KR101774151B1 - Method and apparatus of enhancing iris recognition security using distributed iris template storage and matching - Google Patents

Abstract

The present invention relates to a method and an apparatus of enhancing iris recognition security using distributed iris template storage and matching. More particularly, the present invention relates to a method and an apparatus of enhancing iris recognition security using distributed iris template storage and matching. The method includes a step of generating an iris template from an iris image obtained by iris recognition, a step of dividing the generated iris template into n element templates, a step of dividing and storing or registering the divided n element templates in a predetermined element template database (DB), and a step of measuring a distance between the stored pre-registered element template and an element template for authentication to authenticate the iris template through one-to-one comparison, or measuring a distance between an element template for identification and a plurality of pre-registered element templates to identify the iris template through one-to-many comparison.

Description

FIELD OF THE INVENTION [0001] The present invention relates to a method and apparatus for enhancing iris recognition security using iris template distributed storage and matching,

The present invention relates to a method and apparatus for enhancing iris recognition security using iris template distributed storage and matching. More particularly, the present invention relates to a method of generating an iris template from an iris image obtained through iris recognition, dividing the generated iris template into n element templates, dividing n element templates into a predetermined element template database (DB) (1: 1 comparison) of the iris template or measuring the distance between a plurality of registered element templates and the identification element template stored therein by measuring the distance between the stored registration element template and the authentication element template And a method for identifying iris templates (one-to-many comparison), and a method and apparatus for enhancing iris recognition security using iris template distributed storage and matching.

In addition to security devices such as CCTV, access devices such as door locks, cameras, video and camcorders, as well as various mobile devices such as smart phones, tablets, PDAs, PCs and laptops, : Internet of Things) Demand and application for biometrics are increasing rapidly in various services such as mobile payment and smart key.

In addition, recently, researches for applying to the real world are being applied rapidly as applied as one of important information protection techniques in non-face-to-face transactions through Internet banking, financial services, and the Internet.

In order to perform such biometrics, it is necessary to acquire biometric data such as a part of a body such as a fingerprint and a face, a sign of a body, a gait, and so on. In recent years, Iris recognition using iris information has been applied rapidly in various smart phones and financial settlement systems in recent years.

Iris recognition has higher accuracy than other recognition, and iris has 266 identification features compared to 40 most commonly used fingerprint identification features. Moreover, it is known that there are many people who do not identify fingerprints in the business of issuing e-resident cards, etc. in India, and Daugman's patents that are widely used in iris recognition have expired, providing a technological environment that can be widely used around the world to be.

However, since the iris information can not be changed unlike the password or the PIN, if the iris information stored for user authentication is stolen by another person, it can cause a serious problem. Specifically, when the biometrics information is lost or stolen by another person, it has a fatal disadvantage that it is difficult to change easily if the user wants it, such as a password or an ID.

In this paper, we propose a novel biometric template based on a biometric template extracted from an original image such as a fingerprint image (Arun Ross, Jidnya Shah, Anil K. Jain, "From template to image: Reconstructing fingerprints from minutiae points" , IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 29, No. 4, 2007).

Therefore, protection studies on biometric templates including iris templates have begun to be actively studied, and various methods have begun to be applied.

First, a watermarking technique is applied to a biometric template, or a feature transformation or biometric cryptosystem based method is used. Also, in Biometric Cryptosystem, there is a method (Key Generation) for generating an encryption key directly from biometric information, a key for storing an encryption key in combination with biometric information, and then extracting it again using biometric information if necessary Binding method is known to be used.

  Another method is to use a convertible biometric template or a cancellable biometric template technique that issues a new template by applying a new transformation to the original biometric information even if the biometric template is leaked. (Jain, Anil K., Karthik Nandakumar, and Abhishek Nagar. "Biometric template security." EURASIP Journal on Advances in Signal Processing 2008).

Despite these various methods, iris templates may leak out during the process of storing, registering, and authenticating iris templates. Therefore, in order to apply iris recognition to financial transactions, KFTC recently separated the iris template into two places, and after storing the iris template, It is also known that the system is considering.

However, according to the data released in the April 2015 math meeting, it is reported that even if the iris templates are leaked out of the whole iris template, the risk of iris authentication may be high.

Therefore, considering the case where the original iris template itself is exposed, there is a need for a security-enhanced safe operation method in which the iris template is separated and stored, and then the accurate iris authentication is performed without rearranging the separated iris templates.

In the prior art related to the present invention, Korean Patent Publication No. 10-1275590 provides a false-type error correction code-based fuzzy-bolt method for protecting a biometric information template. The fingerprint template is divided into an iris template It is not related to the invention.

Another prior art related to the present invention is disclosed in US 2008/024696 A1, which provides a method for sequentially extracting feature elements from an iris template for personal authentication. The method includes dividing an iris template to enhance biometric authentication security It is not related to the invention. It also relates to a method for protecting an iris template based on an obfuscating data point, which is related to the present invention for enhancing iris recognition security by dividing an iris template none.

A problem to be solved by the present invention is to divide an iris template into a plurality of fragments in order to prevent an iris template from flowing out in the course of performing iris recognition, to store the separated iris templates in different physical locations, The present invention also provides a security enhanced method and apparatus for enhancing security of iris recognition in which fragments are not combined into a single template even in the case of identification, and are authenticated or identified in separate states.

Another object of the present invention is to provide a method and an apparatus for enhancing security of iris recognition in which even if some iris templates are leaked, the iris recognition is not performed due to the iris template.

SUMMARY OF THE INVENTION [0008] Generating an iris template from an iris image acquired through iris recognition, dividing the generated iris template into n element templates, separating the n element-divided element templates into the previously promised element template database (DB) Storing and / or registering iris templates; and a step of authenticating iris templates (one-to-one comparison) by measuring distances between separately registered element template templates and authentication element templates. .

According to another aspect of the present invention, there is provided a method for processing an iris image, comprising the steps of: generating an iris template from an iris image acquired through iris recognition; dividing the generated iris template into n element templates; And storing the separated element template database in a database (DB), and identifying (one to many) iris templates by measuring a distance between a plurality of previously registered element template templates and an identification element template And to provide a method for enhancing iris recognition using iris template distributed storage and matching.

A further object of the present invention is to provide a method for enhancing iris recognition security using iris template distributed storage and matching including existing authentication and intruder prevention enforcement authentication when calculating a hamming distance between two separated iris templates .

According to another aspect of the present invention, there is provided an image processing apparatus including means for generating an iris template from an iris image obtained through iris recognition, means for dividing the generated iris template into n element templates, And means for comparing and authenticating the iris template one-to-one by measuring the distance between the previously registered element template template and the element template for authentication separately and means for separately storing and registering in the element template database And to provide an iris recognition security enhancement device using template distributed storage and matching.

