JP2001307093A - Image data collation device, image data collation method and storage medium storing image data collation processing program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To accurately perform the collation of images considering a rotation deviation between registered image data and collation image data and to shorten time required for the collation in an image data collation device for collating fingerprint image data for instance. SOLUTION: For a collation fingerprint image B rotationally converted by respective rotation deviation correction angles θm (=0 deg., 1 deg., -1 deg., 2 deg., -2 deg., 3 deg., -3 deg.,..., k deg., -k deg. [m = the integer of 1 to k×2+1 and k>=1]) including the rotation deviation correction angle θ1=0 deg., by alternately executing the two kinds of collation processings that are the collation processing in the case of arranging a template area Ai inside a registered fingerprint image A and the collation processing in the case of arranging the template area Bi inside the rotation-converted collation fingerprint image B, the fingerprint collation of the same person/the same finger provided with the rotation deviation is performed. The possibility of obtaining collation matching is raised at the smaller rotation deviation correction angle θm, the arithmetic processing amount is reduced and collation time is shortened.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image data collating apparatus for collating fingerprint image data, an image data collating method, and a storage medium storing an image data collating processing program.

[0002]

2. Description of the Related Art For example, a personal computer (PC)
As one of the conventional fingerprint matching functions that operate on the above, there are feature figures (branch points, branch points, etc.) extracted from two fingerprint data of registered fingerprint data (registered fingerprint data) and fingerprint data to be matched (collated fingerprint data). End point etc.)
There is a fingerprint matching method "characteristic figure matching method" for determining the identity of the two fingerprint data. The "characteristic figure matching method" is effective in many cases where images are compared with each other in addition to fingerprints, and its effectiveness is well known.

However, the fingerprint data of the subject to be registered or collated is: (1) The fingerprint has a shallow "valley" and is not clear fingerprint data.

(2) The skin is soft, and the “mountain” of the fingerprint is easily broken.

(3) The appearance positions of characteristic figures (branch points, end points, etc.) tend to change.

(4) When the number of characteristic figures (branch points, end points, etc.) has a characteristic that changes greatly every time fingerprint data is collected, the probability of the collation failure in the above “characteristic figure collation method” It is said that the number of persons having fingerprints having such characteristics is about two to three per 100 persons.

This is too large in consideration of the fact that a standard value of about 0.1% is set as a false rejection rate or false acceptance rate at the time of fingerprint data collation, which is a problem in terms of authentication accuracy. .

Therefore, such a "characteristic figure collation method"
As a fingerprint data collation method that solves the above problem, an image data collation method filed by the same applicant (Japanese Patent Application No.
372205: filed on December 28, 1998).

In the image data collation method of the prior application, even in the case of fingerprint data having the above-described characteristics, the probability of collation failure is suppressed, and collation of registered fingerprint data and collation fingerprint data with sufficient authentication accuracy is achieved. There is disclosed a fingerprint data collation function capable of performing the following.

FIG. 18 is a flowchart showing the procedure of fingerprint data collation in the fingerprint data collation apparatus of the prior application.

FIG. 19 is a view showing a plurality of reference areas arranged in the registered fingerprint data in accordance with the fingerprint data collation procedure of the prior application and a plurality of areas detected on the collation fingerprint data based on the reference areas.

That is, as shown in FIGS. 18 and 19, (1) multi-tone registered fingerprint data: a plurality of rectangular areas A _i [i = 1 to N: an integer of N ≧ 2 (in this case, N = 5)]
Are defined and arranged (see FIG. 19A).

[0013] (2) wherein each rectangular region A _i, the collation fingerprint data: while scanning on B, using the pixel data in the collation fingerprint data B corresponding to the pixel data and its corresponding in each rectangular region A _i To calculate the correlation coefficient.

[0014] (3) the correlation coefficient for detecting a plurality of areas B _i which maximizes from the collation fingerprint data B (FIG. 19
(B)).

(4) The distribution of the plurality of rectangular areas {A _i | i = 1, 2,..., N} defined in the registered fingerprint data A and the plurality of areas {B _i
| I = 1, 2,..., N} and evaluates the identity of the registered fingerprint A and the collated fingerprint B. This is a fingerprint data collation method “template collation method using correlation coefficient”.

As described above, the "template matching method using correlation coefficient" which is the fingerprint data matching method of the prior application is as follows.
For each region A _i in which a plurality of regions are defined and arranged in the registered fingerprint data A, the region B _i having the maximum correlation coefficient is determined using the pixel data that can exist in the verification fingerprint data B. detected from the data B, the area defined in the registered fingerprint data _{a {a i | i = 1,2} , ..., N} the area detected from the distribution and the collation fingerprint data B {B _i | _i = 1 ,
2,..., N}, and the identity of the registered fingerprint data A and the collated fingerprint data B is evaluated for collation. Since the rotational deviation is not taken into account, for example, as shown in FIG. 20, when the collation fingerprint data B is collected, the collation fingerprint data B is collected with a rotational deviation with respect to the registered fingerprint data A for some reason. In this case, even if the verification fingerprint data is the same person and the same fingerprint data as the registered fingerprint data, an inappropriate area is detected as the area B _i having the maximum correlation coefficient, and the definition area ΔA _i | I = 1,2,
, N} and the detection area {B _i | i = 1, 2,
, N} are different from each other and are evaluated as not matching the registered fingerprint data.

FIG. 20 shows an example in which a plurality of reference areas arranged in the registered fingerprint data in accordance with the fingerprint data collation procedure of the prior application and a plurality of inappropriate areas based on the reference areas are detected in the collation fingerprint data. FIG.

[0018]

SUMMARY OF THE INVENTION The present invention has been made in view of the above-described problems, and it is intended to compare registered image data with collated image data even in a state in which the collated image has a rotational displacement. It is an object of the present invention to provide an image data collation device, an image data collation method, and a storage medium storing an image data collation processing program that can be performed accurately.

[0019]

An image data collating apparatus according to claim 1 of the present invention is an image data collating apparatus for collating image data A and image data B to determine the identity of the two. An image rotating means for rotating the image data A or the image data B by a predetermined angle, and an image data A for each rotation of the image data A or B by the image rotating means.
A first template arranging means for arranging a template defining a plurality of areas with respect to a plurality of areas having a maximum correlation with each of the plurality of areas arranged in the image data A by the first template arranging means A first correlation area detecting means for detecting an area on the image data B; a mutual positional relationship between a plurality of areas arranged in the image data A by the first template arranging means; and a first correlation area detecting means. First collation judging means for judging the identity between the image data A and the image data B by comparing the mutual positional relationship of a plurality of correlation areas detected on the image data B; A second template arranging means for arranging a template defining a plurality of regions in the image data B for each rotation of the data A or B; A second correlation area detecting means for detecting, on the image data A, a plurality of correlation areas having a maximum correlation with each of the plurality of areas arranged in the image data B by the arranging means; By comparing the mutual positional relationship between the plurality of regions arranged in the image data B and the relative positional relationship between the plurality of correlation regions detected on the image data A by the second correlation region detection means, the image data A and the A second collation judging means for judging the identity with the image data B.

In the image data collating device according to the first aspect of the present invention, for example, when the image data B is rotated by a predetermined angle, the image data A is output every time the image data B is rotated. , A template defining a plurality of regions is arranged, and a plurality of correlation regions having the maximum correlation with each of the plurality of template regions are detected on the rotated image data B. Then, by comparing the mutual positional relationship between the plurality of regions arranged in the image data A and the mutual positional relationship between the plurality of correlation regions detected on the image data B, the identity between the image data A and the image data B is determined. Is determined. On the other hand, a template that defines a plurality of regions for the image data B is arranged for each rotation of the image data B, and a plurality of correlation regions having the maximum correlation with each of the plurality of template regions is defined as the plurality of regions. It is detected on the image data A. Then, by comparing the mutual positional relationship between the plurality of regions arranged in the image data B and the mutual positional relationship between the plurality of correlation regions detected on the image data A, the identity between the image data A and the image data B is determined. Is determined. As a result, while the number of rotations (angle) of the image data B is small, the possibility that the matching of the image data A and B can be achieved increases, and the matching time can be shortened.

According to a sixth aspect of the present invention, in the image data collating apparatus, the first template arranging means arranges a template defining a plurality of regions with respect to the image data A or the second template Whether the arrangement means arranges a template defining a plurality of areas for the image data B is determined by the correlation value obtained by the first correlation area detection means and the correlation value obtained by the second correlation area detection means A template layout image selecting means for selecting based on the above, and when the first template layout means is selected by the template layout selecting means, the image rotating means, the first template layout means, the first correlation The area detection means and the first collation determination means collate and determine the image data A and the image data B. When the plate arranging unit is selected, the image data A and the image data B are collated by the image rotating unit, the second template arranging unit, the second correlation area detecting unit, and the second collating and judging unit. And a selection control means for determining.

In the image data collating apparatus according to the sixth aspect of the present invention, when a template area is arranged in the image data A, the correlation value obtained on the image data B with respect to the template area is expressed by: When the template area is arranged in the image data B, the template is arranged in the image data A while rotating the image data A or the image data B based on the correlation value obtained on the image data A with respect to the template area. And a process of detecting the correlation with the image data B and determining the collation, and a process of arranging the template in the image data B and detecting the correlation with the image data A and determining the collation are selected. For example, a process that has a large correlation value and easily obtains a matching match between the image data A and B is selected, so that the matching time can be further reduced.

[0023]

Embodiments of the present invention will be described below with reference to the drawings.

(First Embodiment) FIG. 1 is a block diagram showing a configuration of an electronic circuit of a fingerprint data matching device according to an embodiment of the image data matching device of the present invention.

This fingerprint data collation device includes a control unit (CP
U) 11, a storage device 12, a RAM 13, an image reading device 14, a display unit 15, an input unit 16, a storage medium reading unit 18, and a transmission control unit 19, and are interconnected via a bus 17.

The control unit (CPU) 11 responds to an input signal from the input unit 12 by using a control program stored in the storage device 12 in advance or from an external storage medium 18a such as a floppy disk FD.
The storage device 1 via a storage medium reading unit 18 such as a DD
2 or the fingerprint matching program read from the storage device 20b of the external computer terminal (program server 20a) to the storage device 12 via the transmission control unit 19 via the communication network 20. It starts up and controls the operation of each part of the circuit using the RAM 13 as a work memory.

