JP2003216952A - Image data collation method, image data collation device, and program - Google Patents

Abstract

(57) [Summary] [PROBLEMS] To suppress a decrease in matching accuracy that occurs when matching image data representing an image that is not necessarily a good target for matching. A maximum correlation area detection unit (43) determines an area having the maximum correlation with a first area whose arrangement is defined on a registered fingerprint image in a registered fingerprint image data storage unit (20). From the collation fingerprint image. Based on the positional relationship of the maximum correlation area on the collation fingerprint image, the template arrangement management unit 41 assigns a second location on the registered fingerprint image where the overlap with the first area is smaller than that according to the first definition. The regions are rearranged, and the maximum correlation region detection unit 43 detects, from the second image, a region having the maximum correlation with the redefined second region. The collation determination processing unit 44 determines the degree of similarity between the two images based on the difference between the positional relationship between the first region and the redefined second region and the positional relationship between the maximum correlation regions. I do.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a technique for collating image data, and more particularly to a technique that enables collation of image data representing an image that is not necessarily a good target for collation.

[0002]

2. Description of the Related Art In order to collate image data representing an image that is not necessarily a good target for collation,
The following techniques have been proposed. this is,
The image data of an image showing a human fingerprint as shown in FIG. 7 is collated, and image data of a fingerprint registered in advance (hereinafter referred to as “registered fingerprint image data”) and its The collation with the image data of the fingerprint (hereinafter referred to as “collated fingerprint image data”) to be collated with the data is performed according to the procedure from the following. Registered fingerprint image A represented by registered fingerprint image data
(I + 1) areas are defined and arranged therein. One of these areas will be referred to as a main template A ₀ , and the other area will be referred to as a sub template A _i . Collation fingerprint image B represented by the collation fingerprint image data
While scanning the area of the same shape and size as A ₀ above,
A correlation coefficient indicating the degree of correlation between the pixel data included in the area and the pixel data in A ₀ is calculated, and the area having the highest correlation is detected to detect the area B ₀ . To do. Repositioning of each A _i is performed based on the position of the region B ₀ on B, and the positional relationship between A ₀ and A _i is changed. While scanning an area having the same shape and size as A _i in B, a correlation coefficient is calculated for each A _i between the pixel data included in the area and the pixel data in A _i , and for each A _i A region whose value has the highest correlation is detected and set as a region B _i . The positional relationship between A ₀ and A _i in A is compared with the positional relationship between B ₀ and B _{i in} B, and the identity between A and B is evaluated based on the comparison result.

In the above procedure,
Further description will be given with reference to FIG. The registered fingerprint image A shown in FIG. 8A shows a fingerprint image as shown in FIG. 7, and i = 4, that is, one main template and four sub-templates in the process of An example of a state in which a total of five areas are arranged in this registered fingerprint image A according to the definition is shown.

Further, FIG. 8B shows an example in which B ₀ detected by the processing is arranged on the collation fingerprint image B in which the fingerprint image shown in FIG. 7 is represented,
In this example, the area B ₀ detected within the scanning range has the width WIDTH and the height HEIGHT, and is the collation fingerprint image B.
Shows a state outside the range of the effective area Ex, y defined in advance. In such a state, the rearrangement of sub-templates, which is a process, is performed.

As shown in FIG. 8B, the rearrangement of the sub-template A _i is performed by the amount of deviation from the effective area Ex, y in the arrangement of the area B ₀ (dx in the X-axis direction, Y-axis). Based on dy) in the direction, each A _i is moved in parallel in the direction opposite to the amount of the shift, on the registered fingerprint image A, and arranged as shown in FIG. 8C. As a result, even if the fingerprint image is acquired with a deviation from the center of the collated fingerprint image B, the fingerprint image can be collated while maintaining the desired collation accuracy.

