JPH0443469A - Detection device for fingerprint picture rotational amount - Google Patents

Abstract

PURPOSE:To easily and accurately detect the coordinate rotational angle of a collation picture correspond to a fingerprint registration picture by providing a means outputting an angle difference appearing most frequently among angle differences in directions where respective fingerprint feature points of a registration picture are detected as the rotational angle of the collation picture. CONSTITUTION:A collation picture reader 1 detects a finterprint and reads it as the collation picture. A position adjustment circuit 25 overlaps the registration picture of the fingerprint which is previously stored with the collation picture by aligning screen center with each other. The angle difference between the direction of the fingerprint feature point of the collation picture, which exists in a prescribed range, and the direction of the fingerprint feature point of the registration picture is detected as to respective fingerprint feature points of the registration picture in an overlapped state in a control computer 26, and the angle difference appearing most frequently is outputted as the rotational angle of the collation picture among the angle differences in the direction where respective fingerprint feature points of the registration picture is detected. Thus, an operation quantity becomes considerably little and correspondence can be executed with the processing capacity of about a micro computer since a parameter is not required to calculate as to respective fingerprint features points.

Description

[Detailed Description of the Invention] [Industrial Application Field] The present invention is a fingerprint image rotation amount detection method that detects how much a fingerprint verification image is rotated with respect to a registered image, as a premise for reliable fingerprint verification. Regarding equipment.

[Prior Art] Fingerprints are useful for identifying the same person, and have been widely used in the field of criminal investigation. In recent years, various attempts to automate fingerprint verification have been proposed. Verification is performed by matching the coordinates of the fingerprint verification image and the registered image.

Conventionally, this verification has been performed through extensive calculations using large-scale computers. Therefore, for example, JP-A-52-8584
In Publication No. 1, several parameters (minutiae relationships) are given for each fingerprint minutiae mentioned above, and only minutiae pairs with matching minutiae relationships are extracted from the verification image and the registered image, and the coordinates of both images are calculated. It has been proposed that the amount of variation can be made with a relatively small total amount of H regardless of the conditions at the time of stamping.

[Problems to be Solved by the Invention] However, even with the device proposed above, the amount of calculation required to calculate the position and parameters of each fingerprint minutiae may exceed the processing capacity of a microcomputer. When applied to a keyless entry system for a house, etc., there is a problem that the device is not compact.

By the way, in the above-mentioned keyless entry system, etc., the fingertip is restrained to some extent by the fingerprint detection unit, so the amount of coordinate variation is not so large compared to general fingerprint verification, and it is necessary to detect and correct only rotational variation. Fingerprint matching with sufficient accuracy is possible.

SUMMARY OF THE INVENTION In view of this background, it is an object of the present invention to provide a fingerprint image rotation amount detection device that can easily and reliably detect the coordinate rotation angle of a verification image with respect to a fingerprint registration image.

[Means for Solving the Problems] To explain in detail the present invention, as shown in FIG. means for overlapping the image and the above-mentioned verification image by aligning their screen centers, and for each fingerprint minutiae of the registered image in the overlapping state, determining the direction of the fingerprint minutiae of the verification image existing within a predetermined range and the fingerprint of the registered image; A means for detecting the angular difference in the direction of the minutiae, and a means for detecting the angular difference in the direction detected for each fingerprint minutiae of the registered image;
and means for outputting the angle difference that appears most frequently as the rotation angle of the matching image.

[Operation] In the device configured as described above, since the registered image and the verification image in the keyless entry system etc. have a relatively small amount of rotational variation, the registered image and the matching image in the keyless entry system, etc., have a relatively small amount of rotational variation, so that within a predetermined range centered on each fingerprint minutiae of the registered image in the superimposed images. There is a high probability that the corresponding fingerprint minutiae in the matching image exists.

When the directional differences (angular differences) between both fingerprint minutiae are detected for each of the predetermined ranges, the angular difference that is most frequently obtained matches the rotation angle of the matching image.

According to such a device, there is no need to calculate parameters for each fingerprint minutiae as in the conventional device, so the amount of calculation becomes extremely small, and the processing power of a microcomputer is sufficient.

[Example] FIG. 2 shows the overall configuration of the device. Reference numeral 1 in the figure is a verification image reader, and an opening 11 is provided in the earthen wall through which one side of the triangular prism 12 is exposed, and this opening 11 is a slot that guides the fingertip M (see Figure 3). ). Above reader 1
Inside is a light source 13 that makes a light beam enter the prism 12.
is provided, and the fingerprint on the surface of the fingertip applied to the prism 12 is irradiated and input to the camera 15 through the lens 14.

