JPH11134498A - Pattern collating device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To eliminate the influence of a background or stain as much as possible and to improve a recognition rate by adopting differences in a gradation value between a pattern image and a background image, and collating an image only of registered patterns and an image only of collated patterns. SOLUTION: At the time of fingerprint registering, a control part 20-1 fetches the image on a prism 10-32 with a frame memory 20-5 as a background image in a state where a light source 10-31 is turned on and a finger is not placed on a fingerprint sensor 10-3. Then, a user puts the finger on a prism 10-32 and fetches it as a registered fingerprint image A including the background. After that, difference in the gradation value between the registered fingerprint image A and the background image B is adopted so as to obtain an image C of only a registered fingerprint. At the time of a fingerprint collation, the finger is put on the prism 10-32, the fingerprint is obtained in the same way as that of registering and it is fetched as a collated fingerprint image D including the background. Difference between the collated fingerprint image D and the background image B is adopted so as to obtain the image E of only a collated fingerprint. Then, the fingerprint is collated based on the images C and E.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a pattern matching device for matching a registered pattern with a matching pattern.

[0002]

2. Description of the Related Art In recent years, in fields requiring personal recognition such as access control to computer rooms and important machine rooms, access control to computer terminals and financial terminals of banks, etc.
A voice collation device and a fingerprint collation device are being adopted in place of conventional passwords and ID cards.

[Prior application] The applicant of the present application has previously filed Japanese Patent Application No. 7-1.
No. 08526 proposes a “pattern matching device”. In this pattern matching device, two-dimensional discrete Fourier transform is performed on the image data (two-dimensional pattern data) of the matching fingerprint to create matching Fourier image data. And
The matching Fourier image data is combined with the registered Fourier image data of the registered fingerprint created by performing the same processing, and the combined Fourier image data is subjected to amplitude suppression processing (log processing). Perform a discrete Fourier transform. Then, from the predetermined correlation component area appearing in the synthesized Fourier image data subjected to the two-dimensional discrete Fourier transform, upper n pixels having a higher intensity of the correlation component are extracted, and the intensity of the correlation component of the extracted n pixels is extracted. Is used as a correlation value and compared with a threshold value. If the correlation value is higher than the threshold value, it is determined that the registered fingerprint matches the collation fingerprint.

However, in the prior application, although it is hardly affected by the change in illuminance of the input image, a slight change in shading in the background of the image data of the registered fingerprint and the image data of the verification fingerprint is also taken in as identification information. For this reason,
Immediately after registration, for example, if there is dirt on the surface of the prism of the fingerprint input device, the background information also matches with the fingerprint of another person, and the correlation value becomes higher and may exceed the threshold value. There is a possibility that the person and another person are erroneously determined to be the same.

[Prior application] Then, the present applicant has filed Japanese Patent Application No.
No. 219759 proposes a pattern matching device capable of removing the influence of the background and increasing the recognition rate.
In this pattern matching device, the image data of the matching fingerprint is
After performing a background separation process such as cutting a low illuminance portion or converting a low illuminance portion into white noise, a two-dimensional discrete Fourier transform is performed to obtain collation Fourier image data. For example, if the optical system of the fingerprint input system is configured by the optical path separation method,
Where the prism touches the finger placement surface (the ridge of the finger) appears bright, and where it does not touch (the valley or the background of the finger) appears dark, so it is necessary to cut off the low-light portions corresponding to the background. A value is set, and a value below this threshold is forcibly set to 0. Then, the registered Fourier image data created by performing the same processing as the collated Fourier image data is synthesized, and the registered fingerprint and the collated fingerprint are collated in the same manner as in the prior application.

[0006]

However, even in the case of this prior application, variations in the optical system of the fingerprint input unit (fingerprint sensor) at the time of manufacturing (some backgrounds appear brighter than the threshold value) and prisms do not. Finger dirt on the finger placement surface (ring-shaped dirt generated on the contour of the finger) may remain as noise, resulting in poor recognition performance.

SUMMARY OF THE INVENTION The present invention has been made to solve such a problem, and an object of the present invention is to reduce the influence of background and dirt as much as possible and to further improve the recognition rate. It is to provide a device.

