. Like fingerprints, the pattern of the iris does not change with age, so it can be used as a personal authentication method.

Iris authentication uses a method of photographing the iris with a camera and comparing the features of the iris. On the other hand, personal authentication is mainly used in areas where security is important, such as access control, e-commerce, financial transactions, personal computer (PC) security, and office payment systems, so forged irises are not registered users. It is most important to distinguish effectively (hereinafter referred to as'forged iris').

Until recently, it has been recognized that it is difficult to acquire an iris image of a specific person, and it is almost impossible to make a counterfeit iris. Nevertheless, counterfeit irises such as paper with iris images printed with high-performance printers or bills with iris images printed on them have been found.

When such a counterfeit iris is input to a conventional iris recognition apparatus, an iris image similar to a bioiris is obtained, and there is room for processing without distinction from the bioiris through a process of extracting a feature point.

[Related inventions]

1. Counterfeit iris detection system and method for detecting counterfeit iris by fusing multiple spectroscopic images (Republic of Korea Patent No. 711110)

In the present invention, a method of detecting a fake iris using two or more iris images photographed in multi-spectral bands is proposed. In order to implement the present invention, a multi-spectral iris image photographing apparatus capable of photographing images of various frequency bands is required.

An object of the present invention is to provide a counterfeit iris discrimination apparatus and method capable of discriminating a counterfeit iris and a biometric fingerprint by using a variation of a feature point extracted from a series of eye images taken in series.

In order to achieve the above object, a method for determining a counterfeit iris according to the present invention includes: generating a portion of an eye by photographing a user attempting authentication by a first camera unit; Repeating a process of extracting an iris portion from a plurality of the eye portion images generated by the first camera unit at a predetermined frame rate and extracting feature points of the iris; During the repetition step, if a position of a feature point is different among the plurality of eye part images or a change in a feature point in which a feature point is not extracted is detected, the iris being authenticated is determined as a living body, and if a change in the feature point is not detected, it is determined as a fake iris. It includes the steps.

User guide for counterfeit identification

According to an embodiment, the method for discriminating a counterfeit iris of the present invention may further include displaying a guide for requesting at least one operation of changing the location of the iris or preventing the iris from being visible.

In this case, the repeating step is preferably performed for a predetermined measurement time after the step of displaying the guidance. Further, the guidance may be, for example, a request to blink the eye or a request to stare in a different direction by rolling the pupil.

In addition, in the case of guiding the user, it is preferable to detect a change in the feature point among the eye part images generated in the remaining frames except for the first frame and the last frame of the measurement time.

Meanwhile, the displaying of the guide is preferably performed when the user's eye is recognized while repeating the step of generating the eye portion image.

Save log

The method for discriminating a forged iris of the present invention may further include the step of generating a face image of the user by the second camera unit and storing the result together with the determination result of the determining.

Counterfeit iris discrimination device

The present invention also extends to a counterfeit iris discrimination device that performs the above-described counterfeit iris discrimination method. The counterfeit iris discrimination apparatus of the present invention includes a first camera unit for photographing a user attempting authentication at a predetermined frame rate to generate a plurality of eye part images; An iris detection unit extracting an iris portion from each of the plurality of eye portion images; A feature point extracting unit for extracting a feature point of the iris from the iris portion; It includes a counterfeit judgment.

The counterfeit determination unit judges the iris being authenticated as a living body and detects the erroneous image based on the extraction result of the feature point extracting unit, if the position of the feature point is different among the plurality of eye parts images or a variation of the feature point in which the feature point is not extracted is detected. If not, the counterfeit determination is performed by judging by the counterfeit iris.

The counterfeit iris discrimination device according to the present invention is based on whether there is a variation in the feature points extracted from the captured image after requesting at least one operation to change the location of the iris or to prevent the iris from being seen by the user who attempts the iris authentication. It is possible to determine whether the iris being attempted to be authenticated is a counterfeit iris.

Since the counterfeit iris discrimination method of the present invention does not illuminate the user who attempts authentication, the user does not dazzle the light or cause discomfort to the user.

In addition, the method of discriminating the forged iris of the present invention is very simple because the separate hardware device is not used for discriminating the forged iris.

1 is a block diagram of a device for discriminating a counterfeit iris of the present invention;
Figure 2 is a flow chart provided in the description of the forgery iris discrimination method of the present invention,
3 is a block diagram of an apparatus for discriminating a forged iris according to another embodiment of the present invention.

Hereinafter, the present invention will be described in more detail with reference to the drawings.

