KR20170061405A - Method for Certificating Pattern of Sweat Pore - Google Patents

Abstract

The present invention relates to a method for authenticating a pore hole, and a method for authenticating a pore hole according to the present invention is a method for performing a method using an apparatus having a sensor unit capable of sensing a fingerprint, A first step of reading the sensed value of the sensed data to generate recognition data capable of distinguishing a ridge and a valley of the fingerprint when the sensed data is acquired; A second step of identifying the feature points and identifying at least s (s? 3) pore locations distributed on the fingerprint ridge area; and determining a position of one of the s pore locations by using the identified one or more feature points, (3? T? S) of pore positions on the basis of the determined reference point, A step of creating a pore template containing the generated pore data and storing the generated pore template in a designated storage area or storing the geometric relationship of the generated pore data in a storage area of a pore template stored in a designated storage area, And a fifth step of verifying that the matching is within the tolerance range compared with the geometric relationship.

Description

[0001] The present invention relates to a method for certifying patterns of sweat pores,

The present invention relates to a method of detecting a geometric relationship of pores distributed on a fingerprint ridge region based on a reference point by sensing a body part of a user and determining a position of a pore among the s pore locations as a reference point using feature points of a fingerprint ridge pattern And compared with the geometric relationship of the previously stored pore templates to verify that they match within an allowable error range.

With the recent activation of smart phones, a fingerprint module is embedded in a smart phone, and fingerprint recognition is used for operations or services requiring various security. It is expected that fingerprints will be more useful in the future than other living bodies because recognition process is convenient.

On the other hand, since fingerprint recognition is convenient, the possibility of forgery is easy. When fingerprint recognition is attempted by simulating fingerprints through materials having physical, chemical, and electrical characteristics similar to the epidermis of a human body, the conventional fingerprint recognition technology has a very difficult problem to exclude such simulated fingerprints. For example, when fingerprints are simulated using Gummi, which is very similar to the skin composition of the human body, it is very difficult to exclude such simulated fingerprints through conventional fingerprint recognition technology.

Examples of techniques for excluding such simulated fingerprints include Japanese Patent Application Laid-Open Nos. 2000-123143, 10-302047, 2000-194848, and 2000-172833, 10-2005-0051659 and the like.

However, in the technique disclosed in Japanese Patent Application Laid-Open No. 2000-123143 and Japanese Patent Application Laid-Open No. 10-302047, it is determined whether or not the subject is a living body by the current value of the subject, the capacitance, the electric resistance, , It is difficult to exclude a simulated fingerprint using a substance having chemical and electrical characteristics. In the technique disclosed in Japanese Patent Application Laid-Open No. Hei 10-370295, a counterfeit fingerprint is judged based on whether or not the electrostatic sensor responds. 2000-172833, it is difficult to exclude a simulated fingerprint using materials having physical, chemical and electrical characteristics similar to those of the skin of a human being, because the forgery fingerprint is judged by the frequency characteristic of impedance, which is an electrical characteristic . Korean Patent Laid-Open No. 10-2005-0051659 discloses a method of detecting a living body by using the presence or absence of sweat when scanning a sweep method of a fingerprint. However, in the case of a substance having physical, chemical and electrical characteristics similar to the skin of a human body It is difficult to exclude water if it is attempted to recognize it.

In order to solve the above problems, an object of the present invention is to detect at least one feature point extracted on a fingerprint ridge pattern structure by sensing a user's body part, and to identify at least s (3) And determining a position of one of the s pore locations as a reference point using the identified feature points to determine a geometric relationship with at least t (3? T? S) pore locations based on the reference point A pore template including the generated pore hole data is generated and stored in a designated storage area or a geometric relationship of the generated pore hole data is compared with a geometric relationship of a pore hole template stored in a designated storage area A punched hole pattern authentication method for authenticating whether or not to match within an allowable error range As it has.

A method for authenticating a pore hole according to the present invention is a method for performing a method using an apparatus having a sensor unit capable of sensing a fingerprint, the method comprising: sensing a sensed value of the sensed data, A first step of generating recognition data capable of distinguishing a ridge and a valley of a fingerprint from each other, and identifying one or more feature points extracted on the fingerprint ridge pattern structure using the recognition data, A second step of determining at least s (3) pore positions of at least one s pore, and a third step of determining a position of one of the s pore locations as a reference point using the identified one or more feature points, (4 < / = t >) to generate pore data including a geometric relationship with at least t And creating a pore template containing the generated pore data and storing the created pore template in a designated storage area or comparing the geometric relationship of the generated pore data with a geometric relationship of a pore template stored in a designated storage area, And a fifth step of authenticating whether or not it is matched.

According to the present invention, the second step includes the steps of: determining a base sensing value for a ridge area included in the recognition data; and calculating S (S? 3) distributed on the ridge area using the base sensing value, Identifying at least s (3 ≤ s ≤ S) sensing value singularity regions of the identified S sensing value singularity regions as pore holes formed in the body region sensed by the sensor unit and confirming the position of the s pore holes.

According to the present invention, the first step includes generating N pieces of recognition data obtained by sensing N (N > = 2) times of a user's body part in a specified ms (millisecond) (N + 1) -th recognition data among the n < th > recognition data and the (n + 1) (N-1) pieces of difference recognition data including the n-th piece of recognition data obtained by subtracting the value of the (n-1) pieces of recognition data from the ridge area of the generated (N-1) 3) number of sensing value singularity regions; and identifying at least s (3? S? S) sensing value singularity regions among the identified S sensing singularity singularity regions as pore holes formed in the body region And recognizing the position of the s pore holes.

According to the present invention, the first step includes generating N pieces of recognition data obtained by sensing N (N &gt; = 2) times of a user's body part in a specified ms (millisecond) (N + 1) (1? N <N) recognition data obtained by subtracting the sensed value of the first recognition data from the sensed value of the (n + 1) Generating S (S? 3) cumulative difference recognition data including the (N-1) cumulative difference recognition data and the S (S? 3) And recognizing at least s (3? S? S) sensing value singularity regions of the identified S sensing value singularity regions as pore holes formed in the body region sensed by the sensor section to identify s pore positions .

According to the present invention, the third step may include determining, as a reference point, the position of one of the s pore locations on the basis of the types of minutiae existing on the ridge pattern.

According to the present invention, the third step includes a step of determining a position of one of the s pore holes as a reference point based on a ridge pattern structure and an arrangement relationship of at least one feature point existing on the ridge pattern .

According to the present invention, the third step may include the step of determining, as a reference point, the position of one of the s pore locations based on the arrangement relationship between two or more feature points existing on the ridge pattern. On the other hand, the arrangement relationship among the minutiae points may include at least one of the minutiae point types, the distance relation between the minutiae points, the angle relation between the minutiae points and the minutiae points.

According to the present invention, the geometric relationship may include at least one of a distance relation between the reference point and the porthole position, an angle relationship between the reference point and the porthole position, a distance relation between the porthole position and the porthole position, and an angle relationship between the porthole position and the porthole position Or may include two or more relationships. On the other hand, the geometric relationship may include at least U (U? 3) effective distance relationships or angular relationships.

According to the present invention, in the fourth step, when the pore data is stored, at least U (U &gt; 3) corresponding to the union of the effective geometric relationships calculated by repeatedly sensing the same body part ) Geometric relationships of the pore holes.

According to the present invention, in the case of storing the pore data, the fourth step includes generating a plurality of pore data including a geometric relationship by a plurality of reference points, and the fifth step includes a step And storing the generated pore template in a designated storage area.

According to the present invention, in the fifth step, when the pore data is authenticated, the step of coordinate-rotating the geometric relationship of the generated pore data based on the reference point so as to match the geometric relationship of the pore template, And comparing the rotated geometric relationship with the geometric relationship of the pore template to verify that it matches within the tolerance range.

According to the present invention, in the fifth step, when the pore data is authenticated, at least u (3? U? U) geometric relations among the U (U? 3) geometric relations included in the pore templates are generated And matching the geometric relationship of the pore hole data with the tolerance within the tolerance range.

