KR20150145966A - Finger vein authentication system - Google Patents

Abstract

The purpose of the present invention is to provide a vein authentication system capable of accurately and rapidly determining a vein pattern of people since a rotating body which includes a light source unit and a CCD camera unit (130) on an opposing position of the inner side photographs the entire outer side of fingers while being rotated by a rotary driving unit. To achieve the purpose, the vein authentication system according to the present invention comprises: the rotating body of a hollow cylindrical shape; the light source unit to emit far red light by being located in the inner side of the rotating body; the CCD camera unit to form an image including fingers of a user on the inner side of the rotating body and convert the image into an electric signal; an optical filter to transmit light of a specific wavelength only between the lights from the light source unit; the rotary driving unit to rotate the rotating body; a memory unit to store a level set curvature program for performing a calculation to extract a finger vein pattern in the image including the fingers by using a level set curvature; and a control unit to drive the level set curvature program. The CCD camera unit forms the image along the outer side of the fingers as the rotating body is rotated.

Description

[0001] FINGER VEIN AUTHENTICATION SYSTEM [0002]

[0001] The present invention relates to a vein authentication system, and more particularly, to a vein authentication system in which a rotating body including a light source unit and a CCD camera unit at an inward facing position is rotated by a rotation driving unit, To a vein authentication system for accurately and quickly discriminating vein patterns of people.

In general, bio-metrics is a method of recognizing individuals using physiological or behavioral characteristics of humans. Typical biometric technologies include fingerprint, face, iris, vein, signature, and speaker recognition. Among these biometric recognition methods, vein recognition has a high recognition performance and has advantages of less rejection and inconvenience of users and faster recognition time.

For example, according to the study of "Yanagawa", it has been proved that the person can identify himself or herself even in the vein of the human. According to the study of "Yanagawa" mentioned above, Is a degree of freedom similar to highly reliable iris patterns and is suitable for personal authentication.

As described above, studies are being conducted to accurately and quickly determine the vein pattern of a person by acquiring a vein of a finger and using personal authentication.

However, in the past, only the underside of the finger of the person who wants to be authenticated is picked up by the camera and compared with the vein pattern data of the people who have been stored, the finger of the person to be authenticated in the finger- The vein authentication system mistakenly captures a vein pattern of a person to be authenticated, resulting in failure to perform accurate authentication and result in an error or vein pattern discrepancy (rejection).

SUMMARY OF THE INVENTION The present invention has been conceived in view of the above-described points, and it is an object of the present invention to provide an image reading apparatus, It is an object of the present invention to provide a vein authentication system for accurately and quickly discriminating vein patterns of people by imaging.

Another object of the present invention is to recognize, collate, and discriminate a user's vein pattern at a low capacity / high speed by analyzing a level set curvature using the vein authentication system.

In order to achieve the above object, a vein authentication system according to the present invention is characterized in that a vein authentication system according to the present invention includes a rotatable body having either a top surface or a bottom surface opened, a hollow shape rotatably disposed on an inner surface of the rotatable body, A CCD camera unit configured to pick up an image including a user's finger on the inner surface of the rotating body facing the light source unit and then convert the picked-up image into an electrical signal; A rotation driving unit having a protrusion at one side for rotating the rotating body, and an operation for extracting a finger vein pattern from the image including the finger using a level set curvature A memory unit for storing a level set curvature program to be executed, Comprising a control unit, and by rotating the rotating is characterized in that the CCD image pick-up camera portion along the outer surface of the finger.

Further, in the vein authentication system according to the present invention, the level set curvature program may cause the control unit to perform: (a) removing noise from the image including the finger acquired from the CCD camera unit; (b) separating an image of the finger portion only by removing a peripheral portion from an image including the finger from which noise has been removed; (c) extracting a finger vein pattern from an image of only the finger portion using a level set curvature; (d) binarizing the extracted finger vein pattern; (e) instructing the processed binarized finger vein pattern to be thinned.

