JP2002334332A - Device and method for image collation, program and recording medium - Google Patents

Abstract

PROBLEM TO BE SOLVED: To improve collation precision. SOLUTION: An image processing means 10 outputs 1st images before and after contraction processing in order. A converting means 20 repeatedly perform at least one of a translation process and a rotating process for a 2nd image by a fixed quantity. A collating means 30 compares the 1st images before and after the contraction processing with the 2nd image to find consistency 403. An arithmetic means 40 finds a mean consistency 404 as the mean value of consistency 403. A maximum consistency extracting means 50 finds the maximum consistency 405 among mean consistency 404. A decision means 60 decides that the 1st images and 2nd image are identical when the maximum consistency 405 is larger than a threshold.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

The present invention evaluates the degree of similarity between a pre-registered image and a newly input image in an image having periodicity such as a fingerprint, a nose print, an iris, and a texture pattern. The present invention relates to an image matching device, an image matching method, a program, and a recording medium for determining whether a newly input image is the same as a previously registered image.

[0002]

2. Description of the Related Art Conventionally, various image collating apparatuses have been known. For example, the document “Kobayashi,“ Fingerprint Matching Using Thinned Image Pattern Matching ”, IEICE Transactions (D-II), vo1.J79-D-II, no.3, pp.330-340, March1996.
In the fingerprint matching device as an example of the image matching device described in “1”, the images themselves are subjected to pattern matching to determine whether the two images are the same fingerprint image or different fingerprint images. FIG. 17 is a block diagram showing the configuration of a fingerprint matching device using such pattern matching. This fingerprint matching device includes an image input device 109, an image database 209, and a processing device 309.

[0003] The image input device 109 detects unevenness of a fingerprint of a finger placed on a sensor of the image input device 109 by a sensor, and performs analog / digital conversion and 2 conversion on a signal output from the sensor.
Perform image processing such as binarization. The output of the image input device 109 is a binary image in which the convex portion of the fingerprint is represented by a pixel having black luminance (black pixel), and the concave portion of the fingerprint is represented by a pixel having white luminance (white pixel). The convex portion of the fingerprint may be a white pixel, and the concave portion of the fingerprint may be a black pixel. Here, the image output by the image input device 109 is called an inspection image.

The image database 209 stores fingerprint images acquired in advance as registration data. Here, the image stored in the image database 209 is called a registered image. The processing device 309 compares the inspection image output from the image input device 109 with the registered image output from the image database 209, and determines whether the two images are the same fingerprint image or different fingerprint images. Is determined. In order to improve the determination accuracy (collation accuracy), the processing device 309 includes a conversion unit 29, a collation unit 39, a maximum matching rate extraction unit 59, and a determination unit 69.

[0005] The conversion means 29 outputs a registered image in which each pixel of the input registered image is translated and rotated by a fixed amount of change. The matching unit 39 compares the luminance value of each pixel at the same position between the registered image output from the conversion unit 29 and the inspection image output from the image input device 109, and determines the number of pixels having the same luminance value. The similarity (matching rate) between the inspection image and the registered image is calculated from the total number of matching pixels and the total number of black pixels of the registered image, which are totaled in a preset collation area. Further, the matching unit 39 converts the conversion unit 29 until the parallel movement amount is out of the preset range.
In order to repeat the translation and rotation by the translation and the comparison and collation by itself, the translation means 29
18 is output.

[0006] The maximum matching rate extracting means 59 includes a matching means 39.
Is the maximum value (maximum match rate) from the match rates 419 output by
420 is obtained and output. The judging means 69 compares the maximum matching rate 420 with a preset threshold value,
If the maximum matching rate 419 is equal to or larger than the threshold value, it is determined that the fingerprint images are the same, and if the maximum matching rate 419 is smaller than the threshold value, it is determined that the fingerprint images are different.

FIG. 18 is a flowchart showing the collating operation of the fingerprint collating apparatus shown in FIG. First, the image input device 1
09 detects the fingerprint of the finger placed on the sensor and generates an inspection image (step S51). Processing unit 309
When the inspection image is input from the image input device 109 (Step S52) and the registered image is input from the image database 209 (Step S53), the registered image is translated and rotated by the conversion unit 29 (Step S53).
54), comparing the registered image output from the conversion means 29 with the inspection image output from the image input device 109;
To obtain a match rate 419 (step S5).
5).

[0008] Then, the processing unit 309 determines the coincidence rate 419
The maximum match rate 420 is obtained from the maximum match rate 420 by the maximum match rate extracting means 59 (steps S56 and S57). Processing unit 3
In step 09, the parallel movement and the comparison and collation are repeated until the amount of parallel movement is out of the preset range (NO in step S58). Finally, the determination means 69 of the processing device 309 determines that the fingerprint image is the same when the maximum coincidence rate 420 is equal to or higher than the threshold value (YES in step S59), and when the maximum coincidence rate 420 is smaller than the threshold value. Is determined to be a different fingerprint image. Note that the processing of the conversion unit 29 may be performed on an inspection image instead of on a registered image.

[0009]

FIG. 19 shows a state where the registered image and the inspection image are compared and collated by the fingerprint collating apparatus shown in FIG. In the conventional fingerprint collation device, the ratio of the number of black pixels to the total number of pixels of the inspection image needs to be constant in order to obtain the maximum matching rate used as a determination index from the number of matching pixels. For example, the ratio of the number of black pixels to the total number of pixels is 5
When set to 0%, the maximum matching rate in matching (identification) between fingerprint images acquired from the same finger is ideally 1
00%, but actually decreased due to misalignment etc.
Below 00%. On the other hand, the maximum matching rate in the collation (collation of others) between fingerprint images obtained from different fingers is ideally a value of about 50%.

However, in the conventional fingerprint collation device,
If the pixels are at the same position and have the same luminance, they are evaluated as coincident pixels regardless of whether the verification is for an individual or for another person. For this reason, in the matching of an image having a similar pattern such as a fingerprint, the maximum matching rate in the case of the other person matching greatly exceeds 50%, and the difference in the maximum matching rate between the personal matching and the other person matching becomes large. May be smaller. For the above reasons, the conventional fingerprint matching device has a problem that it is difficult to set a threshold value for determining whether the fingerprint image is the same fingerprint image or a different fingerprint image, and the matching accuracy is reduced. This problem also occurs in other image matching devices other than the fingerprint matching device. SUMMARY An advantage of some aspects of the invention is to provide an image collation device, an image collation method, a program, and a recording medium that can improve collation accuracy.

[0011]

According to the present invention, there is provided an image processing apparatus for repeatedly executing contraction processing on a first image and sequentially outputting the first images before and after the contraction processing. And (10) repeatedly executing at least one of the translation processing and the rotation processing on the second image at regular intervals within a preset range, and outputs the processed second image. The first conversion means (20) compares the first image before and after the contraction processing and the first image after the contraction processing and the second image, which are output for each processing of the image processing means, with each other and agrees with each other. A first collation unit (30) for determining a rate (403); and a first image before the contraction process and a second image after the contraction process for each process of the first conversion unit. Is the average value of multiple match rates obtained from the comparison (404) calculating means for calculating the (4
0), extracting means (50) for obtaining at least one of the maximum matching rate and the minimum matching rate from the average of the matching rates output from the calculating means, and the maximum matching rate or the minimum matching rate output from the extracting means Determining means for determining whether the first image and the second image are the same using at least one of the following. Further, the image collating apparatus of the present invention executes the thinning processing on the first image, repeatedly executes the expansion processing on the first image after the thinning processing, and performs the expansion processing before and after the expansion processing. An image processing means (11) for sequentially outputting the subsequent first image, and repeating at least one of a translation process and a rotation process for the second image at a fixed amount within a preset range First conversion means (20) for executing and outputting a second image after processing, and a first image before or after the expansion processing output for each processing of the image processing means First comparing means (31) for comparing and collating the second image with the second image to obtain a coincidence ratio (403); and performing the expansion processing before and after the expansion processing for each processing of the first conversion means. The second image obtained by comparing and comparing the first image with the second image later. Calculating means (40) for obtaining an average matching rate (404) which is an average value of the matching rates, and extracting means for obtaining at least one of the maximum matching rate or the minimum matching rate from the average matching rates output from the calculating means. (50) and determining means (60) for determining whether the first image and the second image are the same using at least one of the maximum matching rate and the minimum matching rate output from the extracting means. It is provided.

The image collating apparatus of the present invention further includes an image processing means (10) for repeatedly executing contraction processing on the first image and sequentially outputting the first images before and after the contraction processing. A first conversion for repeatedly executing at least one of a translation process and a rotation process on the second image at predetermined intervals within a preset range, and outputting a processed second image. Means (20), first storage means (90) for storing the first images before and after the contraction processing output from the image processing means, and the first storage means (90) for storing the first images. A first collating unit (32) for comparing and collating each of the first images with the second image to obtain a coincidence ratio (403); and Ratio of each first image and the second image stored in the first storage means Calculating means (40) for obtaining an average of matching rates (404), which is an average value of a plurality of matching rates obtained from the collation; and calculating a maximum matching rate or a minimum matching rate from the average of matching rates output from the calculating means. Extraction means (50) for determining at least one, and at least one of the maximum coincidence rate and the minimum coincidence rate output from the extraction means, determine whether the first image and the second image are the same. Means (60). Further, the image collating apparatus of the present invention executes the thinning processing on the first image, repeatedly executes the expansion processing on the first image after the thinning processing, and performs the expansion processing before and after the expansion processing. An image processing means (11) for sequentially outputting the subsequent first image, and repeating at least one of a translation process and a rotation process for the second image at a fixed amount within a preset range First conversion means (20) for executing and outputting a processed second image, and a first conversion means for storing the first images before and after the expansion processing output from the image processing means. Storage means (90), and first collation means (32) for comparing and collating each first image and the second image stored in the first storage means to obtain a coincidence rate (403) In the first storage means for each processing of the first conversion means. Calculating means (40) for obtaining an average of matching rates (404), which is an average value of a plurality of matching rates obtained by comparing and comparing each of the obtained first images with the second image, and outputting from the calculating means. Extracting means (50) for obtaining at least one of the maximum matching rate and the minimum matching rate from the average of the matching rates to be obtained
And a determining means (60) for determining whether the first image and the second image are the same using at least one of the maximum matching rate and the minimum matching rate output from the extracting means. is there.

Further, the image collating apparatus of the present invention has an image storage for storing data indicating a weight given to each pixel of the first image according to the distance from the center line of the pattern and the first image. Means (201), at least one of a translation process and a rotation process for the second image is repeatedly executed at predetermined intervals within a preset range, and the processed second image is output. The first conversion means (20) performs comparison and comparison between the first image and the second image, and obtains a match rate (403) by a weighted average calculation based on the weight.
First matching means (36) for obtaining the maximum matching rate or minimum matching rate from a plurality of matching rates obtained by the plurality of processes of the first conversion means (50). And a determining means (60) for determining whether the first image and the second image are the same using at least one of the maximum matching rate and the minimum matching rate output from the extracting means. is there.

