JPH0628458A - Fingerprint matching device - Google Patents

Abstract

PURPOSE:To improve a fingerprint matching rate caused by misalignment in the fingerprint matching device for comparing an inputted fingerprint image and a dictionary pattern stored in a dictionary and confirming the person himself. CONSTITUTION:The device is constituted of a fingerprint sensor 1 for reading a fingerprint image, a binarizing circuit 2 for converting an output of the fingerprint sensor 1 to digital data, and thereafter, binarizing it, a frame memory 3 for storing an output of the binarizing circuit 2, a feature information extracting part 10 for dividing the fingerprint image read out of the frame memory 3 into plural blocks, and extracting almost the same number of feature points from each divided block, a dictionary storage part 11 for registering the feature points of every block extracted by the feature information extracting part 10 as a dictionary, and a matching part 12 for executing a matching by using a block area of a part of dictionary patterns registered in the dictionary storage part 11 as a dictionary, at the time of matching the fingerprint image read out of the frame memory 3 and the dictionary pattern read out of the dictionary storage part 11.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a fingerprint collation apparatus for comparing an input fingerprint image with a dictionary pattern stored in a dictionary to identify the person.

In recent years, as computers have been introduced into a wide range of social systems, system security has attracted a lot of interested persons. Many questions have been raised in terms of ensuring security for the ID cards and passwords that have been used so far as means for confirming the identity when entering a computer room or using a terminal. On the other hand, fingerprints are considered to be the most effective means of personal identification because fingerprints have two major characteristics, that is, they are the same for all people and do not change for the rest of the life, and much research and development has been done on simple personal identification systems using fingerprints. There is.

[0003]

2. Description of the Related Art FIG. 8 is a conceptual diagram showing the construction of a conventional fingerprint collation device. First, the operation at the time of registration will be described. A fingerprint pattern is detected by pressing a finger against the fingerprint sensor 1 and converted into digital data by an A / D converter (not shown) in the fingerprint sensor 1. The converted digital data (fingerprint data) is converted into binary data of “0” and “1” by the subsequent binarization circuit 2 and stored in the frame memory 3.

The fingerprint data stored in the frame memory 3 is sequentially read out, and then enters the characteristic information extracting section 4 to extract characteristic information. Here, the characteristic information is, for example, as shown in FIG.
It refers to a branch point as shown in (a) or an end point as shown in (b). The fingerprint can be specified by the number of such branch points and end points at which positions. The extracted feature information is stored in the fingerprint dictionary storage unit 5. The above operation is repeated for a plurality of individuals, and the characteristic information of the individuals is stored in the fingerprint dictionary storage unit 5.

When the registration of the feature information amount in the fingerprint dictionary storage unit 5 is completed in this way, the collation operation of the individual fingerprint is started this time. In the case of collation, a finger (a finger used for registration in advance, for example, an index finger) is placed on the fingerprint sensor 1 and then an ID number of the user is input with a ten-key pad (not shown). As a result,
The collation unit 6 can narrow the search range by determining the search range of the fingerprint dictionary storage unit 5 based on the ID number and reading it at the time of the collation.

A fingerprint pattern is detected in the same manner as at the time of registration, and is converted into digital data by an A / D converter (not shown) in the fingerprint sensor 1. The converted digital data is converted into binary data of “0” and “1” by the subsequent binarization circuit 2 and stored in the frame memory 3.

The collation unit 6 reads out the collation fingerprint image stored in the frame memory 3 and the individual characteristic information stored in the fingerprint dictionary storage unit 5, and collates both (pattern matching). . When the number of matching feature patterns is greater than or equal to a predetermined number, it is determined that the fingerprints match.

Next, regarding the pattern matching operation,
Further details will be described. 10A is read by the fingerprint sensor 1, binarized by the binarization circuit 2, and the frame memory 3 is read.
It is a fingerprint image contained in. In the figure, the shaded areas are ridges (mountain lines) and the white areas are valley lines. The feature information extraction unit 4 extracts feature points from the fingerprint image and cuts out a plurality of fingerprint images (feature patterns) centering on the feature points in a window shape.

FIG. 10B is a diagram showing a characteristic pattern as a fingerprint dictionary. W in the figure is the alignment window, and the remaining 1 to 6 are windows extracted around the alignment window W. While maintaining this positional relationship, it is registered in the fingerprint dictionary storage unit 5 as a dictionary.

At the time of matching, the matching unit 6 pattern-matches the window of the fingerprint dictionary with the input fingerprint image.
The fingerprint dictionary is divided into one alignment window W and a plurality of matching peripheral windows. First, the registration window W is scanned with respect to the fingerprint image to perform pattern matching,
Grasp the amount of movement of the input image with respect to the registered image. After that, the matching window is shifted by the amount of movement of the alignment window to perform matching. FIG. 10C shows the state of pattern matching. In the figure, H is the read fingerprint image. The alignment window W is scanned for this fingerprint image, a matching pattern is searched for, and the movement amount is memorized at the matching position. When the remaining matching windows are moved by the same amount, the state shown in FIG. When performing this pattern matching, the matching window is two-dimensionally scanned by a slight amount in order to cope with the distortion caused by the softness of human skin, and the pattern matching is performed.

FIG. 11 is a flowchart showing the operation of the conventional device. First, pattern matching of the alignment window image is performed (S1). This pattern matching is
As shown in (c) of FIG. 10, the positioning window W (positioning feature point) is superimposed on the read fingerprint image so that both images match. Then, it is checked whether or not it is a candidate point by whether or not the positioning window W can be matched (S2).

If it is not a candidate point, the positioning window W is moved (S3) and it is checked whether it is within the action range (S4). If it is within the action range, the process returns to step S1. If it is out of the action range, the fingerprint collation is rejected (S5).

If a candidate point is found in step S2, pattern matching is performed on the other matching window (matching feature point) images by the same amount as the movement amount of the positioning window (S6). Then, it is checked whether the pattern matching has passed (S7). If you pass,
Add 1 to the number of pattern matchings that have passed until then,
The number of passes is compared with the reference threshold (S8). If the number of passes is equal to or greater than the threshold value, the person is confirmed (S9).

If it fails in step S7, it is checked whether all windows have ended (S10). If all windows have ended, the number of passes has not reached the reference threshold. Therefore, it refuses to judge that the person is (S
11). If the pattern matching for all windows is not completed, the process proceeds to another peripheral image (S12) and pattern matching is performed. Note that step S10 is also executed when the number of passes is not greater than or equal to the threshold value in step S8.

[0015]

In the conventional device,
A problem occurs when the finger placement position is misaligned when registering the fingerprint dictionary and when collating. If the position where this finger is placed shifts,
It occurs because the person's habit is likely to appear during verification. For example,
If the finger is placed as shown in FIG.
The amount of information is smaller than when the fingerprint dictionary is registered (Fig. (A) shows a normal placement).

Therefore, there may occur a case where the feature points used for alignment do not exist in the collation fingerprint image. That is, since the field of view of the fingerprint sensor is limited, there may occur a case where the portion registered in the fingerprint dictionary cannot be detected. In particular, when a special finger is placed when registering the fingerprint dictionary, the collation rate after that may decrease. In order to correct such a positional shift between the fingerprint image for collation and the fingerprint dictionary, there is also a method of collating with a wide field of view of the fingerprint dictionary, but since the area of the image to be processed increases, the collation speed decreases. Resulting in.

The present invention has been made in view of the above problems, and an object thereof is to provide a fingerprint collation apparatus capable of improving the collation rate.

[0018]

FIG. 1 is a block diagram showing the principle of the present invention. The same parts as those in FIG. 8 are designated by the same reference numerals. In the figure, 1 is a fingerprint sensor for reading a fingerprint image, 2 is a binarization circuit for converting the output of the fingerprint sensor 1 into digital data, and then binarizing it, 3 is the binarization circuit 2
It is a frame memory that stores the output of.

Reference numeral 10 denotes a feature information extraction unit that divides the fingerprint image read from the frame memory 3 into a plurality of blocks, and extracts substantially the same number of feature points from each of the divided blocks.
Is a dictionary storage unit for registering the feature points for each block extracted by the feature information extraction unit 10 as a dictionary, and 12 is used for matching the fingerprint image read from the frame memory 3 with the dictionary pattern read from the dictionary storage unit 11. , Dictionary storage unit 11
It is a collation unit that collates using a partial block area of the dictionary pattern registered in.

[0020]

The fingerprint image read out from the frame memory 3 is divided into a plurality of blocks, the feature information extracting unit 10 extracts approximately the same number of feature points from each divided block, and the blocks extracted by the feature information extracting unit 10 Each feature point is registered in the dictionary storage unit 11 as a dictionary. When the collation fingerprint image is input, the fingerprint image and the dictionary storage unit 1 are input.
A partial block area of the dictionary pattern stored in 1 is used as a dictionary. As a result, even if a fingerprint image is deformed and input at the time of matching, the fingerprint dictionary block area corresponding to the deformed area can be used as the fingerprint dictionary, so that the matching rate can be improved.

[0021]

Embodiments of the present invention will now be described in detail with reference to the drawings.

FIG. 2 is a flow chart showing an example of the operation of the present invention, showing the operation at the time of registering the fingerprint dictionary. First,
A registered image is input from the fingerprint sensor 1 (S1). The input registration image is binarized by the subsequent binarization circuit 2 (S
2) After being thinned (S3), it is once stored in the frame memory 3.

Next, the feature extraction unit 10 uses the frame memory 3
The feature points are extracted from the registered image read from (S4), and a fingerprint dictionary is created (S5). Next, the characteristic information extraction unit 10
Divides the registered image into a plurality of small areas (blocks) (S
6).

FIG. 3 is a diagram showing how the registered image is divided. In the example shown in the figure, an example is shown in which the block is divided into three blocks vertically and three blocks horizontally, that is, a total of nine blocks. Next, each block is associated with the feature point image (feature pattern) of each fingerprint dictionary (S7). □ in the figure indicates a feature point. Then, the feature patterns are selected from each block almost uniformly.

Next, a feature point for alignment is selected from the central block E (S8). Then, when the alignment feature point is selected, the created dictionary is stored in the dictionary storage unit 11
(S9).

When the registration of the collation fingerprint dictionary is completed, the process proceeds to fingerprint collation. FIG. 4 is a flowchart showing an example of the operation of the present invention, showing the operation at the time of matching. First, the collation image is input from the fingerprint sensor 1 (S1). The input collation image is binarized by the binarization circuit 2 and then enters the frame memory 3. Then, the matching unit 12 reads the input matching image from the frame memory 3 and searches for the matching feature point by matching it with the matching feature point stored in the dictionary storage unit 11, Matching is performed (S2).

Next, the matching unit 12 calculates the position shift amount and direction of the matching image with respect to the dictionary image by the positioning in step S2 (S3). FIG. 5 is an explanatory diagram of selecting a dictionary area according to a position shift. (A) is a read collation image, and (b) is a fingerprint dictionary stored in the dictionary storage unit 11. The characteristic pattern for each block of the fingerprint dictionary is the same as the characteristic pattern extracted in FIG.

The matching image shown in FIG. 5 (a) is tilted to the upper right of the screen. Therefore, the alignment feature points are searched for from the matching image. When the alignment feature point is found, the alignment feature point stored in the dictionary storage unit 11 and the alignment feature point in the matching image are aligned to determine the positional shift amount of the matching image and the position. Calculate the deviation direction.

When the position shift amount and the direction are obtained, the area of the fingerprint dictionary to be used is selected (S4).

Here, as shown in FIG. 5, 2 × 2 blocks among 3 × 3 blocks are used as a fingerprint dictionary. As a result, the area B1 shown in FIG.
Is selected as the fingerprint dictionary. When the fingerprint dictionary area is selected, the matching unit 12 corrects the positional deviation of the fingerprint dictionary as shown in the figure (S5) and performs pattern matching (S).
6). As described above, according to the present invention, since the fingerprint dictionary block corresponding to the positional deviation of the matching image is selected and the pattern matching is performed, the fingerprint matching rate due to the positional deviation can be improved.

FIG. 6 is a flow chart showing the operation of another embodiment of the present invention, showing the operation at the time of fingerprint dictionary registration.
In this embodiment, when extracting the alignment feature points,
In addition to the positive alignment feature points, multiple secondary alignment feature points are created, and when the alignment fails at the positive alignment feature points, the remaining secondary alignment feature points are used. The position is adjusted by adjusting the position.

First, a registration image is input from the fingerprint sensor 1 (S1). The input registered image is the binarization circuit 2 that follows.
Are binarized (S2), thinned (S3), and then temporarily stored in the frame memory 3.

Next, the feature extraction unit 10 uses the frame memory 3
The feature points are extracted from the registered image read from (S4), and a fingerprint dictionary is created (S5). Next, the characteristic information extraction unit 10
Divides the registered image into a plurality of small areas (blocks) (S
6). For example, in the case of FIG.
An example of division into a total of 9 blocks is shown. Next, each block is associated with the feature point image (feature pattern) of each fingerprint dictionary (S7). The squares in FIG. 3 indicate characteristic points. Then, the feature patterns are selected from each block almost uniformly.

Next, a feature point for alignment is selected from the central block E (S8). Next, a sub-positioning feature point image is selected from each block other than the central portion (S9). The feature information extraction unit registers the dictionary pattern created in this way in the dictionary storage unit 11 (S10).

When the registration of the fingerprint dictionary is completed, the input fingerprint is collated next. FIG. 7 is a flow chart showing the operation of another embodiment of the present invention, showing the operation at the time of matching. First, the collation image is input from the fingerprint sensor 1 (S1).
The input collation image is binarized by the binarization circuit 2 and then enters the frame memory 3. Then, the matching unit 12
Reads out the input matching image from the frame memory 3 and finds the alignment feature point by matching it with the alignment feature point stored in the dictionary storage unit 11 and performs alignment (S2). ).

Next, it is checked whether or not the alignment is successful (S3). If the alignment is successful, the matching unit 12 calculates the position shift amount and direction of the matching image with respect to the dictionary image by the alignment in step S2 (S4). When the position shift amount and the direction are obtained, the area of the fingerprint dictionary to be used is selected (S5).

Here, as shown in FIG. 5, 2 × 2 blocks among 3 × 3 blocks are used as a fingerprint dictionary. As a result, the area B1 shown in FIG.
Is selected as the fingerprint dictionary. When the fingerprint dictionary area is selected, the collation unit 12 corrects the positional deviation of the fingerprint dictionary as shown in the figure (S6) and performs pattern matching (S).
7).

Here, a case where the alignment is not successful in step S3 will be described. In this case, since the positive alignment feature point could not be aligned, it is checked whether or not the secondary alignment feature point exists (S9).
The fingerprint matching process ends. If it exists, one is selected from the plurality of sub-positioning feature points (S1
0), alignment with the collation image is performed (S2).

If the person is confirmed in step S8, it is checked whether the number of times of use of the auxiliary positioning feature points used is equal to or more than a predetermined threshold value (S11). In step S12, the matching unit 12 swaps the windows of the primary and secondary alignment feature points.

As described above, according to the present invention, since the fingerprint dictionary block corresponding to the positional deviation of the collation image is selected and the pattern matching is performed, the fingerprint collation rate due to the positional deviation can be improved.

[0041]

As described above in detail, according to the present invention, the registration fingerprint dictionary area is set to be larger than the matching fingerprint image area, and at the time of matching, the position is determined based on the alignment feature points. By obtaining the shift and the direction and selecting the block area of the fingerprint dictionary to be used from the position shift and the direction to perform the fingerprint matching, the fingerprint matching rate due to the position shift can be improved.

[Brief description of drawings]

FIG. 1 is a principle block diagram of the present invention.

FIG. 2 is a flowchart (at the time of registration) showing an example of the operation of the present invention.

FIG. 3 is a diagram showing how a registered image is divided.

FIG. 4 is a flowchart (at the time of collation) showing an example of the operation of the present invention.

FIG. 5 is an explanatory diagram of dictionary area selection according to a position shift.

FIG. 6 is a flowchart (during registration) showing the operation of another embodiment of the present invention.

FIG. 7 is a flow chart (at the time of collation) showing the operation of another embodiment of the present invention.

FIG. 8 is a conceptual diagram of a configuration of a conventional fingerprint matching device.

FIG. 9 is a diagram illustrating an example of fingerprint characteristic information.

FIG. 10 is an operation explanatory diagram of pattern matching.

FIG. 11 is a flowchart showing the operation of the conventional device.

FIG. 12 is an explanatory diagram of how to place a finger.

[Explanation of symbols]

 1 Fingerprint Sensor 2 Binarization Circuit 3 Frame Memory 10 Feature Information Extraction Section 11 Dictionary Storage Section 12 Collation Section

Claims (5)

[Claims] 1. A fingerprint sensor (1) for reading a fingerprint image, a binarization circuit (2) for binarizing the output of the fingerprint sensor (1) into digital data, and the binarization. A frame memory (3) for storing the output of the circuit (2) and feature information for dividing the fingerprint image read from the frame memory (3) into a plurality of blocks and extracting approximately the same number of feature points from each of the divided blocks. An extraction unit (10), a dictionary storage unit (11) for registering the feature points of each block extracted by the feature information extraction unit (10) as a dictionary, a fingerprint image read from the frame memory (3), and a dictionary storage When collating with the dictionary pattern read from the unit (11), the collation unit (12) that collates by using a partial block area of the dictionary pattern registered in the dictionary storage unit (11) as a dictionary. Fingerprint Coupling devices. 2. The feature information extraction unit (10) is characterized in that a feature point for alignment is selected from a fingerprint image area in the center of the visual field and registered in the dictionary storage unit (11). The fingerprint matching device according to claim 1. 3. The matching unit (12) searches the fingerprint image read from the frame memory (3) for alignment feature points and performs alignment, and the amount and direction of displacement of the alignment image with respect to the dictionary image. Is calculated, and the dictionary area to be used in the dictionary storage unit (11) is selected from the displacement direction and amount,
2. The fingerprint collation apparatus according to claim 1, wherein the collation operation is performed after the displacement of the dictionary is corrected. 4. The feature information extraction unit (10) extracts a sub-feature point in addition to the positive feature point for alignment at the time of extracting the alignment feature points for each block into which the feature information extraction unit (10) has been divided, and the dictionary storage unit (10). 11), and if the collation unit (12) fails to align the positive alignment feature point, the fingerprint dictionary is aligned using the secondary alignment feature point. The fingerprint collation device according to claim 3, wherein 5. The collation unit (12) records the frequency of use of the primary and secondary alignment feature points, and stores the dictionary storage unit (when the frequency of secondary use exceeds a certain threshold value). The fingerprint collation apparatus according to claim 4, wherein the positive and the subordinate of 11) are switched.