According to the present invention, by authenticating the inherent geometrical relationship formed by the pores formed in the fingerprint ridge area separately from the fingerprint matching confirmation, even if the fingerprint is copied using materials having physical, chemical, and electrical characteristics similar to the human epidermis, Unless you simulate it, there is an advantage of significantly reducing the threat of hacking by fingerprinting.

According to the present invention, by using the fingerprint matching as identification means for identifying the user and using the geometric relationship of the pores formed in the fingerprint ridge as the authentication means for authenticating that the fingerprint is an actual user, identification and authentication are simultaneously There is an advantage to provide.

BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a view showing a cross-sectional structure of a skin against sweat glands formed on a human body;
2 is a view illustrating an optical image of a ridge, a bone, and a pore formed in a fingerprint of a human body.
FIGS. 3A to 3F are diagrams showing cross-sectional structures of a ridge, a bone, and a pore formed in a fingerprint of a human body.
4A and 4B are views showing a cross-sectional structure for sensing ridges, bones, and pores formed in the fingerprint of a human body.
5 is a functional block diagram of an apparatus for recognizing and authenticating pore holes according to an embodiment of the present invention.
Figure 6 illustrates an example of a geometric relationship according to an embodiment of the present invention.
7 is a diagram illustrating a process of recognizing and authenticating pores according to an embodiment of the present invention.

The operation principle of the preferred embodiment of the present invention will be described in detail with reference to the accompanying drawings and description. It should be understood, however, that the drawings and the following detailed description are exemplary and explanatory and are intended to provide further explanation of the invention, and are not to be construed as limiting the present invention.

In other words, the following embodiments correspond to the preferred embodiment of the preferred embodiment of the present invention. In the following embodiments, a specific configuration (or step) is omitted, or a specific configuration (or step) (Or steps), or an embodiment that incorporates functions implemented in more than one configuration (or step) into any one configuration (or step), a particular configuration (or step) It will be apparent that the present invention is not limited to the embodiments described below. Therefore, it should be clearly stated that various embodiments corresponding to subsets or combinations based on the following embodiments can be subdivided based on the filing date of the present invention.

In the following description of the present invention, a detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention rather unclear. The terms used below are defined in consideration of the functions of the present invention, which may vary depending on the user, intention or custom of the operator. Therefore, the definition should be based on the contents throughout the present invention.

As a result, the technical idea of the present invention is determined by the claims, and the following embodiments are merely means for effectively explaining the technical idea of the present invention to a person having ordinary skill in the art to which the present invention belongs Only.

FIG. 1 is a view showing a skin cross-sectional structure for the sweat glands formed on the human body.

There are two types of sweat glands in the human body: eccrine sweat glands and apocrine sweat glands. Apocrine sweat glands are sweat glands that are formed with hair and sebaceous glands. They are distributed in the armpits, outer ear (outer ear canal), eyelids, etc., and the eczrine sweat glands are sweat glands distributed throughout the skin except the glans part of the body, Among them, eccrine sweat glands are mainly distributed in the palms, soles, underarms, and forehead skin. The sweat produced from each sweat gland moves along the sweat pouch and is discharged to the outside through the pores. The size of the sweat pouch is about 50 times smaller than the thickness of the hair (about 50 μm to 70 μm).

2 is a view illustrating an optical image of a ridge, a bone, and a pore formed in a fingerprint of a human body.

Ridges of the fingerprint are formed along the positions of the sweat glands in fingers or toes of the body parts of the human body, and valleys are formed between ridges and ridges. That is, the ridge of the fingerprint is a ridge of the skin along the sweat glands formed on the finger or the toe. Some rinse sweat glands are distributed mainly in ridge of fingerprints, but some of apocrine glands may be formed.

Male ridges are formed at intervals of 200 μm to 850 μm and average distances are measured at about 460 μm. In the case of females, ridges are formed at intervals of 200 μm to 750 μm, and the average distance is measured to be about 410 μm. Also, the distance between pores is formed at intervals of 200 mu m to 1500 mu m, and the average distance is measured to be about 830 mu m. However, the above figures are average statistics and the actual distance may vary from person to person.

FIGS. 3A to 3F are views showing cross-sectional structures of ridges, bones, and pores formed in a fingerprint of a human body.

In more detail, FIGS. 3A to 3F show a short structure when the fingerprint of the human body is directed upward. The pores formed on the ridge of the fingerprint can be formed in various shapes such as circular, elliptical, and fusiform, and the cross section of the pores has a crater shape. At this time, the diameter of the crater is within 200 占 퐉.

When the sweat produced in the sweat glands starts to swell, the sweat produced in the sweat glands moves along the sweat gang as shown in FIG. 3b, and sweats as shown in FIGS. 3c to 3e to fill the craters of the swallow gang first. According to the definition of the present invention, the sweat which is sweated and is held in the crater of the pore hole as shown in Figs. 3c to 3e is defined as &quot; micro sweat &quot;. According to another definition of the present invention, fine sweat can be defined as perspiration sweating less than 1 μL.

If the sweat generated in the sweat glands is further sweated in the sweated minute sweat state as shown in FIGS. 3c to 3e, the sweated sweat flows over the crater of the sweat hole as shown in FIG. 3f. The present invention defines sweat flowing over a crater of a pore as "wet sweat" as shown in FIG. 3f. Preferably, the wet sweat first flows along the ridge and then overflows in the bone direction. Usually, the expression "sweat" means wet sweat.

On the other hand, according to the experiment of the applicant, it is unusual for the perspirated fine sweat to grow as the wet sweat as shown in FIG. 3f, as shown in FIGS. 3c to 3e, unless a specific perspiration induction situation occurs. In the human body, about 500 to 900 pores are arranged irregularly per 1 cm 2. In some of these pores, fine sweat is generated irregularly as shown in FIGS. 3c to 3e. However, most of the fine sweat is only accumulated in the crater of the pore, as shown in FIG. 3c, FIG. 3d or FIG. 3e, and disappears, and it is rare to grow wet sweat as shown in FIG. 3f unless a special sweat induction situation occurs. According to the definition of the present invention, the perspiration of fine sweat which is present in the crater of a pore as shown in Fig. 3c, Fig. 3d or 3e is defined as &quot; fine sweating &quot;. That is, in the present invention, micro-sweating can be defined as sweating in the form of being swollen in the crater of the pore as shown in FIG. 3c, FIG. 3d or FIG. 3e and then disappearing without growing with wet sweat.

In addition, according to the repeated experiments of the applicant, it has been found that microscopic sweating occurs very irregularly (that is, unpredictable in which pores it swells) and in some milligrams, in milliseconds, in figures 3b to 3c or 3d or 3e As shown in FIG. 3B, and then the fine perspiration disappears as shown in FIG. 3B. The reason why the fine perspiration persists in ms units as shown in FIG. 3B, FIG. 3C, FIG. 3D or FIG. 3E and then disappears as shown in FIG. 3B is because very small amount of fine perspiration sweated in a very small amount or less evaporates at the same time, It is assumed that the fine sweat is sucked into the state of FIG. 3b by a certain biological reaction. On the other hand, in the case of some other minute sweating, it has been confirmed that the sweating state is maintained for a predetermined time (for example, ms units to one second) as shown in FIG. 3C, FIG. 3D or FIG. However, the fine sweat which has been maintained for a certain period of time is mostly extinguished to the state of FIG. 3b unless a specific perspiration induction state occurs, and it can be confirmed that only a part of the fine sweat which has been maintained for a certain period of time grows as wet sweat.

The recognition of the pore hole of the present invention is characterized by recognizing the pore in the untreated state as shown in FIG. 3A or FIG. 3B and the sweat pore swollen in fine sweat as shown in FIG. 3C, FIG. 3D or FIG. 3E. The perforation recognition of the present invention can be sensed through a sensor unit 505 having a sensor capable of sensing a fingerprint. According to the method of the present invention, the sensor of the sensor unit 505 may be any sensor (for example, an electrostatic sensor, an optical sensor, an ultrasonic sensor, or the like) as long as the sensor can recognize the fingerprint, The characteristics of the present invention will be described with reference to embodiments using a sensor unit 505 having an electrostatic sensor. However, it should be clear that embodiments of the present invention are by no means limited to the manner in which electrostatic sensors are used.

