JPH0628463A - Fingerprint matching device - Google Patents

Abstract

(57) [Summary] [Object] The present invention relates to a fingerprint collation device for comparing an input fingerprint image with a dictionary pattern stored in a dictionary to confirm the person's identity, and fingerprint collation with an image having a high degree of identity at the time of registration. It is an object of the present invention to provide a fingerprint collation device capable of performing. A fingerprint sensor 1 for inputting a fingerprint image, a binarization circuit 2 for binarizing the output of the fingerprint sensor 1, a binarization memory 3 for storing the output of the binarization circuit 2, and the binary A feature extraction unit 10 that extracts feature points from the fingerprint image read from the binarization memory 3, and data related to the complexity of the fingerprint image that is also extracted from the fingerprint image read from the binarization memory 3 and stored. A complexity evaluation unit 11 for comparing and evaluating the complexity of the fingerprint image for use with the complexity of the registered fingerprint image, a fingerprint dictionary storage unit 12 for registering the feature pattern extracted by the feature extraction unit 11 as a dictionary, and collation It is composed of a collation unit 13 that collates the fingerprint image with the fingerprint dictionary registered in the fingerprint dictionary storage unit 12.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a fingerprint collation apparatus for comparing an input fingerprint image with a dictionary pattern stored in a dictionary to identify the person.

In recent years, as computers have been introduced into a wide range of social systems, system security has attracted a lot of interested persons. Many questions have been raised in terms of ensuring security for the ID cards and passwords that have been used so far as means for confirming the identity when entering a computer room or using a terminal. On the other hand, fingerprints are considered to be the most effective means of personal identification because fingerprints have two major characteristics, that is, they are the same for all people and do not change for the rest of the life, and much research and development has been done on simple personal identification systems using fingerprints. There is.

[0003]

2. Description of the Related Art FIG. 8 is a conceptual diagram showing the construction of a conventional fingerprint collation device. First, the operation at the time of registration will be described. 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) in the fingerprint sensor 1. The converted digital data (fingerprint data) is converted into binary data of “0” and “1” by the subsequent binarization circuit 2 and stored in the binarization memory 3.

The fingerprint data stored in the binarized memory 3 are sequentially read out, and then enter the characteristic information extracting section 4 to extract characteristic information. Here, the characteristic information is, for example, as shown in FIG.
It refers to a branch point as shown in (a) or an end point as shown in (b). The fingerprint can be specified by the number of such branch points and end points at which positions. The extracted feature information is stored in the fingerprint dictionary storage unit 5. The above operation is repeated for a plurality of individuals, and the characteristic information of the individuals is stored in the fingerprint dictionary storage unit 5.

When the registration of the feature information amount in the fingerprint dictionary storage unit 5 is completed in this way, the collation operation of the individual fingerprint is started this time. In the case of collation, a finger (a finger used for registration in advance, for example, an index finger) is placed on the fingerprint sensor 1 and then an ID number of the user is input with a ten-key pad (not shown). As a result,
The collation unit 6 can narrow the search range by determining the search range of the fingerprint dictionary storage unit 5 based on the ID number and reading it at the time of the collation.

A fingerprint pattern is detected in the same manner as at the time of registration, and is converted into digital data by an A / D converter (not shown) in the fingerprint sensor 1. The converted digital data is converted into binary data of “0” and “1” by the subsequent binarization circuit 2 and stored in the binarization memory 3.

The collation unit 6 reads out the collation fingerprint image stored in the binarization memory 3 and the individual characteristic information stored in the fingerprint dictionary storage unit 5, and collates both (pattern matching). I do. When the number of matching feature patterns is greater than or equal to a predetermined number, it is determined that the fingerprints match.

Next, regarding the pattern matching operation,
Further details will be described. Here, the moving window method will be described. FIG. 10A shows a fingerprint image read by the fingerprint sensor 1 and binarized by the binarization circuit 2 and stored in the binarization memory 3. In the figure, the shaded areas are ridges (mountain lines) and the white areas are valley lines. The feature information extraction unit 4 extracts feature points from the fingerprint image and cuts out a plurality of fingerprint images (feature patterns) centering on the feature points in a window shape.

