JPH05189546A - Device for discriminating authenticity of fingerprint featured point - Google Patents

Abstract

PURPOSE:To accurately discriminate the authenticity of the feature points of fingerprints. CONSTITUTION:This authenticity discriminating device discriminates the authenticity of the featured points of rising lines of the fingerprint extracted out of a fingerprint image. The device is provided with an adjacent rising line detecting part 7 to detect the rising lines adjacent to the featured points, a rising line number detecting part 8 which scans a specific area including a featured point and its adjacent rising line and detects the number of rising lines with each scanning, and a discriminating part 9 which discriminates the authenticity of the featured points based on the change of the number of rising lines detected by the part 8.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an authenticity determination device for fingerprint feature points during fingerprint registration. Fingerprints are widely used as a method of personal identification. The ridge line forming the fingerprint has a part (end point) that is interrupted in the middle and a part (branch point) that is divided into two parts, which are called feature points. Then, the position and type of this characteristic point are registered as personal information, and the individual is identified by collating with this.

When registering the feature points, the feature points are extracted from the fingerprint image using a feature extraction mask or the like. The extracted feature points are short-circuited with a ridge due to sweat or the like on the finger. False feature points that are not the original features of the fingerprint, such as false branch points and false endpoints that cause cracks in the ridge due to a dry finger are likely to occur. Therefore, it is required to accurately determine the authenticity of the extracted feature points.

[0003]

2. Description of the Related Art FIG. 15 is an explanatory diagram of a conventional end point authenticity determination method, and FIG. 16 is an explanatory diagram of a conventional branch point authenticity determination method.
For information on registration and verification of fingerprint feature points, refer to "Personal verification device using holographic fingerprint sensor", for example.
It is described in PRU-88-38 of the Institute of Electronics, Information and Communication Engineers.

FIG. 15 shows a part of a ridge of a fingerprint image, which is composed of the end point A and another end point B existing in the vicinity of the end point A when the authenticity of the extracted end point A is judged. It is verified whether there are other ridges in the rectangular area shown in Fig. 15 (b).
If it does not exist, the end point A is judged as a false end point, and if it exists, the other end points in the vicinity are subjected to the same verification as shown in Fig. 15 (a). If a ridge exists for each end point, the end point A is determined to be a true end point.

FIG. 16 shows an example of judging the truth of a branch point. A midpoint P between a branch point C to be judged and a branch point D in the vicinity of the branch point C is obtained, and the midpoint P is set in the vicinity area. If there is a ridge, the branch point C is determined to be a false branch point, and if there is no ridge, such a determination is made for all nearby branch points, and if no ridge exists. , The branch point C is determined to be a true branch point.

[0006]

The authenticity determination method for a feature point is based on the relationship with other nearby feature points, but in the conventional determination method described above, the feature point of interest It is necessary to investigate the relations with all the feature points in the vicinity, and if the feature points have a complicated shape, the true feature points, especially in the case of branch points, the true feature points are There is a problem that it may be determined as a feature point.

In view of the above problems, it is an object of the present invention to provide a fingerprint feature point authenticity determination device for accurately determining the authenticity of a feature point.

[0008]

A corresponding functional portion will be extracted from the configuration diagram of one embodiment shown in FIG. An adjacent ridge detecting unit 7 detects an adjacent ridge adjacent to the feature point on the fingerprint image. A ridge line number detection unit 8 scans a predetermined area including the feature points and the adjacent ridge lines to detect the number of ridge lines for each scan. A determination unit 9 determines the authenticity of the feature point based on the detected change in the number of ridges.

[0009]

The adjacent ridge detector 7 detects an adjacent ridge adjacent to the feature point to be determined. For example, the ridge direction at a feature point on the fingerprint ridge is obtained, a direction orthogonal to this ridge direction is searched, and the fingerprint ridge detected first within a predetermined distance is set as an adjacent ridge. It depends on the method. Next, the ridge line number detection unit 8 scans a predetermined region including the feature points and the detected adjacent ridge lines, for example, in a direction orthogonal to the ridge direction, and detects the number of ridge lines for each scan. . Then, the determination unit 9
Determines the authenticity of the feature point based on the change in the number of detected ridges.