1, the forged iris discrimination apparatus 100 of the present invention includes a user interface 101, an image acquisition module 110 and a control module 130.

The user interface 101 is a means for displaying various guides for discriminating irises described below to a user in a visual way or outputting it to the user in an audible way. For example, a display means such as an LCD or LED or a voice output means such as a speaker may correspond to the user interface 101.

The image acquisition module 110 includes at least one light source 111 and at least one first camera unit 113 to acquire an iris image.

The light source 111 emits light of a predetermined wavelength toward the user's eyes in order to photograph an image of the user's eyes. The wavelength of the light emitted from the light source 111 may be any band and white light may be used, but infrared light is preferred. When the infrared light source 111 is used, the first camera unit 113 must use an infrared filter, so that the influence of external natural light can be excluded, and the light source 111 can provide sufficient illumination.

The first camera unit 113 includes an lens 113a and an image sensor 113b, and generates an eye portion image as an image emitted from the light source 111 and reflected by the user's eye portion and incident. When the light source 111 emits infrared rays, the first camera unit 113 may further include a filter that passes the infrared region.

Depending on the angle of view of the first camera unit 113 formed by the lens 113a, the first camera unit 113 may be configured to photograph one eye of the user or may be configured to photograph both eyes.

When the first camera unit 113 is configured to photograph one eye, the forged iris discrimination device 100 includes two first camera units 113 arranged side by side to shoot two eyes, respectively. You may.

The first camera unit 113 photographs the user's eye part at a predetermined frame rate for iris recognition, and provides the obtained plurality of eye part images to the control module 130.

Meanwhile, as described below, in order to confirm the user's authentication attempt, the first camera unit 113 periodically photographs the front, in which case, the first camera unit 113 may photograph at a lower speed than the predetermined frame rate.

The control module 130 includes an iris detection unit 131, a feature point extraction unit 133, and a counterfeit determination unit 135, and controls the overall operation of the forged iris discrimination device 100 of the present invention.

The iris detection unit 131 performs a pre-processing process for discriminating the iris, and extracts the iris portion from the eye portion image provided by the image acquisition module 110 at a predetermined frame rate. The iris partial extraction can be applied to various methods known in the art. For example, since the eye part image includes all of the eyebrows and eyelids, including the user's pupil, the edge of the pupil is detected through edge detection in the eye part image, and the position of the pupil through the Hough Transform The position of the iris can be detected by detecting.

On the other hand, a method of confirming the user's authentication attempt can be various methods including a user operating a button or confirming access with a proximity sensor, and one of the methods uses an image captured by the image acquisition module 110. will be. In this case, the iris detection unit 131 checks the degree to which the eye portion image is input from the image provided by the image acquisition module 110 and notifies the counterfeit determination unit 135 to check whether the user attempts to authenticate. have. At this time, the image processing may not be a processing degree for extracting a feature point from the image of the eye, but may also be performed, for example, to recognize a facial contour.

The feature point extraction unit 133 extracts information for iris authentication by extracting feature point data from the iris portion detected by the iris detection unit 131. The feature point data extracted by the feature point extracting unit 133 includes a feature point of an iris pattern unique to the user. In addition, iris feature points can be extracted by applying various information and extraction methods known in the art.

The forgery determination unit 135 performs forgery determination based on the feature point data provided by the feature point extraction unit 133. The basic method of forgery discrimination is to check whether there is an error image in a series of images of a plurality of eye parts generated during a measurement period. Here, the error image refers to an image in which a feature point and a feature point are extracted from different eye part images during a measurement period or feature points are not extracted at all. If an error image is detected, the iris being authenticated is regarded as a living body. On the contrary, if no error image is detected, the iris being authenticated is considered as a counterfeit iris. The method of determining the counterfeit iris of the counterfeit determination unit 135 will be described again below with reference to FIG. 2.

How to judge counterfeit iris

In the basic method of determining the forged iris of the present invention, the first camera unit 113 photographs a user who attempts authentication to generate an eye portion image, and the iris detection unit 131 sets the frame rate at which the first camera unit 113 is preset. It is performed while extracting the iris portion from the plurality of eye portion images generated by, and repeating the process of extracting the feature points of the iris by the feature point extraction unit 133.

The counterfeit determination unit 135 determines the iris being authenticated as a living body when the location of the feature points is different among the plurality of eye part images or an error image in which the feature points are not extracted is determined, and if the error image is not detected, the counterfeit iris is determined.

