JP2002279413A - Device for identifying dummy fingerprint and device for collating fingerprint - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a small and inexpensive device for identifying dummy fingerprint capable of correctly identifying a dummy fingerprint. SOLUTION: A standard deviation calculating section 21 calculates standard deviation of each pixel value of an input fingerprint image. A standard deviation value memory 22 stores standard deviation values for N frame portion, sequentially transmitted from the section 21. A standard deviation variation degree determining section 23 gives the difference between the maximum value and the minimum value of the standard deviation values, between the frames by using N of standard deviation values stored in the memory 22 and identifies to be a living body fingerprint, if the value is at or larger a threshold. If below the threshold value, the section 23 identifies to be a dummy fingerprint. Thereby the dummy fingerprint, having gelatin as component showing little changes in the standard deviation, is accurately identified as being a dummy fingerprint.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

[0001] 1. Field of the Invention [0002] The present invention relates to a pseudo fingerprint discriminating apparatus used for performing personal authentication using a biometric fingerprint and a fingerprint matching apparatus using the pseudo fingerprint discriminating apparatus.

[0002]

2. Description of the Related Art Conventionally, personal identification is generally performed using a user ID (identifier) unique to an individual, a password, a combination thereof, or the like. The password is used to confirm the identity of the user using information known only to the user himself, but the personal authentication method using this password is a really weak method. That is, first, the use of information that is easy for the user to remember is easily imagined or guessed by others, and the information that is hard to imagine or guessed by others is also difficult for the user himself to remember. Therefore, it is considered that the personal authentication method using a password always has a risk of being leaked to others.

Recently, in order to reduce these risks,
It is recommended that you change your password regularly.
However, the task of changing the password and remembering the changed password is a considerable burden on the user himself. In particular, in recent years, the use of a plurality of information device systems has increased, and therefore, the need to remember a plurality of user IDs and passwords has increased. In such a case, it is very difficult to reliably grasp each password.

In recent years, a personal authentication technique using biometric information called biometrics has been spotlighted as a personal authentication method for overcoming such weaknesses of passwords. In particular, among these, personal authentication technology using fingerprints has been increasingly applied to commercialization than other biometric information due to simplicity of handling and miniaturization of devices.

[0005] The above-mentioned fingerprint has the characteristic that it is unique to all and is life-long, and is optimal for personal authentication. Conventionally, optical sensors and capacitive sensors have been sold at low cost for fingerprint imaging, and a fingerprint recognition system is often constructed using these sensors.

However, in the case of a fingerprint recognition system using the above-mentioned optical sensor, a pseudo fingerprint provided on an artificial finger made of rubber such as silicon is authenticated. On the other hand, in the case of a fingerprint recognition system using a capacitance type sensor, authentication is not performed using a pseudo fingerprint made of rubber such as silicon. However, in the case of a pseudo-fingerprint using gelatin having a property close to that of a living body, authentication is performed even by a fingerprint recognition system using a capacitance type sensor. For example, in IEICE Technical Report ISEC2000-45 “Does fingerprint matching devices accept artificial fingers?”, It was proved by experiments that pseudo fingerprints using gelatin were almost accepted by commercial fingerprint matching sensors. are doing.

Therefore, as a technique for discriminating the pseudo-fingerprint,
Various techniques have been proposed. For example, JP-A-2000-
In the authentication device and the authentication method disclosed in Japanese Patent No. 76450, the “order of fingerprint information input at the time of registration” is previously provided as registration information. Are compared to determine the pseudo fingerprint. In addition, JP-A-2
In the fingerprint image input device disclosed in Japanese Patent Application Laid-Open No. 000-20684, the living body identification device disclosed in Japanese Patent Application Laid-Open No. H11-45338, and the uneven pattern reading device disclosed in Japanese Patent Application Laid-Open No. In addition to the basic function of capturing a fingerprint, a biometric identification device is attached to the inside and outside of the sensor for obtaining the above information, and a pseudo fingerprint is determined.

[0008]

However, Japanese Patent Application Laid-Open No. 2000-20684 and Japanese Patent Application Laid-Open No.
In the devices disclosed in Japanese Patent Application Laid-Open No. 8 and Japanese Patent Application Laid-Open No. 10-307904, a biometric identification device is attached to the inside and outside of the fingerprint reading device in addition to the basic function of capturing a fingerprint. Therefore, in addition to the basic functions, a new light source, a control device for the light source, and the like are required, and there is a problem that the device becomes large and the price becomes expensive.

[0009] In the authentication device disclosed in Japanese Patent Laid-Open No. 2000-76450, the input order at the time of registration is registered in advance. Therefore, when the input order at the time of collation is different from the registration order, the pseudo fingerprint is correctly determined. However, there is a problem in that if the input order is accidentally the same as the registration information by trying the combinations of the input order several times, there is a possibility that the authentication may be performed.

It is an object of the present invention to provide a small and inexpensive pseudo-fingerprint discriminating apparatus capable of correctly discriminating a pseudo-fingerprint in any case.

