JP2001202513A - Fingerprint matching device and matching method - Google Patents

Abstract

(57) [Problem] To provide a fingerprint collation device and a collation method thereof, which reduce an erroneous recognition rate at the time of fingerprint collation and reduce complicated regular maintenance opportunities. SOLUTION: A fingerprint characteristic amount is extracted from a fingerprint image read by a fingerprint sensor 1, and the extracted characteristic amount is compared with a previously registered characteristic amount by a coincidence degree calculating means 4 to calculate a fingerprint coincidence degree. The degree of coincidence is compared with a threshold value by the comparing means 5 to output a judgment result, and the judgment result and the degree of coincidence are stored in the collation history memory 7. Then, the average value of the coincidence is calculated by the average coincidence calculating means 8, and the threshold value is changed by the threshold value changing means 9 according to the average coincidence.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a fingerprint matching device for matching a fingerprint read by a fingerprint sensor with a registered fingerprint, and a matching method therefor.

[0002]

2. Description of the Related Art FIG. 6 is a functional block diagram showing a conventional fingerprint matching device. When the user places his / her finger on the fingerprint sensor unit 1, the fingerprint sensor unit 1 reads the fingerprint and performs image processing by the image processing feature extraction unit 2 to extract the feature amount of the fingerprint. The coincidence calculating means 4 compares the characteristic amount of the fingerprint registered in the characteristic amount memory 3 with the extracted characteristic amount and calculates the degree of coincidence. This matching degree is compared with the threshold value 6 by the comparing means 5, and the result of the personal authentication is output and recorded in the collation history memory 7.

[0003]

In the above-mentioned conventional fingerprint collating apparatus, the threshold value for determining the degree of coincidence is set to a constant value. The rate at which the person is determined to be the person is reduced,
There is a problem with personal authentication. Further, in order to avoid this, there is a problem that maintenance such as changing the threshold value is required periodically by checking the history of the degree of coincidence, which is complicated.

SUMMARY OF THE INVENTION The present invention has been made to solve the above problems, and provides a fingerprint collation apparatus and a collation method thereof capable of reducing a false recognition rate and reducing complicated periodic maintenance. With the goal.

[0005]

A fingerprint matching apparatus according to a first aspect of the present invention compares the degree of coincidence between a feature amount of an input fingerprint and a feature amount of a registered fingerprint with a threshold value. Output the judgment result, calculate the average value of the degree of coincidence,
The threshold value is changed according to the average coincidence.

A fingerprint matching device according to a second aspect of the present invention is the fingerprint matching device according to the first aspect, wherein the threshold value is set low when the average matching degree is low, and the threshold value is set high when the average matching degree is high. It was made.

The fingerprint matching device according to a third aspect of the present invention outputs a determination result by comparing the degree of coincidence between the feature amount of the inputted fingerprint and the feature amount of the registered fingerprint with a threshold value. The average value of the coincidences is calculated, and when the average coincidence is equal to or less than a predetermined value, an abnormal alarm is issued.

The fingerprint matching device according to a fourth aspect of the present invention is the fingerprint matching device according to the first or the second aspect of the present invention, wherein the coincidences of which the judgment result is passed are integrated, and a predetermined number of times of the passed coincidence are obtained. When the integrated value is equal to or less than the reference value, an abnormal alarm is issued.

Further, in the fingerprint matching method according to the fifth invention, a fingerprint feature amount is extracted from a fingerprint image read by a fingerprint sensor, and the extracted fingerprint feature amount and a previously registered fingerprint feature amount are determined. The calculated coincidence is compared with a predetermined threshold value to output a judgment result, and the judgment result and the coincidence are stored. The method includes the steps of calculating an average value and changing a threshold value according to the calculated average coincidence.

[0010]

DESCRIPTION OF THE PREFERRED EMBODIMENTS Embodiment 1 1 to 3 are diagrams showing an embodiment of the first, second and fifth aspects of the present invention. FIG. 1 is a functional configuration diagram, FIG. 2 is a content diagram of a collation history memory, and FIG. 3 is a threshold. It is a value curve figure. In FIG. 1, reference numeral 1 denotes a fingerprint sensor unit for reading a fingerprint image, and 2 denotes a fingerprint sensor unit.
This is an image processing / feature extraction unit that processes a fingerprint image from the image processing apparatus and extracts its characteristic amount (branch point, end point, etc. of the fingerprint).