In one embodiment of the image collating apparatus according to the present invention, at least one of a translation process and a rotation process is performed on the second image at the first initial position in a predetermined range. A second conversion means (21) for repeatedly executing the processing every fixed amount within the range and outputting a processed second image;
For each processing of the second conversion means, a second image obtained by comparing the second image output from the second conversion means with the first image to obtain a coincidence rate (407). Means (33), when the coincidence rate output from the second matching means is maximum, the translation amount, rotation angle or translation of the second image from the first initial position to the current position Second storage means (9) for storing both the amount and the rotation angle.
1), wherein the first converting means (22) comprises:
The position obtained by adding the parallel movement amount, the rotation angle or the parallel movement amount and the rotation angle stored in the second storage means to the first initial position is defined as a second initial position. After moving the second image, at least one of a translation process and a rotation process is performed on the second image. In one configuration example of the image matching device of the present invention, a range preset in the first conversion unit is smaller than a range preset in the second conversion unit. Also, one configuration example of the image matching device of the present invention is configured such that the translation amount per one rotation, the rotation angle or the translation amount and the rotation angle per one time performed by the second conversion means on the second image are: The amount of translation and rotation angle or the amount of translation and rotation angle per rotation performed by the first conversion means on the second image at one time. In one configuration example of the image matching device of the present invention, the area of the matching area for which the second matching means determines the matching rate is smaller than the area of the matching area for which the first matching means determines the matching rate. Things.

Further, the image collating method of the present invention repeatedly executes a contraction process on the first image, and sequentially outputs the first images before and after the contraction process, and a second process. A first conversion procedure of repeatedly executing at least one of the translation processing and the rotation processing for each of the images within a preset range at regular intervals, and outputting a processed second image; The first image before and after the contraction processing or the second image output after the contraction processing, which is output for each processing of the image processing procedure, is compared and collated to determine a match rate and stored in a memory. And a plurality of coincidence rates obtained from comparison and comparison between the first image before and after the contraction processing and the second image for each processing of the first conversion procedure. The function of calculating the average of the matching rates, which is the average of A procedure for extracting at least one of a maximum match rate or a minimum match rate from the average of the match rates and storing the same in a memory; and the first image using at least one of the maximum match rate or the minimum match rate. And a determination procedure for determining whether the second image is the same. Further, the image matching method of the present invention executes thinning processing on the first image, repeatedly executes dilation processing on the first image after the thinning processing, and performs pre-expansion processing and expansion processing. An image processing procedure for sequentially outputting the subsequent first image, and repeatedly executing at least one of a translation process and a rotation process on the second image at predetermined intervals within a preset range; Second after processing
A first conversion procedure for outputting an image of the image and a first image after the expansion processing or the first image after the expansion processing, which is output for each processing of the image processing procedure, are compared and collated. A first matching procedure for determining a match rate and storing the same in a memory;
It is an average value of a plurality of coincidence rates obtained from comparison and comparison between the first image before and after the dilation processing and the second image for each processing of the first conversion procedure. An arithmetic procedure for obtaining an average of the match rates and storing the average in the memory; an extraction procedure for obtaining at least one of the maximum match rate or the minimum match rate from the average of the match rates and storing the same in the memory; And determining whether the first image and the second image are the same using at least one of the following.

The image collating method of the present invention repeatedly executes contraction processing on the first image, and sequentially outputs the first images before and after the contraction processing, and the second image processing procedure. A first conversion procedure of repeatedly executing at least one of the translation processing and the rotation processing for each of the images within a preset range at regular intervals, and outputting a processed second image; A first storage procedure for storing a first image before the contraction processing and after the contraction processing in a memory; a first image stored in the first storage procedure;
A first matching procedure of comparing and comparing the images with each other to obtain a match rate and storing the same in a memory; and each first processing stored in the first storage procedure for each process of the first conversion procedure. A calculation procedure for obtaining an average of the coincidence rates, which is an average value of a plurality of coincidence rates obtained from the comparison and comparison between the image of the second image and the second image, and storing the average in the memory; An extraction procedure for obtaining at least one of the minimum matching rates and storing the same in a memory; and determining whether the first image and the second image are the same using at least one of the maximum matching rate or the minimum matching rate. The procedure is executed. Further, the image matching method of the present invention executes thinning processing on the first image, repeatedly executes dilation processing on the first image after the thinning processing, and performs pre-expansion processing and expansion processing. An image processing procedure for sequentially outputting the subsequent first image, and repeatedly executing at least one of a translation process and a rotation process on the second image at predetermined intervals within a preset range; A first conversion procedure for outputting a second image after the processing, a first storage procedure for storing the first images before and after the expansion processing in a memory, and a first storage procedure Each stored first image and the second image
A first matching procedure of comparing and comparing the images with each other to obtain a match rate and storing the same in a memory; and each first processing stored in the first storage procedure for each process of the first conversion procedure. A calculation procedure for obtaining an average of the coincidence rates, which is an average value of a plurality of coincidence rates obtained from the comparison and comparison between the image of the second image and the second image, and storing the average in the memory; An extraction procedure for obtaining at least one of the minimum matching rates and storing the same in a memory; and determining whether the first image and the second image are the same using at least one of the maximum matching rate or the minimum matching rate. The procedure is executed.

Further, in the image matching method of the present invention, data indicating the weight given to each pixel of the first image according to the distance from the center line of the pattern and the first image are stored in a memory. An image accumulation procedure and at least one of a translation process and a rotation process on the second image are repeatedly executed at predetermined intervals within a preset range, and the processed second image is output. A first conversion procedure, a first comparison procedure of comparing and collating the first image with the second image, obtaining a match rate by a weighted average calculation based on the weight, and storing the same in a memory; An extraction procedure for obtaining at least one of a maximum match rate or a minimum match rate from a plurality of match rates obtained by a plurality of processes of the first conversion procedure and storing the same in a memory; and a maximum match output from the extraction procedure Rate or least match Using said at least one of the first
And a determination procedure for determining whether the second image is the same as the second image.

In one embodiment of the image matching method according to the present invention, before each procedure, at least one of a translation process and a rotation process is performed on the second image at the first initial position. Is repeatedly executed at regular intervals within a preset range, and a second image is output after the processing. A second conversion procedure is performed for each processing of the second conversion procedure.
And comparing the second image output from the conversion procedure with the first image to obtain a coincidence rate and storing the same in a memory.
And when the coincidence rate output from the second collation procedure is maximized, the translation amount, rotation angle or translation amount of the second image from the first initial position to the current position And a second storage procedure for storing both the rotation angle and the rotation angle in a memory, wherein the first conversion procedure includes the translation amount, the rotation angle or the translation amount and the rotation amount stored in the second storage procedure. A position obtained by adding an angle to the first initial position is defined as a second initial position.
Is moved, and at least one of a translation process and a rotation process is performed on the second image. In one configuration example of the image matching method of the present invention, a range preset in the first conversion procedure is smaller than a range preset in the second conversion procedure. . Further, one configuration example of the image matching method of the present invention includes a translation amount per one time performed on the second image in the second conversion procedure;
The rotation angle or the translation amount and the rotation angle are set to be larger than the translation amount, the rotation angle or the translation amount and the rotation angle per one time performed on the second image in the first conversion procedure. It was made. In one configuration example of the image matching method of the present invention, the area of the matching area for obtaining the matching rate in the second matching procedure is made smaller than the area of the matching area for obtaining the matching rate in the first matching procedure. It is like that.

[0019]

DESCRIPTION OF THE PREFERRED EMBODIMENTS According to the present invention, a process of translating, rotating, or translating and rotating a first image in order to correct a displacement between a first image and a second image, and a process after the process. While repeating the process of comparing and collating the first image and the second image to determine the degree of similarity (coincidence rate), the second image was compared and collated while being contracted or expanded by image processing. The point that the coincidence rate is averaged is different from the conventional image matching apparatus.

[First Embodiment] A case where an image is a fingerprint will be described below as an embodiment of the present invention. FIG. 1 is a block diagram illustrating a configuration of an image matching device according to a first embodiment of the present invention. This image matching device includes an image input device 100, an image database 200, and a processing device 300.

The image input device 100 detects unevenness of a fingerprint of a finger placed on a sensor (not shown) of the image input device 100 by a sensor, and performs analog / digital conversion (A / D) on a signal output from the sensor. Image processing such as D conversion) and binarization. The output of the image input device 100 is a binary image in which the convex portion of the fingerprint is represented by a pixel having black luminance (black pixel), and the concave portion of the fingerprint is represented by a pixel having white luminance (white pixel). The convex portion of the fingerprint may be a white pixel, and the concave portion of the fingerprint may be a black pixel. Hereinafter, the image output by the image input device 100 is referred to as an inspection image.

The image input device 100 detects the capacitance formed between the electrode of the small sense unit arranged two-dimensionally on the LSI chip and the skin of the finger touched via the insulating film. , A capacitance detection type fingerprint sensor that senses an uneven pattern of a fingerprint, an A / D converter that A / D converts an output signal of the sensor, and binarization of output data of the A / D converter. It comprises a processor for executing image processing and a storage device such as a semiconductor memory for storing image data. Regarding the capacitance detection type fingerprint sensor, see, for example, the document “M. Tartagni and R. Guerrieri,“ A fingerprint se
nsor based on the feedback capacitive sensing schem
e ", IEEE J. Solid-State Circuits, vol.33, pp.133-142, J
an, 1998 ".

The image database 200 stores fingerprint images acquired in advance as registration data. The image database 200 is configured by a storage device such as a hard disk device or a nonvolatile memory. Less than,
The image stored in the image database 200 is called a registered image.

The processing device 300 compares and compares the inspection image output from the image input device 100 with the registered image output from the image database 200, and determines whether the two images are the same fingerprint image or different fingerprint images. Is determined. In order to improve the determination accuracy (collation accuracy), the processing device 300 includes an image processing unit 10, a conversion unit 20,
It comprises a matching means 30, a calculating means 40, a maximum matching rate extracting means 50, and a determining means 60. The difference from the conventional example is that an image processing unit 10 and a calculation unit 40 are provided. Such a processing device 300 can be realized by a processor and a storage device such as a semiconductor memory.

The image processing means 10 includes an image input device 100
The shrinking process of narrowing the inspection image output from the pattern in the direction perpendicular to the center line of the pattern by, for example, one pixel is repeatedly executed, and the inspection image subjected to the shrinking process for each processing is compared with the collation unit 3.
Output to 0. The contraction processing can be realized by setting the pixel of interest to a white pixel if at least one white pixel exists near the pixel of interest (around 4 or 8).