[0011]

In order to achieve the above object, a first aspect of the present invention is to determine that the fingerprint image is a pseudo fingerprint based on a plurality of fingerprint images continuously captured by a fingerprint image sensor. A pseudo fingerprint discriminating device for discriminating, comprising: a calculating unit for calculating a feature value relating to a pixel value of each fingerprint image sequentially transmitted from the fingerprint imaging sensor; and a feature value storing a predetermined number of the sequentially calculated feature values. A storage unit and a pseudo fingerprint discriminating unit that obtains an evaluation value representing a transition of the predetermined number of extraordinary amounts and discriminates the pseudo fingerprint based on the evaluation value are provided.

A bio-fingerprint is a conductor and has a small amount of charge capacity. When a finger is placed on a fingerprint sensor, a charge is released from the charge capacity. In addition, the pressing pressure when the finger is placed on the fingerprint sensor gradually increases with time. Therefore, the pixel values of the obtained fingerprint image and the variations thereof change with time. On the other hand, in the case of a pseudo fingerprint containing gelatin as a component, the above transition amount is small. According to the above configuration, a feature amount relating to pixel values of a plurality of fingerprint images sequentially captured is calculated, and the pseudo fingerprint is determined based on an evaluation value representing a transition of a predetermined number of feature amounts. Therefore, the pseudo fingerprint is distinguished from the bio fingerprint and is correctly determined based on the evaluation value that is significantly different between the bio fingerprint and the pseudo fingerprint.

In one embodiment, in the pseudo fingerprint discriminating apparatus according to the first aspect of the present invention, the calculating unit calculates a standard deviation value as a feature amount related to a pixel value of the fingerprint image. The pseudo-fingerprint determining unit is characterized in that the degree of change in the predetermined number of standard deviation values is obtained as the evaluation value.

According to this embodiment, in the case of a bio-fingerprint, the pseudo-fingerprint is used as the bio-fingerprint by utilizing the fact that the standard deviation of the pixel values of the predetermined number of fingerprint images increases with time. Is distinguished correctly.

In one embodiment, in the pseudo fingerprint discriminating apparatus according to the first aspect of the present invention, the calculating section calculates an added value of a value obtained by binarizing each pixel value as a feature value relating to the pixel value of the fingerprint image. Is calculated, and the pseudo fingerprint discriminating section obtains the degree of change in the predetermined number of added values as the evaluation value.

According to this embodiment, in the case of a biometric fingerprint, the fact that the sum of the binarized pixel values of the predetermined number of fingerprint images rises with time is utilized. The pseudo fingerprint is distinguished from the biometric fingerprint and is correctly determined.

In one embodiment, in the pseudo fingerprint discriminating apparatus according to the first aspect of the present invention, the calculating unit calculates a standard deviation value as a feature amount related to a pixel value of the fingerprint image; A second calculating unit that calculates an added value of the binarized value of each pixel value as a feature amount, wherein the pseudo fingerprint discriminating unit determines the degree of change in the predetermined number of standard deviation values as the evaluation value and the degree of change. The degree of change in a predetermined number of added values is obtained, and when at least one of the evaluation values is less than a threshold value, the fingerprint is determined to be the pseudo fingerprint.

According to this embodiment, based on the standard deviation of pixel values for the predetermined number of fingerprint images and the sum of binarized pixel values, the pseudo-fingerprint and the biometric fingerprint are further determined. It is accurately distinguished and accurately determined.

In one embodiment, the pseudo fingerprint discriminating apparatus according to the first aspect of the present invention further comprises an image feature registering section for registering the predetermined number of feature amounts relating to the biometric fingerprint calculated by the calculating section. The pseudo-fingerprint determination unit, as the evaluation value, the transition of the predetermined number of feature amounts for the fingerprint to be determined calculated by the calculation unit, and the predetermined number of feature amounts for the registered biometric fingerprint. It is characterized in that a correlation value with a transition is obtained.

According to this embodiment, based on the correlation value between the transition of the characteristic amount of the biometric fingerprint registered in advance in the image characteristic registration unit and the transition of the characteristic amount of the fingerprint to be discriminated, the pseudo fingerprint is obtained. Is more accurately distinguished from the biometric fingerprint and is correctly determined.

According to a second aspect of the present invention, there is provided a fingerprint collating apparatus which authenticates an individual by collating a fingerprint image picked up by a fingerprint image sensor with a registered fingerprint image. When the pseudo fingerprint discriminating apparatus determines that the captured fingerprint image is not a pseudo fingerprint but a biological fingerprint, the fingerprint image is compared with the registered fingerprint image.

According to the above configuration, the comparison with the registered fingerprint image is performed based only on the fingerprint image previously determined to be a biological fingerprint by the pseudo fingerprint determining device. Therefore, authentication of the individual by the pseudo fingerprint is prevented.

In one embodiment, in the fingerprint collating apparatus according to the second invention, a frame memory for temporarily storing a fingerprint image picked up by the fingerprint image sensor is provided;
A first density distribution creating unit that creates a pixel density distribution in one direction in the stored one fingerprint image, and a second density creation unit that creates a pixel density distribution in the other direction intersecting the one direction in the fingerprint image. (2) A rectangular fingerprint area is extracted from the fingerprint image based on the pixel density distribution in one direction and the pixel density distribution in the other direction, based on the pixel density distribution in one direction, and the pseudo fingerprint discriminating apparatus determines the fingerprint image as the fingerprint image. It is characterized by including a rectangular area extracting unit for sending.