Hereinafter, with reference to FIG. 2, a description will be given of a method for discriminating a forged iris of the present invention, focusing on the operation of the counterfeit determination unit 135.

<Confirmation of iris authentication attempt: S201, S203>

The first camera unit 113 photographs the front at a predetermined frame rate to generate an image and provides it to the control module 130. At this time, the light source 111 may or may not illuminate the front (S201).

The iris detection unit 131 detects the user's eyes by performing image processing on the image captured by the first camera unit 113. The counterfeit determination unit 135 determines that the user's iris authentication is attempted when the iris detection unit 131 recognizes the user's eye (S203).

The iris detection unit 131 may perform the degree of detecting the outline of the pupil through edge detection in the eye portion image, or detect the location of the iris by detecting the location of the pupil through a Hough Transform. You can also perform tasks.

<User guide for counterfeit identification: S205>

In step S203, the counterfeit determination unit 135 that recognizes the user's eye provides a user guide for counterfeit identification to the user through the user interface 101.

As is known, the pattern of the feature points of the user's iris does not change in any state, but the position of the iris (feature point) in the image of the eye portion taken by the first camera unit 113 may change, and when the eyes are closed, the feature points are not extracted It might be. For example, an operation of blinking an eye may occur momentarily to hide the iris from the image taken by the first camera unit 113. It is noted that counterfeit irises do not perform this action.

Therefore, the user guide for forgery discrimination is to determine whether the iris that attempts to iris authentication is a forgery by requesting an operation to create a change in a feature point extracted from the iris, so that the iris location is not changed or the iris is not visible. Any action may be used as long as it requests at least one user action. However, a user action that can be performed in a very short time is particularly preferable.

Therefore, the user's motion may correspond to a motion of blinking an eye, a motion of staring at a direction other than the front (eg, left, right, up or down) by rolling the pupil, or a motion of moving the face slightly left and right or up and down.

The user guidance for forgery discrimination may be output through voice through a speaker, or may be visually displayed using a display means.

<Iris recognition / feature point extraction during measurement time: S207 to S211>

After displaying the user guide for forgery discrimination, the forgery determination unit 135 turns on the light source 111 and causes the first camera unit 113 to take a user's eye at a predetermined frame rate to generate an eye portion image. Control. Here, the shooting speed of the first camera unit 113 may be the same as or different from the shooting speed of step S201 (S207).

The iris detection unit 131 recognizes the iris portion from the image of the eye portion taken by the first camera unit 113, and the feature point extraction unit 133 extracts the feature points of the iris (S209).

In steps S207 and S209, a plurality of (n) eye partial images are generated and iris recognition and feature point extraction are repeated multiple (n) times by performing multiple (n) repetitions during a predetermined measurement time. For example, when the shooting speed of the first camera unit 113 is set to 10 frames per second and the measurement time is set to 2 seconds, the iris detection unit 131 provides 20 images (n=20) of the eye portion provided for 2 seconds. Feature points are extracted from. Here, the measurement time is preferably set longer than the time required for the user to perform the guided operation according to the user guidance in step S205, and can be determined experimentally (S211).

<Forgery iris discrimination according to error image detection: S213 to S217>

When the measurement time has elapsed, the counterfeit determination unit 135 determines whether there is an error image among the plurality of (n) eye portion images. Here, the error image refers to an image of a portion of the eye where the feature point is different from the other or the feature point is not extracted at all (S213).

If, when the false image is detected among the plurality of (n) eye part images, the forgery determination unit 135 determines the iris being authenticated as a living body (S215), and if the error image is not detected, the authenticated iris is determined as a fake iris. ((S217).

If the user blinks the eye according to the guidance of step S205, the image of the user's eyelid moving downward to cover the iris is included among the plurality of eye part images captured during the measurement time (for example, 2 seconds). The iris-covered image is classified as an error image because the feature points are not properly extracted. Forged irises in the form of high resolution printed on paper or synthetic resin cannot perform an operation in accordance with the user's guidance, so no error image is generated.

If in step S205 the user is guided to move the pupil, let's assume that the user moves the pupil. If the user moves the pupil during the measurement time and does not blink the eyes, the same feature points can be extracted from all the images of the multiple eye parts photographed. However, the position of the feature points of some images is different from the position of the feature points of the remaining images. For example, if there is an image in which the location of the feature point differs from the error range based on the location of the feature point extracted from the first image taken after the start of the measurement time, it may be classified as an error image.

Meanwhile, even if the pupil is guided to move in step S205, the user may blink the eye in addition to moving the pupil. Therefore, the determination criteria of the error image may be irrelevant to the guidance of step S205.

