JPH09259272A - Living body recognition method in fingerprint collation - Google Patents

Abstract

PROBLEM TO BE SOLVED: To prevent an improper use by a pseudo fingerprint in the case of identifying a biological fingerprint and the pseudo fingerprint. SOLUTION: Image signals for which the image of a fingerprint is picked up are binarized, the black picture elements of fingerprint images for one screen for which a dent line is indicated by the black picture elements and an elevation line is indicated by white picture elements are reprieved and the continuity of the black picture elements is identified. Whether or not a continuous picture element number is less than a first threshold value is judged and a sweat gland present not on the dent line but on the elevation line is judged when it is less than the first threshold value. Then, the sweat gland is counted up over one screen, whether or not the counted value is more than a second threshold value is judged, biological fingerprint stamping is judged in the case that it is more than the second threshold value and pseudo fingerprint stamping is judged in the case that the counted value of the sweat gland is not more than the second threshold value.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a biometric recognition method for distinguishing whether an imprinted fingerprint in fingerprint matching is a biometric fingerprint or a pseudo fingerprint. The fingerprint collation is a collation of a fingerprint registered in advance and a newly imprinted fingerprint to confirm the identity. The registered fingerprint in this case is obtained by binarizing a multi-valued image signal of an imprinted fingerprint to detect a plurality of feature points, and registering a region of a predetermined size including the feature points, including coordinate information thereof. It is stored in a file. Then, at the time of fingerprint collation, the multi-valued image signal or the binarized image signal obtained by imaging the imprinted fingerprint is compared and collated with the multi-valued image signal or the binarized image signal including the characteristic points read from the registration file, and the predetermined value is obtained. If there are coincident points in more than a few areas, it is determined that the collation coincides.

[0002]

2. Description of the Related Art FIG. 7 is a flowchart of fingerprint collation in a conventional example. A fingerprint is imprinted (C1), and the imprinted fingerprint is captured by a camera and a multi-valued image signal is captured (C2). At this time, the average luminance of the multi-valued image signal within a certain area is calculated, and if it exceeds a preset threshold value, it is determined that fingerprint imprinting has been performed, and this multi-valued image signal is binarized (C
3) Then, the collation process with the registered fingerprint is performed (C4), and it is determined whether or not the collation is successful (C5).

A fingerprint has two major feature points, that is, a ridge end point and a bifurcation point. In most fingerprint collation devices, a binary image signal of an area of a predetermined size including the feature point portion. Alternatively, the multi-valued image signal is stored in the registration file as registration data including the coordinate information of the area. The fingerprint collation process is to binarize the multi-valued image signal of the imprinted fingerprint or to collate it with the registered data of the registered fingerprint as a multi-valued image signal. When the number of matches of is equal to or more than a predetermined number, it is determined that the verification is successful, the person is confirmed (C6), and unlocking is performed. If the number is not equal to or more than the predetermined number, it is regarded as a failure and a collation process failure process is performed (C
7).

FIG. 8 is a flowchart of fingerprint registration of a conventional example, which includes fingerprint imprinting (D1) and multi-value image capturing (D1).
2), the binarization (D3) step is the same as the steps (C1) to (C3) at the time of fingerprint collation in FIG. 7, except that the binarized image is subjected to the thinning process and the thinning process. With respect to the ridge, the end points and the branch points are extracted as feature points, and based on the coordinate information of the feature points, a region of a predetermined size of the binary image signal or the multivalued image signal is cut out, and the coordinate information is obtained. At the same time, a registration process for making the registration data is performed (D4).

After the registration process, it is judged whether or not the registration is successful (D5). That is, if the characteristic points of a predetermined number or more cannot be extracted, the number of registered data is small, so that the registration is rejected and the registration failure process (D7) is performed. In that case, for example, re-registration processing is performed. If a predetermined number or more of characteristic points can be extracted, the dictionary data is registered as a pass (D6).

