JP6526494B2 - INFORMATION PROCESSING PROGRAM AND INFORMATION PROCESSING DEVICE - Google Patents

Description

  The present invention relates to an information processing program and an information processing apparatus that analyze an image and create collation information used for collation of biological information.

  In recent years, various fingerprint authentication apparatuses that can be mounted on mobile devices such as smartphones and notebook computers have been studied. For example, Patent Document 1 discloses a personal identification apparatus that is less susceptible to disturbances such as the inclination of a finger with respect to a fingerprint sensor by using information obtained by frequency spectrum converting a fingerprint image as collation information used for collation.

Patent No. 3057590 specification

  With the miniaturization of fingerprint sensors mounted on mobile devices, the images of fingerprints acquired are smaller than before. When the user performs a fingerprint input operation, the finger of the hand holding the mobile device often contacts the fingerprint sensor mounted on the mobile device. In this case, the user must move the finger in an unnatural direction, so the fingerprint input operation tends to be unstable. That is, an image acquired under the condition that the position and the angle are different from those at the time of registration is easily acquired. Therefore, there is a need for a technique for creating matching information that is less susceptible to biological information acquisition conditions even when the size of the image is smaller than in the past.

  An object of the present invention is to provide an information processing program and an information processing apparatus capable of creating collation information which is not easily influenced by acquisition conditions of biometric information even when the size of an image representing biometric information is smaller than the conventional one. It is to be.

  An information processing program according to a first aspect of the present invention is characterized in that an image acquisition step of acquiring an image, and the image acquired in the image acquisition step is analyzed in a computer provided with a processor and storage means. Extraction step of extracting points, feature point acquisition step of acquiring three of the feature points extracted in the extraction step, and geometry of a triangle represented by the three feature points acquired in the feature point acquisition step Calculation step of calculating a scientific feature amount, a selection step of selecting two feature points as attention points from the three feature points obtained in the feature point acquisition step, and the selection step A first point on a line segment connecting the two selected target points, the first point corresponding to the position of the first reference point being a point determined based on the geometric feature quantity Corresponding to the first information for each of the plurality of first information acquired in the reference point acquiring step of acquiring information for each of the plurality of first reference points different in position and the plurality of first information acquired in the reference point acquiring step Color information corresponding to a second reference point, which is a point on the circumference of a circle having a predetermined radius centered on the first reference point to be extracted, which is a point determined based on the geometrical feature value; 2. A sample, which is information in which the second information corresponding to the position of the two reference points is associated, is acquired for each of the plurality of second reference points whose positions are different from each other, and the plurality of acquired samples; A sample information acquiring step for performing processing of using information associated with one information as sample information, and the plurality of first reference points based on the sample information acquired in the sample information acquiring step Each of them is information in which a frequency component of change of the color information with respect to the second information is calculated, and the frequency component calculated for each of the plurality of first reference points is associated with the first information. Storage control for storing frequency information acquisition step for acquiring frequency information, and information associating the sample information and the frequency information with the geometric feature amount as collation information used for collation of biological information It is a program for executing steps.

  If collation information is generated based on the information processing program of the first aspect, collation information including sample information and frequency information is acquired based on the feature points extracted from the image. The sample information and the frequency information are information representing a change in color information of points around a line segment connecting two focused points selected from among the extracted feature points. For this reason, even when the number of feature points extracted from the image is small, it is possible to generate information that can be accurately collated. The sample information and the frequency information are information acquired about the point determined based on the geometric feature. Therefore, if the verification information is generated based on this program, the information represented by the image (for example, represented by a fingerprint image or a vein image) as compared to the case where the information is acquired regarding the point where the geometric feature is not considered. It is possible to generate verification information in which the influence of rotation or movement of the biometric information) with respect to the reference is reduced.

  The selection step of the information processing program according to the first aspect may select each of the three sets of two attention points corresponding to a combination of all two points of the three feature points. If the collation information is generated based on the information processing program in this case, more collation information is generated as compared with the case where one set of two attention points is selected.

  The information processing program according to the first aspect may include a collating step of collating the collation information for test to be collated with the collation information for reference stored in the storage unit. If collation of biological information is executed based on the information processing program in this case, sample information and frequency information are acquired based on the feature points extracted from the image, so the number of feature points extracted from the image is small. Also, it is possible to match with high accuracy. The sample information and the frequency information are information acquired about the point determined based on the geometric feature. Therefore, when collating based on this program, the influence of rotation or movement of the biological information with respect to the reference is reduced compared to the case where information is acquired about the point where the geometric feature is not considered. Accurate matching results can be obtained.

  The feature point acquiring step of the information processing program according to the first aspect is characterized in that, among the plurality of feature points extracted in the extracting step, the plurality of feature points within a predetermined range determined based on the predetermined radius. In the case of selecting one feature point, a plurality of sets of the three feature points corresponding to all combinations are acquired, and the selecting step is performed by using the plurality of sets of three feature points acquired in the feature point acquiring step. Among these, based on the geometric feature quantity calculated in the feature quantity calculation step, processing is performed to select the two attention points for the three feature points whose area of the triangle is equal to or larger than a predetermined value, In the matching step, the geometric features of the test triangle represented by the test matching information and the reference triangle represented by the reference matching information. A pair extraction step of extracting a pair of the test triangle and the reference triangle whose similarity is equal to or less than a threshold value by comparing in order of decreasing area of the triangle; and extracting the pair extraction step The information processing apparatus may further include a post extraction extraction step of collating the sample information and the frequency information corresponding to the test triangle and the sample information and the frequency information corresponding to the reference triangle.

  When the positions of the three feature points acquired in the feature point acquisition step are close to each other, and the area of the triangle represented by the three feature points is less than a predetermined value, the area of the triangle is greater than or equal to the predetermined value There is less change in the color information indicated by the sample information than in the case of. For this reason, if matching of biometric information is executed based on the information processing program in this case, if the area of the triangle represented by the three feature points is less than a predetermined value, the matching is performed based on the three feature points. No information is obtained. Therefore, according to the program of the present invention, compared with the case where the matching information is generated based on the three feature points where the area of the triangle is less than the predetermined value, the accuracy of the matching using the matching information can be enhanced.

An information processing apparatus according to a second aspect of the present invention extracts feature points by analyzing storage means for storing information, image acquisition means for acquiring an image, and the image acquired by the image acquisition means. Extraction means, feature point acquisition means for acquiring three of the feature points extracted by the extraction means, and geometrical feature quantities of triangles represented by the three feature points acquired by the feature point acquisition means Among the three feature points acquired by the feature point acquisition means, selection means for selecting two feature points as the focus points, and 2 selected by the selection means First information corresponding to a position of a first reference point which is a point on a line segment connecting the two attention points and which is a point determined based on the geometrical feature amount, Second A predetermined radius centered on the first reference point corresponding to the first information for each of the plurality of first information acquired by the reference point acquisition means acquired for each of the reference points and the plurality of first information acquired by the reference point acquisition means Color information corresponding to a second reference point which is a point on the circumference of the circle and is a point determined based on the geometric feature, and second information corresponding to the position of the second reference point Is obtained for each of the plurality of second reference points whose positions are different from each other, and information obtained by associating the plurality of obtained samples with the first information is used as sample information. Said color for said second information for each of said plurality of first reference points based on sample information acquisition means for performing processing and said sample information acquired by said sample information acquisition means Frequency information acquiring means for calculating frequency components of change of information, and acquiring frequency information which is information in which the frequency components calculated for each of the plurality of first reference points are associated with the first information; Storage control means for storing information in which sample information and the frequency information are associated with the geometric feature amount as collation information used for collation of biological information.

  The information processing apparatus according to the second aspect acquires sample information and frequency information based on feature points extracted from an image, so that matching information can be accurately collated even when the number of feature points extracted from an image is small. Can be generated. The sample information and the frequency information are information acquired about the point determined based on the geometric feature. Therefore, the information processing apparatus is based on the information represented by the image (for example, the biometric information represented by the fingerprint image or the vein image) as compared to the case where the information is acquired about the point where the geometric feature is not considered. It is possible to generate verification information in which the influence of rotation or movement with respect to the user is reduced.