According to the above configuration, only the rectangular fingerprint area from which the background area has been removed from the fingerprint image is sent to the pseudo fingerprint discriminating apparatus. Therefore, in the pseudo fingerprint discriminating apparatus, the calculation processing of the feature amount regarding the pixel value of each fingerprint image in the calculation unit is rapidly performed.

[0025]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described in detail with reference to the illustrated embodiments. In the present embodiment, by continuously capturing images captured by the fingerprint sensor,
The degree of change in a captured image is extracted, and a biological fingerprint and a pseudo fingerprint are discriminated based on the degree of change.

FIG. 1 is a block diagram of a fingerprint collating apparatus equipped with the pseudo fingerprint discriminating apparatus of the present embodiment. The fingerprint sensor 1 is a capacitance type sensor and can capture a fingerprint on the surface of a finger. In this capacitance type sensor, in the case of a pseudo fingerprint made of rubber such as silicon, a fingerprint image is not generated because no charge is generated on the surface due to its principle. Therefore, the pseudo fingerprint made of rubber can be eliminated. However, even if an optical sensor or the like is used as the fingerprint sensor 1, the pseudo fingerprints can be determined by extracting the degree of change in the image because each person's finger placement is unique. it can.

As shown in FIG. 2, the capacitance type sensor 1 has a basic structure in which a plurality of capacitors 12 are arranged on a silicon wafer 11 and an amplifier 13 is connected to the arranged capacitors 12. Have. Biological fingerprints are conductors and have a small amount of charge capacity. Therefore, when the fingerprint 14 is placed on the capacitance type sensor 1,
Since the surface of the fingerprint 14 has irregularities, the capacitance (= Cr) of the capacitor 12 increases in the convex portion (ridge portion), while the capacitance (Cb) of the capacitor 12 decreases in the concave portion. By utilizing this, the capacitance sensor 1 captures and captures the unevenness of the fingerprint as an image based on the output from the amplifier 13.

FIGS. 3 and 4 show the transition of the standard deviation of the pixel value in one frame of image for each pseudo-fingerprint and bio-fingerprint using gelatin as components and the binarization of the pixel value. And the transition of the number of bright pixels. In the case of a biometric fingerprint, if a fingerprint image is continuously captured by the capacitance type sensor 1, the image becomes clear with the lapse of time (elapse of a frame) due to the charge accumulation effect. However, in the case of a pseudo fingerprint containing gelatin as a component, there is little change in the image regardless of the passage of time. In the present embodiment, the pseudo fingerprint is determined by using the degree of change with time of the image.

Thus, the image data of the fingerprint image picked up by the capacitance type sensor 1 (hereinafter simply referred to as a fingerprint image) is stored in the input fingerprint control unit 2 and
It is transferred to the pseudo fingerprint discrimination processing unit 3. The specific configuration of the pseudo fingerprint discrimination processing unit 3 is shown in FIG. Further, the input fingerprint control unit 2 controls the capacitance type sensor 1 to continuously capture a fingerprint image.

The pseudo-fingerprint discriminating section 3 discriminates whether the fingerprint imaged on the basis of the input fingerprint image is a biometric fingerprint or a pseudo-fingerprint. When it is determined that the fingerprint is a biological fingerprint, the input fingerprint control unit 2 is notified of the determination. On the other hand, when it is determined that the fingerprint is a pseudo fingerprint, the result is notified to the result notification processing unit 10. The input fingerprint control unit 2 sends the stored fingerprint image to the preprocessing unit 4 upon receiving the notification that the input fingerprint is a biometric fingerprint from the pseudo fingerprint discrimination processing unit 3. Then, the preprocessing unit 4 performs a process for improving the quality of the fingerprint image. Then, the characteristic information of the fingerprint is extracted by the characteristic extraction processing unit 5 from the fingerprint image after the processing. The feature information is feature point information generally called a minutiae.

The feature information extracted by the feature extraction processing unit 5 is sent to a recognition control unit 6. The recognition control unit 6 controls the registration processing unit 7 to perform fingerprint registration processing, and controls the matching processing unit 8 to perform fingerprint matching processing. In the case of fingerprint registration processing, the recognition control unit 6 sends the feature information from the feature extraction processing unit 5 to the registration processing unit 7 and stores it in the registration memory 9. On the other hand, in the case of the fingerprint collation processing, the recognition control unit 6 sends the feature information from the feature extraction processing unit 5 to the collation processing unit 8. Then, the feature information stored in the registration memory 9 is sent to the matching processing unit 8, and the matching processing unit 8 performs a matching process on both the feature information. Then, the collation result is sent to the result notification processing unit 10, and the result notification processing unit 10 displays the collation result on a display or the like. Further, when the result notification processing unit 10 receives the notification of the pseudo fingerprint from the pseudo fingerprint discrimination processing unit 3, the result notification processing unit 10 displays the judgment result indicating the pseudo fingerprint on a display or the like.