4A and 4B are views showing a cross-sectional structure for sensing a ridge, a bone, and a pore formed in a fingerprint of a human body.

More specifically, FIG. 4A shows a cross-sectional structure for sensing fingerprint ridges, bones, and pores in FIG. 3A using a sensor unit 505 having an electrostatic sensor for sensing a capacitance, and FIG. And a fingerprint ridge, a bone, and a pore of the finger in Fig. 3d are sensed by using a sensor unit 505 having an expression sensor.

Referring to FIGS. 4A and 4B, the ridges of ridges, bones, and pores of the fingerprint are in contact with (or in proximity to) the sensor unit 505. Therefore, when the sensor unit 505 is made of an electrostatic sensor, the electrostatic sensor acquires a sensing value closest to the capacitance of the human body with respect to the ridge. On the other hand, as compared with the ridge, the ridge is spaced apart from the sensor unit 505 by a predetermined distance or more. Accordingly, when the sensor unit 505 is made of an electrostatic sensor, the electrostatic sensor acquires a sensing value of a capacitance sufficiently contrasted with the capacitance of the ridge to the valley. The sensor unit 505 can acquire sensing data capable of distinguishing ridges of fingerprints from each other by comparing the sensing values of ridges and bones.

On the other hand, pit-shaped pores having a diameter of about 200 mu m are irregularly arranged at intervals of about 830 mu m on the ridge. Therefore, in order to sense pores having a diameter of about 200 μm, the sensor resolution of the sensor unit 505 (for example, the size of one pixel of the electrostatic sensor provided in the sensor unit 505) is preferably 50 μm or less. When the sensor resolution is 50 μm or less, the sensor unit 505 can effectively sense the pores through at least one to four sensors.

As shown in FIG. 4A, in an untreated state where sweat does not swell, a void is formed in the pores on the fingerprint ridge. Therefore, when the sensor unit 505 is an electrostatic sensor, the electrostatic sensor can obtain a sensing value corresponding to a sensing value between the sensing value of the ridge and the sensing value of the ridge relative to the pore of FIG. 4A.

As shown in FIG. 4B, when the sweat sweating occurs, the sweat sweat contains salts, amino acids, cells and the like. Therefore, the sweat capacitance may be larger than that of the human body. Therefore, when the sensor unit 505 is made of an electrostatic sensor, the electrostatic sensor can obtain a sensing value corresponding to a capacitance larger than the sensed value of the ridge with respect to the pore of FIG. 4A.

5 is a functional block diagram of an apparatus 500 for recognizing and authenticating pore holes according to an embodiment of the present invention.

5 shows a functional configuration of an apparatus 500 for recognizing a pore formed on a ridge of a fingerprint by using a sensor unit 505 capable of sensing a fingerprint. In the technical field of the present invention, Those skilled in the art will be able to refer to and / or modify this FIG. 5 to infer various embodiments of the apparatus 500 (e.g., some of the components may be omitted, or broken down, or combined) The present invention is not limited to the above-described embodiments, and the technical features of the present invention are not limited only by the method shown in FIG.

The device 500 of the present invention is a general term for a configuration for recognizing pores formed on a ridge of a fingerprint using a sensor unit 505 capable of sensing a fingerprint and is a module (or chip) type , A distributed system including various devices and servers on a network, and the like.

According to a first embodiment of the present invention, the device 500 of the present invention may be implemented in the form of various devices for use by a user. For example, the device 500 may be implemented in the form of a terminal (e.g., a smart phone, a mobile phone, a tablet PC, a notebook PC, etc.), a recognition device, an authentication device, a door lock device, 5 may be implemented in the form of H / W, S / W or a combination thereof mounted on each device.

According to the second embodiment of the present invention, the apparatus 500 of the present invention can be implemented in the form of a module (or a chip) mounted on various devices used by a user. For example, the device 500 may be implemented in the form of a module (or chip) embedded in various devices such as a terminal, a recognition device, an authentication device, a door lock device, etc. used by a user, The configuration unit may be implemented in a form of H / W or S / W or a combination thereof mounted on the module (or chip), and according to an implementation method, a part of the functional components shown in FIG. And the other part may be implemented on the device side on which the module (or chip) is mounted.

According to the third embodiment of the present invention, the apparatus 500 of the present invention can be distributedly implemented through various devices used by users and servers on the network. For example, the device 500 may include various devices such as a terminal, a recognition device, an authentication device, a door lock device, etc., used by a user and a server on a network. And other parts may be implemented in a server on the network.

According to a fourth embodiment of the present invention, the apparatus 500 of the present invention can be implemented in a form of a combination of at least two embodiments among the first to third embodiments. That is, the present invention is not limited to the method of implementing the device 500 or the embodiment, and if it is implemented in any form, it is evident that the function of the device 500 is included in the scope of the present invention if the function of the claim is implemented .

The apparatus 500 of the present invention includes a sensor unit 505 capable of sensing a fingerprint in a hardware manner. The sensor unit 505 may be any sensor capable of recognizing a fingerprint, such as an electrostatic sensor, an optical sensor, an ultrasonic sensor, or the like. If the sensor is capable of sensing fingerprints, It is evident that the sensor unit 505 of the present invention is available and belongs to the scope of the right. Hereinafter, the characteristics of the present invention will be described with reference to an embodiment using a sensor unit 505 having an electrostatic sensor for sensing a capacitance. However, it should be clear that embodiments of the present invention are by no means limited to the manner in which electrostatic sensors are used.

According to the method of the present invention, the sensor unit 505 preferably has a resolution of 50 μm or less (for example, one pixel of the electrostatic sensor).

Referring to FIG. 5, the apparatus 500 includes a sensing unit 510 for sensing sensing data obtained by sensing a user's body part through the sensing unit 505, A fingerprint storage unit 520 for generating fingerprint templates corresponding to the extracted feature points and storing the generated fingerprint templates in a designated storage area, And a fingerprint matching unit 525 that authenticates the extracted feature points using a user's fingerprint template previously stored in the fingerprint matching unit. The fingerprint recognition unit 515, the fingerprint storage unit 520, and the fingerprint matching unit 525 may be omitted according to the embodiment, and thus the present invention is not limited thereto.

The sensing processing unit 510 acquires sensing data obtained by sensing a body part of the user through the sensor of the sensor unit 505. Preferably, the sensing unit 510 acquires image sensing data of pixels. It is preferable that one pixel of the sensing data is 50 mu m or less.

The fingerprint recognition unit 515 performs a process for preliminarily correcting the sensing data obtained through the sensing processing unit 510 according to a specified fingerprint recognition algorithm. Preferably, the fingerprint recognition unit 515 performs a smoothing process on the sensing data obtained through the sensing unit 510, and the noise in the sensing process is removed through the smoothing process.

The fingerprint recognition unit 515 performs a preprocessing procedure for reading the corrected sensing data obtained through the sensing processing unit 510. [ Preferably, the fingerprint recognition unit 515 performs a binarization process, a thinning process, and a directionality extraction process for the acquired / corrected sensing data. The binarization procedure includes a procedure for distinguishing between a ridge portion and a valley portion on the sensing data in black and white. The thinning procedure includes a process of distinguishing the width of the ridge on the binarized sensing data by a line of a specified reference pixel (e.g., one pixel). The directional extraction procedure includes a procedure of extracting a relative direction of a ridge (e.g., a thin line) within the entire area of the binarized or thinned sensing data.

The fingerprint recognition unit 515 reads the preprocessed sensing data and performs a process of extracting minutiae points on the ridge pattern included in the sensing data. Preferably, the feature point includes at least one of a start point, an end point, a branch point, a center point, and a delta, and may be a merge, a loop, a bridge, a cross, , Triangle, Break, Spur, Ladder, Double Break, Break & Merge, Iceland, and more. have.

