KR102347697B1 - Device and method for generating cancelable fingerprint template for low-quality images - Google Patents

Abstract

An apparatus for generating a replaceable fingerprint template is disclosed. The fingerprint template generating apparatus includes a minutiae extractor for extracting minutiae from a user's fingerprint image, and a triangulation unit for performing Delaunay triangulation to generate a plurality of triangles from the extracted minutiae, each of the and a vector generator generating a plurality of vectors corresponding to each of the plurality of triangles, and a vector converter generating the user's fingerprint template by multiplying a matrix made of the plurality of vectors by an arbitrary matrix.

Description

DEVICE AND METHOD FOR GENERATING CANCELABLE FINGERPRINT TEMPLATE FOR LOW-QUALITY IMAGES

The present invention relates to processing of fingerprint information, which is one of biometric authentication data, and more particularly, to an apparatus and method for generating a replaceable fingerprint template from a low-quality image.

A fingerprint template refers to a feature point extracted from a fingerprint image and made into information. The feature point can be obtained from the ridge constituting the fingerprint and is composed of an endpoint and a branch point. The end point represents the part where the ridge is broken, and the branch point represents the part where one ridge is divided into two ridges. The feature point, whose position is defined by two-dimensional coordinates, is distorted or rotated by the image quality of the fingerprint image, noise, or finger pressure, so it is not easy to obtain the same coordinate value every time even for the same fingerprint. This property is called fuzzy property. As one of the methods for solving the fuzzy property, there is a method of obtaining a feature point after aligning the fingerprint image using a singularity. The singularity is information that determines the overall shape of the fingerprint, and the representative points are the point with the highest rate of inflection of the ridge (core) and the point where the three ridges are adjacent to each other (delta). If a feature point is obtained after sorting with this singularity as the origin, the information is not significantly different in the case of fingerprints of the same person, so that similar information can be obtained every time.

The biggest advantage and disadvantage of biometric information, including fingerprints, is that it does not change significantly during life and cannot be replaced. This is an advantage because once it is registered for authentication using biometric information, it does not have to be changed often, but once it is leaked to an attacker, it cannot be changed like a password, so you should always be careful about storing it safely. In order to safely store a fingerprint template, if an existing encryption technique is applied and stored in the server, when matching, the server decrypts the stored fingerprint template and then performs matching. If it is a malicious attacker or a malicious server, there is a problem in that the user's original fingerprint information can be easily obtained at this time. One of the solutions is to use a one-way function, which uses the singularity and feature point of the fingerprint to put the generated information together with the secret key into the one-way function so that the original information cannot be known. At this time, the one-way function must be set so that the original fingerprint information cannot be obtained even if the secret key and the parameters of the function are disclosed. For safety reasons, these methods must additionally satisfy the properties of discardability, non-connectivity and efficiency. Disposability is that if the converted template is exposed to an attacker, the user should be able to create different templates with the same fingerprint information using a new secret key and parameters. The inability to connect means that the same user cannot be inferred by looking at the converted templates stored on different servers, and the efficiency should not be significantly different from the error rate of matching generally used without considering safety when using this technique. it means. A technique that satisfies these properties is called a substitutable fingerprint template generation technique.

A replaceable fingerprint template was first proposed in Non-Patent Document [1]. In addition, non-patent document [2] proposes a method using information relative to k close to Minusia, but has a disadvantage in that the amount of computation required to satisfy the substitutable property is large.

Republic of Korea Patent No. 0497226 (published on June 23, 2005) Republic of Korea Patent Publication No. 2004-0105065 (published on 14.12. 2004) Japanese Patent Application Laid-Open No. 2005-065940 (published on June 23, 2005) Republic of Korea Patent Registration No. 0714303 (2007.05.07. Announcement)

N. K. Ratha, J. H. Connell, and R. M. Bolle, “Enhancing security and privacy in biometrics-based authentication systems,” IBM Systems Journal, vol. 40, no. 3, pp. 614-634, 2001. S. Wang, W. Yang, and J. Hu, “Design of alignment-free cancelable fingerprint templates with zoned minutia pairs,” Pattern Recognition, vol. 66, pp. 295-301, 2017.

In the prior art, feature values are generated by using direction information of Minusia. However, in the case of a low-quality fingerprint image, there is a problem in that the direction of the same minusia is greatly changed due to distortion such as crushing of ridges during image processing. Accordingly, the present invention intends to propose a method of generating a fingerprint template using a new feature value in which authentication accuracy is maintained without using minutiae directional information.