FIG. 10B is a diagram showing a characteristic pattern as a fingerprint dictionary. W in the figure is the alignment window, and the remaining 1 to 6 are windows extracted around the alignment window W. While maintaining this positional relationship, it is registered in the fingerprint dictionary storage unit 5 as a dictionary.

At the time of matching, the matching unit 6 pattern-matches the window of the fingerprint dictionary with the input fingerprint image.
The fingerprint dictionary is divided into one alignment window W and a plurality of matching peripheral windows. First, the registration window W is scanned with respect to the fingerprint image to perform pattern matching,
Grasp the amount of movement of the input image with respect to the registered image. After that, the matching window is shifted by the amount of movement of the alignment window to perform matching. FIG. 10C shows the state of pattern matching. In the figure, H is the read fingerprint image. The alignment window W is scanned for this fingerprint image, a matching pattern is searched for, and the movement amount is memorized at the matching position. When the remaining matching windows are moved by the same amount, the state shown in FIG. When performing this pattern matching, the matching window is two-dimensionally scanned by a slight amount in order to cope with the distortion caused by the softness of human skin, and the pattern matching is performed.

[0011]

In the conventional apparatus, the brightness of the fingerprint image, the number of white pixels in the binary image, and the like are used to determine the timing to start the fingerprint collation. FIG. 11 is an explanatory diagram of the determination of the conventional collation start time. The vertical axis represents brightness (or the number of white pixels), and the horizontal axis represents elapsed time. This figure is
It shows changes in brightness and the number of white pixels from the moment of pressing to the start of matching. When these values exceed a predetermined threshold value L, the matching process is started.

However, in this method, since the judgment is made using the integral information of the input image, in the case of a partially sweated fingerprint or the like, the collation processing is started even in an unstable state, so that it is not always necessary at the time of registration. There was a problem that images with a high degree of identity could not be matched.

The present invention has been made in view of the above problems, and an object of the present invention is to provide a fingerprint collation device capable of performing fingerprint collation with an image having a high degree of identity at the time of registration.

[0014]

FIG. 1 is a block diagram showing the principle of the present invention. The same parts as those in FIG. 8 are designated by the same reference numerals. In the figure, 1 is a fingerprint sensor for inputting a fingerprint image, 2 is a binarization circuit for binarizing the output of the fingerprint sensor 1,
Reference numeral 3 is a binarizing memory for storing the output of the binarizing circuit 2.

Reference numeral 10 is a feature extraction unit for extracting feature points from the fingerprint image read out from the binarization memory 2, and 11 is also 2
Data on the complexity of the fingerprint image is extracted from the fingerprint image read from the binarization memory 3 and stored, and at the time of fingerprint matching, the complexity of the fingerprint image for verification and the complexity of the registered fingerprint image are compared and evaluated. It is a means.

Reference numeral 12 is a fingerprint dictionary storage unit for registering the feature pattern extracted by the feature extraction unit 10 as a dictionary, and 13 is a collation for collating the fingerprint image for collation with the fingerprint dictionary registered in the fingerprint dictionary storage unit 12. It is a department.

[0017]

The complexity evaluation means 11 extracts a parameter relating to the complexity of the fingerprint (for example, the total length of the boundary lines of the pattern) from the binarizing memory 3 and stores it at the time of registration.
Then, the complexity evaluation unit 11 confirms that the complexity of the matching fingerprint image is equal to the complexity of the fingerprint image at the time of registration, or is lower than the complexity at the time of registration, and then the matching unit 13 A verification start signal is given.

FIG. 2 is a diagram for explaining the operation of the present invention and is a diagram showing changes in the fingerprint image during the imprinting process. (A) shows the fingerprint image at the beginning of imprinting, and (b) shows the fingerprint image after stabilization. At the beginning of imprinting, the fingerprint image is complicated as shown in (a). As time goes by, it becomes simple as shown in (b). Therefore, the complexity evaluation unit 11 determines that the degree of the complexity is sufficient for performing the fingerprint verification, and then starts the verification.