FIG. 2 is a block diagram of an information processing apparatus 10; FIG. 2 is a functional block diagram of the information processing apparatus 10. It is a flowchart of collation information processing. It is a flowchart of the image-analysis process performed by the collation information processing of FIG. It is an image 41 representing the reference biometric information acquired from the biometric information acquisition device 8. It is a figure explaining the process of extracting the feature points P1 to P11 from the image 41 of FIG. It is executed in the image analysis process of FIG. It is a flowchart of collation information acquisition processing. It is explanatory drawing of the local coordinate system 60. FIG. It is explanatory drawing of the setting method of a 1st reference point and a 2nd reference point. FIG. 7 is an explanatory diagram of a sample 71, sample data 72, and sample information 73. It is explanatory drawing of the collation information 75 for a reference containing the sample information, the sample image, the frequency information, and the frequency image acquired for every two attention points. It is explanatory drawing of the process of calculating a frequency component based on the change of the color information with respect to 2nd information represented by sample data. It is explanatory drawing of collation information registered into DB28. It is a figure which shows the image 51 for a test, and the feature points PT1 to PT3 contained in the image 51. FIG. It is explanatory drawing of the collation information 85 for a test including the sample information, the sample image, the frequency information, and the frequency image which were acquired for every two attention points about the image 51. FIG. It is a flowchart of the collation process performed by collation information processing of FIG. It is explanatory drawing of the process of collating the collation information for a test, and the collation information for a reference. It is explanatory drawing of the process of calculating the similarity of the frequency information for a test, and the frequency information for a reference. It is explanatory drawing of the process of calculating the similarity of the frequency information for a test, and the frequency information for a reference. It is explanatory drawing of the process of calculating the similarity of the frequency information for a test, and the frequency information for a reference. It is explanatory drawing of the process of calculating the similarity of the sample information for a test, and the sample information for a reference. It is explanatory drawing of the process of calculating the similarity of the sample information for a test, and the sample information for a reference. It is explanatory drawing of the process of calculating the similarity of the sample information for a test, and the sample information for a reference.

  One embodiment of the present invention will be described with reference to the drawings. The specific plural numerical values exemplified in the following embodiments are one example, and the present invention is not limited to these plural numerical values. In the following description, image data is simply referred to as an "image".

  The information processing apparatus 10 will be described with reference to FIG. The information processing apparatus 10 is an electronic device provided with a function of authenticating a user by biometric information. The biometric information is selected from various biometric information such as, for example, a face image, a fingerprint, a vein, and an iris. The biometric information of the present embodiment is a fingerprint. In the present embodiment, the information processing apparatus 10 is a known smart phone. The information processing apparatus 10 analyzes an image obtained by capturing a fingerprint, generates matching information for reference necessary for matching using the fingerprint, and stores the database (DB) 28 stored in the flash memory 4 of the information processing apparatus 10 Have a function to store in The information processing apparatus 10 analyzes an image obtained by capturing a fingerprint, generates test verification information necessary for verification using the fingerprint, and generates the generated test verification information and the reference information stored in the DB 28. It has a function of collating with the collation information of

  As shown in FIG. 1, the information processing apparatus 10 includes a CPU 1, a ROM 2, a RAM 3, a flash memory 4, a communication I / F 5, a display unit 6, a touch panel 7, and a biological information acquisition apparatus 8. The CPU 1 is a processor that controls the information processing apparatus 10. The CPU 1 is electrically connected to the ROM 2, the RAM 3, the flash memory 4, the communication I / F 5, the display unit 6, the touch panel 7, and the biological information acquisition apparatus 8. The ROM 2 stores a BIOS, a boot program, and initial setting values. The RAM 3 stores various temporary data. The flash memory 4 stores a program that the CPU 1 executes to control the information processing apparatus 10, an OS (Operating System), and a DB 28. The communication I / F 5 is a controller for performing communication with an external device. The display unit 6 is a liquid crystal display. The touch panel 7 is provided on the surface of the display unit 6. The biometric information acquisition device 8 acquires an image obtained by imaging the biometric information. The biological information acquisition device 8 of the present embodiment is a capacitive type area sensor. In detail, the biological information acquisition device 8 is a sensor that determines the unevenness of the fingerprint from the charge amount of the matrix surface electrode, and represents color information with a gradation value of 256 gradations for each pixel. Color information is information representing a color. The resolution is, for example, 508 dpi (dots per inch).

  An overview of the functions of the information processing apparatus 10 will be described with reference to FIG. The information processing apparatus 10 includes a biological information acquisition apparatus 8, an image acquisition unit 21, a feature point extraction unit 22, a geometric feature quantity calculation unit 23, a sample information acquisition unit 24, a frequency information acquisition unit 25, a collation unit 27, and a registration unit. 26, and the DB 28, and the processing corresponding to each functional block is executed by the CPU 1 (see FIG. 1).

  The biometric information acquisition device 8 outputs an image to the image acquisition unit 21. The image acquisition unit 21 acquires an image output from the biological information acquisition device 8. The feature point extraction unit 22 extracts two-dimensional coordinates of feature points in the image coordinate system based on the image acquired from the image acquisition unit 21. The two-dimensional coordinates of the image coordinate system of this embodiment are coordinates set in pixel units based on the position of the pixel in the image. The two-dimensional coordinates of the image coordinate system will be described later. The feature points are, for example, points extracted according to the method of extraction of magazines (see, for example, Japanese Patent No. 1289457) and Scale-Invariant Feature Transform (SIFT) (see, for example, US Patent No. 6,711,293). Or at least one of the points extracted according to. The feature points of this embodiment are extracted according to the method of extracting minutia described in Japanese Patent No. 1289457.

  The geometric feature amount calculation unit 23 acquires coordinates of feature points within a predetermined range among the plurality of feature points extracted by the feature point extraction unit 22. The geometric feature quantity calculation unit 23 selects three feature points from among a plurality of feature points whose coordinates are acquired, and calculates a geometric feature quantity of a triangle represented by the selected three feature points. Do. For example, geometric feature quantities include coordinates of three feature points, inclination (vector) of a line segment represented by two notable points selected from among the three feature points, side length of triangle, triangle It is suitably selected from the inside angle of and the area of a triangle. The coordinates of the three feature points are represented by absolute coordinates or relative coordinates of the image coordinate system. In addition to the coordinates of the image coordinate system, the geometric feature quantity calculation unit 23 of the present embodiment sets a local coordinate system in addition to the coordinates of the image coordinate system, and the coordinates of the three feature points in the local coordinate system Represents The local coordinate system will be described later. The geometric feature amount calculation unit 23 according to the present embodiment acquires a plurality of sets of three feature points corresponding to all combinations in the case of selecting three feature points from a plurality of feature points within a predetermined range. , Calculate geometric features for each.