A fingerprint template generating apparatus according to an embodiment of the present invention generates a plurality of triangles from the extracted minutiae by performing a minutiae extraction unit, which extracts minutiae from a user's fingerprint image, and Delaunay triangulation. a triangulation unit, a vector generating unit generating a plurality of vectors each corresponding to each of the plurality of triangles, and a vector transformation generating the user's fingerprint template by multiplying a matrix consisting of the plurality of vectors by an arbitrary matrix includes wealth.

A fingerprint template generating method according to an embodiment of the present invention is performed by a computing device including at least a processor, extracting feature points from a user's fingerprint image, and performing Dolone triangulation to obtain a plurality of points from the extracted feature points. generating triangles, generating a plurality of vectors each corresponding to each of the plurality of triangles, and generating the fingerprint template of the user by multiplying a matrix of the plurality of vectors by an arbitrary matrix. include

According to the apparatus and method for generating a replaceable fingerprint template according to an embodiment of the present invention, there is an effect of increasing the authentication success rate in a low-quality fingerprint image. A high authentication success rate can be obtained from low-resolution images by using minusia coordinate information that is not significantly affected by low-resolution image processing.

In order to more fully understand the drawings recited in the Detailed Description, a detailed description of each drawing is provided.
1 is a functional block diagram of an apparatus for generating a fingerprint template according to an embodiment of the present invention.
FIG. 2 shows a result of feature extraction by the feature extraction unit shown in FIG. 1 and a result of Dolone triangulation by the triangulation unit.
FIG. 3 is a diagram for explaining a vector generation operation by the vector generator shown in FIG. 1 .
FIG. 4 is a diagram for explaining an operation of generating a fingerprint template by the vector converter shown in FIG. 1 .
FIG. 5 is a flowchart illustrating a fingerprint template generating method performed by the fingerprint template generating apparatus shown in FIG. 1 .

Specific structural or functional descriptions of the embodiments according to the concept of the present invention disclosed in this specification are only exemplified for the purpose of explaining the embodiments according to the concept of the present invention, and the embodiments according to the concept of the present invention are It may be implemented in various forms and is not limited to the embodiments described herein.

Since the embodiments according to the concept of the present invention may have various changes and may have various forms, the embodiments will be illustrated in the drawings and described in detail herein. However, this is not intended to limit the embodiments according to the concept of the present invention to specific disclosed forms, and includes all modifications, equivalents, or substitutes included in the spirit and scope of the present invention.

Terms such as first or second may be used to describe various elements, but the elements should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another, for example without departing from the scope of the inventive concept, a first component may be termed a second component and similarly a second component A component may also be referred to as a first component.

When a component is referred to as being “connected” or “connected” to another component, it is understood that it may be directly connected or connected to the other component, but other components may exist in between. it should be On the other hand, when it is said that a certain element is "directly connected" or "directly connected" to another element, it should be understood that the other element does not exist in the middle. Other expressions describing the relationship between components, such as "between" and "immediately between" or "neighboring to" and "directly adjacent to", etc., should be interpreted similarly.

The terms used herein are used only to describe specific embodiments, and are not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly dictates otherwise. In this specification, terms such as "comprise" or "have" are intended to designate that a feature, number, step, operation, component, part, or combination thereof described herein exists, but one or more other features It should be understood that it does not preclude the possibility of the presence or addition of numbers, steps, operations, components, parts, or combinations thereof.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and should not be interpreted in an ideal or excessively formal meaning unless explicitly defined in the present specification. does not

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. However, the scope of the patent application is not limited or limited by these examples. Like reference numerals in each figure indicate like elements.

1 is a functional block diagram of an apparatus for generating a replaceable fingerprint template according to an embodiment of the present invention.

Referring to FIG. 1 , the fingerprint template generating device 10 can generate a replaceable fingerprint template showing a higher authentication success rate in a low-resolution image by using a new feature value that replaces the directional information of a minutiae (feature point). have. In addition, an authentication operation for the user may be performed using the generated fingerprint template.

The fingerprint template generating device 10 includes a receiving unit 110 , a feature point extracting unit 120 , a triangulating unit 130 , a vector generating unit 140 , a vector converting unit 150 , an authenticating unit 160 , and a storage unit ( 170) may include at least one or more.

