JP2013214132A - Feature point information setting device, feature point information setting method, and feature point information setting program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To rapidly and correctly specify the type of each feature point in a fingerprint image.SOLUTION: A feature point information setting device comprises: means for alternately setting A and B points at a constant interval on a straight line perpendicular to a feature point direction at each feature point, and acquiring density values of a fingerprint image at the A and B points; means for calculating averages A and B of the acquired density values of the different A points and B points, respectively; and means for, on the basis of a magnitude relationship between the average density values A and B corresponding to each feature point, determining the type of the feature point.

Description

  The present invention relates to a fingerprint collation system that performs collation processing based on a fingerprint image, and more particularly to a feature point information setting device that determines attributes of each feature point in a fingerprint image.

  In the feature point information setting system for setting feature point information in a fingerprint image, generally, as shown in FIG. 1, the position of the feature point is designated based on the shape of the fingerprint ridge in the inputted fingerprint image, and each feature point is set. Direction information (feature point direction) and type as attribute information are set.

  The types of feature points include branch points and end points as shown in FIG. In the fingerprint collation device, it is possible to speed up the collation process by performing fingerprint collation based on the feature point information including the position of each feature point in the fingerprint image, the feature point direction, and the type of the feature point. Can effectively improve the accuracy of fingerprint verification.

  By the way, setting of feature point information is often performed manually by an operator of a fingerprint collation device, for example, on an inputted fingerprint image. In this case, the operator of the fingerprint collation device may miss the feature point in the fingerprint image, miss the feature point, or input the feature point information.

  In addition, the input fingerprint image may have obscured ridges or low quality in the image, as in the case of retained fingerprints in FIG. 6 (A) and FIG. 6 (B), for example. Yes, even if the feature point can be located in the image, it is difficult to determine the type of each feature point. There is an inconvenience that a mistake in decision is made.

  On the other hand, when there are a large number of input fingerprint images or when many feature points included in the fingerprint image are included, it is required to quickly and accurately determine the type of each feature point. .

  In addition, in the fingerprint collation device, feature point attribute information set in advance by an operator or the like is an important factor that determines the accuracy of fingerprint collation. For example, there is an error in feature point information in an unclear fingerprint image. Has the disadvantage that the accuracy of fingerprint matching is reduced.

  As a related technology, fingerprint data including information about feature points is created for each fingerprint image, and common feature points that are the same feature points are identified from the correspondence of feature points among a plurality of fingerprint data. A fingerprint collation system that performs fingerprint collation based on synthetic fingerprint data created based on feature points is disclosed (Patent Document 1).

JP 2001-344604 A

  However, even in the related art described in Patent Document 1, when the ridge of the fingerprint image is unclear, the feature point information corresponding to each feature point, particularly whether the feature point is an end point or a branch point is determined. There is an inconvenience that the accuracy and accuracy of the type determination are reduced. In addition, when a large amount of feature points are included in the fingerprint image, setting of each feature point information takes a lot of time and effort.

[Object of invention]
The present invention provides a feature point information setting device, a feature point information setting method, and a feature point information setting program capable of improving the inconveniences of the related techniques and quickly and accurately specifying the type of each feature point in a fingerprint image. Its purpose is to provide.

In order to achieve the above object, the feature point information setting device according to the present invention is configured so that the position of each feature point and the direction of each feature point included in a fingerprint image are set in advance. A fingerprint feature point information setting device including a feature point type determination unit for determining a type,
The feature point type determination unit includes a point A which is a density measurement point on a feature point vertical straight line set in a direction perpendicular to a line segment representing the feature point direction of each feature point on the fingerprint image, and Cross point density value acquisition means for alternately setting B points at regular intervals corresponding to the ridges of the fingerprint image and acquiring density values at the points A and B of the fingerprint image; An average density value Av which is an average value of density values of different A points, and an average density value calculating means for calculating an average density value Bv which is an average value of the acquired density values of different B points; and the average density value A feature point that determines the type of the feature point as a branch point when Av is higher than the average density value Bv, and determines that the type of the feature point is an end point when the average density value Av is lower than the average density value Bv With type determination means It is characterized in.