  The sample information acquisition unit 24 acquires sample information based on the geometrical feature quantities of the three feature points acquired by the geometrical feature quantity calculation unit 23 and a predetermined acquisition condition. The sample information is information in which color information is associated with information (first information and second information) corresponding to a position indicating an acquisition condition of the color information. The sample information is acquired, for example, by the following procedure. Two feature points are respectively selected as focus points from the three feature points. The sample information acquiring unit 24 of the present embodiment is a triangle represented by three feature points based on the geometric feature amount among the plurality of sets of three feature points acquired by the geometric feature amount calculating unit 23. A process of selecting two notable points is executed for three feature points whose area is greater than or equal to a predetermined value. The sample information acquisition unit 24 determines a point on a line segment connecting the two selected target points, which is determined based on the geometric feature as a first reference point. First information is acquired for each of a plurality of first reference points whose positions are different from each other. The first information is information corresponding to the position of the first reference point. The first information may be information defining the position of the first reference point with respect to the reference, for example, absolute coordinates (for example, coordinates of the image coordinate system), relative coordinates (for example, coordinates of the local coordinate system), and the reference It may be an angle to the If the acquisition order of the first reference points is determined with respect to the reference, the first information may be the acquisition order of the first reference points. A plurality of samples are acquired for each of the plurality of acquired first information. The sample is information in which color information corresponding to the second reference point is associated with the second information. The second reference point is a point on the circumference of a circle having a predetermined radius centered on the first reference point corresponding to the first information, and is a point determined based on the geometric feature quantity. The second information is information corresponding to the position of the second reference point. The second information may be information defining the position of the second reference point with respect to the reference, for example, absolute coordinates (for example, coordinates of the image coordinate system), relative coordinates (for example, coordinates of the local coordinate system), and the reference It may be an angle to the If the acquisition order of the second reference points is determined with respect to the reference, the second information may be the acquisition order of the second reference points. The plurality of samples are samples obtained for each of a plurality of second reference points that are different in position from each other. Information in which the plurality of acquired samples are associated with the first information is used as sample information.

  The frequency information acquisition unit 25 acquires frequency information based on the sample information acquired from the sample information acquisition unit 24. The frequency information calculates, for each of the plurality of first reference points, frequency components of the change in color information with respect to the second information, and associates the calculated frequency component for each of the plurality of first reference points with the first information. Information. The frequency component of the present embodiment is a one-dimensional group delay spectrum calculated according to a known method (see Patents Nos. 3057590 and 379 9057).

  The registration unit 26 causes the DB 28 to store reference verification information used for verification of biometric information. The matching information is information in which sample information and frequency information are associated with geometric feature quantities. In the present embodiment, collation information is stored for each of three feature points of all combinations selected from valid feature points. The collation unit 27 collates the test collation information with the reference collation information stored in the DB 28. More specifically, the matching unit 27 sets each geometric feature of the test triangle represented by the test match information and the reference triangle represented by the reference match information to a triangle. A pair of test triangles and reference triangles whose similarity is equal to or less than a threshold value is extracted by comparing them in descending order of area. The collation unit 27 collates sample information and frequency information corresponding to the extracted test triangle with sample information and frequency information corresponding to the reference triangle.

1. 3. Process at the time of registration Referring to FIG. 3, the collation information processing executed by the information processing apparatus 10 will be described by way of an example in which collation information is registered. The verification information processing is started when the user inputs a start instruction. The start instruction includes an instruction as to whether the collation information acquired from the image is registered in the DB 28 as collation information for reference, or whether the collation information is to be collated with the collation information for reference registered in the DB 28. When the CPU 1 of the information processing apparatus 10 detects the input of the start instruction of the collation information processing, the CPU 1 reads out the information processing program for executing the collation information processing stored in the flash memory 4 to the RAM 3 and instructs Then, the processing of each step described below is performed. In the present embodiment, feedback processing that prompts re-input is performed until biological information that satisfies the requirements for extracting feature points (for example, the sharpness of an image) is acquired. The biometric information acquired by collation information processing shall satisfy the requirement which extracts collation information using an algorithm from biometric information. The information and data acquired or generated in the process of processing are stored in the RAM 3 as appropriate. Various setting values necessary for the process are stored in advance in the flash memory 4. Hereinafter, the steps are abbreviated as "S".

  As shown in FIG. 3, the CPU 1 executes an image analysis process (S1). The image analysis process will be described with reference to FIG. When the biological information acquisition device 8 detects a touch of a finger, the biological information acquisition device 8 outputs, to the CPU 1, a signal capable of specifying an image obtained by photographing a fingerprint. The CPU 1 receives a signal output from the biological information acquisition device 8. As shown in FIG. 4, the CPU 1 acquires an image based on the received signal (S11). In S11, for example, an image 41 shown in FIG. 5 is acquired. In the image 41, two-dimensional coordinates of an image coordinate system indicated by Xp and Yp in FIG. 5 are set. The position of the upper left pixel of the image 41 is set as the origin of the two-dimensional coordinates 45 (see FIG. 6) of the image coordinate system. The positions of pixels separated from the origin of the two-dimensional coordinate 45 by x pixels in the Xp plus direction and separated from the origin by y pixels in the Yp plus direction are denoted as coordinates (x, y). The image 41 is a square image representing a shooting range of a square of 1 cm square and having 192 pixels in the Xp direction (horizontal direction) and 192 pixels in the Yp direction (vertical direction). In the two-dimensional coordinates 45 of the image coordinate system, each of the points P1 to P11 is within the range 43 representing the size of the image 41. Although not shown, known preprocessing is appropriately performed on the image acquired in S11.

  The CPU 1 extracts feature points from the image acquired in S11 (S12). The CPU 1 of the present embodiment represents a point representing an end point of a dead end of a ridge, which is a series of convex portions of a fingerprint, and a bifurcated branch point according to a known method (see, for example, Japanese Patent No. 1289457). Extract each of the points as feature points. As shown in FIG. 6, from the image 41, each of a point representing an end point surrounded by a circle 42 and a point representing a branch point is extracted as a feature point. The eleven feature points extracted from FIG. 41 are referred to as points P1 to P11.

  The CPU 1 extracts valid feature points from the feature points extracted in S12, and executes processing for obtaining the number J of valid feature points (J is an integer of 0 or more) (S13 to S16). The CPU 1 of the present embodiment sets feature points within the range 44 as valid feature points, and sets feature points outside the range 44 as invalid feature points. The range 44 is a rectangular range in which four sides are 15 pixels inside of the rectangle indicating the range 43 representing the size of the image 41. The feature points within the range 44 are regarded as effective feature points in order to obtain feature points that can be set within the range 43 with a second reference point to be described later. Information for specifying the range 44 is predetermined based on acquisition conditions of the second reference point described later, and is stored in the flash memory 4.

  Specifically, the CPU 1 acquires one coordinate of a feature point not subjected to the process of S13 from the feature points extracted in S12 (S13). The CPU 1 determines whether the coordinates acquired in S13 are within the range 44 (S14). The CPU 1 sets the point inside the boundary of the range 44 and the point on the boundary of the range 44 within the range 44. If the coordinates are within the range 44 (S14: YES), the CPU 1 sets the feature point indicated by the coordinates obtained in S13 as a valid feature point and increments the number J by 1 (S15). The initial value of the number J is zero. The points P1 to P11 of the specific example are all within the range 44 (S14: YES). Therefore, the number J in the specific example is finally 11. If the coordinates are out of the range 44 (S14: NO), or after S15, the CPU 1 determines whether the process of S13 has been performed for all of the feature points extracted in S12 (S16). If there is a feature point whose coordinates are not acquired in the process of S13 (S16: NO), the CPU 1 returns the process to S13. When the process of S13 is executed for all of the feature points extracted in S12 (S16: YES), the CPU 1 determines whether the number J is larger than 2 (S17). When the number J is 2 or less (S17: NO), the CPU 1 ends the image analysis processing, and returns the processing to the collation information processing of FIG.

The number J in the specific example is 11 and is larger than 2 (S17: YES). In this case, the CPU 1 calculates all combinations in the case of selecting three feature points from the number J of valid feature points (S18). In the specific example, the number J is 11, and the CPU 1 calculates 165 combinations of ₁₁ C ₃ . The CPU 1 selects one combination for which S19 is not executed from among the combinations calculated in S18, and acquires coordinates of three feature points indicated by the selected combination (S19). The case where the CPU 1 acquires two-dimensional coordinates of the image coordinate system for each of the points P1, P4, and P8 in FIG. 6 as three feature points will be described as a specific example. The CPU 1 calculates the area of a triangle connecting the three feature points based on the coordinates obtained in S19 (S20). The CPU 1 determines whether the area calculated in S20 is larger than the threshold (S21). S <b> 20 and S <b> 21 are processing for extracting three feature points to be subjected to matching information acquisition processing described later. The three feature points acquired in S19 may be in positions relatively close to one another, such as points P1, P2, and P3, for example. Like points P1, P2 and P4, they may be on substantially the same straight line. In these cases, when the collation information is acquired according to the procedure described later, the number of samples may be reduced or a plurality of similar samples may be acquired, so that collation information suitable for collation may not be obtained. Therefore, when the area of the triangle is equal to or less than the threshold, the CPU 1 of the present embodiment does not acquire the matching information based on the coordinates of the three feature points. If the area is equal to or less than the threshold (S21: NO), the CPU 1 discards the combination of the three feature points whose coordinates are obtained in S19 (S24), and executes the process of S25 described later.

