JPH0452975A - Fingerprint pattern sorting device - Google Patents

Abstract

PURPOSE:To realize the stable and correct sorting of a pattern by providing a sorting means to sort the pattern into plural predetermined fingerprint assortments according to the shape of a ridge line and the tendency of a ridge line direction in a main scanning and a subscanning direction of a collected fingerprint. CONSTITUTION:A fingerprint picture is collected and photoelectric-converted by a picture input part 10, and is outputted as two-dimensional picture data by an A/D converting part 11. Then, in a sorting processing part 18, a two-dimensional picture is divided into plural grid-shaped areas, and the inside of a prescribed frame including the central position of the fingerprint is scanned by making a vertical direction in the direction of the joint of a finger a main scanning direction and making an orthogonal direction a subscanning direction, and the shape of the ridge line is discriminated from each ridge line direction on main scanning, and the shape of the ridge line is discriminated by referring to the adjacent ridge line direction in the direction outside the frame if the ridge line direction of an adjacent area in the main scanning deviates by more than a prescribed angle, and the tendency of the ridge line direction is discriminated from the ridge line direction and the central position, and the fingerprint pattern is sorted into plural predetermined fingerprint assortments according to the shape of the ridge line and the tendency of the ridge line direction. Thus, the stable and correct fingerprint pattern sorting can be realized.

Description

DETAILED DESCRIPTION OF THE INVENTION BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a fingerprint pattern classification device, and more particularly to a fingerprint pattern classification device for automatically classifying the patterns of collected fingerprints.

Prior Art Conventional classification methods using features obtained from the ridge direction include matching with a standard pattern created in advance (Goto, Ichinami Nakamura, Okuno, "Classification of fingerprint images based on directional distribution pattern"). , IEICE Technical Report vol. 1.81.. n, o
, 210. IE81-88), and by considering the ridge as a vector field5 and using the values of the line integral of its rotation and the area integral of its divergence (Noda, Hateru, Kobayashi, Kato; ``Fingerprint slam classifier''
, Institute of Electronics and Communication Engineers, PRL73-97) The center (hereinafter referred to as the core) and ridges of the fingerprint serve as the basis for classification.
A method has been proposed in which classification is performed based on the presence, number, and position of triangle-shaped ::-angles (hereinafter referred to as deltas).

In the conventional method described in 1-1, the presence or absence of deltas plays an important role in the classification process, and the drawback is that deltas are difficult to collect depending on their location on the fingerprint. There is. In particular, in a fingerprint matching device for criminal investigation that targets latent fingerprints, fingerprints with missing deltas are often processed, and it is usually impossible to use deltas for classification.

Furthermore, the extraction of cores and deltas by standard pattern matching has a problem in that the extraction is likely to be greatly influenced by the standard patterns created in advance.

OBJECT OF THE INVENTION Therefore, the present invention was made to solve the drawbacks of the prior art, and its purpose is to perform stable and accurate pattern classification without relying on unstable delta classification. The object of the present invention is to provide a fingerprint pattern classification device that is possible.

Structure of the Invention The fingerprint pattern classification device according to the present invention includes means for collecting a fingerprint image and outputting it as two-dimensional image data, and dividing the two-dimensional image into a plurality of regions in a grid pattern, and dividing the two-dimensional image into a plurality of regions in a grid pattern, and dividing the two-dimensional image into a plurality of regions in a grid pattern. means for detecting a ridge direction in that area of a fingerprint; means for detecting a center position of the fingerprint from each ridge direction in the area; and a means for detecting a center position of the fingerprint from the direction of each ridge in the area; a direction perpendicular to the main scanning direction and a sub-scanning direction perpendicular to the main scanning direction; means for determining the shape of a ridge by referring to a ridge direction on a main scan in an out-of-frame direction adjacent to this main scan when the ridge directions of adjacent regions are separated by a predetermined angle or more; a means for determining a tendency of the ridge direction from the direction and the center position, and a classifying means for classifying the fingerprint pattern according to a plurality of fingerprint classifications predetermined based on the shape of the ridges and the tendency of the ridge direction. The fingerprint pattern classification device is characterized by:

Embodiments Hereinafter, embodiments of the present invention will be described with reference to the drawings.