The storage device 12 is constituted by a ROM of a semiconductor memory, a hard disk device HD, or the like, and in addition to previously storing the above-described control program read out by the control unit (CPU) 11 immediately after turning on the power of the present verification device. And a registered fingerprint image of the subject read in advance by the image reading device 14.

The RAM 13 is a work memory used by the control unit (CPU) 11 when executing the above-described control program.

The image reading device 14 is a device for acquiring (collecting) a registered fingerprint image and a collation fingerprint image of the subject, and is, for example, an image scanner device or an image sensor such as a CCD (charge coupled device).

The display unit 15 is a display device, such as a CRT or a liquid crystal display, for displaying a result of collation between the registered fingerprint image and the collation fingerprint image.

The input unit 16 is an input device such as a keyboard device for the user of the present collation device to instruct the control unit (CPU) 11 to acquire a fingerprint image or to start a fingerprint collation process described later. .

FIG. 2 shows the RAM 1 of the fingerprint data collating apparatus.
FIG. 3 is a diagram showing a data memory secured in No. 3;

The RAM 13 has a read image memory 13
a, a collation fingerprint image memory 13b, a collation fingerprint rotation image memory 13c, a registered fingerprint position memory 13d, a collation fingerprint position memory 13e, a rotation angle memory 13f, and the like.

In the read image memory 13a, the image data of the fingerprint of the subject read by the image reading device 14 is temporarily stored as a multi-tone image.

The collation fingerprint image memory 13b stores the image data of the fingerprint of the subject to be collated read by the image reader 14 as a multi-tone image, and the collation fingerprint image data is stored in the storage device. 12 is normalized and stored according to the number of pixels and the pixel pitch of the registered fingerprint image data stored and registered.

The rotated fingerprint image memory 13c stores image data that has been subjected to a rotation process when the matched fingerprint image data stored in the matched fingerprint image memory 13b is rotated by the rotation deviation correction angle θm.

The registered fingerprint position memory 13d stores coordinate data indicating the defined position of each of a plurality of rectangular areas Ai defined as templates for the registered fingerprint image data A stored and registered in the storage device 12, or the collation data. When a plurality of rectangular areas bi are defined as templates for the collation fingerprint image data B stored in the fingerprint image memory 13b, the respective partial images and the maximum correlation coefficient are calculated on the registered fingerprint image data A. Are detected, and coordinate data indicating the positions of the plurality of detected rectangular areas ai on the registered fingerprint image data A is stored.

When a plurality of rectangular areas Ai are defined as templates for the registered fingerprint image data A stored and registered in the storage device 12, the matching fingerprint position memory 13e has the maximum relative relationship with each partial image. A plurality of rectangular areas Bi on the matching fingerprint image data B whose number is calculated
Is detected, and the coordinate data indicating the position of each of the plurality of detected rectangular areas Bi on the collation fingerprint image data B or the collation fingerprint image data B stored in the collation fingerprint image memory 13b is defined as a template. The coordinate data indicating the defined position of each of the plurality of rectangular regions bi is stored.

The rotation angle memory 13h stores the verification fingerprint image data B stored in the verification fingerprint rotation image memory 13c.
Is stored.

FIG. 3 is a block diagram showing a configuration of an operation function accompanying execution of the fingerprint collation processing program of the first embodiment of the fingerprint data collation apparatus.

In the functional block of the operation function in the fingerprint data collating apparatus, the corresponding components of the electronic circuit in FIGS. 1 and 2 are indicated by reference numerals in parentheses.

The fingerprint data input unit 21 includes an image reading device 14, a read image memory 13a, and a collation fingerprint image memory 13b, and inputs a fingerprint image to be registered or a fingerprint image to be collated as a multi-tone image. The registered fingerprint image data A input by the fingerprint data input unit 21 is given to the registered fingerprint data storage unit 22 and stored and registered in the storage device 12, and the collated fingerprint image data B
Is given to the rotation conversion processing unit 24 in the collation processing unit 23.

The registered fingerprint image data A stored and registered by the registered fingerprint data storage unit 22 is given to the template arrangement processing unit 25 or the maximum correlation area detection processing unit 26 in the matching processing unit 23.

The matching processing unit 23 includes a control unit (CPU) 1
1, a fingerprint collation processing program in the storage device 12, a collation fingerprint rotation image memory 13c, a registered fingerprint position memory 13d,
It includes a collation fingerprint position memory 13e and a rotation angle memory 13f.

The rotation conversion processing unit 24 converts the entire collation fingerprint image data B provided from the fingerprint data input unit 21 into an angle θm (= 0, 1, −1, 2, −2, 3, −3,. k,
−k [m = 1 to k × 2 + 1, integer of k ≧ 1]) (the actual rotation conversion is not performed when θ1 = 0). The collation fingerprint image data B, which has been rotationally converted by the above, is provided to the maximum correlation area detection processing unit 26 or the template arrangement processing unit 25.

The template arrangement processing section 25 applies a plurality of rectangular areas A _i [i = 1 to N: N ≧ 5 to the registered fingerprint image data A stored and registered in the registered fingerprint data storage section 22.
2 (in this case, N = 5)] is defined and arranged as a template (see FIG. 6A), or is added to the collation fingerprint image data B that has been rotationally transformed by the rotational transformation processing unit 24 at an angle θm. against a plurality of rectangular regions _b i [i = _1~
N: an integer of N ≧ 2 (N = 5 in this case)] is defined and arranged as a template (see FIG. 8B), and is arranged on the registered fingerprint image data A by the template arrangement processing unit 25. The partial image data in the range corresponding to each of the plurality of rectangular areas Ai or the partial image data in the range corresponding to each of the plurality of rectangular areas bi arranged on the verification fingerprint image data B are subjected to the maximum correlation area detection processing. Section 26.

The maximum correlation area detection processing section 26
Registered fingerprint image data A in plate arrangement processing unit 25
When a plurality of rectangular areas Ai are arranged for
The partial images corresponding to the respective rectangular areas Ai are rotationally transformed.
The verification fingerprint rotated and converted by the angle θm in the processing unit 24
While scanning on the image data B, the respective rectangular areas A _i
Pixel data and corresponding fingerprint image data B corresponding thereto
The correlation coefficient is calculated using the pixel data in
A plurality of areas where the coefficient is maximum (maximum correlation area) B_iIlluminate
Detected from the fingerprint image data B (see FIG. 6) or
In the template layout processing unit 25, the illumination after the rotation conversion is performed.
A plurality of rectangular areas bi are arranged for the fingerprint image data B.
If it is determined that the part corresponding to each rectangular area bi
While scanning the minute image on the registered fingerprint image data A,
Each rectangular area b_iPixel data in the
Correlation coefficient using pixel data in recorded fingerprint image data A
And calculate the multiple regions (corresponding to the maximum
Correlation area) a_iFrom the registered fingerprint image data A
(See FIG. 8).

Then, the template arrangement processing section 25
A plurality of rectangular areas A for the registered fingerprint image data A
When i is arranged, the coordinate data indicating the position of each rectangular area Ai on the registered fingerprint image data A and the maximum correlation area detection processing unit 26 are detected on the collation fingerprint image data B after the rotation conversion. And the coordinate data indicating the position of each of the plurality of maximum correlation areas Bi
7 and the template arrangement processing unit 25
In the case where a plurality of rectangular areas bi are arranged with respect to the collation fingerprint image data B after the rotation conversion, coordinate data indicating the position of each of the rectangular areas bi on the collation fingerprint image data B and the maximum correlation area detection processing The coordinate data indicating the positions of the plurality of maximum correlation areas ai detected on the registered fingerprint image data A by the section 26
7 given.

When a plurality of rectangular areas Ai are arranged for the registered fingerprint image data A in the template arrangement processing section 25, the collation judgment processing section 27 receives the registered fingerprint image given from the template arrangement processing section 25. Based on coordinate data indicating the position of each rectangular area Ai on the data A and coordinate data indicating the position of each of the plurality of maximum correlation areas Bi detected by the maximum correlation area detection processing unit 26, the registered fingerprint image data A, the arrangement position distribution (mutual positional relationship) of the rectangular area Ai in A is compared with the position distribution (mutual positional relationship) of the detection area Bi in the rotated fingerprint fingerprint image data B. The similarity is determined to evaluate the identity. When a plurality of rectangular areas bi are arranged for the post-rotation verification fingerprint image data B in the template arrangement processing unit 25, on the post-rotation verification fingerprint image data B given from the template arrangement processing unit 25, Rectangular area b
i, based on the coordinate data indicating each position and the coordinate data indicating the position of each of the plurality of maximum correlation areas ai detected by the maximum correlation area detection processing unit 26, the rectangular area bi in the rotated verification fingerprint image data B. Is compared with the position distribution (mutual positional relationship) of the detection area ai in the registered fingerprint image data A, and based on the difference, the similarity between the registered fingerprint image and the collation fingerprint image is determined. Assess identity. Then, the evaluation result of the identity between the registered fingerprint image and the collation fingerprint image obtained by the collation determination processing unit 27 is given to the collation result display unit 28 and displayed.

Next, the fingerprint matching function of the first embodiment in the fingerprint data matching device having the above-described configuration will be described.

FIG. 4 is a flowchart showing a fingerprint collation process (part 1) of the first embodiment of the fingerprint data collation device.

FIG. 5 is a flowchart showing the fingerprint collation processing (part 2) of the first embodiment of the fingerprint data collation apparatus.

FIG. 6 shows a template area Ai on a registered fingerprint image A accompanying the fingerprint collation processing of the fingerprint data collation apparatus.
Position distribution and maximum correlation area B on collation fingerprint image B
It is a figure which shows the comparison state with the detection position distribution of i.

FIG. 7 shows the position data of the template position and the maximum correlation area detection position stored in the registered fingerprint position memory 13d and the collated fingerprint position memory 13e in the RAM 13 in accordance with the fingerprint collation processing of the fingerprint data collation device. FIG.

FIG. 8 shows a template area bi on the collation fingerprint image B accompanying the fingerprint collation processing of the fingerprint data collation apparatus.
Position distribution and the maximum correlation area a on the registered fingerprint image A
It is a figure which shows the comparison state with the detection position distribution of i.

FIG. 9 shows the position data of the template position and the maximum correlation area detection position respectively stored in the collation fingerprint position memory 13e and the registered fingerprint position memory 13d in the RAM 13 in accordance with the fingerprint collation processing of the fingerprint data collation device. FIG.