By doing so, fingerprint collation can be performed on an image having a high degree of identity with that at the time of registration.

[0020]

Embodiments of the present invention will now be described in detail with reference to the drawings.

FIG. 3 is a block diagram showing the configuration of an embodiment of the present invention. The same parts as those in FIG. 1 are designated by the same reference numerals. The complexity evaluation unit 11 includes a memory 11a that stores data related to complexity, and a complexity evaluation unit 11b that reads the data stored in the memory 11a and evaluates the state of the input fingerprint image for verification. ing.
In addition, the complexity evaluation unit 11 outputs from the matching unit 13 each time matching is performed.
A signal is input to the internal memory each time a collation is performed.
The operation of the apparatus configured as described above will be described below with reference to the flowchart of FIG. (At the time of registration) First, a fingerprint image is input from the fingerprint sensor 1 (S1). The input fingerprint image enters the binarization circuit 2 and is binarized (S2). The binarized binary image is 2
It is stored in the binarization memory 3. The feature extraction unit 10 extracts feature information from the fingerprint image read from the binarization memory 3 (S3). On the other hand, the complexity evaluation unit 11b uses the binarization memory 3
Extract data about complexity from the fingerprint image read from the.

FIG. 5 to FIG. 7 are diagrams showing examples of complexity parameters. FIG. 5 uses the cumulative total of the boundary lengths of patterns as a parameter indicating complexity. A shown in the figure
The shaded area from 1 to A10 is a ridge. When the total of the boundary line lengths of these areas A1 to A10 is obtained, it can be used as a parameter (index) of complexity. That is, at the initial stage of imprinting as shown in FIG. 2A, the ridges are chopped, and the cumulative total value of the boundary line lengths of these chopped regions becomes large and complicated.

FIG. 6 uses the number of connected patterns as a parameter indicating complexity. There are 10 black pixels in the figure.
Individually shown. Pixels are one set in the case where any of eight directions of vertical, horizontal, and diagonal are adjacent, and one set in the case of the figure. However, vertical and horizontal 4
If it is determined that there is a connection only in the direction, the black pixels shown in the figure are three sets of B0, B1, and B2.
Thus, if the difference in the number of collations when the eight directions are adjacent to each other and when the four directions are adjacent to each other is defined as the pattern connection number, this pattern connection number is also a parameter that indicates complexity. Can be used as That is, the more complex the image, the greater the number of connections.

FIG. 7 uses the number of sweat glands existing in a ridge as a parameter indicating complexity. There are a plurality of sweat glands a in the ridge 20. Then, it is determined that the image is more complicated as the number of sweat pores is larger.

Returning again to the flowchart of FIG. When the extraction of the complexity data is completed, the feature pattern extracted by the feature extraction unit 10 is registered in the fingerprint dictionary storage unit 12 (S
5). At the same time, the complexity data evaluated by the complexity evaluation unit 11b is registered in the memory 11a (S5). (During collation) A fingerprint image for collation is input from the fingerprint sensor 1 (S6). At this time, the finger is left on the fingerprint sensor 1 for a while and the image is fixed (S7). As described with reference to FIG. 2, this image stabilization requires waiting until a stable pattern is obtained because the fingerprint image is not stable and has a complicated pattern at the beginning when the finger is pressed on the fingerprint sensor 1. Because. The binarized image is stored in the binarization memory 3.

When the image is fixed, the binarization circuit 2 binarizes the input image (S8). The complexity evaluation unit 11b
The fingerprint image read from the binary memory 3 and the complexity data read from the memory 11a are compared and collated to compare the degree of complexity (S9). Then, when the degree of complexity is larger than the reference value stored in the memory 11a, the image is not stable yet, so the process returns to step S7 and the image is fixed.

Here, when comparing the degrees of complexity, one of the cumulative value of the boundary lengths of the patterns, the cumulative value of the number of connected patterns, the number of sweat pores, etc. may be used. However, two or three may be used. Also,
In determining the degree of complexity, these complexity parameters may be combined to make a comprehensive determination.