  In the specific example, it is determined that the area is larger than the threshold (S21: YES), and the CPU 1 executes the collation information acquisition process (S22). The collation information acquisition processing is processing for acquiring collation information used for collation of biological information based on the coordinates of the three feature points acquired in S19. As shown in FIG. 7, in the matching information acquisition process, first, the CPU 1 calculates the distance d between two points included in the three feature points based on the coordinates acquired in S19 of FIG. 4 (S32). The distance d is the length of each side of the triangle represented by the three feature points. In the specific example, the distance between points P1 and P4, the distance between points P4 and P8, and the distance between points P8 and P1 are calculated.

  The CPU 1 sets a local coordinate system based on the calculation result of S32 (S33). The local coordinate system is relative coordinates set for each triangle based on the coordinates of the three feature points acquired in S19. Specifically, the CPU 1 sets the Xk axis of the local coordinate system on the line segment connecting the two longest points among the three distances d calculated in S32. The CPU 1 sets the side with the remaining one point as the positive direction of the Yk axis, and the point on the left side of the two points on the Xk axis as the origin. In the specific example, the local coordinate system 60 is set for the points P1, P4 and P8 as shown in FIG. Of the sides LA, LB, and LC included in the triangle TRR formed by the points P1, P4, and P8, the side LA is the longest. That is, the distance between the point P4 and the point P8 is the longest. Therefore, the Xk axis is set on the side LA, the side with the point P1 with respect to the side LA is the positive direction of the Yk axis, and the point P8 on the left side of the points P4 and P8 is the origin.

  The CPU 1 acquires two feature points of the combination not acquired in S34 as the focus points from among the three feature points (S34). The CPU 1 first acquires two points (two points on the Xk axis) forming the base in the local coordinate system, and thereafter acquires a combination of two points clockwise. In the specific example, the CPU 1 acquires two notable points in the order of the combination of the point P4 and the point P8, the combination of the point P8 and the point P1, and the combination of the point P1 and the point P4. The CPU 1 uses one of the two points of interest acquired in S34 as the start point and the other as the end point, and calculates a direction vector V from the start point to the end point (S35). The CPU 1 starts from a point on the upstream side when following the sides of a triangle formed by three feature points clockwise, and ends to a point on the downstream side. The CPU 1 calculates the direction vector V in two-dimensional coordinates in the image coordinate system. The CPU 1 according to the present embodiment, in the combination of P4 and P8, the vector VA from the point P4 to the point P8, and in the combination of the point P8 and the point P1, the vector VB from the point P8 to the point P1 In the combination, vectors VC moving from the point P1 to the point P4 are respectively calculated (S35).

  The CPU 1 calculates the value L (S36). The value L is a positive integer obtained by rounding off the decimal part of the distance d between the two points of interest acquired in S34. The CPU 1 determines the first reference point based on the geometric feature of the triangle, and calculates the coordinates of the set first reference point (S37). The coordinates of the first reference point are obtained by two-dimensional coordinates of the image coordinate system. The CPU 1 of the present embodiment sets (L + 1) first reference points on the line connecting the two points of interest acquired in S34. The (L + 1) first reference points are both ends of a line segment connecting two focus points (that is, two focus points) and points which equally divide the two focus points by the interval U. The interval U is a value obtained by dividing the distance d between two focus points by the number L. In the present embodiment, the interval U is approximately one. The CPU 1 sequentially sets the i-th first reference points at equal intervals U from the start point to the end point of the line segment connecting the two points of interest using the direction vector calculated in S35 and the coordinates of the start point Do. i is a natural number from 1 to (L + 1).

  The CPU 1 acquires sample information (S38). The CPU 1 of the present embodiment acquires sample information for each of two attention points for each of the three feature points of all combinations calculated in S18 of FIG. 4. A method of acquiring sample information will be described using a specific example. The CPU I1 sets a plurality of second reference points based on the coordinates of the first reference point acquired in S37, and calculates the coordinates of the set second reference points. In this embodiment, 128 second reference points are set at equal intervals on the circumference of a circle with a radius of 15 pixels centered on the first reference point. The radius R of the circle and the number N of second reference points may be appropriately set in consideration of the size of the image, the resolution, the authentication accuracy, the processing speed, and the like. The number N of second reference points is preferably set to a power of 2 from the viewpoint of acquiring frequency information described later.

  The CPU 1 of the present embodiment calculates the coordinates of the j-th second reference point corresponding to the i-th first reference point as follows. j is a natural number of 1 to 128 (N). A point where j is 1 is called a start point SP. As shown in FIG. 9, when the two attention points are the points P4 and P8, the first reference point P4 is on the circle C1 of the radius R centering on the point P4, and the first reference point P4 On the other hand, a point Q11 in the vector VA direction is set as the start point SP. For the first reference point P8, a point Q12 located on the circle C2 of radius R centered on the point P8 and in the vector VA direction with respect to the first reference point P8 is set as the start point SP. When the two attention points are the points P8 and P1, the point Q21 which is on the circle C2 for the first reference point P8 and in the vector VB direction with respect to the first reference point P8 is the start point SP It is set. For the first reference point P1, a point Q22 located on a circle C3 of radius R centered on the point P1 and in the vector VB direction with respect to the first reference point P1 is set as the start point SP. When the two attention points are the points P1 and P4, the point Q31 which is on the circle C3 for the first reference point P1 and in the vector VC direction with respect to the first reference point P1 is set as the start point SP Be done. For the first reference point P4, a point Q32 located on the circle C1 and in the vector VC direction with respect to the first reference point P4 is set as the start point SP. The second reference points after j = 2 are set for each sampling interval counterclockwise from the start point SP. When the sampling interval of this embodiment is expressed by an angle with respect to a circle, it is an angle obtained by dividing 360 degrees (2π radians) by 128.

  The CPU 1 obtains a sample for each of the plurality of second reference points. The sample acquisition method will be described with reference to FIG. The CPU 1 of the present embodiment acquires the gradation value of the pixel represented by the second reference point as color information. If the coordinates of the second reference point are in units of sub-pixels (if the absolute coordinates are not integers), the CPU 1 uses the tone values of the four pixels in the vicinity of the second reference point by the well-known bilinear interpolation method. Calculate the color information of the reference point. The CPU 1 sets, as a sample 71, information in which color information acquired for one second reference point is associated with second information corresponding to the second reference point. The second information in the present embodiment is j representing the acquisition order corresponding to the position of the second reference point with respect to the start point SP. That is, the second information of the present embodiment is represented by a natural number of 1 to 128.

  As schematically shown in FIG. 10, the CPU 1 associates a plurality of samples 71 obtained for one first reference point with the first information to generate sample data 72. The CPU 1 performs the above processing for each of (L + 1) first reference points set for one set of two attention points, and acquires sample information 73. That is, the sample information 73 includes (L + 1) sample data 72 calculated for each of the (L + 1) first reference points. Each sample data 72 includes N samples 71 obtained for each of the N second reference points. The sample information 73 is acquired for every two attention points. In the specific example, as shown in FIG. 11, in the specific example, the sample information SDR1 is obtained for the points P4 and P8, the sample information SDR2 is obtained for the points P8 and P1, and the sample information SDR3 is obtained for the points P1 and P4. Ru.