[0006]

In the rearrangement process in the above-mentioned conventional fingerprint image data collating method, the sub-templates are moved in parallel in the same direction. As shown, some sub-templates may overlap with the main template. In particular, if the positional relationship between the sub-templates A _i is defined as being arranged adjacent to the main template A _{i as} shown in FIG. 8A, the sub-template A _i overlaps with the main template A _0. There is a high possibility that it will happen.

When the sub-template A _i and the main template A ₀ overlap, the areas B _i and B ₀ having the highest correlation with them naturally tend to overlap. In the processing of 1., the registered fingerprint image and the matching fingerprint image are identified based on the positional relationship between A ₀ and A _i in the registered fingerprint image and the positional relationship between B ₀ and B _i in the matching fingerprint image. Therefore, when such areas overlap, the false acceptance rate monotonically deteriorates as the amount of overlap increases, that is, it is displayed on both the registered fingerprint image and the collation fingerprint image. Even if the fingerprints that are present are not of the same person, the fingerprints of these two will increase the probability of being mistaken for being the same.

In view of the above problems, it is a problem to be solved by the present invention to suppress a decrease in collation accuracy that occurs when collating image data representing an image that is not necessarily a target for collation. is there.

[0009]

According to the present invention, image data representing a first image and image data representing a second image are collated to determine the degree of similarity between the two images. The image data collating method, the image data collating apparatus, and the program for causing a computer to perform the image data collating process are premised.

In the image data collating method according to one aspect of the present invention, a definition of the arrangement of the first area and a predetermined positional relationship with the first area are provided on the first image. The definition of the arrangement of the second region having, from the second image, to detect the first maximum correlation region is a region having the maximum correlation with the first region, the first maximum correlation region Based on the positional relationship on the second image, between the position on the first image and the second region where the overlap with the first region is arranged according to the definition. Redefinition is performed by arranging the second area at the position that is less than the overlap that occurs, and a second maximum correlation area that is an area having the maximum correlation with the second area whose arrangement is redefined is defined. Detected from the second image,
Difference between the positional relationship between the first area and the second area whose arrangement has been redefined, and the positional relationship between the first maximum correlation area and the second maximum correlation area. The above-mentioned problem is solved by determining the degree of similarity based on the above.

Here, the first image and the second image are images representing, for example, a fingerprint. According to the above method, by redefining the placement of the second area,
The amount of overlap between the regions that occurs between the arrangement of the first area and the arrangement of the second area after the redefinition is determined by the arrangement of the first area and the arrangement of the second area according to the first definition. Since the amount of overlap between the areas generated between and is smaller than that of the other area, deterioration of the false acceptance rate is reduced, and as a result, deterioration of matching accuracy is suppressed.

In the image data collating method according to the present invention described above, in the redefinition, the second area is arranged at a position on the first image that does not overlap with the first area. You can also do it. By doing so, the false acceptance rate due to the overlap between the first area and the second area does not occur at all.

Further, in the above-mentioned image data collating method according to the present invention, there are a plurality of the second areas, and among the second areas arranged according to the definition, between the second area and the first area. It is also possible to redefine the above-mentioned arrangement for those in which overlapping occurs.

Among the plurality of second areas, the one having no overlap with the first area due to the first definition does not cause the deterioration of the acceptance rate of others, and thus the redefinition is carried out. The processing load is reduced by the reduction in the number of regions for performing the verification, and the processing for matching is speeded up.

According to another aspect of the present invention, there is provided an image data collating apparatus, wherein a definition of the arrangement of a first area and a predetermined position between the first area and the first area are provided on the first image. An arrangement defining means for defining an arrangement of a second area having a relationship, and a first maximum correlation area which is an area having a maximum correlation with the first area from the second image, Based on the positional relationship between the one detection means and the first maximum correlation area on the second image, the position on the first image and the overlap with the first area are arranged according to the definition. Redefinition means for redefining the second area at the position where there is less overlap with the second area, and the second area with redefinition of the arrangement. The second maximum phase, which is the region where the correlation with A second detecting means for detecting a region from the second image, a positional relationship between the first region and the second region in which the layout is redefined, and the first maximum correlation region. The above-mentioned problem can be solved by configuring the determination means for determining the degree of similarity based on the difference between the second maximum correlation area and the positional relationship between the second maximum correlation area and the second maximum correlation area.