In order to achieve the above object, the feature point information setting method according to the present invention includes a feature point type determination unit 3 for acquiring a fingerprint image in which the position and the feature point direction of each preset feature point are set. In the fingerprint feature point information setting device, a fingerprint feature point information setting method for determining the type of each feature point by a predetermined procedure,
A point that is a density measurement point on a feature point intersection line segment set in an intersection state including a feature point vertical straight line perpendicular to a line segment representing the feature point direction of each feature point on the fingerprint image And B are alternately set at regular intervals corresponding to the ridges of the fingerprint image, and then the density values at the points A and B of the fingerprint image are obtained,
Next, an average density value Av, which is an average value of the acquired density values of different A points, and an average density value Bv, which is an average value of the acquired density values of different B points, are calculated.
Subsequently, when the average density value Av is higher than the average density value Bv, the type of the feature point is determined as a branch point, and when the average density value Av is lower than the average density value Bv, the type of the feature point is determined. The feature point type determination unit 3 sequentially executes each of the operation steps.

In order to achieve the above object, a feature point information setting program according to the present invention includes a feature point type determination unit 3 that acquires a fingerprint image in which the position and the feature point direction of each preset feature point are set. A fingerprint feature point information setting program for determining the type of each feature point in the fingerprint feature point information setting device,
A point that is a density measurement point on a feature point intersection line segment set in an intersection state including a feature point vertical straight line perpendicular to a line segment representing the feature point direction of each feature point on the fingerprint image A cross-direction density value acquisition processing function that alternately sets the B and B points at regular intervals corresponding to the ridges of the fingerprint image and acquires density values at the A and B points of the fingerprint image;
An average density value Av that is an average value of the acquired density values of different A points, and an average density value calculation processing function that calculates an average density value Bv that is an average value of the acquired density values of different B points;
When the average density value Av is higher than the average density value Bv, the type of the feature point is determined as a branch point, and when the average density value Av is lower than the average density value Bv, the type of the feature point is an end point. A feature point type determination processing function for determining
Each of these processing functions is realized by a computer provided in the above-described feature point type determination unit 3.

  Since the present invention is configured and functions as described above, according to this, the points A and B are alternately arranged at regular intervals on the line segment intersecting the feature point direction of each feature point included in the fingerprint image. And the density values of the fingerprint images at points A and B are acquired to calculate the average density values of points A and B, and the magnitude relationship between the average density values Av and Bv corresponding to each feature point Since the feature point type is determined by the feature point information setting system, the feature point information setting method, and the feature point information capable of quickly and accurately determining the type of each feature point in the fingerprint image. A configuration program can be provided.

It is a schematic block diagram which shows one Embodiment of the feature point information setting apparatus which concerns on this invention. It is a block diagram which shows an example of an internal structure of the feature point classification determination part in the feature point information setting apparatus disclosed in FIG. It is explanatory drawing which shows an example of the vertical straight line, A point, and B point which the feature point classification determination part in the feature point information setting apparatus disclosed in FIG. 1 set corresponding to the end point in the fingerprint image. It is explanatory drawing which shows an example of the vertical straight line, A point, and B point which the feature point classification determination part in the feature point information setting apparatus disclosed in FIG. 1 set corresponding to the branch point in the fingerprint image. It is a flowchart which shows the operation | movement process step in the feature point classification determination part of the feature point information setting apparatus disclosed in FIG. 6A and 6B are explanatory diagrams showing examples of feature points and surrounding pixels in a blurred fingerprint image, respectively. It is explanatory drawing which shows an example of the position of the feature point in a fingerprint image, and a feature point direction. It is explanatory drawing which shows an example of the branch point and end point as a kind of feature point in a fingerprint image.

Next, an embodiment of the present invention will be described with reference to FIGS.
First, the basic configuration content of one embodiment will be described, and then the specific content will be described.
First, as shown in FIG. 1, the feature point information setting apparatus 10 according to the present embodiment receives fingerprint image data inputted from the outside, stores it in a storage means, and displays ridges (FIG. A feature point position specifying unit 1 that specifies the position of the feature point in the fingerprint image based on the shape of the hatched portion in 1), and the feature point direction at each specified feature point along the ridge of the fingerprint image A feature point direction determination unit 2 that determines the method, and a feature point type determination unit 3 that determines the type of each feature point for which the feature point direction is determined (that is, whether each feature point is an end point or a branch point) It is configured with.

  Among these, the determination of the type of each feature point by the feature point type determination unit 3 is performed as described later on the basis of information relating to the feature point direction preset by the feature point direction determination unit 2. It has become.

