JPH03266187A - Fingerprint verification method - Google Patents

Abstract

PURPOSE:To surely confirm a fingerprint as the one of a principal by counting the number of feature points existing in the neighborhood of at least one feature point that coincides when a person is confirmed as the principal, and confirming the person as the principal when the number is within a certain threshold value. CONSTITUTION:A fingerprint image is inputted, and the pattern matching of the feature point is performed, and the number of feature points existing in the neighborhood of at least one feature point that coincides is counted, and collation is refused when the number exceeds the certain threshold value, and the person is recognized as the principal when it is within the certain threshold value. In other words, since a large number of forgery fingerprint false feature points exist, it can be judged that the fingerprint is the one of the false fingerprint when the number of feature points in the neighborhood of the feature point that coincides exceeds a certain constant value (threshold value). In such a way, it is possible to surely confirm the fingerprint as the one of the principal.

Description

[Detailed Description of the Invention] [Summary] This invention relates to a fingerprint matching method in which an input fingerprint image is compared with minutiae points of a registered fingerprint pattern to confirm the identity of the person. The purpose of the first invention is to input a fingerprint image, perform pattern matching of minutiae, and if a certain number or more of minutiae match and the identity of the person is confirmed, at least one The system counts the number of feature points in the vicinity of the matching feature points, and if this number exceeds a certain threshold, the match is rejected, and if it is within a certain threshold, the person is authenticated. Configure.

The second invention is to input a fingerprint image, perform pattern matching of minutiae points, and when a certain number or more of minutiae points match and the person is identified, the length of the fingerprint ridge of at least one fingerprint image is determined. If the maximum value is less than a certain threshold value, verification is rejected, and if it is more than a certain threshold value, the identity is recognized.

[Industrial Field of Application] The present invention relates to a fingerprint matching method in which an input fingerprint image is matched with minutiae points of a registered fingerprint pattern to confirm the identity of the person.

In recent years, as computers have been introduced into a wide range of social systems, system security has become a focus of interest among those concerned. Many questions have been raised about the security of ID cards and passwords, which have been used up until now to verify one's identity when entering a computer room or using a terminal. On the other hand, fingerprints have two major characteristics: they are unique to all people, and they remain unchanged throughout life, so they are considered the most powerful means of identity verification, and much research and development has been conducted on simple personal identification systems using fingerprints. There is.

[Conventional technology] FIG. 4 is a conceptual diagram of the configuration of a conventional fingerprint matching system.

First, the operation at the time of registration will be explained.

A fingerprint pattern is detected by pressing a finger against the fingerprint sensor 1, and converted into digital data by an A/D converter (not shown) within the fingerprint sensor 1.

The converted digital chill data (fingerprint data) is
The value is converted into binary data of "0" and "1" by the value circuit 2 and stored in the frame memory 3.

After the fingerprint data stored in the frame memory 3 is sequentially read out, it enters a feature information extraction/verification circuit 4, where feature information is extracted. Here, the characteristic information means, for example, Fig. 5 (
Refers to branch points as shown in (a) and end points as shown in (b). A fingerprint can be identified based on the position and shape of such branch points and end points. The extracted feature information is stored in the personal feature information data file 5. The above operations are repeated for a plurality of individuals, and the individual characteristic information is stored in the personal characteristic information data file 5.

When the registration of the amount of feature information in the personal feature information data file 5 is completed in this way, an operation for comparing the fingerprint of the individual is started. In the case of verification, when a finger (the finger used for registration in advance, for example, the index finger) is pressed against the fingerprint sensor 1, the fingerprint pattern is detected in the same way as during registration, and the A/D converter (not shown) in the fingerprint sensor 1 detects the fingerprint pattern. Convert to digital data using

The converted digital data is subsequently converted into binary data of "0" and "1" by the binarization circuit 2 and stored in the frame memory 3.

The characteristic information extraction/verification circuit 4 reads out the fingerprint data for verification stored in the frame memory 3 and the characteristic information for each individual stored in the personal characteristic information data file 5.
Perform both matching (pattern matching). When the number of matching feature information is equal to or greater than a predetermined number, it is determined that the fingerprints match.