The conversion means 20 includes an image database 200
Then, a registered image is obtained by translating (shifting) each pixel of the registered image input from the initial position (the position at the time of input from the image database 200) by a predetermined amount in accordance with a later-described parallel movement amount specifying signal 402. The shift operation by the conversion means 20 will be described. First, a coordinate system is set for a registered image, a primary conversion is performed to translate the coordinates of each pixel determined by the coordinate system in parallel, and finally, each pixel after the primary conversion is converted. By reconstructing the image based on the coordinates of, a registered image that has been translated is generated.

The collating unit 30 compares and collates the luminance values of the inspection image output from the image processing unit 10 and the registered image output from the converting unit 20 for each pixel at the same position, and the luminance values match. By calculating the number of black pixels in the first collation area set in advance and dividing the total number of matching pixels by the total number of black pixels in the registered image, the degree of similarity between the inspection image and the registered image (matching rate) Find 403. The number of coincident pixels × 2 / (the number of all black pixels in the registered image + the number of all black pixels in the inspection image) may be used as the coincidence rate 403.

The collation unit 30 performs the contraction processing of the inspection image by the image processing unit 10 and the self-contraction process until the minimum line width in the inspection image becomes 0 pixels and comparison and collation of the inspection image and the registered image become impossible. The inspection image prompting signal 401 is output to the image processing means 10 in order to repeat the comparison and collation according to. Further, when the moving amount of the registered image from the initial position to the current position (the position after the translation by the conversion unit 20 is performed) is within a predetermined range, the collating unit 30 performs the parallel shifting of the registered image. In order to execute again the calculation of the coincidence rate, a parallel movement amount designation signal 402 for designating the movement amount of the registered image at one time is output to the conversion means 20. The conversion means 20 translates the registered image by an amount designated by the translation amount designation signal 402.

The calculating means 40 calculates and outputs an average value (average of coincidence rates) 404 of a plurality of coincidence rates 403 which is a result of comparing and comparing each inspection image before and after the contraction processing with the registered image. . The maximum matching rate extraction means 50 calculates and outputs the maximum matching rate (maximum matching rate) 405 from the average matching rate 404 output by the calculating means 40. Judgment means 60
Compares the maximum matching rate 405 with a preset threshold value, determines that the fingerprint image is the same when the maximum matching rate 405 is equal to or greater than the threshold value, and determines that the maximum matching rate 405 is greater than the threshold value. If smaller, it is determined to be a different fingerprint image.

FIG. 2 shows the collating operation of the image collating apparatus according to the present embodiment. First, the image input device 100 detects a fingerprint of a finger placed on a sensor and generates an inspection image (Step S1). The processing device 300 includes the image input device 100
(Step S2), and when a registered image is input from the image database 200 (step S2).
3) The inspection image is stored by the image processing means 10 and the registered image is translated by the conversion means 20 (step S4).

The collating means 30 compares and collates the inspection image output from the image processing means 10 with the registered image output from the converting means 20, and determines the number of black pixels having the same luminance value in a predetermined number of black pixels. 1 in the collation area, and the match rate 403
Is obtained (step S5). Here, the matching means 3
Since the test image prompting signal 401 is not output from 0, the image processing unit 10 stores the test image input from the image input device 100 and outputs the test image as it is.
No contraction processing is performed.

The calculating means 40 stores the coincidence rate 403 output from the collating means 30 (step S6). next,
The collation unit 30 determines whether the minimum line width in the inspection image output from the image processing unit 10 is equal to or less than one pixel (step S7). Image processing means 10 for contraction processing
, An inspection image prompting signal 401 is output.

When the test image prompting signal 401 is input, the image processing means 10 executes contraction processing on the test image stored immediately before, and stores the test image after the contraction processing, and Output (Step S8).
The collation unit 30 performs the process of step S5 again,
A matching rate 403 is calculated from the contracted inspection image and the registered image output from the conversion means 20.
The matching rate 403 is stored (step S6).

Unless the minimum line width of the inspection image after the contraction processing becomes 0, the processing of steps S8, S5, and S6 is repeated, and each inspection image before and after the contraction processing is compared with the registered image. A plurality of matching rates 403 as a result of the comparison are obtained. Next, when the minimum line width of the inspection image output from the image processing unit 10 in the immediately preceding step S8 is equal to or smaller than one pixel (YES in step S7), the arithmetic unit 40 calculates the average of the plurality of stored coincidence rates 403. Calculate and output the value (average matching rate) 404 (Step S)
9).

The maximum coincidence rate extracting means 50 is provided by the arithmetic means 40
It is determined whether or not the average matching rate 404 output from is the maximum value (step S10). If it is the maximum value, this value is stored as the maximum matching rate 405 (step S11). Subsequently, the matching unit 30 determines whether the moving amount of the registered image from the initial position to the current position is within a preset range (Step S12). An inspection image restoration signal is output to the image processing means 10, and a translation amount designation signal 402 is output to the conversion means 20.

When the inspection image restoration signal is input, the image processing means 10 returns the inspection image to the state before the contraction processing input from the image input device 100 and stores the image, and outputs this inspection image to the collation means 30 (Step S13). The conversion unit 20 translates the registered image by an amount designated by the translation amount designation signal 402 (step S4). Thus, as long as the movement amount of the registered image from the initial position to the current position is within a preset range, steps S13 and S13 are performed.
The processes from 4 to S11 are repeated.

If the average match rate 404 output from the calculating means 40 is larger than the stored maximum match rate 405 (YES in step S10), the average match rate 404 is stored as a new maximum match rate 405. Needless to say, this is performed (step S11).

When the moving amount of the registered image exceeds the preset range (NO in step S12), the judging means 60 compares the maximum matching rate 405 with a preset threshold (step S14). ), Maximum match rate 40
If 5 is equal to or greater than the threshold, the fingerprint images are determined to be the same, and if the maximum matching rate 405 is smaller than the threshold, the fingerprint images are determined to be different.

The difference from the conventional image collating apparatus is that the coincidence rate 403 corresponding to a plurality of inspection images having different line widths obtained by repeating the contraction processing by the image processing means 10 and the comparison and collation by the collation means 30 is calculated by the arithmetic means. The point 40 is an average output.

FIG. 3 is a schematic diagram showing an example of the inspection image before the contraction processing output from the image input device 100 and the inspection image after the contraction processing output from the image processing means 10. FIG. 3A shows an inspection image before the contraction processing, and FIG.
FIG. 3C shows the inspection image obtained by performing the contraction processing once on the inspection image shown in FIG. 3A, and FIG. 3C shows the inspection image obtained by performing the contraction processing twice on the inspection image shown in FIG. The inspection image when it becomes a pixel is shown.

FIG. 4 is a schematic diagram showing a state in which the inspection image and the registered image are compared and collated. However, in FIG. 4, three comparisons and comparisons performed between the registered image and each of the inspection images in FIGS. 3A to 3C are combined into one. When the registered image and the inspection image are optimally aligned by the parallel movement of the registered image, the average matching rate 404 becomes maximum, and the maximum matching rate 405 is obtained.

Here, in the case of collation (identification) between fingerprint images acquired from the same finger, if the registered image and the inspection image are optimally aligned, the number of matching pixels will be the fingerprint acquired from a different finger. This is larger than in the case of matching between images (other person matching). In particular, when the inspection image is contracted as shown in FIG. 4 to reduce the overlap between the registered image and the inspection image, the difference in the number of matching pixels between the personal verification and the other person verification is enlarged, The difference between the coincidence rates 405 is enlarged.

That is, in the case of the identity verification, for the pixel where the inspection image of FIG. 3 (c) and the registered image overlap, the pixel between the registered image and each of the inspection images of FIG. 3 (a) to FIG. Since the coincidence of the luminance values is counted in all of the three comparisons performed, the coincidence of the luminance values is counted three times in total for the same pixel. Similarly, the inspection image and the registered image shown in FIG. For the pixel where is overlapped, the registered image and FIG.
3A, the coincidence of the luminance values is counted respectively in the two comparisons and comparisons performed with each inspection image in FIG. 3B, so that the coincidence of the luminance values is counted twice in total.
As for the pixel where the inspection image and the registered image in (a) overlap, the coincidence of the luminance values is counted once.

Therefore, when the maximum match rate 405 (average match rate 404) is obtained by averaging the match rates 403 obtained as a result of the three comparisons, the match rate 405 is larger than the maximum match rate 405 in the case of another person match. . As described above, in the present embodiment, the maximum matching rate 405 approaches 100% as the degree of matching between the registered image and the inspection image that has been subjected to the contraction processing, in particular, the inspection image that has been narrowed to a degree close to the core line, increases. Therefore, the difference between the maximum matching rates 405 between the personal verification and the other person verification can be enlarged, and the verification accuracy can be improved.

[Second Embodiment] FIG. 5 shows a second embodiment of the present invention.
FIG. 2 is a block diagram illustrating a configuration of an image matching device according to an embodiment of the present invention, in which the same components as those in FIG. 1 are denoted by the same reference numerals. The difference between the present embodiment and the first embodiment is that the processing device 301 includes an image processing unit 11 instead of the image processing unit 10 and a matching unit 31 instead of the matching unit 30.

The image processing means 11 comprises a thinning means 70 and an expanding means 80. The thinning unit 70 performs a thinning process for thinning the inspection image output from the image input device 100 so that the inspection image becomes a center line having a line width of 1 pixel in all places, and expands the inspection image that has been subjected to the thinning process. Output to 80. The thinning process is a method of sequentially removing black pixels outside the pixel group while keeping the connectivity (four or eight) of black pixels when focusing on a set of black pixels (Hildi).
(tch thinning).

The dilation means 80 repeatedly executes dilation processing of thickening the thinned inspection image by, for example, one pixel in a direction perpendicular to the center line of the pattern, and executes the dilation-processed inspection image for each processing. Output to the collating means 31. The dilation processing can be realized by setting the target pixel to a black pixel if at least one black pixel exists near the target pixel (near four or eight).

FIG. 6 is a flowchart showing the collating operation of the image collating apparatus of the present embodiment, and the same processes as those in FIG. 2 are denoted by the same reference numerals. The processing in steps S1 to S3 is exactly the same as in the first embodiment. The thinning unit 70 performs a thinning process on the inspection image output from the image input device 100, and outputs the thinned inspection image to the expansion unit 80 (Step S15). The conversion means 20 translates the registered image output from the image database 200 in parallel (step S4).

The comparing means 31 compares and compares the inspection image output from the image processing means 11 (expansion means 80) with the registered image output from the converting means 20, and the same as in the first embodiment. The rate 403 is obtained (step S5). It should be noted that here, the inspection image prompting signal 401
Is not output, the dilation means 80 only stores the thinned inspection image output from the thinning means 70 and outputs it as it is, without performing the dilation processing.