According to this structure, the same operation and effect as those of the image data collating method according to the present invention described above can be obtained. Further, even in the case of a program for causing a computer to perform the process corresponding to the above-described image data matching method according to the present invention, by causing the computer to read and execute the program, the image data according to the present invention described above. The same action and effect as the collation method can be obtained, and the above-mentioned problems can be solved.

[0017]

BEST MODE FOR CARRYING OUT THE INVENTION Embodiments of the present invention will be described below with reference to the drawings. Here, an embodiment in which the present invention is used for collation of fingerprint image data will be described. FIG. 1 is a diagram showing the configuration of a fingerprint image data collation device (hereinafter referred to as “this device”) for carrying out the present invention.

The fingerprint image data input unit 10 acquires fingerprint image data, and is composed of, for example, an image scanner or an image sensor such as a CCD (Charge Coupled Device). Fingerprint image data input unit 10
The fingerprint image represented by the fingerprint image data acquired in step 7 is the image illustrated in FIG. 7. Although the fingerprint image shown in the figure is binarized, the fingerprint image data may represent a multi-gradation fingerprint image.

The fingerprint image data acquired by the fingerprint image data input unit 10 is registered and stored in the registered fingerprint image data storage unit 20. This registered fingerprint image data storage unit 20
The fingerprint image data stored in is treated as the registered fingerprint image data described above. Collation fingerprint image data storage unit 3
In 0, the fingerprint image data of the subject, which is acquired by the fingerprint image data input unit 10 and whose fingerprint is collated by this apparatus, that is, the collated fingerprint image data described above is temporarily stored.

The fingerprint collation processing unit 40 performs a process of collating the registered fingerprint image data stored in the registered fingerprint image data storage unit 20 with the collated fingerprint image data stored in the collated fingerprint image data storage unit 30. Be done. The fingerprint collation processing unit 40 includes a rotation conversion unit 42 and a template placement management unit 4
1, a maximum correlation detection unit 43, and a collation determination processing unit 44.

The rotation conversion unit 42 rotates the registered fingerprint image represented by the registered fingerprint image data input to the fingerprint collation processing unit 40 according to a predetermined instruction. The template arrangement management unit 41 arranges a plurality of regions having a predetermined size at predetermined positions in the registered fingerprint image after the processing by the rotation conversion unit 42. These areas arranged by the template arrangement management unit 41 are referred to as "templates".

The maximum correlation area detection unit 43 is registered by the template arrangement management unit 41 among the areas of a predetermined size in the collation fingerprint image represented by the collation fingerprint image data input to the fingerprint collation processing unit 40. The position of the template having the highest correlation with each template arranged in the fingerprint image is detected. Based on the position on the collation fingerprint image of the area detected by the maximum correlation area detecting unit 43, the template arrangement management unit 41 described above re-arranges the template in the registered fingerprint image once arranged.

The matching determination processing section 44 compares the distribution of the plurality of areas arranged in the registered fingerprint image by the template arrangement management section 41 with the distribution of the plurality of areas detected by the maximum correlation area detecting section 43. The identity of the registered fingerprint image and the collation fingerprint image is determined based on the comparison result.

In the collation result display section 50, the fingerprint collation processing section 4
The result of the collation processing performed by the collation determination processing unit 44 of 0 is displayed. This device is configured as described above. Note that the present apparatus includes a computer having a standard configuration, that is, a CPU that controls each component by executing a control program, a ROM, a RAM, and a magnetic storage device, and the CPU controls each component. A storage unit that is used as a storage area for a control program or a work area when the CPU executes the control program or a storage area for various data, an input unit that acquires various data corresponding to a user operation, a display, etc. An image scanner, an image sensor, etc. as the fingerprint image data input unit 10 in a computer including an output unit that presents various data to the user to notify the user and an I / F unit that provides an interface function for connecting to a network. Can also be configured by connecting.