According to another aspect of the present invention, there is provided an image processing apparatus including means for generating an iris template from an iris image obtained through iris recognition, means for dividing the generated iris template into n element templates, And an element template database (DB) assigned to the iris template database (DB), and means for comparing and identifying a plurality of iris templates by measuring a distance between a plurality of previously registered element template templates and an identification element template stored separately And an iris recognition security enhancing device using iris template distributed storage and matching.

The method includes the steps of generating an iris template from an iris image acquired through iris recognition, dividing the generated iris template into n element templates, dividing n element templates into a predetermined element template database (DB) And a step of authenticating the iris template (one-to-one comparison) by measuring the distance between the separated registered element template and the element template for authentication, thereby separating the iris template, There is an advantageous effect that security-enhanced authentication for performing iris recognition while preventing the iris template from leaking without rearranging the templates is advantageous.

Another effect of the present invention is to create an iris template from an iris image obtained through iris recognition, to divide the generated iris template into n element templates, to divide n element templates into element templates A step of separately storing or registering the iris templates in a database (DB), and a step of identifying iris templates (one-to-many comparison) by measuring distances between a plurality of separately registered element templates and identification element templates, There is an advantageous effect that it is possible to perform security-enhanced identification for performing iris recognition while preventing the iris template from flowing out without rearranging the separated iris templates.

Another effect of the present invention is that when calculating the hamming distance between the two separated iris templates, the basic authentication and intruder prevention enforcement authentication are provided so that even if some iris templates are leaked, iris recognition is performed due to the iris template There is an advantageous effect.

Another effect of the present invention is to provide an image processing apparatus, comprising: means for generating an iris template from an iris image obtained through iris recognition; means for dividing the generated iris template into n element templates; Means for separately storing or registering the iris templates in an element template database (DB), and means for comparing and authenticating the iris templates one-to-one by measuring distances between the separately registered previously registered element template and the element template for authentication. And an iris recognition security enhancing device using matching is provided to separate iris templates and to perform iris recognition with iris recognition while preventing iris templates from being leaked without rearranging the separated iris templates There is an advantageous effect.

Another effect of the present invention is to provide an image processing apparatus, comprising: means for generating an iris template from an iris image obtained through iris recognition; means for dividing the generated iris template into n element templates; Means for separately storing and registering in an element template database (DB), and means for comparing and identifying a plurality of iris templates by measuring distances between a plurality of previously registered element template templates and an identification element template stored separately The present invention provides a security enhancing device for iris recognition using iris template distributed storage and matching to separate an iris template and to prevent iris template from leaking without rearranging separated iris templates, There is an advantageous effect.

FIG. 1 illustrates an example of a concept of an iris recognition process using a divided iris template according to an embodiment of the present invention. Referring to FIG.
FIG. 2 illustrates an exemplary process for generating an iris template from an iris image according to an exemplary embodiment of the present invention. Referring to FIG.
FIG. 3 illustrates an example of an iris template generated from data that can be processed by a computer according to an embodiment of the present invention.
FIG. 4 is a flowchart illustrating a method for performing security-enhanced iris authentication by dividing an iris template according to an embodiment of the present invention into element templates.
5 is a flowchart illustrating a method of dividing an iris template into element templates according to an embodiment of the present invention.
6 is a diagram illustrating an example of a method for collecting pixel attribute values, masking information, pixel position information, and rotation information of an iris template constituting an iris template of a pixel size according to an embodiment of the present invention. to be.
FIG. 7 is an illustration for explaining a method of separating into element templates by position selection according to an embodiment of the present invention.
FIG. 8 is an illustration for explaining a method of separating element templates into attribute templates according to an embodiment of the present invention.
9 is a flowchart illustrating a method of storing and registering an iris template according to an embodiment of the present invention as an element template.
FIG. 10 is an illustration for explaining a method of storing an element template according to an embodiment of the present invention.
FIG. 11 is a flowchart illustrating a method of authenticating (one-to-one comparison) an iris template using an element template according to an embodiment of the present invention.
12 is an exemplary illustration for explaining an iris template authentication method using an element template according to an embodiment of the present invention.
13 illustrates the types of element templates generated in consideration of iris template rotation information according to an embodiment of the present invention.
FIG. 14 is an illustration for explaining a method of obtaining a matching distance in consideration of rotation according to an embodiment of the present invention.
FIG. 15 is an illustration for explaining a method of comparing rotated Iris templates according to an embodiment of the present invention.
16 is an illustration for explaining a method of authenticating an iris template by basic authentication when a masking part exists according to an embodiment of the present invention.
FIG. 17 is an illustration for explaining a method of authenticating an iris template with an intruder-prevention-enhanced authentication when a masking part exists according to an embodiment of the present invention.

Hereinafter, the present invention will be described in detail.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Reference will now be made in detail to the preferred embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the like elements throughout. The idea and its core composition and function are not limited.

Accordingly, those skilled in the art will appreciate that various modifications and variations can be made in the present invention without departing from the spirit and scope of the present invention. Various modifications and variations are possible in light of the above teachings, and the technical constructions to which such modifications and variations are applied are also within the scope of the present invention.

In describing the constituent elements of the present invention, the terms A, B, (a), (b) and the like can be used. These terms are intended to distinguish the constituent elements from other constituent elements, and the terms do not limit the nature, order or order of the constituent elements. When a component is described as being "connected", "comprising", or "configured" to another component, the component may be directly connected or connected to the other component, It is to be understood that the element may be "connected "," comprising "

Further, in the present invention, different reference numerals are assigned to the same components even in different drawings for easy understanding.

In the present invention, iris recognition is first performed by acquiring an iris image, extracting the iris feature from the acquired iris image, and registering, storing, or encoding the iris feature (hereinafter, referred to as an 'iris template').

In the present invention, Daugman's method most widely used in iris recognition is exemplified. Daugman's method is used for most iris recognition, and since the patent has expired and is used worldwide, it is best suited as an example of explanation.

Therefore, it should be understood that even if the iris recognition security enhancing method and apparatus using the iris template distributed storage and matching is used in Daugman's way, it can be applied to other iris recognition sufficiently.

[Example]

Hereinafter, the present invention will be described in detail.

In the present invention, Verification is used in the case of 1: 1 matching and Identification or Searching is used in the case of 1: N matching.

FIG. 1 illustrates an example of a concept of an iris recognition process using a divided iris template according to an embodiment of the present invention. Referring to FIG.