[0008]

In order to achieve such an object, a first invention (an invention according to claim 1) includes a background image capturing means for capturing a background image before pattern input, and a background image. A first background separating unit that obtains a difference in gray value between the registered pattern image and the background image and obtains only the registered pattern as an image; and obtains a difference in gray value between the comparison pattern image including the background image and the background image. A second background separating unit that uses only the matching pattern as an image, and a pattern matching unit that performs matching between the registered pattern only image and the matching pattern only image are provided. According to the present invention, an image of only a registered pattern is created by taking a difference in gray value between a registered pattern image including a background image and a background image before pattern input, and a matching pattern image including a background image and a pattern image before pattern input are created. The image of only the matching pattern is created by taking the difference between the grayscale values of the background image and the image of the created matching pattern and the image of the matching pattern only.

The second invention (the invention according to claim 2) is the first invention.
In the present invention, a contrast pattern image including a background image and a background immediately before the input of the matching pattern are obtained by taking a difference in gray value between the registered pattern image including the background image and the background image immediately before the input of the registered pattern. The difference of the gray value from the image is obtained, and only the collation pattern is used as the image. According to the present invention, only the registered pattern image is created by taking the difference in the gray value between the registered pattern image including the background image and the background image immediately before the input of the registered pattern, and the matching pattern image including the background image and the matching pattern The image of only the matching pattern is created by taking the difference in the gray value from the background image immediately before the input, and the created image of only the registered pattern and the image of only the matching pattern are compared.

The third invention (the invention according to claim 3) is the first invention.
In the second aspect, when the average value of the grayscale values of the input image before the pattern input satisfies a predetermined criterion,
The input image is taken in as a background image. According to the present invention, if the average value of the grayscale values of the input image before the pattern input does not satisfy the predetermined criterion, the input image is not taken in as the background image. A fourth invention (an invention according to a fourth invention) is the third invention, wherein, when the average value of the grayscale values of the input image before the pattern input is less than a predetermined judgment criterion, the input operation of the temporary pattern is stopped and then the second pattern is again performed. An operation instruction is given to perform an input operation. According to the present invention, if the average value of the grayscale values of the input image before the pattern input does not satisfy the predetermined criterion, an instruction such as “place your finger at the correct position. <Cleaning the glass surface>” is issued. It is.

The fifth invention (the invention according to claim 5) is the first invention.
In the fourth invention, when calculating the difference between the gray value of the registered pattern image including the background image and the background image before the input of the registered pattern, the gray value of a pixel whose difference is equal to or less than a predetermined value is set to the minimum value or the maximum value. When calculating the difference in gray value between the matching pattern image including the background image and the background image before the input of the matching pattern, the gray value of a pixel whose difference is equal to or less than a predetermined value is replaced with a minimum value or a maximum value. It was made. According to the present invention, when calculating the difference between the gray value of the registered pattern image including the background image and the background image before the input of the registered pattern, the pixel whose difference is equal to or less than the predetermined value has the minimum or maximum gray value. Is replaced by the value. Further, when calculating the difference in the gray value between the registered pattern image including the background image and the background image before the pattern input, the pixel whose difference is equal to or less than a predetermined value is replaced with the minimum value or the maximum value of the gray value. As a result, an image of only the registered pattern and an image of only the verification pattern are obtained in which the contrast between the pattern and the other images is clear.

[0012]

DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described in detail based on embodiments. FIG. 2 is a block diagram of a fingerprint matching device according to an embodiment of the present invention. In FIG. 1, reference numeral 10 denotes an operation unit, and reference numeral 20 denotes a control unit. The operation unit 10 includes a numeric keypad 10-1, a display (LCD).
A fingerprint sensor 10-3 is provided together with 10-2.
The fingerprint sensor 10-3 includes a light source (LED) 10-31, a prism 10-32, and a CCD camera 10-33. The control unit 20 includes a control unit 20-1 having a CPU, a ROM 20-2, a RAM 20-3, a hard disk (HD) 20-4, and a frame memory (F).
M) 20-5, an external connection unit (I / F) 20-6, and a Fourier transform unit (FFT) 20-7.
A registration program and a collation program are stored in M20-2.

[Registration of Fingerprint] In this fingerprint collating apparatus, the fingerprint of the user is registered as follows. That is,
Before operation, the user turns on the power and turns on the light source 10-.
31 is turned on (step 301 shown in FIG. 3). At this time, on the prism 10-32 of the fingerprint sensor 10-3,
Do not put your finger yet. Then, the control unit 20-1 sets the image on the prism 10-32 at this time as a background image candidate.
Captured via the frame memory 20-5 (step 3
02). Then, the average value M of the grayscale values of the image area of the captured background image candidate is obtained (step 303).