[0006]

In fingerprint registration and fingerprint collation, in the general case of registering and collating as a binary image signal, the finger of the registrant who has registered the fingerprint is used by a silicone rubber or the like. When a pseudo-fingerprint of a fingerprint type is imprinted, the average brightness of a multi-valued image signal captured by a camera exceeds a predetermined value, so this multi-valued image signal is captured and binarized. Then, the fingerprint matching process is performed. As a result, there is a problem that the identity is confirmed by the matching and matching. That is, there is a possibility of misuse by performing fingerprint matching by imprinting a fingerprint using a pseudo fingerprint instead of the biometric fingerprint. An object of the present invention is to prevent abuse by imprinting a pseudo fingerprint.

[0007]

A biometric recognition method in fingerprint collation according to the present invention binarizes an image signal obtained by picking up a fingerprint so that one screen portion shows valley lines by black pixels and ridge lines by white pixels. The black pixels of the fingerprint image are searched, the continuity of the black pixels is identified, and it is determined whether the number of continuous pixels is less than or equal to a first threshold value.
When it is below the first threshold value, it is determined to be a sweat gland existing in a ridge, this sweat gland is counted up over one screen, and it is determined whether or not the count value of this sweat gland is equal to or more than a second threshold value.
This includes a process of determining biometric fingerprint imprinting in the case of being equal to or larger than the second threshold value, and determines whether the finger is a living finger or a pseudo finger according to the sweat glands present in the ridge.

Further, when it is determined that the fingerprint is a biometric fingerprint, a process of registering an imprinted fingerprint including the coordinates of all sweat glands can be included. That is, fingerprint registration is performed by including the coordinates of the sweat glands along with characteristic points such as end points and bifurcation points, and when the fingerprints are collated, the sweat glands can be collated to prevent abuse by a pseudo finger.

[0009]

DESCRIPTION OF THE PREFERRED EMBODIMENTS FIG. 1 is a flow chart of a first embodiment of the present invention, showing a case of fingerprint collation, and first, it is judged whether or not fingerprint imprinting is performed (A1). As described above, this is determined as fingerprint imprinting because the average brightness in a certain area of the multi-valued image signal obtained by capturing the imprinted fingerprint with a camera exceeds a predetermined value. Next, this multi-valued image signal is taken in (A2), binarized (A3), and the black pixel of this binarized binary image signal is searched (A4).

Then, the continuity of the black pixels is checked to determine whether it is less than or equal to the threshold value (A5). This is because the valleys of the fingerprint are black pixels, the ridges are white pixels, the sweat glands existing on the ridges are black pixels, and the valleys formed by the black pixels have continuity, but the sweat glands are dispersed in dots. Therefore, it does not have continuity. Therefore, if the continuity of the black pixels is not less than or equal to the first threshold value, it is determined that it is not a sweat gland, and step (A
Go to 8).

If the continuity of black pixels is less than or equal to the first threshold value, it is regarded as a sweat gland, and the coordinates of the sweat gland in the case where the coordinates of the sweat gland are also registered as a registered fingerprint are checked (A6). Then, when the registered sweat gland coordinates and the imprinted fingerprint sweat gland coordinates match, the number of detected sweat glands is counted up (A7). If it is determined in step (A6) that the registered sweat gland coordinates and the imprinted fingerprint sweat gland coordinates do not match, the process proceeds to step (A8).

In this step (A8), it is determined whether or not the entire area of the binary image has been searched. If the search for the entire area has not been completed, step (A8)
When the process shifts to 4) and the search for the entire area is completed, it is determined whether the detected number of sweat glands is within the determination range, that is, whether the count value of the detected number of sweat glands is equal to or more than the second threshold value. A
9). If the number of detected sweat glands is within the determination range, the process shifts to collation processing (A10). If it is not within the determination range, it is determined that the finger is not a living finger and the process is forcibly terminated (A13).

In the collating process (A10), the collating process is performed on the region including the characteristic points of the fingerprint as in the conventional example, and it is determined whether or not there are a predetermined number of coincident regions or more (A1).
1) If the number of matching areas is equal to or more than a predetermined number, the person is identified (A12). If the number of matching areas is not equal to or more than a predetermined number, collation failure processing is performed (A14).