  The feature point type determination unit 3 is a straight line (hereinafter referred to as “feature point perpendicular”) perpendicular to the feature point direction (arrow direction) corresponding to each feature point (for example, a in FIG. 3 and b in FIG. 4). Vertical density value acquisition means 31 for setting a straight line).

  This vertical density value acquisition means 31 sets two types of points, that is, a white point (point A) and a black point (point B) at equal intervals on the feature point vertical line set in FIGS. A white point / black point setting function and a density value acquisition function for acquiring the density value of the pixel at each position of the white point (point A) and the black point (point B) are provided.

In this case, in FIG. 3 and FIG. 4, the feature point vertical straight line is represented by a dotted line. Further, the positions of the white point (A point) and the black point (B point) are exemplarily set in FIGS.
In FIGS. 3 and 4, first, a black point (B point) is set in a region close to the feature points a and b, and the white point (A Point) and black point (point B) are sequentially set repeatedly.
Here, in the present embodiment, the region close to the feature points a and b is on the ridge (in the case of FIG. 3) where the intersection of the feature point direction (the direction of the arrow) described above and the feature point vertical straight line exists. A region between ridges (in the case of FIG. 4, a valley) is shown.

  Thus, the vertical direction density value acquisition unit 31 can acquire density values at regular intervals along the feature point vertical straight line set corresponding to the target feature points a and b.

  Further, the feature point type determination unit 3 described above includes density average value calculation means 32 that calculates the average value of the density values of the points A and B acquired by the vertical direction density value acquisition means 31. Here, the average density value at each point A is Av, and the average density value at each point B is Bv.

  The vertical density value acquisition means 31 changes the distance between the points A and B set on the feature point vertical straight line, and acquires the density value at the points A and B every time this change is made. It has an acquisition interval change function.

  Further, the above-described density average value calculation means 32 corresponds to Av, which is the average density value value of the A point acquired by the vertical direction density value acquisition means 31 corresponding to a plurality of different A points, and a plurality of different B points. And an average value calculation function for calculating Bv, which is the average density value acquired in this way.

  Further, the density average value calculating means 32 calculates and stores the difference between the calculated average density values Av and Bv (hereinafter referred to as “average density difference value”), and the average when the average density difference value becomes maximum. A maximum average density value determining function for determining density values Av and Bv is provided.

  Thus, for example, in FIG. 3, the white point A is set in the valley region between the ridges on the fingerprint image, and the black point B is set on the ridge on the fingerprint image. Therefore, the difference between the average density value Av at point A (closer to white (255)) and the average density value Bv at point B (closer to black (0)) increases.

  In FIG. 4, the black point B is in the valley region between the ridges on the fingerprint image, and the white point A is on the ridge (shaded portion) on the fingerprint image. Therefore, the difference between the average density value at point B (closer to white (255)) and the average density value at point A (closer to black (0)) becomes larger.

  Here, the vertical density value acquisition means 31 has a function of setting a straight line that passes through a position a certain distance away from the feature point in the feature point direction side and is perpendicular to the feature point direction as a feature point vertical straight line (vertical straight line position setting function). ).

  When the vertical density value acquisition unit 31 sets the distance between the point A and the point B corresponding to the target feature point a or the target point b, another feature point (near the target feature point) ( The value of the distance between the points A and B determined in advance corresponding to the neighboring feature point) is acquired, and the distance between the points A and B corresponding to the target feature point a or b based on this value It is good also as a structure provided with the function (density value acquisition point distance setting function) which sets this.

Further, the vertical density value acquisition means 31 may have a function of setting the distance between the points A and B based on the average value of the ridge width in a certain region including the target feature point a or b. Good.
Thereby, for example, when the ridge direction in a certain region including the target feature point is stable, that is, when the ridge width variance is equal to or less than a certain value, the density average value calculating means 32 calculates the average density. It becomes possible to quickly calculate the average density values Av and Bv when the difference value is maximum.

  Then, the feature point type determination unit 33 described above determines the type of the feature point (target feature point / for example, b) corresponding to the case where the calculated average density value Av is higher than the average density value Bv as a branch point, In addition, a feature point type determination function is provided that determines the type of the target feature point (for example, a) as an end point when the average density value Av is lower than the average density value Bv.