Next, the fingerprint collation processing performed by this apparatus will be described. This fingerprint collation process is a process performed by the fingerprint collation processing unit 40 in FIG. 1, and the collation fingerprint image data acquired by the fingerprint image data input unit 10 and the registration fingerprint image data storage unit 20 previously stored. This is a process of making a collation determination with fingerprint image data.

The contents of the fingerprint collation process will be described below with reference to the flow chart shown in FIG. First, S1
In 01, the registered fingerprint image data is stored in the registered fingerprint image data storage unit 20
The collation fingerprint image data is read respectively. The fingerprint collation performed by this apparatus is premised on so-called one-to-one authentication, and the registered fingerprint image data that is collated with the collated fingerprint image data before execution of this fingerprint collation processing is, for example, It is assumed that it is uniquely specified in advance by the recognition code and password entered by the subject.

In S102, the rotation conversion unit 42 performs a process of substituting the initial value "-θmMAX" into the parameter θm for setting the image shift correction angle. here,
The image misalignment correction angle prevents misjudgment that the verification fingerprint image and the registered fingerprint image are not the same due to the misalignment in the rotational direction that may occur between the subjects of the same person. In order to do so, it refers to the rotation angle in the rotation conversion performed on the registered fingerprint image before the collation determination. As this image shift correction angle, θm>
When set to 0, clockwise rotation conversion is performed, and when set to θm <0, counterclockwise rotation conversion is performed. In this embodiment, the range of θm is −θm
MAX ≦ θm ≦ + θmMAX.

In step S103, the registered fingerprint image data read by the processing in step S101 is rotationally converted by the rotation conversion unit 41 by the angle θm. In S104, the template arrangement management unit 41 arranges the reference rectangular area mt at the position of the coordinates (x ₀ , y ₀ ) on the registered fingerprint image represented by the registered fingerprint image data. This area m
t is also called a main template. As the coordinates indicating the position of the rectangular area in the fingerprint image, the coordinates of the pixel of the fingerprint image located at the center of the rectangular area are used.

In step S105, the template placement management unit 41 places a plurality of sub-rectangular regions st _{i at} the position of coordinates (x _i , y _i ) on the registered fingerprint image represented by the registered fingerprint image data. This area st _i is also called a sub-template. Above S104 and S105
Figure 3 shows how each template is placed by the process
It is shown in (a). The registered fingerprint image A shown in the figure shows a fingerprint image as illustrated in FIG. 7, and the main template mt and the sub-template st _i (where i = 1 to 4) are arranged in the registered fingerprint image A. It is shown that it is done.

In step S106, the maximum correlation area detection unit 43 causes the area having the same shape and area as the main template mt, and the image represented in the area and the main template mt after the rotation conversion in the previous step.
The region MT having the maximum correlation coefficient with the image shown in is detected from the collation fingerprint image, and in the subsequent S107, the coordinates (X ₀ , Y ₀ ) indicating the position of the region MT in the collation fingerprint image. Is obtained.

In the detection processing of S106 described above, the area M
In order to detect T, a process of calculating the correlation coefficient between the area on the matching fingerprint image and the main template mt on the registered fingerprint image is performed. Therefore, the calculation of this correlation coefficient will be described. Note that here, the rectangular area A and the rectangular area B
The calculation of the correlation coefficient between and will be described.

First, the pixels contained in each of the rectangular area A and the rectangular area B are 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. Further, signal intensities, which are multi-gradation values indicating light and shade for these pixels, are defined as X _ij and Y _mn , respectively.

When these signal intensities are generalized and expressed as Z _pq , the following equation is defined.

[0034]

[Equation 1]

In the above equation, N represents the total number of pixels included in the rectangular area. Further, in the above equation, Σ indicates that it is the sum total of all the pixels included in the rectangular area. That is, the above equation represents the average value of the signal intensities of the pixels included in the rectangular area.

