JP2006330872A - Fingerprint collation device, method and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a fingerprint collation device, method and program capable of enhancing a collation precision. <P>SOLUTION: This fingerprint collation device is provided with: a fingerprint image input part 110 for capturing a collation fingerprint image as the object of collation; a pre-processing part 132 for extracting branch points and end points included in a ridge line included in the captured collation fingerprint image as feature points; a feature point extracting part 134 and a partial line extracting part 136 for extracting the ridge line held between the adjacent two feature points as a partial line; a junction extraction processing part 138 and a function approximation processing part 140 for approximating the shape of the extracted partial line by one or more functions; and a similarity decision processing part 142 for retrieving a registration fingerprint image similar to the collation fingerprint image or accessory information corresponding to the registration fingerprint image based on characteristic information relevant to the function approximation processing. <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 corresponding 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 problem, 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. Or feature point extracting means for extracting branch points and end points included in valley lines as feature points; partial line extracting means for extracting ridges or valley lines sandwiched between two adjacent feature points as partial lines; A function approximation means for approximating the shape of the partial line extracted by the line extraction means with one or a plurality of functions, and a registered fingerprint image similar to the verification fingerprint image based on feature information related to the approximation processing by the function approximation means, or Search means for searching for accompanying information corresponding to the registered fingerprint image 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. Extracted by a feature point extraction step for extracting points and end points as feature points, a partial line extraction step for extracting a ridge or valley line sandwiched between two adjacent feature points as a partial line, and a partial line extraction means Corresponding to the registered fingerprint image similar to the verification fingerprint image or this registered fingerprint image based on the function approximation step that approximates the shape of the partial line with one or a plurality of functions and the feature information related to the approximation processing in the function approximation step And a search step for searching for accompanying information.

  Further, the fingerprint collation program of the present invention is a feature point extraction unit that extracts a computer as a feature point using a branch point and an end point included in a ridge or valley line included in a collation fingerprint image captured by a fingerprint image capture unit. And a partial line extracting means for extracting a ridge or valley line sandwiched between two adjacent feature points as a partial line, and approximating the shape of the partial line extracted by the partial line extracting means with one or a plurality of functions. Based on the function approximating means and the feature information related to the approximating process by the function approximating means, it is made to function as a search means for searching for a registered fingerprint image similar to the collation fingerprint image or associated information corresponding to this registered fingerprint image.

  By approximating the shape of the partial line extracted by dividing the ridges and valleys of the fingerprint at the branch points and end points and performing fingerprint matching using the result, the accuracy based on the detailed shape of the fingerprint is improved. High fingerprint verification can be performed.

  In addition, feature information storage means in which feature information created in association with the process of approximating the shape of the partial line included in the above-described registered fingerprint image with one or a plurality of functions is stored for each of the plurality of registered fingerprint images. Further, it is desirable that the search means compare the feature information corresponding to the collation fingerprint image with the feature information corresponding to the plurality of registered fingerprint images stored in the feature information storage means. Thereby, the feature information of the registered fingerprint image stored in advance can be read in order and compared with the feature information of the collation fingerprint image, so that similar registered fingerprint images can be easily searched for and compared. Even if there are many registered fingerprint images, the processing is not complicated and the processing can be simplified.

  Further, when the feature information corresponding to the registered fingerprint image is acquired using the above-described fingerprint image capturing means, feature point extracting means, partial line extracting means, and function approximating means, this feature information is stored in the feature information storing means. It is desirable to further include characteristic information storage processing means for storing. This makes it possible to add a registered fingerprint image to be verified as appropriate.

  Further, the partial line extracting means described above separately extracts coordinate values for each of the X coordinate and Y coordinate of each pixel constituting the partial line, and the function approximating means converts the coordinate values extracted by the partial line extracting means. Based on this, it is desirable to separately perform function approximation processing corresponding to the X coordinate and function approximation processing corresponding to the Y coordinate. As a result, the function approximation process can be performed by paying attention to one variable, so that the process can be simplified.