As shown in FIG. 1, an iris template is first generated from an iris image. At this time, the iris template is mainly generated as data that can be processed by a computer. (Hereinafter, referred to as an " element template ") that divides the generated iris template into n (hereinafter, n represents a natural number of 2 or more) Database (DB) '). The element template (hereinafter, referred to as 'authentication element template'), which is separated from the iris template (hereinafter, referred to as 'authentication iris template') generated for authentication, is an element template (Hereinafter referred to as "pre-registered element template"). That is, the divided elemental authentication template and the previously registered elemental template are compared. In the authentication and identification process, each elemental template is not merged into one iris template before division again.

FIG. 2 illustrates an exemplary process for generating an iris template from an iris image according to an exemplary embodiment of the present invention. Referring to FIG.

As shown in FIG. 2, first, a human's eye is photographed using infrared rays, and the pupil and iris boundaries are detected in the photographed image, thereby separating regions corresponding to the iris. Extract the separated centrifugal area into a rectangular image and extract the iris template from the image of the rectangle. The Daugman method generates an iris template consisting of a real part and an imaginary part.

FIG. 3 illustrates an example of an iris template generated from data that can be processed by a computer according to an embodiment of the present invention.

In most extraction processes, the iris template is generated as data that can be processed by a computer. As shown in FIG. 3, the encoded template is also called a so-called code and has a value of 0 and 1. Generally, the size of the iris template is used according to the type of iris information recommended by a company or an institution (hereinafter, an iris template is coded as a computer-executable one unless otherwise mentioned).

In the case of the iris template, a template having a pixel size of 4 * 64, 4 * 128, 4 * 256, 8 * 64, 8 * 128 and 8 * 256 is mainly used.

FIG. 4 is a flowchart illustrating a method for performing security-enhanced iris authentication by dividing an iris template according to an embodiment of the present invention into element templates.

As shown in FIG. 4, first, an iris template is generated from iris information obtained through the iris recognition apparatus (S401). The generated iris template is divided into n element templates (S402). The element templates divided into n are separately stored and registered in an element template database (DB) that is reserved to be stored in advance (S403).

If authentication or identification is performed, step (S404) of comparing the one-to-one (1: 1) comparison and authentication of the iris template by measuring the distance between the previously registered element template and the element template for authentication in the registration step (S403) (Hereinafter referred to as " identification element template ") separated from an iris template (hereinafter, referred to as 'identification iris template') for identification with a plurality of stored previously registered element templates, (Step S405) of comparing and identifying one to many (1: N).

Further, the step (S406) of encrypting the pre-registered element template, the authentication element template, and the identification element template using a watermarking technique, biohashing, robust hashing, can do.

 4, steps S401 to S406 are sequentially performed. However, this is merely an exemplary description of the technical idea of an embodiment of the present invention, and it is to be understood that the technical knowledge in the technical field to which the embodiment of the present invention belongs It will be understood by those skilled in the art that various modifications and variations can be made by changing the order described in FIG. 4 or by executing one or more of steps S401 through S406 in parallel without departing from the essential characteristics of an embodiment of the present invention , And FIG. 4 is not limited to the time-series order.

5 is a flowchart illustrating a method of dividing an iris template into element templates according to an embodiment of the present invention.

5, in order to generate n element templates, first, pixel attribute values and masking information constituting the iris template, position information (hereinafter, referred to as 'pixel position information') in the iris template of the selected pixel, (S501) of collecting the rotation information of the template and the like. Based on the collected pixel property values, masking information, pixel position information, and rotation information of the iris template, the iris template is divided into n element templates (S502), and transmitting the separated n element templates (S503).

In addition, additional information (storage time, conversion time, log information, etc.) generated in the process of collecting and separating the pixel property values, the masking information, the pixel position information and the rotation information of the iris template, (Step S504) may be additionally provided.

5, it is described that steps S501 to S504 are sequentially executed. However, this is merely an exemplary description of the technical idea of the embodiment of the present invention, and it is to be understood that the technical knowledge in the technical field to which the embodiment of the present invention belongs It will be understood by those skilled in the art that various modifications and variations may be possible in practicing the invention without departing from the essential characteristics of one embodiment of the present invention or by executing one or more of the steps S501 through S504 in parallel, , And FIG. 5 is not limited to the time-series order.

Hereinafter, a method of collecting pixel attribute values, masking information, pixel position information, and rotation information of an iris template in order to generate n element templates from the iris template will be described in detail.

When the iris template is generated by the Daugman method, each pixel constituting the iris template has a value of 0 or 1. And has masking information for representing pixels which are hard to recognize due to occlusion or light reflection of the iris region. In general, if the masking information is 1, the attribute value of the corresponding pixel is used. If the masking information is 0, the masking information is not used. Generally, a matrix representing an attribute value of pixels constituting the iris template and a matrix representing masking information are stored and stored.

 6 is a diagram illustrating an example of a method for collecting pixel attribute values, masking information, pixel position information, and rotation information of an iris template constituting an iris template of a pixel size according to an embodiment of the present invention. to be.

As shown in FIG. 6, each pixel attribute value, masking information, pixel position information, rotation information of the iris template, and the like constituting the exemplary 3 * 8 pixel size iris template are collected.

Therefore, the collected information is represented by a matrix, an ordered pair or a vector such as [pixel property value, masking information, pixel position information, and iris template rotation information], and is mainly stored in a header file format.

Specifically, if a pixel at the second position in the horizontal direction and the position at the third position in the vertical direction are selected, the pixel attribute value, the masking information (1,1), and the pixel position information (2, 3) are collected. If a pixel at the third position in the horizontal direction and the position at the fourth position in the vertical direction are selected, the pixel attribute value, the masking information (1,0), and the pixel position information (3,4) can be collected. The iris template rotation information to be described later stores information for shifting a bit of a certain size in the iris template in proportion to the rotation angle of the iris image. In FIG. 6, since the iris template without rotation is assumed and exemplified, 0-bit iris template rotation information is obtained.

Therefore, each pixel is represented as a matrix, a pair of sets, or a vector with information as [(1,1), (2,3), 0], [(1,0), (3,4)

Next, the method of separating the iris template into n element templates based on the collected pixel attribute values, masking information, pixel position information, and iris template rotation information will be described in detail.

First, determine how many element templates the one iris template should be divided into. If it is decided to divide n (n is a natural number of 2 or more) element templates, select pixels to be included in each element template. In this case, location selection and attribute selection are used as the selection method. More specifically, the position selection is a method of randomly randomly selecting a position, collecting pixel attribute values and masking information of a selected position, and dividing the pixel attribute values and masking information into individual element templates. On the other hand, the attribute selection is performed by randomly selecting a position among the pixels having the attribute information of 1 (on the contrary, 0) and dividing the pixel into the element template first, and if all pixels having a value of 1 After that, the position is randomly selected among the pixels having the value of 0 (having the opposite 1), and is divided into the element template.