In the case of registering a fingerprint of a user, the fingerprint storage unit 520 may generate a fingerprint template including the extracted minutiae and store the fingerprint template in a designated storage area. According to the embodiment of the present invention, in order to register a fingerprint of a user, the sensor unit 505 senses the same part of the user's body (e.g., touching the same part of the body to the sensor unit 505, The fingerprint storage unit 520 may generate a fingerprint template including the union of the minutiae repeatedly extracted in the repeated process and store the fingerprint template in the designated storage area.

On the other hand, when authenticating the user's fingerprint, the fingerprint matching unit 525 compares the fingerprint templates stored in the designated storage area with the extracted feature points through the fingerprint recognition unit 515 to determine whether they match or not. A fingerprint matching result is generated.

Referring to FIG. 5, the apparatus 500 includes a recognition data generating unit 500 for reading sensing values of sensing data obtained through the sensing processing unit 510 for recognizing pore holes and generating recognition data capable of distinguishing ridges and valleys, (530). Meanwhile, according to another embodiment of the present invention, the sensing unit 510 senses N (N &gt; = 3) times of the body part of the user in units of a predetermined sensing period ms (millisecond) through the sensor unit 505 In this case, the recognition data generation unit 530 can generate N pieces of recognition data capable of distinguishing ridges and valleys by reading the sensed values of the N pieces of sensing data obtained through the sensing unit 510. [

The recognition data generation unit 530 reads the sensing value of the sensing data obtained through the sensing processing unit 510 to distinguish the ridge and the valley, and at the same time, the sensing value corresponding to the pores included in the ridge is undermined And generates the recognition data corrected so as not to be corrected. Preferably, the recognition data generator 530 removes the noise of the sensor provided in the sensor unit 505 (for example, a noise generated by the frequency signal applied to the electrostatic sensor) from the sensing value of the sensing data (For example, noise caused by contamination on the surface of the sensor unit 505), a correction for removing the noise generated in the sensing process through the sensor unit 505 (For example, noise caused by moisture or dust in the body part contacting with the sensor unit 505) caused by noise from the image data, correction for image processing such as contrast, contrast, and contrast of the ridge area and the bony area on the sensing data By performing at least one or two or more correction procedures, it is possible to distinguish ridges and valleys, and at the same time generate recognition data in which the sensing value corresponding to the pores on the ridges is not damaged The. That is, the fingerprint recognizing unit 515 performs smoothing, binarization, thinning, and the like to damage the sensed value of the pore on the ridge, while the recognition data generating unit 530 does not damage the sensed value of the pore on the ridge And performs correction to improve the quality of the sensing data to generate recognition data.

Referring to FIG. 5, the apparatus 500 includes a singularity identification unit 535 for identifying S (S? 3) sensing value singularity regions distributed on a ridge region included in the recognition data, A pore recognition part 540 recognizing at least s (3? S? S) sensing value singularity areas of the S sensing area singularity areas as s pore holes formed in a body part of a user sensed through the sensor part 505, And a feature point checking unit 555 for checking the feature points of the ridge pattern matching the ridge region included in the recognition data according to the method of operation.

According to the first outlier discrimination embodiment of the present invention, the outlier discriminator 535 determines the baseline sensing value for the ridge area included in the recognition data, and uses the base sensing value for the ridge area (S &gt; = 3) sensing value singularity regions can be identified.

If at least one piece of recognition data that can distinguish ridges and valleys from the recognition data generation unit 530 and that does not damage the pore sensing value is generated, the singularity identification unit 535 identifies the ridge area included in the recognition data The base sensing value for the ridge region in the bony region is determined. Here, the base sensing value may be defined as a sensing value corresponding to a body part in contact with the sensor part 505 of the user's body part, and / or a sensing value serving as a reference for distinguishing a ridge area and a bony area.

According to the first base sensing value determination method of the present invention, the outlier identification unit 535 can determine the base sensing value for the ridge region with respect to the entire area of the recognition data.

According to the second base sensing value determination method of the present invention, the outlier identification unit 535 divides the recognition data into a designated area according to a specified rule, and calculates a base sensing value for the ridge area for each divided area You can decide. The body part contacting the sensor part 505 is not a two-dimensional plane structure but a three-dimensional structure. Therefore, when the body part is in contact with the sensor part 505 of the two-dimensional planar structure, the body part of the three-dimensional structure contacts the sensor part 505 of the two-dimensional planar structure, It is difficult to determine a single basis sensing value for the entire area of the recognition data because the distribution of contact forces is difficult to uniformly act on the entire body part. Even if the geometric shape of the sensor unit 505 is made to match with the body part of the three-dimensional structure, since the distribution of the force of contacting the body part with the sensor unit 505 is not always uniform, Determining a single baseline sensing value can be daunting. Accordingly, the outlier identification unit 535 may divide the recognition data into a designated region according to a specified rule, and determine a base sensing value for the ridge region for each divided region. For example, the singularity identification unit 535 may divide the recognition data into a grid structure, a concentric circle structure, or a sector shape to determine a base sensing value for the ridge region for each divided region .

According to the third base sensing value determination method of the present invention, the outlier discrimination unit 535 identifies a gradation pattern of the sensing value included in the recognition data, and outputs the recognition data based on the gradation pattern The base sensing value for the ridge area can be determined for each area. That is, since the distribution of the force of contacting the body part with the sensor part 505 is not always uniform, there is a gradation pattern in the sensing value between the part where the user applies more force and the part where less force is applied. The outlier identification unit 535 identifies the gradation pattern of the sensing value, divides the gradation pattern into a predetermined number of steps, divides the recognition data on the basis of the gradation pattern, and determines a base sensing value for the ridge region for each region have.

According to the fourth base sensing value determination method of the present invention, the singularity identification unit 535 may determine a ridge included in the recognition data by partially combining two or more of the first through third basis sensing value determination methods, The base sensing value for the region can be determined.

Meanwhile, embodiments for determining the base sensing value according to any one of the first to fourth base sensing value determination methods may be variously provided.

According to the first base sensing value determination method of the present invention, the outlier discrimination unit 535 identifies a specific region (for example, the entire region of the recognition data) of the recognition data by using any one of the first to fourth base sensing value determination methods Region or a divided region) of the ridge region and the bony region, and may determine the calculated region distinguishing value as the base sensing value of the ridge region.

According to the second base sensing value determination method of the present invention, the outlier discrimination unit 535 may determine the first base sensing value by using one of the first to fourth base sensing value determination methods, (For example, an arithmetic expression for correcting an error) is substituted for a value calculated by dividing the value of the area discrimination value into a base sensing area of the ridge area Value. &Lt; / RTI &gt;

According to the third base sensing value determination method of the present invention, the outlier discrimination unit 535 determines whether or not the sensed data included in the specified area of the recognition data And a value belonging to the designated distribution region on the sensing value distribution may be determined as the base sensing value of the ridge region. For example, when the sensing value distribution of the designated area is in the form of a normal distribution, the singularity identification unit 535 identifies a value belonging to the mean (m) of the normal distribution or within the standard deviation Can be determined as the base sensing value of the ridge area.

According to the fourth base sensing value determination method of the present invention, the outlier discrimination unit 535 determines whether or not the sensed data included in the specified area of the recognition data And a value belonging to the designated distribution area on the sensing value distribution is substituted into the specified correction equation to determine the calculated value as the base sensing value of the ridge area.

According to the fifth base sensing value determination method of the present invention, the outlier discrimination unit 535 may determine whether or not the sensed data included in the specified area of the recognition data And the calculated average value may be determined as the base sensing value of the ridge region.

According to the sixth base sensing value determination embodiment of the present invention, the outlier identification unit 535 identifies the first base sensing value by using one of the first to fourth base sensing value determination methods, And calculating the calculated value by substituting the calculated average value into the specified correction operation equation as the base sensing value of the ridge region.

According to the seventh base sensing value determination embodiment of the present invention, the outlier identification unit 535 may modify at least one of the first to sixth base sensing value determination embodiments, or partially combine two or more embodiments The base sensing value for the ridge region can be determined, and thus the present invention is not limited thereto.

When the base sensing value for the ridge area included in the designated area (for example, the entire area or the divided area) of the recognition data is determined, the outlier identification unit 535 uses the base sensing value of the designated area (S &gt; = 3) sensing value singularity regions distributed on the ridge region included in the region. Preferably, the sensing value singularity region includes a region having a diameter of 200um or less, and may be identified with an interval of 200um to 1500um.