The calculating means 40 stores the coincidence rate 403 output from the collating means 31 (step S6). next,
The collation unit 31 determines whether the minimum line width in the inspection image output from the image processing unit 11 is equal to or larger than a preset number of pixels (step S16). An inspection image prompting signal 401 is output to the image processing means 11 to cause the image processing means 11 to perform the inspection.

When the test image prompting signal 401 is input, the dilation means 80 executes dilation processing on the test image stored immediately before, stores the test image after dilation processing, and outputs the test image to the collation means 31. (Step S17). The collation unit 31 performs the processing of step S5 again, obtains a coincidence rate 403 from the dilated inspection image and the registered image output from the conversion unit 20, and the arithmetic unit 40 stores the coincidence rate 403. (Step S6).

In this manner, as long as the minimum line width of the inspection image after the dilation processing does not exceed the set number of pixels, step S17,
The processing of S5 and S6 is repeated, and a plurality of coincidence rates 403 are obtained as a result of comparing and checking each inspection image before the expansion processing (after the thinning processing) and after the expansion processing with the registered image. Next, when the minimum line width of the inspection image output from the image processing unit 11 in the immediately preceding step S17 is equal to or larger than the set number of pixels (YES in step S16), the arithmetic unit 40
Similar to the first embodiment, the average matching rate 404 is calculated and output (step S9).

The processing in steps S10 and S11 is exactly the same as in the first embodiment. The collation unit 31 determines whether the movement amount of the registered image from the initial position to the current position is within a preset range (step S12). If the movement amount is within the preset range, the image processing unit 11, and outputs an inspection image restoration signal to the conversion means 20 and a parallel movement amount designation signal 402 to the conversion means 20.

When the inspection image restoration signal is input, the expansion means 80 returns the inspection image to the state after the thinning processing input from the thinning means 70 and stores it, and outputs this inspection image to the collation means 31 (Step S18). Conversion means 2
A value of 0 translates the registered image by the amount specified by the translation amount designation signal 402 (step S4). Thus,
As long as the movement amount of the registered image from the initial position to the current position is within a preset range, steps S4 to S6, S1
6, S17, and the processing of S9 to S11 are repeated. The processing in step S14 is exactly the same as in the first embodiment.

In the first embodiment, when the line width of the inspection image before the contraction processing is small, the number of times of execution of the contraction processing is smaller than when the line width is large. For this reason, the number of times of execution of the comparison and collation (the number of times of execution of the contraction process + 1) cannot be set to an optimal value, and the maximum matching rate 405 between the identity verification and the others verification is not obtained.
It is difficult to widen the difference sufficiently.

On the other hand, in the present embodiment, the inspection image is once thinned and then thickened by the expansion processing, so that the line width of the inspection image can be controlled to an optimum width for comparison and collation. . As a result, even if the line width of the inspection image before the contraction processing is small, the difference in the maximum matching rate 405 between the personal verification and the verification of another person can be sufficiently enlarged, and the verification accuracy can be improved. it can.

[Third Embodiment] FIG. 7 shows a third embodiment of the present invention.
FIG. 2 is a block diagram illustrating a configuration of an image matching device according to an embodiment of the present invention, in which the same components as those in FIG. 1 are denoted by the same reference numerals. The difference between the present embodiment and the first embodiment is that the processing device 302 is newly provided with a storage unit 90,
The point is that a matching means 32 is provided instead of 0.

The storage means 90 stores all the inspection images before and after the contraction processing output from the image processing means 10 and an inspection image prompting signal 401 for prompting the output of the inspection image.
, The stored inspection images are sequentially output. The matching unit 32 compares and compares each inspection image before and after the contraction processing sequentially output from the storage unit 90 with the registered image output from the conversion unit 20, and determines a match rate of 40 for each inspection image.
Ask for 3.

FIG. 8 is a flowchart showing the collating operation of the image collating apparatus of the present embodiment, and the same processes as those in FIG. 2 are denoted by the same reference numerals. The processing in steps S1 and S2 is exactly the same as in the first embodiment. Processing unit 3
When an inspection image is input from the image input device 100, the image processing unit 02 stores and outputs the inspection image,
The storage unit 90 stores the inspection image output from the image processing unit 10 (Step S19). The inspection image output first from the image processing means 10 is an inspection image that has been input from the image input device 100 and has not been subjected to the contraction processing.

Subsequently, the image processing means 10 executes contraction processing on the inspection image stored immediately before, and stores the inspection image after the contraction processing and outputs it to the storage means 90 (step S20). The storage unit 90 determines whether or not the minimum line width in the inspection image after the contraction processing output from the image processing unit 10 is 0 pixel (step S21). The inspection image is stored (Step 19). Thus, the processing of steps S19 and S20 is repeated until the minimum line width of the inspection image after the contraction processing becomes 0, and each inspection image before and after the contraction processing is stored in the storage unit 90.

Next, when the registered image is input from the image database 200, the processing device 302 (step S).
3), the registered image is translated by the conversion means 20 (step S4). The matching unit 32 outputs an inspection image prompting signal 401 to the storage unit 90 to output the inspection image. In response to the inspection image prompting signal 401, the storage unit 90 outputs one of the stored inspection images to the matching unit 32. The collation unit 32 compares and compares the inspection image output from the storage unit 90 with the registered image output from the conversion unit 20, and determines the number of black pixels having the same luminance value in the first collation region. Total within the match rate 403
Is obtained (step S22).

The calculating means 40 stores the coincidence rate 403 output from the collating means 32 (step S6). next,
The matching unit 32 determines whether there is an inspection image for which comparison and comparison has not been completed among the inspection images stored in the storage unit 90 (step S23), and there is an inspection image for which comparison and comparison has not been completed. In this case, an inspection image prompting signal 401 is output to the storage means 90 in order to output the incomplete inspection image.
In response to the inspection image prompting signal 401, the storage unit 90
Outputs one inspection image for which comparison and comparison has not been completed to the comparison unit 32. The matching unit 32 performs the processing of step S22 again to obtain the coincidence rate 403, and the arithmetic unit 40 stores the coincidence rate 403 (step S6).

In this manner, the processing of steps S22 and S6 is performed for each inspection image for which comparison and collation has not been completed, and the coincidence rate 403 is calculated and stored for each inspection image. Steps S9 to S
The processing in S12 and S14 is exactly the same as in the first embodiment. Note that, in the present embodiment, it is not necessary to execute the processing of step S13.

In the first embodiment, when the parallel movement processing of the registered image in step S4 is performed twice or more, step S4 is performed.
Before step 4, step S13 was executed to return the inspection image to the state before the contraction processing, and after step S4, the contraction processing of step S8 had to be executed again. On the other hand, in the present embodiment, since each inspection image before and after the contraction processing is stored in the storage unit 90, if the parallel movement processing of the registered image in step S4 is performed twice or more, the step It is not necessary to perform the restoration processing of the inspection image and the contraction processing of the inspection image again before S4. Therefore, the frequency of image processing can be reduced, so that the processing can be speeded up as compared with the first embodiment.

In this embodiment, the processing device 302
Of the processing apparatus 30 of the first embodiment
Although 0 is used, the configuration of the second embodiment may be used. In the case of the second embodiment, a storage unit 90 may be added between the expansion unit 80 and the comparison unit 31.

[Fourth Embodiment] FIG. 9 shows a fourth embodiment of the present invention.
FIG. 2 is a block diagram illustrating a configuration of an image matching device according to an embodiment of the present invention, in which the same components as those in FIG. 1 are denoted by the same reference numerals. The difference between this embodiment and the first embodiment is that the first embodiment
In addition, the conversion unit 21 is used as a unit for the processing unit 303 to roughly correct the relative displacement between the registered image and the inspection image.
, Matching means 33 and storage means 91,
Is that the amount of movement when the maximum matching rate is obtained is stored in the storage means 91 while repeating the parallel movement by the comparison means and the comparison and collation by the collation means 33. Second, a movement amount is output from the storage unit 91 to the conversion unit 22 corresponding to the conversion unit 20 of the first embodiment, and a second initial position based on the movement amount and the first initial position is output. Is to start the parallel movement of the inspection image by the conversion means 22.

The conversion means 21 converts the image database 200
Then, a registered image is output in which each pixel of the registered image input from is translated by a predetermined amount from a first initial position (the position at the time of input from the image database 200) according to a translation amount designation signal 406 described later. The matching means 33
Registered image output from conversion means 21 and image input device 1
In the inspection image output from 00, the luminance values are compared and collated for each pixel at the same position, the number of black pixels having the same luminance value is totaled in the second verification area, and the total number of matching pixels is calculated. The coincidence rate 407 between the inspection image and the registered image is obtained by dividing by the number of black pixels of the registered image.

Further, the collation means 33 outputs a movement amount signal 4 representing the movement amount of the registered image from the first initial position to the current position (the position after the parallel movement by the conversion means 21).
08 to the storage means 91, and when the movement amount is within the first range set in advance, the conversion means 21 is re-executed to execute the parallel movement of the registered image and the calculation of the coincidence rate again. A parallel movement amount designation signal 406 for designating the movement amount of the registered image at one time is output. Conversion means 21
Translates the registered image by an amount designated by the translation amount designation signal 406. Here, the first range is the same as the range set in the matching unit 30 of the first embodiment.

The storage means 91 stores the movement amount signal 408 output from the matching means 33 when the coincidence rate 407 output from the matching means 33 is maximum, and uses this as the movement amount signal 409 for the conversion means 22. Output to The conversion unit 22 moves the registered image input from the image database 200 to the second initial position, using a position obtained by adding the movement amount represented by the movement amount signal 409 to the first initial position as a second initial position. Then, a registered image in which each pixel of the registered image is translated by a predetermined amount in accordance with the translation amount designation signal 402 is output.

The matching unit 34 obtains the coincidence rate 403 between the inspection image output from the image processing unit 10 and the registered image output from the conversion unit 22 in the same manner as the matching unit 30.
Furthermore, the matching unit 34 determines that the amount of movement of the registered image from the second initial position to the current position (the position after the parallel movement by the conversion unit 22) is within the second range set in advance. And outputs a parallel movement amount designation signal 402 for designating the movement amount of the registered image per one time. The conversion means 22
The registered image is translated by an amount designated by the translation amount designation signal 402. Here, the second range is set to a range smaller than the first range.

FIG. 10 is a flowchart showing the collating operation of the image collating apparatus of the present embodiment. The same processes as those in FIG. 2 are denoted by the same reference numerals. First, the image input device 1
00 detects a fingerprint of a finger placed on the sensor and generates an inspection image (step S1). The processing device 303
When an inspection image is input from the image input device 100 (step S24) and a registered image is input from the image database 200 (step S25), the registered image is translated by the conversion unit 21 (step S26). Note that the initial translation amount may be zero.