Further, in the vein authentication system according to the present invention, the extracting of the finger vein pattern using the level set curvature in (c) may further comprise: (c1) extracting the finger vein pattern from each of all the pixels constituting the image of the finger portion only (C2) a second operation for generating at least one level set, which is a closed curve generated by connecting pixels having the same pixel intensity among all the pixels, and (c3) A third computation for defining the at least one contour line as a set of contour lines; and (c4) generating at least one line connecting the points of each of the at least one contour line with a minimum curvature with respect to the outside of the contour line set (C5) a fifth operation for recognizing and extracting the one or more lines as a vein pattern.

Further, in the vein authentication system according to the present invention, the curvature in (c4)

는 상기 곡률이며, w는 상기 등고선 세트의 그래디언트 벡터(gradient vector)인 것을 특징으로 한다., Where < RTI ID = 0.0 >

Is the curvature, and w is a gradient vector of the contour line set.

Further, in the vein authentication system according to the present invention, the optical filter unit is a near infrared ray band pass filter (NIR Pass Filter), and the oxyhemoglobin (HbO ₂ ) and the deoxyhemoglobin (Hb) in the hemoglobin contained in the vein of the user's finger And is configured to transmit only light having a wavelength of 630 to 1,000 nm suitable for detection.

The vein authentication system according to the present invention further includes a key input unit configured to include a plurality of keys including numbers, letters, and symbols and output a key signal corresponding to a key selected by the user.

The vein authentication system according to the present invention is characterized in that the control unit rotates the rotator by 1/2 cycle so that the CCD camera captures only the bottom surface and both sides of the finger.

Further, in the vein authentication system according to the present invention, the optical filter unit is formed in the shape of the finger rest portion, and the finger is seated on the optical filter unit.

According to the present invention, the rotating body including the light source unit and the CCD camera unit 130 at the facing positions on the inner surface is rotated by the rotation driving unit to pick up the entire outer surface of the finger, There is an effect of prompt discrimination.

Also, there is an effect of recognizing, verifying, and discriminating a user's vein pattern at a low capacity / high speed by analyzing a level set curvature using the vein authentication system.

값을 8비트 그레이 레벨로 정규화하여 나타낸 도면.
도 8은 레벨 세트 곡률 프로그램에 따라 추출된 정맥 화상을 기존의 방식들에 따른 정맥 화상과 비교하여 나타낸 도면.FIG. 1A is a perspective view showing an appearance of a vein authentication system according to an embodiment of the present invention; FIG.
Fig. 1B is a view for explaining the internal structure of the image processing apparatus in the vein authentication system of Fig. 1A. Fig.
1C is an exploded perspective view of the vein image processing apparatus.
FIG. 2 is a block diagram for explaining an internal configuration of the vein authentication system of FIG. 1; FIG.
FIG. 3 is an algorithm flow diagram illustrating the process of extracting a vein pattern according to an instruction of a level set curvature program by the vein authentication system of FIG. 1A. FIG.
Fig. 4 is a diagram showing an image of a finger whose noise has been removed, according to a level set curvature program, by comparing it with an image before noise removal; Fig.
5 is a diagram showing a result screen obtained by separating an image of only a finger portion from all the images in accordance with a level set curvature program.
6A is a diagram showing a state in which a finger image is converted into a contour shape according to a level set curvature program;
6B is a diagram showing a manner in which a level set curvature program identifies a finger vein pattern using the contour lines of Fig. 6A; Fig.
FIG. 7 is a cross-

Figure normalized to 8 bit gray level.
8 is a view showing a vein image extracted according to a level set curvature program, in comparison with a vein image according to conventional methods;

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the drawings, the same reference numerals are used to designate the same or similar components throughout the drawings. In the following description of the present invention, a detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention rather unclear.

Throughout the specification, when an element is referred to as "comprising ", it means that it can include other elements as well, without excluding other elements unless specifically stated otherwise. Also, the terms " part, "" module," and " module ", etc. in the specification mean a unit for processing at least one function or operation and may be implemented by hardware or software or a combination of hardware and software have.