Reference numeral 3 denotes a feature memory for storing a fingerprint feature output from the image processing / feature extraction means 2. Reference numeral 4 denotes a feature at the time of registration stored in the feature memory 3 and an image processing / feature extraction unit 2. The matching degree calculating means 5 for comparing the feature amounts at the time of matching and calculating the degree of matching by comparing the matching degree from the matching degree calculating means 4 with the threshold value from the threshold value setting means 6,
This is a comparison unit that determines whether the registered fingerprint and the verification fingerprint are the same.

Reference numeral 7 denotes a collation history memory for storing the coincidence from the coincidence calculating means 4 and the judgment result from the comparing means 5;
Is an average coincidence calculating means for calculating an average value of the coincidences from the collation history memory 7, and 9 is a threshold value change for changing the threshold value of the personal identification based on the average coincidence calculated by the average coincidence calculation means 8. Means.

Next, the operation of this embodiment will be described. (1) At the time of fingerprint registration When a user places a finger on the fingerprint sensor unit 1, the fingerprint sensor unit 1 reads a fingerprint. The read fingerprint image is sent to the image processing / feature extracting means 2, where the image is processed to extract a fingerprint feature amount. Then, the feature amount is stored in the feature amount memory 3, that is, the fingerprint is registered.

(2) At the time of fingerprint collation As in the case of fingerprint registration, when the user places his / her finger on the fingerprint sensor unit 1, a feature amount is extracted by the image processing / feature extraction means 2,
It is sent to the coincidence calculating means 4. The matching degree calculating means 4 compares the registered fingerprint feature quantity registered in the feature quantity memory 3 with the matching fingerprint feature quantity from the image processing / feature extracting means 2 at the time of matching, and calculates the matching degree. The degree of coincidence is 100% if the registered fingerprint feature and the verification fingerprint feature are exactly the same,
If they are completely different, it is 0%, and usually has a value of 0 to 100%.

The degree of coincidence is sent to the comparing means 5 and compared with the threshold value from the threshold value setting means 6, and the result of the personal authentication is output. The fingerprint collation apparatus is completed by the above operation, but usually records a collation history in order to facilitate maintenance. That is, the authentication result from the comparing means 5 and the matching degree from the matching degree calculating means 4 are stored in the matching history memory 7. FIG. 2 shows the contents of the collation history memory 7.
Shown in In the figure, the ID number is a number unique to the finger, the circle of the judgment result is a person, the cross is another person, and the degree of coincidence is a value of 0 to 100%.

Each time a timer (not shown) reaches a predetermined time or the number of new histories reaches a predetermined value, the average coincidence calculating means 8 averages the items of the coincidence in the collation history memory 7. However, when averaging is performed to eliminate the possibility that others will be mischievous, the degree of coincidence will be constant (eg, 30%).
The average value is calculated only when the above is true. Further, the average value is sent to the threshold value changing means 9 to change the threshold value for the personal identification.

For example, as shown in FIG. 3, if the average value of the coincidence is low, the threshold value is set low, and if the average value of the coincidence is high, the threshold value is set high. However, the lower limit value Th1 and the upper limit value Th2 to be changed are provided, and the threshold value is suppressed to the lower limit value Th1 to the upper limit value Th2 so that the range of change falls within the range of the performance of personal authentication. This makes it possible to automatically lower the threshold value and maintain the identity authentication rate in the same manner as in the related art when the degree of identity match decreases.

In this way, the average value of the coincidences stored in the collation history memory 7 is calculated, and if the average coincidence is low, the threshold value for personal identification is set lower, and the average coincidence is determined. When the value is high, the threshold value for the personal identification is set to be higher, so that the erroneous recognition rate in fingerprint collation can be reduced.

Embodiment 2 FIG. 4 is a functional configuration diagram showing an embodiment of the third invention of the present invention, and the same parts as those in FIG. 1 are denoted by the same reference numerals. (The same applies to the following embodiments.)
2 and 3 are also used in the second embodiment. In this embodiment, the threshold value changing means 9 is deleted from the one shown in FIG.
An abnormal alarm signal 10a is output.

Next, the operation of this embodiment will be described with respect to portions different from the first embodiment. When the average degree of coincidence output from the average degree of coincidence calculation means 8 falls below a predetermined threshold, the alarm device 10 outputs an abnormality alarm signal 10a to issue an abnormality. In this way, when the average coincidence drops extremely, an abnormality is issued,
Opportunities for complicated periodic maintenance are reduced, and maintenance can be facilitated.

Embodiment 3 FIG. 5 is a functional configuration diagram showing an embodiment of the fourth invention of the present invention. 2 and 3 are also used in the third embodiment. This embodiment is obtained by adding an alarm device 10 and a judgment result integrating means 11 to the configuration shown in FIG.