  The CPU 1 generates a sample image based on the acquired sample information (S39). In the specific example, sample images 76 to 78 shown in FIG. 11 are respectively generated for each of the three sets of two attention points. The longitudinal directions of the sample images 76 to 78 correspond to the first information, and the lateral directions correspond to the second information. The color of each pixel of the sample images 76 to 78 represents color information of the pixel corresponding to the combination of the first information and the second information.

  The CPU 1 acquires frequency information based on the sample information acquired in S38 (S40). The CPU 1 of the present embodiment calculates, as frequency information, a one-dimensional group delay spectrum of a change in color information with respect to the second information for each of the first information according to the known method described above. Group delay spectrum (GDS) is defined as the frequency derivative of the phase spectrum in the power transfer function. As illustrated in FIG. 12, GDS 83 calculated based on sample information 82 separates and emphasizes individual peaks of the frequency spectrum of sample information 82. The number of elements in the GDS array is the number of elements in the phase spectrum minus one. Specifically, the CPU 1 calculates GDS by taking the phase differentiation of the power spectrum obtained by subjecting the weighted LPC coefficient to fast Fourier transform, and calculates the calculated GDS as a frequency component. In the specific example, as shown in FIG. 11, frequency information FDR1 is acquired for points P4 and P8, frequency information FDR2 is acquired for points P8 and P1, and frequency information FDR3 is acquired for points P1 and P4.

  The CPU 1 generates a frequency image based on the acquired frequency information (S41). In the specific example, frequency images 79 to 81 shown in FIG. 11 are respectively generated. The CPU 1 thins pixels with small GDS intensity (decreases gradation value). In the specific example, the short direction of the frequency images 79 to 81 corresponds to the number of elements, and the longitudinal direction corresponds to the second information. The color of each pixel of the frequency images 79 to 81 represents the GDS intensity of the pixel corresponding to the combination of the number of elements and the second information. The CPU 1 darkens pixels with relatively large GDS intensities (increases gradation values). The CPU 1 dims pixels with relatively small GDS intensity (decreases the gradation value).

  The CPU 1 stores the information in which the sample information and the frequency information are associated with the geometric feature amount in the RAM 3 as collation information used for collation of biological information (S42). As shown in FIG. 11, in the specific example, the matching information 75 in which the sample information SDR1 to SDR3 and the frequency information FDR1 to FDR3 are associated with the geometric feature GDR is stored in the RAM 3. The geometric feature GDR includes the area calculated in S20, the distance calculated in S32, the coordinates of the local coordinate system set in S33, the direction vector V calculated in S35, and the internal angle of the triangle. The collation information 75 of the present embodiment includes the sample image generated in S39 of FIG. 7 and the frequency image generated in S41. The CPU 1 ends the verification information acquisition process, and returns the process to the image analysis process shown in FIG.

  As shown in FIG. 3, after S22, the CPU 1 determines whether three feature points of all combinations calculated in S18 are acquired in the process of S19 (S25). If there is a combination that has not been acquired (S25: NO), the CPU 1 returns the process to S19. If three feature points of all combinations are acquired in the process of S19 (S25: YES), the CPU 1 ends the image analysis process, and returns the process to the collation information process of FIG.

  The CPU 1 determines whether the collation information is acquired in S1 (S2). When collation information is not acquired (S2: NO), CPU1 performs an error notice (S6). The CPU 1 displays an error message on the display unit 6, for example. When collation information is acquired (S2: YES), it is judged whether registration information acquired by S1 is registered in DB28 (refer FIG. 2) as collation information for a reference (S3). Information as to whether or not to register is included in, for example, the start instruction. In the specific example, it is determined to register (S3: YES), and the CPU 1 stores the collation information acquired in S1 in the DB 28 of the flash memory 4. In the present embodiment, of the three feature points of all the combinations calculated in S18 of FIG. 4, the matching information is acquired for the combinations satisfying the requirement of S21. In the specific example, as shown in FIG. 13, a plurality of pieces of collation information including the collation information 75 in the case where the three feature points are the points P1, P4 and P8 are registered in the DB 28. If not registered (S3: NO), the CPU 1 executes the matching process in which the matching information acquired in S1 is the matching information for the test to be matched (S5). After one of S4, S5, and S6, the CPU 1 ends the verification information processing.

2. Processing at the time of matching The example at the time of matching is the case where the matching information extracted from the image 41 of FIG. 5 is used as the matching information for reference and the image 51 of FIG. The collation information processing of will be described. In the verification information processing at the time of verification, S1 is executed as in the case of the verification information processing at the time of registration. For example, when points PT1, PT2 and PT3 of FIG. 14 are acquired as three feature points in S19 of FIG. 4, sample information SDT1 to SDT3 of FIG. 15 are acquired in S38 of FIG. To 88 are generated. In S40, frequency information FDT1 to FDT3 are acquired, and in S41, frequency images 89 to 91 are generated. In S42, collation information 85 is stored.

  In S2, it is judged that collation information was acquired (S2: YES), and it is judged that it does not register based on start directions (S3: NO). The CPU 1 executes the collation process (S5). As shown in FIG. 14, in the collation process, the CPU 1 sorts the collation information corresponding to each of a plurality of sets of three feature points based on the area S of the triangle included in the collation information, and collates information in descending order of the area S Rearrange (S51). The CPU 1 executes the process of S51 for each of the reference collation information stored in the DB 28 and the test collation information acquired in S1 of FIG. When the reference collation information stored in the DB 28 is sorted in advance, the CPU 1 sorts only the test collation information acquired in S1 of FIG. By the process of S51, as schematically shown in FIG. 17, a plurality of sets of three feature points included in the verification information are three feature points for each of the verification information for test and the verification information for reference. The area S of the triangle formed by is sorted in descending order.

  The CPU 1 selects one set of three feature points in the descending order of the area S from the plurality of sets of three feature points included in the test verification information (S52). The CPU 1 selects one set of three feature points in the descending order of the area S from the plurality of sets of three feature points included in the reference collation information (S53). The CPU 1 uses the geometric feature quantities associated with the three feature points for test acquired in S52, and the geometric feature quantities associated with the three feature points for reference acquired in S53. The difference of is calculated (S54). In the process of S54, a triangle formed by the three feature points for test acquired in S52 (hereinafter referred to as a "test triangle") and a triangle formed by the three feature points for reference acquired in S53 (hereinafter described) , Is referred to as “reference triangle”). In the present embodiment, the coordinates of the local coordinate system and the internal angle of the triangle are used as the geometric feature quantities at S54.

  The CPU 1 determines whether the difference between the geometric feature quantities calculated in S54 is smaller than a threshold (S55). If the difference between the coordinates of the local coordinate system for each of the three feature points is equal to or greater than the threshold, and / or if the difference between the internal angles of the triangle is equal to or greater than the threshold (S55: NO), the CPU 1 performs geometry Based on the target feature amount, processing is performed when the test triangle and the reference triangle are not similar. Specifically, the CPU 1 determines whether the difference in length between the first long side and the second long side of the three sides of the test triangle is larger than the threshold (S63). The process of S63 is the case where the triangle represented by the three test points for testing is a triangle close to an isosceles triangle in which the difference in length between the first long side and the second long side is less than the threshold. It is a process considered. When the difference in length between the first long side LK1 and the second long side LK2 is equal to or less than the threshold value, as in a triangle TRK formed by the points PK1, PK2, and PK3 in FIG. 17 (S63: NO), The CPU 1 resets the coordinates of the local coordinate system regarding the three feature points for test (S64). Specifically, the CPU 1 sets a local coordinate system 61 in which the second longest side LK2 is disposed on the Xk axis and the side on which the point PK2 is located is the Yk axis plus side (S64). The CPU 1 returns the process to S54.