  Further, the search means described above checks for a match / mismatch between the partial line included in the collation fingerprint image and the partial line included in the registered fingerprint image, and when the number of matching partial lines exceeds a predetermined value, It is desirable to determine that the registered fingerprint image matches the verification fingerprint image. Thereby, it is possible to determine that the registered fingerprint image in which most of the shapes of the ridges or valleys match is matched with the verification fingerprint image, and the accuracy of fingerprint verification can be improved.

  Further, the feature information described above includes the partial line length as the length of the partial line, and the search means can check the partial line match / mismatch for the partial lines having a close partial line length value. desirable. As a result, the number of partial lines for checking match / mismatch can be reduced, and the processing can be simplified and the processing time can be shortened.

  In addition, the above-described feature information includes the order of a plurality of functions constituting the partial line, and it is desirable that the search unit examines the match / mismatch of the partial lines based on the order of the plurality of functions. Alternatively, the above-described feature information includes an array of section lengths corresponding to each of a plurality of functions constituting the partial line, and the search means can determine whether the partial lines match or not based on the order of the section lengths. It is desirable to investigate. Further, it is desirable that the search means described above examines the match / mismatch of the partial lines based on the matching distance or the degree of correlation calculated using the parameters that specify the functions constituting the partial lines. The order of the plurality of functions constituting the partial line, the arrangement of the respective section lengths, and the parameters for specifying the plurality of functions are considered to be important characteristics representing the shape of the partial line. Therefore, by using these, it is possible to perform highly accurate fingerprint collation.

  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 stores feature amounts extracted in correspondence with a plurality of fingerprint images (these images are referred to as “registered fingerprint images”) whose similarity is compared with the captured verification fingerprint image during the verification process. . A specific example of the feature amount 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 a feature amount of 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 feature amount. For this purpose, the fingerprint verification processing unit 130 includes a preprocessing unit 132, a feature point extraction unit 134, a partial line extraction unit 136, a joint point extraction processing unit 138, a function approximation processing unit 140, a similarity determination processing unit 142, and a verification result. An output processing unit 144 is provided.

  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, 3, 4, and 6 and end points 2, 7, 10, and 13.

  The partial line extraction unit 136 extracts a ridge sandwiched between two feature points adjacent along the same ridge as a partial line. In the case of the collation fingerprint image shown in FIG. 2, for example, a part of the ridge sandwiched between the branch point 1 and the end point 13 is extracted as a partial line. By the way, for a closed ridge including only one branch point, the entire closed ridge is extracted as a partial line. Similarly, a closed ridge that does not include any branch point or end point is also extracted as a partial line. In this way, all partial lines included in the collation fingerprint image are extracted.

  FIG. 3 is a diagram showing an outline of a partial line extracted by the partial line extraction unit 136. FIG. 4 is a diagram showing a state of change in which the X coordinate of the extracted partial line is separated using a parametric variable. FIG. 5 is a diagram showing a state of change in which the Y coordinate of the extracted partial line is separated using a parametric variable.

  In FIG. 3, circles (◯) indicate pixels constituting the partial lines, and the numbers given to the circles indicate the order of the pixels when the partial lines are traced from one end. In addition, although the actual partial line is comprised by many pixels compared with the example shown in FIG. 3, in order to simplify description, in FIG. 3, a partial line shall be comprised by a small number of pixels. .

  For example, the partial line extraction unit 136 starts scanning by assigning a number “1” to the pixel corresponding to the feature point (ridge branching point or end point) at one end. In the example illustrated in FIG. 3, the partial line extraction unit 136 detects each pixel constituting the partial line while tracking the partial line in the clockwise direction with the pixel having the number “1” as the tracking start pixel. Each pixel is given a serial number “2”, “3”,. The pixel detection operation along the partial line is performed until the pixel to be detected reaches the other end of the partial line. FIG. 4 is a graph in which the number of each pixel constituting the partial line is plotted on the horizontal axis and the X coordinate value of each pixel is plotted on the vertical axis. FIG. 5 is a graph in which the numbers of the pixels constituting the partial line are plotted on the horizontal axis and the Y coordinate values of the pixels are plotted on the vertical axis. As described above, the partial line extraction unit 136 extracts the partial lines by separately recording the X coordinate value and the Y coordinate value using the serial number indicating the detection order given to each pixel constituting the partial line as a parameter. I do. In the above description, as an example, the X coordinate value and the Y coordinate value are recorded separately using a parameter, but the combination of the X coordinate value and the Y coordinate value is recorded without using the parameter. You may do it.