The fingerprint image obtained by the camera 15 is sent to the measuring section 2 as a verification image via a video signal line 16.

The measurement unit 2 is operated by a control computer 26 that controls a binarization circuit 21, an image memory 22, a registration memory 23, an image processing circuit 24, an alignment circuit 25, and each of the above-mentioned circuits 21, 24, and 25 and performs calculations described later. It is configured. Note that the binarization circuit 21, the image processing circuit 24, and the alignment circuit 25 are all known circuits.

The binarization circuit 21 binarizes the input matching image, and the binarized matching image is stored in the image memory 22. The stored binarized image is subjected to noise removal and thinning in the image processing circuit 24, and fingerprint minutiae are extracted. A registered image is previously stored in the registration memory 23 in a binarized manner, and noise removal and fingerprint feature point extraction have already been completed for this registered image.

Here, an example of a registered image is shown in FIG. 4, and P1 in the figure is an end point of a ridge, which is one of the fingerprint minutiae. FIG. 5 is an example of a verification image, and P2 in the figure is a fingerprint minutiae corresponding to the fingerprint minutiae P1. The registered image and the verification image are overlapped in the alignment circuit 25 with their screen centers aligned. The superimposed images are shown in FIG.

By the way, the position of the fingertip M, which is regulated by the slot opening 11, does not change greatly, and for example, the rotation amount of 20 degrees of the 0-degree concave at the center of the screen, as shown in FIG. If there is almost no coordinate variation in the axial direction, there are 36 pixels at a position 100 pixels apart.

Therefore, if the rotation amount of the matching image is about 20 degrees with respect to the registered image, on the superimposed image in FIG. Furthermore, the probability that the fingerprint minutiae P2 of the matching image corresponding to this exists is extremely high.

Then, the direction difference (angular difference) Δθ between the direction θ2 (FIG. 7) of the fingerprint minutiae P2 of the registered image existing within the above range and the direction θ1 of the fingerprint minutiae P1 of the verification image is calculated. FIG. 9 shows the results of performing this on all fingerprint minutiae points of the registered image. The figure is a graph in which the horizontal axis represents the angular difference in units of 5 degrees, and the vertical axis represents the number of fingerprint minutiae that showed the same angular difference.According to this, Δθ=2
It is known that the number of fingerprint minutiae showing the angle (10 degrees) is the largest, and therefore, the angular difference Δθ between the mutually corresponding fingerprint minutiae points is 10 degrees. This, of course, indicates the rotation angle of the matching image, and is output as a rotation angle signal from the control computer (FIG. 2).

In addition, in the above embodiment, the matching image is rotated at 20 degrees, for example.
If you rotate it 40 degrees and 60 degrees and overlap it with the registered image, and detect the rotation angle based on each state,
Even when the angle of the fingertip used for fingerprint detection changes significantly, the amount of image rotation can be accurately detected.

[Effects of the Invention] As described above, according to the fingerprint image rotation amount detection device of the present invention, it is possible to accurately know the relative rotation angle between the verification image and the registered image without performing complicated and large amounts of calculations. It is possible to make the entire fingerprint verification device compact.

[Brief explanation of drawings]

Figure 1 is a complaint correspondence diagram, Figure 2 is an overall configuration diagram of the device,
Figure 3 is a partial plan view of the verification image reader, Figures 4 and 5 are diagrams showing the registered fingerprint image and verification image, respectively, Figure 6 is a diagram showing the superimposed images, and Figure 7 is the diagram showing the overlapped images. A partially enlarged view of the image, FIG. 8 is a diagram showing the relationship between the image rotation angle and pixels, and FIG. 9 is a graph showing each direction difference and the number of feature points. 1...Verification image reading device (verification image reading means) 12...
・Prism 13...Light source 15...Camera 2...Measuring section 25...Positioning recess 8 (image overlapping means) 26...
Control computer (angular difference detection means, rotation angle output means) Fig. 4 Fig. 5

Claims (1)

[Claims] means for detecting a fingerprint and reading it as a verification image; means for superimposing a pre-stored registered fingerprint image and the verification image by aligning the screen centers; means for detecting the angular difference between the direction of the fingerprint minutiae of the verification image existing within the range and the direction of the fingerprint minutiae of the registered image; , means for outputting the angle difference that appears most frequently as the rotation angle of the verification image.