For example, the fingerprint template generating apparatus 10 may include a feature point extracting unit 120 , a triangulating unit 130 , a vector generating unit 140 , and a vector converting unit 150 . According to an embodiment, the fingerprint template generating apparatus 10 may further include a receiving unit 110 and/or a storage unit 170 .

According to an embodiment, the fingerprint template generating apparatus 10 may further include an authenticator 160 . In this case, since the fingerprint template generating apparatus 10 performs an authentication operation by comparing the generated fingerprint template with the user's fingerprint template previously stored in the storage unit 170, it may be referred to as an authentication device.

The receiver 110 may receive a fingerprint image from a user. For example, the receiver 110 may include a scanner for scanning a user's fingerprint. According to an embodiment, the receiver 110 may receive a user image from an external scanning device. The user's fingerprint image received by the receiving unit 110 may be stored in the storage unit 170 . According to an embodiment, the user's image may be previously stored in the storage unit 170 , and in this case, the configuration of the receiving unit 110 may be omitted.

The feature point extraction unit 120 stores the user's fingerprint image received by the receiving unit 110, the user's fingerprint image received by the receiving unit 110 and then stored in the storage unit 170, or stored in the storage unit 170 in advance. It is possible to extract feature points (minusia) from the user's fingerprint image. The feature point may be obtained from ridges constituting the fingerprint and may include at least one of an endpoint and a branch point. Information on the key points extracted by the key point extraction unit 120 may be stored in the storage unit 170 . An example of feature point extraction is shown on the left side of FIG. 2 . Since the feature point extraction operation and an algorithm related thereto are widely known, a detailed description thereof will be omitted.

The triangulation unit 130 may perform delaunchary triangulation using the extracted feature points. Dolone triangulation can be performed in such a way that a triangle is constructed from a given set of points, in particular in such a way that the minimum interior angle of the triangle is maximized. This will always produce the same triangle construction if the given set of points is the same. According to an embodiment, the triangulation unit 130 may generate only one or more triangles. That is, not all possible triangles may be created, but only some triangles may be created. Information on the triangles generated as a result of the triangulation operation by the triangulation unit 130 may be stored in the storage unit 170 . An example of a Dolone triangulation is shown on the right side of FIG. 2 . Since the Dolone triangulation technique also corresponds to a well-known conventional technique, a detailed description thereof will be omitted.

The vector generator 140 may convert each of the generated triangles into a vector. According to an embodiment, the vector generator 140 may generate a k×3 matrix by transforming each of the triangles into a three-dimensional vector. Here, k may mean the number of generated triangles. That is, each row of the generated matrix may be composed of elements of one vector. According to an embodiment, the vector generator 140 may convert only k or less of a predetermined number of triangles into a vector. Information on the transformed or generated vectors may be stored in the storage unit 170 . In addition, a detailed operation of the vector generator 140 will be described later.

The vector converter 150 may expand the dimension of each of the vectors generated by the vector generator 140 . For example, each of the three-dimensional vectors generated by the vector generator 140 may be converted into a four-dimensional or higher vector by the vector converter 150 . In another embodiment, the vector transform unit 150 may generate a k×p matrix by multiplying the matrix generated by the vector generating unit 140 by an arbitrary matrix. That is, the vector converter 150 may convert each of the three-dimensional vectors into a p-dimensional vector. A detailed operation of the vector converter 150 will be described later.

The authentication unit 160 may authenticate the user by comparing the user's fingerprint template generated by the vector conversion unit 150 with the user's fingerprint template stored in advance in the storage unit 170 . Specifically, the authenticator 160 may calculate the number of matching triangles according to the comparison result, and determine whether to authenticate the user based on the number of matched triangles.

For example, the authenticator 160 may authenticate the user when the number of matching triangles is a number (a is an arbitrary natural number) or more, or the ratio of the matching triangles is more than b (b is an arbitrary real number). As another example, the authenticator 160 may determine whether to authenticate the user using Equation (1).

[Equation 1]

은 저장부(170)에 미리 저장되어 있는 지문 템플릿을 구성하는 삼각형의 개수, 즉 지문 템플릿의 행의 크기를 의미할 수 있다.

은 삼각화부(130)에 의해 생성된 삼각형의 개수, 벡터 생성부(140)에 의해 생성된 벡터의 개수, 벡터 변환부(150)에 의해 변환된 벡터의 개수, 또는 벡터 변환부(150)에 의해 생성된 지문 템플릿의 행의 크기를 의미할 수 있다.