Here, the feature information extraction/verification circuit 4 extracts the feature points (
Branching point, end point. Verification is performed by looking at the distribution and shape matching (see FIG. 5). FIG. 6 is a diagram showing an example of fingerprint verification using pattern matching. There are minutiae points 1 to 6 around the reference pattern P, and pattern matching of these minutiae points is being performed. However, since fingers are soft and elastic, the distribution and shape of the fingerprint minutiae is changes to some extent. Therefore, when performing fingerprint verification, it is necessary to provide a certain degree of tolerance to the distribution and shape of minutiae.

[Problems to be Solved by the Invention] However, if a tolerance is given to the distribution and shape of fingerprint minutiae, if a forged fingerprint with countless minutiae is input, pattern matching will not be performed due to the tolerance. ,
There is a problem where it is determined that the person is the person himself/herself. FIG. 7 is a diagram showing how pattern matching is performed on forged fingerprints. When the same feature points 1 to 6 as in FIG. 6 are matched with the fake fingerprint, most of the feature points match as shown in the figure.

The present invention has been made in view of the above-mentioned problems, and an object of the present invention is to provide a fingerprint verification method that can reliably confirm that the fingerprint is the person's fingerprint.

[Means for Solving the Problems] FIG. 1 is a flowchart showing the principle of the first invention method;
FIG. 2 is a flowchart showing the principle of the second invention method.

The first invention is to input a fingerprint image (step 1), perform pattern matching of minutiae (step 2), and if a certain number or more of minutiae match and the person is identified, at least one matching feature is detected. The number of feature points in the vicinity of the point is counted (Step 3), and if this number is above a certain threshold, the verification is rejected, and if it is within a certain threshold, the person is recognized (Step 4). ), and the second invention is configured as follows: input a fingerprint image (step 1), perform pattern matching of minutiae (step 2), and if a certain number or more of minutiae match and the identity of the person is confirmed, at least Find the maximum length of the fingerprint ridge in one fingerprint image (step 3), and if the maximum value is less than a certain threshold, the verification will be rejected, and if it is more than a certain threshold, the fingerprint ridge will be recognized as the original person. (Step 4).

[Operation] (First invention) First, the number of feature points in the vicinity of matched feature points is counted. In the case of a forged fingerprint as shown in Figure 7, the number of pseudo minutiae points is very large, so if the number of minutiae points in the vicinity of the matched minutiae point is greater than a certain value (threshold value), the fingerprint is a fake fingerprint. Therefore, it is sufficient to reject the verification. Therefore, according to the present invention, it is possible to reliably confirm that the fingerprint is the person's fingerprint.

(Second invention) As is clear from FIG. 7, it is noticed that the length of the fingerprint ridge is short in the case of a fake fingerprint. Therefore, a certain reference value (threshold value) is set for the length of the fingerprint ridge, and if the maximum value of the ridge of the read fingerprint is smaller than this threshold value, it can be determined that the fingerprint is a fake fingerprint. All you have to do is reject the verification. Therefore, according to the present invention, it is possible to reliably confirm that the fingerprint is the person's fingerprint.

[Example] Hereinafter, an example of the present invention will be described in detail with reference to the drawings.

FIG. 3 is a diagram showing an example of a system configuration for implementing the method of the present invention. In the figure, reference numeral 11 denotes a fingerprint input unit, which is composed of a fingerprint sensor and a numeric keypad for manual commands. 12 is an image input unit which receives a fingerprint image reading signal (analog data) sent from the fingerprint input unit 11, converts it into digital data, and stores this digital data in a frame memory, a frame memory. It is comprised of a binarization circuit that binarizes digital data using a predetermined threshold value and a binarization memory that stores the binarized data.

Reference numeral 13 denotes a matching circuit section, which is comprised of a matching dictionary memory storing the feature points of each individual as a dictionary and a matching circuit. Reference numeral 14 denotes a feature extraction unit, which is composed of a thinning circuit that thins the binary data of the read fingerprint and a thinning memory that stores the thinning data. The feature extraction unit 14
is used when registering a fingerprint pattern as a dictionary in the matching dictionary memory. That is, features are extracted based on the binarized data after thinning and stored in a matching dictionary memory.