As described above, the feature point type determination unit 3 of the fingerprint feature point information setting device 10 has the above-described components when the position and direction (feature point direction) of each feature point in the fingerprint image is set in advance. (Vertical density value acquisition means 31, density average value calculation means 32, and feature point type determination means 33) are actuated to quickly and accurately determine the type of each feature point (for example, feature points a and b). be able to.
Therefore, in the fingerprint feature point information setting device 10 according to the present embodiment, feature point information (feature point position, feature point direction, and type) indicating the attributes of the fingerprint feature points is input to the fingerprint image data input externally. On the other hand, it is possible to set accurately and quickly.

(Description of operation)
Next, the operation content in the said embodiment is demonstrated.
First, the basic operation procedure of the feature point information setting device in the above embodiment will be described, and then the overall operation will be described in detail.

  The vertical density value acquisition unit 31 shown in FIG. 2 operates to set a feature point vertical line that is a straight line perpendicular to the feature point direction of each feature point in the fingerprint image, and A and B on the feature point vertical line. The points are alternately set at regular intervals (see FIGS. 3 and 4). Subsequently, the vertical density value acquisition unit 31 acquires the density value of the fingerprint image at the points A and B (vertical density value acquisition step).

  Next, the density average value calculating means 32 calculates the average density value A that is the average value of the density values of the different acquired A points and the average density value B that is the average value of the acquired density values of the different B points. Each is calculated (concentration average value calculation step).

  Finally, the feature point type determination means 33 determines the type of the feature point (target feature point) corresponding to the case where the calculated average density value A is higher than the average density value B as a branch point, and the average When the density value A is lower than the average density value B, the type of the target feature point is determined as an end point (a feature point type determination step).

Here, with respect to the vertical direction density value acquisition step, the density average value calculation step, and the feature point type determination step, the execution contents are programmed and realized by a computer provided in the feature point type determination unit 3. It may be configured.
In addition, the program may be recorded on a non-transitory storage medium such as a DVD, a CD, or a flash memory. In this case, the program is read from the recording medium by a computer and executed.

  Next, the operation content of the above-described feature point information setting apparatus 10 will be described in more detail with reference to FIGS.

  First, when digitized fingerprint image data is input to the feature point position specifying unit 1 of the feature point information setting device 10, the feature point position specifying unit 1 stores it in a data storage means (not shown). Subsequently, the feature point position specifying unit 1 specifies the positions of the feature points a and b in the fingerprint image based on the shape of the ridges in the fingerprint image.

In this embodiment, the feature point position designation in this case is configured to be executed by the feature point position designation unit 1 based on a command input from the outside through an input unit (not shown) by an operator. However, the feature point position designation unit 1 may execute the designation of the position according to a preset program.
Subsequently, the feature point direction determination unit 2 operates to determine the feature point direction at each designated feature point.

  Next, the vertical density value acquisition unit 31 of the feature point type determination unit 3 operates to acquire a fingerprint image in which the feature point position and the feature point direction are set by the feature point position specification unit 1 and the feature point direction determination unit 2. (FIG. 2). At the same time, the vertical density value acquisition unit 31 sets a straight line (feature point vertical straight line) perpendicular to the feature point direction for each feature point in the fingerprint image.

  Subsequently, the vertical density value acquisition means 31 sets two types of points (white point A and black point B) at equal intervals on the set feature point vertical line, and the white point A And the density value of the pixel in each position of the black point B is acquired (FIG. 5: step S101 / vertical direction density value acquisition process).

  Next, the density average value calculation unit 32 calculates Av, which is an average value of density values acquired corresponding to a plurality of different A points, and an average value of density values acquired corresponding to a plurality of different B points. Each Bv is calculated (FIG. 5: step S102).

  Next, the vertical density value acquisition unit 31 changes the distance between the points A and B set on the feature point vertical straight line, and re-acquires the density values at the points A and B (FIG. 5: Step S101). To the concentration value acquisition interval).

  Here, the density average value calculation means 32 calculates Av and Bv based on the re-acquired density values at points A and B, and also calculates the difference between the calculated average density values Av and Bv (hereinafter referred to as “average density difference value”). Are calculated and stored, and average density values Av and Bv when the average density difference value is maximized are determined (FIG. 5: step S103 / average density difference value is maximized).