  The joint point extraction processing unit 138 extracts, for each partial line extracted by the partial line extraction unit 136, a joint point at which the partial line tendency changes. For example, a corner point at which the angle of the partial line suddenly changes is extracted as a junction point. Joint point extraction processing and function approximation processing are performed separately for each of the partial line focused on the X coordinate shown in FIG. 4 and the partial line focused on the Y coordinate shown in FIG.

  The function approximation processing unit 140 approximates a partial region (segmented region) divided by two junction points adjacent to each other using one function of a straight line, an arc, or a free curve. Then, feature information related to this approximation process is created. For example, when the segmented region can be approximated by a straight line, a straight line is used as the approximation function, and when the segmented area cannot be approximated by a straight line and can be approximated by an arc, an arc is used as the approximation function. When an arc cannot be approximated, a free curve is used as an approximation function. When a straight line is used as the approximate function, the sign indicating that the function used is a straight line and the parameter indicating the shape of the partitioned area approximated by the straight line are characteristic information about the approximate function corresponding to this partitioned area. Created as Similarly, when an arc is used as the approximation function, a sign indicating that the function used is an arc and a parameter indicating the shape of the segment area approximated by the arc are approximate functions corresponding to the segment area. As feature information. When a free curve is used as an approximate function, a sign indicating that the function used is a free curve and a parameter indicating the shape of the segmented region approximated by the free curve is an approximate function corresponding to this segmented region. As feature information.

It should be noted that the determination of which function can approximate the segmented area is based on whether the error between the segmented area and the approximate function (error obtained by the least squares method) is less than a predetermined value. It is done by examining whether. The parameter indicating the shape of the segmented region may be any parameter as long as the shape of the segmented region can be specified. For example, as disclosed in Japanese Patent No. 2646475, the following parameters are used. It may be.
(1) For a straight line: flag indicating a straight line, coordinates of the start point of a segmented area (2) For an arc: a flag indicating a circular arc, the coordinates of the start point of the arc, the coefficient of the central angle between joint points, existing between joint points Number of pixels to be used, coefficients of approximate function (Each coefficient when an arc is expressed by a linear combination of trigonometric functions, for example)
(3) In the case of a free curve: the number of dimensions of an approximate function indicating a free curve between junction points (≧ 3), the number of pixels existing between the junction points, the center of variation in pixel columns between the junction points, and the coefficient of the approximation function .

  The similarity determination processing unit 142 determines the similarity between the verification fingerprint image and each registered fingerprint image based on the feature information extracted corresponding to the verification fingerprint image, and selects a registered fingerprint image that matches the verification fingerprint image. decide. The feature information used for the similarity determination includes, in addition to the parameter indicating the shape of the section area described above, the partial line length of each partial line (the length of each partial line), and a plurality of functions constituting the dividing line. Included are the order, the section length (segment area length) corresponding to each of a plurality of functions composing the section line, the matching distance and the correlation degree of the functions composing the collation fingerprint image and the registered fingerprint image, etc. ing.

  6 and 7 are diagrams showing an outline of feature information extracted by each process of the partial line extraction unit 136, the junction point extraction processing unit 138, and the function approximation processing unit 140. FIG. A piece of feature information shown in FIG. 6 is extracted for one collation fingerprint image. In the example shown in FIG. 6, the collation fingerprint image of interest includes a plurality of partial lines indicated by partial lines 1, 2, 3,... (Each partial line length is a partial line length 1, 2, 3 ...). Each partial line is associated with an X-axis function table and a Y-axis function table.