In a state where the fingerprint image A of the subject to be registered read by the image reading device 14 in the fingerprint data input unit 21 is previously stored and registered in the storage device 12 in the registered fingerprint data storage unit 22, The fingerprint image of the subject to be collated is stored in the image reading device 14.
Is written to the read image memory 13a in the RAM 13 and transferred to the collation fingerprint image memory 13b for storage.

Then, the fingerprint collation processing shown in FIGS. 4 and 5 is started. First, the entire collation fingerprint image B, which is a multi-tone image collected and stored in the collation fingerprint image memory 13b by the fingerprint data input unit 21, is In the rotation conversion processing unit 24, the rotational deviation correction angle θm (= 0 °, 1 °, −1 °, 2
°, -2 °, 3 °, -3 °, ..., k °, -k ° [m = 1
Ｋk × 2 + 1, k ≧ 1]]) and is stored in the fingerprint fingerprint rotation image memory 13c (step S).
1). However, when θ1 = 0, actual rotation conversion is not performed.

Then, in the template arrangement processing unit 25, the storage device 12 in the registered fingerprint data storage unit 22
FIG. 6 shows the multi-tone registered fingerprint image A stored in FIG.
As shown in (a), a plurality of rectangular template areas A _i
[I = 1 to N: an integer of N ≧ 2 (N = 5 in this case)] is defined and arranged, and coordinate data indicating the position of each template area Ai is registered as shown in FIG. The data is stored in the fingerprint position memory 13d (step S2).

Then, in the maximum correlation area detection processing section 26 in the collation processing section 23, the partial image corresponding to each rectangular template area Ai defined and arranged with respect to the registered fingerprint image A is converted in the rotation conversion processing section 24. After raster rotation by one pixel in the horizontal and vertical directions on the verification fingerprint image B stored in the verification fingerprint rotation image memory 13c after the rotation of θm, all pixel data in the template Ai and the corresponding verification fingerprint image are sequentially scanned. A correlation coefficient using the pixel data in B is calculated. Then, the region Bi in the collation fingerprint image B in which the correlation coefficient is maximum is shown in FIG.
7B, the coordinate data indicating the detection position of each maximum correlation area Bi is stored in the collation fingerprint position memory 13e as shown in FIG. 7B (steps S3 and S4). The calculation of the correlation coefficient will be described later.

Calculation of the maximum correlation coefficient on the post-rotation verification fingerprint image B based on the image data of each rectangular template area Ai defined on the registered fingerprint image A, and its area B
The detection of i is sequentially performed for each rectangular template area Ai (steps S3 to S5), and it is assumed that each area Bi on the collation fingerprint image B having the maximum correlation coefficient in all the rectangular template areas Ai has been detected. When the determination is made, in the matching determination processing unit 27 in the matching processing unit 23, the plurality of rectangular template areas ｛A _i | i = 1, 2,... Defined in the registered fingerprint image A as shown in FIG. , N} and the distribution (mutual positional relationship) of the plurality of regions {B _i | i = 1, 2,..., N} detected from the collation fingerprint image B, are compared. The identity between the registered fingerprint A and the verification fingerprint B is evaluated (steps S5 → S6).

That is, this collation determination processing (step S
6), coordinates A1 (X) that specify the positions of the rectangular template area A1 arranged on the registered fingerprint image A and the maximum correlation rectangular area B1 detected on the collation fingerprint image B on each image.
0, Y0) and B1 (XD0, YD0) as reference coordinates,
Each rectangular template area A arranged in the registered fingerprint image A
Coordinates A2 (X1, Y1) to A5 (X4, Y4), B2 specifying the positions of the respective maximum correlation rectangular areas B2 to B5 detected on the collation fingerprint image B and the respective maximum correlation rectangular areas B2 to B5.
For (XD1, YD1) to B5 (XD4, YD4), each relative distance between A1 and A2, A3, A4, A5 and B
Δi (i = 1, 2, 3, 4), which is the difference between the relative distances 1 and B2, B3, B4, B5, is calculated based on the following equation.

[0063]

(Equation 1)

Then, it is determined whether or not all the calculated Δi are within a predetermined value. If all of the calculated Δi are within the predetermined value, it is determined that the registered fingerprint A and the collated fingerprint B are coincident. It is determined that the fingerprint A and the verification fingerprint B do not match (step S7). Note that the predetermined value used here is, for example, ΔΔ based on fingerprint image data obtained from a plurality of persons.
i is actually calculated, and is set to a value at which desired collation accuracy is obtained based on the distribution of the calculation result.

Here, when it is determined that the registered fingerprint A and the collated fingerprint B are the same fingerprint, the series of collation processing is terminated, and the collated fingerprint A is collated with the collated fingerprint by the collation result display section 28 (15). It is displayed that fingerprint B is the same fingerprint (step S7 → end).

On the other hand, if it is not determined that the registered fingerprint A and the collated fingerprint B are the same fingerprint, then the template arrangement processing unit 25 performs the rotation after θm stored in the collated fingerprint rotated image memory 13c. Collation fingerprint image B
In contrast, as shown in FIG. 8B, a plurality of rectangular template areas b _i [i = 1 to N: an integer of N ≧ 2 (in this case, N
= 5)] is defined and the coordinate data indicating the position of each template area bi is stored in the collation fingerprint position memory 13e as shown in FIG. 9A (steps S7 → S8).

Then, in the maximum correlation area detection processing section 26 in the verification processing section 23, each rectangular template area bi defined and arranged with respect to the verification fingerprint image B after the rotation of θm.
Is stored in the registered fingerprint data storage unit 22.
The registered fingerprint image A stored and registered in the storage device 12 at
While performing raster scanning one pixel at a time in the horizontal and vertical directions, a correlation coefficient is sequentially calculated using all the pixel data in the template bi and the corresponding pixel data in the registered fingerprint image A. Then, the area ai in the registered fingerprint image A where the correlation coefficient is maximum is shown in FIG.
As shown in FIG. 9B, coordinate data indicating the detection position of each maximum correlation area ai is stored in the registered fingerprint position memory 13d as shown in FIG. 9B (steps S9 and S9).
10). The calculation of the correlation coefficient will be described later.

The calculation of the maximum correlation coefficient on the registered fingerprint image A based on the image data of each rectangular template region bi defined on the collation fingerprint image B after the θm rotation and the detection of the region ai are as follows. The process is sequentially performed for each rectangular template region bi (steps S9 to S11). If it is determined that each region ai on the registered fingerprint image A having the maximum correlation coefficient has been detected in all the rectangular template regions bi, the collation is performed. In the collation determination processing unit 27 in the processing unit 23,
As shown in FIG. 8, the plurality of rectangular template areas ｛b _i | i = 1, defined in the rotated verification fingerprint image B,
, N ， distribution (mutual positional relationship) and registered fingerprint image A
The plurality of areas {a _i | i = 1, 2, 2,
, N} (the mutual positional relationship), and the identity of the registered fingerprint A and the collated fingerprint B is evaluated (step S).
11 → S12).

That is, this collation determination processing (step S
12), coordinates b1 (X0, Y0) for specifying the positions of the rectangular template area b1 arranged on the collation fingerprint image B after the rotation of θm and the maximum correlation rectangular area a1 detected on the registered fingerprint image A on each image. , A1 (XD0, YD0) and θ
The coordinates b2 (X1) that specify the positions of the rectangular template areas b2 to b5 arranged in the collated fingerprint image B after m rotation and the maximum correlation rectangular areas a2 to a5 detected on the registered fingerprint image A on the respective images. , Y1) to b5 (X4, Y
4), a2 (XD1, YD1) to a5 (XD4, YD
4), Δi (i = 1, 2, 3, 4), which is the difference between each relative distance between b1 and b2, b3, b4, and b5 and each relative distance between a1 and a2, a2, a3, a4, and a5. ) Is calculated based on the above equation.

Then, it is determined whether or not all the calculated Δi are within a predetermined value. If all the calculated Δi are within the predetermined value, it is determined that the registered fingerprint A and the collated fingerprint B are coincident. It is determined that the fingerprint A and the verification fingerprint B do not match (step S13).

Here, if it is determined that the registered fingerprint A and the collated fingerprint B are the same fingerprint, the series of collation processing is terminated, and the collated fingerprint A is collated with the collated fingerprint A by the collation result display section 28 (15). It is displayed that fingerprint B is the same fingerprint (step S13 → end).

On the other hand, when it is not determined that the registered fingerprint A and the verification fingerprint B are the same fingerprint, all the rotational deviation correction angles θm (=
0 °, 1 °, -1 °, 2 °, -2 °, 3 °, -3 °,
.., K °, −k ° [m = 1 to k × 2 + 1, k ≧ 1 integer]), for each of the rotated verification fingerprint images B after rotation, the registered fingerprint image A according to steps S1 to S13 and It is determined whether the collation processing has been performed (step S
13 → S14).

When it is determined that a series of collation processing with the registered fingerprint image A has not been performed for the rotated collation fingerprint image B, which has been rotationally converted by all the rotation deviation correction angles θm specified above, with the registered fingerprint image A. Returning to the processing from step S1, the collation fingerprint image is subjected to rotation conversion processing by the next rotational deviation correction angle θm (= m + 1), and the rotated collation fingerprint image B is similarly registered with the registered fingerprint image A as described above. The collation processing when the template area Ai is defined and arranged thereon, and the collation processing when the template area bi is defined and arranged on the rotated collation fingerprint image B are repeatedly performed (step S14 → S1 to S13).

If it is determined that a series of collation processing with the registered fingerprint image A has been performed for the rotated collation fingerprint image B that has been rotationally converted by all the rotational deviation correction angles θm, the series of collation processing is performed. The matching process is terminated, and the matching result display unit 28 (15) displays that the registered fingerprint A and the matching fingerprint B are not the same fingerprint (step S14 → end).

Next, the calculation of the correlation coefficient used in steps S3 to S5 and steps S9 to S11 of the fingerprint collation processing shown in FIGS. 4 and 5 will be described. Here, a description will be given as calculation of a correlation coefficient between the rectangular area A and the rectangular area B.

First, the pixels included in each of the rectangular area A and the rectangular area B are represented by A (i, j) and B (m,
n). However, the total number of pixels included in each of the rectangular area A and the rectangular area B is equal. Also, let _{Xij and Ymn} be signal intensities, which are multi-tone values indicating shading for these pixels.

When these signal strengths are generalized and expressed as Zpq, the following equation is defined.