  If the difference in length between the first long side and the second long side is larger than the threshold (S63: YES), the CPU 1 reads out the three feature points for reference selected in S53 in the order of reading It is determined whether or not there are three feature points of (S65). The CPU 1 of the present embodiment reads out three feature points in the descending order of the area S of the triangle from the reference collation information. If the reading order is not the last (S65: NO), the CPU 1 returns the process to S53. If the reading order is the last (S65: YES), the CPU 1 discards the three feature points for test selected in S52 (S66). The CPU 1 determines whether the three feature points for test selected in S52 are the last feature points in the reading order (S67). The CPU 1 of the present embodiment reads out three feature points in the descending order of the area S of the triangle from the verification information for test. If the reading order is not the last (S67: NO), the CPU 1 returns the process to S52. If the reading order is the last (S67: YES), the CPU 1 determines that the authentication is unsuccessful (S68). The CPU 1 ends the collation processing, and returns the processing to the collation information processing of FIG. After S5, the CPU 1 ends the verification information processing.

  In S55, if the difference between the coordinates of the local coordinate system for each of the three feature points is smaller than the threshold and the difference between the internal angles of the triangle is smaller than the threshold (S55: YES), CPU 1 calculates the similarity of the frequency information (S58). Specifically, the CPU 1 determines the similarity between the frequency information acquired for the three feature points for test selected in S52 and the frequency information acquired for the three feature points for reference selected in S53. Calculate A publicly known method should just be suitably used as a calculation method of similarity. The CPU 1 according to the present embodiment calculates a distance value as the similarity using known DP matching. The CPU 1 of the present embodiment calculates the distance value of the frequency information for each of the three sets of two attention points selected from the three feature points.

Specifically, as shown in FIG. 17, when the reference triangle is the triangle TRR and the test triangle is the triangle TRT, the frequency information for reference is the frequency information FDR1 to FDR3 in FIG. Are the frequency information FDT1 to FDT3 of FIG. In this case, as schematically shown in FIG. 18, the CPU 1 applies the frequency image 79 and the frequency image 89 to DP matching to obtain the distance value DF1. In the present embodiment, the matching cost is determined based on the 14 components corresponding to 1 to 14 selected by prioritizing low-order components in order to eliminate noise. In FIG. 18, a frequency image 89 representing test frequency information FDT1 is shown on the upper side. In FIG. 18, the frequency image 79 representing the frequency information FDR 1 for reference is shown on the left side in the direction corresponding to the frequency image 89. The direction corresponding to the frequency image 89 is such that the frequency image 79 is inverted about the lower end of the frequency image, and then the inverted frequency image 79 is rotated 90 degrees clockwise from the upper left end of the inverted frequency image 79 Obtained by The CPU 1 starts the path search from the upper left corresponding point, traces the corresponding point with the smallest matching cost among the adjacent corresponding points, and searches for a path leading to the lower right corresponding point. In FIG. 18, the path is indicated by a thick line 95 extending substantially straight from the upper left to the lower right. The same applies to a diagram schematically showing the following DP matching. As schematically shown in FIG. 19, the CPU 1 applies the frequency image 80 and the frequency image 90 to DP matching to obtain a distance value DF2. As schematically shown in FIG. 20, the CPU 1 applies the frequency image 81 and the frequency image 91 to DP matching to obtain a distance value DF3. The CPU 1 calculates a standardized distance value DFD based on the three calculated distance values.
DFD = (DF−DFH) / DFS (1)
In equation (1), DF is an actual distance value (one of DF1 to DF3) obtained by DP matching of frequency information. DFH is an average value of distance values obtained by DP matching of frequency information. DSS is a standard deviation of distance values obtained by DP matching of frequency information. DFH and DFS in the present embodiment are values set in advance based on DP matching results of a plurality of frequency information. Based on the equation (1), standardized distance values DFD1 to DFD3 are calculated from the distance values DF1 to DF3. As the distance value DFD is larger, the degree of similarity is smaller than in the case where the value is smaller.

The CPU 1 calculates the similarity of the sample information (S59). Specifically, the CPU 1 measures the similarity between the sample information acquired for the three feature points for test selected in S52 and the sample information acquired for the three feature points for reference selected in S53. Calculate A publicly known method should just be chosen suitably as a calculation method of similarity. In the present embodiment, similarly to the case of the frequency information, a known DP matching is used to calculate a distance value as the similarity. The CPU 1 calculates the distance value of the sample information for each of the three sets of two attention points selected from the three feature points. In the specific example, the sample information for reference is the sample information SDR1 to SDR3 of FIG. 11, and the sample information for test is the sample information SDT1 to SDT3 of FIG. In this case, as schematically shown in FIG. 21, the CPU 1 applies the sample image 76 and the sample image 86 to DP matching to obtain the distance value DS1. As schematically shown in FIG. 22, the CPU 1 subjects the sample image 77 and the sample image 87 to DP matching to obtain a distance value DS2. As schematically shown in FIG. 23, the CPU 1 subjects the sample image 78 and the sample image 88 to DP matching to obtain a distance value DS3. The CPU 1 calculates a standardized distance value DSD according to the following equation (2) for each of the three calculated distance values.
DSD = (DS-DSH) / DSS ... Formula (2)
In equation (2), DS is an actual distance value (one of DS1 to DS3) obtained by DP matching of sample information. DSH is an average value of distance values obtained by DP matching of sample information. DSS is a standard deviation of distance values obtained by DP matching. The DSH and DSS in the present embodiment are values set in advance based on the DP matching results of a plurality of sample information. Based on the equation (2), a standardized distance value DSD1 to DSD3 is calculated from the distance values DS1 to DS3. As the distance value DSD is larger, the degree of similarity is smaller than when the value is smaller.

The CPU 1 calculates the similarity D to be used for collation based on the similarity of the frequency information calculated in S58 and the similarity of the sample information calculated in S59 (S60). Specifically, the CPU 1 adds values obtained by multiplying each of the similarity of the frequency information calculated in S58 and the similarity of the sample information calculated in S59 by a coefficient. The factor is preset in consideration of the authentication result. The CPU 1 of the present embodiment calculates the similarity D in accordance with the equation (3). However, B is a number of 0 or more and 1 or less. The similarity D is calculated for each of two target points. For example, for the points P4 and P8, the similarity D1 is calculated based on B × DSD1 + (1-B) × DFD1.
D = B × DSD + (1-B) × DFD formula (3)

  The CPU 1 determines whether the similarity DR is smaller than a threshold (S61). In the present embodiment, the representative value of the three similarities D calculated for every two attention points in S60 is taken as the similarity DR used for the comparison in S61. The similarity DR is, for example, one of an average value, a minimum value, an intermediate value, and a maximum value of three similarities. The threshold value of S61 is appropriately set according to the representative value. If the similarity DR is smaller than the threshold (S61: YES), the CPU 1 determines that the authentication is successful (S62). If the similarity is equal to or higher than the threshold (S61: NO), the CPU 1 determines that the authentication is unsuccessful (S68). After the process of S62 or S68, the CPU 1 ends the verification process, and returns the process to the verification information process of FIG. The CPU 1 ends the verification information processing as described above. Although not shown, when the authentication experiment using the collation information of the present embodiment and the authentication experiment performed by the conventional method are performed, authentication accuracy equal to or higher than the conventional one is confirmed by the collation information processing of the present embodiment.