(A1) Location selection (location selection)

FIG. 7 is an illustration for explaining a method of separating into element templates by position selection according to an embodiment of the present invention.

As shown in FIG. 7, when an iris template of 3 * 8 pixel size is composed of 8 element templates, an element template is constructed in random order by selecting positions randomly among 24 pixels. The pixels constituting the first element template randomly select three pixels out of the total 24 pixels. The selected three pixel position information is (1,1), (2.4), and (1,8). The pixels constituting the second element template randomly select three pixels out of the total of 24 pixels out of the previously selected three pixels. The selected pixel position information is (1, 5), (3, 3), (3, 5). Repeat this way until the last element template is constructed. At this time, the number of pixels included in each element template does not necessarily have to be the same. For example, the number of pixels included in each element template may vary from 3, 3, 3, 2, 1, 3, 4, and 5, even if it is divided into 8 element templates.

(A2) Attribute selection

FIG. 8 is an illustration for explaining a method of separating element templates into attribute templates according to an embodiment of the present invention.

8, when an iris template having a size of 3 * 8 pixels is composed of 8 element templates, among the 24 pixels, firstly, randomly positioned among the pixels having masking information of 1 (conversely, having 0) After the element templates are constructed in the selected order, the elements are randomly selected from the pixels having masking information of 0 (inversely 1), and the element template is constructed in the selected order. First, among the total of 24 pixels, three pixels are randomly selected out of 20 pixels having masking information of 1. The selected three pixel position information is (1,1), (1.3), (1,5). The pixels constituting the second element template randomly select three pixels among the twenty pixels having the masking information 1, out of the three selected from the three pixels. If all 20 pixels with masking information of 1 are selected after repeating this way, the selection is made from four pixels with masking information of 0. Since there are four pixels with masking information 0, the last selected pixel and the eighth element template three pixels correspond to the 7th element template. The pixel position information selected by the 7th element template is (2,5), (3,3), (3,5), and the pixel position information selected by the 8th element template is (3,4), ), (3, 7). At this time, the number of pixels included in each element template does not necessarily have to be the same. For example, the number of pixels included in each element template may vary from 3, 3, 3, 2, 1, 3, 4, and 5, even if it is divided into 8 element templates.

When dividing into n element templates by position selection or attribute selection, the size of each element template does not necessarily have to be the same as described above. There is no problem in application if the pixel attribute value, masking information, pixel position information, and iris template rotation information of the iris template separately stored in the respective element templates can be stored without being damaged, and the capacity of the element template database (DB) The same element template can be duplicated and divided according to the number.

It should be understood, however, that the same application is possible even if the sizes of the respective element templates are different, although it is assumed that the sizes of the element templates are the same for convenience of explanation.

9 is a flowchart illustrating a method of storing and registering an iris template according to an embodiment of the present invention as an element template.

As shown in FIG. 9, first, pixel position information of pixels constituting an element template divided into n sections from an iris template and information (hereinafter referred to as 'element template division information') of iris templates before division are stored in an element template (S901) of confirming whether the element template database (DB) matches the element template division information preliminarily stored in association with the element template database (DB) (S902) of storing and registering the element template in the database DB. At this time, the step S903 of storing the element template division information transmitted to the element template database DB together with the element template database DB, or the element template division information transmitted to the element template database DB, DB) (S904) of storing only the element template.

9, it is described that steps S901 to S904 are sequentially executed. However, this is merely an example of the technical idea of an embodiment of the present invention, and it is to be understood that the technical knowledge in the technical field to which the embodiment of the present invention belongs It will be understood by those skilled in the art that various modifications and variations can be made by changing the order described in FIG. 9 and executing one or more of steps S901 to S904 in parallel without departing from the essential characteristics of an embodiment of the present invention , And FIG. 9 is not limited to the time-series order.

The following details how to store and register element templates.

As shown in FIG. 9, element templates divided into n sections from the iris template are stored in the element template database (DB) 1, 2, 3,. , and n, respectively. The element template database (DB) is predetermined in advance to store only the element template matching the element template division information.

The element template division information may constitute an element template database (DB) having a size corresponding to all pixels (for example, 8 * 256 = 2048), but in reality, considering elemental aspects of cost and technical efficiency, The method of segmentation is appropriate.

The element template division information is given with reference to the order and position in the division using position selection or attribute selection. In the present invention, for the sake of convenience of description, it is divided into position selection, and the divided element templates are arranged in order 1, 2, 3, ... , n. However, this is not a specific rule.

FIG. 10 is an illustration for explaining a method of storing an element template according to an embodiment of the present invention.

As shown in FIG. 10, when the element template is stored and registered in the element template database DB, the element template database DB receives the element template division information and confirms whether the element template division information matches the previously designated element template division information , And stores or registers the transferred element template only when they match. At this time, the element template division information is transmitted together with the element template to be stored, or the element template division information is used for simply determining whether or not the element template division information is stored, and may not be stored and registered in the element template database (DB). When the element template database (DB) does not store the element template division information, a gateway or the like can generally store the element template division information in the communication network.

 (B1) Method of storing element template division information together

As shown in Fig. 10 (a), the iris template is divided into four element templates, and then the element template division information is 1 , 2 , 3 , and 4 , respectively, according to the divided positions.

First, when element template division information 1 is sent to four element template databases DB 1 , DB 2 , DB 3 and DB 4 , each element template database DB stores element template division information . DB 2 , DB 3 , and DB 4 will not match and will reject, and DB 1 will send a signal that they will match. After receiving a transmission that the coincidence signal is sent to the storage element template with the template elements in the first division information DB 1. At this time, not only the transferred element template but also the element template division information 1 can be stored at the same time.

Such a method does not need to constitute a means for storing element template division information in particular, and has a merit in that the process of transmitting and storing can be simplified and the work can be performed quickly. However, if a specific element template database (DB) is infiltrated and related data is leaked, not only the element template but also the element template division information is known to the outside, so that the position of the pixel of the iris template before the division can be known, The possibility of being able to be increased.

(B2) Method of transmitting except element template division information

As shown in FIG. 12 (b), the iris template is divided into four element templates and has element template division information of 1 , 2 , 3 and 4 according to the divided positions.

First, the element template division information 1 is sent to DB 1 , DB 2 , DB 3 , and DB 4 , and each element template database (DB) is checked to see if it matches the element template division information to be stored in advance. Each element template database (DB) is checked to see if it matches element template division information to be stored in advance. DB 2 , DB 3 , and DB 4 will not match and will reject, and DB 1 will send a signal that they will match. After receiving a transmission that the coincidence signal is sent to the storage element template with the template elements in the first division information DB 1. When the element template with the after transmitting the that match the signal element template segmentation information 1 is transferred and stored in the DB 1, element template database (DB) stores only the transmission element template, element template division information 1 with Do not save.