1A is a perspective view showing an appearance of a vein authentication system 1 according to the present invention. FIG. 1B is a view for explaining an internal structure of a vein image processing apparatus 10 in a vein authentication system 1, FIG. 2 is an exploded perspective view of the vein image processing apparatus 10, and FIG. 2 is a block diagram for explaining an internal configuration of the vein authentication system 1. As shown in FIG.

The vein authentication system 1 according to the present invention acquires the image of the user's finger F irradiated with the near infrared ray light as a digital image through the CCD camera, And identifies the individual by a method of comparing the extracted pattern feature with previously registered user information.

For example, the vein authentication system 1 can be installed on the wall next to the door, and the user can simply insert the finger F into the finger rest S of the vein image processing apparatus 10 Accessing authentication can be completed only by the operation of mounting the terminal. At this time, when the vein pattern of the user does not coincide with the vein pattern registered in the system 1, access authentication is denied.

In the following description, the system 1 will be described assuming that the user completes the authentication only by recognizing the vein pattern. However, in another embodiment, before and after the user authenticates the vein pattern, the key input unit 210 ) To enter the password through the security can be strengthened. For example, after the user inputs the password into the key input unit 210, the user may be authenticated in such a manner that the vein pattern is checked once more.

Referring to Figs. 1A, 1B, 1C, and 2, the vein authentication system 1 according to the present invention includes a vein image processing apparatus 10 for largely acquiring an image of a finger F, And an authentication processing unit 20 for performing user authentication processing. The vein image processing apparatus 10 includes a rotatable body 140 having one of an upper surface and a lower surface opened, a hollow body 140, a light source unit 140 disposed on the inner surface of the rotating body 140, (130) configured to capture an image including the user's finger (F) on the inner surface of the rotating body (140) facing the light source unit (110) and to convert the captured image into an electrical signal An optical filter 120 for transmitting only light having a specific wavelength from the light incident from the light source unit 110 and a rotation driving unit 150 having a protrusion 151 on one surface for rotating the rotating body 140 do. The authentication processing unit 20 includes a key input unit 210 configured to output a key signal corresponding to a key selected by the user and configured with a plurality of keys such as numbers, letters, symbols, A display unit 220 for displaying a screen on the outside, a memory unit 230 for storing a level set curvature program, and a control unit 240 for driving the level set curvature program.

Specifically, the vein image processing apparatus 10 is provided with a light source unit 110 which is configured to open either the top or bottom surface and to emit near-infrared light to the inner surface of the hollow shape, an image including the user's finger F A CCD camera unit 130 configured to convert the sensed image into an electrical signal after being picked up is positioned so as to be opposed to each other and an incised cylindrical fingertip portion S formed with a structure in which a finger F is inserted And is inserted into the open surface formed in the whole body 140.

For example, when the user places the finger F on the finger rest portion S for user authentication, the near-infrared light emitted from the light portion 110 passes through the finger F on the finger rest portion S An image of the finger F is picked up in such a manner that the finger F reaches the CCD camera unit 130 after passing through the optical filter unit 120 included in the lower portion of the finger placement unit S. [ At this time, the rotating body 140 picks up all the outer surfaces of the fingers F that are seated on the fingertips S while rotating by the rotation driving unit 150. Most of the conventional methods capture only the undersurface of the finger F that is seated on the finger rest portion S. This is because when the CCD camera portion 130 picks up the vein pattern, The controller 240 may cause an error in determining whether the registered vein pattern matches the registered vein pattern of the user or to determine the different vein patterns in the same vein pattern. However, in the present invention, If the rotating body 140 including all of the CCD camera unit 130 picks up the entire outer surface of the finger F while being rotated by the rotation driving unit 150, . The finger F image picked up by the CCD camera unit 130 is stored in the memory unit 230 under the control of the control unit 240 of the authentication processing apparatus 20. [ After that, the control unit 240 determines whether or not the vein pattern in the image of the finger (F) coincides with the vein pattern of the user previously registered in advance according to the instruction of the level set curvature program 231 And performs a processing operation.