은 비교 결과에 따라 매칭되는 삼각형의 개수를 의미한다.In Equation 1,

may mean the number of triangles constituting the fingerprint template stored in advance in the storage unit 170 , that is, the size of a row of the fingerprint template.

is the number of triangles generated by the triangulation unit 130 , the number of vectors generated by the vector generating unit 140 , the number of vectors converted by the vector converting unit 150 , or the vector converting unit 150 . It may mean the size of the row of the fingerprint template generated by the

is the number of matching triangles according to the comparison result.

In addition, the authentication unit 160 receives the user's fingerprint template (first fingerprint template) generated by the vector conversion unit 150 and the user's fingerprint template (second fingerprint template) stored in advance in the storage unit 170 . By comparison, the number of matching triangles can be calculated. Specifically, when the distance between the vector constituting the first row of the first fingerprint template and the vector constituting the first row of the second fingerprint template is less than a predetermined distance threshold, triangles corresponding to each of the two vectors are determined to be matched. can According to an embodiment, each row of the second fingerprint template of the first fingerprint template may be randomly arranged. In this case, when a vector constituting an arbitrary row of the first fingerprint template and a vector within the distance threshold are included in the second fingerprint template, it may be determined that the two triangles match.

The fingerprint template generating apparatus 10 may include at least one electronic device capable of various arithmetic processing and signal generation. Here, the at least one electronic device may include a processor and/or a computing device in which the processor is installed. Here, the processor is a central processing unit (CPU, Central Processing Unit), a micro controller unit (MCU, Micro Controller Unit), a microcomputer (Micom, Micro Processor), an application processor (AP, Application Processor), an electronic control unit (ECU, Electronic Controlling Unit), a graphic processing unit (GPU, Graphic Processing Unit), and/or a processing unit capable of various arithmetic processing and control signal generation. These processing devices may be implemented using, for example, one or more semiconductor chips and related components. In addition, computing devices include desktop computers, laptop computers, server computers, smart phones, tablet PCs, smart watches, Head Mounted Display (HMD) devices, portable game consoles, navigation devices, and personal digital assistants (PDA). ), an artificial intelligence speaker device, a digital television, a set-top box, a robot, a home appliance, a mechanical device, and/or at least one electronic device capable of performing other information processing functions.

The fingerprint template generating device 10 may be directly or indirectly connected to the storage unit 170 to transmit and receive data. The storage unit 170 stores the user's fingerprint image received by the receiving unit 110, the key points extracted by the key point extraction unit 120, data generated during the Dolone triangulation operation by the triangulation unit 130, and / Alternatively, data generated as a result of the triangulation operation, the vector generated by the vector generator 140 , the data generated by the vector conversion unit 150 , and data generated during the authentication operation by the authenticator 160 . and/or data generated as a result of the authentication operation may be temporarily or non-temporarily stored. In addition, a user's fingerprint template, which is data required to perform an authentication operation, may be previously stored in the storage unit 170 .

The storage unit 170 may include at least one of a main memory device and an auxiliary memory device, and the main memory device may include a ROM and/or a RAM (RAM), and the auxiliary storage device is a flash memory device; It may include a Secure Digital (SD) card, a solid state drive (SSD), a hard disk drive (HDD), a compact disc (CD), a DVD, and/or a laser disc.

The fingerprint template generating apparatus 10 may drive an application stored in the storage unit 170 to perform various operations such as feature point extraction, Dolone triangulation, vector generation, and vector conversion. Here, the application may be directly created by a designer and stored or updated in the storage unit 170, or may be acquired or updated through an electronic software distribution network accessible through a wired or wireless communication network.

FIG. 3 is a diagram for explaining a vector generation operation by the vector generator shown in FIG. 1 . An enlarged view of a triangle indicated in green among a plurality of triangles shown on the left side of FIG. 3 is shown on the right side of FIG. 3 . Hereinafter, a vector generation operation for an exemplary triangle indicated in green will be described.