Next, the following equation will be further defined.

[0037]

[Equation 2]

The above equation represents the root 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 using the definition of the above equation.

[0039]

[Equation 3]

The correlation coefficient between both regions is calculated using the above equation. In the calculation of the correlation coefficient according to the above equation, instead of using the signal intensities of all the pixels in the rectangular area, for example, only the pixels lined up in an arbitrary line in the rectangular area are used. Calculation, using only pixels included in a part of the rectangular area, or using only pixels selected by arbitrarily thinning out the rectangular area There is no problem if the collation accuracy of the fingerprint collation can be obtained. The use of such a calculation method is advantageous because the number of pixels for which the correlation coefficient is calculated is reduced and the calculation amount is reduced. Further, another method of calculating the correlation coefficient may be adopted.

Returning to the explanation of FIG. In S108, it is determined whether or not the position (X ₀ , Y ₀ ) of the area MT obtained in the previous step on the collation fingerprint image is included in the effective area Ex, y defined in advance on the collation fingerprint image. The template placement management unit 41 makes a determination, and the determination result is N
o, that is, the coordinate indicating the position of the area MT is the effective area Ex,
Only when the sub-template st _i is not included in y, the rearrangement process on the registered fingerprint image of the sub-template st _i is performed.

The process of S108 will be described with reference to FIG. In this description, the position before the rearrangement of the main template mt in the registered fingerprint image is (x ₀ , y ₀ ), each sub template st _i (i = 1 to 1).
The position before rearrangement in 4) is assumed to be (x _i , y _i ).
Further, it is assumed that the positional relationship between each sub template st _i and the main template mt is defined as shown in FIG. 3A, and there is no overlapping portion between the respective areas.

In order to simplify the explanation, here,
It is assumed that θm = 0 °. It is detected by the detection process of S106.
The position of the projected area MT is shown in FIG. 3 (b).
If it is detected outside the effective area Ex, y,
Each sub-template detected by the process
st_iHas the same shape and area, and the highest correlation
Area ST_iThe true position of
Area ST _iIs supposed to fall outside the search area of
Be done. Therefore, in such a case by the processing of S108
When it is determined that the
To st_iRearrangement on the registered fingerprint image A, for example
The rearrangement with the arrangement shown in FIG. 3C is performed in S109.
Do it by reason. By doing this, the area ST_iof
The true position exists within the search area in the collation fingerprint image B.
As a result, fingerprint matching can be performed accurately.

In this embodiment, it is assumed that the effective area Ex, y shown in FIG. 3B is defined as follows.

[0045]

[Equation 4]

Here, W _i and H _i are regions ST, respectively.
_i shows the width and height of _i , WIDTH and HEIG
HT indicates the width and height of the collation fingerprint image B. Figure 2
Sub-template st, which is the processing of S109 in
The details of the process of rearranging _i are shown in the flowchart of FIG. Next, this processing will be described.

In this embodiment, the area MT is the collation fingerprint.
If it is outside the effective area Ex, y in image B,
Coordinates indicating the position of the area MT on the collation fingerprint image
(X₀, Y ₀), The sub template st_iof
The coordinate values that specify the placement position can be converted according to the following formula.
By each sub template st_iRelocate
U

[0048]

[Equation 5]

In the above equations, W_iAnd H_i
Is each sub-template st _iShows the width and height of
And rearranged sub templates st_iPlace of
The coordinates indicating the position are (xr_i, Yr_i). above
Of the expressions, (a), (c), (d), and (f)
Sub-template st rearranged based on_iClimbing
FIG. 5 shows the arrangement on the recorded fingerprint image. The same figure
By reference, the sub-templates s
t_iRelocation does not overlap with the main template mt
It is easy to understand that
The increase in false acceptance rate that can occur with the method of the conventional technology is actually
It can be seen that this does not occur in the embodiment.