FIG. 2 shows the case of determining the authenticity of an end point. In FIG. 2 (a), the number of detected ridges changes from 3 to 2, which is within a predetermined range. Indicates that there is no pair of end points in the ridge direction, so it is determined to be a true end point. On the other hand, in Fig. 2 (b), the number of ridges is 3 → 2
The number is changed from book to three, which means that there is a pair of end points in the predetermined area (the end points are interrupted due to the finger being dried, etc.), and thus it is determined as a false end point. ..

As described above, the authenticity of the feature points can be accurately determined by scanning the predetermined area including the feature points and the adjacent ridges and determining the change in the number of ridges.

[0012]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS FIG. 1 is a block diagram of an embodiment, FIG. 3 is a flow chart of authenticity determination operation of a feature point, FIG. 4 is a flow chart of adjacent ridge detection operation, and FIG. 5 is a case where one adjacent ridge is used. FIG. 6 is a diagram showing an example of true / false determination of end points of FIG. 6, FIG. 6 is a diagram showing an example of true / false determination of branch points when one adjacent ridge is used, and FIG. FIG. 8 is a diagram showing an authenticity determination example, FIG. 8 is a diagram showing an authenticity determination example of a branch point when two adjacent ridges are used, and FIG. 9 is based on an end point when one adjacent ridge is used. FIG. 10 is a diagram showing an example of authenticity determination, FIG. 10 is a diagram showing an example of authenticity determination based on an end point when two adjacent ridges are used, FIG. 11 is a principle diagram of adjacent ridge detection, and FIG. 12 is a ridge. FIG. 13 is a diagram showing an example of the number detection method, FIG. 13 is a diagram showing a tracking example when an end point is encountered, and FIG. 14 is a diagram showing a tracking example when a branch point is encountered.

FIG. 1 shows a main part of a fingerprint registration device. In the figure, reference numeral 1 is a fingerprint input device, which optically detects a fingerprint image from a finger. An A / D converter 2 digitally converts the image data of the fingerprint image output from the fingerprint input device 1. A binarization circuit 3 binarizes the A / D-converted fingerprint image. An image memory 4 stores a binarized registration fingerprint image. A feature point detection unit 5 extracts feature points from the registration fingerprint image using a mask or the like, and determines whether they are end points or bifurcation points. An authenticity determination device 6 includes an adjacent ridge detection unit 7 that detects the adjacent ridge lines of the extracted feature points, a ridge line number detection unit 8 that scans a predetermined area, and detects the number of ridge lines for each scan. It is composed of a determination unit 9 for determining false. A registration unit 10 cuts out a fingerprint image in a window shape around the extracted true feature point and registers it as dictionary data.

In the above structure, as shown in FIG.
After binarizing the fingerprint image, feature points are extracted, adjacent ridges are detected for each of the feature points, the number of ridges is detected by scanning within a predetermined area, and true / false based on the change. To judge.

FIG. 4 and FIG. 11 show an example of a method for finding adjacent ridges. First, the ridge direction at the feature point is obtained, and then the direction orthogonal to the ridge direction is obtained. The ridge first discovered within a predetermined distance with respect to this orthogonal direction is defined as an adjacent ridge.

FIG. 12 shows an example of a scanning method for detecting the number of ridges, and FIG. 12 (a) shows a direction orthogonal to the ridge direction when one adjacent ridge is used ( (Orthogonal direction)
FIG. 12 (b) shows the case of scanning in parallel with respect to each other, when two adjacent ridges are used, each adjacent ridge is traced at a predetermined interval, and scanning is performed in the direction connecting the trace points. Is shown. In any case, the scanning direction is not particularly limited, and the fingerprint image is scanned to detect the number of ridges on the scanning line.

FIG. 13 shows a case where an end point E is encountered during tracking of adjacent ridges, and if there is an end point F (a pair of end points) in the ridge direction at the end point E and within a predetermined range. , The tracking is restarted from this end point F. That is, if there are false end points E and F on the adjacent ridge, they are discriminated and scanned.

FIG. 14 shows a case where a branch point G is encountered during the tracking of adjacent ridges, and thereafter, the ridge line H on the feature point side is tracked. Hereinafter, an example of a range for tracking and scanning will be described with reference to FIGS.