_{Let m 1} , m ₂ , and m _{3 be} the vertices of the triangle constituting the minutiae of the fingerprint, respectively, and let c be the center of gravity, for example, one of the centroids of the triangle (external center, inner center, water depth, eccentricity, and center of gravity). Let the vectors from c to each vertex be d ₁ , d ₂ , and d ₃ , and these vectors are in an arbitrary axis (eg, x-axis) of a Cartesian coordinate system with c as the origin and in ascending order of the angle difference between these vectors. _{When these vectors are aligned, let α 1} be the interior angle (or exterior angle) of the vertex pointed to by the vector with the smallest angular difference _{, and let α 2} and α ₃ in that order. One three-dimensional vector of aligned interior angles is created for each triangle. According to this vector generating operation, as many vectors as the number of triangles (k and k are arbitrary natural numbers) included in the fingerprint image are formed. That is, if the number of triangles included in the fingerprint image is k, the number of generated vectors is also k. Also, the vector generator 140 may generate a k×3 matrix by using the generated vectors. Each row of the generated matrix has elements of one of the generated vectors as elements. In the process of generating a k×3 matrix, a vector insertion method may be predetermined. That is, the q-th (q is 1, 2, or 3) element of each vector may be sorted in ascending (or descending) order, in ascending (or descending) order of the size of each vector, and the like. According to an embodiment, they may be arranged in any order.

According to an embodiment, the vector generator 140 may sort the _{vectors d 1} , d ₂ , and d ₃ in a descending order rather than an ascending order of the angle difference. Also, the vector generator 140 may form a vector having an angle difference itself as an element.

FIG. 4 is a view for explaining a vector conversion operation by the vector conversion unit shown in FIG. 1 .

That is, the feature point extractor 120 extracts a plurality of feature points from the user's fingerprint image, and the triangulation unit 130 generates a plurality of triangles by performing Dolone triangulation using the plurality of extracted feature points. Also, the vector generator 140 may convert one triangle into one three-dimensional vector as in the above-described process. According to an embodiment, the vector generating unit 140 may generate a k×3 matrix having the constituent elements of the 3D vector as row elements. A matrix of k×3 may be referred to as a 3D feature set.

The vector transform unit 150 may extend the dimension of each of the vectors generated by the vector generator 140 to a dimension p (p is a natural number greater than 3, for example, p is 4). To this end, the vector transform unit 150 may generate a 3×p matrix having arbitrary values as elements. The generated 3×p matrix may be named as a user key and corresponds to a user. In addition, there may be various methods for generating a user key, but since the present invention is not characterized by a method for generating a user key, a detailed description thereof will be omitted.

The vector converter 150 may generate a k×p matrix by performing a multiplication operation on the 3D feature set generated by the vector generator 140 , that is, a k×3 matrix and a user key. A matrix of k×p may be called a p-dimensional feature set. In addition, the matrix generated by the vector conversion unit 150 can be called a replaceable fingerprint template in that although it is generated based on the user's fingerprint data, there is no concern about the leakage of fingerprint information even if it is leaked.

FIG. 5 is a flowchart illustrating a fingerprint template generating method performed by the fingerprint template generating apparatus shown in FIG. 1 .

First, the receiving unit 110 of the fingerprint template generating device 10 may receive a fingerprint image from the user (S100). The received fingerprint image may be stored in the storage unit 170 . According to an embodiment, the user's fingerprint image may be pre-stored in the storage unit 170, and in this case, step S100 may be omitted.

In step S200 , the keypoint extraction unit 120 of the fingerprint template generating apparatus 10 may extract keypoints of the user's fingerprint image. Also, in step S300 , the triangulation unit 130 of the fingerprint template generating apparatus 10 may perform a Dolone triangulation operation using the extracted feature points.

In step S400 , the vector generator 140 of the fingerprint template generating apparatus 10 forms a vector corresponding to each of the plurality of triangles generated by the Dolone triangulation operation, and generates a matrix including the generated vectors. can

In step S500 , the vector conversion unit 150 of the fingerprint template generating apparatus 10 may generate a replaceable fingerprint template by expanding the dimension of the column of the matrix generated by the vector generating unit 140 .

According to an embodiment, the method of generating a fingerprint template may further include an authentication operation performed by the authenticator 160 . That is, the authentication unit 160 may perform a user authentication operation by comparing the generated fingerprint template with the fingerprint template stored in the storage unit 170 (S600). In this case, the fingerprint template generating method may be referred to as an authentication method or the like.

The device described above may be implemented as a hardware component, a software component, and/or a set of hardware components and software components. For example, the devices and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable array (FPA), and a PLU. It may be implemented using one or more general purpose or special purpose computers, such as a Programmable Logic Unit (Programmable Logic Unit), a microprocessor, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications executed on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For convenience of understanding, although one processing device is sometimes described as being used, one of ordinary skill in the art will recognize that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that can include For example, the processing device may include a plurality of processors or one processor and one controller. Other Processing Configurations are also possible, such as a Parallel Processor.