[0078]

(Equation 2)

In the above equation, N indicates the total number of pixels included in the rectangular area. In the above equation, Σ indicates the sum of all the pixels included in the rectangular area. That is, the above expression indicates the average value of the signal intensity for the pixels included in the rectangular area.

Next, the following expression is further defined.

[0081]

(Equation 3)

The above equation shows the mean square value of the signal intensity for the pixels included in the rectangular area.

Here, the correlation coefficient C _AB between the rectangular area A and the rectangular area B can be calculated by the following equation expressed by using the definition of the above equation.

[0084]

(Equation 4)

A correlation coefficient between regions is calculated using the above equation.

Therefore, according to the fingerprint data collating apparatus of the first embodiment having the above-described configuration, when performing the rotational displacement correction in consideration of the rotational center and the rotational displacement that occurred when the fingerprint image was collected, In many cases, the rotation center does not coincide with the prescribed rotation center in the rotation conversion processing, and the rotational misalignment correction angle at which the collation match is obtained when the template is arranged on the registered fingerprint image A and the collation processing is performed, Focusing on the fact that when the template is arranged on the collation fingerprint image B and the collation processing is performed, the absolute value of the rotation misalignment correction angle at which the collation match is obtained is not equal, and the rotational misalignment correction angle θ1 = 0 ° is included. , Each rotational deviation correction angle θm (= 0
°, 1 °, -1 °, 2 °, -2 °, 3 °, -3 °, ...,
k °, −k ° [m = 1 to k × 2 + 1, k ≧ 1 integer])
The collation processing when the template area Ai is arranged in the registered fingerprint image A for the collation fingerprint image B that has been rotated and converted, and the collation processing when the template area bi is arranged in the collation fingerprint image B that has been rotationally transformed. Since the same matching process is performed alternately, the possibility of obtaining a matching match with a smaller rotation shift correction angle θm increases when performing fingerprint matching of the same person and the same finger having a rotation shift, The amount of calculation processing can be reduced, and the collation time can be reduced.

In the first embodiment, only the collation fingerprint image B is subjected to the rotation conversion process for correcting the rotational deviation, and the collation fingerprint image B which is sequentially rotationally converted by the rotational deviation correction angle θm is registered. Two types of collation processing are alternately performed: a case where the template Ai is defined and arranged on the fingerprint image A and a case where the template bi is defined and arranged on the rotationally transformed collation fingerprint image B. As will be described in the following second embodiment, a collation process performed by defining and arranging a template Ai on a non-rotated registered fingerprint image A for a collation fingerprint image B that is sequentially rotated and converted at a rotational deviation correction angle θm; For the registered fingerprint image A that is sequentially rotated and converted at the shift correction angle θm, the matching process performed by defining and arranging the template bi on the non-rotating matching fingerprint image B is alternately performed. And Hodokosuru configuration, the same way, may be more collation coincidence in a small rotational shift correction angle θm is obtained.

(Second Embodiment) FIG. 10 is a block diagram showing a configuration of an operation function of the fingerprint data matching device according to a second embodiment of the present invention.

In the fingerprint matching operation function according to the second embodiment, the rotation conversion processing unit 24 uses the fingerprint data input unit 2
1 and the registered fingerprint image A provided from the registered fingerprint data storage unit 22 are alternately and rotationally converted by the rotational deviation correction angle θm, and when the collated fingerprint image B is rotationally converted. In the template arrangement processing unit 25, the template area Ai is defined and arranged for the registered fingerprint image A provided from the registered fingerprint data storage unit 22, and when the registered fingerprint image A is rotationally converted, the template area Ai is provided from the fingerprint data input unit 21. The template area bi is defined and arranged for the collation fingerprint image B to be obtained.

In the maximum correlation area detection processing section 26 and the collation determination processing section 27, the template arrangement processing section 25 compares the registered fingerprint image A with the collation fingerprint image B sequentially rotated and converted in the rotation conversion processing section 24. A process for detecting and comparing the maximum correlation area Bi corresponding to the template area Ai defined and arranged above, and a template arrangement processing section for the registered fingerprint image A sequentially rotated and converted by the rotation conversion processing section 24 At 25, the processing of detecting the maximum correlation area ai corresponding to the template area bi defined and arranged on the collation fingerprint image B and performing the collation processing is performed alternately.

Next, a description will be given of a fingerprint matching function according to the second embodiment in the fingerprint data matching device having the above-described configuration.

FIG. 11 is a flowchart showing a fingerprint collation process (part 1) of the second embodiment of the fingerprint data collation device.

FIG. 12 is a flowchart showing the fingerprint collation processing (part 2) of the second embodiment of the fingerprint data collation apparatus.

First, the entire collation fingerprint image B, which is a multi-tone image collected and stored by the fingerprint data input unit 21, is
In the rotation conversion processing unit 24, the rotation deviation correction angle θm (=
0 °, 1 °, -1 °, 2 °, -2 °, 3 °, -3 °,
.., K °, −k ° [m = 1 to k × 2 + 1, k ≧ 1 integer]) are rotationally converted (step S1). Where θ
When 1 = 0, no actual rotation conversion is performed.

Then, in the template arrangement processing unit 25, the non-rotated registered fingerprint image A stored in the registered fingerprint data storage unit 22 is subjected to a plurality of rectangular template areas A _i [i = 1 to N: N ≧ 2. Integer (N = 5 in this case)]
Are defined and arranged (step S2).

Then, in the maximum correlation area detection processing section 26 in the collation processing section 23, the partial image corresponding to each rectangular template area Ai defined and arranged with respect to the registered fingerprint image A is converted in the rotation conversion processing section 24. 1 in the horizontal and vertical directions on the collation fingerprint image B
While being raster-scanned pixel by pixel, a correlation coefficient is sequentially calculated using all the pixel data in the template Ai and the corresponding pixel data in the collation fingerprint image B.
Then, an area Bi in the collation fingerprint image B where the correlation coefficient becomes maximum is detected (steps S3 and S4).

The calculation of the maximum correlation coefficient on the post-rotation verification fingerprint image B based on the image data of each rectangular template area Ai defined on the non-rotated registered fingerprint image A and the detection of the area Bi are as follows. This is performed sequentially for each rectangular template area Ai (steps S3 to S5), and when it is determined that each area Bi on the verification fingerprint image B having the maximum correlation coefficient is detected for all the rectangular template areas Ai, In the matching determination processing unit 27 in the matching processing unit 23,
The distribution (mutual positional relationship) of the plurality of rectangular template regions {A _i | i = 1, 2,..., N} defined in the registered fingerprint image A and the plurality of regions {B detected from the collation fingerprint image B _i | i = 1,2, ..., N} distribution (mutual positional relationship)
Are compared, and the identity of the registered fingerprint A and the collated fingerprint B is evaluated (steps S5 → S6).

If it is determined that the registered fingerprint A and the collated fingerprint B are the same fingerprint, the series of collation processing is terminated, and the collated fingerprint A and the collated fingerprint are displayed by the collation result display unit 28 (15). It is displayed that B is the same fingerprint (step S7 → end).

On the other hand, if it is not determined that the registered fingerprint A and the verification fingerprint B are the same fingerprint, subsequently, the entire registered fingerprint image A stored in the registered fingerprint data storage unit 22 is subjected to the rotation conversion processing. In the section 24, the rotational deviation correction angle θm
(= 0 °, 1 °, -1 °, 2 °, -2 °, 3 °, -3
,..., K °, −k ° (m = 1 to k × 2 + 1, k ≧ 1 integer)) (Steps S7 → S8)
a). However, when θ1 = 0, actual rotation conversion is not performed.

Then, in the template arrangement processing section 25, a plurality of rectangular template areas b _i [i = 1 to N: N ≧ 2 are applied to the non-rotated verification fingerprint image B collected and stored by the fingerprint data input section 21. (In this case N =
5)] is defined and arranged (step S8).

Then, in the maximum correlation area detection processing section 26 in the verification processing section 23, the non-rotated verification fingerprint image B
A partial image corresponding to each rectangular template area bi defined and arranged with respect to
All the pixel data in the template bi and the corresponding pixel data in the registered fingerprint image A were sequentially used while raster-scanning one pixel at a time in the horizontal and vertical directions on the rotationally converted registered fingerprint image A. A correlation coefficient is calculated. Then, the area ai in the registered fingerprint image A where the correlation coefficient becomes the maximum is detected (steps S9 and S1).
0).

The calculation of the maximum correlation coefficient on the registered fingerprint image A after rotation based on the image data of each rectangular template area bi defined on the non-rotated verification fingerprint image B and the detection of the area ai are as follows. This is performed sequentially for each rectangular template area bi (steps S9 to S11). When it is determined that each area ai on the registered fingerprint image A having the maximum correlation coefficient has been detected for all the rectangular template areas bi, In the matching determination processing unit 27 in the matching processing unit 23,
The distribution (mutual positional relationship) of the plurality of rectangular template regions {b _i | i = 1, 2,..., N} defined in the non-rotated collation fingerprint image B and the rectangular fingerprint template detected from the registered fingerprint image A after rotation The distribution (mutual positional relationship) of the plurality of regions {a _i | i = 1, 2,..., N} is compared, and the identity of the registered fingerprint A and the verification fingerprint B is evaluated (step S11 → S1).
2).

When it is determined that the registered fingerprint A and the collated fingerprint B are the same fingerprint, the series of collation processing is terminated, and the collated fingerprint A and collated fingerprint are displayed by the collation result display unit 28 (15). It is displayed that B is the same fingerprint (step S13 → end).

On the other hand, when it is not determined that the registered fingerprint A and the verification fingerprint B are the same fingerprint, all the rotational deviation correction angles θm (=
0 °, 1 °, -1 °, 2 °, -2 °, 3 °, -3 °,
.., K °, −k ° [m = 1 to k × 2 + 1, k ≧ 1 integer]), for each of the post-rotation verification fingerprint image B and the post-rotation registration fingerprint image A, It is determined whether the matching process with the non-rotating registered fingerprint image A and the matching process with the non-rotating matching fingerprint image B according to S1 to S13 have been performed (steps S13 → S14).