In this method, when a specific element template database (DB) is infiltrated and related data is leaked, only the element template pixel attribute value and the masking information are known outside, and the position of the pixel of the outflow portion of the original iris template is known It can not be recovered easily.

However, since the means for storing the element template division information must be separately constructed and stored separately, the transmission and storage processes are complicated and the operation speed is relatively slow.

In recent years, since technologies related to communication means and storage means are rapidly developing, it is more secure from the viewpoint of security to use a method of separately storing element template division information for secure storage of iris templates.

FIG. 11 is a flowchart illustrating a method of authenticating (one-to-one comparison) an iris template using an element template according to an embodiment of the present invention.

11, the distance between the element template for authentication sent to the element template database (DB) having the same element template division information and the pre-registered element template previously registered in the element template database (DB) is calculated (S1102) calculating a value (hereinafter referred to as a 'matching distance') by calculating a distance calculated for each element template database (DB) to a function in the step (S1101) (S1103) when the matching distance is smaller than a predetermined threshold value (hereinafter, referred to as an 'authentication reference'), and a step (S1104) when the matching distance is larger than the authentication reference .

11, steps S1101 to S1104 are sequentially executed. However, this is merely illustrative of the technical idea of an embodiment of the present invention, and it is to be understood that the technical knowledge in the technical field to which the embodiment of the present invention belongs It will be understood by those skilled in the art that various modifications and variations can be made by practicing the same or similar modifications or changing the order described in FIG. 13 without departing from the essential characteristics of one embodiment of the present invention or by performing one or more of the steps S1101 through S1104 in parallel , And Fig. 11 is not limited to the time series order.

Next, the method of authentication of the iris template using the element template will be described in detail.

12 is an exemplary illustration for explaining an iris template authentication method using an element template according to an embodiment of the present invention.

As shown in Fig. 12, after dividing the authentication iris template into four authentication element templates, each authentication element template is stored in an element template database (DB) corresponding to each authentication element template division information . The four element template database (DB) stores the pre-registered element template divided from the pre-registered iris template (hereinafter, referred to as 'pre-registered iris template').

First, the distance between each authentication element template and the previously registered element template is calculated in the four element template database (DB) (mainly, the Hamming distance is used). The distance _{r 1, r 2, r 3} , f (r1, r2, r3, r4) of r ₄ a matching distance is substituted to calculate the function of calculating the final comparison result calculated in each element template database (DB) I ask. If the matching distance is smaller than a predetermined threshold (hereinafter referred to as an authentication reference), it is determined that the iris template is the same iris template.

More specifically, first, values (r ₁ , r ₂ , r ₃ , r ₄ ) calculated from the Hamming distance between the element template for authentication and the template element template in the four element template databases and the values The size (a ₁ , a ₂ , a ₃ , a ₄ ) is obtained. The matching distance of the iris template is calculated by dividing the sum of the calculated Hamming distances (r ₁ + r ₂ + r ₃ + r ₄ ) by the sum of the pixel sizes (a ₁ + a ₂ + a ₃ + a ₄ ).

13 illustrates the types of element templates generated in consideration of iris template rotation information according to an embodiment of the present invention.

As shown in Fig. 13, the element template separated from the authentication iris template may be configured by adding iris template rotation information to one or both of the iris template rotation information to compare with the previously registered element template. In the iris recognition, since the rotated iris image is often acquired due to the motion of the photographer, the photographer may mistakenly recognize the same irrespective of the same photographer without considering the rotation.

FIG. 14 is an illustration for explaining a method of obtaining a matching distance in consideration of rotation according to an embodiment of the present invention.

As shown in Fig. 14, the distance calculated in DB 1 is r _1k, the distance calculated in DB 2 is r _2k, the distance calculated in DB 3 is r _3k, and the distance calculated in DB 4 is r _4k do. Also, each authentication element template and pre-registration element template considers the rotation twice (θ _1, θ ₂ ), and calculates the hamming distance obtained by shifting the bits by the rotation angle size.

First, as the size of θ ₁ (R ₁₁ , r ₂₁ , r ₃₁ , r ₄₁ ) obtained by calculating hamming distances between the authentication element template and the previously registered element template in each of the four element template databases when the rotation is performed (k = 1) Find the pixel size (a ₁₁ , a ₂₁ , a ₃₁ , a ₄₁ ) used to calculate the Hamming distance. The sum of the calculated Hamming distance divided by _{(r 11 + r 21 + r} 31 + r 41) the sum of pixel size _{(a 11 + a 21 + a} 31 + a 41), when θ ₁ rotation gakil The matching distance of the iris template is calculated.

As a second θ ₂ sizes (R ₁₂ , r ₂₂ , r ₃₂ , r ₄₂ ) calculated from the Hamming distance between the authentication element template and the pre-registered element template in each of the four element template databases when the rotation is performed (k = 2) Obtain the pixel size (a ₁₂ , a ₂₂ , a ₃₂ , a ₄₂ ) used to calculate the Hamming distance. The sum of the calculated Hamming distance divided by _{(r 12 + r 22 + r} 32 + r 42) the sum of pixel size _{(a 12 + a 22 + a} 32 + a 42), when the θ ₂ revolution gakil The matching distance of the iris template is calculated.

If the minimum value is smaller than the authentication reference, the same iris template is used. If the minimum value is larger than the authentication reference, the iris template is determined to be different.

Assuming that the rotation is k times, the pixel size used to obtain the hamming distance and the hamming distance between the element template for authentication and the template element template in the i-th element template database can be arranged as the following array. Actually, each element stores its information in an array form in the template database (DB), and then calculates it.

Next, the iris template authentication method using the element template described above is widely used in the iris recognition world at present, and a de facto standard method (Daugman method) is used in detail.

FIG. 15 is an illustration for explaining a method of comparing rotated Iris templates according to an embodiment of the present invention.

When the iris image acquired for iris recognition is rotated and taken, as shown in FIG. 15, in order to compare the two iris templates, the rotated image should be rotated at a certain angle and moved to the reference position. At this time, the matrix of the iris template appears as a result of shifting by a bit of arbitrary size according to the rotation angle.

Specifically, assuming that two iris templates A and B are constructed as follows, and in particular, a rotated iris template is expressed by -1 bit or +1 bit shift, it can be expressed as follows.