The software may include a computer program, code, instructions, or a combination of one or more thereof, and configure the processing device to operate as desired or independently or collectively processed You can command the device. The software and/or data may be any type of machine, component, physical device, virtual equipment, computer storage medium or device, to be interpreted by or provide instructions or data to the processing device. , or may be permanently or temporarily embodied in a transmitted signal wave (Signal Wave). The software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or preferably. The program instructions recorded in the medium may be specially designed and configured for the embodiment, or may be known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical recording media such as CD-ROMs and DVDs, and magnetic such as floppy disks. - Includes hardware devices specially configured to store and execute program instructions, such as Magneto-optical Media, ROM, RAM, Flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

Although the present invention has been described with reference to the embodiment shown in the drawings, which is merely exemplary, those skilled in the art will understand that various modifications and equivalent other embodiments are possible therefrom. For example, the described techniques are performed in an order different from the described method, and/or the described components of the system, structure, apparatus, circuit, etc. are combined or combined in a different form than the described method, or other components Or substituted or substituted by equivalents may achieve an appropriate result. Accordingly, the true technical protection scope of the present invention should be determined by the technical spirit of the appended claims.

10: fingerprint template generating device
110: receiver
120: feature point extraction unit
130: triangularization part
140: vector generator
150: vector conversion unit
160: authentication unit
170: storage

Claims (10)

a minutiae extracting unit for extracting minutiae from the user's fingerprint image;
a triangulation unit generating a plurality of triangles from feature points extracted by performing Delaunay triangulation;
a vector generator for generating a plurality of vectors each corresponding to each of the plurality of triangles and having as an element a size of an interior or exterior angle of the triangle; and
A vector conversion unit for generating a replaceable fingerprint template of the user by multiplying the matrix consisting of the plurality of vectors by an arbitrary matrix that is a user key corresponding to the user,
The vector generator,
Generate first vectors from any one (c) of the triangle toward each vertex,
Sorting the first vectors in ascending order or descending order of the angle difference between the x-axis or y-axis of the rectangular coordinate system having the c as the origin and the first vectors,
generating the vector having as an element the size of an interior or exterior angle corresponding to each of the sorted first vectors,
Fingerprint template generator.
The method of claim 1,
In the matrix of the plurality of vectors, the plurality of vectors are arranged based on the size of the q-th element (q is 1, 2, or 3) of each vector or the size of each vector,
Fingerprint template generator.
delete The method of claim 1,
The vector conversion unit,
generate the random matrix corresponding to the user and having random values as elements;
The size of the row of the arbitrary matrix is 3, and the size of the column of the arbitrary matrix is 4 or more,
Fingerprint template generator.
The method of claim 1,
The fingerprint template generating device further comprises an authentication unit for authenticating the user by comparing the fingerprint template with a previously stored fingerprint template,
Fingerprint template generator.
A method of generating a fingerprint template performed by a computing device comprising at least a processor, the method comprising:
extracting feature points from the user's fingerprint image;
generating a plurality of triangles from the extracted feature points by performing Dolone triangulation;
generating a plurality of vectors each corresponding to each of the plurality of triangles and having as an element the size of an interior or exterior angle of the triangle; and
generating a cancelable fingerprint template of the user by multiplying the matrix consisting of the plurality of vectors by an arbitrary matrix that is a user key corresponding to the user,
The step of generating the plurality of vectors comprises:
generating first vectors directed to each vertex from any one of the triangles (c);
arranging the first vectors in an ascending or descending order of an angle difference between the x-axis or y-axis of a rectangular coordinate system having the c as the origin and each of the first vectors; and
Comprising the step of generating the vector having as an element the size of an interior angle or an exterior angle corresponding to each of the aligned first vectors,
How to create a fingerprint template.
7. The method of claim 6,
In the matrix of the plurality of vectors, the plurality of vectors are arranged based on the size of the q-th element (q is 1, 2, or 3) of each vector or the size of each vector,
How to create a fingerprint template.
delete 7. The method of claim 6,
generating the fingerprint template comprises generating the random matrix corresponding to the user and having random values as elements;
The size of the row of the arbitrary matrix is 3, and the size of the column of the arbitrary matrix is 4 or more,
How to create a fingerprint template.
7. The method of claim 6,
The method of generating the fingerprint template further comprises the step of authenticating the user by comparing the fingerprint template with a previously stored fingerprint template,
How to create a fingerprint template.

Images