  Then, the feature point type determination unit 33 determines that the type of the feature point (for example, b / see FIG. 4) is a branch point when Av is higher than Bv (Av> Bv). On the other hand, when Av is lower than Bv (Av <Bv), the feature point type determination means 33 determines the type of the feature point (for example, a / see FIG. 3) as an end point (FIG. 5: Step S104 / Feature Point Type Determination). Process).

  Thereby, the feature point type determination unit 3 can quickly and accurately determine the determination result as the feature point type (end point or branch point) for the feature point.

  As described above, in the feature point type determination unit 3 of the feature point information setting device 10 according to the above embodiment, when the position of the feature point and the feature point direction in the fingerprint image are specified in advance, each feature point (That is, whether the feature point is an end point or a branch point) can be quickly determined. Therefore, by using this embodiment, it is possible to accurately set feature point information for fingerprint matching for each feature point, and furthermore, an operator involved in input and setting operations of feature point information. It is possible to effectively reduce the time and effort.

  Here, in the above embodiment, instead of the feature point vertical straight line set by the vertical direction density value acquisition unit 31, a feature point crossing straight line in a direction intersecting the line segment representing the feature point direction is used. Then, as in the case of the feature point vertical straight line described above, a plurality of white points A and black points B are set, and based on this, the above-described components are operated to determine the feature point type (end point or branch point) You may make it do.

In this case, the feature point crossing straight line is not necessarily limited to a straight line, and an appropriate curve may be set according to the ridge pattern of the fingerprint image data.
In this way, it is possible to flexibly cope with many complicated fingerprints.

About the above-mentioned embodiment, it is as follows when the summary of the novel technical content is put together.
In addition, although one part or all part of the said embodiment is put together as follows as a novel technique, this invention is not necessarily limited to this.

[Appendix 1]
Fingerprint feature point information setting device provided with a feature point type determination unit 3 that determines the type of each feature point when the position of each feature point and the direction of each feature point are set in advance in a fingerprint image Because
The feature point type determination unit 3
On the fingerprint image, points A and B, which are density measurement points on a feature point vertical line set in a direction perpendicular to the line segment representing the feature point direction of each feature point, are formed as ridges of the fingerprint image. Cross-direction density value acquisition means 31 for alternately setting at regular intervals corresponding to lines and acquiring density values at the points A and B of the fingerprint image;
An average density value Av that is an average value of the acquired density values of different A points, and an average density value calculation means 32 that calculates an average density value Bv that is the average value of the acquired density values of different B points;
When the average density value Av is higher than the average density value Bv, the type of the feature point is determined as a branch point, and when the average density value Av is lower than the average density value Bv, the type of the feature point is set as an end point. A fingerprint feature point information setting device comprising: a feature point type determination unit 33 for determination.

[Appendix 2]
In the fingerprint feature point information setting device according to attachment 1,
The intersecting direction density value acquisition means 31 has a vertical straight line position setting function for setting the feature point vertical straight line passing through a position away from the feature point in the feature point direction side by a certain distance as the feature point vertical straight line. A fingerprint feature point information setting device.

[Appendix 3]
In the fingerprint feature point information setting device according to attachment 1,
The cross direction density value acquisition means 31 is another feature point in the vicinity of the target feature point when setting the distance between the points A and B corresponding to the target feature point as a certain feature point. A density for acquiring the value of the distance between the A and B points determined corresponding to the neighboring feature points and setting the distance between the A and B points corresponding to the target feature points based on this value A fingerprint feature point information setting device having a value acquisition point distance setting function.

[Appendix 4]
In the fingerprint feature point information setting device according to attachment 1,
The intersecting direction density value acquisition means 31 has a vertical straight line position setting function for setting the feature point vertical straight line passing through a position away from the feature point in the feature point direction side by a certain distance as the feature point vertical straight line;
When setting the distance between the points A and B corresponding to the target feature point as a certain feature point, the distance is determined corresponding to a neighboring feature point that is another feature point in the vicinity of the target feature point A density value acquisition point distance setting function for acquiring a distance value between the A and B points and setting a distance between the A and B points corresponding to the target feature point based on the value; This is a fingerprint feature point information setting device.