Next, the operation of this embodiment will be described with respect to portions different from the second embodiment. The determination result integrating means 11 integrates the determination results stored in the collation history memory 7. However, in order to eliminate mischief of another person at the time of accumulating the determination results, only when the coincidence is equal to or more than a certain value (for example, 30%), the coincidence of the judgment result ○ in FIG. 2 is integrated.
Next, when the integrated value from the determination result integrating means 11 becomes equal to or smaller than the reference value, the alarm device 10 outputs an abnormal alarm signal 10a.

As described above, when the integrated value of the determination result, that is, the integrated value of the coincidences for which the determination result is passed, is extremely low, an abnormality is notified, so that the opportunity for complicated periodic maintenance is increased. And maintenance can be facilitated.

[0024]

As described above, according to the first and fifth aspects of the present invention, the degree of coincidence between the feature amount of the input fingerprint and the feature amount of the registered fingerprint is compared with the threshold value to determine the judgment result. Is output, the average value of the coincidence is calculated, and the threshold is changed according to the average coincidence. In the second invention, when the average coincidence is low, the threshold is low, and the average coincidence is high. In some cases, the threshold value is set high, so that the false recognition rate in fingerprint collation can be reduced.

In the third invention, the degree of coincidence between the feature amount of the input fingerprint and the feature amount of the registered fingerprint is compared with a threshold value, and a judgment result is output. When the average coincidence is equal to or less than a predetermined value, an abnormal alarm is issued. According to the fourth aspect of the present invention, the coincidences for which the determination result is passed are integrated, and the integrated value for the predetermined number of times is used as a reference value. Since an abnormal alarm is issued in the following cases, the opportunity for complicated periodic maintenance is reduced, and maintenance can be facilitated.

[Brief description of the drawings]

FIG. 1 is a functional configuration diagram showing a first embodiment of the present invention.

FIG. 2 is a view showing the contents of a collation history memory shown in FIG. 1;

FIG. 3 is a threshold curve diagram showing the first embodiment of the present invention.

FIG. 4 is a functional configuration diagram showing a second embodiment of the present invention.

FIG. 5 is a functional configuration diagram showing a third embodiment of the present invention.

FIG. 6 is a functional configuration diagram showing a conventional fingerprint matching device.

[Explanation of symbols]

1 fingerprint sensor unit, 2 image processing / feature extraction means, 3
Feature memory, 4 coincidence calculation means, 5 comparison means, 6
Threshold setting means, 7 collation history memory, 8 average coincidence calculating means, 9 threshold changing means, 10 alarm device,
10a Abnormal alarm signal

Claims (5)

[Claims] 1. A fingerprint feature value extracted from a fingerprint image read by a fingerprint sensor is compared with a fingerprint feature value registered in advance to calculate a degree of coincidence between fingerprints. An apparatus for outputting a judgment result in comparison with a threshold value and storing the judgment result and the coincidence degree; an average coincidence calculating means for calculating an average value of the stored coincidence degrees; A fingerprint changing device for changing the threshold value according to a degree. 2. The apparatus according to claim 1, wherein said threshold value changing means sets a low threshold value when said average coincidence is low, and sets said threshold value high when said average coincidence is high. Item 3. The fingerprint matching device according to Item 1. 3. A fingerprint matching amount calculated by comparing a fingerprint feature amount extracted from a fingerprint image read by a fingerprint sensor with a fingerprint feature amount registered in advance, and determining the matching degree with a predetermined value. An apparatus for outputting a judgment result in comparison with a threshold value and storing the judgment result and the coincidence degree; an average coincidence calculating means for calculating an average value of the stored coincidence degrees; An alerting device that issues an alarm when the degree becomes lower than a predetermined value. 4. A judgment result accumulation means for accumulating the coincidences whose judgment results have passed, and an alarm device for issuing an abnormal alarm when the integrated value of the number of coincidences obtained for a predetermined number of times is equal to or less than a reference value. The fingerprint matching device according to claim 1 or 2, further comprising: 5. A step of extracting a fingerprint feature amount from a fingerprint image read by a fingerprint sensor, and comparing the extracted fingerprint feature amount with a pre-registered fingerprint feature amount to determine a degree of coincidence of the fingerprint. Calculating, comparing the calculated degree of coincidence with a predetermined threshold, and outputting a determination result, storing the determination result and the degree of coincidence, and averaging the stored degree of coincidence. A fingerprint matching method comprising: calculating a value; and changing the threshold value according to the calculated average coincidence.