FIG. 1 is a block diagram showing one embodiment of the present invention. In this example, a fingerprint image placed on a transparent body or
An image human power section 10 that collects a fingerprint image stamped on a stamping base paper 5 and performs photoelectric conversion, an A/D conversion section 11 that converts the photoelectric conversion signal into two-dimensional quantized image data, and an input control of the fingerprint image. an image storage unit 12 that stores two-dimensional quantized image data; an input unit 19 that manually inputs information regarding fingerprint images to be classified; and an output unit that outputs classification results and various messages. 20, and a classification processing unit 18 that performs classification by inputting image data from the image storage unit 13.

The classification processing unit 18 includes an external interface 14 that inputs the image data from the image storage unit 3 and information regarding the fingerprint image to be classified from the input unit 19 and outputs it to the output unit 20, and a working memory 17. It is composed of a program memory] 6 in which programs are stored, and a central processing unit 15 that is controlled by the programs.

Regarding the fingerprint input unit 10, the optical boundary conditions due to light from a light source for a finger placed on a transparent body are described in Japanese Patent Laid-Open No. 54-19300 and Japanese Patent Laid-Open No. 54-85800. I T V (1ndu
A device that inputs a photoelectrically converted image of a fingerprint pattern using an imaging device such as a digital camera,
As described in Japanese Patent Application Laid-Open No. 1381/1981, No. 74,
There is a device that inputs a fingerprint image on a stamped paper and can be used.

In the present invention, for the upper pattern shown in FIG. 2, the shape of the ridge is detected (the middle part of FIG. 2), and the tendency of the ridge direction (the lower part of FIG. 2) is determined. Perform classification. Incidentally, the broken lines in the pattern in the upper row of FIG. 2 indicate the rows in which the cores are present.

FIG. 3 is a flowchart showing the operation of one embodiment of the present invention. First, in step 310, a fingerprint image is input from the image storage unit 13 through the external interface 14. In step 311, features are extracted from the ridge direction, and in step 312, a region including the core is extracted.

FIG. 4 is a diagram showing a method of processing collected fingerprint images in this embodiment, in which the collected two-dimensional image 40 is arranged in a substantially grid pattern,
It is divided into a plurality of regions (hereinafter referred to as zones), and the ridge direction is detected for each zone and processed as zone data 42.

For example, the ridge direction for each zone is 3 as shown in FIG.
Divide 60 degrees into 16 equal parts and label in one of 16 directions (0 to
15) Use the zone data that is the characteristic obtained.

Note that 8 equal parts, 32 equal parts, 64 equal parts, etc. can also be considered.

In FIG. 4, zone 41 is a region containing the core,
Zone 42 is a direction-determined region, zone 43 is an uncertain region where ridges exist but whose direction cannot be determined, and zone 44 represents a non-data region where ridges do not exist.

In the process of extracting features (zone data) from the ridge direction in step 311, it is necessary to extract the zone data shown in FIG. 4, and in step 312, it is necessary to extract the zone 41 including the core. However, these processes are disclosed in Japanese Patent Application Laid-Open No. 138174/1982 and Japanese Patent Application No. 63-099334 and Japanese Patent Application No. 63-099 filed by the applicant.
No. 335 and Japanese Patent Application No. 83-099136, the detailed description is omitted here.

In the next step 313, the shape of the ridge is detected and determined from the zone data obtained from steps 311 and 312 and the zone including the core. The method will be explained using FIG.