I) iris template B _-1 : -1 bit shift

A iris template A: 1100111000111010

Iris template B _-1 : 1001101010100110

Ii) Iris template B ₊₁ : +1 bit shift

A iris template A: 1100111000111010

Iris template B ₊₁ : 1001101010100110

Therefore, the three hamming distances d _H (A, B), d _H (A, B _-1 ) and d _H (A, B ₊₁ ) considering the iris template rotation information are calculated and the minimum value is selected (See Equation (1)).

- (Formula 1)

If the minimum value 6/14 selected in the above equation (1) is smaller than the authentication standard, the same iris template is used.

Therefore, when storing or transmitting iris template as well as other iris templates, it will be easily understood that iris template rotation information is needed.

The following is a detailed description considering masking information.

As described above, the iris template has a mask matrix portion indicating occlusion of the iris region. It mainly occurs when the iris region is occluded when the eye is closed or momentarily blinked in acquiring the iris image, but it may occur even when light reflection occurs due to illumination. When such a case occurs, masking is performed to be considered in comparison.

However, due to this principle, when a part of the entire iris template is leaked to outside, a case where the imposter not the genuine user is judged as the actual owner may occur.

Specifically, when a portion corresponding to 1/4 of the iris template is leaked, authentication is requested by masking the remaining 3/4 portions other than the leaked portion (hereinafter, referred to as 'occlusion attack' ) Will be described below.

FIG. 16 is an illustration for explaining a method of authenticating an iris template using a basic authentication method (Daugman method) when a masking part exists according to an embodiment of the present invention.

In order to explain more specifically, the size of the iris template A and the iris template B is 100 bits, the value of the hamming distance between the two iris templates is calculated as d _H (A, B) = 0.36, (bit) / value (score)).

(C1) Basic authentication

As shown in Fig. 16, the Daugman method does not perform calculation on the masked part. In actual calculation, 25-bit Hamming distance corresponding to 1/4 of 100 bits which is not masked is obtained by multiplying bit 25 of comparable area by average hamming distance (0.36), and the value is 9 (= 25 * 0.36).

The total Hamming distance _dAugman (A, B) = 9/25 = 0.36 calculated using the above calculation is less than the reference 0.38 (bit / score) for authenticating the same iris template . Therefore, the authentication is accepted because it is the same iris template.

However, as described above, when an occlusion attack comes in, there is a disadvantage that it is highly possible to authenticate the same iris template even though the iris template is another iris template. Therefore, it can be seen that it needs to be supplemented.

 (C2) Enhanced intruder authentication

FIG. 17 is an illustration for explaining a method of authenticating an iris template with an intruder-prevention-enhanced authentication when a masking part exists according to an embodiment of the present invention.

The intruder prevention intensification authentication shown in Fig. 17 can prevent the problem of authenticating with the same iris template even when it is another iris template when an occlusion attack comes in. Specifically, the actual calculation process will be described as follows.

First, the Hamming distance of 25 bits corresponding to 1/4 of the 100 bits which are not masked is obtained by multiplying the bit 25 of the comparable area by the average hamming distance (0.36), and the value is 9 (= 25 * 0.36 ). However, the part corresponding to 3/4 of the masking of 100 bits is calculated by giving an arbitrary value (in the example, calculation is performed by simply putting a probability value of 0.5). That is, a value of 37.5 (= 75 * 0.5) is calculated.

Calculated using the calculated value of the above total Hamming distance d _New (A, B) = (9 + 37.5) / is (25 + 75) = 0.465, which is based on the authentication that the same iris template 0.38 (bit (bit) / Score < / RTI > Therefore, authentication is rejected because it is not the same iris template. Therefore, even when an occlusion attack occurs, it can be seen that the same iris template is not authenticated and no problem occurs.

Generally, the recognition rate is used as a representative index for evaluating whether iris recognition is possible. When the recognition rate is described, an error in iris recognition is determined when an iris of a person different from the iris of a registered user is erroneously determined as the iris of the same user (false acceptance rate, false acceptance rate, (False rejection rate, hereinafter referred to as 'FRR') when a user's iris, such as a registered user's iris, is mistakenly determined to be a third person, In the iris recognition, the lower the FAR and FRR values are, the higher the recognition rate is.

In the present study, which is the basis of the present invention, the presentation data of the Korean Mathematical Society (attached data) assumes that the attribute values of pixels of a certain size are leaked, and the new iris (Hereinafter referred to as an Intruder Acceptance Rate) of the intruder template (threshold value: 0.4) by creating a template (hereinafter referred to as an 'Intruder template').

According to the presentations of the Korean Mathematical Society, it can be seen that the IAR value calculated using the new method is much lower than the IAR value calculated using the Daugman method. Therefore, applying the new method and applying iris recognition will be more secure.

Next, we will discuss how to identify iris templates using element templates.

First, the distance between the authentication element template sent to the element template database (DB) in which the element template division information is identical to a plurality of pre-registered element templates registered in advance in the element template database (DB) is calculated.

(One-to-one correspondence) with a plurality of pre-registered element template k (pre-registered element template_l, pre-registered element template_2, ..., pre-registered element template_k) stored in the element template database (DB) Comparison). At this time, if the distance between the identifying element template and any previously registered element template_k is expressed as Dk, the respective distances are D1, D2, D3, ... , Dk, and the values will vary.

It is possible to calculate the distance between the identifying element template and the pre-registered element template, and align the pre-registered element template in descending order or ascending order by comparing the distance values. In this case, the matching distance may be determined in accordance with a predetermined threshold value (hereinafter, referred to as an 'identification criterion'), wherein a) a candidate registration element having a minimum distance among the values obtained by sorting all the pre- B) All previously registered element templates below the identification criterion can be selected. C) The pre-registered element templates below the identification criterion can be sorted and selected in the order of the minimum number in the minimum number.

For example, if the distance between the identifying element template and any previously registered element template_k is D3 <D1 <Dk <D2 <... ... D3, D1, Dk, and D2 satisfy the discrimination criterion. When the candidate group is determined by the method (A), D3 can be selected because D3 is satisfied. In addition, if the candidate group is determined by the method (B), all of D3, D1, Dk, and D2 are satisfied. In (C) method, D3, D1, and Dk can be selected because D3, D1, and Dk are satisfied if the candidate group is limited to at least three

While the present invention has been described in connection with what is presently considered to be the most practical and preferred embodiments, it is to be understood that the invention is not limited to the disclosed embodiments.

That is, within the scope of the present invention, all of the components may be selectively coupled to one or more of them. In addition, although all of the components may be implemented as one independent hardware, some or all of the components may be selectively combined to perform a part or all of the functions in one or a plurality of hardware. As shown in FIG.