Then, the matching unit 33 compares and matches the registered image output from the conversion unit 21 with the inspection image output from the image input device 100 to obtain a coincidence rate 407 (step S27). The storage unit 91 determines whether or not the coincidence rate 407 output from the matching unit 33 is the maximum value (step S28), and if it is the maximum value, stores the movement amount signal 408 output from the matching unit 33 at this time. (Step S29).

The collating means 33 determines whether the amount of movement of the registered image from the first initial position to the current position is within a first range set in advance (step S30), and determines whether the amount of movement is equal to the first amount. If it is within the range, a translation amount designation signal 406 is output to the conversion means 21. Thus, as long as the movement amount of the registered image from the first initial position to the current position is within the first range, the processing of steps S26 to S29 is repeated.

When the amount of movement of the registered image exceeds the first range (NO in step S30), the storage means 91
The stored movement amount signal 408 is output as a movement amount signal 409. When the moving amount of the registered image exceeds the first range, the conversion unit 22 sets the position obtained by adding the moving amount represented by the moving amount signal 409 to the first initial position as a second initial position. The registered image output from the database 200 is moved to the second initial position (Step S3)
1). Further, the conversion means 22 translates the registered image in accordance with the translation amount designation signal 402 (step S4).

The matching unit 34 compares and matches the inspection image output from the image processing unit 10 with the registered image output from the conversion unit 22, and obtains the coincidence rate 403 as in the first embodiment ( Step S32). Here, since the inspection image prompting signal 401 is not output from the matching unit 34, the image processing unit 10 simply stores the inspection image input from the image input device 100 and outputs it as it is. Not implemented.

The processing in steps S6 to S11 is the same as in the first embodiment. The collating means 34 determines whether the moving amount of the registered image from the second initial position to the current position is within a second range set in advance (step S33).
If the movement amount is within the second range, a parallel movement amount designation signal 402 is output to the conversion means 22. In this way, the second
Of the registered image from the initial position to the current position
As long as it is within the range of steps S13, S4, S32,
Steps S6 to S11 are repeated. Step S13, S
The processing of 14 is exactly the same as that of the first embodiment.

In the present embodiment, in order to roughly correct the relative displacement between the registered image and the inspection image, the maximum matching rate is obtained within the first range, and the position at which the maximum matching rate is obtained is determined by the second position. Since the process described in the first embodiment is executed in the second range smaller than the first range as the initial position of the second position, the range set in the matching unit 30 of the first embodiment and the second range If the range of 1 is the same, in the comparison and collation by the collation means 33, the contraction processing of the inspection image is omitted, and only the maximum matching rate needs to be obtained from the inspection image before the contraction processing and the registered image. The processing time can be reduced as compared with the embodiment.

In this embodiment, the processing device 303
Of the processing apparatus 30 of the first embodiment
Although 0 is used, the configurations of the second and third embodiments may be used. In the case of the second and third embodiments, the conversion means 21, the verification means 33 and the storage means 91 are added, the conversion means 22 is used instead of the conversion means 20, and the functions of the verification means 31, 32 May be added to the function of the matching means 34.

[Fifth Embodiment] FIG. 11 is a block diagram showing the configuration of an image matching apparatus according to a fifth embodiment of the present invention, which is the same as FIGS. 1, 5, 7, and 9. Are given the same reference numerals. In the present embodiment, first to fourth
This is a combination of the above embodiments. Storage means 92
Stores all the inspection images output from the image processing unit 11 before and after the expansion processing, outputs an arbitrary inspection image to the matching unit 35 in response to the inspection image prompting signal 410, and In response to the signal 401, all the stored inspection images are sequentially output.

The collating means 35 has the function of the collating means 33 of the fourth embodiment, and has the function of the storage means 9 before the comparative collation.
2. Inspection image prompting signal 410 for prompting the output of the inspection image
Output function.

FIG. 12 is a flowchart showing the collating operation of the image collating apparatus of the present embodiment. The same processes as those in FIGS. 2, 6, 8 and 10 are denoted by the same reference numerals.
The processing in steps S1, S2 and S15 is exactly the same as in the second embodiment. The storage means 92 stores the image processing means 11
The inspection image output from the (expansion means 80) is stored (step S34). Here, the expansion unit 80 only stores the thinned inspection image output from the thinning unit 70 and outputs it as it is, but does not execute the expansion processing.

The dilation means 80 executes dilation processing on the test image stored immediately before, and stores the test image after dilation processing and outputs it to the storage means 92 (step S3).
5). The storage unit 92 determines whether the minimum line width in the inspection image output from the image processing unit 11 is equal to or greater than a preset number of pixels (step S36). Yes (Step S3
4). In this manner, as long as the minimum line width of the inspection image after the dilation processing does not exceed the set number of pixels, steps S34 and S35
Are repeated, and the inspection images before the expansion processing (after the thinning processing) and after the expansion processing are stored in the storage unit 92.

The processing in step S26 is exactly the same as in the fourth embodiment. The matching unit 35 outputs the inspection image prompting signal 410 to the storage unit 92, and in response to this, the storage unit 92 outputs any one of the stored inspection images to the matching unit 35. The collation means 35 includes the storage means 9
The inspection image output from step 2 and the registered image output from the conversion means 21 are compared and collated to determine a coincidence rate 407 (step S37).

The processing in steps S28 to S30 is the same as in the fourth embodiment. Therefore, as long as the movement amount of the registered image from the first initial position to the current position is within the first range, the processing of steps S26, S37, and S29 is repeated. When the movement amount of the registered image exceeds the first range (NO in step S30), storage means 91 outputs stored movement amount signal 408 as movement amount signal 409. When the moving amount of the registered image exceeds the first range, the conversion unit 22 sets the position obtained by adding the moving amount represented by the moving amount signal 409 to the first initial position as a second initial position. The registered image output from the database 200 is moved to the second initial position (Step S3)
1).

Steps S4, S22, S6, S23, S
The processing from 9 to S12 and S14 is exactly the same as in the third embodiment. Thus, in the present embodiment, the effects of the first to fourth embodiments can be simultaneously obtained.

[Sixth Embodiment] In the fourth and fifth embodiments, the parallel movement outputted by the matching means 33 and 35 for roughly correcting the relative displacement between the registered image and the inspection image. Although the difference between the amount designation signal 406 and the translation amount designation signal 402 output by the collation means 32 and 34 for comparison and collation for each collation area is not described, the amount of one time indicated by the translation amount designation signal 406 is not described. The moving amount may be larger than the moving amount per one time indicated by the parallel movement amount designation signal 402. Also in this case, the configuration of the image collating apparatus and the collating operation thereof are as shown in FIGS.

As described above, in the present embodiment, the amount of movement of the inspection image at one time when the relative displacement between the registered image and the inspection image is roughly corrected is increased. Number of times and matching means 33,3
5, the number of times of comparison and matching can be reduced.
The processing time can be reduced as compared with the fifth embodiment.

[Seventh Embodiment] In the fourth and fifth embodiments, the second matching area in which the matching means 33 and 35 calculate the matching rate 407 and the matching rate 32 and 34 match the matching rate 403.
Although the difference of the first collation region for calculating the first collation region is not mentioned, the area of the second collation region preset in the collation units 33 and 35 is determined by the first collation region preset in the collation units 32 and 34. It may be smaller than the area of the region. Also in this case, the configuration of the image collating apparatus and the collating operation thereof are as shown in FIGS.

As a result, in this embodiment, when the relative displacement between the registered image and the inspection image is roughly corrected, the number of pixels to be compared and compared can be reduced, so that the processing time can be shortened.

[Eighth Embodiment] In the first to seventh embodiments, the registered image is translated, but the inspection image may be translated. When the inspection image is translated, the contraction processing or the expansion processing of the registered image can be performed in advance. Hereinafter, such an embodiment will be described. FIG. 13 is a block diagram showing the configuration of the image matching device according to the present embodiment. The same components as those in FIG. 1 are denoted by the same reference numerals.

The operation of the conversion means 20 is exactly the same as that of the first embodiment except that the object of the parallel movement processing is the inspection image output from the image input device 100. The same registered images as those in the first to seventh embodiments are stored in the image database 201, but the weight W is assigned to each pixel of the registered images in the first to seventh embodiments. And form. FIG. 14 is a diagram illustrating an example of a registered image according to the present embodiment.

In FIG. 14, load areas A, B, and C indicate black pixel areas. The load area A corresponds to, for example, an image obtained by subjecting the registered images of the first to seventh embodiments to contraction processing twice, for example, by the same method as the image processing means 10 and is the area closest to the center line. The load area B is, for example, 1
This corresponds to an area obtained by removing the load area A from the image subjected to the rotational shrinkage processing, and is an area slightly distant from the center line. The load area C corresponds to an area excluding the load area B from the same registered image, and is an area farthest from the center line.

The weight W is assigned such that the value becomes larger in a load region closer to the center line. For example, in the example of FIG. 14, the weight W0 = 0 is assigned to the white pixel, the weight W1 = 1 is assigned to the load area C of the black pixel, the weight W2 = 2 is assigned to the load area B, Area A
Is given a weight W3 = 3. As described above, the image database 201 stores the same registered images as those in the first to seventh embodiments, and data indicating the weight W of each pixel of the registered images.

The collating means 36 compares and collates the luminance value of each pixel at the same position between the inspection image output from the converting means 20 and the registered image output from the image database 201, and outputs a black image having the same luminance value. The number of pixels is totaled for each of the load regions A, B, and C within the first collation region set in advance, and a match rate 403 is calculated from the total number of matching pixels for each load region by the following equation.

Matching rate = (AA × W3 + AB × W2 + AC × W1) / (NA + NB + NC) (1) In equation (1), AA is the number of matching pixels in the load area A,
AB is the number of matching pixels in the load area B, AC is the number of matching pixels in the load area C, NA is the number of black pixels in the load area A in the registered image, NB is the number of black pixels in the load area B in the registered image, NC is the number of black pixels in the load area C in the registered image.

The collation means 36 outputs a parallel movement amount designation signal 402, similarly to the collation means 30. In the present embodiment, the registered image is divided into three load regions. However, the number of load regions may be two or more. Even when the number of load regions is other than three, the same as in equation (1) is applied. Needless to say, the matching rate 403 can be calculated.

FIG. 15 is a flowchart showing the collating operation of the image collating apparatus according to the present embodiment, and the same processes as those in FIG. 2 are denoted by the same reference numerals. Image database 20
1 outputs the registered image and data indicating the weight W of each pixel of the registered image to the matching unit 36 (step S4).
0).