The control unit 20-1 compares the obtained average value M of the grayscale values of the background image candidate with a predetermined value a (step 304). If M <a, the background image candidate is compared with the background image candidate. Captured as B (step 305). In this embodiment, the optical system is configured by the optical path separation method, and the place where the finger rests on the finger placement surface of the prism 10-32 (the ridge of the finger) appears bright, and the place where it does not contact (the finger valley). (Lines and backgrounds) appear dark. That is, in this embodiment, by setting the predetermined value a as an appropriate value, a background image candidate having an average value M of the shading values smaller than the predetermined value a is fetched as a background image B containing no noise.

In the case where the optical system is constructed by the total reflection method, the portion that comes into contact with the finger mounting surface of the prism 10-32 (the ridge of the finger) appears dark, and the portion that does not come into contact (the valley line of the finger or the like). Background) is bright. Therefore, in this case, by setting the predetermined value a as an appropriate value, a background image candidate having an average value M of the shading values exceeding the predetermined value a is taken in as a background image B containing no noise.

In step 304, if M ≧ a, it is determined whether a finger is already placed on the prism 10-32.
Alternatively, it is determined that the finger placement surface of the prism 10-32 is dirty, and the process proceeds to step 306. In step 306, the control unit 20-1 additionally displays a message (“Place your finger at the correct position. <Clean glass surface>”) as shown in FIG. 5 on the display 10-2. In this case, a similar message may be given by voice. In this embodiment, at the time of the initial state, the background image B has an average background value. Therefore,
If M ≧ a in step 304, an average background value is used as the background image B at the time of initializing,
After the initial time, the previous background image B is used.

Next, the user inputs the ID number assigned to the user using the numeric keypad 10-1 (FIG. 4).
Step 401), a finger is placed on the prism 10-32 of the fingerprint sensor 10-3. The prism 10-32 is irradiated with light from the light source 10-31, and since the optical system is configured by the optical path separation method, the valley portion of the fingerprint is dark,
At the ridges, bright and contrast fingerprint patterns are collected. The pattern of this collected fingerprint (registered fingerprint) is A
By the / D conversion, as a grayscale image (image data: two-dimensional pattern data) of 320 × 400 pixels and 256 gradations,
It is provided to the control unit 20.

The control unit 20-1 stores the image data of the registered fingerprint provided by the operation unit 10 in the frame memory 20-
Then, the image is taken in as a registered fingerprint image A including a background image through Step 5 (Step 402). Then, the difference between the gray value of the registered fingerprint image A and the background image B is calculated, and only the registered fingerprint image C is obtained.
(C = AB) is obtained (step 403). However, the difference between the grayscale values of the registered fingerprint image A and the background image B is a predetermined value b.
If there is the following pixel C (x, y), the gray value of that pixel is set to the minimum value (= 0). At this time, the pixel C
The gray value of (x, y) may be set to the maximum value.
As a result, only the registered fingerprint in which the contrast between the registered fingerprint and the other images is clear is obtained, and the matching accuracy is improved.

Then, the control unit 20-1 performs a reduction process on the image C of only the registered fingerprint (step 404).
In this reduction processing, the original image data of 320 × 400 pixels and 256 gradations is thinned out by 4 pixel bits in the x direction (horizontal direction) by excluding the left and right ends by 32 pixels, thereby obtaining the y direction ( 8) for the top and bottom edges
This is performed by thinning out at a three-pixel pitch except for each pixel.
As a result, the image C of only the registered fingerprint is reduced to image data of 64 × 128 pixels and 256 gradations (see FIG. 6).

Then, the control unit 20-1 sends the reduced registered fingerprint only image C (see FIG. 1A) to the Fourier transforming unit 20-7, and converts the registered fingerprint only image C into a two-dimensional discrete Fourier Perform a transform (DFT) (Step 40)
5). Thus, the registered fingerprint only image C shown in FIG. 1A becomes Fourier image data (registered Fourier image data) as shown in FIG. 1B. Control unit 20-
1 creates a file of the Fourier image data as original image data of the registered fingerprint (only the registered fingerprint is a Fourier image) C 'in the hard disk 20-4 in association with the ID number (step 406).