The control unit 240 may rotate the rotator 140 by 1/2 cycle so that the CCD camera unit 130 captures only the bottom surface and both sides of the finger F. [ This is because the vein pattern of the finger F can solve an error of determining the same vein pattern as an error or a different vein pattern that may occur in the control unit 240 by capturing only the bottom face and both sides. That is, people's finger (F) vein pattern has a vein pattern different for each person like fingerprint. To accurately determine the vein pattern, it is necessary to capture the bottom face and the side face of the finger F have. The control unit 240 determines whether or not the vein pattern in the image of the finger F matches the vein pattern of the user registered in advance with the finger F picked up by the CCD camera unit 130. [ Since the electrical signal data on the image is smaller than the electrical signal data on the entire outer surface of the finger F, it is possible to reduce the data amount of the electrical signal stored in the memory unit 230 by the control unit 240 .

On the other hand, the rotation driving part 150 has a protrusion 151 on one surface to rotate the rotating body 140. These protrusions 151 may have threads (not shown), and such threads are bolted to the closed surface of the rotating body 140. It is obvious that the closed surface of the rotating body 140 has a threaded hole so that the protruding portion 151 can be bolted.

Further, the rotating body 140 is preferably formed in a cylindrical shape, but is not limited thereto. For example, the light source unit 110 and the CCD camera unit 130 may be formed so as to be opposed to the inner surface even if the rotating body 140 is formed in a square column shape.

Next, the light source unit 110 may include one or a plurality of LEDs or laser diodes having a structure that emits near infrared light having a wavelength of 630 to 1,000 nm, for example. According to a preferred embodiment, a light wave guide made of PDMS material can be attached to the rear surface of the light source unit 110, so that light can be incident on the finger F without spreading to the side .

The optical filter unit 120 may include a near infrared ray band pass filter (NIR Pass Filter), for example. The optical filter unit 120 functions to capture only a finger vein image even in a situation where the user's finger F is exposed to visible light. According to a preferred embodiment, the optical filter unit 120 can be configured to transmit only light having a wavelength of 630 to 1,000 nm suitable for detection of oxyhemoglobin (HbO2) and dioxyhemoglobin (Hb) in hemoglobin. Meanwhile, the optical filter 120 may be formed in the shape of a finger-seating portion S so that the finger F may be seated on the optical filter portion 120. That is, in the present embodiment, the optical filter unit 120 is formed by including the optical filter unit 120 in the lower portion of the finger-seating unit S. However, the present invention is not limited to this, and the optical filter unit 120 may be formed in the shape of the finger- It is possible. This is advantageous in that a clearance can be ensured on the space between the finger seat S and the rotating body 140 inserted into the through hole of the rotating body 140. In addition, Since the one finger 120 and the finger rest S are integrally formed, the manufacturing cost can be reduced.

The CCD camera unit 130 performs an operation of converting an image of the finger F picked up by the near-infrared light emitted from the light source unit 110 into an electrical signal. The electrical signal image relating to the finger F acquired by the CCD camera unit 130 is stored in the memory unit 230 under the control of the control unit 240. [

3 is an algorithm flowchart showing a process of extracting a vein pattern from an image related to a finger received from the CCD camera unit 130 in accordance with a command of the level set curvature program 231 by the control unit 240. FIG.

3, the control unit 240 of the authentication processing apparatus 20 drives the "level set curvature program 231" stored in the memory unit 230 to (a) (S301) for removing noise from the image relating to the finger acquired from the image processing unit 130, and (b) processing for separating the image of only the finger portion by removing the peripheral portion from the image relating to the finger from which noise has been removed (S303) of extracting a finger vein pattern from an image of only the finger portion using a level set curvature (S303); (d) A binarizing processing operation S304, and (d) a processing operation S305 of thinning the binarized finger vein pattern.