The conversion means 20 translates the inspection image output from the image input device 100 (step S4).
2). The collation unit 36 compares and compares the inspection image output from the conversion unit 20 with the registered image output from the image database 201, and obtains a coincidence rate 403 according to equation (1) (step S43). Matching rate 403 of the present embodiment
Is equivalent to the coincidence rate average 404 of the first embodiment, so that there is no need to use the calculating means 40.

The maximum coincidence rate extracting means 50 includes
It is determined whether or not the matching rate 403 output from is the maximum value (step S44). If it is the maximum value, this value is stored as the maximum matching rate 405 (step S45). continue,
The collation unit 36 determines whether the movement amount of the inspection image from the initial position to the current position is within a preset range (step S46). If the movement amount is within the preset range, the conversion unit 20 To output the parallel movement amount designation signal 402.

The conversion means 20 outputs a translation amount designation signal 40
The inspection image is translated by the amount specified in step 2 (step S42). Thus, as long as the movement amount of the registered image from the initial position to the current position is within a preset range,
Steps S42 to S45 are repeated.

When the moving amount of the inspection image exceeds the range set in advance (NO in step S46), the determination means 60 performs the processing in step S14 as in the first embodiment. As described above, in the present embodiment, by preparing a registered image in which the weight W is assigned to each pixel in advance, the image processing unit 10 becomes unnecessary, and it is not necessary to repeatedly perform the contraction processing. Therefore, the processing can be speeded up as compared with the first embodiment.

In the present embodiment, the black pixel region in the registered image is divided into a plurality of load regions by contracting the registered image. However, as in the second embodiment, the registered image is temporarily stored. Each load region may be determined by thinning and then thickening by expansion processing. Further, the configuration of the present embodiment may be applied to the fourth embodiment.

[Ninth Embodiment] FIG. 16 is a block diagram showing a configuration of an image matching apparatus according to a ninth embodiment of the present invention. The configuration of the image matching device described in the first to eighth embodiments can be realized by the computer 306. This computer 306 has a CPU 500, a ROM
(Read Only Memory) 501, RAM (Random Access M)
emory) 502, an auxiliary storage device 503 such as a flexible disk device, a large-capacity auxiliary storage device 504 such as a hard disk device, and an interface device 5 serving as an interface with a display device (not shown) for outputting video.
05, an interface device 506 serving as an interface with a keyboard (not shown), and an interface device 507 serving as an interface with the image input device 100.

The image databases 200 and 201 store RA
It can be realized by the M502 or the auxiliary storage device 504. In the apparatus shown in FIG. 16, a program for realizing the image collating method of the present invention is provided in a state recorded on a recording medium such as a flexible disk, a CD-ROM, and a memory card. This recording medium is stored in a computer 3
When inserted into the auxiliary storage device 503, the program recorded on the medium is read. And the CPU 500
Writes the read program into the RAM 502 or the auxiliary storage device 504, and executes the processing described in the first to eighth embodiments according to the program. Thus, processing similar to that of the first to eighth embodiments can be realized.

In the above-described first to ninth embodiments, the case where the image to be collated is a fingerprint image has been described. Then, the present invention can be applied.

In the first to ninth embodiments, the number of matching pixels is counted using black pixels. However, the number of matching pixels may be counted using white pixels. Also, the first to first
In the ninth embodiment, the registered image and the inspection image are binary images, but a grayscale image of, for example, 256 gradations before the binarization processing may be used. In this case, a pixel whose difference in luminance value between the inspection image and the registered image is within a predetermined range may be set as a matching pixel.

Although the conversion means 20 to 22 translate the inspection image or the registered image in parallel in order to correct the positional deviation between the inspection image and the registered image, the conversion means 20 to 22 may rotate the inspection image or the registered image. Both translation and rotation may be performed. When both the parallel movement and the rotation are performed, not only the positional deviation but also the angular deviation can be corrected. When performing both the translation and the rotation, for example, after rotating the inspection image or the registered image by a certain angle, the translation of the inspection image or the registered image is repeated as described above, and the total amount of the translation is previously determined. At a point in time when the set image exceeds the set range, the inspection image or the registered image may be rotated again by a predetermined angle, and a process of repeating the parallel movement of the inspection image or the registered image may be performed.

However, when performing both the parallel movement and the rotation, it is necessary to set the respective ranges of the parallel movement amount and the rotation angle in the matching means 30 to 36. Collation means 30
36 to 36 designate parallel movements for designating the movement amount per inspection image if the movement amount of the registered image from the first or second initial position to the current position is within the range of a predetermined parallel movement amount. The moving amount designation signals 402 and 406 are output, and if the rotation angle of the inspection image from the first or second initial position to the current position is within the range of the preset rotation angle, one time of the inspection image is output. Outputs a rotation angle specification signal that specifies the rotation angle. When only rotation is performed, a rotation angle designation signal is output.

The conversion means 20 to 22 translate the inspection image or the registered image in accordance with the translation amount designation signals 402 and 406, and rotate the inspection image or the registered image in accordance with the rotation angle designation signal. When performing both the parallel movement and the rotation, the collation unit 33 calculates the movement amount signal 408 representing the movement amount of the inspection image or the registered image from the first initial position to the current position, and the movement amount signal 408 from the first initial position. Outputting an angle signal representing the rotation angle of the inspection image or the registered image up to the current position,
The storage unit 91 stores the movement amount signal 408 and the angle signal output from the matching unit 33 when the coincidence rate 407 becomes the maximum, and outputs them to the conversion unit 22.

In the first to ninth embodiments, only the maximum match rate is used to determine whether the inspection image and the registered image are the same. However, at least one of the maximum match rate and the minimum match rate is used. May be used. As a method of using both the maximum matching rate and the minimum matching rate, a maximum matching rate and a minimum matching rate are obtained by the extracting means from the matching rate average 404 (the matching rate 403 in the eighth embodiment). A match rate difference, which is a difference from the minimum match rate, is obtained, and whether the match rate difference is equal to or greater than a predetermined threshold is determined by a determination unit. And a method for determining that the registered images are the same. According to this method, the difference in the determination index between the personal verification and the verification by another can be enlarged, so that the verification accuracy can be further improved.

A quotient obtained by dividing the maximum matching rate by the minimum matching rate is obtained by the extracting means, and it is determined by the determining means whether or not this quotient is equal to or greater than a predetermined threshold value. In this case, the inspection image and the registered image may be determined to be the same. According to this method, when the minimum matching rate is smaller than the maximum matching rate by two digits or more, the difference between the judgment indexes between the personal verification and the other verification can be increased, so that the verification accuracy is further improved. Can be.

Further, the maximum coincidence rate is equal to or higher than a preset first threshold value and the minimum coincidence rate is set to a second preset threshold value.
(The first threshold ≧ the second threshold), it may be determined that the inspection image and the registered image are the same. According to this method, the range of the matching rate in which the threshold value can be set can be expanded, so that the matching accuracy can be further improved.

When the minimum matching rate is smaller than a preset threshold value, it may be determined that the inspection image and the registered image are the same. According to this method, the processing can be simplified by reducing the maximum matching rate extraction processing, so that the processing time can be reduced.

[0114]

According to the present invention, the first conversion means repeatedly executes at least one of the translation processing and the rotation processing on the second image at predetermined intervals within a preset range. By doing so, while correcting the positional shift between the first image and the second image, before each contraction process (before the dilation process) and after the contraction process (after the dilation process) ), The first image and the second image are compared and collated to determine a coincidence rate, and an average of the coincidence rates is obtained, whereby a second image that does not coincide with the first image is obtained. In comparison, a second image that is likely to be the same as the first image (the first image that has been subjected to the contraction process or the first image that has not been subjected to the expansion process that has been subjected to only the thinning process) has been compared and compared. Image with matching pixels) should have a higher matching rate. Since it is, it is possible to enlarge the difference in determination index between the personal identification with others collation can be improved collation precision.

Further, since the first storage means is provided, the first images before the contraction processing (before the expansion processing) and after the contraction processing (after the expansion processing) are stored in the first storage means. Therefore, it is not necessary to perform the contraction processing or the expansion processing on the first image every time the processing of the first conversion unit is performed. Therefore, the frequency of image processing can be reduced, and the processing can be speeded up.

A first image in which each pixel is given a weight is prepared in advance, and the weight is set so that the value is larger in an area closer to the center line of the pattern. By calculating the matching rate by a weighted average calculation from the number of matching pixels at the same position and the same brightness of the image and the weight,
Since the matching rate of the second image that is more likely to be the same as the first image can be made higher than the second image that does not match the first image, the identity verification is performed. And the difference of the judgment index between the person verification and others verification,
The matching accuracy can be improved. Further, at the time of comparison and collation, it is not necessary to perform the contraction processing or the expansion processing of the first image, so that the processing can be sped up.

Further, a second conversion means, a second collation means and a second storage means are provided so that the range preset in the first conversion means is larger than the range preset in the second conversion means. The first conversion unit sets the position obtained by adding the translation amount, the rotation angle or the translation amount and the rotation angle stored in the second storage unit to the first initial position as a second initial position. After the second image is moved to the second initial position, at least one of a translation process and a rotation process is performed on the second image, so that the first image and the second image are processed. A second conversion unit, a second collation unit, and a second conversion unit for roughly correcting the relative displacement between the two images.
Since only the maximum matching rate needs to be obtained in the storage means, the processing time can be reduced.

Further, the first conversion means converts the amount of parallel movement, rotation angle or the amount of parallel movement and rotation angle to be executed for the second image by the second conversion means into the second image. By making it larger than the parallel movement amount, rotation angle or parallel movement amount and rotation angle per one executed for
Since the amount of movement per time of the second image when roughly correcting the positional deviation between the first image and the second image is increased, the number of times of the parallel movement processing by the second conversion means and the second The number of times of comparison and collation by the collation means can be reduced,
Processing time can be reduced.

Further, by making the area of the matching area for which the second matching means obtains the matching rate smaller than the area of the matching area for which the first matching means obtains the matching rate, the first image and the second image are obtained. When roughly correcting the relative displacement of the image, the number of pixels to be compared and matched can be reduced,
Processing time can be reduced.

[Brief description of the drawings]

FIG. 1 is a block diagram illustrating a configuration of an image matching device according to a first embodiment of the present invention.

FIG. 2 is a flowchart illustrating a collation operation of the image collation device according to the first embodiment of the present invention.

FIG. 3 is a diagram illustrating an example of an inspection image before a contraction process and an inspection image after a contraction process.

FIG. 4 is a schematic diagram showing a state in which an inspection image and a registered image are compared and collated in the first embodiment of the present invention.

FIG. 5 is a block diagram illustrating a configuration of an image matching device according to a second embodiment of the present invention.

FIG. 6 is a flowchart illustrating a collation operation of the image collation device according to the second embodiment of the present invention.

FIG. 7 is a block diagram illustrating a configuration of an image matching device according to a third embodiment of the present invention.

FIG. 8 is a flowchart illustrating a collation operation of the image collation device according to the third embodiment of the present invention.

FIG. 9 is a block diagram illustrating a configuration of an image matching device according to a fourth embodiment of the present invention.

FIG. 10 is a flowchart illustrating a collation operation of the image collation device according to the fourth embodiment of the present invention.

FIG. 11 is a block diagram illustrating a configuration of an image matching device according to a fifth embodiment of the present invention.

FIG. 12 is a flowchart illustrating a collation operation of an image collation device according to a fifth embodiment of the present invention.

FIG. 13 is a block diagram illustrating a configuration of an image matching device according to an eighth embodiment of the present invention.

FIG. 14 is a diagram illustrating an example of a registered image according to the eighth embodiment of the present invention.

FIG. 15 is a flowchart illustrating a collation operation of the image collation device according to the eighth embodiment of the present invention.

FIG. 16 is a block diagram illustrating a configuration of an image matching device according to a ninth embodiment of the present invention.

FIG. 17 is a block diagram showing a configuration of a conventional fingerprint matching device.

FIG. 18 is a flowchart illustrating a collation operation of the fingerprint collation device in FIG. 17;

FIG. 19 is an enlarged schematic diagram of a fingerprint for explaining a problem of the conventional fingerprint matching device.

[Explanation of symbols]

100 image input device, 200, 201 image database, 300, 301, 302, 303, 304, 30
5 processing apparatus, 10, 11 image processing means, 20, 2
1, 22,... Conversion means, 30, 31, 32, 33, 34,
35, 36: matching means, 40: calculating means, 50: maximum matching rate extracting means, 60: determining means, 70: thinning means, 8
0: expansion means, 90, 91, 92: storage means.

 ──────────────────────────────────────────────────続 き Continuing on the front page (72) Inventor Takahiro Hanada 2-3-1 Otemachi, Chiyoda-ku, Tokyo Inside Nippon Telegraph and Telephone Corporation (72) Inventor Mamoru Nakanishi 2-3-1, Otemachi, Chiyoda-ku, Tokyo No. 1 Nippon Telegraph and Telephone Corporation F term (reference) 5B043 BA02 CA02 EA12 GA05 5L096 BA15 EA04 EA15 EA16 GA19 HA07 JA03

Claims (28)

[Claims] An image matching device for determining whether a first image and a second image are the same, wherein a contraction process is repeatedly performed on the first image, and a first image before and after the contraction process is executed. An image processing means for sequentially outputting the image of the second image, and at least one of the parallel movement process and the rotation process for the second image is repeatedly executed at regular intervals within a preset range. First to output 2 images
A first means for comparing and comparing a first image before or after the contraction processing and a second image output after the contraction processing, which is output for each processing of the image processing means, to obtain a coincidence rate; And a plurality of coincidence rates obtained from comparison and comparison between the first image before and after the contraction processing and the second image for each processing of the first conversion means. Calculating means for calculating the average of the coincidence rates which are the average values of the extraction means; extracting means for obtaining at least one of the maximum coincidence rate and the minimum coincidence rate from the average of the coincidence rates output from the arithmetic means; An image matching apparatus, comprising: a determination unit configured to determine whether the first image and the second image are the same using at least one of a maximum matching rate and a minimum matching rate. 2. An image collating apparatus which determines whether a first image and a second image are the same, executes a thinning process on the first image, and executes the first image after the thinning process. Image processing means for repeatedly executing dilation processing on the second image and sequentially outputting the first images before and after the dilation processing; and at least one of translation and rotation processing on the second image Is repeatedly executed at predetermined intervals within a preset range, and a first image is output to output a second image after processing.
And a first image after the dilation processing and a second image output before and after the dilation processing, which are output for each processing of the image processing means, are compared with each other to obtain a match rate. And a plurality of matching rates obtained from comparison and comparison between the first image before and after the dilation processing and the second image for each processing of the first conversion means. Calculating means for calculating the average of the coincidence rates which are the average values of the extraction means; extracting means for obtaining at least one of the maximum coincidence rate and the minimum coincidence rate from the average of the coincidence rates output from the arithmetic means; An image matching apparatus, comprising: a determination unit configured to determine whether the first image and the second image are the same using at least one of a maximum matching rate and a minimum matching rate. 3. An image matching device for determining whether a first image and a second image are the same, wherein the first image is repeatedly subjected to a contraction process, and the first image is subjected to a first contraction process before and after the contraction process. An image processing means for sequentially outputting the image of the second image, and at least one of the parallel movement process and the rotation process for the second image is repeatedly executed at regular intervals within a preset range. First to output 2 images
Conversion means; first storage means for storing the first images before and after the contraction processing output from the image processing means; and each of the first images stored in the first storage means. First matching means for comparing and comparing the image of the second image with the second image to obtain a matching rate; and for each processing of the first conversion means, each of the first and second images stored in the first storage means Calculating means for calculating an average of a plurality of matching rates obtained by comparing and comparing the first image and the second image; and a maximum matching rate among the average of matching rates output from the calculating means. Extracting means for determining at least one of a rate or a minimum matching rate; and determining whether the first image and the second image are the same using at least one of the maximum matching rate or the minimum matching rate output from the extracting means. Determining means for determining Image matching system. 4. An image collating apparatus which determines whether a first image and a second image are the same, executes a thinning process on the first image, and executes the first image after the thinning process. Image processing means for repeatedly executing dilation processing on the second image and sequentially outputting the first images before and after the dilation processing; and at least one of translation and rotation processing on the second image Is repeatedly executed at predetermined intervals within a preset range, and a first image is output to output a second image after processing.
Conversion means; first storage means for storing the first images before and after the expansion processing output from the image processing means; and each of the first images stored in the first storage means. First matching means for comparing and comparing the image of the second image with the second image to obtain a matching rate; and for each processing of the first conversion means, each of the first and second images stored in the first storage means Calculating means for calculating an average of a plurality of matching rates obtained by comparing and comparing the first image and the second image; and a maximum matching rate among the average of matching rates output from the calculating means. Extracting means for determining at least one of a rate or a minimum matching rate; and determining whether the first image and the second image are the same using at least one of the maximum matching rate or the minimum matching rate output from the extracting means. Determining means for determining Image matching system. 5. An image matching device for determining whether a first image and a second image are the same, wherein a weight given to each pixel of the first image according to the distance from the center line of the pattern is indicated. Image storage means for storing data and the first image; and repeatedly executing at least one of a translation process and a rotation process on the second image at predetermined intervals within a preset range. Output the second image after processing
A first matching unit that compares and matches the first image with the second image and obtains a matching rate by a weighted average operation based on the weight; and a plurality of the first converting units. Extracting means for obtaining at least one of a maximum matching rate or a minimum matching rate from a plurality of matching rates obtained by the above-mentioned processes, and at least one of the maximum matching rate or the minimum matching rate output from the extracting means, An image matching device, comprising: a determination unit configured to determine whether a first image is the same as the second image. 6. The image matching apparatus according to claim 1, wherein at least one of a translation process and a rotation process is performed on the second image at the first initial position in advance. A second conversion means for repeatedly executing the processing every fixed amount within a set range and outputting a processed second image; and for each processing of the second conversion means, the second conversion means Second matching means for comparing and matching the second image output from the first image with the first image to obtain a matching rate; and when the matching rate output from the second matching means is maximum, The second from the first initial position to the current position
And a second storage unit for storing both the parallel movement amount, the rotation angle, or both the parallel movement amount and the rotation angle of the image, wherein the first conversion unit stores the parallel movement amount stored in the second storage unit. A position obtained by adding the movement amount, the rotation angle or the parallel movement amount and the rotation angle to the first initial position is defined as a second initial position, and the second image is moved to the second initial position. An image matching device, wherein at least one of a translation process and a rotation process is performed on the second image. 7. The image collating apparatus according to claim 6, wherein the range set in advance by said first conversion means is determined by said second conversion means.
An image matching apparatus characterized in that the area is smaller than a range set in advance by the conversion means. 8. The image collating apparatus according to claim 6, wherein the second conversion means executes a translation amount, a rotation angle, or a translation amount and a rotation angle per one time performed on the second image. An image collating apparatus, wherein the first conversion unit executes a larger amount of translation or rotation angle or a parallel movement amount or rotation angle per one time performed on the second image. 9. The image collating apparatus according to claim 6, wherein the area of the collation area for which the second collation means finds the matching rate is smaller than the area of the collation area for which the first collation means finds the matching rate. An image collating apparatus characterized in that: 10. An image matching method for determining whether a first image and a second image are the same, wherein a contraction process is repeatedly performed on the first image, and a first image before and after the contraction process is executed. An image processing procedure for sequentially outputting the images, and at least one of a translation process and a rotation process for the second image is repeatedly executed at regular intervals within a preset range. First to output 2 images
And comparing the first image before the contraction processing or after the contraction processing and the second image, which are output for each processing of the image processing procedure, with the second image to obtain a coincidence rate, and A first comparison procedure stored in the first conversion procedure, and a comparison and comparison between the first image before the contraction processing and the second image after the contraction processing for each processing of the first conversion procedure. Calculating an average of the coincidence rates, which is an average value of the plurality of coincidence rates, and storing the average in the memory; and extracting and calculating at least one of the maximum coincidence rate or the minimum coincidence rate from the average of the coincidence rates and storing the same in the memory. And a determining step of determining whether the first image and the second image are the same using at least one of the maximum matching rate and the minimum matching rate. 11. An image matching method for determining whether a first image and a second image are the same, wherein a thinning process is performed on the first image, and the first image after the thinning process is executed. An image processing procedure for repeatedly executing dilation processing on the image and sequentially outputting the first images before and after the dilation processing, and at least one of a translation processing and a rotation processing on the second image Is repeatedly executed at predetermined intervals within a preset range, and a first image is output to output a second image after processing.
And comparing the first image before the dilation processing or the first image after the dilation processing and the second image, which are output for each processing of the image processing procedure, to obtain a matching rate, A first comparison procedure stored in the first conversion procedure, and a comparison and comparison between the first image before and after the dilation processing and the second image for each processing of the first conversion procedure. Calculating an average of the coincidence rates, which is an average value of the plurality of coincidence rates, and storing the average in the memory; and extracting and calculating at least one of the maximum coincidence rate or the minimum coincidence rate from the average of the coincidence rates and storing the same in the memory. And a determining step of determining whether the first image and the second image are the same using at least one of the maximum matching rate and the minimum matching rate. 12. An image matching method for determining whether a first image and a second image are the same, wherein a contraction process is repeatedly performed on the first image, and a first image before and after the contraction process is processed. An image processing procedure for sequentially outputting the images, and at least one of a translation process and a rotation process for the second image is repeatedly executed at regular intervals within a preset range. First to output 2 images
A first storage procedure for storing the first images before and after the contraction processing in a memory; and a first image stored in the first storage procedure and the second image. A first matching procedure of comparing and comparing the images with each other to obtain a matching rate and storing the same in a memory; and for each processing of the first conversion procedure, each first processing stored in the first storage procedure is performed. Calculating an average of a plurality of match rates obtained from the comparison and comparison between the image and the second image, and storing the obtained match rate average in a memory; and a maximum match rate or An extraction procedure of obtaining at least one of the minimum coincidence rates and storing the same in a memory; and determining whether the first image and the second image are the same using at least one of the maximum coincidence rate or the minimum coincidence rate. And an image collating method. 13. An image matching method for determining whether a first image and a second image are the same, wherein a thinning process is performed on the first image, and the first image after the thinning process is executed. An image processing procedure for repeatedly executing dilation processing on the image and sequentially outputting the first images before and after the dilation processing, and at least one of a translation processing and a rotation processing on the second image Is repeatedly executed at predetermined intervals within a preset range, and a first image is output to output a second image after processing.
A first storage procedure for storing the first images before and after the expansion processing in a memory; and a first image stored in the first storage procedure and the second image. A first matching procedure of comparing and comparing the images with each other to obtain a matching rate and storing the same in a memory; and for each processing of the first conversion procedure, each first processing stored in the first storage procedure is performed. Calculating an average of a plurality of match rates obtained from the comparison and comparison between the image and the second image, and storing the obtained match rate average in a memory; and a maximum match rate or An extraction procedure of obtaining at least one of the minimum matching rates and storing the same in a memory; and determining whether the first image and the second image are the same using at least one of the maximum matching rate or the minimum matching rate. And an image collating method. 14. An image matching method for determining whether a first image and a second image are the same, wherein a weight given to each pixel of the first image according to a distance from a center line of the pattern is indicated. An image storage procedure for storing data and the first image in a memory; and at least one of a translation process and a rotation process for the second image are repeated at predetermined intervals within a preset range. Execute the first image to output the processed second image
A first matching procedure in which the first image and the second image are compared and compared, a matching rate is obtained by a weighted average calculation based on the weights, and the matching rate is stored in a memory; An extraction step of obtaining at least one of a maximum match rate or a minimum match rate from a plurality of match rates obtained by a plurality of processes of the conversion procedure and storing the same in a memory; A determining step of determining whether the first image and the second image are the same using at least one of a minimum matching rate. 15. The image matching method according to claim 10, wherein, prior to each step, the second image in the first initial position is selected from a translation process and a rotation process. A second conversion procedure of repeatedly executing at least one process within a preset range for each fixed amount and outputting a processed second image; and for each processing of the second conversion procedure, A second collation procedure for comparing and collating the second image output from the second conversion procedure with the first image to obtain a match rate and storing the same in a memory; and outputting from the second collation procedure. When the obtained coincidence rate becomes the maximum, the second position from the first initial position to the current position
And a second storage procedure for storing both the translation amount and the rotation angle or both the translation amount and the rotation angle of the image in the memory. The first conversion procedure is stored in the second storage procedure. The second image is moved to the second initial position, where the parallel movement amount, the rotation angle or the position obtained by adding the parallel movement amount and the rotation angle to the first initial position is defined as a second initial position. And performing at least one of a translation process and a rotation process on the second image. 16. The image matching method according to claim 15, wherein the range set in advance in the first conversion procedure is the second range.
An image matching method characterized in that the range is smaller than a preset range in the conversion procedure. 17. The image matching method according to claim 15, wherein the translation amount, the rotation angle, or the translation amount and the rotation angle per one time performed on the second image in the second conversion procedure are determined. An image collation method, wherein the amount of translation and the angle of rotation or the amount of translation and rotation each time performed on the second image in the first conversion procedure are larger than each other. 18. The image matching method according to claim 15, wherein an area of the matching area for obtaining the matching rate in the second matching procedure is smaller than an area of the matching area for obtaining the matching rate in the first matching procedure. An image matching method comprising: 19. An image comparison program for determining whether a first image and a second image are the same, wherein a contraction process is repeatedly performed on the first image, and the first image before and after the contraction process is executed. An image processing procedure for sequentially outputting the images, and at least one of a translation process and a rotation process for the second image is repeatedly executed at regular intervals within a preset range. First to output 2 images
And comparing the first image before the contraction processing or after the contraction processing and the second image, which are output for each processing of the image processing procedure, with the second image to obtain a coincidence rate, and A first comparison procedure stored in the first conversion procedure, and a comparison and comparison between the first image before the contraction processing and the second image after the contraction processing for each processing of the first conversion procedure. Calculating an average of the coincidence rates, which is an average value of the plurality of coincidence rates, and storing the average in the memory; and extracting and calculating at least one of the maximum coincidence rate or the minimum coincidence rate from the average of the coincidence rates and storing the same in the memory. An image matching program for causing a computer to execute: a determination step of determining whether the first image and the second image are the same using at least one of the maximum matching rate and the minimum matching rate. . 20. An image matching program for determining whether a first image and a second image are the same, wherein a thinning process is performed on the first image, and the first image after the thinning process is executed. An image processing procedure for repeatedly executing dilation processing on the image and sequentially outputting the first images before and after the dilation processing, and at least one of a translation processing and a rotation processing on the second image Is repeatedly executed at predetermined intervals within a preset range, and a first image is output to output a second image after processing.
And comparing the first image before the dilation processing or the first image after the dilation processing and the second image, which are output for each processing of the image processing procedure, to obtain a matching rate, A first comparison procedure stored in the first conversion procedure, and a comparison and comparison between the first image before and after the dilation processing and the second image for each processing of the first conversion procedure. Calculating an average of the coincidence rates, which is an average value of the plurality of coincidence rates, and storing the average in the memory; and extracting and calculating at least one of the maximum coincidence rate or the minimum coincidence rate from the average of the coincidence rates and storing the same in the memory. An image matching program for causing a computer to execute: a determination step of determining whether the first image and the second image are the same using at least one of the maximum matching rate and the minimum matching rate. . 21. An image matching program for determining whether a first image and a second image are the same, wherein a contraction process is repeatedly performed on the first image, and the first image before and after the contraction process is executed. An image processing procedure for sequentially outputting the images, and at least one of a translation process and a rotation process for the second image is repeatedly executed at regular intervals within a preset range. First to output 2 images
A first storage procedure for storing the first images before and after the contraction processing in a memory; and a first image stored in the first storage procedure and the second image. A first matching procedure of comparing and comparing the images with each other to obtain a matching rate and storing the same in a memory; and for each processing of the first conversion procedure, each first processing stored in the first storage procedure is performed. Calculating an average of a plurality of match rates obtained from the comparison and comparison between the image and the second image, and storing the obtained match rate average in a memory; and a maximum match rate or An extraction procedure of obtaining at least one of the minimum coincidence rates and storing the same in a memory; and determining whether the first image and the second image are the same using at least one of the maximum coincidence rate or the minimum coincidence rate. And causing the computer to execute the steps. Image matching program. 22. An image matching program for determining whether a first image and a second image are the same, wherein a thinning process is performed on the first image, and the first image after the thinning process is executed. An image processing procedure for repeatedly executing dilation processing on the image and sequentially outputting the first images before and after the dilation processing, and at least one of a translation processing and a rotation processing on the second image Is repeatedly executed at predetermined intervals within a preset range, and a first image is output to output a second image after processing.
A first storage procedure for storing the first images before and after the expansion processing in a memory; and a first image stored in the first storage procedure and the second image. A first matching procedure of comparing and comparing the images with each other to obtain a matching rate and storing the same in a memory; and for each processing of the first conversion procedure, each first processing stored in the first storage procedure is performed. Calculating an average of a plurality of match rates obtained from the comparison and comparison between the image and the second image, and storing the obtained match rate average in a memory; and a maximum match rate or An extraction procedure of obtaining at least one of the minimum coincidence rates and storing the same in a memory; and determining whether the first image and the second image are the same using at least one of the maximum coincidence rate or the minimum coincidence rate. And causing the computer to execute the steps. Image matching program. 23. An image matching program for judging whether a first image and a second image are the same, and showing a weight given to each pixel of the first image according to the distance from the center line of the pattern. An image storage procedure for storing data and the first image in a memory; and at least one of a translation process and a rotation process for the second image are repeated at predetermined intervals within a preset range. Execute the first image to output the processed second image
A first matching procedure in which the first image and the second image are compared and matched, a matching rate is obtained by a weighted average operation based on the weight, and the matching rate is stored in a memory; An extraction step of obtaining at least one of a maximum match rate or a minimum match rate from a plurality of match rates obtained by a plurality of processes of the conversion procedure and storing the same in a memory; An image matching program for causing a computer to execute a determining step of determining whether the first image and the second image are the same using at least one of a minimum matching rate. 24. The image collation program according to claim 19, wherein, prior to each of the steps, the second image at the first initial position is selected from a translation process and a rotation process. A second conversion procedure of repeatedly executing at least one process within a preset range for each fixed amount and outputting a processed second image; and for each processing of the second conversion procedure, A second collation procedure for comparing and collating the second image output from the second conversion procedure with the first image to obtain a coincidence rate and storing the same in a memory; and outputting from the second collation procedure. When the obtained coincidence rate becomes the maximum, the second position from the first initial position to the current position
And a second storage procedure of storing both the translation amount and the rotation angle or both the translation amount and the rotation angle of the image in the memory. The first conversion procedure is performed in the second storage procedure. The second image is moved to the second initial position with the stored parallel movement amount, rotation angle, or position obtained by adding the parallel movement amount and the rotation angle added to the first initial position as a second initial position. An image matching program for executing at least one of a translation process and a rotation process on the second image; 25. The image matching program according to claim 24, wherein the range set in advance in the first conversion procedure is the second range.
An image matching program characterized in that the size is smaller than a preset range in the conversion procedure. 26. The image matching program according to claim 24, wherein the translation amount, the rotation angle, or the translation amount and the rotation angle per one time performed on the second image in the second conversion procedure are determined. An image collation program, wherein the amount of translation and the angle of rotation, or the amount of translation and rotation, each time executed for the second image in the first conversion procedure are larger than the amount of translation and rotation. 27. The image matching program according to claim 24, wherein the area of the matching area for obtaining the matching rate in the second matching procedure is smaller than the area of the matching area for obtaining the matching rate in the first matching procedure. An image collation program characterized by performing: 28. A recording medium on which the image collation program according to claim 19 is recorded.