According to the processing shown in the flow chart of FIG. 4, the rearrangement is performed by the above-mentioned method. That is, when the result of the determination process as to whether X ₀ <α _x in S201 is Yes, the rearrangement is performed according to the above equation (a) in S202. On the other hand, S201
If the result of the determination process of No is, that is, if X ₀ ≧ α _x , the result of the determination process of whether X ₀ <β _x in S203 is Yes, the above formula (c) is used in S204. Further, when the result of the determination processing in S203 is No, that is, when X ₀ ≧ β _x , the rearrangement is performed by the above equation (b) in S205.

If the result of the determination process as to whether Y ₀ <α _y in S206 is Yes, S207
In, the rearrangement is performed according to the above equation (d).
On the other hand, when the result of the determination processing in S206 is No, that is, when Y ₀ ≧ α _y , Y ₀ <β _y in S208
If the result of the determination process of whether or not is Yes, S2
The rearrangement according to the above equation (f) at 09 also
When the result of the determination process in S208 is No, that is, when Y ₀ ≧ β _y , the above (e) is executed in S210.
Rearrangement is performed according to the formula.

The processing in S109 of FIG. 2 is as described above.
Will be done. In addition, the service shown in FIG.
Template_iThe rearrangement of is X₀≧ β_xAnd
Tsu Y ₀<Α_y(C) in the above formula and
Show the case where the rearrangement based on both equations in (d) is performed.
Cage, st₃About 3 sub-templates except
It shows how the location has been changed.

Continuing with the description of FIG. 2, in S110, the maximum correlation area detecting unit 43 causes the sub-template st _i
Which has the same shape and the same area, and the correlation coefficient between the image represented in the region and the image represented in the sub-template st _i after the rotation conversion in the previous step is the maximum. The area ST _i is detected from the collation fingerprint image. Here, the calculation of the correlation coefficient performed in the process of S110 may be performed by a method similar to that performed in the process of S106 described above, for example.

At S111, all possible values of i are
Area ST by the processing of S110 _iDetection of
Whether or not the maximum correlation is detected by the maximum correlation detector 43.
Only when the determination result is No, the process returns to S110,
Undetected area ST_iIs detected.

In S112, the collation determination process is performed by comparing the positional relationship between the main template mt and the sub template st _i on the registered fingerprint image with the positional relationship between the area MT and the area ST _i on the collated fingerprint image. The processing is performed by the unit 44, and the identity of the registered fingerprint image and the collation fingerprint image is determined in S113.

The sameness between the registered fingerprint image and the collation fingerprint image
The determination is performed as follows, for example. First,
In-template mt (x₀, Y₀) And subtemplate
To st_i(X _i, Y_i) And the area MT
(X₀, Y₀) And area ST_i(X_i, Y_i) Relative distance
The difference Δi from the separation is calculated based on the following formula for all i.
Put out.

[0057]

[Equation 6]

It is determined whether or not all the Δi calculated in this way fall within a predetermined value. Here, if all Δi are within the predetermined value, the collation determination is OK, that is, it is determined that the fingerprints represented by both data are the same, while if not, the collation determination NG, That is, it is determined that the fingerprints represented by both data are not the same. The predetermined value used here is, for example, a value at which Δi is actually calculated from fingerprint image data obtained from a plurality of people and a desired matching accuracy is obtained based on the distribution of the calculation results.

Instead of the method described above, for example, m
A figure formed with t and st _i as vertices and MT and S
It is also possible to employ various image collation determination methods such as determination based on a difference in shape or area with a figure formed with T _i as a vertex. In step S114, the collation fingerprint determination unit 4 determines whether or not the result of the determination as to the identity between the registered fingerprint image and the collation fingerprint image performed as described above is OK, that is, the determination result that both are the same is obtained.
If the result of the determination is Yes, that is, the collation is OK, the fingerprint collation processing shown in FIG. 2 is completed, and the fingerprint collation processing unit 40 causes the collation result display unit 50 to display the collation OK.