Meanwhile, according to the embodiment of the present invention, the minutia matching unit 555 may identify the minutiae of the ridge pattern matching with the ridge region included in the recognition data, in cooperation with the fingerprint recognition unit 515. [ In this case, the outlier identification unit 535 can identify a sensing value singularity area distributed near a minutia point on the ridge pattern using the basis sensing value of the designated area.

According to the first sensing value identification embodiment of the present invention, the outlier discrimination section 535 identifies the discrimination data on the ridge area included in the specified area (for example, the entire area or the divided area) of the recognition data, An area that is greater than or equal to the '+' contrast value can be identified as the sensing value singularity area. For example, when fine sweat is generated on the ridge-shaped pores as shown in FIG. 3E, the outlier identification unit 535 detects an area of the ridge area that is equal to or greater than a predetermined '+' contrast value than the base sensing value, Area. &Lt; / RTI &gt;

According to the second sensing value identification method of the present invention, the outlier identification unit 535 identifies, on the ridge area included in the designated area of the recognition data, an area that is less than or equal to a pre- Value can be identified as a singularity domain. For example, when fine sweat is not generated on the ridge-shaped pores as shown in FIG. 3A or FIG. 3B, the outlier identification unit 535 detects an area in the ridge area that is less than a predetermined '-' And can be identified as the sensing value singularity region.

According to the third sensing value discrimination embodiment of the present invention, the outlier discrimination unit 535 identifies the third sensing value in the ridge area included in the designated area of the recognition data in the area which is less than the pre- A region including a region equal to or greater than the '+' contrast value may be identified as the sensing value singularity region. For example, when a very small amount of fine sweat is generated on the ridge-shaped pores of the ridge as shown in FIG. 3C, the outlier identification unit 535 determines that the ridge region has been previously set in the region that is less than the pre- A region including a region equal to or greater than the '+' contrast value may be identified as the sensing value singularity region.

According to the fourth sensing value identification method of the present invention, the singularity identification unit 535 identifies, on the ridge area included in the designated area of the recognition data, A region including an area less than or equal to a '-' contrast value may be identified as the sensing value singularity area.

According to the fifth sensing value identification method of the present invention, the outlier identification unit 535 identifies, on the ridge area included in the designated area of the recognition data, an area having a value of the '+' A region in which regions having a contrast value equal to or less than a value of '-' are connected to each other can be identified as the sensing value singularity region.

According to the sixth sensing value discrimination embodiment of the present invention, the outlier discrimination unit 535 discriminates the sensed value on the ridge area in the form of partially combining two or more embodiments among the first to fifth sensing value discrimination examples It is possible to identify the singularity region, and thus the present invention is not limited thereto.

If S sensing value singularity regions distributed on the ridge region are identified through the first to sixth sensing value identification examples, the pore recognition unit 540 recognizes at least s (3 &amp;le; s &amp;le; S) sensed value singularity regions are recognized as s pore holes formed in a body part of a user sensed through the sensor unit 505, and the recognized s pore locations are confirmed.

Meanwhile, the minutia matching unit 555 may extract the minutiae of the ridge pattern matching with the ridge area included in the recognition data, in cooperation with the fingerprint recognition unit 515, can confirm. In this case, the porthole recognizing unit 540 recognizes the s sensed value singular point regions arranged in the vicinity of the minutiae points of the ridge pattern as s pore holes formed in the body part of the user who sensed through the sensor unit 505 And recognize the positions of the recognized s pore holes.

According to the second embodiment of the present invention, the sensing part 510 senses the user's body part N times in a sensing period and generates N recognition data through the recognition data generation part 530 , The singularity discriminator 535 matches the ridge and the valley of each of the N pieces of recognition data to generate the n (1? N <N) recognition data and the (n + 1) (N-1) pieces of difference data containing nth subtraction data obtained by subtracting the sensed value of the n-th recognition data from the sensed value of the (n-1) -th recognition data, (S &gt; = 3) sensing value singularity regions distributed on the ridge region of the difference data.

When the recognition data generation unit 530 generates N pieces of recognition data that can distinguish ridges and valleys and that do not damage the pore sensing value, the outlier identification unit 535 recognizes the recognition data generation unit 530 (N + 1) -th recognition data and the ridge and valley of the (n + 1) -th recognition data, (N-1) pieces of difference data are generated by repeating the process of generating the n-th data by subtracting the difference data. For example, the recognition data generation unit 530 generates first data by subtracting the sensing value of the first recognition data from the sensing value of the second recognition data, and generates second recognition data from the sensing value of the third recognition data The second cumulative difference data may be generated by subtracting the sensed value of the data, and the third cumulative difference data may be generated by subtracting the sensed value of the third recognized data from the sensed value of the fourth recognized data.

According to the embodiment of the present invention, the sensing processing unit 510 obtains N sensing data obtained by sensing the same body part N times in the specified ms while the body part of the user is in contact with the sensor part 505 At this time, even if the user tries to fix the body part, the body part in contact with the sensor part 505 can move subtly. The outlier discriminator 535 generates the n-th difference data by subtracting the sensed value of the (n + 1) -th recognition data from the sensed value of the (n + 1) -th recognition data by matching the ridge and the valley of each recognition data, Can be corrected.

Meanwhile, while the sensing processing unit 510 acquires N sensing data obtained by sensing the body part of the user in contact with the sensor unit 505 N times in a specified ms unit, the user can not recognize his or her body part in the sensor unit 505, The contact pressure applied by the user to the sensor unit 505 can be changed in units of ms. As long as the contact pressure does not change to such a degree that the ridge pattern of the body part contacting the sensor part 505 is distorted, the sensing value of the ridge area and the bony area of the body part sensed by the sensor part 505 There is no significant change, but the sensed value of the pore area formed on the ridge area changes greatly even when the contact pressure is small. Therefore, when the sensed value of the n-th recognition data is subtracted from the sensed value of the (n + 1) -th recognition data continuously obtained, the sensed value of the ridge area and the bony area of the n- While the sensing value of at least a part of the pore area of the pore area formed on the ridge area has a peak shape.

The outlier identification unit 535 identifies at least one sensing value singularity area distributed in a peak shape on the ridge area by the generated (N-1) pieces of difference data, identifies (S &gt; = 3) sensing value singularity regions corresponding to the union of the sensing value singularity regions of the respective sensing values. According to the method of the present invention, the sensing value singularity area can be more clearly identified as the N is larger and / or the total time for acquiring the sensing data is longer.

Meanwhile, according to an example of the second singular point region identification example, the minutia matching unit 555 may extract the minutiae point of the ridge pattern matching with the ridge region included in the recognition data in cooperation with the fingerprint recognition unit 515, can confirm. In this case, the outlier identification unit 535 can identify the sensing value singular point area distributed near the minutia points on the ridge pattern using the (N-1) pieces of difference data.

When the S sensed value singular point regions distributed in the ridge region (or in the vicinity of the minutiae points of the ridge pattern) are identified through the singularity identification unit 535, the pore recognition unit 540 identifies the identified S sensed value singularities S (3? S? S) sensing point singularity regions of the region are recognized as s pore holes formed in the body part of the user who sensed through the sensor unit 505 and the recognized s pore positions are confirmed.

Meanwhile, according to an example of the second singular point region identification example, the minutia matching unit 555 may extract the minutiae point of the ridge pattern matching with the ridge region included in the recognition data in cooperation with the fingerprint recognition unit 515, can confirm. In this case, the porthole recognizing unit 540 recognizes the s sensed value singular point regions arranged in the vicinity of the minutiae points of the ridge pattern as s pore holes formed in the body part of the user who sensed through the sensor unit 505 And recognize the positions of the recognized s pore holes.

According to the third discrimination region identification method of the present invention, the sensing part 510 senses the user's body part N times in a sensing period and generates N recognition data through the recognition data generation part 530 The singularity discriminator 535 matches the ridges and valleys of the generated N pieces of recognition data and outputs the first recognition data at a sensing value of the (n + 1) (1? N <N) (N-1) cumulative difference data including nth cumulative difference data obtained by subtracting the sensed values from the cumulative difference data, and generates S (n-1) (S &gt; = 3) sensing value singularity regions.