Next, referring to FIG. 5, the operation of determining whether the fingerprint is a biometric fingerprint or a pseudo fingerprint by the pseudo fingerprint discrimination processing unit 3 will be described in detail. Here, the pseudo fingerprint discrimination processing unit 3 shown in FIG. 5 has a configuration based on the transition result of the standard deviation of the pixel values shown in FIG. The fingerprint image from the input fingerprint control unit 2 is input to the standard deviation calculation unit 21, and the standard deviation S of the fingerprint image is calculated according to the following equation (1). Here, f (i, j): pixel value 0 ≦ i <n 0 ≦ j <mn n: number of horizontal pixels of the fingerprint image m: number of vertical pixels of the fingerprint image

The standard deviation value for each fingerprint image calculated by the above equation (1) is stored in the standard deviation memory 22. Thus, the standard deviation value memory 22 stores the standard deviation values of the fingerprint images from the first frame to the Nth frame (the 26th frame in FIG. 3) sequentially transmitted from the standard deviation calculation unit 21. . Using the stored N standard deviation values, the standard deviation change degree determination unit 23 determines whether the fingerprint is a biometric fingerprint or a pseudo fingerprint according to Expression (2) by using the evaluation value V (e, s). S (e) is the maximum value of the N standard deviation values,
S (s) is the minimum value of the N standard deviation values. V (e, s) = S (e) −S (s) e ≠ s If V (e, s) ≧ Th Result 1 ... (2) Else Result 0

That is, the standard deviation change degree determining section 2
If the evaluation value V (e, s) is equal to or larger than the threshold value Th, it is determined that the fingerprint is a biometric fingerprint, and the result 3 is returned to the input fingerprint control unit 2.
On the other hand, if the evaluation value V (e, s) is less than the threshold value Th, it is determined that the fingerprint is a pseudo fingerprint, and the result “0” is output to the result notification processing unit 1.
It is sent to 0.

FIGS. 6 to 8 show a specific configuration of the pseudo fingerprint discrimination processing unit 3 different from that of FIG. The pseudo fingerprint discrimination processing unit 3 shown in FIG. 6 has a configuration based on the transition result of the number of bright pixels when the pixel values shown in FIG. 4 are binarized. The fingerprint image from the input fingerprint control unit 2 is converted to a binarized addition unit 2
5, each pixel value in the fingerprint image is binarized and added. In this way, the total number of bright pixels whose binary value is “1” is calculated. In this case, the binarization is performed by a binarization process using a discriminant analysis method (1980 IEICE (D) Vol.
J63-D, No. 42, pp349-356, “Automatic threshold selection method based on discriminant analysis and least square criterion”).

The calculated sum of the binarized values for each fingerprint image is stored in the sum memory 26. Thus,
The addition value memory 26 stores the above addition values of N frames of fingerprint images sequentially transmitted from the binarization addition unit 25. Then, the added value change degree determination unit 27 uses the stored N added values to determine whether it is a biometric fingerprint or a pseudo fingerprint according to Expression (3), and evaluates the evaluation value X (e, s). ). Note that B (e) is the maximum value of the N added values, and B (s) is the minimum value of the N added values. X (e, s) = B (e) −B (s) e ≠ s If X (e, s) ≧ Tb Result 1 (3) Else Result 0

That is, the added value change degree determination section 27
If the evaluation value X (e, s) is equal to or larger than the threshold value Tb, it is determined that the fingerprint is a biological fingerprint, and the result “1” is returned to the input fingerprint control unit 2. On the other hand, if the evaluation value X (e, s) is less than the threshold value Tb, it is determined that the fingerprint is a pseudo fingerprint, and the result “0” is returned to the result notification processing unit 10.
It is sent to.

The pseudo fingerprint discriminating unit 3 shown in FIG.
Has a configuration based on the transition result of the standard deviation of the pixel values shown in FIG. 5 and a configuration based on the transition result of the number of bright pixels shown in FIG. The fingerprint image from the input fingerprint control unit 2 is input to the standard deviation calculating unit 31 and the binarizing adding unit 33, and the standard deviation calculating unit 31 calculates the standard deviation S of the fingerprint image according to the above equation (1). Each pixel value in the fingerprint image is binarized and added by the binarization adding unit 33.

The standard deviation values of the N frames of fingerprint images sequentially transmitted from the standard deviation calculating section 31 are stored in the standard deviation memory 32. Further, the addition value of the fingerprint images of N frames sequentially transmitted from the binarization addition unit 33 is stored in the addition value memory 34.
Then, the change degree comprehensive determination unit 35 uses the stored N standard deviation values and the N added values to calculate the equation (4).
Is determined based on the evaluation value V (e, s) and the evaluation value X (e, s). Note that S
(e) and B (e) are the maximum values of the N standard deviation values and the added values. S (s) and B (s) are the minimum values of the N standard deviation values and the added values. V (e, s) = S (e) −S (s) e ≠ s X (e, s) = B (e) −B (s) If V (e, s) ≧ Th (4) and X (e, s) ≧ Tb Result 1 Else Result 0

That is, the change degree comprehensive judgment section 35
If the evaluation value V (e, s) is greater than or equal to the threshold Th and the evaluation value X (e, s) is greater than or equal to the threshold Tb, it is determined that the fingerprint is a biological fingerprint, and the result “1” is input. Return to control unit 2. On the other hand, if the evaluation value V (e, s) is less than the threshold value Th or the evaluation value X (e, s) is less than the threshold value Tb, it is determined that the fingerprint is a pseudo fingerprint and the result is “0”. Is sent to the result notification processing unit 10.