On the other hand, if the determination result of S114 is No, S
The process proceeds to 115, and the rotation conversion unit 42 increases the current value of the parameter θm described above by 1 °. The amount of increase in this angle may be set arbitrarily, but it should be noted that the smaller the value, the finer the correction of the image shift, but the greater the amount of processing of the entire fingerprint matching process. Is.

In S116, the rotation conversion unit 42 determines whether or not the current value of the parameter θm is equal to or less than the above-described value + θmMAX. If the determination result is Yes, the process returns to S103 and the above-described process is performed. Repeated. On the other hand, if the determination result in S116 is No, the fingerprint collation processing shown in FIG. 2 ends, and the fingerprint collation processing unit 40 causes the collation result display unit 50 to display the collation NG.

The above-described processing is the fingerprint collation processing, and the fingerprint collation processing unit 40 performs this processing to collate the fingerprint image data by this apparatus.
In the above-described embodiment, the main template mt and the sub-template st _i arranged on the registered fingerprint image are rectangular areas, but the shapes of these templates may be arbitrary. Also, the main template mt
Although the areas of the sub-templates st _i are all the same, they may have different sizes.

Further, in the above-described embodiment, regarding the initial arrangement of the main template mt and each sub-template st _i , each vertex of the main template mt is in contact with each sub-template st _i as shown in FIG. 3A. However, the initial placement may be a state in which the two templates are separated from each other. Moreover, even if the initial arrangement of these templates is overlapped, the overlapping size of each area on the collation fingerprint image having the largest correlation with the relocated template is larger than the overlapping size. By rearranging each template so as to be small, it is possible to reduce the degradation of the false acceptance rate that may occur in the method of the related art.

In order to configure the fingerprint collation processing performed by the fingerprint collation processing unit 40 in the present apparatus described above using the computer having the standard configuration as described above, the above-described FIG. This can be realized by creating a control program for causing a computer to perform the fingerprint matching process shown in FIG. 4, and causing the computer to read and execute the control program.

The present invention can also be implemented by a computer by recording such a control program on a computer-readable recording medium and causing the computer to read the program from the recording medium and execute the program. . FIG. 6 shows an example of a recording medium in which the recorded control program can be read by a computer. As shown in the figure, as the recording medium, for example, a storage device 62 such as a ROM or a hard disk device provided as an internal or external accessory device in the computer 61, or a flexible disk, MO (magneto-optical disk), CD- A portable recording medium 63 such as a ROM or a DVD-ROM can be used. Further, the recording medium may be a storage device 66 that is connected to the computer 61 via the network 64 and that is included in the computer that functions as the program server 65. In this case, the transmission signal obtained by modulating the carrier wave with the data signal expressing the control program is transmitted from the program server 65 through the network 64 which is the transmission medium, and the computer 61 demodulates the received transmission signal. The control program can be executed by playing back the control program.

In addition, the present invention is not limited to the above-described embodiment, and various improvements and changes can be made.

[0067]

As described in detail above, the present invention is
First, the first maximum correlation region having the maximum correlation with the first region whose arrangement is defined on the first image is detected from the second image. Then, based on the positional relationship of the first maximum correlation region on the second image, the overlap with the first region is less than the overlap that occurs with the second region arranged according to the first definition. The second area is arranged at the position on the first screen and redefined, and the second maximum correlation area with the maximum correlation with the redefined second area is detected from the second image. . After that, based on the difference between the positional relationship between the first area and the second area whose arrangement has been redefined, and the positional relationship between the first maximum correlation area and the second maximum correlation area. To determine the degree of similarity.

By doing so, it is possible to prevent the collation accuracy from deteriorating when collating image data representing an image which is not necessarily good as a collation target.

[Brief description of drawings]

FIG. 1 is a diagram showing a configuration of a fingerprint image data collation device for implementing the present invention.

FIG. 2 is a flowchart showing the processing contents of fingerprint collation processing.