Then, the collation processing of the non-rotated registered fingerprint image A with respect to the non-rotated registered fingerprint image A of the rotated collated fingerprint image B, which has been rotationally converted by all the prescribed rotational deviation correction angles θm, is performed. If it is determined that the matching process with the non-rotating matching fingerprint image B for A has not been performed, the process returns to the process from step S1, and the rotation conversion is performed using the next rotation shift correction angle θm (= m + 1). The collation processing when the template region Ai is defined and arranged on the non-rotated registered fingerprint image A for the collated fingerprint image B, and the registered fingerprint image A that has been rotationally transformed by the next rotational deviation correction angle θm (= m + 1) Are repeatedly performed when the template region bi is defined and arranged on the non-rotated verification fingerprint image B (step S14 → S1 to S1).
S13).

Further, the collation processing of the non-rotated registered fingerprint image A with respect to the non-rotated registered fingerprint image A of each rotated collated fingerprint image B, which has been rotationally converted by all the rotational deviation correction angles θm, is performed. If it is determined that the collation processing with the non-rotated collation fingerprint image B has been performed, the series of collation processing is terminated, and the collation fingerprint A and the collation fingerprint B are the same on the collation result display unit 28 (15). It is displayed that it is not a fingerprint (step S14 → end).

Therefore, even with the fingerprint data collation device of the second embodiment, it is possible to obtain collation coincidence at a smaller rotational misalignment correction angle θm for performing fingerprint collation of the same person / same finger having rotational misalignment. Is higher,
The amount of calculation processing can be reduced, and the collation time can be reduced.

In the second embodiment, when the collation fingerprint image B is rotationally transformed, the template area Ai is defined and arranged on the non-rotated registered fingerprint image A, and the collation processing with the collation fingerprint image B after the rotation is performed. In addition, when the registered fingerprint image A is rotationally converted, the template bi is defined and arranged on the non-rotated collation fingerprint image B and the collation processing with the rotated registered fingerprint image A is performed. As described in the third embodiment, the collation fingerprint image B and the registered fingerprint image A are alternately rotated and converted, and the rotationally transformed collation fingerprint image B and the registered fingerprint image A are converted into the template areas bi and Ai. Are defined and the matching process with the non-rotating registered fingerprint image A and the matching process with the non-rotating matching fingerprint image B are alternately performed. May be collation coincidence is obtained in .theta.m.

(Third Embodiment) FIG. 13 is a block diagram showing the configuration of the operation function of the fingerprint data matching device according to the execution of the fingerprint matching processing program of the third embodiment.

In the fingerprint collation operation function of the third embodiment, the rotation conversion processing unit 24 uses the fingerprint data input unit 2
1 and the registered fingerprint image A provided from the registered fingerprint data storage unit 22 are alternately rotated by the rotational deviation correction angle θm. The template areas bi and Ai are defined and arranged for the registered fingerprint image A.

Then, the maximum correlation area detection processing section 26 and the collation determination processing section 27 apply the non-rotated registered fingerprint image A given from the registered fingerprint data storage section 22 to the template arrangement processing section 25 after each rotation. The process of detecting the maximum correlation area ai corresponding to the template area bi defined and arranged on the collation fingerprint image B and performing the collation is performed. The non-rotational collation fingerprint image B provided from the fingerprint data input unit 21 The arrangement processing unit 25 alternately performs the process of detecting the maximum correlation area Bi corresponding to the template area Ai defined and arranged on the registered fingerprint image A after each rotation and checking the maximum correlation area Bi.

Therefore, even with the fingerprint data collation device of the third embodiment, it is possible to perform collation at a smaller rotational misalignment correction angle θm when performing fingerprint collation of the same person / same finger having rotational misalignment. Is higher,
The amount of calculation processing can be reduced, and the collation time can be reduced.

In the second embodiment, when the collation fingerprint image B is rotationally transformed, the template area Ai is defined and arranged on the non-rotated registration fingerprint image A, and the collation with the rotated collation fingerprint image B is performed. And a process of defining and arranging a template area bi on a non-rotated collation fingerprint image B when the registered fingerprint image A is rotationally transformed and collating with the registered fingerprint image A after the rotation. In the state where the matching judgment cannot be obtained, the rotation deviation correction angle θm is sequentially updated and alternately repeated. However, as described in the following fourth embodiment, the rotation deviation correction angle of the initial setting is set. When θm (θ1 = 0 °), the verification fingerprint image B when the template area Ai is defined and arranged on the registered fingerprint image A
Maximum correlation coefficient MAXC calculated in the matching process for
The magnitude of C is compared with the maximum correlation coefficient maxcc calculated in the collation processing on the registered fingerprint image A when the template area bi is defined and arranged on the collation fingerprint image B. If the maximum correlation coefficient MAXCC in the case where the template area Ai is defined and arranged on the registered fingerprint image A is larger, the registered fingerprint image A is sequentially rotated and converted by the rotational deviation correction angle θm. When the matching process performed by defining the template region Ai is selected and fingerprint matching is performed, and the maximum correlation coefficient maxcc when the template region bi is defined and arranged on the matching fingerprint image B is larger, With a configuration in which the collation processing performed by defining the template area bi on the collation fingerprint image B while sequentially rotating and converting the registered fingerprint image A by the rotational deviation correction angle θm and performing the fingerprint collation is performed, the number of calculations is further reduced. The matching time may be reduced by the processing amount.

(Fourth Embodiment) FIG. 14 is a block diagram showing a configuration of an operation function of the fingerprint data matching device according to a fourth embodiment of the present invention.

In the fingerprint collation operation function of the fourth embodiment, the collation fingerprint image B given from the fingerprint data input unit 21 is converted by the rotation conversion processing unit 24 into the rotational deviation correction angle θm.
When the rotation is converted by the
Area A on the registered fingerprint image A given by
i is defined and arranged, the maximum correlation area detection processing unit 26 and the collation determination processing unit 27 detect a region where the maximum correlation coefficient is calculated on the rotated collation fingerprint image B, and perform fingerprint collation; When the registered fingerprint image A given from the registered fingerprint data storage unit 22 is rotationally converted by the rotation conversion processing unit 24 at the rotational deviation correction angle θm, the template area bi is added to the collation fingerprint image B given from the fingerprint data input unit 21. Is defined, and the maximum correlation area detection processing unit 26 and the collation determination processing unit 27 detect the area where the maximum correlation coefficient is calculated on the rotated registered fingerprint image A, and perform fingerprint collation. . In this case, the rotation conversion processing unit 2
The rotation deviation correction angle θm at 4 is θ1 accompanying the initial setting.
= 0 °, the template area A on the registered fingerprint image A calculated by the maximum correlation area detection processing unit 26
The maximum correlation coefficient MAXCC for the collation fingerprint image B when 1 is arranged and the maximum correlation coefficient maxcc for the registered fingerprint image A when the template area b1 is arranged on the collation fingerprint image B are selected from the template arrangement fingerprint data. If the processing unit 29 makes a comparison, the template placement fingerprint data selection processing unit 29 determines that the maximum correlation coefficient MAXCC when the template area A1 is defined and placed on the registered fingerprint image A is larger, In the processing after θ2 = 1 ° after updating the correction angle θm, the collation fingerprint image B obtained from the fingerprint data input unit 21
Is fixedly given to the rotation conversion processing unit 24, and the registered fingerprint image A obtained from the registered fingerprint data storage unit 22 is fixed and given to the template arrangement processing unit 25. Ai is defined and fixed to the process of collating with the collation fingerprint image B which is sequentially rotated and converted. Further, the maximum correlation coefficient max when the template area b1 is defined and arranged on the collation fingerprint image B
When it is determined that cc is larger, the registered fingerprint image A obtained from the registered fingerprint data storage unit 22 is fixed to the rotation conversion processing unit 24 in the processing after θ2 = 1 ° in which the rotational deviation correction angle θm is updated. At the same time, the collation fingerprint image B obtained from the fingerprint data input unit 21 is selected and determined so as to be fixedly provided to the template arrangement processing unit 25.
The template region bi is defined and arranged in the collation fingerprint image B, and is fixed to the process of performing collation with the registered fingerprint image A that is sequentially rotated and converted.

Next, a description will be given of a fingerprint matching function according to the fourth embodiment in the fingerprint data matching device having the above-described configuration.

FIG. 15 is a flowchart showing a fingerprint collation process (part 1) of the fourth embodiment of the fingerprint data collation device.

FIG. 16 is a flowchart showing the fingerprint collation processing (part 2) of the fingerprint data collation apparatus according to the fourth embodiment.

First, the entirety of the collation fingerprint image B, which is a multi-tone image collected and stored by the fingerprint data input unit 21, is
In the rotation conversion processing unit 24, the rotation deviation correction angle θm (=
0 °, 1 °, -1 °, 2 °, -2 °, 3 °, -3 °,
.., K °, −k ° [m = 1 to k × 2 + 1, k ≧ 1 integer]) are rotationally converted (step S1).

However, only when the rotational deviation correction angle θm is θ1 = 0 ° by the initial setting, that is, in this step S
Only in the first rotation conversion process of the collation fingerprint image B in No. 1, the actual rotation conversion is not performed.

Then, in the template arrangement processing unit 25, the non-rotated registered fingerprint image A stored in the registered fingerprint data storage unit 22 is subjected to a plurality of rectangular template areas A _i [i = 1 to N: N ≧ 2. Integer (N = 5 in this case)]
Are defined and arranged (step S2).

Then, in the maximum correlation area detection processing section 26 in the collation processing section 23, the partial image corresponding to each rectangular template area Ai defined and arranged with respect to the registered fingerprint image A is converted in the rotation conversion processing section 24. All the pixel data in the template Ai are sequentially scanned while raster-scanning one pixel at a time in the horizontal and vertical directions on the collation fingerprint image B that has been rotationally transformed by θm (substantially not rotated when θ1 = 0 °). The correlation coefficient using the corresponding pixel data in the collation fingerprint image B is calculated. Then, an area Bi in the collation fingerprint image B where the correlation coefficient becomes maximum is detected (steps S3 and S4).

The first fingerprint defined on the registered fingerprint image A
The maximum correlation coefficient value calculated when detecting the area B1 from the collation fingerprint image B for the rectangular template area A1 is M
AXCC is provided to the template arrangement fingerprint data selection processing unit 29.