The pseudo fingerprint discriminating unit 3 shown in FIG.
Has a configuration based on the transition result of the standard deviation of the pixel values shown in FIG. 5 and a configuration based on the transition result of the number of bright pixels shown in FIG. When determining whether the fingerprint is a biometric fingerprint or a pseudo fingerprint, the fingerprint image of the registrant is used.
(I.e. fingerprint image of a living body fingerprint) is to determine on the basis of the correlation between the correlation and the bright pixel number of changes in the trend of the standard deviation obtained from.

The standard deviation calculation unit 41, standard deviation value memory 42, binarization addition unit 43 and addition value memory 44 in FIG. 8 correspond to the standard deviation calculation unit 31, standard deviation value memory 32, binarization addition Unit 33 and addition value memory 34
Is the same as Then, the input fingerprint control unit 2 (see FIG. 1)
Reads the sum of the standard deviation value and the binarized value for N frames of the registrant stored in the standard deviation value memory 42 and the addition value memory 44 at the time of registration, and stores the characteristic information in the registration memory 9. Is to be stored together. The registration memory 9 has a storage area for the standard deviation value and a storage area for the sum of the binarized values.

At the time of the collation processing, the fingerprint sensor 1
The fingerprint image of the input person imaged at is input from the input fingerprint control unit 2 to the standard deviation calculation unit 41 and the binarization addition unit 43,
The obtained sum of the N standard deviation values and the binarized values is stored in the standard deviation memory 42 and the sum memory 44. Then, the change degree correlation processing unit 45 calculates the sum of the N standard deviation values and the binarized values of the input person stored above and the N standard deviations of the registrant stored in the registration memory 9. Using the value and the sum of the binarized values, determination as to whether the fingerprint is a biometric fingerprint or a pseudo fingerprint is made based on the evaluation value P (i, k) according to equation (5). Note that Bi (s) and Vi (s) are the sum of the binarized values and the standard deviation in the s-th frame of the registrant i. Bk (s) and Vk (s) are the s-th of the input person.
The sum of the binarized values and the standard deviation in the frame. P (i, k) = α · Pb + β · Pv (5) where α, β: constant α + β ≦ 1 If P (i, k) ≦ Tp Result 1 Else Result 0

That is, Pb is the residual sum of squares of the added value of the registrant and the input person, and Pv is the residual square sum of the standard deviation value of the registrant and the input person. It can be considered that the smaller the residual sum of squares, the better the correlation.
Therefore, if the evaluation value P (i, k) is equal to or smaller than the threshold value Tp, the change degree correlation processing unit 45 determines that the fingerprint is a registered fingerprint (biological fingerprint) and returns a result “1” to the input fingerprint control unit 2. . On the other hand, if the evaluation value P (i, k) is less than the threshold value Tp, it is determined that the fingerprint is a pseudo fingerprint, and the result “0” is sent to the result notification processing unit 10.

The input fingerprint control unit 2 extracts a rectangular partial fingerprint image consisting of a fingerprint area from the fingerprint image picked up by the capacitance type sensor 1, and converts the extracted partial fingerprint image into a pseudo fingerprint. The data is sent to the determination processing unit 3. FIG. 9 is a block diagram of the partial fingerprint image extraction unit 51 provided in the input fingerprint control unit 2 and extracting the partial fingerprint image. Hereinafter, a partial fingerprint image extraction processing operation by the partial fingerprint image extracting unit 51 will be described.

The fingerprint image for one frame input to the input fingerprint control unit 2 is temporarily stored in the frame memory 52 in the partial fingerprint image extraction unit 51. Then, the vertical density distribution creating unit 53 creates a vertical density distribution of the fingerprint image stored in the frame memory 52. The horizontal density distribution creating unit 54 creates a horizontal density distribution.

Here, the density distribution means a distribution of the projection density Yhist (i) in the vertical direction and a projection density Xhist (j) in the horizontal direction.
And is calculated by equation (6). Here, f (i, j): pixel value 0 ≦ i <n 0 ≦ j <mn n: number of horizontal pixels of the fingerprint image m: number of vertical pixels of the fingerprint image

Thus, the above-mentioned density distributions Yhist (i), Xhist
When (j) is calculated, the rectangular area extraction unit 55 extracts a partial fingerprint image based on the vertical density distribution Yhist (i) and the horizontal density distribution Xhist (j).

That is, first, according to equation (7), the difference between the vertical pixel row in which the difference between adjacent vertical density values Yhist (i) is larger than the threshold value Ti and the difference between the adjacent horizontal density Xhist (j) is calculated. Is larger than the threshold value Tj. i: 0 → n / 2 If | Yhist (i) −Yhist (i + 1) |> Ti Si = i Else Si = 0 i: (n−1) → n / 2 If | Yhist (i) −Yhist ( i-1) |> Ti Ei = i Else Ei = n-1 j: 0 → m / 2 (7) If | Xhist (j) −Xhist (j + 1) |> Tj Sj = j Else Sj = 0 j: (m−1) → m / 2 If | Xhist (j) −Xhist (j−1) |> Tj Ej = j Else Ej = m−1

Then, for i = 0 to n / 2, the minimum of the number i of the pixel row in which the difference between the adjacent vertical density values Yhist (i) is larger than the threshold value Ti (ie, Si where SiＳ0) is the minimum. Find the value S (I). Also, for i = n / 2 to (n−1),
The number i of the pixel row in which the difference between the adjacent vertical density values Yhist (i) is larger than the threshold value Ti (that is, Ei ≠ (n−1))
Find the maximum value E (I) of i). For j = 0 to m / 2, the minimum value S (J) of the pixel row number j (that is, Sj where Sj ≠ 0) where the difference between adjacent horizontal density values Xhist (j) is larger than the threshold value Tj. ). Further, for j = m / 2 to (m-1), the number j of the pixel row in which the difference between the adjacent horizontal density values Xhist (j) is larger than the threshold value Tj (that is, Ej which is Ejｍ (m-1)) ) Is obtained. Then, a rectangular area in the input fingerprint image that satisfies S (I) ≦ i ≦ E (I) and S (J) ≦ j ≦ E (J) is extracted as the partial fingerprint image.

