JP2002298126A - Method and device for determining input fingerprint state - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a method and a device for determining the input fingerprint state to determine whether or not the input fingerprint image is suitable for authentication capable of correctly determining with a simple configuration whether or not the fingerprint input from a fingerprint information input unit is suitable for the fingerprint authentication without image processing requiring a long time of calculation. SOLUTION: The input fingerprint image is divided into fine areas of the predetermined size to determine whether or not the fingerprint comprising raised lines and valley lines is present in each finely divided area, and the state of the skin surface in the finely divided area is determined. Whether or not the fingerprint image is suitable for the fingerprint authentication is determined from the result of determination of the fingerprint presence in each area and the result of the state determination.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

[0001] 1. Field of the Invention [0002] The present invention relates to a method and an apparatus for determining an input fingerprint state.

In recent years, personal authentication devices using fingerprints have been put to practical use and used. However, in personal authentication systems based on biometrics (biological information) using fingerprints, finger roughness, dry fingers, wet fingers, etc. If a fingerprint that is not suitable for fingerprint authentication is input for creating registration template data due to factors such as a thin input fingerprint, data that is not suitable as a registration template may be created. Also, when a similar fingerprint is input for personal authentication, it is possible that the matching rate for authenticating the user cannot be cleared.

[0003] The present invention provides a method for determining whether an input image is suitable for fingerprint authentication without performing image processing which is generally said to take a long time such as thinning an image obtained from a fingerprint sensor at a software level. At the same time, fingerprints that are not suitable for fingerprint authentication are dry, wet, rough,
The present invention relates to a method for determining a fingerprint state such as a thin finger.

[0004]

2. Description of the Related Art As a conventional technique for judging the state of a finger, for example, there is a "fingerprint recognition discriminating apparatus and a dry finger detection method" disclosed in Japanese Patent Application Laid-Open No. Hei 5-309082. This method is shown as the configuration of the conventional example shown in FIG. In this conventional example, a finger 81 is placed on a fingerprint detection unit 80, a resistance value is converted into a voltage value by a resistance value detection electrode 82, a digital signal is converted by an A / D converter or a comparator 83, and the finger is determined by the CPU 84. It measures the degree of drying or wetting. However, in the method of this conventional example, detection is performed by hardware. To change the degree of dryness or wetness to be detected, hardware (resistance value detection electrode 82, A / D converter or comparator 83) is used.
Etc.) must be changed, which inevitably increases costs.

In order to avoid this, it is conceivable to control by software whether or not an image obtained by an existing fingerprint sensor is taken. For example, as a timing for capturing an input fingerprint, a process of permitting capture only with the area of the input image can be considered. Specifically, the image input from the fingerprint information input unit is subdivided (blocked) into a predetermined size, and the histogram of each block is calculated. The histogram can be obtained by obtaining the number of pixels distributed in each lightness by setting the lightness of the pixels in each block to 256 for black and 0 for black, and the average value of the histogram clears a predetermined threshold. , It is recognized that fingerprints (ridge lines (peak lines) and valley lines) exist on the block. If the ratio between the total number of block divisions and the number of blocks in which the fingerprint is present satisfies the predetermined threshold value, the image is taken in assuming that the fingerprint is present in the input image, and the user is authenticated.

FIG. 16 shows an example of a fingerprint image used for explaining a conventional example. This image is 300 pixels vertically with 256 tones ×
It is a square of 300 pixels horizontally. This image is subdivided, and the size of one block to be subdivided can be appropriately compared with the ratio of the total number of blocks to the number of blocks where data existed. If only care is taken that the effect is not affected, then the block may be arbitrarily sized. For example, in the case of an image as shown in FIG. 16 (height: 300 pixels × width: 300 pixels), a total of 225 blocks of 15 blocks in length and width may be used. In this case, the size of one block is 400 pixels of 20 pixels × 20 pixels. FIG. 17 shows a state where the image of FIG. 14 is subdivided.

Next, a histogram of each block is calculated, and an average value of the histogram is obtained. For example, FIG.
18 shows the pixel distribution of the two blocks, and FIG. Indicates the seventh block in the seventh column of FIG. 17, in which ridges and valleys definitely exist. The average value of the histogram for this block is about 210. vice versa,
B. of FIG. In the 13th block in the 14th column of FIG. 17, although data exists, it is difficult to determine that ridges (convex lines) and valley lines (concave lines) exist. The average value of the histogram of this block is about 250 (a block of pixels close to white). It is determined whether or not the average value thus obtained exceeds a predetermined threshold value, and the block is determined as having a fingerprint, and the block not exceeding the threshold value is determined as having no fingerprint.
The average value calculated in this way varies depending on the density of the ridges and the number of ridges in the block, but when the size of one block is 400 pixels, the block in which the ridges and valleys are present appropriately The average value of the histogram of
Shows between 00 and 230. From this, the average value of the histogram falls within this range (hereinafter referred to as the threshold range)
, It can be determined that a fingerprint exists. The threshold range is determined by the size of the subdivided block,
It is necessary to use an optimal value depending on the background color of the fingerprint image.

In this manner, each block is determined. If the ratio of blocks determined to have a fingerprint exceeds a predetermined threshold value (for example, 80%) for all blocks, it is determined that a fingerprint is present.

As described above, even in the prior art, it is possible to determine whether an image input from a fingerprint input device has been input with an area suitable for collation, and an image with a small area can be discarded in advance. It was possible.

[0010]

As described above, according to the above-mentioned prior art, it is possible to determine whether an image input from a fingerprint input device has been input with an area suitable for collation. Can be destroyed in advance. However, in this conventional technique, since the existence of the ridge is not actually confirmed, the determination result has to be said to be unstable. Also, since only the area of the collected fingerprint is determined, it is not possible to determine the state of the fingerprint, and even if a finger whose finger is too rough to be recognized as a fingerprint is input, a certain area is determined. If it satisfies even this, there is a problem that the data is imported and the personal authentication rate is remarkably reduced.

[0011] The present invention solves the above-mentioned problems of the prior art, and eliminates the need for image processing requiring a lot of calculation time and makes it possible to determine whether a fingerprint input from a fingerprint information input unit is an image suitable for fingerprint authentication. It is an object of the present invention to provide an input fingerprint state determination method and apparatus capable of accurately determining whether or not a fingerprint has a simple configuration. Another object is to detect and notify a reason such as thinness.

[0012]

According to the personal authentication technique of the present invention, as a pre-process for performing fingerprint authentication, the state of dry, wet, roughened finger, thin finger, etc. is accurately determined from the image input to the fingerprint sensor. However, input images that are not suitable for fingerprint authentication can be excluded in advance. As a result, it is possible to avoid that the fingerprint authentication is executed with the fingerprint image that is not suitable for the fingerprint authentication and the authentication fails. In addition, by rejecting the capture of images that are not suitable for fingerprint authentication and instructing countermeasures, all at the software level, a highly accurate fingerprint matching system can be realized without changing the existing fingerprint sensor. Becomes

FIG. 1 shows the principle configuration of the present invention, and FIG. 2 shows a processing flow according to the present invention.

In FIG. 1, 1 is a fingerprint information input unit, 2 is an image segmentation unit, 3 is a segmented image ridge existence judging unit, 4 is a segmented image state judging unit, 5 is an image capture determining unit, and 6 is an image capturing determining unit. An image state determination unit.

The operation of FIG. 1 will be described with reference to the processing flow of FIG. 2. A person who wants to register a fingerprint or a person who has already registered a fingerprint and wants to authenticate is placed in the input position of the fingerprint information input unit 1. When a finger is placed, a predetermined area is scanned and fingerprint information (fingerprint image) is input (S1 in FIG. 2). Next, the fingerprint image is subdivided into blocks of a predetermined size in the image subdivision section 2 (S2 in FIG. 2). Next, the subdivision image ridge presence determination unit 3 pays attention to the continuity of black (ridges or noise) and white (valley lines or background) of pixels for all subdivision images (blocks). Is determined (S3 in FIG. 2).
The subdivided image state determination unit 4 determines whether the pixel state of the subdivided image has a wet tendency or a dry tendency.
It is determined whether the image state is neither wet nor dry (S4 in FIG. 2). The result determined for each block by the subdivided image ridge existence determining unit 3 and the subdivided image state determining unit 4 is supplied to the image capture determining unit 5,
The input fingerprint state is determined based on the ratio between the total number of blocks and the number of blocks for which the presence of the fingerprint has been confirmed, and the determination result of the image state (S5 in FIG. 2), and whether or not the image is suitable for fingerprint authentication is determined. (S6 in FIG. 2). As a result, when it is determined that the fingerprint authentication is suitable, the process proceeds to a predetermined process by a fingerprint authentication mechanism (not shown) or a fingerprint registration mechanism (S7 in FIG. 2). If it is determined that the fingerprint is not suitable for fingerprint authentication, the image state determination unit 6 determines the reason for not being suitable for fingerprint authentication, and shifts to fingerprint input processing again. At this time, by providing an image state notifying means (display means or audio output means not shown), the reason why it is determined that the fingerprint authentication is not suitable and a measure for improving it are shown to the user. The user can perform fingerprint authentication without feeling stress.

As described above, according to the method of the present invention, it is possible to quickly determine whether or not an input image is suitable for fingerprint authentication without performing complicated image processing. Thus, the determination result is suitable for fingerprint authentication. If the image does not exist, the image is discarded and the collection is repeated, so that fingerprint authentication can be performed only on an image suitable for fingerprint authentication.

[0017]

FIG. 3 shows the configuration of the embodiment. In the figure, 1 to 5 are the same as those in FIG.
1 is a fingerprint information input unit, 2 is an image subdivision unit, and 3 'is a subdivided image fingerprint existence determination unit (corresponding to the subdivided image ridge existence determination unit 3 in FIG. 1) that determines whether a fingerprint exists in the subdivided image. ) And 4 are subdivided image state determination units, 5 is an image capture determination unit, and 1a is an image binarization unit. Also, 6a ~
6c corresponds to the image state determination unit 6 in FIG. 1, 6a is a thin finger determination unit, 6b is a dry fingerprint determination unit, and 6c is a wet fingerprint determination unit.

FIG. 4 is a processing flow of the embodiment, and the operation of the embodiment will be described below. First, a fingerprint image is input to the fingerprint information input unit 1 (S1 in FIG. 4), and the input fingerprint information is binarized in the image binarization unit 1a. At this time,
Conventionally, there are various methods for determining a threshold value of the binarization processing. For example, a mode method of obtaining an intermediate value using a histogram and performing binarization depending on whether the intermediate value is larger or smaller is used. Any method may be used.
Next, the binarized image is subdivided into a predetermined size in the image subdivision unit 2 (S2 in FIG. 4). For all of the subdivided images, the presence of a ridge is determined by determining the presence of a ridge in the subdivided image fingerprint presence determination unit 3 ′, and at the same time, the subdivided image state determination unit 4 changes the state of the pixel from the pixel state. It is determined whether there is a tendency, a tendency to dry, or a state that is neither wet nor dry (S3 in FIG. 4). A detailed method of determining the presence of a ridge will be described later with reference to FIGS.

For each of the blocks determined in this way, the image capture determining unit 5 calculates the ratio between the total number of subdivisions and the number of blocks for which the presence of a fingerprint has been confirmed (S4 in FIG. 4), and determines whether the image is suitable for fingerprint authentication. It is determined (S5). As a result, if it is determined that the fingerprint authentication is suitable, the process proceeds to a predetermined registration / collation process by a fingerprint authentication function unit (not shown) or a fingerprint registration unit (S6 in FIG. 4). If it is determined that it is not suitable for fingerprint authentication, the process proceeds to the determination of the state of the input image (S7 in FIG. 4) to check the reason why it is determined that it is not suitable for fingerprint authentication (S7 in FIG. 4).
Whether the finger is thin (the area of the fingerprint is small)
S8, S9), determination of whether the fingerprint is a dry fingerprint by the dry fingerprint determination section 6b (S10, S11 in FIG. 4), wet fingerprint determination section 6c
(S12, S13 in FIG. 4). If the fingerprint is not a wet fingerprint, it is determined that the finger is rough (S14 in FIG. 4). The output is output to an output means (display device not shown) as a reason for determining that it is not suitable, and the user is informed again.
It waits for a fingerprint input from the fingerprint information input unit 1. In order to determine the reason for determining that the above fingerprint authentication is not suitable,
Details of the processing will be described later with reference to FIGS. In addition,
It goes without saying that the processing order for obtaining the reason that it is determined that it is not suitable for fingerprint authentication can be freely changed.

Here, the detailed operation of the embodiment will be described using a specific example of a fingerprint image. FIG. 5 shows an example of an input fingerprint image. In this fingerprint image, an image of 15 mm × 15 mm, which is a size required for a fingerprint image, is a square of 300 pixels × 300 pixels, and the background color is white. By binarizing the input fingerprint image shown in FIG. 5 by the image binarizing unit 1a, an image shown as an example of the binarized image in FIG. 6 can be obtained. In this example, the threshold value is binarized using 230. When the binarized image shown in FIG. 6 is subdivided by the image subdivision unit 2, the ridge spacing of the fingerprint of a person differs from person to person, and a wide part and a narrow part coexist in the same finger. It has been found that a distribution such as 1 to 4 lines is formed in 0.5 mm. In this embodiment, a 0.5 mm × 0.5 mm square is subdivided into an area (block) of 10 pixels × 10 pixels (100 pixels), and the image size of the area of 100 pixels is adopted. That is, FIG. 7 shows a state in which the image of FIG. 6 is subdivided, which is subdivided into 30 (vertical) × 30 (horizontal) regions (blocks), and one region (block).
Is 10 pixels × 10 pixels. In this embodiment, 1
This is an example in which processing is performed using a square area of 0 pixels × 10 pixels. However, as long as this area can be confirmed with one to four ridges, the subdivision method and the area shape are not limited.

FIG. 8 shows, by way of example, the contents of the area of the sixth column and the 18th row in the subdivided area of FIG. Since the image has already been binarized, the background color and valley lines are set to 0 (white) in FIG.
Data such as a fingerprint or noise is represented as 1 (black).

In order to determine whether a ridge exists in a block, the present invention employs a method of determining the continuity of pixels by providing determination lines in the vertical and horizontal directions in the block.
Therefore, in this embodiment, since one block of pixels is 10 pixels × 10 pixels, the number of determination lines in the block is 20 in length and width. However, as described above, since the ridge spacing of the human fingerprint is 1 to 4 between 0.5 mm,
Block described in the present embodiment (100 pixels of 0.5 mm square)
If there are four ridges inside, the ridge width per one becomes 2.5 pixels. From this, if black (pixel representing a ridge) is continuous on three or more pixels on the determination line and white (pixel on a valley) is also continuous on three or more pixels, a fingerprint (ridge) is displayed on the determination line. Is determined to exist.

FIG. 9 is a diagram showing the position of the judgment line in the embodiment. As described above, since the continuity check is performed for three pixels, it is possible to sufficiently evaluate if judgment is made every two lines. Therefore, three judgments (1) to (3) in the horizontal direction are performed in one block. A total of six lines including the line and three determination lines (4) to (6) in the vertical direction. By limiting the determination line in this way, the processing speed can be improved. In this case, if the continuity of ridges can be confirmed in three or more lines out of the six determination lines, it is set so that ridges are determined. FIG.
Then, judgment line (2), judgment line (4), judgment line (5)
The continuity of three pixels of ridges and valleys (that is, three or more “1” or “0” are continuous) can be confirmed in a total of four determination lines (6). Can be determined. Then, the image shown in FIG.
In line 8), the presence of fingerprints (ridges and valleys) can be confirmed.

FIGS. 10 and 11 show the processing flow (part 1) and (part 2) of the judgment for each block. FIG. 9 above
The processing is performed for each block using the determination line shown in FIG. 10, and at this time, as shown on the right side of FIG.
In FIG. 10, the first block is selected as a processing target (S1 in FIG. 10), and the block number (No) is stored in the corresponding area (S2). Next, it is determined whether this block is suitable for the determination process (S3 in FIG. 10). This determination is made by identifying whether the block contains only background pixels (when the background is white, all pixels are white), or by identifying whether the block contains three or more ridges. Do. It is assumed that such a block is not suitable for the determination process, and a set indicating that the block is not to be processed is set in the data storage area (S4), and the next block is set to be processed (S5 in FIG. 10). Return. S3
When it is determined that the block is suitable for the determination processing in step (1), a setting is made to indicate that fact (S 10 in FIG. 10).
6), i = 0, k = 1 (where i represents the count value of the determination line, and k represents the number of lines for which the presence of ridges and valleys has been confirmed) (S7). Next, it is determined whether i exceeds 7 (S8), and if it does, the process proceeds to S13 in FIG. 11. If not, white of 3 pixels or more and 3 pixels or more are added to the i-th determination line. It is determined whether or not black exists (S9).

Here, it is determined whether the presence of white and black of three or more pixels has been confirmed (S10 in FIG. 10), and if confirmed, k is updated (+1) (S11), and then i is updated. (+
1) Yes (S12). If it cannot be confirmed in S10, the process proceeds to S12, i is updated, and the process returns to S8.
Thus, steps S9 to S12 are repeated until i becomes 1 to 6.
Is executed, and when i becomes 7, the process proceeds to S13 in FIG. 11 to determine whether k ≧ 3, and determines that k is not applicable (two or less lines of white and black with three or more pixels) are processed. Determines that there is no fingerprint (S14), and sets that no fingerprint exists in the data storage area corresponding to the block (S15). If the determination is affirmative in step S13, it is determined that a fingerprint exists in the processing target block (step S16), and the state is set to indicate that a fingerprint exists in the data storage area corresponding to this block (step S17). ), The coordinates of the block (relative to the entire screen) are set in the data storage area (S18), and then the state of the block (whether wet or not)
Either a dry state or a state that is neither wet nor dry) is set in the data storage area (S1).
9). The state of the block is determined by detecting the ratio of the presence of black, the ratio of the presence of white, and the ratio of black to white in all the pixels in the block and determining whether the ratio exceeds a preset ratio.

Subsequently, it is determined whether or not processing of all blocks has been completed (S20 in FIG. 11). If processing has not been completed, the next block is processed (S21), and the process returns to S2 in FIG. Repeated until finished.

It should be noted that the judgment line is not particularly determined as long as it can be judged every two lines even if it is not as shown in FIG.

The states of the blocks thus divided are individually determined. As for the block to be determined, the determination may be performed for all 900 blocks, but it is useless to process a block in which no pixel exists (all pixels are background colors) as shown in FIG. For this reason, the processing speed of such an image can be improved by excluding it from the processing target because there is no ridge in advance.

Since a method of determining the presence of a fingerprint based on the continuity of pixels is employed, a block in which data (black) of three or more pixels does not exist in a block is excluded from the processing target because no ridge exists in advance. You can do it. In this way, the processing speed can be further improved by excluding unnecessary processing blocks from processing targets and defining them in advance as blocks having no ridges.

The block to be processed is processed in three stages of wet, dry, dry and not wet, depending on the ratio of white and black and the continuity of the pixel, together with the process of confirming the presence of a fingerprint by connecting pixels. Recognize the state of the block. Specifically, for example, irrespective of the continuity, if the ratio of black is about 80%, it is determined that there is a tendency to wet, and conversely, if the ratio of white is about 80%, there is a tendency to dry. Is determined. If neither of these is present, it is determined that neither dry nor wet. Needless to say, the severity of the determination can be freely set by slightly changing the state determination ratio.

As absolute coordinates with respect to the input image,
Regardless of the presence of the ridges of the block to be processed, if the coordinates of the top, bottom, left, and right of the block where the data exists are held by the processing of S18 in FIG. The input fingerprint coordinates and the input fingerprint area can be recognized by the upper coordinates of the upper block, the left coordinates of the leftmost block, the right coordinates of the rightmost block, and the lower coordinates of the lowermost block. .

Next, a method of determining whether the input fingerprint image is suitable as a fingerprint authentication fingerprint image based on the 900 block information determined in this way will be described.

In this embodiment, it is assumed that a fingerprint collation function capable of performing fingerprint authentication without any problem is incorporated in the system if ridges and valleys exist in about 80% of the whole. Therefore, if the presence of fingerprints (ridges and valleys) can be confirmed in 80% of the 900 blocks, that is, in 720 blocks or more, the input image may be fetched as an image suitable for fingerprint authentication and the process may be shifted to the fingerprint matching function.

However, the element that is determined to be suitable for fingerprint authentication must be defined based on the performance of the fingerprint collation function for actually collating the fingerprint.

It should be noted that, depending on the type of the fingerprint sensor, the background color of the collected image may be white or black. Also, the input image sizes are various. However, even in such an image, the same processing can be performed based on the present embodiment by changing the size of the image or changing the method of recognizing the background color.

Next, a description will be given of processing up to the determination of the state of the input image when it is determined that the input fingerprint is not suitable for fingerprint authentication.

FIG. 12 shows a flowchart up to the determination of a thin finger, which is executed by the thin finger determination section 6a of FIG. 3 and shows details of S8 and S9 of FIG.

In this case, the area ratio of the input fingerprint (block including ridges and valleys) to the entire image is set as a variable n (S1 in FIG. 12). Next, it is determined whether or not n> 60% (S2 in FIG. 12). If the value does not reach 60%, the process shifts to wet or dry fingerprint determination processing. If it is 60% or more, the number of input fingerprint blocks and the number of ridge confirmation blocks are determined. Is set as a variable m (S3), it is determined whether m exceeds 70% (S4), and if not, the process proceeds to wet or dry fingerprint determination processing. It is determined that the finger is thin (or the area of the input fingerprint is small) (S5),
finish.

In the processing shown in FIG. 12, if the ratio of the block to be processed to the input image area is large, there is no problem in the input area, and the processing shifts to wet / dry determination processing. If the ratio of the processing target block to the input image area is small, it is considered that a fingerprint with a thin finger has been input. Here, the input fingerprint area described above may be used as the area of the processing target block serving as a determination element. However, the input image area is small and the finger is thin, but the block to be processed is extremely wet.
Alternatively, since it is conceivable that the block is extremely dry, if the ratio of blocks determined to have ridges to the processing target block is small, the final determination shifts to wet finger determination and dry finger determination. Conversely, if the ratio of the blocks determined to have ridges to the processing target block is large, it can be determined that the finger is definitely thin. As described above, when the input fingerprint area is smaller than the input image area and the ridge existence ratio of the processing target block is high, it is determined that the finger is thin. When it is determined that the finger is thin, the reason is that only part of the fingerprint is input because the finger is lightly placed on the fingerprint input unit.
In some cases, the reason is that the finger is actually thin. The former case may be adopted as a normal one by performing fingerprint input again, and the latter case can be dealt with by changing to use another thick finger for authentication.

In FIG. 12, the ratio of the block to be processed to the area of the input image is 60%, and the ratio of the blocks determined to have ridges to the block to be processed is 70%. It goes without saying that some settings can be changed depending on factors such as the engine performance that authenticates.

FIG. 13 is a flow chart until the dry fingerprint is determined. In FIG. 13, before this processing, FIG.
Is considered to have been completed. First, for all blocks to be processed,
Drying (80% white (valley or background) in the above example
Degree distribution), wet (in the above example, the ratio of black (ridges) is 8)
(The distribution is about 0%), and the number determined to be neither dry nor wet is counted and set as i, j, k (FIG. 13).
S1). It is determined whether the ratio of the blocks determined to be dry in the determination processing target block exceeds a predetermined threshold value (60%) (S2 in FIG. 13), and if it exceeds, it is determined that the fingerprint is a dry fingerprint (S4). Even when the ratio of the blocks determined to be dry does not exceed the predetermined threshold (60%), i,
It is determined whether the ratio of j and k is not less than 50%, not more than 30%, and not more than 30% (S3 in FIG. 13). If so, it is judged as a dry fingerprint. I do.

In FIG. 13, the threshold value for judging a dry fingerprint is 60%, and the judgment ratio of the block state is 50% or more for dry: 30% or less for wetness: 30% for neither dry nor wet.
% Or less, but it goes without saying that this ratio can be slightly changed depending on factors such as the performance of the engine that actually authenticates the fingerprint.

FIG. 14 shows a flowchart up to the determination of a wet fingerprint. In FIG. 14, before this processing,
It is assumed that the thin finger determination process illustrated in FIG. 12 and the dry fingerprint determination process illustrated in FIG. 13 have been completed.

First, the ratio of the block to be processed and the blocks determined to have ridges, and the number of blocks determined to be dry, wet, and neither dry nor wet for all blocks to be processed are counted. It is set as i, j, k (S1 in FIG. 14). In this process, the value calculated in the determination of the dry fingerprint can be used as it is. It is determined whether the ratio of the block determined to be wet to the processing target block exceeds a predetermined threshold (60%) (S in FIG. 14).
2) If it exceeds, determine it as a wet fingerprint (S
4). Then, even when the ratio of the blocks determined to be wet does not exceed the predetermined threshold, the ratio of i, j, k is 30
%, 50% or more, and 30% or less (S3 in FIG. 14). In other words, compared to a block determined to be wet and a block determined to be neither dry nor wet,
If the ratio of the blocks determined to be wet is obviously large, the block is determined to be a wet fingerprint and the process is terminated. If this condition is not met, it is determined that the finger is rough (S in FIG. 14).
5), end.

In FIG. 14, the threshold value for judging a wet fingerprint is 6
0%, block state judgment ratio 50% or more wet: 30% or less dry: 30% or less when neither dry nor wet, but this ratio depends on factors such as engine performance for actually authenticating fingerprints. Needless to say, the settings can be changed somewhat.

If it cannot be determined that the fingerprint is wet,
It is conceivable that the collected fingerprints are mixed in the dry part and the wet part at the same ratio. In this case as well, the fingerprint is not suitable for fingerprint authentication. However, such a determination is often made for a finger whose finger roughness is remarkable, so that it is determined that the finger is rough.

In this embodiment, as the processing order for determining the state of the image, the processing for determining a thin fingerprint, the processing for determining a dry fingerprint, and the processing for determining a wet fingerprint will be described. However, depending on how the judgment process is constructed,
It is needless to say that the determination order can be changed. For example, the determination process can be freely interchanged, such as performing a dry fingerprint determination on an image that does not involve a wet fingerprint determination.

That is, an image such as the existence of ridges in each block (subdivided area) obtained by dividing the input image and whether each block has a wet tendency, a dry tendency, or neither wet nor dry. If the input fingerprint coordinates and input fingerprint area information from the coordinates of each block are determined regardless of the state of the ridge and the presence of the ridge, the state of the input image can be freely determined using the contents. It is possible to do. In addition, if the function to create and compare fingerprint feature points tends to reduce the authentication rate if an image near the center of the fingerprint cannot be accurately collected, the coordinates near the center can be specified from the above input fingerprint coordinates. However, it is also possible to determine whether the state of the fingerprint in the coordinates is in a wet tendency or a dry state, and determine whether the fingerprint is unsuitable for authentication. As described above, it is also possible to increase the degree of freedom as to whether an abnormal fingerprint or a normal fingerprint is obtained as a result of partially determining the state according to the nature of the fingerprint matching function to be used.

(Appendix 1) In an input fingerprint state determination method for determining whether an input fingerprint image is suitable for authentication, the input fingerprint image is subdivided into regions of a predetermined size, and ridges are included in each subdivided region. A determination is made as to whether a fingerprint consisting of a valley line is present, the state of the skin surface in the subdivided area is determined, and a fingerprint suitable for fingerprint authentication is determined from the fingerprint presence determination result and the state determination result for each area. An input fingerprint state determination method characterized by determining whether an image is an image.

(Supplementary Note 2) The input fingerprint state determination method according to Supplementary Note 1, characterized in that at least one of ridges or valleys is selected to be subdivided into such a size that it can be identified.

(Supplementary Note 3) In Supplementary Note 1, for each image of each of the subdivided regions, for each pixel arranged in the vertical and horizontal directions, the interval between the pixels in the vertical and horizontal directions is at least the width of a ridge or a valley line. An input fingerprint state determination method, comprising: determining whether a fingerprint is present based on whether a predetermined number of pixels representing ridges or valleys are continuous based on a determination line that has been placed.

(Supplementary Note 4) In Supplementary Note 1, for each image of each of the subdivided regions, the ratio of the presence of pixels representing ridges and the ratio of the presence of pixels representing valleys or background in the image is determined. When the ratio of the pixels representing the line is equal to or more than a predetermined value, the wet state is set. When the ratio of the pixels representing the valley line or the background is equal to or more than the predetermined value, the dry state is set. An input fingerprint state determination method, wherein the input fingerprint state is determined by determining the ratio of a region that is neither wet nor dry, and determining the ratio of each of these states.

(Supplementary Note 5) The input fingerprint state determination method according to supplementary note 4, wherein the determination of the fingerprint state is performed by determining whether the fingerprint is thin, dry, wet, or rough.

(Supplementary Note 6) In an input fingerprint state determination device that determines whether an input fingerprint image is suitable for authentication, a subdivision section that subdivides the input fingerprint image into regions of a predetermined size, A fingerprint presence determination unit that determines whether a fingerprint composed of ridges and valleys is present therein, a state determination unit that determines the state of the skin surface in the subdivided region,
An input comprising: a fingerprint image state determination unit that determines whether a fingerprint image is appropriate for fingerprint authentication based on a determination result of the fingerprint presence determination unit and a determination result of the state determination unit for each area. Fingerprint state determination device.

(Supplementary Note 7) In Supplementary Note 6, the fingerprint presence determination unit may determine at least ridges or valleys in the vertical and horizontal directions for each pixel vertically and horizontally for each image of each subdivided region. An input fingerprint state determination device for determining whether a fingerprint exists based on whether or not a predetermined number of pixels representing ridges or valleys are consecutively determined based on determination lines spaced by a line width.

(Supplementary Note 8) In Supplementary Note 6, the fingerprint image state determination unit may determine, for each image of each of the subdivided regions, the ratio of the presence of the pixel representing the ridge in the image and the pixel representing the valley or the background. The existence ratio is determined, and when the ratio of the pixels representing the ridge line is equal to or more than a predetermined value, the wet state is set.
The ratio of the wet region to the entire region, the ratio of the dry state, and the ratio of the region that is neither wet nor dry are determined.
An input fingerprint state determination device, wherein the fingerprint state is determined by determining each of these ratios.

(Supplementary note 9) In Supplementary note 6, when the fingerprint image state determination unit determines that the fingerprint is not suitable for fingerprint authentication, a reason such as a thin fingerprint, a dry state, or a wet state is output. Input fingerprint state determination device.

[0058]

According to the present invention, the presence of ridges can be confirmed at high speed without performing processing such as thinning the image input to the fingerprint image input unit, which requires a large calculation time. If the image is not suitable for authentication, the reason for determining that the image is not suitable, such as dryness, wetness, roughened fingers, or thin fingers, is also determined, and the function of rejecting the image is realized.