Thereafter, the control unit 240 may judge whether or not the finger vein pattern with the thinning coincides with the previously registered finger vein pattern with respect to the user, in accordance with the instruction of the level set curvature program 231 Of course.

The level set curvature program 231 may be stored in an external storage medium such as a flexible disk, a hard disk, an optical disk, a magneto-optical disk, a CD-ROM, a CD-R, a magnetic tape, a nonvolatile memory card, May be supplied to the vein authentication system 1 by using the vein authentication system 1.

Hereinafter, the vein extraction algorithm provided by the level set curvature program 231 will be described in detail with reference to FIG. 4 to FIG.

[Noise removal processing (S301)]

The level set curvature program 231 applied to the vein authentication system 1 according to the present invention performs an operation for removing noise from an image related to a finger, for example, using a Gaussian filtering method.

)을 선택하는 연산 과정을 수행할 수 있다.For example, the level set curvature program 231 includes an arithmetic operation of dividing an image of a finger into blocks of a predetermined size, for example, M lines and N pixels, and a standard deviation of pixel values of the divided blocks Calculating a minimum standard deviation (σmin) quantized to an integer value by selecting the smallest standard deviation among the plurality of blocks, calculating a minimum standard deviation (σmin) of the block having a standard deviation within a predetermined range from the minimum standard deviation (

) Can be performed.

)은 다음의 수학식 1을 사용하여 도출가능하다.At this time,

) Can be derived using the following equation (1).

[Equation 1]

는 상기 선택된 블럭을 나타내며,

는 FLOOR함수로서, 주어진 값보다 작거나 같은 최대 정수값을 구하는 함수를 말한다. here,

Represents the selected block,

Is a FLOOR function that obtains a maximum integer value that is less than or equal to a given value.

)들에 대해서 가우시안(Gaussian) 필터링을 하기 위한 필터계수를 산출하며, 이때, 필터계수는 양자화된 최소표준값차(σmin )로부터 다음의 수학식 2에 의해 산출할 수 있다.Thereafter, the level set curvature program 231 is applied to the selected block (

The filter coefficient is calculated from the quantized minimum standard value difference (min) by the following equation (2). &Quot; (2) "

&Quot; (2) "

Then, the level set curvature program 231 performs filtering on the selected blocks? Min according to the calculated filter coefficients.

)으로 산출하며, 이것은 다음의 수학식 3과 같이 나타난다.Then, the level set curvature program 231 calculates the standard deviation of the difference between the selected blocks and the value obtained by Gaussian filtering the selected blocks as a noise measurement value (

), Which is expressed by the following equation (3).

&Quot; (3) "

With this process, the level set curvature program 231 can calculate the noise irrelevant to the finger portion of the image relating to the finger, and can eliminate the noise.

Fig. 4 shows an image of the finger with noise removed compared with the image before noise removal, according to the level set curvature program 231. Fig.

[Processing for separating images of only a finger portion (S302)] [

The level set curvature program 231 applied to the vein authentication system 1 according to the present invention performs an operation of separating an image of only a finger portion from an image of a finger.

The image captured by the CCD camera unit 130 includes not only an image of the finger portion but also an image of the surrounding object.

According to a preferred embodiment, the level set curvature program 231 performs an operation of separating an image of only a finger portion from the entire image using an edge detect function using a divergence of gradient (gradient) can do.

For example, the edge detection function using the divergence of the gradient can use the following equation (4).

&Quot; (4) "

5 shows a result screen obtained by separating the image of only the finger portion from the entire image in accordance with the level set curvature program 231. [

[Processing for extracting the finger vein pattern using the level set curvature (S303)] [

The level set curvature program 231 applied to the vein authentication system 1 according to the present invention performs an operation of extracting a finger vein pattern from an image of a finger portion using a level set curvature.

Here, a level set refers to a set of pixels having the same intensity when each pixel value of an image is regarded as an intensity function.

Thus, if the intensity function is a continuous function, the points that make up one level set form one contour line.

Specifically, the level set curvature program 231 includes (c1) a first operation that defines a pixel intensity for each of the pixels constituting the finger image, and (c2) (C3) a third operation for defining the one or more contour lines as a set of contour lines; (c4) a third operation for defining a contour line outside the set of contour lines; (C5) a fifth operation for recognizing the one or more lines as a vein pattern and extracting the line; (c5) a fourth operation for generating one or more lines connecting the points of the at least one contour line, A finger vein pattern is extracted from the finger image.

6A shows a state in which a finger image is converted into a contour line set according to a level set curvature program 231, and FIG. 6B shows a state in which a level set curvature program 231 is generated by using the curvature of the contour line set of FIG. And the vein pattern is discriminated.

First, referring to FIG. 6A, an operation for defining a pixel intensity for each of all pixels constituting an image of only a finger portion in a finger image, an operation for connecting pixels having the same pixel intensity among all the pixels A set of contour lines is created by an operation that creates one or more level sets that are closed curves.

Next, referring to FIG. 6B, the level set curvature program 231 includes an operation of generating one or more lines connecting the points of each of the one or more contour lines with a minimum curvature on the basis of the outside of the contour line set, , A vein pattern is extracted from the finger image by an operation of recognizing and extracting the one or more lines as a vein pattern.

The lines connecting the points with the minimum curvature based on the outside of this contour set are similar to the way of finding valleys in the contour line from a geographical point of view.

Concretely, the level set curvature program 231 calculates a line connecting the points at which the curvature becomes the maximum, when calculated from the outside of the set of contour lines on each contour line constituting the set of contour lines included in the finger image The line connecting the points that become the ridge becomes the valley and the place where the vein is distributed in the finger image corresponds to the pattern of the valley on the contour line set.

가 가장 작은 점들을 찾는 것에 의해 구할 수 있다.The point at which this curvature becomes minimum is obtained by the following equation (5)

Can be obtained by finding the smallest points.

&Quot; (5) "

는 곡률이고 w는 그래디언트 벡터이며, 손가락 정맥에 해당하는 부분은 뚜렷이 낮은 값을 갖는다.here

Is the curvature, w is the gradient vector, and the portion corresponding to the finger vein is clearly low Lt; / RTI >

As described above, the level set curvature can be obtained by using a divergence of a normalized gradient. At this time, the gradient vector is collected in the ridge line portion in the contour line, and the gradient vector is diverged in the valley portion intuitively Can be confirmed.

값을 8비트 그레이 레벨로 정규화하여 나타낸 것이며, 정맥의 중심 라인에 해당하는 부분이 뚜렷이 작은 값을 가지는 것을 확인할 수 있다.
Figure 7

Value is normalized to an 8-bit gray level, and the portion corresponding to the center line of the vein has a distinctly smaller value.

[Processing of binarizing the level set curvature (S304) and processing of thinning (S305)]

The level set curvature program 231 applied to the vein authentication system 1 according to the present invention includes an operation S304 for binarizing a finger vein pattern extracted using a level set curvature, The thinning operation 305 is performed.

Here, the binarization process performed by the level set curvature program 231 is to reduce the storage space of the extracted vein in consideration of the capacity of the memory unit 230, and also to reduce the matching time, .

In addition, the thinning performed by the level set curvature program () is to convert a thick vein display into a thin vein display, so that a larger amount of vein information can be stored without distortion.

FIG. 8 is a flowchart showing a procedure of extracting a vein pattern from a finger image in accordance with a level set curvature program 231, extracting a final vein image obtained by binarizing and thinning the extracted pattern, And a second intravenous image according to a conventional local threshold method.

As can be seen from FIG. 8, the shape of the vein image obtained according to the level set curvature program 231 according to the present invention is much clearer than the existing vein image, and accordingly, .

The level set curvature program 231 applied to the vein authentication system 1 according to the present invention may be recorded in a computer-readable recording medium. Examples of such computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage, and the like, as well as being implemented in the form of a carrier wave (e.g., transmission over the Internet) . The computer-readable recording medium may also be distributed over a networked computer system so that computer readable code in a distributed manner may be stored and executed. In addition, functional programs, codes, and code segments for implementing the present embodiment can be easily inferred by programmers in the technical field to which the present embodiment belongs.

In addition, the present invention is not necessarily limited to these embodiments, as long as all the constituent elements constituting the embodiment of the present invention are described as being combined into one operation. That is, within the scope of the present invention, all of the components may be selectively coupled to one or more of them. In addition, although all of the components may be implemented as one independent hardware, some or all of the components may be selectively combined to provide a program module that performs some or all of the functions in one or a plurality of hardware As shown in FIG.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or essential characteristics thereof. . Therefore, the embodiments disclosed in the present invention are intended to illustrate rather than limit the scope of the present invention, and the scope of the technical idea of the present invention is not limited by these embodiments. The scope of protection of the present invention should be construed according to the following claims, and all technical ideas within the scope of equivalents should be construed as falling within the scope of the present invention.

1: vein authentication system 10: vein image processing device
20: Authentication processing unit 110: Light source unit
120: light source filter unit 130: CCD camera unit
140: Rotor 150:
151: protrusion 210: key input unit
220: display unit 230: memory unit
231: level set curvature program 240:

Claims (8)

Wherein the rotating body has a hollow shape in which one of the upper surface and the lower surface is opened,
A light source unit disposed on the inner surface of the rotating body and configured to emit near-
A CCD camera unit configured to capture an image including a user's finger on the inner surface of the rotating body facing the light source unit and then convert the captured image into an electrical signal;
An optical filter that transmits only light of a specific wavelength among lights incident from the light source unit,
A rotation driving unit having a protrusion on one surface thereof for rotating the rotating body;
A memory unit for storing a level set curvature program for performing an operation of extracting a finger vein pattern from an image including the finger using a level set curvature,
And a control unit for driving the level set curvature program, wherein the CCD camera unit captures an image along an outer surface of the finger by rotating the rotating body. The method according to claim 1,
The level set curvature program may cause the control unit to,
(a) removing noise from an image including the finger acquired from the CCD camera unit;
(b) separating an image of the finger portion only by removing a peripheral portion from an image including the finger from which noise has been removed;
(c) extracting a finger vein pattern from an image of only the finger portion using a level set curvature;
(d) binarizing the extracted finger vein pattern;
(e) instructing the binarized processed finger vein pattern to be thinned. 3. The method of claim 2,
The extraction of the finger vein pattern using the level set curvature in (c)
(c1) a first operation for defining a pixel intensity for each of all the pixels constituting the image of the finger portion only,
(c2) a second operation for generating at least one level set, which is a closed curve generated by connecting pixels having the same pixel intensity among all the pixels,
(c3) a third operation of defining the one or more contour lines as a set of contour lines,
(c4) a fourth operation for generating at least one line connecting points of each of the at least one contour line, the curvature of which is minimum with respect to the outside of the set of contour lines;
(c5) recognizing the at least one line as a vein pattern and extracting the vein pattern. The method of claim 3,
The curvature in (c4)

, Where < RTI ID = 0.0 >

Is the curvature, and w is a gradient vector of the set of contours. 3. The method of claim 2,
The optical filter unit is a near infrared ray band pass filter (NIR pass filter), and it can detect only the light of 630 to 1,000 nm wavelength suitable for detection of oxyhemoglobin (HbO ₂ ) and deoxyhemoglobin (Hb) in the hemoglobin contained in the vein of the user's finger The vein authentication system comprising: 3. The method of claim 2,
And a key input unit configured to output a key signal corresponding to a key selected by the user, the key input unit comprising a plurality of keys including numbers, letters, and symbols. The method according to claim 1,
Wherein the control unit rotates the rotator by 1/2 cycle so that the CCD camera unit captures only the bottom surface and both sides of the finger. The method according to claim 1,
Wherein the optical filter unit is formed in the shape of the finger rest part and the finger is seated on the optical filter part.

Images