[Appendix 5]
In the fingerprint feature point information setting device according to any one of appendices 1 to 4,
The cross direction density value acquisition means 31 includes a density value acquisition interval change function for changing the distance between the points A and B and acquiring the density values at the points A and B each time the change is made.
The density average value calculating means 32 calculates the average density values Av and Bv corresponding to the points A and B acquired by the cross direction density value acquiring means 31, and the difference is maximum. A fingerprint feature point information setting device comprising a maximum difference average density value determination function for determining the average density values Av and Bv of the fingerprint.

[Appendix 6]
In the fingerprint feature point information setting device according to any one of appendices 1 to 5,
The intersecting direction density value acquisition means 31 has an intersecting line segment setting function for setting a feature point intersecting line segment in a direction intersecting with a line segment representing the feature point direction instead of the function of setting the feature point vertical straight line. With the configuration
A fingerprint feature point characterized in that a plurality of white points A and black points B are set on the feature point intersection line segment set by the intersection line segment setting function as in the case of the feature point vertical straight line. Information setting device.

[Appendix 7] (Invention of Method)
In a fingerprint feature point information setting device having a feature point type determination unit 3 for acquiring a fingerprint image in which the position and the feature point direction of each feature point set in advance are set, the type of each feature point is determined according to a predetermined procedure. A fingerprint feature point information setting method determined by
A point that is a density measurement point on a feature point intersection line segment set in an intersection state including a feature point vertical straight line perpendicular to a line segment representing the feature point direction of each feature point on the fingerprint image And B are alternately set at regular intervals corresponding to the ridges of the fingerprint image, and then the density values at the points A and B of the fingerprint image are obtained,
Next, an average density value Av, which is an average value of the acquired density values of different A points, and an average density value Bv, which is an average value of the acquired density values of different B points, are calculated.
Subsequently, when the average density value Av is higher than the average density value Bv, the type of the feature point is determined as a branch point, and when the average density value Av is lower than the average density value Bv, the type of the feature point is determined. Is determined to be an end point,
The feature point information setting method, wherein the feature point type determination unit 3 sequentially executes the operation steps.

[Appendix 8] (Program invention)
To determine the type of each feature point in a fingerprint feature point information setting device including a feature point type determination unit 3 for acquiring a fingerprint image in which the position and the direction of the feature point are set in advance. Fingerprint feature point information setting program of
A point that is a density measurement point on a feature point intersection line segment set in an intersection state including a feature point vertical straight line perpendicular to a line segment representing the feature point direction of each feature point on the fingerprint image A cross-direction density value acquisition processing function that alternately sets the B and B points at regular intervals corresponding to the ridges of the fingerprint image and acquires density values at the A and B points of the fingerprint image;
An average density value Av that is an average value of the acquired density values of different A points, and an average density value calculation processing function that calculates an average density value Bv that is an average value of the acquired density values of different B points;
When the average density value Av is higher than the average density value Bv, the type of the feature point is determined as a branch point, and when the average density value Av is lower than the average density value Bv, the type of the feature point is an end point. A feature point type determination processing function for determining
A fingerprint feature point information setting program characterized in that each of these processing functions is realized by a computer provided in the above-described feature point type determination unit 3.

  The present invention can be effectively applied to a fingerprint feature point information setting system that sets feature point information including the position, direction, and type of feature points for a fingerprint image for fingerprint verification.

DESCRIPTION OF SYMBOLS 1 Feature point position specification part 2 Feature point direction determination part 3 Feature point type determination part 10 Feature point information setting apparatus 31 Vertical direction density value acquisition means 32 Density average value calculation means 33 Feature point type determination means

Claims (8)

