JPH05135159A - Fingerprint collation device - Google Patents

Abstract

PURPOSE:To provide a fingerprint collation device which obtains successive accurate binary images as a fingerprint collation device which confirms a person himself by comparing an inputted fingerprint image with dictionary patterns stored in a dictionary. CONSTITUTION:A fingerprint collation device is constituted including a fingerprint sensor 1 which inputs fingerprint information, a gradation image storage part 10 which converts an output of the fingerprint sensor 1 into a gradation image and stores it, a line width measuring circuit 11 which measures the line width of the fingerprint image read out from the gradation image stores part 10, and a local threshold value calculating circuit 12 which calculates the measure width of lattices from the output of the line width measuring circuit 11 and also calculates the local binary threshold value in the lattices according to the calculated measure width.

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 people concerned. Many questions have been raised in terms of ensuring security for the ID cards and passwords that have been used up to now as a means of 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 for personal identification because they have two major characteristics, that is, they are the same for all people and are constant throughout life, and a lot of research and development has been conducted on a simple personal identification system using fingerprints. There is.

[0003]

2. Description of the Related Art FIG. 5 is a conceptual diagram of the structure of a conventional fingerprint collation device. A fingerprint collation device normally handles a fingerprint as an image. First, the operation at the time of registration will be described. The 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 binarizing circuit 2 and stored in the binarizing memory (frame memory) 3.

The fingerprint data stored in the binarized memory 3 is sequentially read out, and then enters 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 matching, after inputting his / her own ID number with a ten-key pad (not shown), a finger (a finger used for registration in advance, for example, an index finger) is placed on the fingerprint sensor 1. 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 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 fingerprint image for collation stored in the binarization memory 3 and the characteristic information for each individual 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.

[0008]

In the conventional apparatus as described above, as a method of binarizing the fingerprint image, the input image is divided into a grid shape, and the average density in each grid of the divided grid is locally determined. It was used as a threshold. 2 obtained in this way
In the binarized image, a discontinuous step is often generated at the boundary line of the cells. When registering the feature information as a fingerprint dictionary, thinning and feature extraction are performed on the binarized image.
If there is a step, pseudo feature points such as cracks and whiskers are likely to occur.

FIG. 7 is a diagram showing how pseudo feature points are generated. (A) shows a binarized image and (b) shows a thinned image.
In (a), the shaded area is a ridge, and the other areas are valleys. In the figure, the input image is divided into cells of length LW both vertically and horizontally (four divisions in the figure). This binarized image is obtained by using the average density in each grid as a threshold value and
Since it is quantified, there is a step at the boundary of the cells. When the binarized image is subjected to a thinning process, a mustache A (branch point) and a crack B (end point) are generated as shown in (b). Such A and B become pseudo feature points.

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 obtaining continuous and accurate binary images.

[0011]

FIG. 1 is a block diagram showing the principle of the present invention. The same parts as those in FIG. 5 are designated by the same reference numerals. In the figure, 1 is a fingerprint sensor for inputting fingerprint information, 10 is a grayscale image storage unit for converting the output of the fingerprint sensor 1 into a grayscale image and storing the same, and 11 is the grayscale image storage unit 10
A line width measuring circuit for measuring the line width of the fingerprint image read from the fingerprint image is calculated based on the output of the line width measuring circuit 11 and the grid width is calculated based on the calculated grid width. Local 2
It is a local threshold value calculation circuit that calculates a threshold value for binarization.

[0012]

When the grayscale image of the fingerprint is divided into the grid-like cells and binarized, if the ratio between the line widths of the ridges and valleys and the length of one side of the cells is adjusted, the binarized image It is empirically known that a step is less likely to occur even on the boundary line of the cells. If this condition is shown, (line width) / (cell width) = 0.3 to 0.6 (1) Under this condition, the number of ridges and valleys in the grid is about 1: 2, and the most continuous binary image is obtained.

FIG. 2 is a diagram showing the relationship between the line width WD and the cells LW. Therefore, the line width measuring circuit 11 measures the line width WD, and the cell width calculating circuit 12 calculates the cell width LW according to the equation (1).
To determine. This makes it possible to accurately
A value image can be obtained.

[0014]

Embodiments of the present invention will now be described in detail with reference to the drawings. FIG. 3 is a configuration block diagram showing an embodiment of the present invention. The same parts as those in FIG. 1 are designated by the same reference numerals. In the figure, 1 is a fingerprint sensor for reading a fingerprint image, and 10 is a grayscale image storage unit for converting the read fingerprint image into digital data using an A / D converter (not shown) and storing it as multi-value grayscale image data. ..

Reference numeral 11 is a line width measuring circuit for measuring the line width from the gray image read out from the gray image storage unit 10. Reference numeral 12 is based on the output of the line width measuring circuit 11, and the cell width is calculated. A local threshold value calculation circuit that calculates a local binarization threshold value in the grid based on the eye width, and 13 uses the threshold value obtained by the local threshold value calculation circuit 12 to display the grayscale image stored in the grayscale image storage unit 10. This is a binarizing circuit for binarizing.

Reference numeral 14 is a fingerprint binarized image storage unit for storing binarized binarized image data, and 15 is a fingerprint dictionary for extracting feature points of the binarized fingerprint image data by the binarization circuit 13. This is a registration / collation circuit that performs registration (pattern matching) between the fingerprint image for collation and the fingerprint dictionary while registering in the fingerprint binary image storage unit 14. The operation of the circuit thus configured will be described below. (At the time of registration) The fingerprint image read by the fingerprint sensor 1 is converted into multivalued digital data and stored in the grayscale image storage unit 10. The line width measuring circuit 11 reads the fingerprint image data stored in the grayscale image storage unit 10 and measures the line width WD of the ridge line and the valley line. A specific example of line width measurement is shown below.