  In the information processing apparatus 10, the CPU 1 corresponds to a processor of the present invention. The RAM 3 and the flash memory 4 correspond to the storage means of the present invention. The process of S11 of FIG. 4 corresponds to the image acquisition step of the present invention. The CPU 1 functioning as the image acquisition unit 21 in S11 corresponds to the image acquisition means of the present invention. The process of S12 corresponds to the extraction step of the present invention. The CPU 1 functioning as the feature point extraction unit 22 in S12 corresponds to the extraction means of the present invention. The process of S19 corresponds to the feature point acquiring step of the present invention. The CPU 1 that executes the process of S19 functions as feature point acquisition means of the present invention. The processes of S20 and S32 and S35 of FIG. 7 correspond to the feature amount calculating step of the present invention. The CPU 1 functioning as the geometric feature quantity calculator 23 in S20 and S32 and S35 in FIG. 7 corresponds to the feature quantity calculation means of the present invention. The process of S34 corresponds to the selection step of the present invention. The CPU 1 that executes the process of S34 functions as a selection unit of the present invention. The process of S37 corresponds to the reference point acquiring step of the present invention. The CPU 1 that executes the process of S37 functions as a reference point acquisition unit of the present invention. The process of S38 corresponds to the sample information acquisition step of the present invention. The CPU 1 that executes the process of S38 functions as sample information acquisition means of the present invention. The process of S40 corresponds to the frequency information acquisition step of the present invention. The CPU 1 that executes the process of S40 functions as frequency information acquisition means of the present invention. S42 and S4 correspond to the storage control step of the present invention. The CPU 1 that executes the processes of S42 and S4 functions as storage control means of the present invention. The process of S5 corresponds to the verification step of the present invention. The processes of S52 to S55 correspond to the pair extraction step of the present invention. S58 to S62 and S68 correspond to the post-extraction matching step of the present invention.

  The information processing apparatus 10 that executes the information processing program of the present embodiment acquires sample information and frequency information based on the feature points extracted from the image (S38, S40). The sample information and the frequency information are information acquired about a second reference point determined based on geometric feature quantities represented by three feature points extracted from the image. For example, based on the image 41 shown in FIG. 5, the sample information SDR1 to SDR3 in FIG. 11 are obtained for the three feature points P1, P4 and P8. Based on the image 51 shown in FIG. 14, the sample information SDT1 to SDT3 of FIG. 15 are acquired for the three feature points PT1, PT2 and PT3. The image 51 is an image captured in a state in which biological information is moved and rotated with respect to the image 41. The sample images 76 to 78 generated from the sample information SDR1 to SDR3 and the sample images 86 to 88 generated from the sample information SDT1 to SDT3 represent similar striped patterns. That is, in the verification information of the present embodiment, the influence of the rotation or movement of the biometric information with respect to the reference is reduced. As described above, when the verification information is generated based on the information processing program, the biological information represented by the image is rotated with respect to the reference, as compared with the case where the information is acquired about the point where the geometric feature is not considered. , And can generate matching information with reduced influence.

  The sample information and frequency information acquired based on the three feature points are information in which change patterns of color information of pixels around two focus points are efficiently and effectively acquired according to conditions defined by the information processing program. is there. For example, assuming that the second reference point is set on the side of a square arranged with reference to the first reference point, the ridge and the side are arranged substantially parallel depending on the direction in which the side of the square is arranged. There is something to be done. In such a case, even if the graphic in which the second reference point is arranged is changed from a circle to a square, and the same processing as that of the present embodiment is performed, the CPU 1 displays color information representing a characteristic change in biological information. I can not get On the other hand, the CPU 1 sets the second reference point on the circumference of the circle of radius R and the center of the first reference point, to thereby obtain the characteristic change of the color information of the pixels around the first reference point. Easy to get. Therefore, even when the number of feature points extracted from an image is relatively small, the information processing apparatus 10 can generate matching information that can be accurately matched.

  The sample image is an image in which color information included in the image is rearranged in accordance with a condition defined by a program, and can be said to represent real space information. On the other hand, the frequency image is obtained by converting real space information into frequency space information. For this reason, sample information and frequency information are considered to have different meanings. The information processing apparatus 10 according to the present embodiment generates collation information including both sample information and frequency information. Therefore, the amount of information can be increased as compared with the case where either sample information or frequency information is included. That is, by performing collation using the collation information of the present embodiment, it is appropriate to determine whether the similarity is more in terms of more viewpoints than in the case of using the information including only one of the sample information and the frequency information. Can be determined. In this embodiment, after standardizing each of the sample information and the frequency information, the similarity (D) is calculated by multiplying the coefficient (contribution rate). Therefore, the similarity D can be obtained by relatively simple calculation using sample information having different meanings from each other and frequency information.

  The CPU 1 of the present embodiment acquires sample information and frequency information for three sets of two attention points corresponding to all combinations in the case of selecting two feature points from three characteristic points. Since the number of sample information and frequency information to be acquired is larger than when one set of two points of interest is selected, accurate matching is possible even when the number of feature points extracted from an image is small Information can be generated.

  Since the information processing apparatus 10 collates the biometric information using the collation information, even if the number of feature points extracted from the image is small, the collation can be performed with high accuracy. The sample information and the frequency information are information acquired about the point determined based on the geometric feature. Therefore, in the information processing apparatus 10, the influence of the rotation or movement of the biological information with respect to the reference is reduced compared to the case where the information is acquired about the point where the geometric feature is not considered. Good matching results can be obtained.

  When the positions of the three feature points acquired in the feature point acquisition step are close to each other, and the area of the triangle represented by the three feature points is less than a predetermined value, the area of the triangle is greater than or equal to the predetermined value There is less change in the color information indicated by the sample information than in the case of. Therefore, when the area of the triangle represented by the three feature points is less than the predetermined value, the information processing apparatus 10 does not acquire the matching information based on the three feature points (S24). Therefore, the information processing apparatus 10 can improve the accuracy of the matching using the matching information as compared to the case where the matching information is generated based on the three feature points where the area of the triangle is less than the predetermined value.

  The CPU 1 can simplify the process of extracting a reference triangle similar to the test triangle by setting the coordinates of the local coordinate system. As a result, the CPU 1 can reduce the processing time required for verification.

  The CPU 1 of the present embodiment selects the verification information to be used for verification, giving priority to the case where the area is particularly large. That is, the CPU 1 can further improve the collation accuracy while shortening the processing time required for the collation by preferentially using the collation information having a large amount of information among the collation information acquired based on the image for the collation.

  The information processing program and the information processing apparatus of the present invention are not limited to the above embodiments, and various changes may be made without departing from the scope of the present invention. For example, the following modifications (A) to (C) may be added as appropriate.

  (A) The configuration of the information processing apparatus 10 may be changed as appropriate. For example, the information processing apparatus 10 is not limited to a smart phone, and may be, for example, a mobile device such as a notebook PC, a tablet PC, and a mobile phone, or an automated teller machine (ATM) and an on-chip device. It may be a device such as a room exit management device. The biometric information acquisition device 8 may be provided separately from the information processing device 10. In that case, the biometric information acquisition device 8 and the information processing device 10 may be connected by a connection cable, or wirelessly connected as in Bluetooth (registered trademark) and NFC (Near Field Communication). Good. The detection method of the biological information acquisition device 8 is not limited to the electrostatic capacitance method, and may be another method (for example, an electric field type, a pressure type, an optical type). The biological information acquisition device 8 is not limited to a planar type, and may be a linear type. The size, color information and resolution of the image generated by the biological information acquisition device 8 may be changed as appropriate. Therefore, for example, the color information may be information corresponding to a color image in addition to information corresponding to a black and white image.

  (B) The information processing program may be stored in the storage device of the information processing apparatus 10 before the information processing apparatus 10 executes the program. Therefore, each of the method of acquiring the information processing program, the acquisition path, and the device storing the information processing program may be changed as appropriate. The information processing program executed by the processor of the information processing device 10 may be received from another device via a cable or wireless communication, and may be stored in a storage device such as a flash memory. Other devices include, for example, a PC (personal computer) and a server connected via a network.

  (C) Each step of the verification information processing of FIG. 3 is not limited to the example executed by the CPU 1, and part or all may be executed by another electronic device (for example, an ASIC). Each step of the above process may be distributed and processed by a plurality of electronic devices (for example, a plurality of CPUs). Respective steps of the collation information processing of the above embodiment can be changed in order, omitted, and added as needed. Based on an instruction from the CPU 1 of the information processing apparatus 10, the operating system (OS) or the like operating on the information processing apparatus 10 performs a part or all of the actual processing, and the processing of the above embodiment is realized by the processing. Are also included in the scope of the present disclosure. For example, the following changes (C-1) to (C-6) may be appropriately added to the verification information processing.

  (C-1) Preprocessing may be appropriately performed on the image acquired in S11. For example, a filtering process may be performed to remove high frequency components of the image as noise. By performing the filtering process, the gradation change of the edge portion of the image becomes gentle. As a filter used for the filtering process, any one of a known low pass filter, Gaussian filter, moving average filter, median filter, and averaging filter may be used. In another example, a filtering process for extracting only specific frequency band components may be performed on the image acquired in S11. A band including the period of unevenness of the fingerprint may be selected as the specific frequency band. In this case, as a filter used for the filtering process, a known band pass filter may be mentioned.

  (C-2) The conditions for extracting the three feature points that are targets for acquiring the matching information in S21 of FIG. 4 may be changed as appropriate. For example, the CPU 1 may determine whether to acquire the matching information based on whether the value of the maximum interior angle is within a predetermined range, in addition to the area of the triangle formed by the three points. The CPU 1 may omit the process of S21 and may acquire collation information for each of the three feature points corresponding to all the combinations calculated in S18. The CPU 1 may acquire collation information for a predetermined set of three feature points in descending order of area.

  (C-3) In S58, the calculation method of the similarity of frequency information may be changed suitably. For example, when a one-dimensional group delay spectrum similar to that of the present embodiment is used as a frequency component, noise components may appear strongly in high-order components. In consideration of such a case, frequency information may be selected based on frequency information including a predetermined number of components selected with priority given to low-order components. The predetermined number may be determined in advance in consideration of the number of samples, authentication accuracy, etc. For example, when the number N of samples obtained for one first reference point is 128, the predetermined number is 10 to 63. It is set to one. Preferably, the predetermined number is set to any of 12 to 20. In the case of the number of samples N, the predetermined number is preferably set from (number of samples N / 10) to (number of samples N / 5).

  (C-4) The frequency component is not limited to the one-dimensional group delay spectrum. For example, as the frequency components, other known frequency components such as an LPC spectrum, a group delay spectrum, an LPC cepstrum, a cepstrum, an autocorrelation function, and a cross correlation function may be used.

  (C-5) Matching may be performed in combination with known matching information. For example, the final determination may be performed by combining the verification result and the verification result using the verification information method of the present invention by a known minutiae method. In this way, matching is performed from various points of view, and it is expected that the matching accuracy is improved.

  (C-6) The setting conditions (for example, the number, the interval, the acquisition order, and the like) of the first reference point and the second reference point may be changed as appropriate. Sample information and frequency information may be acquired for one side or two sides of the three sides of the triangle. One direction vector of S35 may be calculated for one triangle. In this case, when sample information and frequency information are acquired for a plurality of sides among the three sides of a triangle, the start point SP may be determined based on a common direction vector. The three pieces of sample information calculated for each of the three sides of the triangle may be appropriately combined and treated as one piece of sample information. Similarly, three pieces of frequency information calculated for each of the three sides of the triangle may be appropriately combined and treated as one piece of frequency information. In this case, it is possible to collate using all three sample information and three frequency information calculated for each of the three sides. The process of generating a sample image and the process of generating a frequency image may be omitted as appropriate. The geometric feature, the first information, and the second information may be changed as appropriate.

1 CPU
2 ROM
3 RAM
4 flash memory 10 information processing apparatus 21 image acquisition unit 22 feature point extraction unit 23 geometric feature amount calculation unit 24 sample information acquisition unit 25 frequency information acquisition unit 26 registration unit 27 collation unit 28 DB

Claims (5)

A computer comprising a processor and storage means,
An image acquisition step of acquiring an image;
An extraction step of analyzing the image acquired in the image acquisition step to extract a feature point;
A feature point acquiring step of acquiring three of the feature points extracted in the extracting step;
A feature amount calculating step of calculating a geometrical feature amount of a triangle represented by the three feature points obtained in the feature point obtaining step;
A selection step of selecting two feature points as focus points from the three feature points obtained in the feature point obtaining step;
A first point corresponding to a position of a first reference point which is a point on a line segment connecting the two attention points selected in the selection step and which is a point determined based on the geometric feature value A reference point acquiring step of acquiring each of a plurality of first reference points different in position from each other;
For each of the plurality of pieces of first information acquired in the reference point acquisition step,
A point on the circumference of a circle of a predetermined radius centered on the first reference point corresponding to the first information, the second reference point being a point determined based on the geometric feature amount A sample, which is information in which color information is associated with second information corresponding to the position of the second reference point, is acquired for each of the plurality of second reference points whose positions are different from each other,
A sample information acquisition step of performing processing of using information obtained by associating the plurality of acquired samples with the first information as sample information;
For each of the plurality of first reference points based on the sample information acquired in the sample information acquisition step,
Calculating a frequency component of change of the color information with respect to the second information;
A frequency information acquisition step of acquiring frequency information which is information in which the frequency component calculated for each of the plurality of first reference points is associated with the first information;
An information processing program for executing a storage control step of storing information in which the sample information and the frequency information are associated with the geometric feature amount as collation information used for collation of biological information.   The information processing program according to claim 1, wherein the selection step selects each of the three sets of two attention points corresponding to a combination of all two points of the three feature points.   3. The information processing program according to claim 1, further comprising a collation step of collating the collation information for test to be collated with the collation information for reference stored in the storage unit. . In the feature point acquiring step, the three feature points are selected from a plurality of feature points within a predetermined range determined based on the predetermined radius among the plurality of feature points extracted in the extracting step. Acquiring a plurality of sets of the three feature points corresponding to all combinations,
In the selection step, the area of the triangle has a predetermined value based on the geometric feature quantity calculated in the feature quantity calculation step among the plurality of sets of three feature points acquired in the feature point acquisition step Execute processing to select the two attention points for the three feature points that are the above
The matching step is
Each of the geometric feature quantities of the test triangle represented by the test verification information and the reference triangle represented by the reference verification information has a large area of the triangle A pair extraction step of extracting a pair of the test triangle and the reference triangle whose similarity is equal to or less than a threshold value in order of comparison;
A post-extraction matching step of matching the sample information and the frequency information corresponding to the test triangle extracted in the pair extraction step with the sample information and the frequency information corresponding to the reference triangle; The information processing program according to claim 3, comprising. Storage means for storing information;
Image acquisition means for acquiring an image;
An extraction unit that analyzes the image acquired by the image acquisition unit and extracts a feature point;
Feature point acquisition means for acquiring three of the feature points extracted by the extraction means;
Feature quantity calculation means for calculating a geometric feature quantity of a triangle represented by the three feature points acquired by the feature point acquisition means;
Selection means for selecting two feature points as focus points respectively from the three feature points obtained by the feature point obtaining means;
First information corresponding to a position of a first reference point which is a point on a line segment connecting the two attention points selected by the selection means and which is a point determined based on the geometric feature amount Reference point acquiring means for acquiring each of a plurality of first reference points different in position from each other;
For each of the plurality of pieces of first information acquired by the reference point acquisition unit,
A point on the circumference of a circle of a predetermined radius centered on the first reference point corresponding to the first information, the second reference point being a point determined based on the geometric feature amount A sample, which is information in which color information is associated with second information corresponding to the position of the second reference point, is acquired for each of the plurality of second reference points whose positions are different from each other,
Sample information acquisition means for performing processing of using information obtained by associating the plurality of acquired samples with the first information as sample information;
For each of the plurality of first reference points, based on the sample information acquired by the sample information acquiring unit,
Calculating a frequency component of change of the color information with respect to the second information;
Frequency information acquisition means for acquiring frequency information which is information in which the frequency component calculated for each of the plurality of first reference points is associated with the first information;
Storage control means for storing, in the storage means, information in which the sample information and the frequency information are associated with the geometrical feature amount as collation information used for collation of biological information apparatus.