The codes and code segments constituting the computer program may be easily deduced by those skilled in the art. Such a computer program can be stored in a computer-readable storage medium, readable and executed by a computer, thereby realizing an embodiment of the present invention. The storage medium of the computer program may include a computer including a magnetic recording medium, an optical recording medium, a carrier wave medium, a hard disk, a memory chip, or the like, or any recording medium readable by a processor.

The iris recognition security enhancement method using the iris template distributed storage and matching is described by the computer or server based on the iris template distributed storage and matching. We will discuss the iris recognition security enhancement device using distributed iris template storage and matching.

The technical structure described later can be included in the iris recognition security enhancing apparatus using iris template distributed storage and matching according to the present invention.

Means for generating an iris template from iris images obtained for iris recognition, and means for dividing the generated iris template into n element templates.

and means for separating and storing n element templates divided and stored in an element template database (DB) predetermined in advance. The distance between the previously registered element template and the element template for authentication is measured, and the iris template One-to-one comparison and authentication.

The apparatus for enhancing iris recognition using iris template distributed storage and matching further includes means for comparing a plurality of iris templates by a plurality of iris templates by measuring a distance between the plurality of previously registered element templates and the identification element template .

Means for encrypting an iris template or n element templates using a watermarking technique, biohashing, robust hashing means, and an encryption key or the like.

The means for dividing the iris template into n element templates includes means for collecting pixel attribute values, masking information, pixel position information, and iris template rotation information from the iris template to generate n element templates, And the like.

As a means for separating and collecting the pixel attribute value, the masking information, the pixel position information, and the iris template rotation information, position selection or attribute selection may be used.

The position selection may include randomly randomly selecting the position of the pixel, and collecting the pixel attribute value and the masking information of the selected position and dividing the pixel attribute value and the masking information into individual element templates.

In the attribute selection, the attribute information has a value of 1, or conversely, a position is randomly selected from among pixels having 0, and is firstly divided into element templates, and all pixels having a value of 1 or having a value of 0 are selected And a means for randomly selecting a position among the pixels having a value of 0 thereafter or inversely 1 and dividing the pixel template into element templates.

The means for separating and storing the element templates divided into n in the pre-designated element template database (DB) comprises means for dividing each element template division information transmitted by the n element templates divided from the iris template into the element template database (DB) Means for confirming whether or not the element template division information matches the previously stored element template division information; And

And means for storing and registering element templates in a predetermined element template database (DB) in which the element template division information is matched.

The means for storing and registering the element template in the designated element template database (DB) in which the element template division information is matched includes means for storing the element template division information transferred to the element template database (DB) together in the element template database Can be configured.

The means for storing and registering the element template in the designated element template database (DB) matching the element template division information does not store the element template division information transferred to the element template database (DB) in the element template database (DB) Element template only.

The means for measuring the distance between the stored pre-registered element template and the element template for authentication and comparing the iris templates on a one-to-one basis

Means for calculating a distance between an authentication element template sent to an element template database (DB) in which element template division information coincides with a pre-registered element template registered in advance in an element template database (DB) And calculating a matching distance calculated by substituting the calculated distance for each DB into a function.

And comparing the obtained matching distance with the authentication criterion to determine whether the same iris template is present or not.

The means for measuring the distance between a plurality of previously registered element templates and the identification element template to compare a plurality of iris templates in a one-to-many manner includes a discriminating element template and a plurality of pre-registered element templates And a means for obtaining a candidate group from the calculated matching distance by using the calculated distance.

And means for selecting the selected one or more pre-registered element templates as the same element template.

And means for calculating a hamming distance between element templates by the distance between the stored pre-registered element template and the element template for authentication.

And means for calculating a hamming distance between element templates with a distance between a plurality of previously registered element templates and an identifying element template.

The sum of the distances (r ₁ , r ₂ , r ₃ , ..., r _n ) of the element template for authentication and the registered element template calculated in the n element template database (DB) By a sum of the pixel sizes (a ₁ , a ₂ , a ₃ , ..., a _n ) used for the pixel value of the pixel.

And when the matching distance is two or more, the minimum value may be selected.

When the matching distance is calculated in consideration of the rotation of the element template, a hamming distance obtained by shifting the bits by the rotation angle size can be used.

And means for calculating a hamming distance between element templates without calculating the masked pixels of the element template for authentication.

The hamming distance between the element templates can be calculated by fixing the hamming distance of masked pixels in the element template for authentication to a specific value.

It is possible to calculate the hamming distance between the element templates without calculating the masked pixels among the identification element templates.

The hamming distance between the element templates can be calculated by fixing the hamming distance of the masked pixel in the identification element template to a specific value.

The specific value for fixing the hamming distance of the masked pixel may be 0.5.

When the identifying element template is an iris template, a specific value for fixing the hamming distance of the masked pixel may be 0.5.

A candidate registration element template having a minimum distance among the values obtained by sorting all the previously registered element templates that are equal to or lower than the identification criterion is selected as the candidate group from the calculated matching distance or all the previously registered element templates below the identification criterion are selected, And a means for sorting the following pre-registered element templates and selecting a minimum number in the order close to the minimum value.

The element template division information transmitted to the element template database DB can be stored in the gateway without being stored in the element template database DB.

The technical constructions applied to the method invention can be selectively applied to the apparatus invention.

The method includes the steps of generating an iris template from an iris image acquired through iris recognition, dividing the generated iris template into n element templates, dividing n element templates into a predetermined element template database (DB) (1: 1 comparison) of the iris template or a distance between a plurality of previously registered element templates and an identification element template by measuring the distance between the stored registered element template and the element template for authentication And a method for identifying iris templates (one-to-many comparison). The method and apparatus for enhancing iris recognition using iris template distributed storage and matching are provided to enhance security, and thus are highly likely to be used industrially.