  As shown in FIG. 7, the X-axis function table includes the total number of functions, the partial line length, the total number of sample points, the number of straight lines, the total length of straight lines, the number of arcs, the total length of arcs, the number of curves, and the total length of each curve. The section length, the number of sample points, the start point sample number (the serial numbers shown in FIGS. 3 and 4), the section length and parameters corresponding to each function are included. The total number of functions is the total number of functions included in the focused partial line and is equal to the number of segmented areas. The partial line length is the length of the partial line of interest. The number of straight lines is the number of segmented areas that are approximated by straight lines in the segmented areas constituting the target partial line. The total length of the straight line is a total value of the lengths of the divided areas approximated by straight lines in the divided areas constituting the target partial line. The number of arcs is the number of segmented areas approximated by arcs in each segmented area constituting the focused partial line. The total arc length is a total value of the lengths of the segment areas approximated by the arcs in the segment areas constituting the target partial line. The number of curves is the number of segmented regions that are approximated by a free curve in each segmented region constituting the focused partial line. The total curve length is the total value of the lengths of the segmented regions approximated by the free curve in the segmented regions constituting the target partial line. In FIG. 7, a plurality of functions corresponding to the “X-axis function” indicate functions that approximate each segmented area constituting the target partial line. It corresponds.

  The similarity determination processing unit 142 can know the number of partial lines by referring to the table shown in FIG. Further, the similarity determination processing unit 142 refers to the table shown in FIG. 7 to determine the order of a plurality of functions constituting each partial line and the section length corresponding to each of the plurality of functions constituting each partial line. It is possible to know the sequence of the (segmented area length). The Y-axis function table has the same contents.

  The collation result output processing unit 144 displays a 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 feature information shown in FIGS. 6 and 7 is 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 feature information. In order to specify a fingerprint image, it is necessary to extract feature information having the same content for many registered fingerprint images in advance and register it in the fingerprint DB 120.

  FIG. 8 is a diagram showing a configuration of a database creation apparatus that performs feature information extraction on a registered fingerprint image in advance and registers it in the fingerprint DB 120. The configuration shown in FIG. 8 may be provided as a part of the fingerprint verification apparatus shown in FIG. 1, but may be constructed separately from the fingerprint verification apparatus shown in FIG. The database creation device shown in FIG. 8 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 feature information of many 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 processing for extracting feature information 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 partial line extraction unit 223, a joint point extraction processing unit 224, a function approximation processing unit 225, and a file creation processing unit 226. Among these, the basic operations of the preprocessing unit 221, the feature point extraction unit 222, the partial line extraction unit 223, the joint point extraction processing unit 224, and the function approximation processing unit 225 except for the file creation processing unit 226 are shown in FIG. This is the same as each component having the same name in the fingerprint verification processing unit 130 shown, and a detailed description of the operation is omitted.

  The file creation processing unit 226 registers the extracted feature information for each registered fingerprint image in the fingerprint DB 120 as a set of files. The operation unit 230 is used to extract feature information corresponding to a 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 registration contents of feature information and accompanying information and displaying various operation screens necessary for registration.

  By using the database creating apparatus having such a configuration, the feature information of a plurality of registered fingerprint images having basically the same contents as the feature information of the collation fingerprint image shown in FIGS. 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 partial line extraction units 136 and 223 are partial line extraction units. In addition, the junction point extraction processing units 138 and 224, the function approximation processing units 140 and 225 are function approximation units, the similarity determination processing unit 142 is a search unit, the fingerprint DB 120 is a feature information storage unit, and a file creation processing unit 226 is Each corresponds to the feature information storage processing means. 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 partial line extraction units 136 and 223 is the operation of the partial line extraction step, and the operation performed by the junction point extraction processing units 138 and 224 and the function approximation processing units 140 and 225 is the operation of the function approximation step. The operation performed by the determination processing unit 142 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. 9 is a flowchart showing an operation procedure for extracting feature information about the collation fingerprint image. 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). Next, the feature point extraction unit 134 extracts branch points and end points included in the collated fingerprint image after the preprocessing is completed as feature points (step 102). Further, the partial line extraction unit 136 extracts a part of the ridge divided by the branch point and the end point included in the thinned ridge as a partial line (step 103). This partial line extraction is performed for all ridges included in the entire range of the acquired collation fingerprint image or a predetermined range (for example, a certain range including the center of the collation fingerprint image).