First, as shown in FIG. 6A, starting from the zone 41 containing the core, the core is scanned within the frame 52, with the negative to positive direction of the y-axis (direction axis perpendicular to the finger joints) being the main scanning direction. By sub-scanning in both positive and negative directions of the X-axis (direction axis parallel to the finger joints) centering on the zone 41 containing the zone 41, only the direction determination zone 42 is checked for the presence or absence of the direction label shown in FIG. You can check the type. As a result, the shape of the ridge on the main scanning line in the y-axis direction is detected.

For example, in the example shown in FIG. 6A, the shape of the ridge corresponding to the right flow hoof pattern (No. 2) shown in the middle row of FIG. 2 is detected.

The method for determining the frame 52 in FIG. 6A is as follows. The upper limit of the frame 52 is the line that includes the zone 41 including the core, and from this line as the starting point, the main scanning direction is from the negative to the positive direction of the X axis, and the sub scanning is from the negative to the positive direction of the y axis. The number of labels in each direction of the direction determination zone 42 is calculated, and the horizontal tendency H is calculated using the following formula.

H-[L, OOX a (0) +0.05X (a
(L) + a (7) )+0,05X fa(2)
+a(8) l ] / [1,OOx (a(0)
+a(4) l +0.05X fa(1) +a(
8) +a (5) → -a (7) ) + 2
X O, mouth 5X (a(2) +a(6)
)] where a(n) is the number of direction-determined zones of label n existing on the scan.

Then, the value H calculated above for each scan is compared with a predetermined threshold value St, and the row that is the first scan that satisfies the condition H<81 is set as the lower limit of the frame 52.

Note that when the number of sub-scans is an odd number, the lower limit is one line further down in the negative and positive directions of the y-axis.

The left and right limits of the frame 52 are two-dimensional image data 40 as shown in FIG. 6A.
However, since the left and right 2 to 3 columns are often unclear and cannot serve as zone data, these 2 to 3 columns may be excluded.

In the case of the image data as shown in FIG. 6B (in this example, the two-dimensional image data of the spiral pattern shown in No. 1 in FIG. 2), the portion 54 is The label values (see FIG. 5), which are each zone data, are significantly different in adjacent parts.

For example, when the difference in label values is expressed in Figure 5, "4
”, and there is a direction difference of approximately 90 degrees. In such a case, it is not possible to grasp the shape in the ridge direction using only the data of each zone on the main scan of this part.

Therefore, in such a case, as shown in FIG.
5 is detected, the direction label of the outer (left side) main scanning line 56'' adjacent to the sub-scanning direction (X direction) is checked, and
Detect the ridge direction. In this way, if the outside zone data is also taken into account when making a determination, it becomes possible to detect the ridge direction more accurately.

In the example of FIG. 6C, the spiral pattern (No. 1
．． ) is detected.

The method for determining the tendency of the ridge direction in step 314 will be described based on FIGS. 7 and 8. First, a rectangular frame 6 as shown in FIG. Based on this, the tendency of the ridge direction is calculated.

For example, the tendency in the direction from the lower left to the upper right in frame 6] is calculated using the following formula.

I, -[1,00x a (2) +0.05X
Ia (1) + a (3)) → 0.05x
ia (0) + a (4) l ]
/ [1 old IXfa (2) ia (6) ) +
0.50X (a(1) +a(3) -+a(5)
+a(7)) +0.05X fa(11)+a(
4) From l
A ridge direction trend is determined.

The upper limit and C limit of frame 61 are the same as the - limit and lower limit of frame 1]2, and the left limit is the zone containing -j A/↓1,
The right limit is the next column in the positive direction of the 'c-X axis with respect to this column.

Next, two rectangular frames 6263 as shown in FIG. 8 are provided, and the same calculation as above is performed for each frame to determine the tendency of the ridge direction within each frame. In this example, the tendency of the ridge direction corresponding to the right flow hoof pattern (No. 2) shown in the lower part of FIG. 2 is determined.

Note that the frames 62 and 63 in FIG. 8 are determined as follows.