As described above, steps (A4)-(A
According to 9), the sweat gland detection process of the imprinted fingerprint is performed, and when the fingerprint image has a sweat gland and the number of the sweat glands is equal to or larger than the second threshold value, it is determined that the living finger is imprinted. Since fingerprint identification is performed by identifying and, it is possible to prevent abuse by a pseudo finger.

In a binary image of a biometric fingerprint, for example, as shown in FIG. 2, a valley line having continuity of black pixels, a ridge line of white pixels, and a plurality of sweat glands of black pixels in the ridge line. It exists. A binary image obtained by imprinting a pseudo finger made of silicone rubber or the like on the biometric fingerprint is as shown in FIG. That is, the sweat glands in the pseudo finger are crushed, so the binary image of the pseudo fingerprint is
As in the case of the image processing, the sweat component is not included, as the noise component is removed.

Therefore, as shown in FIG. 4A, a binary image of the valley line 1, the ridge line 2 and the sweat gland 3 which are enlarged and only partially shown is scanned as indicated by the one-dot chain line arrow. Black pixels are marked. (B) shows a marked black pixel. Then, as shown in (C), the continuity of the black pixels is checked by using the mask 4 having a predetermined size.

In the case of FIG. 4C, a mask having a size of 3 × 3 pixels is shown, but in general, a mask having a size of about 16 × 16 pixels can be used. In this case, the mask is moved to check the number of continuous black pixels in the vertical and horizontal directions of the target pixel. For example, in the case of a 16 × 16 pixel mask,
A group of black pixels in which an arbitrary number of black pixels in the mask are in an isolated state is determined as the sweat gland 3 instead of the valley line 1 and the coordinate value of the sweat gland 3 is held. When a mask having a small number of pixels is used, the number of continuous pixels in the vertical and horizontal directions is checked. Can be determined. In the case of the binary image of the biometric fingerprint in FIG. 2, for example, a group of black pixels in the mask that is not continuous with the black pixels outside the mask is determined to be the sweat gland 3, and a large number of the sweat glands 3 are detected. However, in the case of the pseudo fingerprint binary image of FIG. 3, the sweat glands are zero or close thereto. Therefore, the detected sweat glands are counted up, and if the count value is equal to or larger than the second threshold value, it can be reliably determined that the fingerprint is a biometric fingerprint.

FIG. 5 is a flow chart of the second embodiment of the present invention, showing the case of fingerprint registration. As in the case of the fingerprint collation described above, it is judged whether or not the fingerprint is imprinted (B1) and imprinted. In this case, the multi-valued image is captured (B2), the multi-valued image is binarized (B3), the black pixels of this binary image are searched, and the continuity of the black pixels is checked (B4).

Next, it is determined whether or not the continuity of black pixels is less than or equal to a first threshold value (B5), and if it is less than or equal to the first threshold value, it is determined to be a sweat gland and counted up (B6). Then, it is determined whether or not all areas have been searched (B7), and when the search is completed, it is determined whether or not the number of sweat glands detected is equal to or greater than the determination threshold (B8). That is, it is determined whether or not the count value of the sweat glands is equal to or larger than the second threshold value. If the count value is not equal to or larger than the second threshold value, it is determined to be a pseudo-fingerprint and forced termination (B14). Second
If it is equal to or more than the threshold value of, the coordinates of all sweat glands are registered (B9), and the number of detected sweat glands is registered (B10).

Next, similarly to the conventional example, the binary image signal of the area including the characteristic points is registered as registration data (B1
1) It is judged whether or not the registration is successful depending on whether or not the number of characteristic points is a predetermined number or more (B12), and if there is a predetermined number or more, the dictionary data is registered (B13). If there is not more than the predetermined number, registration failure processing is performed (B15).

The above-mentioned steps (B4) to (B10) show the steps of the sweat gland detection processing, and even at the time of fingerprint registration,
By determining whether the biometric fingerprint or the pseudo fingerprint is detected by the sweat gland detection and registering the coordinates of the detected sweat gland, it is possible to reliably prevent the misuse of the pseudo fingerprint.