The calculation of the maximum correlation coefficient and the detection of the area Bi on the post-rotation collation fingerprint image B based on the image data of each rectangular template area Ai defined on the non-rotated registered fingerprint image A are performed. , Each rectangular template area Ai
When each region Bi on the collation fingerprint image B having the maximum correlation coefficient is determined to be detected in all the rectangular template regions Ai, it is sequentially performed (steps S3 to S5). , The distribution (mutual positional relationship) of the plurality of rectangular template regions {A _i | i = 1, 2,..., N} defined in the registered fingerprint image A and the matching fingerprint image B The detected distributions (mutual positional relationships) of the plurality of regions {B _i | i = 1, 2,..., N} are compared, and the identity of the registered fingerprint A and the verification fingerprint B is evaluated (step S5). → S6).

If it is determined that the registered fingerprint A and the collated fingerprint B are the same fingerprint, the series of collation processing is terminated, and the collated fingerprint A and the collated fingerprint are displayed by the collation result display unit 28 (15). It is displayed that B is the same fingerprint (step S7 → end).

On the other hand, if it is not determined that the registered fingerprint A and the collated fingerprint B are the same fingerprint, the rotation deviation correction angle θm currently set in the rotation conversion processing unit 24 is set to θ1 = 0 in the initial setting. ° (Step S
7 → S7a).

Here, the rotation deviation correction angle θm currently set in the rotation conversion processing section 24 is set to θ
If it is determined that 1 = 0 °, then the entirety of the registered fingerprint image A stored in the registered fingerprint data storage unit 22 is rotated by the rotation conversion processing unit 24 so that the rotational deviation correction angle θm (= 0) °, 1 °, -1 °, 2 °, -2 °, 3 °,-
3 °,..., K °, −k ° [m = 1 to k × 2 + 1, k ≧ 1
) (Steps S7a → S8)
a).

However, only when this rotational deviation correction angle θm is θ1 = 0 ° by the initial setting, that is, in this step S
Only during the first rotation conversion processing of the registered fingerprint image A in 8a, the actual rotation conversion is not performed.

Then, in the template arrangement processing section 25, a plurality of rectangular template areas b _i [i = 1 to N: N ≧ 2 are applied to the non-rotated verification fingerprint image B collected and stored by the fingerprint data input section 21. (In this case N =
5)] is defined and arranged (step S8).

Then, in the maximum correlation area detection processing section 26 in the verification processing section 23, the non-rotated verification fingerprint image B
A partial image corresponding to each rectangular template area bi defined and arranged with respect to
While raster-scanning one pixel at a time in the horizontal and vertical directions on the registered fingerprint image A that has been rotationally converted (substantially unrotated when θ1 = 0 °), all pixel data in the template bi and the corresponding pixel data are sequentially scanned. The correlation coefficient using the pixel data in the registered fingerprint image A to be calculated is calculated. Then, the area ai in the registered fingerprint image A where the correlation coefficient becomes the maximum is detected (steps S9 and S10).

Here, the first defined on the collation fingerprint image B
The maximum correlation coefficient value calculated when detecting the area a1 from the registered fingerprint image A for the rectangular template area b1 is m
axcc is given to the template arrangement fingerprint data selection processing unit 29.

The calculation of the maximum correlation coefficient on the registered fingerprint image A after the rotation processing based on the image data of each rectangular template area bi defined on the non-rotated verification fingerprint image B and the detection of the area ai are as follows. , Each rectangular template area bi
The processing is sequentially performed for each of the rectangular template areas bi (steps S9 to S11). When it is determined that each area ai on the registered fingerprint image A having the maximum correlation coefficient has been detected in all the rectangular template areas bi, the matching processing unit 23 , The distribution (mutual positional relationship) of the plurality of rectangular template areas {b _i | i = 1, 2,..., N} defined in the collation fingerprint image B and the registered fingerprint image A The detected distributions (mutual positional relationships) of the plurality of regions {a _i | i = 1, 2,..., N} are compared, and the identity of the registered fingerprint A and the verification fingerprint B is evaluated (step S11). → S12).

If it is determined that the registered fingerprint A and the collated fingerprint B are the same fingerprint, the series of collation processing is terminated, and the collated fingerprint A and the collated fingerprint are displayed by the collation result display unit 28 (15). It is displayed that B is the same fingerprint (step S13 → end).

On the other hand, if it is not determined that the registered fingerprint A and the collated fingerprint B are the same fingerprint, the rotation deviation correction angle θm currently set in the rotation conversion processing unit 24 is set to θ1 = 0 according to the initial setting. ° (Step S
13 → S13a).

Here, the rotation deviation correction angle θm currently set in the rotation conversion processing section 24 is set to θ
When it is determined that 1 = 0 °, the template-arranged fingerprint data selection processing unit 29 selects the first rectangular template area A1 arranged on the registered fingerprint image A given from the maximum correlation area detection processing unit 26. Is compared with the maximum correlation coefficient value MAXCC of the first rectangular template area b1 arranged on the verification fingerprint image B with the maximum correlation coefficient value MAXcc of the registration fingerprint image A with respect to the verification fingerprint image B of the verification fingerprint image B. Step S13a → S15).

[0136] Then, the first
The maximum correlation coefficient value MAXCC of the rectangular template area A1 with the collation fingerprint image B is larger than the maximum correlation coefficient value maxcc of the first rectangular template area b1 arranged on the collation fingerprint image B with the registered fingerprint image A. If it is determined to be larger (or more), the template area Ai is defined in the registered fingerprint image A in the processing after θ2 = 1 ° in which the rotation shift correction angle θm is sequentially updated and set in the rotation conversion processing unit 24. Step S1 of arranging and collating the fingerprint image B by sequentially rotating and converting the fingerprint
The fingerprint matching process in steps S15 to S7 is performed (step S15).
→ S1 to S7).

In step S7, when it is not determined that the registered fingerprint A and the verification fingerprint B are the same fingerprint, all the rotational deviation correction angles θm (= 0 °, 1 °, -1 °, 2
°, -2 °, 3 °, -3 °, ..., k °, -k ° [m = 1
Ｋk × 2 + 1, k ≧ 1 integer]], it is determined whether or not the matching process in which the template area Ai is arranged in the non-rotated registered fingerprint image A has been performed for each of the rotated matching fingerprint images B. (Step S7 → S14)
a).

Then, with respect to the reference fingerprint image B after each rotation, which has been rotationally converted by all of the specified rotational deviation correction angles θm, a comparison process is performed in which the template area Ai is arranged in the non-rotated registered fingerprint image A. If it is determined that there is no registered fingerprint image A, the process returns to the process from step S1 again, and the template is placed on the non-rotated registered fingerprint image A of the collation fingerprint image B rotated and converted by the updated rotational deviation correction angle θm (= m + 1). The collation processing in which the area Ai is defined and arranged is repeatedly performed (step S14a → S1 to S1).
7).

If it is determined that the registered fingerprint A and the collated fingerprint B are the same fingerprint, the series of collation processing is terminated, and the collated fingerprint A and the collated fingerprint are displayed by the collation result display unit 28 (15). It is displayed that B is the same fingerprint (step S7 → end).

If it is determined that the collation processing has been performed on the non-rotated registered fingerprint image A for each rotated collation fingerprint image B, which has been rotationally converted by all the rotational deviation correction angles θm, A series of collation processing is completed, and the registered fingerprint A and collated fingerprint B are displayed on the collation result display unit 28 (15).
Is displayed as not the same fingerprint (step S14).
a → end).

On the other hand, in step S15, the first rectangular template area b arranged on the collation fingerprint image B
Maximum correlation coefficient value maxc with registered fingerprint image A for 1
If it is determined that c is larger than the maximum correlation coefficient value MAXCC of the first rectangular template area A1 arranged on the registered fingerprint image A with the collation fingerprint image B,
Rotational deviation correction angle θm in the rotation conversion processing unit 24
Are sequentially updated and set in the processing after θ2 = 1 °.
The fingerprint collation processing in steps S8a to S13 is performed in which the template area bi is defined and arranged in the collation fingerprint image B, and the registered fingerprint image A is sequentially rotated and converted to perform fingerprint collation (step S15 → S8a to S13).

In this step S13, when it is not determined that the registered fingerprint A and the verification fingerprint B are the same fingerprint, all the rotational deviation correction angles θm (= 0 °, 1 °, -1 °,
2 °, -2 °, 3 °, -3 °, ..., k °, -k [m =
1 to k × 2 + 1, integer of k ≧ 1]), it is determined whether or not the matching process in which the template area bi is arranged in the non-rotating matching fingerprint image B is performed for each of the registered fingerprint images A after rotation. (Step S13 → S
14b).

Then, for each registered fingerprint image A after the rotation, which has been rotationally converted by all the prescribed rotational deviation correction angles θm, a collation process in which the template area bi is arranged on the non-rotated collation fingerprint image B is performed. If it is determined that there is no registered fingerprint image A, the process returns to the processing from step S8a again, and the template is placed on the non-rotated verification fingerprint image B of the registered fingerprint image A that has been rotationally converted by the updated rotational deviation correction angle θm (= m + 1). The collation processing in which the region bi is defined and arranged is repeatedly performed (step S14b → S8a to S8a).
13).

When it is determined that the registered fingerprint A and the collated fingerprint B are the same fingerprint, the series of collation processing is terminated, and the registered fingerprint A and the collated fingerprint are displayed by the collation result display unit 28 (15). It is displayed that B is the same fingerprint (step S13 → end).

If it is determined that the comparison processing of the non-rotated verification fingerprint image B has been performed on the rotated registered fingerprint image A that has been rotationally converted by all the rotational deviation correction angles θm, A series of collation processing is completed, and the registered fingerprint A and collated fingerprint B are displayed on the collation result display unit 28 (15).
Is displayed as not the same fingerprint (step S14).
b → end).

Therefore, according to the fingerprint data collation apparatus of the fourth embodiment, the fingerprint collation processing for defining and arranging the template area Ai in the registered fingerprint image A and collating with the collation fingerprint image B which is sequentially rotated and converted is performed. And a fingerprint collation process in which a template region bi is defined and arranged in the collation fingerprint image B and collation is performed with a registered fingerprint image A which is sequentially rotated and converted. In the same manner as in the first to third embodiments, the fingerprint matching of the same person and the same finger having a rotational deviation is performed at a smaller rotational deviation correction angle θm as in the first to third embodiments. Not only is the possibility that a matching match can be obtained increased, but also the matching time can be greatly reduced with a smaller amount of calculation processing.