The degree of complexity of the input image depends on the memory 11a.
If it is less than or equal to the reference value entered,
Since the input image has been stabilized, the complexity evaluation unit 1
1b sends a command signal to the matching unit 13 to start the matching process (S10). The matching unit 13 performs matching (pattern matching) between the fingerprint image read from the binarization memory 3 and the feature points registered in the fingerprint dictionary storage unit 12 to confirm the identity.

When the fingerprint collation cannot be performed to confirm the person, the process returns to step S6 to input the collation fingerprint image, but the number of collations is stored in the memory 11a. Then, the complexity evaluation unit 11b stores the history information every time the complexity is evaluated.

Then, based on the number of trials, the complexity at the time of confirming the person, and the past history information, the complexity evaluation section 11b determines the complexity determination threshold value at the next collation. If such a system is adopted, it becomes possible to obtain an optimum reference value at the time of comparing the complexity, and the matching speed can be increased.

[0031]

As described above in detail, according to the present invention, when the collation fingerprint image is input, the collation is started after the complexity becomes equal to or less than the reference value. By doing so, it is possible to provide a fingerprint collation device that can perform fingerprint collation with an image that is highly identical to that at the time of registration, and has a large practical effect.

[Brief description of drawings]

FIG. 1 is a principle block diagram of the present invention.

FIG. 2 is a diagram showing a change in a fingerprint image in the imprinting process.

FIG. 3 is a configuration block diagram showing an embodiment of the present invention.

FIG. 4 is a flowchart showing the operation of the present invention.

FIG. 5 is a diagram showing an example of a parameter of complexity.

FIG. 6 is a diagram showing an example of a parameter of complexity.

FIG. 7 is a diagram showing an example of a parameter of complexity.

FIG. 8 is a conceptual diagram of a configuration of a conventional fingerprint matching device.

FIG. 9 is a diagram illustrating an example of fingerprint characteristic information.

FIG. 10 is an operation explanatory diagram of pattern matching.

FIG. 11 is an explanatory diagram of conventional matching start time determination.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Fingerprint sensor 2 Binarization circuit 3 Binarization memory 10 Feature extraction unit 11 Complexity evaluation means 12 Fingerprint dictionary storage unit 13 Collation unit

Claims (6)

[Claims] 1. A fingerprint sensor (1) for inputting a fingerprint image
And a binarization circuit (2) for binarizing the output of the fingerprint sensor (1)
And a binarization memory (3) for storing the output of the binarization circuit (2)
A feature extraction unit (10) for extracting feature points from the fingerprint image read from the binarization memory (3), and data on the complexity of the fingerprint image from the fingerprint image also read from the binarization memory (3) A complexity evaluation unit (1) that extracts and stores the extracted fingerprints and stores them, and compares and evaluates the complexity of the fingerprint image for verification with the complexity of the registered fingerprint image during fingerprint matching.
1), a fingerprint dictionary storage unit (12) for registering the feature pattern extracted by the feature extraction unit (10) as a dictionary, a fingerprint image for collation, and a fingerprint dictionary registered in the fingerprint dictionary storage unit (12). A fingerprint collation device including a collation unit (13) for collating the. 2. The complexity evaluation means (11) confirms that the complexity of the collation fingerprint image is equal to the complexity of the fingerprint image at the time of registration or is lower than the complexity at the time of registration, The fingerprint collation device according to claim 1, wherein a collation start signal is given to the collation unit (13). 3. The fingerprint collation apparatus according to claim 1, wherein a cumulative total of boundary lengths of patterns is used as the complexity of the fingerprint image. 4. The fingerprint collation apparatus according to claim 1, wherein a cumulative total of the number of connected patterns is used as the complexity of the fingerprint image. 5. The fingerprint collation apparatus according to claim 1, wherein the total number of sweat pores is used as the complexity of the fingerprint image. 6. The complexity evaluation means (11) stores an average value of the number of trials and complexity, and determines a complexity determination threshold value for the next time from the complexity at the time of successful identification and past history information. The fingerprint collation device according to claim 1, wherein the fingerprint collation device is determined.