FIG. 3 is a diagram for explaining how templates are rearranged by fingerprint matching processing.

FIG. 4 is a flowchart showing the processing contents of rearrangement processing of a sub rectangular area st _i .

FIG. 5 is a diagram showing an example of rearrangement of sub-templates.

FIG. 6 is a diagram showing an example of a recording medium that allows a computer to read a recorded program.

FIG. 7 is a diagram showing an example of a fingerprint image represented by fingerprint image data.

FIG. 8 is a diagram illustrating a conventional fingerprint image data matching method.

[Explanation of symbols]

10 Fingerprint image data input section 20 Registered fingerprint image data storage 30 Collation fingerprint image data storage unit 40 Fingerprint matching processing unit 41 Template placement management section 42 rotation converter 43 Maximum Correlation Area Detection Unit 44 Collation determination processing unit 50 Verification result display 61 Computer 62, 66 storage device 63 Portable recording medium 64 network 65 Program server

Claims (6)

[Claims] 1. An image data collation method for collating image data representing a first image with image data representing a second image to determine the degree of similarity between the two images. The definition of the arrangement of the first area on the first image, and the definition of the arrangement of the second area having a predetermined positional relationship with the first area, the second From the image, to detect the first maximum correlation region is a region where the correlation with the first region is the maximum, based on the positional relationship on the second image about the first maximum correlation region, the first Arranging the second region at a position on one image where the overlap with the first region is less than the overlap with the second region arranged according to the definition Redefinition of The second maximum correlation area, which is the area having the maximum correlation with the area, is detected from the second image, and the position between the first area and the second area in which the arrangement is redefined The image data matching method, wherein the degree of similarity is determined based on a relationship and a positional relationship between the first maximum correlation region and the second maximum correlation region. 2. The first image and the second image are
An image representing a fingerprint, wherein the image is a fingerprint.
The image data matching method described in. 3. The redefinition comprises arranging the second region at a position on the first image that does not overlap with the first region. Image data matching method. 4. The redefinition of the arrangement is performed for a plurality of the second areas, of the second areas arranged according to the definition, which overlap with the first area. The image data matching method according to claim 1, wherein the image data matching method is performed. 5. An image data collating apparatus for collating image data representing a first image with image data representing a second image to determine the degree of similarity between the two images. An arrangement defining means for defining the arrangement of the first area on the first image and the arrangement of the second area having a predetermined positional relationship with the first area. From the second image, a first detection means for detecting a first maximum correlation region, which is a region having the maximum correlation with the first region, and the second image about the first maximum correlation region Based on the positional relationship above, the overlap with the first area at the position on the first image is less than the overlap with the second area arranged according to the definition. A layout that redefines the location of the second area Position redefinition means, second detection means for detecting from the second image a second maximum correlation region, which is a region where the correlation between the redefinition of the placement and the second region is maximum, Based on the difference between the positional relationship between the one area and the second area whose arrangement has been redefined, and the positional relationship between the first maximum correlation area and the second maximum correlation area. Image data collating apparatus, characterized by: 6. A computer is provided with image data collation processing for collating image data representing a first image with image data representing a second image to determine the degree of similarity between the two images. A program for executing the definition of the arrangement of the first area on the first image, and the arrangement of the second area having a predetermined positional relationship with the first area. And a process of detecting a first maximum correlation region, which is a region in which the correlation with the first region is maximum, from the second image, and the first about the first maximum correlation region. On the basis of the positional relationship on the two images, a position on the first image and an overlap with the first region is more than an overlap that occurs between the second region arranged according to the definition. The second area at the position becoming less A process of performing redefinition of arranging, and a process of detecting a second maximum correlation region, which is a region having the maximum correlation with the second region in which the redefinition of arrangement is performed, from the second image, In the positional relationship between the first area and the second area whose arrangement is redefined, and the positional relationship between the first maximum correlation area and the second maximum correlation area. A program for causing a computer to perform a process of determining the degree of similarity based on the above.