In step S15 in the fingerprint matching process of the fourth embodiment, the maximum correlation coefficient value MAXCC with the matching fingerprint image B for the first rectangular template area A1 arranged on the registered fingerprint image A, and the matching fingerprint Image B
The configuration is such that the magnitude of the maximum correlation coefficient value maxcc with the registered fingerprint image A with respect to the first rectangular template region b1 arranged above is compared and determined. Instead, a plurality of rectangles arranged on the registered fingerprint image A are determined. The maximum phase relationship between the average value of the maximum correlation coefficient value MAXCC of each of the template regions Ai and the matching fingerprint image B and the registered fingerprint image A of each of the plurality of rectangular template regions bi arranged on the matching fingerprint image B A configuration for comparing and judging the magnitude of the numerical value maxcc with the average value may be adopted.

In the fourth embodiment, when the collation fingerprint image B is rotationally converted, the template area Ai is defined and arranged on the non-rotated registered fingerprint image A, and the collation with the collation fingerprint image B after the rotation processing is performed. When the registered fingerprint image A is rotated and converted, the template bi is defined and arranged on the non-rotated collated fingerprint image B, and the collation process with the registered fingerprint image A after the rotation process is performed. As described in the fifth embodiment of the present invention, the template region b
The configuration may be such that i and Ai are defined and arranged to perform a matching process with a non-rotated registered fingerprint image A or a matching process with a non-rotated registered fingerprint image B.

(Fifth Embodiment) FIG. 17 is a block diagram showing a configuration of an operation function of the fingerprint data matching device according to a fifth embodiment of the present invention.

In the fingerprint collation operation function of the fifth embodiment, the registered fingerprint image A is rotationally converted by the rotation conversion processing unit 24 through the template arrangement fingerprint data selection processing unit 29.
When the template arrangement processing unit 25 defines and arranges the template area Ai with respect to the rotation-converted registered fingerprint image A, the template arrangement fingerprint data selection processing unit 2
9, the non-rotated verification fingerprint image B is directly supplied to the maximum correlation area detection processing unit 26, and the verification fingerprint image B is rotationally converted by the rotation conversion processing unit 24 through the template arrangement fingerprint data selection processing unit 29. When the template region bi is defined and arranged by the template arrangement processing unit 25 with respect to the collated fingerprint image B, the non-rotated registered fingerprint image A is directly transferred to the maximum correlation region detection processing unit 26 through the template arrangement fingerprint data selection processing unit 29. Give to.

Then, at the initially set rotational deviation correction angle θm (θ1 = 0 °), the registered fingerprint image A is rotationally converted, the template area Ai is defined and arranged, and calculation is performed with the non-rotated verification fingerprint image B. Maximum correlation coefficient value MAXC
C and the rotational deviation correction angle θm (θ1 =
0 °), the collation fingerprint image B is rotationally transformed and the template area bi is defined and arranged, and the maximum correlation coefficient value maxcc calculated between the non-rotated registered fingerprint image A and the maximum correlation area detection processing unit 26 Is given to the template arrangement fingerprint data selection processing unit 29 to judge the magnitude, and in the processing after θ2 = 1 ° which is the rotational deviation correction angle θm that is sequentially updated, the registered fingerprint image A is rotationally converted to the template area Ai. A fingerprint collation process performed between the collation fingerprint image B and the collation fingerprint image B which is defined and arranged, or the collation fingerprint image B
Is rotationally transformed, the template area bi is defined and arranged, and a fingerprint collation process to be performed with the non-rotated registered fingerprint image A is selected and determined.

Therefore, the fingerprint data collation device of the fifth embodiment also requires a smaller rotation deviation correction angle to perform fingerprint collation of the same person / finger having a rotational deviation, as in the fourth embodiment. Not only is it more likely that a matching match is obtained at θm, but also the matching time can be greatly reduced with a smaller amount of computation.

In the third and fifth embodiments, in the rotation conversion processing of the registered fingerprint image A or the collated fingerprint image B on the side where the template area is defined and arranged,
Although the entire fingerprint image A or B is rotationally converted, the configuration may be such that only a partial fingerprint image area to be defined and defined in the template area of the fingerprint image A or B is rotationally converted. According to this, the amount of the image to be subjected to the rotation conversion processing itself can be reduced, and the rotation conversion processing time can be shortened to further reduce the fingerprint collation processing time.

In the matching process between the registered fingerprint image A and the matching fingerprint image B in each of the above embodiments, Ai, Bi,
Although the regions bi and ai are rectangular regions, the shapes of these regions are not limited to rectangles and may be arbitrary. It is desirable that the sizes and shapes of the regions Ai, Bi, bi, and ai are the same, but even if there is a slight difference, it is acceptable as long as the required fingerprint matching accuracy is obtained.
Further, the positions where the template areas Ai and bi are defined and arranged may be arbitrary.

In the collation judgment, in addition to the method of evaluating Δi in the above-described processing, for example, Ai or b
Various methods such as determination based on a difference in shape or area between a graphic formed with i as the vertex and a graphic formed with Bi or ai as the vertex can be adopted.

It should be noted that the method described in each of the above embodiments, that is, the first method based on each operation function block diagram and each flowchart in FIGS. 3 to 5 and FIGS.
Each of the techniques such as the fingerprint collation processing in each of the fifth to fifth embodiments is implemented as a program that can be executed by a computer, such as a memory card (ROM card, RAM
Card, magnetic disk (floppy disk, hard disk, etc.), optical disk (CD-ROM, DVD
Etc.), and can be stored in an external storage medium 18a such as a semiconductor memory and distributed. Then, the computer of the fingerprint data collation apparatus reads the program stored in the external storage medium 18a into the storage device 12, and the operation is controlled by the read program, thereby performing the fingerprint collation function described in the above embodiment. And can execute the same processing according to the above-described method.

Data of a program for realizing each of the above methods can be transmitted on a network (public line) 20 in the form of a program code, and transmitted by a fingerprint data collation apparatus connected to the network 20. The above-described program data can be fetched by the control unit 19 to realize the above-described fingerprint matching function.

[0158]

As described above, according to the image data collating device according to the first aspect of the present invention, for example, when the image data B is rotated by a predetermined angle, the rotation of the image data B is performed. A template defining a plurality of regions is arranged for each image data A, and a plurality of correlation regions having the maximum correlation with each of the plurality of template regions is detected on the rotated image data B. Then, by comparing the mutual positional relationship between the plurality of regions arranged in the image data A and the mutual positional relationship between the plurality of correlation regions detected on the image data B, the identity between the image data A and the image data B is determined. Is determined. On the other hand, a template that defines a plurality of regions for the image data B is arranged for each rotation of the image data B, and a plurality of correlation regions having the maximum correlation with each of the plurality of template regions is defined as the plurality of regions. It is detected on the image data A. And
The identity of the image data A and the image data B is determined by comparing the mutual positional relationship between the plurality of regions arranged in the image data B and the mutual positional relationship between the plurality of correlation regions detected on the image data A. Is done. Thus, while the number of rotations (angle) of the image data B is small, the image data A and B
Is more likely to be matched and the matching time can be reduced.

Further, according to the image data collating device according to the sixth aspect of the present invention, when a template area is arranged in the image data A, the correlation value obtained on the image data B with respect to the template area is obtained by: When a template area is arranged in the image data B, based on a correlation value obtained on the image data A for the template area,
While rotating the image data A or the image data B, a template is arranged on the image data A to detect the correlation with the image data B and determine the collation. Is selected, a process that has a large correlation value and is easy to obtain a matching match between the image data A and B is selected. It can be shortened.

Therefore, even if the collation image has a rotational deviation, it is possible to accurately collate the registered image data with the collation image data, and to reduce the time required for the collation. Will be possible.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a configuration of an electronic circuit of a fingerprint data matching device according to an embodiment of the image data matching device of the present invention.

FIG. 2 is a diagram showing a data memory secured in a RAM of the fingerprint data collation apparatus.

FIG. 3 is a block diagram showing a configuration of an operation function accompanying execution of a fingerprint matching processing program of the first embodiment of the fingerprint data matching apparatus.

FIG. 4 is a flowchart showing a fingerprint collation process (part 1) of the first embodiment of the fingerprint data collation device;

FIG. 5 is a flowchart showing a fingerprint collation process (part 2) of the first embodiment of the fingerprint data collation device.

FIG. 6 shows a comparison between the arrangement position distribution of the template area Ai on the registered fingerprint image A and the detection position distribution of the maximum correlation area Bi on the collation fingerprint image B in the fingerprint collation processing of the fingerprint data collation apparatus. FIG.

FIG. 7 is a view showing respective position data of a template position and a maximum correlation area detection position stored in a registered fingerprint position memory and a collated fingerprint position memory in a RAM in accordance with the fingerprint collation processing of the fingerprint data collation device.

FIG. 8 shows a comparison between the arrangement position distribution of the template area bi on the collation fingerprint image B and the detection position distribution of the maximum correlation area ai on the registered fingerprint image A in the fingerprint collation processing of the fingerprint data collation apparatus. FIG.

FIG. 9 is a diagram showing position data of a template position and a maximum correlation area detection position stored in a collation fingerprint position memory and a registered fingerprint position memory in a RAM in accordance with the fingerprint collation processing of the fingerprint data collation device.

FIG. 10 is a block diagram showing a configuration of an operation function associated with execution of a fingerprint matching processing program of the second embodiment of the fingerprint data matching apparatus.

FIG. 11 is a flowchart showing a fingerprint matching process (1) of the fingerprint data matching device according to the second embodiment.

FIG. 12 is a flowchart showing a fingerprint matching process (part 2) of the fingerprint data matching device according to the second embodiment.

FIG. 13 is a block diagram showing a configuration of an operation function associated with execution of a fingerprint matching processing program of the third embodiment of the fingerprint data matching device.

FIG. 14 is a block diagram showing a configuration of an operation function according to execution of a fingerprint collation processing program of a fourth embodiment of the fingerprint data collation device.

FIG. 15 is a flowchart illustrating a fingerprint matching process (part 1) of the fingerprint data matching device according to a fourth embodiment.

FIG. 16 is a flowchart showing a fingerprint collation process (part 2) of the fourth embodiment of the fingerprint data collation device.

FIG. 17 is a block diagram showing a configuration of an operation function associated with execution of a fingerprint matching processing program according to a fifth embodiment of the fingerprint data matching device.

FIG. 18 is a flowchart showing a procedure of fingerprint data collation in the fingerprint data collation apparatus of the prior application.

FIG. 19 is a diagram showing a plurality of reference regions arranged in registered fingerprint data in accordance with the fingerprint data collation procedure of the prior application and a plurality of regions detected on the collation fingerprint data based on the reference regions.