FIG. 6 is a functional block diagram of the embodiment of the present invention, in which 11 is a fingerprint image pickup unit, 12 is an input operation unit, and 13 is an input operation unit.
Is an image input unit, 14 is a binarization unit, 15 is a black pixel search unit,
Reference numeral 16 is a continuity detection unit, 17 is a sweat gland determination unit, 18 is a collation processing unit, 19 is a registration unit, and 20 is a collation determination output unit.

The fingerprint image pickup section 11 includes a camera for picking up an imprinted fingerprint, and applies a fingerprint picked up image signal to the image input section 13. The input operation unit 12 includes a numeric keypad and the like, and inputs a fingerprint registration request, a fingerprint collation request, an identification number, and the like. Further, the image input unit 13 determines that the fingerprint is imprinted and fetches it when the average luminance in the predetermined determination exceeds the predetermined value based on the captured image signal from the fingerprint image capturing unit 11, and for example, 1 pixel is 8 bits. Digitized into 256 gradation display,
It is added to the binarization unit 14.

The image signal binarized by the binarization unit 14 is applied to the black pixel search unit 15 to search and mark black pixels for one screen, and the continuity detection unit 16 selects black pixels. Of the sweat gland determination unit 17,
If the number of continuous black pixels is greater than or equal to the first threshold, it is determined as a valley line,
If the number of continuous black pixels is less than or equal to the first threshold value, it is determined to be a sweat gland,
This sweat gland is counted up, and if the value counted for one screen is equal to or greater than the second threshold value, it is determined to be a biometric fingerprint, and if it does not exceed the second threshold value, it is determined to be a pseudo fingerprint.

The collation processing unit 18 collates the fingerprint image determined to be a biometric fingerprint with the registration unit 19 or collates with the fingerprint registered in the registration unit 19, and when it is determined to be a pseudo fingerprint, the registration process also collates. Processing is also forced to end. Further, when the identity verification is obtained as a result of the verification processing, unlocking processing or the like is performed in the verification determination output unit 20. The function of each unit described above can be realized by using a processor, an image memory, or the like.

[0026]

As described above, according to the present invention, when a fingerprint image contains a large number of sweat glands, it is determined to be a biometric fingerprint, and is distinguished from a pseudo-fingerprint that is modeled with silicone rubber or the like. When it is determined that the fingerprint is a pseudo fingerprint, the registration and the collation are forcibly terminated, and the abuse due to the imprint of the pseudo fingerprint can be prevented. Therefore, there is an advantage that the reliability in the fingerprint collation system can be further improved. If it is judged to be a biometric fingerprint,
By registering the fingerprint including the coordinates of the sweat glands, there is an advantage that the reliability of identity verification at the time of fingerprint collation can be dramatically improved.

[Brief description of drawings]

FIG. 1 is a flowchart of a first embodiment of the present invention.

FIG. 2 is an explanatory diagram of a biometric fingerprint binary image.

FIG. 3 is an explanatory diagram of a pseudo fingerprint binary image.

FIG. 4 is an explanatory diagram of sweat gland detection processing according to the embodiment of the present invention.

FIG. 5 is a flowchart according to a second embodiment of the present invention.

FIG. 6 is a functional block diagram of an embodiment of the present invention.

FIG. 7 is a flowchart of fingerprint verification in a conventional example.

FIG. 8 is a flowchart of fingerprint registration of a conventional example.

[Explanation of symbols]

 (A1) to (A14) Fingerprint matching step

Claims (2)

[Claims] 1. An image signal obtained by picking up a fingerprint is binarized,
The black pixels of the fingerprint image for one screen showing the valley line by the black pixel and the ridge line by the white pixel are searched, the continuity of the black pixels is identified, and it is determined whether or not the number of continuous pixels is less than or equal to the first threshold value. However, when it is below the first threshold value, it is determined that the sweat gland exists in the ridge, the sweat gland is counted up over one screen, and it is determined whether the count value of the sweat gland is equal to or greater than the second threshold value. A biometric recognition method in fingerprint matching, comprising the step of determining biometric fingerprint imprinting when the threshold value is 2 or more. 2. The biometric recognition method in fingerprint matching according to claim 1, further comprising a step of performing a process of registering an imprinted fingerprint including coordinates of all sweat glands when it is determined that the biometric fingerprint is imprinted. .