The two-dimensional discrete Fourier transform is described in, for example, "Introduction to Computer Image Processing, edited by Japan Industrial Technology Center, published by Soken Shuppan Co., Ltd., pp. 44-45 (Document 1)". .

[Fingerprint Verification] In this fingerprint verification apparatus, verification of a user's fingerprint is performed as follows. That is, the user turns on the power and turns on the light source 10-31. At this time, the prism 10- of the fingerprint sensor 10-3
Do not place your finger on 32 yet. Then, the control unit 20-
1 captures the background image B according to the flowchart shown in FIG.

Next, the user inputs the ID number assigned to the user using the numeric keypad 10-1 (see FIG. 7).
Step 701), a finger is placed on the prism 10-32 of the fingerprint sensor 10-3. As a result, in the same manner as in the case of fingerprint registration, the pattern of the collected fingerprint (collation fingerprint) is converted into a grayscale image (image data: two-dimensional pattern data) having 320 × 400 pixels and 256 gradations. Given to.

When the control unit 20-1 receives the ID number via the numeric keypad 10-1, the control unit 20-1 sends the ID number to the hard disk 20-.
From the registered fingerprint stored in the file 4, the original image data of the registered fingerprint (only the registered fingerprint is a Fourier image) C ′ corresponding to the ID number is read (step 702).

The control unit 20-1 stores the image data of the collation fingerprint given from the operation unit 10 in the frame memory 20.
Via -5, it is captured as a collation fingerprint image D including a background image (step 703). Then, the difference between the gray values of the collation fingerprint image D and the background image B is obtained, and only the collation fingerprint image E (E = D−B) is obtained (step 704). However,
If there is a pixel E (x, y) in which the difference in gray value between the verification fingerprint image D and the background image B is equal to or smaller than the predetermined value b, the gray value of that pixel is set to the minimum value (= 0). At this time, the pixel E
The gray value of (x, y) may be set to the maximum value.
As a result, the image E is obtained only for the collation fingerprint in which the contrast between the collation fingerprint and the other images is clear, and the collation accuracy is improved.

Then, the control unit 20-1 performs the same reduction processing as that performed in step 404 on the image E only for the collated fingerprint (step 705). As a result, the image E of only the verification fingerprint is reduced to image data of 64 × 128 pixels and 256 gradations.

The control unit 20-1 sends the reduced verification fingerprint only image E (see FIG. 1 (e)) to the Fourier transforming unit 20-7, and converts the verification fingerprint only image E into a two-dimensional discrete Fourier transform. Transform (DFT) (Step 70)
6). Accordingly, the image E of only the collation fingerprint shown in FIG. 1E becomes Fourier image data (collation Fourier image data) as shown in FIG.

Next, the control unit 20-1 uses the Fourier image data as the original image data of the collated fingerprint (only the collated fingerprint is a Fourier image) E ', and reads out the Fourier image E' only of the collated fingerprint in step 702. Only the registered fingerprint is combined with the Fourier image C ′ (step 707) to obtain combined Fourier image data.

Here, the synthesized Fourier image data is expressed as A · e ^j θ where the Fourier image data of the collation fingerprint is A · e ^j θ and A · B when the Fourier image data of the registered fingerprint is B · e ^j φ.
-It is expressed by e ^{j (} θ ^- φ ⁾ . However, A, B, θ, and φ are all functions of the frequency (Fourier) space (u, v).

[0030] ^{and, A · B · e j (} θ - φ) ^{is, A · B · e j (} θ - φ) = A · B · cos (θ-φ) + j · A · B · sin (θ- φ) (1) where A · e ^j θ = α ₁ + jβ ₁ , B · e ^j φ =
When _{α 2 + jβ 2, A =} (α 1 2 + β 1 2) 1/2, B =
_{^{(Α 2 2 + β 2 2}} ) 1/2, θ = tan -1 (β 1 / α 1), φ =
tan ^-1 (β ₂ / α ₂ ). By calculating this equation (1), synthetic Fourier image data is obtained.

Note that A.B.e ^{j (} θ ^- φ ⁾ = A.B.e ^j
θ ・ e- ^j φ = A ・ e ^j θ ・ B ・ e- ^j φ = (α ₁ + j
β ₁ ) · (α ₂ −jβ ₂ ) = (α ₁ · α ₂ + β ₁ ·
The combined Fourier image data may be obtained as β ₂ ) + j (α ₂ β ₁ −α ₁ β ₂ ).

After obtaining the synthesized Fourier image data in this way, the control unit 20-1 performs an amplitude suppression process (step 708). In this embodiment, log processing is performed as amplitude suppression processing. That is, an arithmetic equation of synthesized Fourier image data described above ^{A · B · e j (θ} -
φ ⁾ is taken as log (A · B) · ej ⁽ θ ⁻ φ ⁾ , so that the amplitude A · B is log (A · B)
(A · B> log (A · B)).

FIG. 1D shows the synthesized Fourier image data after the amplitude suppression processing. In the synthesized Fourier image data subjected to the amplitude suppression processing, the influence of the illuminance difference between when the registered fingerprint is collected and when the verification fingerprint is collected is reduced. That is, by performing the amplitude suppression processing, the spectrum intensity of each pixel is suppressed, there is no outstanding value, and more information becomes effective. In addition, by performing amplitude suppression processing, feature points (end points, branch points) and ridge features (vortex, branch), which are personal information, are more emphasized in the fingerprint information, and ridges, which are general fingerprint information, are emphasized. The overall flow and direction can be suppressed.

In this embodiment, log processing is performed as amplitude suppression processing. However, Δ processing may be performed. In addition to log processing and √ processing,
Any processing may be used as long as the amplitude can be suppressed. If all the amplitudes are set to, for example, 1 in the amplitude suppression, that is, if only the phase is used, there is an advantage that the amount of calculation can be reduced and an amount of data can be reduced as compared with the log processing or the √ processing.

After performing the amplitude suppression processing in step 708, the control unit 20-1 sends the synthesized Fourier image data subjected to the amplitude suppression processing to the Fourier transformation unit 20-7.
A second two-dimensional discrete Fourier transform (DFT) is performed (step 709). Thus, the combined Fourier image data shown in FIG. 1D becomes the combined Fourier image data shown in FIG.

Then, the control unit 20-1 executes step 70
9 is obtained, the intensity (amplitude) of the correlation component of each pixel in the predetermined correlation component area is scanned from the synthesized Fourier image data, and a histogram of the intensity of the correlation component of each pixel is obtained. The upper n pixels (8 pixels in this embodiment) having a higher correlation component intensity are extracted from the histogram, and the average of the extracted correlation component intensities of the n pixels is obtained as a correlation value (score) (step 710). . Here, the correlation component area is shown in FIG.
With respect to the synthesized Fourier image data shown in (h), it is defined as a region S0 surrounded by a white dotted line.

Then, the control section 20-1 executes step 71
The correlation value obtained at 0 is compared with a predetermined threshold value (step 711).
It is determined that the registered fingerprint and the matching fingerprint match (step 7).
12), a message to that effect is displayed and the output for the electric lock is transmitted. If the correlation value is less than the threshold value, it is determined that the registered fingerprint and the collation fingerprint do not match (step 713), the fact is displayed, and the process returns to step 701.

Note that, in this embodiment, from the pixels in the correlation component area S0, the upper n
Although the pixels are extracted and the average is used as the correlation value, the sum of the intensities of the correlation components of the upper n pixels may be used as the correlation value. Further, the intensities of the correlation components of all the pixels exceeding the threshold value may be added, and the added value may be used as the correlation value, or the average of the added values may be used as the correlation value. If at least one of the intensities of the correlation components of each pixel is equal to or greater than the threshold value, it may be determined that “match”.
If the number is equal to or more than one, various judgment methods such as judging “match” can be considered.

In this embodiment, the two-dimensional discrete Fourier transform is performed in the Fourier transform unit 20-7, but may be performed in the CPU 20-1. In this embodiment, the reduction processing is performed on the image data of the registered fingerprint in step 404.
The reduction processing may be performed at a stage after reading the Fourier image data of the registered fingerprint (between steps 702 and 703). Further, it is not always necessary to perform the reduction processing on the image data of the registered fingerprint or the collated fingerprint, and the Fourier image data may be created using the input image data as it is. If the reduction processing is performed, the capacity of the image memory used for processing the input image data can be reduced accordingly.

In this embodiment, the two-dimensional discrete Fourier transform is performed in step 709 shown in FIG. 7, but the two-dimensional discrete inverse Fourier transform is performed instead of the two-dimensional discrete Fourier transform. You may do so. That is, instead of performing two-dimensional discrete Fourier transform on the synthesized Fourier image data subjected to the amplitude suppression processing,
A dimensional discrete inverse Fourier transform may be performed. 2
The matching accuracy between the two-dimensional discrete Fourier transform and the two-dimensional discrete inverse Fourier transform does not change quantitatively. The two-dimensional discrete inverse Fourier transform is described in the aforementioned reference 1.

Further, in this embodiment, the amplitude suppression processing is performed in step 708 shown in FIG. 7, but the amplitude suppression processing may be omitted. By performing the amplitude suppression processing in step 708, the influence of the illuminance difference between the time when the registered fingerprint is collected and the time when the verification fingerprint is collected in the synthesized Fourier image data is reduced. , Bifurcation points) and features of ridges (vortices, bifurcations) are further emphasized, and the matching accuracy is significantly improved.

In this embodiment, the two-dimensional discrete Fourier transform is performed by performing amplitude suppression processing on the synthesized Fourier image data (step 70).
8, 709), and may be combined after performing amplitude suppression processing on the Fourier image data of the registered fingerprint and the collated fingerprint before combining, respectively. That is, as shown in FIG. 8A, a step 407 for performing amplitude suppression processing is provided between steps 405 and 406 in FIG. 4, and as shown in FIG. 8B, steps 707 and 708 in FIG. May be replaced.

In this case, the Fourier image data (registered Fourier image data) of the registered fingerprint subjected to the amplitude suppression process as shown in FIG. 1C is obtained by the amplitude suppression process of step 407. 707 and 708
As a result, Fourier image data (collation Fourier image data) of the collation fingerprint subjected to the amplitude suppression processing as shown in FIG. Then, the Fourier image data of the registered fingerprint and the verification fingerprint subjected to the amplitude suppression processing are combined, and combined Fourier image data as shown in FIG. 1D is obtained.

At this time, the suppression rate of the amplitude of the combined Fourier image data is smaller than the case where the amplitude suppression processing is performed on the synthesized Fourier image data (FIG. 7). Therefore,
When the amplitude suppression processing is performed on the synthesized Fourier image data (FIG. 7), the matching accuracy is improved as compared with the method of performing amplitude suppression processing and then generating the synthesized Fourier image data (FIG. 8). In the case where the synthesized Fourier image data is obtained after performing the amplitude suppression process (FIG. 8), the synthesized Fourier image data is not subjected to the two-dimensional discrete Fourier transform, but to the two-dimensional discrete inverse Fourier transform. You may.

For reference, FIG. 9 shows each image of the fingerprint collation process when the collation fingerprint is another person, corresponding to FIG. FIG.
Are the images in the fingerprint collation process when the collation fingerprint is the principal, and the correlation component area S when the collation fingerprint is the principal.
A portion where the intensity of the correlation component is high occurs at 0, but does not occur when the verification fingerprint is another person.

In this embodiment, the case of performing fingerprint collation has been described as an example. However, the present invention can be similarly applied to the case of performing voiceprint collation, and can be handled as image data regardless of fingerprints and voiceprints. It can be used for collation of various two-dimensional patterns that can be performed. Further, the present invention is not limited to the two-dimensional pattern collation, and the same can be applied to the N-dimensional pattern collation such as a one-dimensional pattern or a three-dimensional pattern.

In this embodiment, the two-dimensional pattern is obtained as an image. However, it is not always necessary to obtain the two-dimensional pattern as an image. For example, a vibration detector is two-dimensionally arranged at each location, and a two-dimensional pattern (seismic wave) obtained by the two-dimensionally arranged vibration detector is used as a collation pattern, which is collated with a pattern registered in advance. You may do so. In addition, a flow measuring device is two-dimensionally arranged at each part, and a two-dimensional pattern (flow distribution) obtained by the two-dimensionally arranged flow measuring device is set as a collation pattern, and collated with a pre-registered pattern. You may make it.

[0048]

As is apparent from the above description, according to the present invention, in the first invention, registration is performed by taking a difference in gray value between a registered pattern image including a background image and a background image before pattern input. An image of only the pattern is created, an image of only the matching pattern is created by taking the difference in the gray value between the matching pattern image including the background image and the background image before the pattern input, and the created registered pattern only image and the matching pattern are created. Only the collation with the image is performed, so that the influence of the background and dirt can be eliminated as much as possible, and the recognition rate can be further increased, so that the collation accuracy is remarkably improved.
In the second invention, only the registered pattern image is created by taking the difference in the gray value between the registered pattern image including the background image and the background image immediately before the input of the registered pattern, and the matching pattern image including the background image and the matching pattern input are created. The image of only the matching pattern is created by taking the difference in the gray value from the immediately preceding background image, and the created image of only the registered pattern is compared with the image of only the matching pattern. Thus, it is possible to respond to changes in the background and dirt.

According to the third aspect of the present invention, if the average value of the grayscale values of the input image before the pattern input does not satisfy the predetermined criterion, the input image is not taken in as the background image. It is possible to prevent the included image from being taken in as a background image, and to prevent a failure such as disappearing of a pattern when calculating a difference in gray value between the pattern image including the background image and the background image. In the fourth aspect, if the average value of the grayscale values of the input image before the pattern input does not satisfy the predetermined criterion, an instruction such as “place your finger at the correct position. <Clean glass surface>” is issued. Therefore, the operator need not be confused. In the fifth invention, only the registered pattern image and only the collation pattern image in which the contrast between the pattern and the other image is clear are obtained, and the collation accuracy is improved.

[Brief description of the drawings]

FIG. 1 is a diagram illustrating a fingerprint matching process in a fingerprint matching device according to the present invention.

FIG. 2 is a block diagram of the fingerprint matching device.

FIG. 3 is a flowchart illustrating an operation of capturing a background image in the fingerprint collation apparatus.

FIG. 4 is a flowchart for explaining a fingerprint registration operation in the fingerprint matching device.

FIG. 5 is a diagram illustrating a message additionally displayed on a display;

FIG. 6 is a diagram illustrating a reduction process on image data.

FIG. 7 is a flowchart for explaining a fingerprint matching operation in the fingerprint matching device.

FIG. 8 is a flowchart for explaining another example of the fingerprint registration operation and the fingerprint collation operation.

FIG. 9 is a diagram showing each image in a fingerprint matching process when the matching fingerprint is another person, corresponding to FIG. 1;

[Explanation of symbols]

10 operation section, 20 control section, 10-1 numeric keypad, 10-2 display (LCD), 10-3 ...
Fingerprint sensor, 10-31: light source, 10-32, prism, 10-33: CCD camera, 20-1: control unit, 2
0-2 ROM, 20-3 RAM, 20-4 Hard disk (HD), 20-5 Frame memory (F
M), 20-6: external connection unit (I / F), 20-7: Fourier transform unit (FFT).

Claims (5)

[Claims] 1. A background image capturing means for capturing a background image before a pattern is input, and a first background separation for obtaining a difference in gray level between a registered pattern image including the background image and the background image to obtain only a registered pattern image. Means, a second background separating means for obtaining a difference in gray level between the matching pattern image including the background image and the background image and setting only the matching pattern as an image; and A pattern matching device comprising: pattern matching means for performing matching. 2. The image processing apparatus according to claim 1, wherein the first background separating means obtains only the registered pattern by taking a difference in gray value between the registered pattern image including the background image and the background image immediately before the input of the registered pattern. 2. A pattern matching device, wherein the background separating means obtains only a matching pattern image by calculating a difference in gray level between the matching pattern image including the background image and the background image immediately before the input of the matching pattern. 3. The image processing apparatus according to claim 1, wherein the background image capturing unit is configured to determine whether an average value of the grayscale values of the input image before the pattern input satisfies a predetermined criterion.
A pattern matching device characterized by taking in the input image as a background image. 4. The operation instruction according to claim 3, wherein when the average value of the grayscale values of the input image before the pattern input is less than a predetermined judgment criterion, the input operation of the temporary pattern is stopped and then the input operation is performed again. A pattern matching device comprising an operation instructing means for giving the following. 5. The method according to claim 1, wherein the first background separating unit calculates a difference in gray value between the registered pattern image including the background image and the background image before the input of the registered pattern. At this time, the grayscale value of the pixel whose difference is equal to or less than a predetermined value is replaced with a minimum value or a maximum value, and the second background separation means performs shading between the collation pattern image including the background image and the background image before the collation pattern input. A pattern matching apparatus characterized in that, when calculating a difference between values, a grayscale value of a pixel whose difference is equal to or smaller than a predetermined value is replaced with a minimum value or a maximum value.