FIG. 20 shows an example in which a plurality of reference areas arranged in registered fingerprint data and a plurality of inappropriate areas on the matching fingerprint data are detected based on the plurality of reference areas based on the fingerprint data matching procedure of the prior application. FIG.

[Explanation of symbols]

 Reference Signs List 11 ... Control unit (CPU) 12 ... Storage device 13 ... RAM 13a ... Reading image memory 13b ... Verification fingerprint image memory 13c ... Verification fingerprint rotation image memory 13d ... Registration fingerprint position memory 13e ... Verification fingerprint position memory 13f ... Rotation angle memory 14 ... Image reading device 15 ... Display unit 16 ... Input unit 17 ... Bus 18 ... Storage medium reading unit 18a ... External storage medium 19 ... Transmission control unit 20 ... Network 20a ... Program server (external computer terminal) 20b ... Storage of external terminal Apparatus 21 Fingerprint data input unit 22 Registered fingerprint data storage unit 23 Matching processing unit 24 Rotation conversion processing unit 25 Template layout processing unit 26 Maximum correlation area detection processing unit 27 Matching determination processing unit 28 Matching result display Part 29: Template layout fingerprint data selection processing Department

Claims (12)

[Claims] 1. An image data collating apparatus for collating image data A and image data B to determine the identity of the two, wherein the image rotation is performed by rotating the image data A or the image data B by a preset angle. Means, a first template arranging means for arranging a template for defining a plurality of regions in the image data A for each rotation of the image data A or B by the image rotator, and an image by the first template arranging means. First correlation area detection means for detecting, on the image data B, a plurality of correlation areas having the maximum correlation with each of the plurality of areas arranged in the data A; The mutual positional relationship between the arranged plurality of regions and the mutual positional relationship between the plurality of correlation regions detected on the image data B by the first correlation region detecting means. Compared to the image data A
A first collation judging unit for judging the identity of the image data B with the image data B, and a template for defining a plurality of regions for the image data B for each rotation of the image data A or B by the image rotating unit. And a second template arranging means.
A second correlation area detecting means for detecting, on the image data A, a plurality of correlation areas having a maximum correlation with each of the plurality of areas arranged in the image data B by the template arranging means; Means for comparing the mutual positional relationship between the plurality of regions arranged in the image data B with the mutual positional relationship between the plurality of correlation regions detected on the image data A by the second correlation region detecting means. A
And a second collation judging means for judging identity between the image data B and the image data B. 2. The image rotation unit according to claim 1, wherein the image rotation unit rotates only one of the image data A and the image data B at a predetermined angle. 2. The image data collating device according to claim 1. 3. When arranging a template defining a plurality of regions on the image data A by the first template arranging means, the image rotating means preliminarily deletes the image data B which is not the object of the template. When the template that defines a plurality of regions is arranged in the image data B by the second template arranging means by rotating the image data A by the set angle, the image data A that is not the object to be arranged of the template is set in advance. 2. The image data collating apparatus according to claim 1, wherein the image data collating means is an image rotating means for rotating the image data by an angle. 4. When arranging a template defining a plurality of regions on the image data A by the first template arranging means, the image rotating means preliminarily sets the image data A to be arranged on the template. When the template is rotated by the set angle and the second template arranging unit arranges a template defining a plurality of regions with respect to the image data B, the image data B to be arranged of the template is set in advance. 2. The image data collating apparatus according to claim 1, wherein the image data collating means is an image rotating means for rotating the image data by an angle. 5. When arranging a template defining a plurality of regions on the image data A by the first template arranging means, the image rotator includes: When the partial image area including the template arrangement target area is rotated by a preset angle, and the second template arrangement means arranges a template defining a plurality of areas with respect to the image data B, 2. The image data according to claim 1, wherein the image data is image rotation means for rotating a partial image area including the template arrangement target area in the image data B as the template arrangement target by a predetermined angle. Collation device. 6. The method according to claim 1, further comprising: arranging a template for defining a plurality of areas in the image data A by the first template arranging means, or arranging a plurality of areas in the image data B by the second template arranging means. A template arrangement image selecting means for selecting whether to arrange a template defining the correlation based on the correlation value obtained by the first correlation area detection means and the correlation value obtained by the second correlation area detection means, By means of this template arrangement selecting means, the first
When the template arranging means is selected, the image rotating means, the first template arranging means, and the first
When the second template arranging unit is selected, the image rotation unit and the second image arranging unit determine whether the image data A and the image data B have been collated and determined by the first collation determining unit. 2. The image processing apparatus according to claim 1, further comprising: a template arranging unit, the second correlation region detecting unit, and a selection control unit that determines whether or not the image data A and the image data B are to be compared by the second matching determining unit. The image data collation device according to claim 3, claim 4, or claim 5. 7. The template-arranged image selecting means, comprising: a maximum correlation coefficient value on image data B with respect to an area of a template arranged in image data A obtained by the first correlation area detecting means; 2. Correlation value comparison means for comparing and judging the maximum correlation coefficient value on the image data A with respect to the area of the template arranged in the image data B obtained by the second correlation area detection means. When it is determined that the maximum correlation coefficient value on the image data B with respect to the area of the template arranged in the image data A is larger, a plurality of areas are defined for the image data A and the template is arranged. The first template arrangement means is selected, and the maximum correlation on the image data A with respect to the area of the template arranged in the image data B 7. The method according to claim 6, wherein when it is determined that the numerical value is larger, a second template arranging unit that defines a plurality of regions for the image data B and arranges a template is selected. Image data collation device. 8. The image processing apparatus according to claim 1, wherein the template-arranged image selecting unit includes: a maximum correlation coefficient value on the image data B for each of a plurality of regions of the template arranged in the image data A obtained by the first correlation region detecting unit; And the average value of the maximum correlation coefficient values on the image data A for each of the plurality of regions of the template arranged in the image data B obtained by the second correlation region detection means. The correlation value comparing means determines that the average value of the maximum correlation coefficient values on the image data B for each of the plurality of regions of the template arranged in the image data A is larger. In this case, the first template arranging means for arranging a template by defining a plurality of areas for the image data A is selected, and When it is determined that the average value of the maximum correlation coefficient values on the image data A for each of the plurality of regions of the template arranged in B is larger, a plurality of regions are defined for the image data B. 7. The image data collating apparatus according to claim 6, wherein a second template arranging means for arranging the template is selected. 9. An image data collation method for collating image data A and image data B to determine the sameness between the two, wherein the image rotation is performed by rotating the image data A or the image data B by a preset angle. A first template arranging step of arranging a template for defining a plurality of regions in the image data A for each rotation of the image data A or B in the image rotating step; A first method for detecting, on the image data B, a plurality of correlation regions having the maximum correlation with each of the plurality of regions arranged in the data A
And a plurality of correlations detected on the image data B by the first correlation region detecting step, and a mutual positional relationship between a plurality of regions arranged in the image data A by the first template arranging step. A first collation determination step of comparing the image data A and the image data B by comparing the mutual positional relationship between the areas; and an image data B for each rotation of the image data A or B in the image rotation step. A second template arranging step of arranging a template defining a plurality of regions with respect to the plurality of regions, and a plurality of correlations having a maximum correlation with each of the plurality of regions arranged in the image data B by the second template arranging step. Second for detecting an area on image data A
And a plurality of correlations detected on the image data A by the second correlation area detecting step, and a mutual positional relationship between a plurality of areas arranged in the image data B by the second template arranging step. A second collation judging step of judging the identity between the image data A and the image data B by comparing the mutual positional relationship of the areas with each other. 10. The method according to claim 10, further comprising: arranging a template defining a plurality of regions for the image data in the first template arranging step, or arranging a plurality of regions for the image data in the second template arranging step. A template arrangement image selecting step of selecting whether to arrange a template defining the correlation based on the correlation value obtained by the first correlation area detection step and the correlation value obtained by the second correlation area detection step; When the first template placement step is selected by the template placement selection step, the image rotation step, the first template placement step,
The image data A and the image data B are collated and determined in the first correlation region detection step and the first collation determination step, and when the second template arrangement step is selected, the image rotation step is performed. A second template arrangement step, the second correlation area detection step,
The image data matching method according to claim 9, further comprising: a selection control step of determining and comparing the image data A and the image data B by the second matching determination step. 11. A computer which controls image data A
A storage medium storing an image data collation processing program for collating the image data B with the image data B, and rotating the computer by the preset angle of the image data A or the image data B. Image rotation means for rotating the image data A or B by the image rotation means, a first template arrangement means for arranging a template defining a plurality of regions with respect to the image data A, A first correlation area detecting means for detecting, on the image data B, a plurality of correlation areas having the maximum correlation with each of the plurality of areas arranged in the image data A; The mutual positional relationship between the plurality of arranged areas and the plurality of phases detected on the image data B by the first correlation area detecting means. Wherein by comparing the mutual positional relationship of the area image data A
First determining means for determining the identity of the image data B with the image data B, and a second template for defining a plurality of regions for the image data B for each rotation of the image data A or B by the image rotating means. A second correlation area detecting means for detecting, on the image data A, a plurality of correlation areas having a maximum correlation with each of the plurality of areas arranged in the image data B by the second template arranging means. The mutual positional relationship between the plurality of regions arranged in the image data B by the second template arranging unit and the mutual positional relationship between the plurality of correlation regions detected on the image data A by the second correlation region detecting unit; And comparing the image data A
Storage medium storing a computer-readable image data collation processing program functioning as second collation determination means for determining the identity of the image data B with the image data B. 12. The computer according to claim 11, further comprising: arranging a template defining a plurality of regions with respect to the image data by the first template arranging means, or arranging the computer with respect to the image data B by the second template arranging means. Template arrangement image for selecting whether to arrange a template defining a plurality of regions based on the correlation value obtained by the first correlation region detection unit and the correlation value obtained by the second correlation region detection unit Selecting means, when the first template arranging means is selected by the template arrangement selecting means, the image rotating means, the first template arranging means, the first correlation area detecting means, the first collation The image data A and the image data B are collated and determined by the determining means, and the second template arranging means is selected. If the image data A and the image data B are collated and determined by the image rotation unit, the second template arranging unit, the second correlation region detecting unit, and the second collation determining unit, 12. A storage medium storing the computer-readable image data collation processing program according to claim 11, wherein the computer program causes the computer to function as: