JP4600746B2 - Authentication apparatus, authentication method, and program - Google Patents

Description

  The present invention relates to an authentication device, an authentication method, and a program, and is suitable for application to biometric authentication.

  Conventionally, many authentication apparatuses that use biometric fingerprints as targets for biometric authentication have been proposed, but in recent years, blood vessels in the living body have attracted attention as one of targets for biometric authentication.

  This type of authentication device is registered using the property that deoxygenated hemoglobin (venous blood) or oxygenated hemoglobin (arterial blood) that passes through blood vessels specifically absorbs light in the near infrared band (near infrared light). A person's blood vessel is imaged, and blood vessel image data (hereinafter referred to as registered blood vessel image data) obtained as an imaging result (hereinafter referred to as registered blood vessel image data) is registered in a predetermined database.

  In addition, the authentication apparatus images the blood vessel of the collator at an arbitrary timing, and data (hereinafter referred to as collator blood vessel image data) of blood vessel images (hereinafter referred to as collator blood vessel images) obtained as a result of the imaging. And the plurality of registered blood vessel image data registered in the database at this time are sequentially checked to authenticate the registrant.

  In such an authentication apparatus, since a plurality of registered blood vessel image data registered in the database is collated with collator blood vessel image data in an arbitrary order, registration blood vessel image data corresponding to the collator blood vessel image data is detected. In this case, the time required to obtain the authentication result becomes long despite the identity of the person, resulting in a decrease in processing efficiency.

  By the way, as an image ranking method, in response to an input of a search condition that characterizes a target image by a searcher, an image including the search condition is selected as a candidate image from a plurality of images. A method has been proposed in which a ranking correlation between a ranking representing the appearance order of preset search keys and a ranking of search conditions ranked in the input order is calculated, and candidate images are ranked in descending order of the correlation. (See, for example, Patent Document 1).

If this ranking method is adopted, it is considered that the registered blood vessel image data having a high probability of being the person can be collated in order.
Japanese Patent Application No. 7-114573

  However, in this ranking method, the search condition (search key) that characterizes the target image is simple such as “Mt. Fuji”, “Shinkansen”, etc., and the search condition is input. As is apparent from setting the appearance order in the search key itself, it is premised on human intervention, so it is not suitable for blood vessel images for which it is difficult to visually extract the search key.

  In addition, in this ranking method, since the appearance order is set in advance in the search key itself, when a search condition that is out of the search key is input, the ranking of candidate images becomes ambiguous, while the search key If the number of keys is increased, the amount of storage area occupied becomes excessive.

  Therefore, by simply adopting this ranking method, the registered blood vessel image data having a high probability of being an individual cannot be easily collated in order, and there still remains a problem that the processing efficiency of the authentication apparatus is lowered. Become.

  The present invention has been made in consideration of the above points, and intends to propose an authentication device, an authentication method, and a program that can improve the processing efficiency.

In order to solve such a problem, the present invention is an authentication device, in which a pattern storage unit that stores a blood vessel pattern for each group classified by the level of linearity, and for each registered image registered in the database, Rank data storage means in which first rank data representing the similarity to the blood vessel pattern in descending order is stored in association with the registered image , a collation image to be collated with the registered image , and each set of blood vessel patterns Between the generation means for generating the second rank data representing the similarity to the descending order, the second rank data generated by the generation means, and the first rank data stored in the rank data storage means Based on the rank correlation coefficient, it has collation means for sequentially collating registered images registered in the database with collation images.

  Therefore, since this authentication apparatus can perform ranking based on the similarity with the reference image, even if it is difficult to extract the search key by visual inspection without setting the appearance order in advance, It is possible to collate in the order with a high probability of being, and it is possible to easily stabilize the shortening of the collation period in the case of the person himself.

Further, the present invention is an authentication method, wherein for each registered image registered in the database, first rank data representing a descending order of similarity to a blood vessel pattern stored for each group classified by the level of linearity a first step of reading from a storage medium, and the match image to be matched against the registered image, a second step of generating a second ranking data representing the degree of similarity between each pair of the blood vessel pattern in descending order, generating Based on the rank correlation coefficient between the second rank data generated in the step and the first rank data read in the first step, the registered images registered in the database are sequentially collated with the collation image. And a third step.

  Therefore, in this authentication method, since ranking can be performed based on the similarity to the reference image, even if it is difficult to visually extract a search key without setting an appearance order in advance, Since collation can be performed in the order with a certain probability, shortening of the collation period when the person is the person can be easily stabilized.

Furthermore, the present invention is a program, which is a first program that represents, for each registered image registered in the database, a descending order of similarity to a blood vessel pattern stored for each group classified by the level of linearity. reading the rank data from the storage medium, to generate the matching image to be matched against the registered image, the second ranking data representing the degree of similarity between each pair of the blood vessel pattern in descending order, the second order data Then, based on the rank correlation coefficient between the first rank data and the first rank data, the registered image registered in the database is sequentially collated with the collation image.

  Therefore, in this program, since ranking can be performed based on the similarity to the reference image, even if it is difficult to extract the search key by visual inspection without setting the appearance order in advance, it is the person himself / herself. Since collation can be performed in the order of high probability, shortening of the collation period when the person is the person can be easily stabilized.

  According to the present invention, the first rank data representing the degree of similarity of registered images between a plurality of different reference images in descending order is held for each registered image in association with the registered image. Generating second rank data representing descending order of the similarity degree of the collation image with each of the plurality of reference images, the generated second rank data, and each of the first rank data, When the corresponding registered images are sequentially matched with the matching images based on the rank correlation coefficient between them, it is difficult to visually extract the search key without setting the appearance rank in advance. Even in such a case, since the collation can be performed in the order of high probability of being the person, the shortening of the collation period in the case of being the person can be easily stabilized, and thus the processing efficiency can be improved.

  Embodiments to which the present invention is applied will be described in detail below with reference to the drawings.

(1) Overall Configuration of Authentication Device In FIG. 1, reference numeral 1 denotes an authentication device 1 according to the present embodiment as a whole, and the blood vessel imaging unit 2 and the signal processing unit 3 are connected to each other via a cable. Composed.

  The blood vessel imaging unit 2 has a curved guide groove 11 formed so as to imitate a finger FG at a predetermined position of the housing 1A of the authentication device 1, and an imaging opening 12 is formed on the bottom surface of the guide groove 11. Is arranged.

  As a result, the blood vessel imaging unit 2 guides the finger pad of the finger FG to be contacted so as to be applied to the guide groove 11 onto the imaging opening 12, and is brought into contact with the tip of the guide groove 11 in contact with the fingertip. The position of the imaging opening 12 with respect to the finger FG is determined according to the photographer.

  A colorless and transparent opening cover portion 13 made of a predetermined material is provided on the surface of the imaging opening portion 12, while a camera portion 14 is disposed immediately below the imaging opening portion 12 inside the housing 1A. ing.

  Further, on the side surface of the guide groove 11, a pair of near-infrared light sources 15 (15 </ b> A and 15 </ b> B) that irradiate near-infrared light specifically absorbed with respect to hemoglobin as imaging light for blood vessels are provided on the guide groove 11. Is arranged so as to sandwich the imaging opening 12 in parallel with the short direction of the finger, and can be irradiated with near-infrared light on the finger pad side portion of the finger FG in contact with the guide groove 11. .

  Therefore, in this blood vessel imaging unit 2, the ratio of near-infrared light reflected on the surface of the finger FG is remarkably suppressed as compared with the case where near-infrared light is irradiated on the finger pad base of the finger FG. Near-infrared light incident on the inside of the finger FG via the finger FG is absorbed by hemoglobin passing through the blood vessel and scattered in tissues other than the blood vessel through the inner side of the finger FG and from the finger FG. As near-infrared light for projecting blood vessels (hereinafter referred to as blood vessel projection light), the light enters the camera unit 14 via the imaging opening 12 and the opening cover 13 in sequence.

  In the camera unit 14, the macro lens 16 and near-red light that transmits only near-infrared light in a wavelength range (approximately 900 [nm] to 1000 [nm]) that depends on both oxygenation and deoxygenation hemoglobin. An external light transmission filter 17 and a CCD image sensor 18 are sequentially arranged, and blood vessel projection light incident from the opening cover 13 is sequentially passed through the macro lens 16 and the near-infrared light transmission filter 17 to the CCD image sensor 18. To the imaging surface. Thus, the camera unit 14 can faithfully image both venous and arterial capillaries mixed inside the adjacent finger FG.

  Under the control of the signal processing unit 3, the CCD image pickup device 18 picks up an image of a blood vessel formed on the image pickup surface, and the image pickup result is an image signal (hereinafter referred to as a blood vessel image signal) SA1, SA2, ... Are sequentially output to the signal processing unit 3 as SAn.

  On the other hand, the signal processing unit 3, as shown in FIG. 2, communicates with the control unit 20 the blood vessel imaging drive unit 21, the image processing unit 22, the authentication unit 23, the flash memory FM, and an interface (data transmission / reception). This is called an external interface (hereinafter referred to as an external interface).

  The control unit 20 includes a central processing unit (CPU) that controls the authentication apparatus 1 as a whole, a read only memory (ROM) that stores various programs, a random access memory (RAM) as a work memory of the CPU, and the like. A mode for registering a blood vessel of a registrant in the control unit 20 in accordance with an operation of an operation unit (not shown) provided at a predetermined position on the surface of the housing 1A of the authentication device 1 ( Hereinafter, an execution command COM1 of a blood vessel registration mode) or an execution command COM2 of a mode for determining the presence / absence of the registrant (hereinafter referred to as an authentication mode) is given.

  Then, when the blood vessel registration mode execution command COM1 is given from the operation unit (not shown), the control unit 20 changes the operation mode to the blood vessel registration mode based on the corresponding program stored in the ROM. The blood vessel imaging drive unit 21, the image processing unit 22, and the authentication unit 23 are each controlled.

  In this case, the blood vessel imaging drive unit 21 activates the blood vessel imaging unit 2 so as to drive the near-infrared light source 15 and the CCD imaging device 18 of the camera unit 14, respectively. As a result, in the blood vessel imaging unit 2, near infrared light is irradiated from the near infrared light source 15 onto the finger pad side of the imager's finger FG (FIG. 1) that is in contact with the guide groove 11 (FIG. 1) at this time. Then, the blood vessel projection light guided to the imaging surface of the CCD image sensor 18 via the finger FG (FIG. 1) is output from the CCD image sensor 18 as blood vessel image signals SA1, SA2,. The data are sequentially output to 22 A / D (Analog / Digital) converter 22A.

  The A / D converter 22A performs A / D conversion processing on the blood vessel image signals SA1, SA2,..., SAn, and blood vessel image data obtained as a result (hereinafter referred to as blood vessel image data) DA1. , DA2,..., DAn are sent to the filter unit 22B.

  The filter unit 22B performs various filtering processes corresponding to noise component removal and contour enhancement on the blood vessel image data DA1, DA2,..., DAn, and blood vessel image data DB1, DB2,. DBn is sent to the binarization unit 22C.

  The binarization unit 22C performs binarization processing on the blood vessel image data DB1, DB2,..., DBn, and obtains black and white blood vessel images (hereinafter referred to as binary blood vessel images) obtained as a result. (Hereinafter referred to as binary blood vessel image data) DC1, DC2,..., DCn are sent to the thinning unit 22D.

  The thinning unit 22D performs, for example, a morphological process on the binary blood vessel image data DC1, DC2,..., DCn, and the binary blood vessel image based on the binary blood vessel image data DC (DC1 to DCn). Linearize blood vessels.

  Then, the thinning unit 22D selects one binary blood vessel image from a plurality of binary blood vessel images formed of linearized blood vessels (hereinafter referred to as blood vessel lines), and selects the selected 2 The binary blood vessel image data DD corresponding to the value blood vessel image is sent to the authentication unit 23.

  The authentication unit 23 generates binary blood vessel image data DD as registration authentication information RC having a predetermined format, and sends this to the control unit 20.

  When the control unit 20 receives the registration authentication information RC from the authentication unit 23 by controlling the blood vessel imaging drive unit 21, the image processing unit 22, and the authentication unit 23 in this manner, the control unit 20 stores the registration authentication information RC in the flash memory FM. And the blood vessel imaging unit 2 is stopped so as to cancel the control of the blood vessel imaging drive unit 21, the image processing unit 22, and the authentication unit 23.

  In this way, the control unit 20 can execute the blood vessel registration mode.

  On the other hand, when the authentication mode execution command COM2 is given from the operation unit (not shown), the control unit 20 changes the operation mode to the authentication mode based on the corresponding program stored in the ROM. Then, the blood vessel imaging drive unit 21, the image processing unit 22, and the authentication unit 23 are controlled, and the registration authentication information RC registered in the flash memory FM is read out and sent to the authentication unit 23.

  In this case, the blood vessel imaging drive unit 21 activates the blood vessel imaging unit 2 as in the above-described blood vessel registration mode. Further, the image processing unit 22 performs various processes on the blood vessel image signals SA (SA1 to SAn) sequentially output from the blood vessel imaging unit 2 in the same manner as in the blood vessel registration mode, and 2 is obtained as a result. The value blood vessel image data DD is sent to the authentication unit 23.

  The authentication unit 23 displays the blood vessel line formation pattern in the binary blood vessel image based on the binary blood vessel image data DD and the binary blood vessel image based on the registration authentication information RC read from the flash memory FM by the control unit 20. Collate.

  Then, the authentication unit 23 determines whether or not the photographer imaged by the blood vessel imaging unit 2 at this time is a registrant according to the matching degree, and the determination result is sent to the control unit 20 as determination data D1. Send it out.

  When the control unit 20 receives the determination data D1 from the authentication unit 23 by controlling the blood vessel imaging drive unit 21, the image processing unit 22, and the authentication unit 23 in this way, the control unit 20 transmits the determination data D1 via the external interface IF. Then, the blood vessel imaging unit 2 is stopped so as to cancel the control of the blood vessel imaging drive unit 21, the image processing unit 22, and the authentication unit 23.

  In this way, the control unit 20 can execute the authentication mode.

  As described above, the authentication device 1 performs biometric authentication for determining the existence of the person (registrant) with the blood vessel of the unique structure interposed inside the living body as an authentication target, thereby obtaining a fingerprint or the like on the surface of the living body. Compared to the case of the target, not only direct theft from a living body but also impersonation of a registrant by a third party can be prevented.

(2) Specific processing contents of authentication unit In addition to this configuration, the authentication device 1 registers a plurality of binary blood vessel images (hereinafter referred to as registered blood vessel images) registered in the flash memory FM. The authentication processing is executed so as to collate with a binary blood vessel image to be collated with the registered blood vessel image (hereinafter referred to as a collation blood vessel image) in descending order of the probability of being the person himself.

In practice, in the authentication device 1, a plurality of different reference blood vessel images are designated via the operation unit (not shown) as a comparison target between the registered blood vessel image and the verification blood vessel image. The control unit 20 of the authentication device 1 receives a plurality of reference blood vessel image data DS _i ( _i = 1, 2,..., Or m) designated according to a designation operation from an operation unit (not shown), for example, Acquired via the external interface IF, and stores the reference blood vessel image data DSi in the flash memory FM.

In this state, when the control unit 20 transitions to the registration mode, the control unit 20 sends the reference blood vessel image data DS _i stored in the flash memory FM in advance to the authentication unit 23, and at this time, the blood vessel image captured by the blood vessel imaging unit 2 The signal SA (FIG. 2) is sent to the authentication unit 23 as binary blood vessel image data DD via the image processing unit 22.

In this case, the authentication unit 23 generates the binary blood vessel image data DD as registration authentication information RC having a predetermined format under the control of the control unit 20, and the binary based on the binary blood vessel image data DD. A correlation coefficient between the blood vessel image and each reference blood vessel image based on the reference blood vessel image data DS _i is detected as a similarity.

  And the authentication part 23 produces | generates the data DX (this is called 1st order data below) DX which represents the magnitude | size of these similarities (correlation coefficient) in descending order under control of the control part 20, The generated first rank data DX and the registration authentication information RC generated at this time are associated with each other and stored in the flash memory FM.

  Further, each time the control unit 20 transitions to the registration mode, the control unit 20 is a first unit that represents the degree of similarity (correlation coefficient) in descending order between the binary blood vessel image obtained at that time and the plurality of reference blood vessel images. The rank data DX is generated each time, and the first rank data DX is stored in the flash memory FM in association with the registration authentication information RC generated from the binary blood vessel image.

On the other hand, when the control unit 20 transits to the authentication mode, the reference blood vessel image data DS _i stored in the flash memory FM in advance and a plurality of registration authentication information RC _j ( _j = 1) registered in the flash memory FM at this time. , 2, ..., or the first ranking data DX _j respectively associated with n) sends out the authentication unit 23, captured by the time the blood vessel image pickup section 2 the blood vessel image signal SA (Fig. 2) Is sent to the authentication unit 23 as binary blood vessel image data DD via the image processing unit 22.

  In this case, under the control of the control unit 20, the authentication unit 23 performs a matching blood vessel image (binary blood vessel image) based on the binary blood vessel image data DD and a plurality of reference blood vessels, as in the registration mode. Data representing the degree of similarity (correlation coefficient) with the image in descending order (hereinafter referred to as second rank data) is generated.

Then, the authentication unit 23 detects the rank correlation coefficient between the second rank data and each of the first rank data DX _j under the control of the control unit 20, and the rank correlation coefficient value. The corresponding registration authentication information RC _j is sequentially read out from the flash memory FM until the determination result that the user is the registrant in descending order is large, and the registered blood vessel image (binary blood vessel) based on the read registration authentication information RC _j is read. The image) is collated with a collation blood vessel image (binary blood vessel image) based on the binary blood vessel image data DD.

  In this way, the control unit 20 authenticates the plurality of registered blood vessel images registered in the flash memory FM with the matching blood vessel images that are collated with the registered blood vessel images in descending order of the probability of being the registrant. Processing is made so that it can be executed.

(3) Authentication Processing Procedure A series of authentication processing from the registration mode to the authentication mode by the control unit 20 described above is executed according to the authentication processing procedure RT shown in FIG.

  That is, when the main power is turned on, the control unit 20 starts this authentication processing procedure RT in step SP0, and waits for an execution command COM in the blood vessel registration mode or authentication mode in the subsequent step SP1.

  Here, when the control unit 20 receives the blood vessel registration mode execution command COM1 in step SP1, the control unit 20 starts the lower blood vessel registration processing procedure SRT1 in step SP10 (FIG. 4), and in the subsequent step SP11, the registration is performed. A person's blood vessel is generated as binary blood vessel image data DD (FIG. 2).

In step SP12, the control unit 20 reads a plurality of reference blood vessel image data DC _i stored in advance from the flash memory FM, and each reference blood vessel image based on the reference blood vessel image data DC _i and the binary generated in step SP11. Similarities between binary blood vessel images (registered blood vessel images) based on the blood vessel image data DD are respectively detected, and in the subsequent step SP13, first rank data DX _j is generated based on these similarities.

Subsequently, in step SP13, the control unit 20 generates the binary blood vessel image data DD as registration authentication information RC _j , and in the subsequent step SP14, the registration authentication information RC _j and the first order generated in step SP12. After associating the data DX _j with the flash memory FM, the process returns to step SP1 (FIG. 3).

On the other hand, when the control unit 20 receives the authentication mode execution command COM2 in step SP1, the control unit 20 starts the lower collation processing procedure SRT2 in step SP20 (FIG. 5). In the subsequent step SP22, which is generated as binary blood vessel image data DD (FIG. 2), the first rank data DX _j stored in the flash memory FM by the above-described blood vessel registration processing is read, and the read first rank data DX Based on the number of _j , it is determined whether there are a plurality of registered blood vessel images registered in the flash memory FM.

  Here, when the control unit 20 determines that the number of registered blood vessel images is not plural, in the subsequent step SP23, the control unit 20 reads the registered blood vessel information RC corresponding to the first rank data DX read at this time, and The registered blood vessel image based on the registered blood vessel information RC and the collated blood vessel image based on the binary blood vessel image data DD generated in step SP21 are collated, and in step SP24, the presence / absence of the registrant is determined according to the collation degree. After the determination data D1 representing the determination result is transmitted to the outside via the external interface IF, the process returns to step SP1 (FIG. 3).

On the other hand, when the control unit 20 determines that the number of registered blood vessel images is plural, in the subsequent step SP25, the binary blood vessel image data DD is the same as in the above-described steps SP12 and SP13. a verification vessel image based on, generates a second order data based on the similarities between the respective reference blood vessel image based on the plurality of reference blood vessel image data DC _i, in the subsequent step SP26, the second ranking data And the rank correlation coefficient between the first rank data DX _j read in step SP23.

In step SP27, the control unit 20 selects the first rank data DX _j having the largest rank correlation coefficient value, and in subsequent step SP28, the registration authentication information corresponding to the selected first rank data DX _j. RC _j is read from the flash memory FM, a registered blood vessel image (binary blood vessel image) based on the registration authentication information RC _j and a matching blood vessel image (binary blood vessel image) based on the binary blood vessel image data DD generated in step SP21. And match.

Subsequently, in step SP29, the control unit 20 determines the presence / absence of the registrant according to the collation degree. If it is determined that the registrant is not the registrant, the control unit 20 determines all registered blood vessel images in step SP30. Until the collation is completed, in step SP31, the first rank data DX _j having the next largest rank correlation coefficient value is selected, and then the process returns to step SP28 and the above-described processing is repeated.

  In addition, when the control unit 20 determines that the user is the registrant, or if it cannot determine that the user is the registrant even if all the registered blood vessel images are collated with the verification blood vessel image, in the next step SP32, After the determination data D1 representing the determination result is transmitted to the outside via the external interface IF, the process returns to step SP1 (FIG. 3).

  In this way, the authentication unit 23 can execute the authentication process under the control of the control unit 20.

(4) Operation and Effect In the configuration described above, the authentication device 1 registers first rank data that represents the degree of similarity of registered blood vessel images with each of a plurality of different reference blood vessel images in descending order. Each blood vessel image is stored in association with the registered blood vessel image.

  And at the time of authentication, the authentication device 1 generates second rank data that represents the magnitude of the similarity of the collated blood vessel images with each of the plurality of reference blood vessel images in descending order, and the second rank data, Each corresponding registered blood vessel image is sequentially collated with the collated blood vessel image based on the rank correlation coefficient with the plurality of first rank data held in advance.

  Accordingly, in this authentication apparatus 1, since ranking can be performed based on the similarity to the reference image, even if it is difficult to extract the search key by visual inspection and the blood vessel image, the appearance order is set in advance as in the conventional case. Therefore, collation can be performed in the order of high probability of being the principal, and shortening of the collation period in the case of the principal can be reliably stabilized.

  The authentication device 1 does not execute the process of detecting the degree of similarity of the registered blood vessel image at the time of collation, and does not input a search key as in the prior art, and the degree of similarity of the collated blood vessel image. Since it is possible to collate only with the process of detecting the degree of processing and the process of detecting the rank correlation coefficient that has a relatively small processing load compared to the process, it is possible to easily collate in the order of high probability of being the person. .

  According to the above configuration, the first rank data representing the degree of similarity of the registered blood vessel images between the plurality of different reference blood vessel images in descending order is registered for each registered blood vessel image with the registered blood vessel image. The second rank data is stored in association with each other, and at the time of authentication, second rank data that represents the magnitude of the similarity of the matching blood vessel image with each of the plurality of reference blood vessel images is generated in descending order. And the corresponding registered blood vessel image sequentially with the matching blood vessel image based on the rank correlation coefficient between the first rank data and the plurality of first rank data held in advance, Even if it is difficult to extract the search key by visual inspection, it is possible to collate in the order with high probability of being the principal, so the shortening of the collation period is surely stable in the case of the principal. So that it is, thus it is possible to improve the processing efficiency.

(5) Other Embodiments In the above-described embodiments, the first rank data representing the degree of similarity of registered images with each of a plurality of different reference images in descending order is registered for each registered image. Although the case where the flash memory FM is applied as the holding means that holds the image in association with the registered image has been described, the present invention is not limited to this, for example, an HDD (Hard Disk Drive), a detachable device Various other holding means such as Memory Stick (registered trademark of Sony Corporation) can be widely applied.

  In addition, the holding unit is provided in the authentication device 1, but the present invention is not limited to this, and may be connected to the authentication device 1 via a transmission line as a separate body.

Further, the first rank data DXj is held in the same flash memory FM as the plurality of reference images DS _i . However, the present invention is not limited to this and is different from the plurality of reference images DS _i . The first rank data DXj may be held in a place.

  Further, the plurality of reference blood vessel images stored in the flash memory FM may be increased according to the number of registered blood vessel images Rj. In this way, it is possible to maintain the accuracy of the collation ordering in the registered blood vessel image with a processing load commensurate with the number of registered images.

  In the above-described embodiment, the second rank data representing the descending order of the degree of similarity of the collation image with each of the plurality of reference images is generated, the second rank data, As a collation means for sequentially collating each corresponding registered image with the collation image based on the rank correlation coefficient with the rank data, the case where collation is performed according to the collation processing procedure SRT2 shown in FIG. 5 has been described. However, the present invention is not limited to this, and the order and details of the processing may be changed as appropriate.

  Further, as the second rank data (first rank data), in the above-described embodiment, the similarity of the reference blood vessel image (registered blood vessel image) between each of a plurality of different reference blood vessel images is simply determined. Although the case where the sizes are expressed in descending order has been described, the present invention is not limited to this. For example, a plurality of reference blood vessel images approximating a blood vessel image having a highly linear blood vessel pattern, A plurality of reference blood vessel images that approximate a blood vessel image, a plurality of reference blood vessel images that approximate a blood vessel image of a blood vessel pattern with many branches, a plurality of reference blood vessel images that approximate a blood vessel image with a blood vessel pattern with few branches, etc. A plurality of reference blood vessel images that approximate blood vessels classified into a plurality of blood vessel patterns are stored in the flash memory FM as a set, and each reference blood vessel image for each set is stored. The magnitude of the similarity of verification vessel image may be represented in descending order between the.

  In this way, ranking can be performed based on the degree of similarity between each of the reference blood vessel image groups that are characteristically biased from each other. As a result, the processing efficiency can be improved while improving the collation accuracy.

  Furthermore, in the above-described embodiment, both the blood vessel registration mode and the authentication mode are executed as an authentication device that performs authentication based on a plurality of registered images registered in the database and a collation image to be collated with the registered image. However, the present invention is not limited to this, and an authentication device that executes only one of the authentication modes may be applied.

  In this case, for example, in a system configured by an external management device that manages registered images in a database, a registered image managed by the management device, and an authentication device that collates with a verification blood vessel image acquired by itself, Since the authentication device can hold the first rank data generated by the external management device at a predetermined timing, for example, at the time of authentication or registration update, the load of the generation process is reduced. This is particularly effective in that it can be avoided and the storage capacity of the flash memory FM can be reduced accordingly.