FIG. 5 shows a predetermined distance including at least the end point K from the adjacent end ridge (I) on either side of the adjacent ridges I and J on both sides of the end point K to be judged. a
Within a range of up to 2 m on both sides of the end point K with respect to the ridge direction (the value of m is determined by the practical range such as the maximum value of the false end point interval that normally occurs from a dry finger) To
The figure shows the case of scanning while tracking on the adjacent ridge I. When the end point K is true (FIG. 5 (b)), the number of ridges changes from 2 to 1 within a range of 2 m. However, when the end point K is false (FIG. 5B), the number of ridges changes from 2 to 1 to 2. Then, based on this change, the determination unit 9 determines the authenticity of the end point K.

FIG. 6 shows a case in which the branch point L to be judged is scanned a × 2 m in the same manner as in FIG. 5, and the number of ridges for each scan is detected. in this case,
When the branch point L is true (Fig. 5 (a)), the number of ridges remains unchanged, and when the branch point L is false (Fig. 5 (b)), the number of ridges is 2 → Since it changes from 3 to 2, the change is detected and the authenticity is determined.

FIG. 7 shows a case in which the ridges (I, J) on both sides are scanned to determine the authenticity of the end point K. Similar to FIG. 5, the ridge direction is the same as in FIG. , A range of 2 m is scanned centering on the end point K. In this case, as shown in Fig. 7 (a),
In the case of a true end point, the number of ridges changes from 3 to 2, and in the case of a false end point, the number of ridges changes from 3 to 2 → 3 as shown in Fig. 7 (b). To do.

FIG. 8 shows a case where the same range as in FIG. 7 is scanned to determine the truth of the branch point L. When the branch point L is true, as shown in FIG. 8 (a). , 3 ridges →
The number of ridges changes to four, but in the case of false, the number of ridges changes as 3 → 4 → 3 as shown in FIG. 8B.

FIG. 9 shows a method in which the scanning range in the ridge direction is set up to m with reference to the end point K to be determined (the direction is determined by a mask for extracting characteristic points). The number of lines can be detected in half as compared with the case of FIG. The change in the number of ridges is the same as in the case of FIG.

In FIG. 10, when scanning is performed between two adjacent ridges, the ridge direction is set to one side with reference to the end point K to be determined.
This shows the case where the scanning is performed up to, and there is an effect that the scanning time is half that of the case shown in FIG. In this case as well, the change in the number of ridges is the same as in the case of FIG.

As already described, the scanning direction may be substantially perpendicular to the ridge direction, and when an end point or a branch point is encountered, it is determined and traced as shown in FIGS. 13 and 14. You can continue.

As described above, in comparison with the method of searching the relations with the neighboring feature points to judge the authenticity, the judgment can be made by one scanning and the judgment can be made accurately even if the fingerprint ridges are complicated. As a result, fingerprint registration can be performed accurately.

[0027]

As described above, the fingerprint feature point authenticity determination device of the present invention detects the number of ridges in a predetermined area along the adjacent ridges of the feature point, and the authenticity is determined based on the change in the number. Is true, it is possible to accurately determine the authenticity, and it is possible to prevent registration of false feature points, which is very effective in fingerprint collation.

[Brief description of drawings]

FIG. 1 is a configuration diagram of an embodiment.

FIG. 2 is an explanatory diagram of the present invention.

FIG. 3 is a flowchart of an authenticity determination operation of a feature point.

FIG. 4 is a flowchart of an adjacent ridge detection operation.

FIG. 5 is a diagram illustrating an example of authenticity determination of an end point when one adjacent ridge is used.

FIG. 6 is a diagram illustrating an example of true / false determination of a branch point when one adjacent ridge is used.

FIG. 7 is a diagram illustrating an example of authenticity determination of an end point when two adjacent ridges are used.

FIG. 8 is a diagram illustrating an example of true / false determination of a branch point when two adjacent ridges are used.

FIG. 9 is a diagram showing an example of authenticity determination based on an end point when one adjacent ridge is used.