FIG. 4 is a diagram showing a specific example of line width measurement.
First, the fingerprint image 20 in the grayscale image storage unit 10 is scanned at a constant interval IV as shown in (a). Here, the area to be scanned is around ridges in a direction close to the vertical direction of the grayscale image. As a result of scanning, it is assumed that the density distribution as shown in (b) is obtained. The horizontal axis represents the scanning direction, and the vertical axis represents the density.

Now, the pixel to be scanned and the d pixel (d>
0) Calculate the density difference D from a pixel that is distant. The density difference D is obtained by taking the difference of the density data. Where 2
When the number of pixels is on the upward slope, the density difference D is D> 0, and when it is on the downward slope, the density difference D <0.

Here, a certain threshold value TH (positive or negative) is determined, and when D> 0, D>TH> 0, and when D <0, a portion where D <TH <0 is detected. These places are scattered in several chunks. The intervals between the lumps correspond to the cycle of the ridge and valley. The density of the location where D>TH> 0 (or D <TH <0), that is, the area in which the number existing at a constant interval is a certain value or more is determined, and the center position thereof is set as the position of each lump. Measure the distance between each lobe position. Then, assuming that the widths of the ridge line and the valley line are equal to each other, this interval is divided into two to obtain the line width WD of the ridge line and the valley line.

The line width WD is calculated from the line width measuring circuit 11 and given to the local threshold value calculating circuit 12. The local threshold calculation circuit 12 obtains the cell width LW based on the line width WD as LW = CE × WD (2) CE; coefficient (> 0). When the cell width LW is obtained, the fingerprint image stored in the grayscale image storage unit 10 is divided into grids by this LW, the average density in each cell is obtained, and it is set as the threshold value within the cell. ..

The binarization circuit 13 is a local threshold calculation circuit 12
The threshold value for each cell is received, and the image in the cell is binarized using the threshold value. The binary image is a fingerprint 2.
It is stored in the binarized image storage unit 14. In this way, when the binarized data of all the fingerprint images are stored in the fingerprint binary image storage unit 14, the registration / collation circuit 15 extracts the feature points and registers them in the fingerprint binary image storage unit 14. To do. (At the time of collation) The fingerprint image read from the fingerprint sensor 1 is
It is stored in the grayscale image storage unit 10 as multivalued density data. The procedure for binarizing the fingerprint image data stored in the grayscale image storage unit 10 is the same as that at the time of registration.
The binarized collation fingerprint image is stored in the fingerprint binary image storage unit 14
Stored in.

The registration / matching circuit 15 performs pattern matching between the matching fingerprint image stored in the fingerprint binary image storage unit 14 and the fingerprint dictionary (feature point window image). If the matching error at the time of the pattern matching is smaller than a predetermined allowable value, it is determined that they match, and if the matching error is larger than the allowable value, it is determined that they do not match.

[0023]

As described above in detail, according to the present invention, the line width is measured based on the location where the density difference between the pixels of the fingerprint image separated by a certain distance becomes equal to or more than the threshold value, and the constant coefficient is calculated. Provided is a fingerprint collation device capable of obtaining an accurate binary image having no continuous step by calculating a mesh width by multiplying and calculating a threshold value for each calculated mesh. can do.

[Brief description of drawings]

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

FIG. 2 is a diagram showing a relationship between a line width and a cell width.

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

FIG. 4 is a diagram showing a specific example of line width measurement.

FIG. 5 is a conceptual diagram of a configuration of a conventional fingerprint matching device.

FIG. 6 is a diagram illustrating an example of fingerprint characteristic information.

FIG. 7 is a diagram showing how pseudo feature points are generated.

[Explanation of symbols]

 1 Fingerprint Sensor 10 Gray Image Storage Section 11 Line Width Measurement Circuit 12 Local Threshold Calculation Circuit

Claims (4)

[Claims] 1. A fingerprint sensor (1) for inputting fingerprint information.
A grayscale image storage unit (10) for converting the output of the fingerprint sensor (1) into a grayscale image and storing the grayscale image; and a line width for measuring the linewidth of the fingerprint image read from the grayscale image storage unit (10). A measurement circuit (11), and a grid width of the grid is calculated based on the output of the line width measurement circuit (11), and a local binarization threshold value in the grid is calculated based on the calculated grid width. A fingerprint collation device including a threshold value calculation circuit (12). 2. When dividing a grayscale image of a fingerprint into a grid pattern, the local threshold calculation circuit (12) multiplies the measured values of the line widths of the ridges and valleys by a constant coefficient to obtain the grid pattern of the grid. The fingerprint collation device according to claim 1, wherein the fingerprint collation device has a width. 3. When calculating the line width of the grayscale image, the linewidth measuring circuit (11) determines the linewidth of the ridge line and the valley line by the difference value of the densities between the pixels of the grayscale image which are separated by a constant interval. The fingerprint collation device according to claim 1, wherein the fingerprint collation device is calculated. 4. The line width measuring circuit (11) scans a grayscale image, detects a portion where the difference in the density of pixels at both ends of a certain interval becomes a certain value or more, and such a portion is made constant. Find the area where the number of existing in the interval becomes a certain value or more,
2. The fingerprint collation apparatus according to claim 1, wherein intervals between a plurality of area positions are measured, and the intervals are internally divided to calculate line widths of ridges and valleys.