The method of discriminating a counterfeit iris of the present invention is performed by the above method.

Save log

Referring to FIG. 3, the image acquisition module 310 of the counterfeit iris discrimination apparatus 300 according to another embodiment of the present invention is a second camera unit that photographs a user's face separately from the first camera module 113 (311) may be further included.

Since the second camera unit 311 photographs a face image, the second camera unit 311 has a different configuration from the first camera unit 113 that generates an eye portion image. The second camera unit 311 may generate a color image of the user's face with natural light without infrared illumination.

The counterfeit determination unit 331 may control the second camera unit 311 to photograph the face image of the user when the user's eye is recognized in step S203. The counterfeit determination unit 331 may store the face image photographed by the second camera unit 311 in a memory or a storage medium (not shown) together with the determination result of step S215 or S217.

The face image photographed by the second camera unit 311 may be used as log data for a user who has attempted iris authentication.

Although the preferred embodiments of the present invention have been illustrated and described above, the present invention is not limited to the specific embodiments described above, and it is usually in the technical field to which the present invention pertains without departing from the gist of the present invention claimed in the claims. Of course, various modifications can be implemented by a person having knowledge of these, and these modifications should not be individually understood from the technical idea or prospect of the present invention.

111: light source 113: first camera unit
113a: Lens 113b: Image sensor

Claims (12)

Generating a partial eye image by photographing a user attempting authentication by the first camera unit;
Repeating a process of extracting an iris portion from a plurality of the eye portion images generated by the first camera unit at a predetermined frame rate and extracting feature points of the iris; And
During the repetition step, if a position of a feature point is different among the plurality of eye partial images or a change in a feature point in which a feature point is not extracted is detected, the iris being authenticated is determined as a living body, and if a change in the feature point is not detected, it is determined as a counterfeit iris. A method of discriminating a forged iris, comprising the steps of:
According to claim 1,
Further comprising the step of outputting to the user a guide requesting at least one action to change the position of the iris or to make the iris invisible,
The repeating step is a counterfeit iris discrimination method characterized in that it is performed for a predetermined measurement time after the step of displaying the guidance.
According to claim 2,
The guide is a method for discriminating a counterfeit iris, which is characterized in that the user is asked to blink the eye or to roll the pupil to stare in a different direction.
According to claim 2,
In the determining step,
A method for discriminating a forged iris, characterized in that the variation of the feature point is detected from the eye part images generated in the frames other than the first and last frames of the measurement time.
According to claim 2,
A method of discriminating a forged iris, characterized by performing the step of displaying the guide when a user's eye is recognized while repeating the step of generating the eye part image.
According to claim 1,
A second iris discrimination method further comprising the step of generating the user's face image and storing the result together with the determination result of the determining.
A first camera unit that photographs a user attempting authentication at a predetermined frame rate to generate a plurality of eye portion images;
An iris detection unit extracting an iris portion from each of the plurality of eye portion images;
A feature point extraction unit for extracting a feature point of the iris from the iris portion; And
Based on the result of the extraction of the feature point extracting unit, if the position of the feature point is different among the plurality of eye parts images or a change in the feature point in which the feature point is not extracted is determined, the iris being authenticated is determined as a living body and the change in the feature point is not detected. A counterfeit iris discrimination device comprising a counterfeit determination unit for performing counterfeit determination by determining the counterfeit iris.
The method of claim 7,
Further comprising a user interface for displaying a guide for requesting at least one action to change the position of the iris or the iris is not visible to the user under the control of the counterfeit determination unit,
The forged iris discrimination unit is characterized in that forgery iris discrimination is performed based on the extraction result of the feature point extraction unit extracted during a predetermined measurement time after displaying the guidance.
The method of claim 8,
The guide, forgery iris discrimination device characterized in that the user requests to blink or ask the pupil to stare in a different direction.
The method of claim 8,
The counterfeit determination unit,
A counterfeit iris discrimination device, characterized in that the variation of the feature point is detected from the eye part images generated in the frames other than the first frame and the last frame of the measurement time.
The method of claim 8,
The counterfeit determination unit,
A counterfeit iris discrimination device, characterized in that the iris detection unit displays the guide when recognizing an eye of a user attempting iris authentication from an image provided by the first camera unit.
The method of claim 7,
Further comprising a second camera unit for generating the face image of the user,
The counterfeit determination unit is characterized in that for storing the face image together with the result of the counterfeit identification, the iris discrimination device.

Images