FIG. 10 is a diagram illustrating an example of authenticity determination based on an end point when two adjacent ridges are used.

FIG. 11: Principle diagram of adjacent ridge detection

FIG. 12 is a diagram showing an example of a method for detecting the number of ridges.

FIG. 13 is a diagram illustrating a tracking example when the end point is

FIG. 14 is a diagram showing an example of tracking when a branch point is encountered.

FIG. 15 is an explanatory diagram of a method for determining an end point authenticity of a conventional example.

FIG. 16 is an explanatory diagram of a branch point authenticity determination method of a conventional example.

[Explanation of symbols]

 1 Fingerprint Input Device 2 A / D Converter 3 Binarization Circuit 4 Image Memory 5 Feature Point Detection Unit 6 Feature Point Judgment Device 7 Adjacent Ridge Detection Unit 8 Ridge Line Number Detection Unit 9 Judgment Unit 10 Registration Unit

Claims (10)

[Claims] 1. A fingerprint feature point authenticity determination device for determining the authenticity of a feature point of a fingerprint ridge extracted from a fingerprint image, the adjacent ridge detection detecting an adjacent ridge line adjacent to the feature point. A part (7), scanning a predetermined area including the feature point and the adjacent ridge,
Ridge line number detection unit to detect the number of ridge lines for each scan (8)
And a determination unit (9) for determining whether the feature point is true or false based on the detected change in the number of ridges. 2. A range from at least one adjacent ridge line on both sides of the feature point in the direction of the feature point to at least a predetermined distance including the feature point and with respect to the ridge direction. And a ridge line number detection unit that detects the number of ridges in a predetermined range on both sides of the feature point by scanning toward the feature point while tracking the adjacent ridges. Item 1. A fingerprint feature point authenticity determination device according to Item 1. 3. A range from at least one adjacent ridge line on both sides of the feature point in the direction toward the feature point to at least a predetermined distance including the feature point, and with respect to the ridge direction. Is a ridge line number detection unit that detects the number of ridges in a predetermined range on the side of the region representing the feature of the feature point by scanning to the feature point side while tracking the adjacent ridges. The authenticity determination device for fingerprint feature points according to claim 2, wherein 4. The number of ridges between adjacent ridges adjacent to both sides of the feature point and in the ridge direction on both sides of the feature point is tracked as the number of ridges in the region. The authenticity determination device for fingerprint feature points according to claim 1, wherein the authenticity determination device is a ridge line number detection unit that detects by scanning between the adjacent ridge lines. 5. The number of ridges between adjacent ridges adjacent to both sides of the feature point and in the ridge direction in a predetermined range on the side of the region representing the feature of the feature point with the feature point as a reference. 5. The authenticity determination device for fingerprint feature points according to claim 4, wherein is a ridge line number detecting unit that detects by scanning between the adjacent ridges while tracking the adjacent ridges. 6. An adjacent ridge detection unit in which a fingerprint ridge first detected within a predetermined distance in a direction orthogonal to a ridge direction at a feature point on the fingerprint ridge is an adjacent ridge. The authenticity determination device for fingerprint feature points according to claim 1. 7. The authenticity determination device for fingerprint feature points according to claim 1, wherein the authenticity determination device for fingerprint feature points is a ridge line number detection unit that detects the number of ridge lines by scanning in a direction orthogonal to the ridge line direction. .. 8. A ridge line number detection unit for detecting the number of ridge lines by scanning adjacent ridge lines on both sides in a predetermined unit and connecting the trace points to scan the ridge lines. The authenticity determination device for fingerprint feature points according to claim 5. 9. When a ridge, which is one of the feature points, is encountered while tracking the adjacent ridge, the ridge adjacent to the feature point of the two ridges that have branched is a boundary of a predetermined area. The authenticity determination device for fingerprint feature points according to claim 2, claim 3, claim 4, and claim 5, wherein the ridge line number detector tracks and scans as. 10. When an end point, which is one of the feature points, is encountered while tracking an adjacent ridge, and when a pair of end points is detected by searching the ridge direction at the end point, tracking is started from this end point. The authenticity determination device for fingerprint feature points according to claim 2, claim 3 or claim 4, which is a ridge line number detector that restarts.