15 is an internal interface. Reference numeral 16 denotes a control unit that controls the entire operation of the fingerprint matching system, and is composed of a CPU, a work memory for work, and an external interface.

Reference numeral 17 denotes an entry/exit management section connected to the control section 16, which is composed of a personal computer and a floppy disk. The entry/exit management section 17 is connected to the control section 16 and exchanges entry management information.

A door control section 18 receives an unlock signal from the control section 16, and is composed of an electric lock. The operation of the circuit configured as described above will be explained as follows.

A person who wants to enter the room places his or her registered finger on the fingerprint input section 11 and inputs a command from the numeric keypad. As a result, the fingerprint information of the finger is read and sent to the image input section 12 as analog data.

The image input unit 12 converts input analog data into digital data using an A/D converter, and then stores the digital data in a frame memory. The data stored in the frame memory is read out, compared with a predetermined threshold value, and binarized. The binarized data is stored in a binarization memory.

The matching circuit unit 13 uses the above-described fingerprint matching method according to the present invention when performing pattern matching of the binarized data read from the binarized memory and the feature point data read from the matching dictionary memory. If the result of the matching is a pseudo pattern, the matching is rejected. An example of a pseudo pattern is a case where the number of feature points around a point with matching feature points is larger than a threshold value, and a case where the maximum value of a ridge is smaller than a threshold value. In such a case, the verification circuit section 13
notifies the control unit 16 via the internal interface 15 that the verification has been rejected. The control unit 16 sends the fingerprint verification rejection to the entry/exit management unit 17 and causes it to be displayed on the personal computer display unit.

If, as a result of the matching by the matching circuit unit 13, the number of feature points around the point where the matching feature points match is not larger than the threshold value, and the maximum value of the ridges is larger than the threshold value, it is determined that the person is the real person. . This determination result is sent to the control unit 16 via the internal interface 15. The control unit 16 is the entrance/exit management unit 1
Send the identity verification information to 7 and display it on the computer display. At the same time, an unlock signal is sent to the door control unit 18 to open the room door. As a result, those with matching fingerprints can enter the room.

[Effects of the Invention] As explained in detail above, according to the present invention, by focusing on the difference between the pattern of a fake fingerprint and the actual fingerprint pattern, it is possible to reliably confirm that the fingerprint is the original fingerprint. can do.

[Brief explanation of drawings]

Fig. 1 is a flowchart showing the principle of the first method of the invention, Fig. 2 is a flowchart showing the principle of the second method of the invention, Fig. 3 is a diagram showing an example of a system configuration for implementing the method of the invention, Fig. 4 5 is a conceptual diagram of a conventional fingerprint matching system, FIG. 5 is a diagram showing an example of fingerprint characteristic information, FIG. 6 is a diagram showing an example of fingerprint matching using pattern matching, and FIG. 7 is a diagram showing an example of pattern matching for forged fingerprints. FIG. In Fig. 3, 11 is a fingerprint input section, 2 3 4 5 6 virtual image human power section, 2 verification circuit section, 2 feature extraction section, 2 internal interface, 2 control section, 2 talent exit management section, and 1 door control section. It is.

Claims (2)

[Claims] (1) Input a fingerprint image (Step 1), perform pattern matching of minutiae (Step 2), and if a certain number or more of minutiae match and the person is confirmed, at least one matching minutiae will be identified in the vicinity. (Step 3). If this number exceeds a certain threshold, the verification is rejected, and if it is within a certain threshold, the person is recognized (Step 4). A fingerprint verification method characterized by: (2) Input a fingerprint image (Step 1), perform pattern matching of minutiae (Step 2), and if a certain number or more of minutiae match and the person is confirmed, at least one fingerprint ridge of the fingerprint image is detected. Find the maximum length of (Step 3), and if the maximum value is less than a certain threshold, the verification is rejected, and if it is more than a certain threshold, the person is identified (Step 4) A fingerprint verification method characterized by: