JP2007011636A - Apparatus, method and program for collating fingerprint - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a fingerprint collation apparatus, method and program capable of improving the accuracy of collation. <P>SOLUTION: The fingerprint collation apparatus is provided with: a fingerprint input part 110 for entering a collating fingerprint image to be collated; a preprocessing part 132 for extracting branch points and end points included in fingerprint lines included in the entered collating fingerprint image; a feature point extraction part 134; a collation range setting part 136 for extracting an arrangement pattern of feature points; an arrangement pattern extraction part 138; and a similarity judgment processing part 140 for retrieving registered fingerprint images similar to the collating fingerprint image or incidental information corresponding to the registered fingerprint images on the basis of the extracted arrangement pattern. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to a fingerprint collation apparatus, method, and program for extracting a registered fingerprint that matches an input fingerprint image.

In recent years, fingerprint authentication has been used as one method for preventing illegal use of a cash card of a financial institution or picking damage to a house. Fingerprint authentication is a technology that identifies the person who corresponds to a registered fingerprint that matches the fingerprint image by comparing the fingerprint authentication data registered in advance with the feature data extracted from the input fingerprint image. There are various methods conventionally used (for example, refer to Patent Documents 1 and 2).
JP 2004-145447 A (page 2-11, FIG. 1-12) Japanese Patent Laying-Open No. 2004-5532 (page 2-11, FIG. 1-7)

  By the way, when fingerprint authentication technology is used for permission to enter a house, the number of registered fingerprints is not so large, but when fingerprint authentication is used for identity verification in financial institutions, the number of registered fingerprints is dramatic. As a result, the processing time becomes longer and the collation accuracy may be lowered. In addition, various fingerprint authentication techniques (eg, frequency analysis method, pattern matching method, minutia method, etc.) that have been used in the past are not perfect in terms of processing time and collation accuracy, and there is room for improvement. . Therefore, a fingerprint authentication technique that can replace or use these conventional methods is desired.

  The present invention has been created in view of the above points, and an object thereof is to provide a fingerprint authentication apparatus, method, and program capable of improving collation accuracy.

  In order to solve the above-described problems, a fingerprint collation apparatus according to the present invention includes a fingerprint image capturing unit that captures a collation fingerprint image to be collated, and a ridge included in the collation fingerprint image captured by the fingerprint image capturing unit. Alternatively, feature point extraction means for extracting branch points and end points included in valley lines as feature points, placement pattern extraction means for extracting feature point placement patterns extracted by feature point extraction means, and placement pattern extraction means Search means for searching for a registered fingerprint image similar to the collated fingerprint image or accompanying information corresponding to the registered fingerprint image based on the arranged pattern is provided.

  The fingerprint collation method of the present invention includes a fingerprint image capture step for capturing a verification fingerprint image to be verified, and a branch included in a ridge or valley line included in the verification fingerprint image captured in the fingerprint image capture step. A feature point extraction step for extracting points and end points as feature points, a placement pattern extraction step for extracting feature point placement patterns extracted in the feature point extraction step, and a placement pattern extracted in the placement pattern extraction step A search step for searching for a registered fingerprint image similar to the verification fingerprint image or associated information corresponding to the registered fingerprint image.

  Also, the fingerprint collation program of the present invention is a feature point extraction unit that extracts a computer as a feature point using branch points and end points included in ridges or valleys included in a collation fingerprint image captured by a fingerprint image capture unit. An arrangement pattern extraction unit that extracts the arrangement pattern of the feature points extracted by the feature point extraction unit, and a registered fingerprint image similar to the verification fingerprint image or the registration based on the arrangement pattern extracted by the arrangement pattern extraction unit It is made to function as a search means for searching accompanying information corresponding to a fingerprint image.

  Since the arrangement pattern of the branch points and end points included in the ridges and valleys of the fingerprint is considered to be unique information for each fingerprint, fingerprint verification with high accuracy is performed based on this arrangement pattern. Verification can be performed.

  The arrangement pattern described above is preferably a distributed pattern of feature point coordinates along a predetermined direction. Since the arrangement state of the feature points is unique to each fingerprint, it is possible to perform highly accurate fingerprint collation by extracting this as a distributed pattern along one direction and using it for collation.

  Further, the arrangement pattern described above is preferably a dispersion pattern of coordinates of feature points corresponding to this order when the feature points included in the predetermined range are arranged in a predetermined order. Thereby, the arrangement state of each feature point can be grasped by associating the arrangement and the coordinates of each feature point, and it is possible to perform fingerprint collation with high accuracy.

  In addition, it is desirable that the arrangement pattern extraction unit described above extracts the dispersion pattern in two different directions. This makes it possible to accurately grasp the arrangement of feature points included in the fingerprint.

  In addition, the above-described arrangement pattern corresponding to the feature points included in the registered fingerprint image further includes an arrangement pattern storage unit that stores each of the plurality of registered fingerprint images, and the search unit includes an arrangement pattern corresponding to the collation fingerprint image, It is desirable to perform the search process by comparing the arrangement patterns corresponding to a plurality of registered fingerprint images stored in the arrangement pattern storage means. As a result, it is possible to easily search for similar registered fingerprint images by sequentially reading out the arrangement patterns of registered fingerprint images stored in advance and comparing them with the arrangement patterns of verification fingerprint images, which are to be compared. Even if there are many registered fingerprint images, the processing is not complicated and the processing can be simplified.

  In addition, when an arrangement pattern corresponding to a registered fingerprint image is acquired using the above-described fingerprint image capturing unit, feature point extraction unit, and arrangement pattern extraction unit, the arrangement pattern is stored in the arrangement pattern storage unit. It is desirable to further include storage processing means. This makes it possible to add a registered fingerprint image to be verified as appropriate.

  Further, a collation range setting means for setting a collation range including feature points substantially equal to the number of feature points included in the arrangement pattern of the registered fingerprint image to be collated from among the feature points corresponding to the collation fingerprint image described above. It is desirable to provide further. This makes it possible to limit the positions where different arrangement patterns exist for each registered fingerprint image, thereby simplifying the processing and shortening the processing time.

  Hereinafter, a fingerprint collation apparatus according to an embodiment to which the present invention is applied will be described in detail with reference to the drawings.

  FIG. 1 is a diagram illustrating a configuration of a fingerprint collation apparatus according to an embodiment. When a fingerprint image is input, the fingerprint collation apparatus shown in FIG. 1 searches for a registered fingerprint image (registered fingerprint image) similar to this image or accompanying information corresponding to this registered fingerprint image and outputs the search result. A fingerprint image input unit 110, a fingerprint DB (database) 120, a fingerprint collation processing unit 130, an operation unit 150, and a display unit 160.

  The fingerprint image input unit 110 is for taking a fingerprint image (a fingerprint image to be verified is referred to as a “verification fingerprint image”) into the fingerprint verification processing unit 130, and a fingerprint ridge (or an adjacent ridge) The fingerprint image data corresponding to the pattern of the valley line between the two is input. For example, a fingerprint image input unit 110 as an optical scanner that optically reads a ridge shape is used. As a result, it is only necessary to be able to read the ridge shape (or valley line shape) included in the fingerprint. Therefore, when the fingertip is pressed against the detection surface, the change in capacitance due to the contact of the fingerprint ridge is read. A fingerprint image may be acquired. Further, a fingerprint image may be acquired and input using various sensors other than these, or a fingerprint image already in a bitmap format or the like may be read by the fingerprint image input unit 110.

  The fingerprint DB 120 has a feature point arrangement pattern extracted corresponding to a plurality of fingerprint images (these images are referred to as “registered fingerprint images”) whose degree of similarity is compared with the captured collation fingerprint image during the collation processing. Is stored. A specific example of the arrangement pattern will be described later. The fingerprint DB 120 stores various accompanying information corresponding to each registered fingerprint image. For example, the accompanying information includes personal information (name, sex, address, etc.) corresponding to the registered fingerprint image. Prior to processing by the fingerprint collation processing unit 130, it is necessary to register the feature amounts of a plurality of registered fingerprint images in the fingerprint DB 120. Details of this registration process will be described later.

  The fingerprint collation processing unit 130 extracts an arrangement pattern of feature points included in the captured collation fingerprint image, and performs a process of searching for a registered fingerprint image similar to the collation fingerprint image based on the arrangement pattern. For this purpose, the fingerprint collation processing unit 130 includes a pre-processing unit 132, a feature point extraction unit 134, a collation range setting unit 136, an arrangement pattern extraction unit 138, a similarity determination processing unit 140, and a collation result output processing unit 142. Yes.

  The preprocessing unit 132 performs predetermined preprocessing on the collation fingerprint image captured using the fingerprint image input unit 110. For example, as preprocessing, processing for binarizing or thinning a captured fingerprint image is performed. The feature point extraction unit 134 extracts feature points included in the collation fingerprint image after the preprocessing by the preprocessing unit 132 is completed. Here, the feature points refer to the end points and branch points of the thinned ridges.

  FIG. 2 is a diagram illustrating a specific example of feature points included in the collation fingerprint image. The feature point extraction unit 134 extracts branch points and end points included in the collation fingerprint image after the preprocessing is completed. The collation fingerprint image shown in FIG. 2 includes branch points 1, 2, 12 and end points 3, 4, 5, and the like.

  The collation range setting unit 136 sets a collation range including feature points used for fingerprint collation from the feature points extracted by the feature point extraction unit 134. A collation range including the same number (N) of feature points as the number of feature points included in the arrangement pattern corresponding to the registered fingerprint image to be compared is set. For example, as shown in FIG. 2, the collation range setting unit 136 moves a square search range S having a predetermined area within the collation fingerprint image to identify a position where the number of feature points is N, and sets the position to this position. The corresponding search range S is set as the collation range. There may be a plurality of collation ranges in one collation fingerprint image.

  The arrangement pattern extraction unit 138 extracts the feature point arrangement pattern included in the collation range setting unit 136. This arrangement pattern is a dispersion pattern indicating a dispersion state of the arrangement of feature points along a predetermined direction. 3 to 5 are diagrams showing specific examples of arrangement pattern extraction. For example, as shown in FIG. 3, the arrangement pattern extraction unit 138 scans along the direction from the lower left to the upper right of the collation range, and scans in the order close to the scan start point S (more precisely, the scan is perpendicular to the scan direction). Numbers are assigned to the normal distance to the straight line passing through the starting point S in ascending order), and the arrangement pattern as a dispersion pattern of the X coordinate values (the horizontal coordinate values in FIG. 2) and Y when arranged in this order An arrangement pattern as a dispersion pattern of coordinate values (vertical coordinate values in FIG. 2) is extracted. FIG. 4 shows an arrangement pattern of X coordinate values. FIG. 5 shows an arrangement pattern of Y coordinate values. In FIG. 4 and FIG. 5, the numbers assigned to the feature points correspond to the horizontal axis, and the X coordinate value or the Y coordinate value corresponds to the vertical axis.

  In the above-described example, in order to extract the arrangement pattern reflecting the dispersion state of the X coordinate value and the arrangement pattern reflecting the dispersion state of the Y coordinate value, as shown in FIG. The feature points are numbered by scanning in an oblique direction different from both the (direction) and the Y-axis direction (vertical direction). However, the numbering may be performed in another order. For example, the numbering may be performed by scanning along the horizontal direction or the vertical direction.

  The similarity determination processing unit 140 determines the similarity between the verification fingerprint image and each registered fingerprint image based on the arrangement pattern extracted by the arrangement pattern extraction unit 138, and determines a registered fingerprint image that matches the verification fingerprint image. To do. The collation result output processing unit 142 displays the search result (fingerprint collation result) on the screen of the display unit 160, or when a printing operation using the operation unit 150 is performed, a printing apparatus (not shown). To instruct the search results to be printed.

  Incidentally, the arrangement patterns shown in FIGS. 4 and 5 are created based on the image data of the collation fingerprint image input from the fingerprint image input unit 110, and registration that matches the collation fingerprint image using this arrangement pattern. In order to specify a fingerprint image, it is necessary to extract an arrangement pattern having the same content for many registered fingerprint images and register it in the fingerprint DB 120 in advance.

  FIG. 6 is a diagram illustrating a configuration of a database creation apparatus that performs registration in the fingerprint DB 120 by extracting an arrangement pattern in advance for a registered fingerprint image. The configuration shown in FIG. 6 may be provided as a part of the fingerprint collation device shown in FIG. 1, but may be constructed separately from the fingerprint collation device shown in FIG. The database creation device shown in FIG. 6 includes a fingerprint image input unit 210, a database creation unit 220, an operation unit 230, and a display unit 240 in order to register many feature patterns of registered fingerprint images in the fingerprint DB 120.

  The fingerprint image input unit 210 inputs image data indicating grayscale information for each pixel constituting the registered fingerprint image. Similar to the fingerprint image input unit 110 shown in FIG. 1, an optical scanner or other various sensors can be used as the fingerprint image input unit 210.

  The database creation unit 220 performs a process of extracting the feature point arrangement pattern of the registered fingerprint image and registering it in the fingerprint DB 120. For this purpose, the database creation unit 220 includes a preprocessing unit 221, a feature point extraction unit 222, a collation range setting unit 223, an arrangement pattern extraction unit 224, and a file creation processing unit 225. Among these, the basic operations of the pre-processing unit 221 except the file creation processing unit 225, the feature point extraction unit 222, the collation range setting unit 223, and the arrangement pattern extraction unit 224 are the fingerprint collation processing unit 130 shown in FIG. These are the same as the components having the same names, and only the differences will be described. The collation range setting unit 223 sets a collation range for extracting an arrangement pattern corresponding to each registered fingerprint image. When a feature point of the registered fingerprint image as shown in FIG. 2 is extracted, this registered fingerprint is set. A predetermined range corresponding to the center position of the image is set as a collation range. The size of this collation range is constant, and a corresponding number of feature points are included for each registered fingerprint image.

  The file creation processing unit 225 registers the feature point arrangement pattern for each extracted registered fingerprint image in the fingerprint DB 120 as a set of files. When registering the arrangement pattern, the number of feature points included in the collation range used when extracting each registered pattern is registered together with each registered pattern. The operation unit 230 is used to extract an arrangement pattern corresponding to the registered fingerprint image, and to perform an operation instruction necessary for registration. The operation unit 230 is used to input personal information as accompanying information corresponding to each registered fingerprint image. The display unit 240 is used for confirming the registered contents of the arrangement pattern and accompanying information, and for displaying various operation screens necessary for registration.

  By using the database creation device having such a configuration, a plurality of registered fingerprint images having basically the same contents as the collation fingerprint image arrangement patterns shown in FIG. 4 and FIG. Corresponding accompanying information is registered in the fingerprint DB 120.

  The fingerprint image input units 110 and 210 described above are fingerprint image capturing means, the preprocessing units 132 and 221 and the feature point extraction units 134 and 222 are feature point extraction units, and the arrangement pattern extraction units 138 and 224 are arrangement pattern extraction units. Furthermore, the similarity determination processing unit 140 corresponds to the search unit, the fingerprint DB 120 corresponds to the arrangement pattern storage unit, the file creation processing unit 226 corresponds to the arrangement pattern storage processing unit, and the collation range setting units 136 and 223 correspond to the collation range setting unit, respectively. To do. The operations performed by the fingerprint image input units 110 and 210 are the operations of the fingerprint image capturing step, and the operations performed by the preprocessing units 132 and 221 and the feature point extraction units 134 and 222 are the operations of the feature point extraction step. The operation performed by the arrangement pattern extraction units 138 and 224 corresponds to the operation of the arrangement pattern extraction step, and the operation performed by the similarity determination processing unit 140 corresponds to the operation of the search step.

  The fingerprint collation apparatus of this embodiment has such a configuration, and the operation will be described next. FIG. 7 is a flowchart showing an operation procedure for performing fingerprint collation based on the collated fingerprint image in the fingerprint collation processing unit 130. First, when the preprocessing unit 132 acquires the collation fingerprint image input from the fingerprint image input unit 110 (step 100), the preprocessing unit 132 performs preprocessing such as thinning (step 101). Further, the feature point extraction unit 134 extracts the branch point and the end point included in the collation fingerprint image after the preprocessing is completed as the feature point (step 102).

  Next, the similarity determination processing unit 140 reads an arrangement pattern corresponding to one registered fingerprint image to be collated with the number of feature points corresponding to the arrangement pattern (step 103). The collation range setting unit 136 sets a collation range corresponding to the number of feature points (step 104). In addition, the arrangement pattern extraction unit 138 extracts an arrangement pattern corresponding to the set collation range (step 105). Next, the similarity determination processing unit 140 performs similarity determination between the arrangement pattern corresponding to the extracted collation fingerprint image and the arrangement pattern corresponding to the registered fingerprint image read out in step 103 (step 106). It is determined whether or not the two types of arrangement patterns match (step 107). Specifically, an error (for example, a square error) regarding the two types of arrangement patterns related to the X coordinate values shown in FIG. 4 and an error about the two types of arrangement patterns related to the Y coordinate values shown in FIG. When the total value of these is equal to or less than a predetermined value, it is determined that the arrangement pattern corresponding to the collation fingerprint image matches the arrangement pattern corresponding to the registered fingerprint image. In this case, an affirmative determination is made in the determination in step 107, and the collation result output processing unit 142 outputs (displays) the accompanying information corresponding to the registered fingerprint image as a collation result (step 108).

  On the other hand, if the arrangement patterns do not match, a negative determination is made in the determination of step 107, and then the similarity determination processing unit 140 determines whether there is another registered fingerprint image that has not been subjected to the matching process. (Step 109). If there is another registered fingerprint image, an affirmative determination is made, and the process returns to step 103 to repeat the operation of reading the arrangement pattern of the other registered fingerprint image. If there is no other registered fingerprint image, a negative determination is made in the determination in step 109, and a collation result indicating that there is no registered fingerprint image that matches the collation fingerprint image is output (step 108). In this way, a series of fingerprint collation operations are completed.

  In this way, the arrangement pattern of the branch points and end points included in the ridges and valleys of the fingerprint is considered to be unique information for each fingerprint, so by performing fingerprint matching based on this arrangement pattern, It becomes possible to perform fingerprint collation with high accuracy.

  Further, as this arrangement pattern, a distribution pattern of the coordinates of feature points along a predetermined direction is used. Since the arrangement state of the feature points is unique to each fingerprint, it is possible to perform highly accurate fingerprint collation by extracting this as a distributed pattern along one direction and using it for collation.

  Further, as the arrangement pattern, when the feature points included in the predetermined range are arranged in a predetermined order, a distribution pattern of the coordinates of the feature points corresponding to the order is used. Thereby, the arrangement state of each feature point can be grasped by associating the arrangement and the coordinates of each feature point, and it is possible to perform fingerprint collation with high accuracy. In particular, the arrangement of the feature points included in the fingerprint can be accurately grasped by using the distribution patterns extracted in two different directions as the arrangement pattern.

  In addition, it is possible to easily search for similar registered fingerprint images by sequentially reading the arrangement patterns of registered fingerprint images stored in advance and comparing them with the arrangement patterns of verification fingerprint images. Even if there are many fingerprint images, the processing is not complicated and the processing can be simplified. In addition, by using the database creation device shown in FIG. 6, it is possible to appropriately add a registered fingerprint image to be collated.

  In addition, the registered fingerprint image is set by setting a collation range including feature points substantially equal to the number of feature points included in the arrangement pattern of the registered fingerprint image to be collated from among the feature points corresponding to the collated fingerprint image. It is possible to limit the positions where different arrangement patterns exist for each, and it is possible to simplify the processing and shorten the processing time.

  In addition, this invention is not limited to the said embodiment, A various deformation | transformation implementation is possible within the range of the summary of this invention. For example, the operations of the fingerprint collation processing unit 130 and the database creation unit 220 of the above-described embodiment may be performed by a computer including a CPU, a ROM, a RAM, and the like. In this case, the fingerprint collation program stored in the ROM, RAM or other storage device (hard disk device or the like) (executes each step shown in FIG. 7 or the fingerprint collation processing unit 130 or each unit of the database creation unit 220). A program for realizing the function may be executed by the CPU.

  In the above-described embodiment, the branch points and end points included in the ridges of the fingerprint image are extracted as feature points. However, similar branch points and end points are also included in the valley lines between adjacent ridges. Therefore, these may be extracted as feature points to perform fingerprint collation.

It is a figure which shows the structure of the fingerprint collation apparatus of one Embodiment. It is a figure which shows the specific example of the feature point contained in a collation fingerprint image. It is a figure which shows the specific example of arrangement | positioning pattern extraction. It is a figure which shows the specific example of arrangement | positioning pattern extraction. It is a figure which shows the specific example of arrangement | positioning pattern extraction. It is a figure which shows the structure of the database preparation apparatus which extracts the arrangement pattern about a registered fingerprint image beforehand, and registers with respect to fingerprint DB. It is a flowchart which shows the operation | movement procedure which performs fingerprint collation based on a collation fingerprint image in a fingerprint collation process part.

Explanation of symbols

110, 210 Fingerprint image input unit 120 Fingerprint DB (database)
130 Fingerprint verification processing unit 132, 221 Preprocessing unit 134, 222 Feature point extraction unit 136, 223 Verification range setting unit 138, 224 Arrangement pattern extraction unit 140 Similarity determination processing unit 142 Verification result output processing unit 150, 230 Operation unit 160 , 240 Display unit 220 Database creation unit 225 File creation processing unit

Claims (9)

Fingerprint image capturing means for capturing a verification fingerprint image to be verified;
Feature point extracting means for extracting branch points and end points included in ridges or valleys included in the collated fingerprint image captured by the fingerprint image capturing means as feature points;
An arrangement pattern extraction unit that extracts an arrangement pattern of feature points extracted by the feature point extraction unit;
Search means for searching for a registered fingerprint image similar to the collation fingerprint image or accompanying information corresponding to the registered fingerprint image based on the arrangement pattern extracted by the arrangement pattern extraction means;
A fingerprint collation apparatus comprising: In claim 1,
The fingerprint collation apparatus, wherein the arrangement pattern is a distributed pattern of coordinates of the feature points along a predetermined direction. In claim 1,
The arrangement pattern is a distributed pattern of coordinates of each feature point corresponding to the order when the feature points included in a predetermined range are arranged in a predetermined order. . In claim 3,
The arrangement pattern extracting means extracts the distributed pattern in two different directions, and is a fingerprint collation apparatus. In any one of Claims 1-4,
The arrangement pattern storage unit that stores the arrangement pattern corresponding to the feature point included in the registered fingerprint image for each of the plurality of registered fingerprint images,
The search means performs a search process by comparing an arrangement pattern corresponding to the collation fingerprint image and an arrangement pattern corresponding to the plurality of registered fingerprint images stored in the arrangement pattern storage means. A fingerprint verification device. In claim 5,
An arrangement for storing the arrangement pattern in the arrangement pattern storage means when an arrangement pattern corresponding to the registered fingerprint image is acquired using the fingerprint image capturing means, the feature point extraction means, and the arrangement pattern extraction means. A fingerprint collation apparatus further comprising pattern storage processing means. In any one of Claims 1-6,
Collation range setting means for setting a collation range including feature points substantially equal to the number of feature points included in the arrangement pattern of the registered fingerprint image to be collated from among the feature points corresponding to the collation fingerprint image. The fingerprint collation apparatus further comprising: A fingerprint image capturing step for capturing a verification fingerprint image to be verified;
A feature point extracting step of extracting branch points and end points included in ridges or valleys included in the collation fingerprint image captured in the fingerprint image capturing step as feature points;
An arrangement pattern extraction step for extracting an arrangement pattern of the feature points extracted in the feature point extraction step;
Based on the arrangement pattern extracted in the arrangement pattern extraction step, a search step for searching for a registered fingerprint image similar to the verification fingerprint image or accompanying information corresponding to the registered fingerprint image;
A fingerprint collation method comprising: Computer
Feature point extracting means for extracting branch points and end points included in ridges or valleys included in the collated fingerprint image captured by the fingerprint image capturing means as feature points;
An arrangement pattern extraction unit that extracts an arrangement pattern of feature points extracted by the feature point extraction unit;
Search means for searching for a registered fingerprint image similar to the collation fingerprint image or accompanying information corresponding to the registered fingerprint image based on the arrangement pattern extracted by the arrangement pattern extraction means;
Fingerprint verification program that makes it work.

Images