A fingerprint feature point information setting device including a feature point type determining unit that determines the type of each feature point when the position of each feature point and the direction of each feature point are set in advance in a fingerprint image. There,
The feature point type determination unit
On the fingerprint image, points A and B, which are density measurement points on a feature point vertical line set in a direction perpendicular to the line segment representing the feature point direction of each feature point, are formed as ridges of the fingerprint image. Crosswise density value acquisition means for alternately setting at regular intervals corresponding to lines and acquiring density values at points A and B of the fingerprint image;
An average density value Av that is an average value of the acquired density values of different A points, and an average density value calculating means that calculates an average density value Bv that is an average value of the acquired density values of different B points;
When the average density value Av is higher than the average density value Bv, the type of the feature point is determined as a branch point, and when the average density value Av is lower than the average density value Bv, the type of the feature point is set as an end point. A fingerprint feature point information setting device, comprising: a feature point type determining means for determining. In the fingerprint feature point information setting device according to claim 1,
The intersecting direction density value acquisition means has a vertical straight line position setting function for setting the feature point vertical straight line passing through a position away from the feature point toward the feature point direction by a certain distance as the feature point vertical straight line. A fingerprint feature point information setting device. In the fingerprint feature point information setting device according to claim 1,
The intersection direction density value acquisition means, when setting the distance between the points A and B corresponding to the target feature point as a certain feature point, a neighborhood that is another feature point in the vicinity of the target feature point A density value for obtaining a value of a distance between points A and B determined corresponding to the feature point and setting a distance between the points A and B corresponding to the target feature point based on this value A fingerprint feature point information setting device having a distance setting function between acquisition points. In the fingerprint feature point information setting device according to claim 1,
The intersecting direction density value acquisition means includes a vertical straight line position setting function for setting the feature point vertical straight line passing through a position away from the feature point toward the feature point direction by a certain distance as the feature point vertical straight line;
When setting the distance between the points A and B corresponding to the target feature point as a certain feature point, the distance is determined corresponding to a neighboring feature point that is another feature point in the vicinity of the target feature point A density value acquisition point distance setting function for acquiring a distance value between the A and B points and setting a distance between the A and B points corresponding to the target feature point based on the value; This is a fingerprint feature point information setting device. In the fingerprint feature point information setting device according to any one of claims 1 to 4,
The intersecting direction density value acquisition means includes a density value acquisition interval change function for changing the distance between the points A and B and acquiring the density values at the points A and B every time the change is made.
The density average value calculating means calculates the average density values Av and Bv corresponding to the points A and B acquired by the cross direction density value acquiring means, and the average when the difference becomes maximum A fingerprint feature point information setting device comprising a maximum difference average density value determination function for determining density values Av and Bv. In the fingerprint feature point information setting device according to any one of claims 1 to 5,
The intersecting direction density value acquisition means includes an intersecting line segment setting function for setting a feature point intersecting line segment in a direction intersecting with a line segment representing the feature point direction instead of the function of setting the feature point vertical straight line. And
A fingerprint feature point characterized in that a plurality of white points A and black points B are set on the feature point intersection line segment set by the intersection line segment setting function as in the case of the feature point vertical straight line. Information setting device. A fingerprint feature point information setting device having a feature point type determining unit for acquiring a fingerprint image in which a position and a feature point direction of each preset feature point are set. The type of each feature point is determined according to a predetermined procedure. A fingerprint feature point information setting method to be determined,
A point that is a density measurement point on a feature point intersection line segment set in an intersection state including a feature point vertical straight line perpendicular to a line segment representing the feature point direction of each feature point on the fingerprint image And B are alternately set at regular intervals corresponding to the ridges of the fingerprint image, and then the density values at the points A and B of the fingerprint image are obtained,
Next, an average density value Av, which is an average value of the acquired density values of different A points, and an average density value Bv, which is an average value of the acquired density values of different B points, are calculated.
Subsequently, when the average density value Av is higher than the average density value Bv, the type of the feature point is determined as a branch point, and when the average density value Av is lower than the average density value Bv, the type of the feature point is determined. Is determined to be an end point,
The feature point information setting method, wherein the feature point type determination unit sequentially executes the operation steps. A fingerprint feature point information setting device including a feature point type determination unit that acquires a fingerprint image in which a position and a feature point direction of each feature point set in advance is set, and for determining the type of each feature point A fingerprint feature point information setting program,
A point that is a density measurement point on a feature point intersection line segment set in an intersection state including a feature point vertical straight line perpendicular to a line segment representing the feature point direction of each feature point on the fingerprint image A cross-direction density value acquisition processing function that alternately sets the B and B points at regular intervals corresponding to the ridges of the fingerprint image and acquires density values at the A and B points of the fingerprint image;
An average density value Av that is an average value of the acquired density values of different A points, and an average density value calculation processing function that calculates an average density value Bv that is an average value of the acquired density values of different B points;
When the average density value Av is higher than the average density value Bv, the type of the feature point is determined as a branch point, and when the average density value Av is lower than the average density value Bv, the type of the feature point is an end point. A feature point type determination processing function for determining
A fingerprint feature point information setting program characterized in that each of these processing functions is realized by a computer provided in the above-described feature point type determination unit.

Images