When the recognition data generation unit 530 generates N pieces of recognition data that can distinguish ridges and valleys and that do not damage the pore sensing value, the outlier identification unit 535 recognizes the recognition data generation unit 530 (N + 1) -th recognition data by matching the ridge and the valley of the (n + 1) th recognition data and the (n + 1) (N-1) cumulative difference data is generated by repeating the process of generating the n-th cumulative difference data. For example, the outlier discrimination unit 535 generates first accumulated difference data by subtracting the sensed value of the first recognition data from the sensed value of the second recognition data, It is possible to repeat the process of generating the second accumulated difference data by subtracting the sensed value of the data and subtracting the sensed value of the first recognized data from the sensed value of the fourth recognized data to generate the third accumulated difference data.

According to the embodiment of the present invention, the sensing processing unit 510 obtains N sensing data obtained by sensing the same body part N times in the specified ms while the body part of the user is in contact with the sensor part 505 At this time, even if the user tries to fix the body part, the body part in contact with the sensor part 505 can move subtly. The singularity discriminator 535 generates the n-th accumulated difference data by subtracting the sensed value of the first recognition data from the sensed value of the (n + 1) -th recognition data by matching the ridge and the valley of each recognition data It is possible to correct the error caused by the motion of the user.

Meanwhile, while the sensing processing unit 510 acquires N sensing data obtained by sensing the body part of the user in contact with the sensor unit 505 N times in a specified ms unit, the user can not recognize his or her body part in the sensor unit 505, The contact pressure applied by the user to the sensor unit 505 can be changed in units of ms. As long as the contact pressure does not change to such a degree that the ridge pattern of the body part contacting the sensor part 505 is distorted, the sensing value of the ridge area and the bony area of the body part sensed by the sensor part 505 There is no significant change, but the sensed value of the pore area formed on the ridge area changes greatly even when the contact pressure is small. Therefore, when the sensing value of the first recognition data is subtracted from the sensing value of the (n + 1) -th recognition data, the sensing value of the ridge area and the bony area of the n-th accumulation difference data has a sensing value close to '0' Whereas the sensing value of at least a part of the pore region of the pore region formed on the ridge region has a peak shape.

The outlier discriminator 535 identifies at least one sensed value singularity area distributed in a peak shape on the ridge area by the generated (N-1) accumulated difference data, and the (N-1) (S &gt; = 3) sensed value singularity regions corresponding to the union of the respective sensing value singularity regions identified in (1). According to the method of the present invention, the sensing value singularity area can be more clearly identified as the N is larger and / or the total time for acquiring the sensing data is longer.

Meanwhile, according to an example of the third singularity region discrimination embodiment, the minutia matching unit 555 may be configured to perform a minutia matching process with the fingerprint recognition unit 515 to extract minutiae points of a ridge pattern matching with a ridge region included in the recognition data can confirm. In this case, the outlier discriminator 535 can identify the sensed value outlier region distributed near the minutiae points on the ridge pattern using the (N-1) cumulative difference data.

When the S sensed value singular point regions distributed in the ridge region (or in the vicinity of the minutiae points of the ridge pattern) are identified through the singularity identification unit 535, the pore recognition unit 540 identifies the identified S sensed value singularities S (3? S? S) sensing point singularity regions of the region are recognized as s pore holes formed in the body part of the user who sensed through the sensor unit 505 and the recognized s pore positions are confirmed.

Meanwhile, according to an example of the third singularity region discrimination embodiment, the minutia matching unit 555 may be configured to perform a minutia matching process with the fingerprint recognition unit 515 to extract minutiae points of a ridge pattern matching with a ridge region included in the recognition data can confirm. In this case, the porthole recognizing unit 540 recognizes the s sensed value singular point regions arranged in the vicinity of the minutiae points of the ridge pattern as s pore holes formed in the body part of the user who sensed through the sensor unit 505 And recognize the positions of the recognized s pore holes.

Referring to FIG. 5, the apparatus 500 includes a minutia matching unit 555 for identifying minutiae of a ridge pattern matching with a ridge region included in the recognition data, A reference point determining unit (545) for determining a position of a pore of one of the pawl positions of the pawls as a reference point, and pore data including a geometric relationship for at least t (3? T? S) pawl positions based on the determined reference point A pore storage section 560 for storing pore templates including the generated pore data in a designated storage area, a pore storage section 560 for storing the generated pore template data in the designated storage area, A pore hole authentication unit (565) for authenticating the validity of the pore hole data, and a predetermined authentication result including the pore hole authentication result, And an authentication result processing unit 570 that processes the body part of the body part as a result of the biometric authentication.

The minutia matching unit 555 checks the minutiae of the ridge pattern matching with the ridge area included in the recognition data in cooperation with the fingerprint recognition unit 515 , The pore data generating unit 550 generates the pore location of one of the s pore locations identified through the pore hole recognizing unit 540 using one or more minutiae identified through the minutia checking unit 555 It is determined as a reference point for the geometric relationship to be calculated.

According to the first reference point embodiment of the present invention, the reference point determination unit 545 determines a feature point type (e.g., a starting point on a ridge pattern, an end point on a ridge pattern, A branch point, a center point, a delta, a merge, a loop, a bridge, a cross, a triangle, a break, a spur, a ladder, (At least one characteristic point of a double break, a break & merge, and an island), and confirms the pincushion through the porthole recognition unit 540 based on a specific one of the identified minutiae It is possible to determine the position of any one of the s pore holes as the reference point. For example, the reference point determining unit 545 may determine the position of the pit on the ridge corresponding to the delta as the reference point if a delta among the feature points existing on the ridge pattern exists.

According to the second reference point embodiment of the present invention, the reference point determining unit 545 determines the reference point based on the arrangement of the ridge pattern structure confirmed through the fingerprint recognizing unit 515 and one or more feature points existing on the ridge pattern It is possible to determine the position of one of the s pore holes identified through the pore hole recognizing unit 540 as the reference point. For example, when there is a bridge on a ridge pattern composed of a parallel line structure (or a specific curvature structure) having three or more lines of ridges, the reference point determining unit 545 determines the position of the ridge on the ridge corresponding to the bridge, It can be determined as a reference point. Or if both the starting point and the turning point exist on one ridge, the reference point determining unit 545 can determine the position of the ridge on the ridge corresponding to the turning point as the reference point.

According to the third reference point embodiment of the present invention, the reference point determining unit 545 determines the position of the pore recognition unit (e.g., the pore recognition unit) based on the arrangement relationship between two or more feature points existing on the ridge pattern, 540) to determine the position of one of the pores of the s pores identified as the reference point. Here, the arrangement relationship among the minutiae points may include at least one of a minutiae point type, a distance relation between minutiae points, an angle relation between minutiae points, and a minutiae point direction relationship. For example, when the starting point, the ending point, the branching point, and the like are arranged in a triangular structure, the reference point determining unit 545 determines the position of the ridge pitting on the ridge corresponding to the branching point among the starting point, the ending point, .

According to the fourth reference point embodiment of the present invention, the reference point determining unit 545 determines a position of one of the s pawl positions of the s pawl positions as a reference point in a form that at least two or more of the first to third reference point embodiments are partially combined. .

Once a reference point is determined through the reference point determining unit 545, the pore data generating unit 550 determines at least t (3? T? S) pore locations to calculate a geometric relationship based on the determined reference point do. Preferably, the pore data generator 550 can identify the pores distributed near the minutiae points determined as the reference points out of the identified s number of pore holes by the number of t pore holes to calculate the geometric relationship.

The pore data generator 550 calculates the geometric relationship of the t pore locations based on the determined reference point. Preferably, the geometric relationship is at least one or more of a distance relationship between the reference point and the pore position, an angle relationship between the reference point and the pore position, a distance relation between the pore position and the pore position, and an angle relationship between the pore position and the pore position Relationships.

According to the method of the present invention, the calculated geometric relationship may be in the form of a coordinate value, a coordinate distance, a coordinate angle, or the like relative to the sensor unit 505, or may be a shape such as a position, a distance, . &Lt; / RTI &gt; For example, if the pores of the same body region are recognized through the same sensor unit 505, the geometric relationship may be generated based on a coordinate system corresponding to the sensor unit 505, 505, the geometric relationship can be converted into a measurement unit.

According to the method of the present invention, the calculated geometric relationship is defined by at least U (U? 3) effective distance relations (for example, a distance relation between the reference point and the pore position, a distance relation between the pore position and the pore position, (E.g., an angle relationship between the reference point and the pore position, an angle relationship between the pore position and the pore position, and the like). The greater the calculated geometric relationship, the greater the probability of authenticating to match the geometric relationship of the pores.

The pore data generating unit 550 generates pore data including the recognized geometric relationship. Preferably, the pore data basically includes the geometric relationship, and includes coordinate information of the geometric relationship, reference point identification information that identifies the reference point of the geometric relationship, minutia information on the ridge pattern included in or near the geometric relationship Error information of the geometric relationship (for example, error information by various corrections, error information by the characteristics of the sensor unit 505, error information calculated based on the gradient pattern, a structure of the sensor unit 505 and a curvature structure of the body part Error information due to the characteristic, error information due to the contact pressure for contacting the body part with the sensor unit 505, and the like).

According to the method of the present invention, when storing the pore data in the designated storage area, the pore data generator 550 repeats the same body part of the user for a specified number of times or more and again senses (for example, (U &gt; = 3) geometric relations corresponding to the union of the calculated effective geometric relationships by repeating the process of contacting the sensor portion 505 with the sensor portion 505 for a specified number of times or more) .

When storing the created pore data in a designated storage area, the pore storage unit 560 may generate a pore template including the pore data and store the created pore template in a designated storage area. (For example, tolerance information for authentication of a pore hole (for example, tolerance information on a predetermined design, information on the tolerance on a predetermined design, information on the shape of the pore generated in the process of calculating the geometric relationship Error information obtained by correcting the tolerance information on the design through the calculated error information, etc.), identification information of the sensor unit 505 for identifying the sensor unit 505 which senses the pore hole, Sensing method identification information for identifying the sensing method, user identification information, device identification information, and the like).

According to the method of the present invention, when the pore data is stored in the designated storage area, the pore data generator 550 generates a plurality of pore data including a geometric relation of a plurality of reference points, The controller 560 may generate a pore template including the generated plurality of pore data and store the template in a designated storage area.

On the other hand, in the case of authenticating the generated pore data, the pore hole authentication unit 565 confirms the pore template stored in the storage area designated through the pore storage unit 560, and generates the pore data The geometric relationship of the created pore data is compared with the geometric relationship of the identified pore template so that the geometric relationship is matched within an allowable error range Authentication.

According to the technique of the present invention, the geometric relationship authentication of the pore is an analog type stochastic authentication. The geometric relationship of the pore formed in the body part of the user is always constant, but the geometrical relationship (for example, the distance relation and / or the angle relation calculated through the pore data generation unit 550) obtained by sensing it is not always constant, An error necessarily exists. In consideration of such an error, the porthole authentication unit 565 identifies the geometrical relationship of the pore data on a predetermined probability distribution (for example, a Gaussian probability distribution) as shown in FIG. 6 within the geometric relationship of the pore template and the allowable error range It is preferable to authenticate whether or not it is matched.

In addition, according to the technique of the present invention, the position, direction, area, contact pressure, etc. of the body part contacting the sensor part 505 each time the user touches his / her body part to the sensor part 505 is not constant. No matter how constantly the user tries to contact, it can not. The pore-hole authentication unit 565 performs coordinate rotation on the basis of the reference point of the geometric relationship of the generated pore data with the geometric relationship of the pore hole template in consideration of the error, It can be verified that it matches within the allowed tolerance range compared to the geometric relationship. Meanwhile, according to another embodiment of the present invention, the pore-hole authentication unit 565 may perform coordinate matching by matching the geometric relationship of the pore template with the geometric relationship of the generated pore data so as to perform matching authentication.

According to the technique of the present invention, when a user touches and senses the same body part with the sensor part 505, any pores may be formed according to the geometrical structure of the pore formed in the body part of the user (e.g., circular, oval, (For example, the pores of the circular structure are well recognized and any other pores (for example, pear-shaped pores in the fusiform structure may not be recognized well.) The porthole authentication unit 565 recognizes the U- U &lt; / = 3) geometric relations among u (3? U? U) geometric relations are matched within a u geometric relationship and a tolerance range included in the generated pore data, and u geometric relations The geometric relationship can be treated as authenticated.

The authentication result processing unit 570 may generate the final authentication result including the punched hole authentication result authenticated through the pore hole authentication unit 565 and may process the body part of the user as a result of the biometric authentication. Alternatively, the authentication result processing unit 570 may combine the predetermined authentication result including the punched hole authentication result authenticated through the pore hole authentication unit 565 and the fingerprint matching result generated through the fingerprint matching unit 525, A final authentication result for the body part of the user sensed through the authentication unit 505 may be generated and the body part of the user may be processed as a result of the biometric authentication. According to the method of the present invention, the ridge area (or ridge pattern) of the fingerprint is used as identification means (e.g., ID) for identifying the user, and the pore data is authenticated by an authentication means ). &Lt; / RTI &gt; Alternatively, the fingerprint matching result may be used as identification means for identifying the user, and the authentication result of the pore hole authentication may be used as authentication means for authenticating that the user is an actual user.

According to the method of the present invention, when the final authentication result is generated by combining the pore authentication result and the fingerprint matching result, the authentication result processing unit 570 determines that the ridge pattern of the fingerprint matches through the fingerprint matching unit 525 It is possible to generate the final authentication result in which the body part of the user sensed through the sensor unit 505 is successfully authenticated when the authentication unit 565 succeeds and the geometric relationship is matched within the tolerance range specified by the porthole authentication unit 565, Otherwise, the final authentication result corresponding to the authentication failure can be generated. The authentication result processing unit 570 may output the generated final authentication result through the designated means or provide the designated final authentication result through the designated path.

6 illustrates an example of a geometric relationship according to an embodiment of the present invention.

6 illustrates a probability distribution of the distance relation between pores, and it is understood that those skilled in the art will be able to refer to and / or modify FIG. 6 to determine the geometric relationship While various embodiments may be deduced, the present invention includes all of the above-described embodiments.

6, the actual distance between the pore a and the pore b is D when the pore a and the pore b are formed on the body part of the user as shown in Fig. However, the distance between the recognized pore (a) and the pore (b) sensed through the sensor unit 505 may not coincide with D. Accordingly, the present invention applies a tolerance σ to authenticate that the sensed through the sensor unit 505 is matched within an allowable error range, if the distance between recognized pore a and pore b is D1 to D2.

7 is a view illustrating a process of recognizing and authenticating pore holes according to an embodiment of the present invention.

7 shows a process of recognizing and authenticating a pore hole in conjunction with a fingerprint recognition and authentication process of sensing data obtained using a sensor unit 505 capable of sensing a fingerprint. It is possible to refer to and / or modify the FIG. 7 to infer various implementations of the pore recognition and authentication process (e.g., omitting some steps or changing the sequence) However, the present invention includes all of the above-mentioned embodiments, and the technical features of the present invention are not limited only by the method shown in FIG.

Referring to FIG. 7, an apparatus 500 for recognizing a pore according to the present invention acquires sensing data obtained by sensing a specific body part of a user through a sensor of a sensor unit 505 (700). When the sensing data is obtained, the device 500 processes and reads the sensed data according to a specified fingerprint recognition algorithm to extract minutiae points of the ridge pattern (705). If the user's fingerprint is registered, the device 500 generates a fingerprint template corresponding to the extracted feature point and stores the generated fingerprint template in the designated storage area (710). On the other hand, if the fingerprint of the user is to be authenticated, the device 500 compares the extracted fingerprint template stored in the designated storage area with the extracted minutiae to check whether the fingerprint is matched (715), and generates a fingerprint matching result corresponding to the result do.

The pore recognition and authentication process of the present invention may be performed sequentially with the fingerprint recognition and authentication process according to a specified sequence or may be performed by multiplexing with the fingerprint recognition and authentication process. When the sensed data is obtained, the device 500 reads the sensing value of the sensed data to generate recognition data that can discriminate ridges and valleys and does not compromise the pore sensing value (step 725).

The apparatus 500 may include at least one or more than one of the first to third outlier region identification examples of the present invention, S sensing values (730), recognizing at least s sensed value singularity regions of the S sensed value singularity regions as s pore holes, and identifying the positions of the corresponding s pore holes (735).

The apparatus 500 identifies one or more minutiae points present on a ridge pattern matching the ridge area included in the recognition data and identifies one or more minutiae points identified according to the first through fourth reference point embodiments of the present invention (740), and a geometric relationship with at least t (3? T? S) pore positions is calculated (745) based on the determined reference point using any one of the s pore positions as a reference point.

If the geometric relationship is calculated, the apparatus 500 generates pore data including the calculated geometric relationship (750).

If the pores are to be registered, the apparatus 500 generates a pore template including the created pore data and stores the pore template in a designated storage area (750).

On the other hand, if the pores are authenticated, the device 500 compares the geometric relationship of the generated pore data with the geometric relationship of the pore template pre-stored in the designated storage area through the pore template stored in the designated storage area, RTI ID = 0.0 &gt; (760). &Lt; / RTI &gt; According to an embodiment of the present invention, the apparatus 500 can coordinate the geometric relationship of the generated pore data with the geometric relationship of the pore template to match the pore data within the tolerance range (760) . The apparatus 500 generates the pore hole authentication result in which the pore data is authenticated using the pore template (765).

The apparatus 500 may generate the final authentication result (770) by combining the fingerprint matching result and the pore authentication result, or may generate the final authentication result including the pore authentication result. The device 500 outputs the generated final authentication result or provides it to the designated path (775).

500: Apparatus 505: Sensor unit
510: sensing processing unit 515: fingerprint recognition unit
520: fingerprint storage unit 525: fingerprint registration unit
530: recognition data generation unit 535:
540: pore recognition part 545: reference point determination part
550: pore data generator 555: minutia point checker
560: pore storage part 565: pore authentication part
570: Authentication result processing unit

Claims (21)

A method for performing a method through an apparatus having a sensor unit capable of sensing a fingerprint,
A first step of generating recognition data capable of discriminating a ridge and a valley of a fingerprint by reading a sensed value of the sensed data when sensing data obtained by sensing a user's body part is obtained through the sensor unit;
A second step of identifying at least one feature point extracted on the fingerprint ridge pattern structure using the recognition data and identifying at least s (s? 3) pore locations distributed on the fingerprint ridge area;
A third step of determining one of the s pore locations as a reference point using the identified one or more feature points;
A fourth step of generating pore data including a geometric relationship with at least t (3? T? S) pore positions based on the determined reference point; And
A pore template including the created pore data is generated and stored in a designated storage area or a geometric relationship of the generated pore data is compared with a geometric relationship of pore templates stored in a designated storage area to determine whether the pore template is matched within a tolerance range The method comprising the steps of:
The apparatus according to claim 1,
Wherein the pores are formed with a resolution of 50 μm or less.
The apparatus according to claim 1,
And an electrostatic sensor for sensing the electrostatic capacitance.
The method as claimed in claim 1,
Delta, Merge, Loop, Bridge, Cross, Triangle, Break, Spur, etc. on the ridge pattern, and the start point, the end point, the bifurcation point, the center point, the delta, , A ladder, a double break, a break & merge, and an island. &Lt; RTI ID = 0.0 &gt; 11. &lt; / RTI &gt;
2. The method according to claim 1,
Determining a base sensing value for a ridge area included in the recognition data;
Identifying S (S? 3) sensing value singularity regions distributed on the ridge region using the basis sensing value; And
Recognizing at least s (3? S? S) sensing value singularity regions of the identified S sensed value singularity regions as pore holes formed in the body region sensed by the sensor section to identify s pore positions Wherein the pore pattern authentication method comprises the steps of:
The method according to claim 1,
The first step includes generating N pieces of recognition data in which a body part of a user is sensed N (N? 2) times in a specified ms (millisecond)
The second step comprises:
(N + 1) -th recognition data among the n < th &gt; recognition data and the (n + 1) Generating (N-1) pieces of difference recognition data including n-th difference recognition data obtained by subtracting the (n-1)
Identifying S (S? 3) sensing value singularity regions distributed on the ridge region of the generated (N-1) difference recognition data; And
Recognizing at least s (3? S? S) sensing value singularity regions of the identified S sensed value singularity regions as pore holes formed in the body region sensed by the sensor section to identify s pore positions Wherein the pore pattern authentication method comprises the steps of:
The method according to claim 1,
The first step includes generating N pieces of recognition data in which a body part of a user is sensed N (N? 2) times in a specified ms (millisecond)
The second step comprises:
(N + 1) (1? N <N) recognition data obtained by subtracting the sensed value of the first recognition data from the sensed value of the (n + 1) Generating (N-1) cumulative difference recognition data that includes (N-1)
Identifying S (S? 3) sensing value singularity regions distributed on the ridge region of the generated (N-1) cumulative difference recognition data; And
Recognizing at least s (3? S? S) sensing value singularity regions of the identified S sensed value singularity regions as pore holes formed in the body region sensed by the sensor section to identify s pore positions Wherein the pore pattern authentication method comprises the steps of:
The method as claimed in claim 5, 6, or 7,
And a region having a diameter of 200um or less.
The method as claimed in claim 5, 6, or 7,
Wherein the pores are identified at intervals of 200 to 1500 um.
2. The method according to claim 1,
And determining the position of one of the s pore locations as a reference point based on the characteristic point types present on the ridge pattern.
2. The method according to claim 1,
And determining the position of one of the s pore locations as a reference point based on the arrangement of the ridge pattern structure and one or more feature points existing on the ridge pattern.
2. The method according to claim 1,
And determining a position of one of the s pore locations as a reference point based on a layout relationship between two or more feature points existing on the ridge pattern.
13. The method according to claim 12,
A distance relation between minutiae points, an angle relation between minutiae points, and a minutiae point relationship.
2. The method according to claim 1,
And a position of the pore hole distributed near the feature point position determined by the reference point.
2. The method of claim 1,
A distance relation between the reference point and the pore position,
An angular relationship between the reference point and the pore position,
A distance relation between the pore position and the pore position,
And an angle relationship between a pore position and a pore position of the pore hole.
16. The method of claim 1 or 15,
Wherein at least U (U? 3) number of effective distance relationships or angular relationships are included.
2. The method of claim 1,
Further comprising at least one of coordinate information of the geometric relationship, reference point identification information identifying a reference point of the geometric relationship, minutia information on a ridge pattern included in or near the geometric relationship, and error information of the geometric relationship Wherein the pore pattern authentication method comprises:
The method as claimed in claim 1,
When storing the pore data,
And generating pore data including at least U (U? 3) geometric relationships corresponding to a union of the calculated effective geometric relationships by repeatedly sensing the same body part of the user over a predetermined number of times The method comprising:
The method according to claim 1,
When storing the pore data,
The fourth step includes generating a plurality of pore data including a plurality of reference point-specific geometric relationships,
Wherein the fifth step includes generating a pore template containing the generated plurality of pore data and storing the template in a designated storage area.
The method as claimed in claim 1,
In the case of authenticating the pore data,
Rotating the generated geometric relationship of the pore data based on the reference point to coordinate with the geometric relationship of the pore template; And
And comparing the coordinate rotated geometric relationship with a geometric relationship of the pore template to verify that the geometric relationship is matched within a tolerance range.
The method as claimed in claim 1,
In the case of authenticating the pore data,
Authenticating whether at least u (3? U? U) geometric relations among the U (U? 3) geometric relations included in the pore template match within the geometric relationship of the generated pore data and the tolerance range; The method of claim 1,

Images