Claims (27)

A method for enhancing iris recognition using iris template distributed storage and matching,
Generating an iris template from iris images acquired for iris recognition;
Dividing the generated iris template into n element templates;
dividing and storing n element templates divided into n into a predetermined element template database (DB); And
comparing the distance between each of the previously registered element template templates stored in the element template database (DB) and the authentication element template separated by n to compare the iris templates one by one and authenticating A method for enhancing iris recognition using iris template distributed storage and matching. A method for enhancing iris recognition using iris template distributed storage and matching,
Generating an iris template from iris images acquired for iris recognition;
Dividing the generated iris template into n element templates;
dividing and storing n element templates divided into n into a predetermined element template database (DB); And
and comparing and distinguishing a plurality of iris templates from each other by comparing the distance between each of the previously registered element template templates stored in the previously determined element template database and each of the n element authentication template elements separated by n, A method for enhancing iris recognition security using iris template distributed storage and matching. The method according to claim 1 or 2,
A step of applying a watermarking technique or an encryption method using bio-hashing and low-burst hashing, or an encryption key is added to the iris template or the n element template to enhance iris recognition security using iris template distributed storage and matching . The method according to claim 1 or 2,
The step of dividing the iris template into n element templates
collecting pixel attribute values, masking information, pixel position information, and iris template rotation information from an iris template to generate n element templates; And
And transmitting the separated n element templates. The method of enhancing iris recognition security using iris template distributed storage and matching. The method of claim 4,
The iris recognition security enhancing method using iris template distributed storage and matching is characterized by using position selection or attribute selection as a method of collecting and separating pixel attribute values, masking information, pixel position information, and iris template rotation information. The method of claim 5,
The location selection
The method comprising the steps of: randomly randomly selecting a position of a pixel, collecting pixel attribute values and masking information of the selected position, and dividing the pixel attribute value and masking information into individual element templates. The method of claim 5,
The attribute selection
If the attribute information has a value of 1, or conversely, a pixel having a value of 1 or a pixel having a value of 0 is selected all at random, Wherein the iris template is divided into an element template by randomly selecting a position among pixels having a value of 0 or 1 inversely. The method according to claim 1 or 2,
The step of separately storing and registering the element templates divided into n in the previously designated element template database (DB)
Confirming whether each element template division information transmitted by the n element templates divided from the iris template matches the element template division information preliminarily owned by the element template database DB; And
And storing and registering the element template in a predetermined element template database (DB) in which the element template division information is matched. The method of enhancing iris recognition security using iris template distributed storage and matching. The method of claim 8,
In the step of storing and registering the element template in the designated element template database (DB) in which the element template division information is matched,
And storing the element template division information transferred to the element template database (DB) together in the element template database (DB). The method of claim 8,
In the step of storing and registering the element template in the designated element template database (DB) in which the element template division information is matched,
A method for enhancing iris recognition security using iris template distributed storage and matching, characterized by storing only element templates without storing the element template division information transmitted to the element template database (DB) in the element template database (DB). The method according to claim 1,
The step of comparing and authenticating one-to-one the iris template by measuring the distance between the stored pre-registered element template and the element template for authentication
Calculating a distance between an authentication element template sent to an element template database (DB) in which element template division information is matched with a pre-registered element template registered in advance in an element template database (DB);
Calculating a matching distance calculated by substituting the distance calculated for each element template database (DB) into a function; And
Comparing the matching distance obtained in the step and an authentication criterion to determine whether or not the same iris template is present. The method of claim 2,
The step of comparing a plurality of iris templates by a plurality of iris templates by measuring a distance between a plurality of stored pre-registered element templates and an identification element template
Calculating a distance between the identification element template and a plurality of pre-registered element templates pre-registered in the element template database (DB);
Obtaining a candidate group from the calculated matching distance using the distance calculated in the step; And
And selecting one or more pre-registered element templates selected in the step as the same element template. A method for enhancing iris recognition security using iris template distributed storage and matching. The method according to claim 1 or 11,
The distance between the stored pre-registered element template and the element template for authentication
And a hamming distance between element templates is calculated and used. The iris recognition security enhancement method using iris template distributed storage and matching. The method according to claim 2 or 12,
Wherein a hamming distance between element templates is calculated using a distance between a plurality of pre-registered element templates and an identification element template stored in the iris template storing and matching method. The method according to claim 11 or 12,
The sum of the distances (r ₁ , r ₂ , r ₃ , ..., r _n ) of the element template for authentication and the registered element template calculated in the n element template database (DB) (A ₁ , a ₂ , a ₃ ,..., A _n ) used in the iris recognition method. The method according to claim 11 or 12,
Wherein the minimum value is selected when the matching distance is calculated to be two or more. The method according to claim 11 or 12,
Wherein the hamming distance obtained by shifting the bit by a rotation angle is used when the matching distance is calculated in consideration of the rotation of the element template, and the iris recognition security enhancement method using the iris template distributed storage and matching. 14. The method of claim 13,
A method for enhancing iris recognition using iris template distributed storage and matching method, characterized by using basic authentication which calculates a hamming distance between element templates without calculating masked pixels among authentication element templates 14. The method of claim 13,
An iris-template-enhanced authentication is used to calculate hamming distance between element templates by fixing the hamming distance of masked pixels in the element template for authentication to a specific value. The iris template is characterized by distributed storage and matching iris recognition security Strengthening method. 15. The method of claim 14,
A method for enhancing iris recognition security using iris template distributed storage and matching, characterized by using basic authentication that calculates a hamming distance between element templates without calculating masked pixels among identification element templates. 15. The method of claim 14,
Iris recognition template authentication feature that calculates the hamming distance between element templates by fixing the hamming distance of the masked pixels in the identification element template to a specific value is used. Strengthening method. The method of claim 19,
And a specific value of 0.5 is used to fix the hamming distance of the masked pixel. The iris recognition security enhancement method using iris template distributed storage and matching. 23. The method of claim 21,
Wherein when the identification element template is an iris template, 0.5 is used as a specific value for fixing the hamming distance of the masked pixel, and the iris recognition security enhancement method using iris template distributed storage and matching. 16. The method of claim 15,
A pre-registration element template having a minimum distance is selected from the values obtained by sorting all the pre-registration element templates that are equal to or lower than the identification criterion from the calculated matching distance, all pre-registration element templates below the identification criterion are selected, And selecting a minimum number of candidates in a sequence close to a minimum value to obtain a candidate group. The iris recognition security enhancement method using iris template distributed storage and matching. The method of claim 10,
Wherein the element template division information transmitted to the element template database is stored in the gateway without being stored in the element template database. An iris recognition security enhancing apparatus using iris template distributed storage and matching,
Means for generating an iris template from iris images acquired for iris recognition;
Means for dividing the generated iris template into n element templates;
means for separating and storing n element templates divided into n in advance into an element template database (DB) promised; And
and means for comparing and authenticating the iris templates one-to-one by comparing and measuring the distances between the pre-registered element template stored in the pre-determined element template database (DB) and the n element-divided authentication element templates separated by n, An iris recognition security enhancement device using template distributed storage and matching. An iris recognition security enhancing apparatus using iris template distributed storage and matching,
Means for generating an iris template from iris images acquired for iris recognition;
Means for dividing the generated iris template into n element templates;
means for separating and storing n element templates divided into n in advance into an element template database (DB) promised; And
and means for comparing and distinguishing a plurality of iris templates from each other by comparing the distance between each of the previously registered element template templates stored in the previously determined element template database An iris recognition security enhancement device using template distributed storage and matching.

Images