In a personal authentication system or the like having a fingerprint information input unit having a function of collecting fingerprint information as an image, as a preprocessing for extracting fingerprint feature data from the input image, the collected image is subjected to fingerprint authentication. In order to determine whether or not it is suitable for authentication on the spot, and if it is determined that it is not suitable for authentication, the cause of the determination that it is not suitable is determined, and a fingerprint image suitable for fingerprint authentication is captured. It becomes possible. In addition, users who are likely to fail in fingerprint authentication (users who tend to input wet or dry fingerprints) are given feedback on the necessary measures to improve the situation based on the judgment results. Then, it is possible to perform fingerprint matching at a stable authentication rate without giving a stress to the user.

[Brief description of the drawings]

FIG. 1 is a diagram showing the principle configuration of the present invention.

FIG. 2 is a diagram showing a processing flow according to the present invention.

FIG. 3 is a diagram illustrating a configuration of an embodiment.

FIG. 4 is a diagram showing a processing flow of an embodiment.

FIG. 5 is a diagram illustrating an example of an input fingerprint image.

FIG. 6 is a diagram illustrating an example of a binarized image.

FIG. 7 is a diagram showing a state in which the image of FIG. 6 is subdivided.

FIG. 8 is a diagram showing the contents of an area in the sixth column and 18th line in the subdivided area in FIG. 7;

FIG. 9 is a diagram illustrating a determination line position according to the embodiment.

FIG. 10 is a diagram showing a processing flow (part 1) of determination for each block.

FIG. 11 is a diagram showing a processing flow (part 2) of determination for each block.

FIG. 12 is a diagram illustrating a flowchart for determining a thin finger.

FIG. 13 is a diagram illustrating a flowchart for determining a dry fingerprint.

FIG. 14 is a diagram illustrating a flowchart for determining a wet fingerprint.

FIG. 15 is a diagram showing a configuration of a conventional example.

FIG. 16 is a diagram showing an example of a fingerprint image used for explaining a conventional example.

17 is a diagram showing a state where the image of FIG. 16 is subdivided.

FIG. 18 is a diagram showing a distribution of pixels in two blocks.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Fingerprint information input part 2 Image subdivision part 3 Subdivision image ridge existence judgment part 4 Subdivision image state judgment part 5 Image capture determination part 6 Image state judgment part

Claims (5)

[Claims] 1. An input fingerprint state determination method for determining whether an input fingerprint image is suitable for authentication, the input fingerprint image is subdivided into regions of a predetermined size, and ridges and valleys are included in each subdivided region. The presence or absence of a fingerprint consisting of the following is determined, and the state of the skin surface in the subdivided areas is determined. From the results of the fingerprint presence determination and the state determination in each of the above areas, a fingerprint image suitable for fingerprint authentication is determined. Determining the input fingerprint state. 2. The image processing apparatus according to claim 1, wherein each of the pixels arranged in the vertical and horizontal directions is spaced at least by a width of a ridge or a valley in the vertical and horizontal directions for each image of each of the subdivided regions. An input fingerprint state determination method, characterized in that it is determined whether or not a fingerprint is present based on whether or not a predetermined number of pixels representing ridges or valleys are continued based on the determination line. 3. The method according to claim 1, wherein, for each image of each of the subdivided regions, a ratio of a pixel representing a ridge and a ratio of a pixel representing a valley or a background in the image are obtained. When the ratio of the pixels representing the is greater than or equal to a predetermined value, the wet state is set. When the ratio of the pixels representing the valley line or the background is equal to or greater than the predetermined value, the dry state is set. An input fingerprint state determination method, comprising: determining a ratio and a ratio of an area that is neither a wet state nor a dry state, and determining the fingerprint state by determining the ratio of each state. 4. An input fingerprint state determination device for determining whether an input fingerprint image is suitable for authentication, a subdivision section that subdivides the input fingerprint image into regions of a predetermined size, A subdivided image fingerprint existence determination unit that determines whether a fingerprint composed of ridges and valleys exists; a subdivided image state determination unit that determines the state of the skin surface in the subdivided region; A fingerprint image state determination unit that determines whether the fingerprint image is appropriate for fingerprint authentication based on the determination result of the subdivided image fingerprint existence determination unit and the determination result of the subdivided image state determination unit. Input fingerprint state determination device. 5. The subdivided image fingerprint presence determination unit according to claim 4, wherein each of the subdivided region images has at least ridges in the vertical and horizontal directions for each of the pixels arranged vertically and horizontally. Or determining whether or not a fingerprint is present based on whether or not a predetermined number of pixels representing ridges or valleys are consecutively determined based on a determination line spaced by the width of the valley. apparatus.