  Next, the joint point extraction processing unit 138 selects one partial line (step 104), and extracts joint points included in this partial line (step 105). The function approximation processing unit 140 performs function approximation processing on each segmented region segmented by the extracted joint points to create feature information (step 106). Thereafter, the joint point extraction processing unit 138 determines whether or not there is another unprocessed partial line (step 107). If there is, the affirmative determination is made, and the partial line selection process in step 104 is repeated. On the other hand, if there is no unprocessed partial line, a negative determination is made in the determination in step 107, and a series of processes from the acquisition of the collation fingerprint image to the creation of the feature information ends.

  FIG. 10 is a flowchart illustrating an operation procedure of the similarity determination processing unit 142 that performs fingerprint matching using feature information created from a matching fingerprint image. First, the similarity determination processing unit 142 selects one registered fingerprint image (step 200), selects one partial line included in the collation fingerprint image (step 201), and sets the partial line length of the partial line. It is determined whether or not a partial line having a close length is included in the registered fingerprint image (step 202). If it is included, an affirmative determination is made, and whether or not these two partial lines included in the verification fingerprint image and the registered fingerprint image match is determined according to the following procedure. When there are a plurality of partial lines having the same length, this determination is performed for each partial line.

  First, the similarity determination processing unit 142 performs matching processing using the first feature information corresponding to the partial line of the verification fingerprint image and the second feature information corresponding to the partial line of the registered fingerprint image, and performs matching processing. The distance M and the correlation degree S are calculated using the following formula (step 203).

M = ‖f-g‖
S = <f, g> / (‖f‖ × ‖g‖)
Here, ‖ and ‖ indicate norms, and <•> indicates an inner product. Further, f is a vector having the first feature information (three functions 1 to 3) as a component. g is a vector having the second feature information as a component. For example, the parameters shown in FIG. 7 (parameters that specify the functions constituting the partial lines) are used as the first and second feature information.

  The matching distance M indicates the length of the difference vector between the two vectors f and g. Correlation S indicates a cosine value (cos θ) of an angle θ formed by two vectors f and g. When the first feature information corresponding to the partial line of the verification fingerprint image and the second feature information corresponding to the partial line of the registered fingerprint image are very close, the lengths and directions of the two vectors f and g are Since they are similar, the matching distance M is small and the correlation degree S is close to 1. Since there are two or more sets of feature information corresponding to the partial lines, the matching distance M and the correlation degree S are calculated using each feature information, and the calculation results may be summed up for all the feature information.

  Next, the similarity determination processing unit 142 determines whether the total matching distance M for the entire partial line of interest is equal to or less than a predetermined value (step 204). The case where it is equal to or less than the predetermined value is a case where the shapes of the two partial lines are very close to each other. In this case, an affirmative determination is made, and then the similarity determination processing unit 142 updates the count value N of the matching partial line segments (step 205), and whether the count value N has reached a predetermined value. It is determined whether or not (step 206). The case where the count value N reaches a predetermined value is a case where the shape of the partial line for the predetermined value included in the collation fingerprint image matches the shape of the partial line for the predetermined value included in the registered fingerprint image. It is determined that the verification fingerprint image and the registered fingerprint image match. In this case, an affirmative determination is made in the determination in step 206, and the collation result output processing unit 144 outputs (displays) the accompanying information corresponding to the registered fingerprint image as a collation result (step 207).