The lower limit of the frame 62 and the upper limit of the frame 63 are determined by dividing the width from the upper limit to the lower limit of the frame 52 in FIG. 6 into two equal parts. The upper limit of the frame 62 is the upper limit of the frame 52, and the first limit of the frame 63 is the lower limit of the frame 52.

Then, main scanning is performed from the negative to positive direction of the y-axis (iY of the y-axis centered on the zone 41 including the core, and sub-scanning is performed in both directions in the negative direction, and each direction determination zone 42 on the scan is Calculate the number of direction labels and determine the vertical trend ■ using the formula below.

V −[1,00x a, (4) → −0,50x (
a (3) ia (5) + 0.05x (a (2) + a
, (6) l ] / [1,,00x fa(0)i
a (4) l +0.50X (a (L) + a
(3) 1,000 a(5)+a(7) ) +2x0.
05x (a(2) ten a(6) l ]
For each scan, the value ■ calculated by the above formula is compared with a predetermined threshold value S2, and the column that is the first scan of the eel that satisfies the condition of V<32 is determined as the left limit and right limit of the frame 6263. That's what I do.

The reason why the tendency of the ridge direction is determined in two stages using the method shown in FIGS. 7 and 8 in step 31.4 is as follows.

That is, first, it is determined whether or not the tendency of the ridge direction obtained using frames 62 and 63 corresponds to the normal arcuate pattern (No. 5) shown in the lower part of FIG.

If not, it is determined whether the ridge direction tendency obtained using the frame 61 belongs to No., 1-No., or 4 in the lower row of FIG. 2, and the final ridge direction tendency is determined. There is.

In step 315, the shape of the ridge detected in step 313 and the tendency of the ridge direction determined in step 314 are classified by matching them to those shown in FIG.

In step 316, the uncertainty zone 43 is used to determine whether the input fingerprint image is of low quality. This determination method will be described based on FIG.

First, in the classification in step 315, the normal arcuate pattern (No.
, 5) Human fingerprint images classified other than 1. Knee, y, i
6C is provided with a frame 52 as shown in FIG. Scan in the positive direction from .

Here, only the uncertain zone 43 is targeted, and for the human fingerprint image classified as a right flow hoof pattern (No. 2) in step 315, the X coordinate is centered around the zone 41 including the core. Set the positive direction as sub-scanning and step 315
For the human fingerprint image classified as the left arch-shaped pattern (No. 3) in step 315, the sub-scanning is performed in the negative direction of the
Regarding the input fingerprint image classified as o, 4), there is an uncertain zone 43 that exists in each main scan in the y-axis direction, with the zone 41 containing the core as the center and the positive and negative X coordinates as sub-scans. The number of main scans in which uncertain zones 43 exist at a certain percentage or more (hereinafter referred to as defective rows) is calculated.
Based on this, it is determined whether the human fingerprint image is of low quality.

Also, in step 315, a normal arcuate pattern (No, 5) is selected.
For the input fingerprint image classified as 2 as shown in FIG.
In the two rectangular frames 62 and 63, whether or not the quality is low is determined based on the proportion of the uncertain zone 43 that exists within each frame.

In step 317, it is determined whether the low-quality human fingerprint image determined in step 316 is subject to classification rejection (hereinafter referred to as "reject") or reclassification. In this method, the determination is made based on the number of defective columns used in step 316, but in step 31
6, the input fingerprint image determined to be of low quality and the normal arcuate pattern determined to be of low quality are targeted for beam jetting. For the input fingerprint image determined to be rejected in this step 317, the input fingerprint image determined to be rejected in this step 317 is outputted by the output unit 20 through the external interface 14 in step 318.
The result will be output.

In step 319, the input fingerprint image determined to be a target for reclassification in step 316 is corrected. The method is carried out using the established relaxation method, which is a known method.
After the correction, step 812 and subsequent steps are performed again as appropriate. Regarding this established relaxation method, please refer to “Ra5enraid:I
TERTIVE METHODS IN IMAGE
ANALYSIs” Proc, 1EEE Conf
, P, R & 1. P14/18 (1977).

In step 320, the shape and position of the ridge detected in step 313, and the tendency of the ridge direction determined in step 314 are correlated with those in FIG. 9, so that the input fingerprint image to be classified is determined. It is determined whether there is a second classification candidate.

If it is determined in step 320 that the input fingerprint image to be classified does not have a second classification candidate, the classification result in step 315 is output from the output section 20 through the external interface 4 in step 318.

In step 321, a second classification candidate is determined for the input fingerprint image to be classified that is determined to have a second classification candidate. This method consists of the classification result in step 315 of the input fingerprint image to be classified (first row in FIG. 9), the ridge shape and its position detected in step 313 (third row in FIG. 9), and step 314. A second classification candidate is determined by associating the tendency of the ridge direction determined in (fourth row of FIG. 9) with the second row of FIG. 9. Note that the arrow in the third row of FIG. 9 indicates the distance between the shape of the detected ridge and the row containing the core.

If it is determined in step 320 that the human fingerprint image to be classified has a second classification candidate, the classification results in step 315 and step 321 are output from the output unit 20 through the external interface 14 in step 318.
The second classification candidates determined in are output.

As described above, in this embodiment, classification is performed based on the position of the core of zone data.

DETAILED DESCRIPTION OF THE INVENTION As described in detail, according to the present invention, classification is performed by detecting the shape of ridges and determining the tendency of the ridge direction using zone data used in existing automatic fingerprint verification systems. This has the effect of enabling stable fingerprint pattern classification.

Furthermore, the classification effect can also be obtained for classification of latent fingerprints in which the existence of deltas is not guaranteed.

[Brief explanation of drawings]

Figure 1 is a system block diagram of an embodiment of the present invention, Figure 2 is a diagram showing the concept of the pattern classification method used in this embodiment, and Figure 3 is a diagram showing the concept of the pattern classification method used in this embodiment.
FIG. 4 is a flowchart showing the operation of the embodiment of the present invention.
The figure shows an example of the zone data of the collected fingerprint image, FIG. 5 shows the ridge direction label in each zone, FIG. 6 shows the detection of the shape of the ridge, and FIGS. FIG. 8 is a diagram explaining the calculation of the tendency of the ridge direction, and FIG. 9 is a diagram showing the concept of the second classification candidate. Explanation of symbols of main parts 10... Fingerprint image input unit 13... Image storage unit 15... Central processing unit 17... Work memory 18... ... Classification processing unit 4 [] ... Two-dimensional image data 4] ... Zone containing the core 42 ... Direction definite zone 43 ... Undetermined zone 44...Non-data zone

Claims (3)

[Claims] (1) A means for collecting a fingerprint image and outputting it as two-dimensional image data, dividing this two-dimensional image into a plurality of regions in a grid pattern, and determining the ridge direction of the fingerprint in each region for each region. means for detecting the center position of the fingerprint from the direction of each ridge in the area; within a prescribed frame including the center position, a direction perpendicular to the direction of the finger joint is a main scanning direction; means for determining the shape of a ridge from each ridge direction on the main scan while performing these scans, with the orthogonal direction being a sub-scan direction; means for determining the shape of the ridge by referring to the ridge direction on the main scan in the direction outside the frame adjacent to the main scan when the distance is more than a predetermined angle; and a classification means for classifying fingerprint patterns according to a plurality of fingerprint classifications predetermined based on the shape of these ridges and the tendency of the ridge direction. . (2) comprising means for determining the quality of the fingerprint image according to the number of regions in which the ridge direction has been detected and determined; and means for correcting the image according to a predetermined method when the quality is determined to be low; 2. The fingerprint pattern classification device according to claim 1, wherein the fingerprint classification is performed again using the corrected image. (3) Fingerprint pattern classification according to claim 1 or 2, further comprising means for classifying up to a second candidate when the degree of similarity is high and the fingerprint classification is similar to a plurality of fingerprint classifications during classification by the classification means. Device.