  Further, in the above-described embodiment, a blood vessel image intervening inside the living body is applied as the registered image and the collation image. However, the present invention is not limited to this. For example, the blood vessel of the palm, arm, or eye In addition, images of blood vessels in various other biological parts may be applied, and other various authentication target images such as fingerprints on the surface of the living body, paper patterns called patterns, or nerves inside the living body, etc. May be applied. Incidentally, when a nerve is an authentication target, for example, if a marker specific to the nerve is injected into the body and the marker is imaged, the nerve is the authentication target in the same manner as in the above-described embodiment. be able to.

  The present invention can be used in a field using a technique for identifying a living body or the like.

It is a basic diagram which shows the whole structure of the authentication apparatus by this Embodiment. It is a block diagram which shows the structure of a signal processing part. It is a flowchart which shows an authentication process procedure. It is a flowchart which shows the blood vessel registration processing procedure. It is a flowchart which shows a collation process procedure.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 ... Authentication apparatus, 2 ... Blood vessel imaging part, 3 ... Signal processing part, 14 ... Camera part, 15A, 15B ... Near infrared light source, 16 ... Macro lens, 17 ... Near infrared light Transmission filter, 18 ... CCD imaging device, 20 ... control unit, 21 ... blood vessel imaging drive unit, 22A ... A / D conversion unit, 22B ... filter unit, 22C ... binarization unit, 22D ... Thinning unit, 23 ... Authentication unit, IF ... External interface, FM ... Flash memory, FG ... Finger, COM (COM1 and COM2) ... Execution command, SA (SA1 to SAn) ... Vessel image signal, DA (DA1 to DAn), DB (DB1 to DBn) ... vessel image data, DC (DC1 to DCn), DD ... binary vessel image data, D1 ... determination data, DSi ... reference vessel image data, DXj …… First rank data, Cj ...... registration authentication information, RT ...... authentication processing procedure, SRT1 ...... blood vessel registration processing procedure, SRT2 ...... verification procedure.

Claims (6)

A pattern storage unit that stores a blood vessel pattern for each group classified according to the level of linearity;
For each registered image registered in the database, rank data storage means for storing first rank data representing the similarity to each blood vessel pattern in descending order in association with the registered image;
Collating image to be matched against the registered image generating means for generating a second ranking data representing the degree of similarity between each pair of the blood vessel pattern in descending order,
Based on the rank correlation coefficient between the second rank data generated by the generation means and the first rank data stored in the rank data storage means, the registered images registered in the database are An authentication apparatus comprising: a verification unit that sequentially matches a verification image. When the database is updated, for each registered image registered in the database, first ranking data that represents the similarity with each of the blood vessel patterns in descending order is generated, and further associated with the registered image The authentication device according to claim 1. A first step of reading, from the storage medium, first rank data representing descending order of similarity to the blood vessel pattern stored for each group classified by the level of linearity for each registered image registered in the database;
Collating image to be matched against the registered image, a second step of generating a second ranking data representing the degree of similarity between each pair of the blood vessel pattern in descending order,
Based on the rank correlation coefficient between the second rank data generated in the generation step and the first rank data read in the first step, the registered image registered in the database is collated. An authentication method comprising: a third step of sequentially collating with images. When the database is updated, for each registered image registered in the database, there is further provided an associating step of generating first rank data representing the similarity to each of the blood vessel patterns in descending order and associating with the registered image. The authentication method according to claim 3. Against the computer,
For each registered image registered in the database, reading from the storage medium the first rank data representing the similarity with the blood vessel pattern stored for each group classified by the level of linearity in descending order;
Collating image to be matched against the registered image, generating a second ranking data representing the degree of similarity between each pair of the blood vessel pattern in descending order,
A program for executing sequential verification of registered images registered in the database with the verification image based on a rank correlation coefficient between the second rank data and the first rank data. When the database is updated, for each registered image registered in the database, the first rank data indicating the similarity to each of the blood vessel patterns in descending order is generated, and the association with the registered image is further executed. Item 6. The program according to item 5.

Images