  On the other hand, if the number of partial lines having the same shape does not reach the predetermined value, a negative determination is made in step 206, and the similarity determination processing unit 142 then selects another unprocessed image included in the verification fingerprint image. It is determined whether there is a partial line (step 208). If there is another partial line, an affirmative determination is made, and the process returns to step 201 to repeat the selection operation of the other partial line. Further, when the shape matching determination is completed for all the partial lines included in the verification fingerprint image, a negative determination is made in the determination in step 208, and then the similarity determination processing unit 142 performs other verification processing that has not been verified. It is determined whether there is a registered fingerprint image (step 209). If there is another registered fingerprint image, an affirmative determination is made, and the process returns to step 200 to repeat the operation of selecting another registered fingerprint image. If there is no other registered fingerprint image, a negative determination is made in the determination in step 209, and a collation result indicating that there is no registered fingerprint image that matches the collation fingerprint image is output (step 207). In this way, a series of fingerprint collation operations are completed.

  In this way, the branch points and end points included in the fingerprint ridges are a major feature for specifying a fingerprint, and the shape of the ridges sandwiched between these branch points and end points is also a large feature for specifying a fingerprint. It is considered a feature. In the fingerprint collation device according to the present embodiment, by extracting a partial line defined by these branch points and end points, by performing function approximation on the shape of the partial line and performing fingerprint collation using the resulting feature information Therefore, it is possible to perform high-precision fingerprint matching based on the detailed shape of the fingerprint.

  In addition, it is possible to easily search for similar registered fingerprint images by sequentially reading out the feature information of registered fingerprint images stored in advance and comparing them with the feature information of collated 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 apparatus shown in FIG. 8, it is possible to appropriately add a registered fingerprint image to be collated.

  In addition, by performing partial line extraction processing and function approximation processing separately for the X coordinate and Y coordinate, the function approximation processing can be performed by focusing on one variable, thereby simplifying the processing.

  Further, the search means described above checks for a match / mismatch between the partial line included in the collation fingerprint image and the partial line included in the registered fingerprint image, and when the number of matching partial lines exceeds a predetermined value, It is desirable to determine that the registered fingerprint image matches the verification fingerprint image. Thereby, it is possible to determine that the registered fingerprint image in which most of the shapes of the ridges or valleys match is matched with the verification fingerprint image, and the accuracy of fingerprint verification can be improved.

  Further, the feature information described above includes the partial line length as the length of the partial line, and the search means can check the partial line match / mismatch for the partial lines having a close partial line length value. desirable. As a result, the number of partial lines for checking match / mismatch can be reduced, and the processing can be simplified and the processing time can be shortened.

  In the present embodiment, the matching / non-matching of the partial lines is determined based on the matching distance calculated using the parameter that specifies the function constituting the partial lines. A parameter that specifies a plurality of functions that constitute a partial line is considered to be an important feature that represents the shape of the partial line. Therefore, by using these, it is possible to perform highly accurate fingerprint collation.

  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, a fingerprint collation program (each step shown in FIGS. 9 and 10) stored in a ROM or RAM or other storage device (hard disk device or the like) is executed, or a fingerprint collation processing unit 130 or a database creation unit 220 is executed. The program for realizing the function of each part of the above 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.

  In the above-described embodiment, whether the partial line matches or does not match is determined based on the matching distance M calculated using a parameter that specifies a plurality of functions constituting the partial line. You may do it. Or you may make it use the order of several functions which comprise a partial line, and the arrangement | sequence of each section length. That is, when the order of a plurality of functions composing the partial line is the same, or when the length sequence of each segmented area divided by the junction point (corresponding to the position of the junction point) is the same, The shape of the dividing line may be the same.

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 outline of the partial line extracted by the partial line extraction part. It is a figure which shows the mode of the change which isolate | separated the X coordinate of the extracted partial line using the parametric variable. It is a figure which shows the mode of the change which isolate | separated the Y coordinate of the extracted partial line using the parametric variable. It is a figure which shows the outline | summary of the feature information extracted by each process of a partial line extraction part, a junction point extraction process part, and a function approximation process part. It is a figure which shows the outline | summary of the feature information extracted by each process of a partial line extraction part, a junction point extraction process part, and a function approximation process part. It is a figure which shows the structure of the database preparation apparatus which extracts characteristic information about a registered fingerprint image beforehand, and registers with respect to fingerprint DB. It is a flowchart which shows the operation | movement procedure which extracts the characteristic information about a collation fingerprint image. It is a flowchart which shows the operation | movement procedure of the similarity determination process part which performs fingerprint collation using the characteristic information produced from the collation fingerprint image.