As described above, the input fingerprint control section 2 has the partial fingerprint image extracting section 51, and extracts a rectangular partial fingerprint image from the fingerprint image picked up by the capacitance type sensor 1 to simulate it. It is sent to the fingerprint discrimination processing unit 3. Therefore, the target fingerprint image when the standard deviation S is calculated by the pseudo fingerprint discrimination processing unit 3 having the configuration shown in FIGS. 5 and 7 and the binary fingerprint image by the pseudo fingerprint discrimination processing unit 3 having the configuration shown in FIGS. The target fingerprint image in the case of being converted and added is limited to an image of only the fingerprint region from which the surrounding background region has been removed. Therefore, the standard deviation calculation process and the binarization / addition process can be performed quickly.

As described above, in the present embodiment,
A pseudo fingerprint discrimination processing unit 3 is provided, and a standard deviation calculation unit 21 sets a standard value of each pixel value for each frame based on fingerprint images of a predetermined number of frames sequentially picked up and picked up by the capacitance type sensor 1. Calculate the deviation and store it in the standard deviation memory 2
2 is stored. Then, the difference between the maximum value and the minimum value in the standard deviation value of each frame is obtained by the standard deviation change degree determination unit 23, and if the value is equal to or larger than the threshold value, it is determined that the fingerprint is a biometric fingerprint. If it is less than the threshold value, it is determined that the fingerprint is a pseudo fingerprint. Therefore, if the threshold value is set higher than the difference between the maximum value and the minimum value of the standard deviation value in the case of a pseudo fingerprint containing gelatin whose transition amount of the standard deviation is small, the pseudo fingerprint of gelatin can be obtained. However, it can be accurately determined.

That is, according to the present embodiment, a pseudo fingerprint can be determined only by image processing on the fingerprint image picked up by the capacitance type sensor 1 and a new function other than the basic function as the fingerprint collating device is provided. There is no need to mount a light source or a control device for the light source. Therefore, problems such as an increase in the size of the device and an increase in price do not occur.

Also, comparing the pseudo-fingerprint of gelatin and the bio-fingerprint with respect to the transition amount of the input image obtained by binarizing and adding each pixel value, the bio-fingerprint is larger.
Therefore, the pseudo fingerprint discrimination processing unit 3 is configured as shown in FIG. 6, and the binarized addition unit 25 binarizes each pixel value and stores the binarized value in the addition value memory 26. Then, the difference between the maximum value and the minimum value in the above-described addition value of each frame is obtained by the addition value change degree determination unit 27. If the difference is less than the threshold value, it is determined that the fingerprint is a pseudo fingerprint. Fingerprints can be accurately determined.

Alternatively, the pseudo fingerprint discrimination processing unit 3 is configured as shown in FIG.
If the difference between the maximum value and the minimum value in the standard deviation value of each frame is less than the threshold value, or if the difference between the maximum value and the minimum value in the added value of each frame is less than the threshold value,
It can also be determined that it is a pseudo fingerprint.

Alternatively, the pseudo fingerprint discrimination processing unit 3 is configured as shown in FIG. 8, and at the time of registration, the standard deviation calculated by the standard deviation calculation unit 41 and stored in the standard deviation memory 42, and the binarization The addition value of the binarized value calculated by the addition unit 43 and stored in the addition value memory 44 is registered in the registration memory 9 in FIG. 1 together with the characteristic information of the registrant's fingerprint. At the time of collation, if the evaluation value based on the residual sum of squares of the added value and the standard deviation value of the input person and the registrant is less than the threshold value, the change degree correlation processing unit 45 performs a pseudo operation. It can also be determined that it is a fingerprint.

The input fingerprint control unit 2 according to the present embodiment has a partial fingerprint image extracting unit 51, and a rectangular partial fingerprint consisting of a fingerprint area from a fingerprint image picked up by the capacitance type sensor 1. The image is extracted and the pseudo fingerprint discrimination processing unit 3
To be sent to. Therefore, the standard deviation calculation processing and the binarization / addition processing performed by the pseudo fingerprint discrimination processing unit 3 can be performed quickly thereafter.

In the above embodiment, the fingerprint sensor 1 is constituted by a capacitance type sensor. However, even in the case of the optical sensor, the fingerprint image changes with time because of the characteristic that the pressure of the finger of the person gradually increases. Therefore, even when an optical sensor is used as the fingerprint sensor 1, a pseudo fingerprint can be determined in the same manner. However, when a capacitance type sensor is used, a fingerprint image is not generated in the case of a pseudo fingerprint made of rubber such as silicon. For this reason, a pseudo fingerprint made of rubber such as silicon can be eliminated in advance, and the discrimination accuracy is improved by that amount, which is desirable.

Further, in the above embodiment, the difference between the maximum value and the minimum value in the standard deviation value of each frame,
Alternatively, the pseudo fingerprint is determined based on the difference between the maximum value and the minimum value of the binarized value of each frame. However, the determination is not always necessary, and the determination may be made based on the difference between the standard deviation values or the difference between the first frame and the Nth frame. In short, the determination may be made based on the transition of the standard deviation value or the added value.

In the pseudo fingerprint discrimination processing section 3 shown in FIG. 8, the standard deviation memory 42 and the addition memory 44 are used.
Is stored in the registration memory 9 for storing the feature information described above. However, the present invention is not limited to this, and a dedicated image feature registration memory for storing the sum of the standard deviation value and the binarized value of the registrant may be provided.

In the pseudo fingerprint discrimination processing unit 3 shown in FIG. 8, the standard deviation calculated by the standard deviation calculation unit 41 and the sum of the binarized values calculated by the binarization addition unit 43 are calculated. Based on this, a pseudo fingerprint is determined. However, in the present invention, a configuration may be adopted in which a pseudo fingerprint is determined based on one of the standard deviation and the added value.

[0062]

As is clear from the above description, the pseudo fingerprint discriminating apparatus of the first invention calculates the feature value related to the pixel value of each fingerprint image sequentially transmitted from the fingerprint imaging sensor by the calculation unit, and calculates the pseudo fingerprint. The discrimination unit discriminates the pseudo fingerprint based on a predetermined number of evaluation values representing the transition of the extraordinary amount. In addition, the pseudo fingerprint can be correctly distinguished from the biometric fingerprint.

In one embodiment of the pseudo fingerprint discriminating apparatus, the calculating section calculates a standard deviation value as the feature quantity, and the pseudo fingerprint discriminating section calculates the standard deviation value for the predetermined number of standard deviation values. Since the degree of change is obtained as the evaluation value, in the case of a biometric fingerprint, the pseudo value is increased by using the characteristic that the standard deviation value of the pixel value of the predetermined number of fingerprint images increases with time. Fingerprints can be distinguished correctly from biological fingerprints.

In one embodiment of the pseudo fingerprint discriminating apparatus, the calculation unit is configured to binarize a pixel value as the feature value to calculate an added value, Since the degree of change in the sum of the numbers is determined as the evaluation value, in the case of a biometric fingerprint, the pseudo fingerprint is referred to as a biometric fingerprint by utilizing the feature that the sum increases with time. The distinction can be made correctly.

In one embodiment of the pseudo fingerprint discriminating apparatus, the calculation unit includes a first calculation unit that calculates a standard deviation value as the feature amount, and a first calculation unit that calculates a binary value of each pixel value as the feature amount. A second calculating unit for calculating an added value, wherein the pseudo fingerprint discriminating unit obtains the degree of change in the predetermined number of standard deviation values and the degree of change in the predetermined number of added values as the evaluation value. When at least one of the evaluation values is less than the threshold value, it is determined to be the pseudo-fingerprint, so that the standard deviation value of the pixel values for the predetermined number of fingerprint images and the pixel values are binarized. Based on the sum of the values, the pseudo-fingerprint can be distinguished from the bio-fingerprint with higher accuracy and correctly determined.

Further, in the pseudo fingerprint discriminating apparatus of one embodiment, the feature quantity relating to the biometric fingerprint calculated by the above calculating section is registered in the image feature registering section, and the pseudo fingerprint discriminating section is associated with the fingerprint to be discriminated. Since the correlation value between the transition of the characteristic amount and the transition of the characteristic amount relating to the registered biometric fingerprint is obtained as the evaluation value, the characteristic of the biometric fingerprint registered in advance in the image characteristic registration unit is obtained. Based on the correlation value with the change in the amount, the pseudo fingerprint can be more accurately distinguished from the biometric fingerprint and correctly discriminated.

Further, the fingerprint collating apparatus of the second invention comprises the pseudo fingerprint discriminating apparatus of the first invention, and when the result of the discrimination by the pseudo fingerprint discriminating apparatus is a biometric fingerprint, the fingerprint collating apparatus with the registered fingerprint image is used. Since the collation is performed, it is possible to prevent the individual from being authenticated by the pseudo fingerprint.

In this case, since the pseudo fingerprint discriminating apparatus only uses the captured fingerprint image, the basic function of the fingerprint collating apparatus can be used as it is.
No special living body identification device such as a special light source and its control device is required. Therefore, problems such as an increase in the size of the apparatus and an increase in the price do not occur.

Further, the fingerprint collation apparatus according to the embodiment generates a first density distribution by distributing the pixel density in one direction in one fingerprint image which is imaged by the fingerprint image sensor and temporarily stored in the frame memory. , A pixel density distribution in the other direction is created by the second density distribution creating section, and a rectangular fingerprint area is extracted by the rectangular area extracting section based on the pixel density distribution in both directions, and the pseudo fingerprint is created. Since the fingerprint image is sent to the discrimination device as the fingerprint image, the pseudo fingerprint discrimination device allows the calculation unit to quickly calculate the characteristic amount related to the pixel value of each fingerprint image based on the fingerprint region from which the background region has been removed. Can be done.

[Brief description of the drawings]

FIG. 1 is a block diagram of a fingerprint collating apparatus equipped with a pseudo fingerprint discriminating apparatus of the present invention.

FIG. 2 is a basic structural diagram of the capacitance type sensor in FIG.

FIG. 3 is a diagram showing the transition of the standard deviation of the pixel value between a pseudo fingerprint and a biological fingerprint containing gelatin as a component.

FIG. 4 is a diagram showing a change in the number of bright pixels in a pseudo fingerprint and a bio fingerprint using gelatin as a component.

FIG. 5 is a specific block diagram of a pseudo fingerprint discrimination processing unit in FIG. 1;

FIG. 6 is a specific block diagram different from FIG. 5;

FIG. 7 is a specific block diagram different from FIGS. 5 and 6;

FIG. 8 is a specific block diagram different from FIGS.

9 is a block diagram of a partial fingerprint image extraction unit provided in the input fingerprint control unit in FIG.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 ... Fingerprint sensor (capacitance sensor), 2 ... Input fingerprint control part, 3 ... Pseudo fingerprint discrimination processing part, 4 ... Preprocessing part, 5 ... Feature extraction processing part, 6 ... Recognition control part, 7 ... Registration processing 8: collation processing unit, 9: registration memory, 10: result notification processing unit, 21, 31, 41: standard deviation calculation unit, 22, 32, 42: standard deviation value memory, 23: standard deviation change degree determination unit .., 25, 33, 43... Binarization addition section, 26, 34, 44... Addition value memory, 27... Addition value change degree determination section, 35. Partial fingerprint image extraction unit, 52: frame memory, 53: vertical density distribution creation unit, 54: horizontal density distribution creation unit, 55: rectangular area extraction unit

Claims (7)

[Claims] 1. A pseudo fingerprint discriminating device for discriminating that a fingerprint image is a pseudo fingerprint based on a plurality of fingerprint images continuously picked up by a fingerprint image sensor, wherein the pseudo image is sequentially transmitted from the fingerprint image sensor. A calculation unit that calculates a feature amount related to the pixel value of each fingerprint image to be obtained, a feature amount storage unit that stores a predetermined number of feature amounts that are sequentially calculated, and an evaluation value that represents a transition of the predetermined number of extraordinary amounts. A pseudo fingerprint discriminating apparatus comprising: a pseudo fingerprint discriminating unit that determines the pseudo fingerprint based on the evaluation value. 2. The pseudo fingerprint discriminating apparatus according to claim 1, wherein the calculation unit calculates a standard deviation value as a feature amount related to a pixel value of the fingerprint image. And a degree of change in the predetermined number of standard deviation values is obtained as the evaluation value. 3. The pseudo fingerprint discriminating apparatus according to claim 1, wherein the calculation unit calculates, as a feature amount related to a pixel value of the fingerprint image, an added value of a value obtained by binarizing each pixel value. The pseudo fingerprint discriminating apparatus is characterized in that the pseudo fingerprint discriminating unit obtains a degree of change in the predetermined number of added values as the evaluation value. 4. The pseudo fingerprint discriminating apparatus according to claim 1, wherein the calculating unit calculates a standard deviation value as a feature amount related to a pixel value of the fingerprint image, and each pixel as the feature amount. A second calculating unit that calculates an added value of the binarized value, wherein the pseudo fingerprint discriminating unit determines the degree of change in the predetermined number of standard deviation values as the evaluation value and the added value of the predetermined number. A pseudo-fingerprint discriminating device, wherein the pseudo-fingerprint discriminating device is adapted to determine the degree of change in the pseudo-fingerprint, and to determine the pseudo-fingerprint when at least one of the evaluation values is less than the threshold value. 5. The pseudo fingerprint discriminating apparatus according to claim 1, further comprising: an image feature registering section for registering the predetermined number of feature amounts relating to the bio-fingerprint calculated by the calculating section. The section is a correlation value between a transition of the predetermined number of feature amounts regarding the fingerprint to be determined calculated by the calculation unit and a transition of the predetermined number of feature amounts regarding the registered biometric fingerprint, as the evaluation value. A pseudo fingerprint discriminating apparatus characterized in that the pseudo fingerprint is determined. 6. A fingerprint matching device for matching a fingerprint image picked up by a fingerprint image sensor with a registered fingerprint image to authenticate an individual, wherein the pseudo fingerprint according to any one of claims 1 to 5 is provided. A fingerprint identification device for identifying the captured fingerprint image as a bio-fingerprint instead of a pseudo-fingerprint, and collating the fingerprint image with the registered fingerprint image. apparatus. 7. The fingerprint collation device according to claim 6, wherein a frame memory for temporarily storing a fingerprint image picked up by the fingerprint image sensor, and a pixel in one direction in the stored one fingerprint image. A first density distribution creating section for creating a density distribution; a second density distribution creating section for creating a pixel density distribution in the fingerprint image in the other direction intersecting the one direction; and a pixel density in the one direction. A rectangular area extracting unit that extracts a rectangular fingerprint area from the fingerprint image based on the distribution and the pixel density distribution in the other direction, and sends the rectangular fingerprint area to the pseudo fingerprint discriminating apparatus as the fingerprint image. Fingerprint collation device.