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 Partial line extraction unit 138, 224 Joint point extraction processing unit 140, 225 Function approximation processing unit 142 Similarity determination processing unit 144 Verification result output Processing unit 150, 230 Operation unit 160, 240 Display unit 220 Database creation unit 226 File creation processing unit

Claims (11)

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;
Partial line extraction means for extracting the ridge or valley line sandwiched between two adjacent feature points as a partial line;
Function approximating means for approximating the shape of the partial line extracted by the partial line extracting means with one or a plurality of functions;
Search means for searching for a registered fingerprint image similar to the verification fingerprint image or accompanying information corresponding to the registered fingerprint image based on feature information related to the approximation processing by the function approximation means;
A fingerprint collation apparatus comprising: In claim 1,
Feature information storage means for storing feature information created in association with processing for approximating the shape of a partial line included in the registered fingerprint image with one or a plurality of functions is stored for each of the plurality of registered fingerprint images. ,
The search means performs search processing by comparing feature information corresponding to the collation fingerprint image and feature information corresponding to the plurality of registered fingerprint images stored in the feature information storage means. A fingerprint verification device. In claim 2,
When the feature information corresponding to the registered fingerprint image is acquired using the fingerprint image capturing means, the feature point extracting means, the partial line extracting means, and the function approximating means, the feature information is stored in the feature information. A fingerprint collation apparatus further comprising characteristic information storage processing means for storing in the means. In any one of Claims 1-3,
The partial line extracting means separately extracts coordinate values for each of the X coordinate and the Y coordinate of each pixel constituting the partial line,
The function approximation unit separately performs a function approximation process corresponding to the X coordinate and a function approximation process corresponding to the Y coordinate based on the coordinate values extracted by the partial line extraction unit. . In any one of Claims 1-4,
The search means checks for a match / mismatch between the partial line included in the verification fingerprint image and the partial line included in the registered fingerprint image, and when the number of matching partial lines exceeds a predetermined value A fingerprint collation apparatus that performs a determination that the registered fingerprint image matches the collation fingerprint image. In claim 5,
The feature information includes a partial line length as a length of the partial line,
The fingerprint collation apparatus characterized in that the search means examines the partial lines that are close in value of the partial line length for the partial line match / mismatch. In claim 5 or 6,
The feature information includes an order of a plurality of functions constituting the partial line,
The fingerprint collation apparatus characterized in that the search means examines the partial line match / mismatch based on the order of the plurality of functions. In claim 5 or 6,
The feature information includes an array of section lengths corresponding to each of a plurality of functions constituting the partial line,
The fingerprint collation apparatus characterized in that the search means examines the match / mismatch of the partial lines based on the sequence of the section lengths. In claim 5 or 6,
The fingerprint collation apparatus characterized in that the search means checks the partial line match / mismatch based on a matching distance or a correlation calculated using a parameter specifying a function constituting the partial line. 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;
A partial line extracting step of extracting the ridge or the valley line sandwiched between two adjacent feature points as a partial line;
A function approximating step for approximating the shape of the partial line extracted by the partial line extracting means with one or a plurality of functions;
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, based on feature information related to the approximation processing in the function approximation step;
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;
Partial line extraction means for extracting the ridge or valley line sandwiched between two adjacent feature points as a partial line;
Function approximating means for approximating the shape of the partial line extracted by the partial line extracting means with one or a plurality of functions;
Search means for searching for a registered fingerprint image similar to the verification fingerprint image or accompanying information corresponding to the registered fingerprint image based on feature information related to the approximation processing by the function approximation means;
Fingerprint verification program that makes it work.

Images