JP7423039B2 - Authentication device, method and program - Google Patents

Description

The present invention relates to an authentication device, method, and program.

2. Description of the Related Art In recent years, systems (hereinafter referred to as "authentication systems") have been known that perform face authentication on subjects (for example, people) included in images captured by imaging devices used, for example, as surveillance cameras. Note that face authentication refers to identifying (authenticating) a subject by comparing an image of the subject registered in advance with an image of the subject captured by an imaging device.

Generally, in order to implement a face recognition mechanism into an authentication system, it is necessary to register in advance the image of the subject to be identified by face recognition as described above. The registration work is complicated, and the burden of implementing the face recognition mechanism into an authentication system is large.

Japanese Patent Application Publication No. 2001-338295 Japanese Patent Application Publication No. 2018-147475

SUMMARY OF THE INVENTION Therefore, an object of the present invention is to relate to an authentication device, method, and program that can smoothly implement a transition to ecosystem authentication by using other pre-registration type code authentication.

According to one aspect of the present invention, a first acquisition means for acquiring a first image including a subject to which an optical recognition code representing identification information for identifying the subject is attached; code authentication means for executing a code authentication process for an optical recognition code included in the image; and identification information represented by the optical recognition code included in the first image being acquired by executing the code authentication process. a storage means for storing the first image in association with the acquired identification information, and when a plurality of first images are stored in the storage means, the number of the plurality of first images is a threshold value. determining means for determining whether the number of the plurality of first images has reached a threshold; a second acquisition means for acquiring a second image including a subject; and when the second image is acquired, performing face authentication processing on the subject included in the second image using the generated face authentication data ; An authentication device is provided that includes a face authentication means.

The present invention makes it possible to smoothly implement the transition to ecosystem authentication by using other pre-registered code authentication.

FIG. 1 is a diagram illustrating an example of the configuration of an authentication system including an authentication device according to an embodiment. The figure which shows an example of the hardware configuration of an authentication device. FIG. 2 is a diagram illustrating an example of how an imaging device is installed. The figure which shows an example of the image imaged by the imaging device. A diagram for explaining the color bit code in detail. The figure which shows an example of the functional structure of an authentication device. 5 is a flowchart illustrating an example of a processing procedure of an authentication device. 5 is a flowchart illustrating an example of a processing procedure of face authentication data registration processing.

Embodiments of the present invention will be described below with reference to the drawings.
FIG. 1 shows an example of the configuration of an authentication system (network system) including an authentication device according to this embodiment. The authentication system shown in FIG. 1 includes an imaging device 10 and an authentication device 20. The imaging device 10 and the authentication device 20 are connected to each other via a network 30 so that they can communicate with each other.

The imaging device 10 has a function of capturing an image including a subject. The authentication device 20 has a function as a server device that executes authentication processing using images captured by the imaging device 10. Note that the authentication device 20 may be a server device or the like that provides various cloud computing services.

FIG. 2 shows an example of the hardware configuration of the authentication device 20 shown in FIG. 1. As shown in FIG. 2, the authentication device 20 includes a nonvolatile memory 22 connected to a bus 21, a CPU 23, a main memory 24, a wireless communication device 25, and the like.

Nonvolatile memory 22 stores various programs. The various programs stored in the nonvolatile memory 22 include software that operates on the authentication device 20.

The CPU 23 executes various programs stored in the nonvolatile memory 22, for example. Note that the CPU 23 is in charge of controlling the entire authentication device 20.

The main memory 24 is used, for example, as a work area required when the CPU 23 executes various programs.

The wireless communication device 25 has a function of controlling communication with, for example, an external imaging device 10 or the like.

Here, an example of how the imaging device 10 and the authentication device 20 in this embodiment are used will be described.

In this embodiment, the imaging device 10 and the authentication device 20 are used, for example, to monitor (manage) a person entering a predetermined area.

Specifically, as shown in FIG. 3, the imaging device 10 is installed near a door 100 provided at, for example, an entrance to a work area in a company. According to this, an image including a person (for example, an employee) entering and leaving the work area via the door 100 can be captured by the imaging device 10, and entry and exit of the person into and out of the work area can be managed. be able to. The work area may be, for example, an office where desks used by employees are arranged, the premises of a factory or the like, or other spaces. Furthermore, when managing entry and exit to the work area, the imaging device 10 is installed both inside and outside the work area. Although this embodiment will be described as managing entry and exit from the work area, it is also possible to manage only one of entry and exit from the work area.

By the way, as described above, in order to manage the entry and exit of a person into the work area, it is necessary to identify (authenticate) the person from the image captured by the imaging device 10. Facial recognition shall be performed to identify the person.

However, when performing face recognition, it is necessary to register in advance images of all the people to be identified by the face recognition (or data representing the facial feature points of the people extracted from the images). , such registration work is complicated. Therefore, in this embodiment, images necessary for facial recognition are automatically registered using the optical recognition code described below (in other words, images necessary for performing face recognition are automatically registered (in other words, images that are required for performing face recognition are Adopt a configuration that smoothly implements the transition to ecosystem authentication.

FIG. 4 shows an example of an image captured by the imaging device 10 installed near the door 100 as described above.

As shown in FIG. 4, an optical recognition code 110 is attached to the chest of a person (subject) whose entrance into and exit from the work area is controlled. Note that the optical recognition code 110 is not limited to the person's chest, but may be attached to other locations.

In this embodiment, face authentication is performed as described above, but the imaging device 10 captures an image including a person with such an optical recognition code 110 attached, and the optical recognition code 110 is extracted from the image. By reading it, it is also possible to control the person's entry and exit from the room.

That is, in this embodiment, it is assumed that the imaging device 10 (camera) is installed at a position where it can image the chest (optical recognition code 110) of a person approaching the door 100.

The optical recognition code used in this embodiment will be specifically explained below. The optical recognition code in this embodiment includes, for example, a code (hereinafter referred to as a color bit code) in which a plurality of elements are formed in a linear (rod-like) shape. This color bit code has a configuration in which a plurality of cells (elements) each having one of three or more colors are arranged. According to this color bit code, specific data such as identification information (for example, ID, etc.) can be expressed by the transition of colors attached to each cell arranged in plurality.

In the following description, it is assumed that the optical recognition code used in this embodiment is a color bit code.

The color bit code will be explained in detail with reference to FIG. Note that in FIG. 5, only a portion of the color bit code is shown for convenience.

As shown in FIG. 5, the color bit code is configured by arranging a plurality of cells 120 each of which is colored one of red, green, and blue, for example. In FIG. 5, red is shown as R, green as G, and blue as B. In addition, in FIG. 5, for convenience of explanation, an example is shown in which three colors (red, green, and blue) are used in the color bit code, but the transition of the colors attached to each cell 120 is A color bit code may be created using four or more colors as long as it is possible to identify the color.

The cells 120 forming the color bit code are ranges or regions to which one color is assigned, and can have various shapes. In the example shown in FIG. 5, each of the plurality of cells 120 has a rectangular shape, but may have a round shape, a triangular shape, etc., for example. A color bit code is created by arranging such a plurality of cells 120 linearly (straight or curved).

Note that, as described above, since the color bit code represents specific data by color transition, in the color bit code, adjacent cells 120 are not given the same color, but different colors. Color bit codes are created based on such conditions.

Furthermore, the plurality of cells 120 forming the color bit code include endpoint cells. The endpoint cells are cells 120 located at the endpoints (both ends) of a color bit code made up of a group of linearly connected cells. A cell 120 within a color bit code is adjacent to two cells 120, but an endpoint cell is adjacent to only one cell 120. There are always two such endpoint cells in a color bit code. Further, it is assumed that the colors given to such two endpoint cells are necessarily different. As a result, depending on the color assigned to each endpoint cell, it can be determined whether the endpoint cell is a starting point cell (hereinafter referred to as a starting point cell) or an endpoint cell (hereinafter referred to as an endpoint cell). It is possible to determine.

According to the above-mentioned color bit code, specific data can be expressed by the transition (sequence) of three colors, so the restrictions on the size and shape of the area occupied by each color in the color bit code are loose. , it is possible to achieve high reading accuracy even when the color bit code is attached to an uneven surface or flexible material, or displayed on a display device such as a digital signage. can.

In this embodiment, the color bit code is applied to a person entering or leaving the work area as described above. In this case, in this embodiment, the color bit code attached to the person represents identification information (eg, employee ID) for identifying the person. As a result, by reading the color bit code attached to a person (that is, acquiring the identification information represented by the color bit code), the person entering or leaving the work area can be detected with high accuracy. Can be identified (authenticated). It is assumed that information on each person using the authentication system (personal information such as name and employee code) and identification information for identifying the person are registered in advance.

Here, in the example shown in FIG. 4 described above, a name tag with an optical recognition code 110 attached is attached to the person, but the color bit code can achieve high reading accuracy as described above. When a color bit code is used as the optical recognition code 110, it is possible to print the optical recognition code 110 (color bit code) directly on, for example, a jacket worn by a person, or It is also possible to sew the recognition code 110 directly onto the jacket.

Next, FIG. 6 shows an example of the functional configuration of the authentication device 20 according to this embodiment. As shown in FIG. 6, the authentication device 20 includes an image acquisition section 201, a face authentication processing section 202, a code authentication processing section 203, a face authentication data generation section 204, and a storage section 205.

In this embodiment, the image acquisition unit 201, the face authentication processing unit 202, the code authentication processing unit 203, and the face authentication data generation unit 204 are configured such that the CPU 23 (that is, the computer of the authentication device 20) shown in FIG. In other words, it is realized by software. Note that the program executed by the CPU 23 may be stored in advance in a computer-readable storage medium and distributed, or may be downloaded to the authentication device 20 via the network 30. Further, in this embodiment, the storage unit 205 is realized by, for example, the nonvolatile memory 22 shown in FIG. 2.

The image acquisition unit 201 acquires an image captured by the imaging device 10. The image acquired by the image acquisition unit 201 is composed of a plurality of pixels, which are the minimum units of color information.

Note that the imaging device 10 according to the present embodiment is used, for example, to manage the entry and exit of a person, and therefore is assumed to operate continuously during a time period when a person may enter and leave the room. In this case, the image acquisition unit 201 sequentially acquires images captured by the imaging device 10 (in real time).

The face authentication processing unit 202 performs face authentication processing on a person included in the image acquired by the image acquisition unit 201, using an image stored in the storage unit 205, which will be described later.

The code authentication processing unit 203 reads (decodes) the color bit code included in the image acquired by the image acquisition unit 201, thereby executing code authentication processing for the color bit code. Note that the decoding by the code authentication processing unit 203 is performed based on the color transition in the color bit code (that is, the color transition attached to each of the plurality of cells making up the color bit code). Thereby, the code authentication processing unit 203 can acquire the identification information represented by the color bit code included in the image.

Note that when identification information is acquired from a color bit code included in an image acquired by the image acquisition unit 201 by executing the code authentication process, the image is stored in the storage unit 205 in association with the identification information. Stored.

The face authentication data generation unit 204 analyzes the image stored in the storage unit 205 to generate data (hereinafter referred to as face authentication data) representing feature points of a person's face included in the image. The face authentication data generated by the face authentication data generation unit 204 is stored in the storage unit 205 in association with the identification information associated with the image used to generate the face authentication data.

In this embodiment, the above-described face authentication processing unit 202 executes face authentication processing based on the face authentication data stored in the storage unit 205 in this manner.

Hereinafter, an example of the processing procedure of the authentication device 20 in this embodiment will be described with reference to the flowchart of FIG. 7.

First, for example, when the power of the imaging device 10 is turned on, the imaging device 10 is started. By activating the imaging device 10 in this manner, it becomes possible for the imaging device 10 to capture an image. The image captured by the imaging device 10 is transmitted to the authentication device 20.

In this case, the image acquisition unit 201 acquires (receives) an image transmitted from the imaging device 10 (step S1). In the following description, the image acquired in step S1 will be referred to as a target image for convenience.

Here, in this embodiment, the imaging device 10 operates continuously during a time period when a person may enter or leave the room, but if the image captured by the imaging device 10 includes a person, In some cases, there are no people included.

Therefore, it is determined whether or not a person is included in the above-mentioned target image (step S2). Note that the process in step S2 may be executed by, for example, performing image processing such as edge extraction on the target image.

If it is determined that the target image does not include a person (NO in step S2), the process shown in FIG. 7 is ended.

On the other hand, if it is determined that the target image includes a person (YES in step S2), the face authentication processing unit 202 determines whether the target image includes a person based on the face authentication data stored in the storage unit 205. A face recognition process is executed for the person (hereinafter referred to as the target person) who is the target person (step S3). In this case, the face recognition processing unit 202 extracts data representing the feature points of the target person's face (hereinafter referred to as feature point data of the target person) from the area corresponding to the face of the target person in the target image, and Face authentication processing is executed by comparing the data with face authentication data stored in the storage unit 205.

Next, by executing face authentication processing in step S3, it is determined whether or not face authentication for the target person has been successful (step S4). In face recognition processing, if the target person's feature point data matches the face authentication data stored (registered) in the storage unit 205, it is determined that face authentication has been successful, and the target person's feature point data is stored. If the face authentication data does not match the face authentication data stored (registered) in the unit 205, it is determined that the face authentication has failed. In other words, if the target person's feature point data has already been registered in the storage unit 205 as face authentication data, face authentication is successful, and the target person's feature point data has already been registered in the storage unit 205 as face authentication data. Without it, facial recognition will fail.

If it is determined that the face authentication has failed (NO in step S4), the target person's feature point data is not registered as face authentication data in the storage unit 205, so a face authentication data registration process is executed (step S5). ). Details of the face authentication data registration process will be described later.

On the other hand, if it is determined that the face authentication is successful (YES in step S4), the process shown in FIG. 7 is ended.

Here, as will be described later, the face authentication data is stored in the storage unit 205 in association with identification information, and the face authentication processing unit 202 stores the face authentication data in association with the target person's feature point data. The identification information stored in the unit 205 can be acquired as identification information for identifying the target person in the target image.

The identification information for identifying the target person acquired in this way is used to manage entry and exit of the target person into and out of the work area. Specifically, when the face authentication is successful as described above, management information indicating the entry time, room exit time, etc. is stored in the storage unit 205 or the like in association with the identification information for identifying the target person. Furthermore, in a case where the door where the above-described imaging device 10 is installed is locked, control may be performed to unlock the door when face authentication is successful.

Note that the process shown in FIG. 7 is continuously and repeatedly executed while the power of the imaging device 10 is on.

Next, an example of the processing procedure of the above-described face authentication data registration process (the process of step S5 shown in FIG. 7) will be described with reference to the flowchart of FIG. 8.

Here, in this embodiment, it is assumed that each person whose entry and exit to the work area is managed is given a color bit code representing identification information for identifying the person, as described above. According to this, as described above, a person approaches the door provided near the imaging device 10 (that is, approaches the door to enter the work area or approaches the door to exit the work area). If the color bit code exists, the image (target image) acquired in step S1 shown in FIG. 7 includes a color bit code as shown in FIG.

In this case, the code authentication processing unit 203 executes code authentication processing (decoding processing) for the color bit code included in the target image (step S11). This code authentication process will be specifically explained below.

First, the code authentication processing unit 203 executes a process of dividing the target image into each color area (hereinafter referred to as color area dividing process). Here, the target image is generally composed of (pixels that display) various colors including the background, and the patterns thereof are also various. For this reason, in color region segmentation processing, the colors in this target image are segmented into red, green, blue, and achromatic colors in the color space, and the color of each pixel is applied to one of the regions (color equalization). processing) is performed. That is, in the color area segmentation process, a labeling process is executed for each pixel in the target image.

Note that the above-mentioned red, green, and blue are colors defined as colors assigned to each cell configuring a color bit code (hereinafter referred to as constituent colors), but in color area classification processing, for example, lighting, If a color falls within a certain range that can be recognized as one of these constituent colors on the color space, taking into account coloring, fading, etc., then that color (pixel thereof) shall be classified as a constituent color. That is, for example, when dividing a red area, all pixels displaying a certain range of colors centered around red are recognized as the red area. The same applies to the case where the green and blue regions are divided.

Furthermore, achromatic colors are colors other than those recognized as red, green, and blue in the color area classification process.

Further, as described above, the target image is subjected to color equalization processing, but generally, the target image often contains noise components. It is preferable to remove the noise by performing a noise removal process such as matching the color of the surrounding area or averaging the color variation of a minute portion corresponding to this noise.

Next, the code authentication processing unit 203 generates a color bit code area (hereinafter, code (hereinafter referred to as code extraction processing). In this code cutting process, a code area is cut out based on the surrounding colors of each color area (for example, the arrangement of areas of other constituent colors and achromatic areas, etc.), the number of cells that make up the color bit code, etc. . The code area cut out by the code cutting process is represented by, for example, coordinate values (XY coordinate values) on the image.

Note that the color area segmentation process and code cutout process described above are disclosed in, for example, Japanese Patent Application Laid-Open No. 2008-287414, so a detailed explanation thereof will be omitted here.

Next, the code authentication processing unit 203 performs color matching based on the color transitions in the plurality of color regions arranged in the code region cut out from the target image by the code cutout processing (that is, the order of the plurality of color regions). Decode bitcode. According to this, identification information (hereinafter referred to as , object identification information and notation) are obtained. Note that the target identification information acquired by the code authentication processing unit 203 is identification information for identifying a person (target person) included in the target image.

When target identification information is acquired by executing the code authentication process described above, the code authentication processing unit 203 stores the target image in the storage unit 205 in association with the target identification information (step S12).

Next, the face recognition data generation unit 204 determines whether the number of images stored in the storage unit 205 in association with the target identification information has reached a predetermined value (hereinafter referred to as a threshold value). (Step S13). In other words, in step S13, it is determined whether the number of times the face authentication data registration process is performed after an image including the target person is acquired has reached a predetermined number of times.

If it is determined that the number of images has reached the threshold (YES in step S13), the face recognition data generation unit 204 generates an area (face area) that includes the face of the person who appears most frequently in the image. , from each of the images (step S14).

Here, as described above, the image stored in the storage unit 205 in association with the target identification information includes a target person to which a color bit code representing the target identification information is attached. There is a possibility that people other than people are also included. Therefore, by extracting the area that includes the face of the person with the highest appearance frequency as the face area of the target person in step S14, it is possible to exclude people other than the target person in generating face authentication data.

Note that each person included in the image can be identified (distinguished) by comparing the feature points of the person's face.

When the process of step S14 is executed, the face authentication data generation unit 204 generates face authentication data representing the feature points of the target person's face (that is, the target person's face authentication data) (step S15). The face authentication data generated in step S15 is stored (registered) in the storage unit 205 in association with the target identification information described above, and can be used in the process of step S3 (face authentication process) shown in FIG. 7.

On the other hand, if it is determined in step S13 that the number of images has not reached the threshold (NO in step S13), the processes in steps S14 and S15 are not executed, and the face authentication data registration process shown in FIG. 8 is ended. .

According to the facial recognition data registration process described above, when the number of images containing the target person reaches a threshold (that is, the same number of images as the threshold have been collected), the facial recognition data of the target person is acquired using the image. It can be automatically generated and registered.

Note that here we have explained the case where the target identification information is acquired by executing the code authentication process, but for example, if the person included in the target image does not have a color bit code attached, Even if code authentication processing is executed for the user, identification information cannot be obtained. In such a case, the processes after step S13 are not executed, and the face authentication data registration process shown in FIG. 8 is ended.

In addition, when the object identification information is acquired in step S11 described above, management information indicating the entry time or exit time, etc. is stored in association with the object identification information, as in the case where the above-mentioned face authentication is successful. The information is stored in the section 205 or the like. Further, in a case where the door where the imaging device 10 is installed is locked, control may be executed to unlock the door when the object identification information is acquired.

As described above, in this embodiment, an image (first image) including an optical recognition code representing identification information for identifying the target person (subject) is acquired, and the acquired image is Code authentication processing is executed using the optical recognition code (optical recognition code attached to the subject) included in the image, and identification information represented by the optical recognition code is obtained by executing the code authentication processing. If the image is acquired, the image is stored in the storage unit 205 in association with the acquired identification information. Furthermore, in the present embodiment, when an image (second image) including the target person is further acquired after the image is stored in the storage unit 205, the second image is generated using the image stored in the storage unit 205. Based on the face authentication data, face authentication processing is performed on the target person included in the acquired image.

In this embodiment, with such a configuration, images necessary for facial recognition are collected while performing code authentication (that is, while using the authentication system), and facial recognition is performed using the collected images. This eliminates the need to register in advance the image of the person who will use the authentication system. According to this, it is possible to realize face authentication without pre-registration, and it is possible to reduce the burden of implementing a face authentication mechanism. In other words, in this embodiment, it is possible to lower the hurdles for introducing face recognition technology, and to start using the authentication system simply by issuing general identification information (ID).

Note that the authentication device 20 according to the present embodiment can be used to manage entry and exit of a person (for example, an employee, etc.) into a work area, as described above. In this case, when an employee whose facial recognition data is registered enters and leaves the room, the entry and exit of the employee is controlled through facial recognition processing, and the entry and exit of the employee whose facial recognition data is not registered is controlled. If this is done, entry and exit of the employee can be controlled by code authentication processing.

In addition, in this embodiment, the description has been made assuming that a color bit code is attached to a person, but as described above, for a person whose face recognition data is registered, the face recognition process is executed and the person is transferred to the work area. Since it is possible to control the entry and exit of a person, the person in question does not need to be assigned a color bit code.

Furthermore, we have explained that entry and exit from the work area is controlled by executing face recognition processing for people whose face recognition data has been registered, but for example, in environments where security measures (strengthening) are required, face recognition A configuration may be adopted in which both the authentication process and the code authentication process are executed. Generally, a two-factor authentication method is sometimes adopted for security measures, but in this embodiment, even if a two-factor authentication method consisting of face recognition and code authentication is adopted, for example, multiple factors can be used. The complicated work (man-hours) of individually generating authentication data using a separate device or the like is unnecessary, and the burden on the administrator of the authentication device 20 (authentication system) can be reduced.

Note that code authentication processing generally has high accuracy, while face authentication processing tends to have low accuracy. Therefore, if the person included in the image has an optical recognition code attached, code authentication processing is executed, and if the person does not have an optical recognition code attached, facial recognition processing is executed. It may be configured as follows. In addition, for example, while controlling the entry and exit of people into a work area based on the results of code authentication processing, which is basically highly accurate, it is also possible to output warnings etc. based on the results of facial recognition processing, which is less accurate. It may also be a configuration. By setting criteria levels for a plurality of authentication processes (authentication methods) in this way, it is possible to perform processing without slowing down the authentication speed of the authentication device 20 (authentication system) as a whole.

Furthermore, in this embodiment, by executing the above-described face authentication data registration process multiple times, the person who appears most frequently (target person) among the people included in the plurality of images stored in the storage unit 205 is identified. By generating face recognition data based on (the image of) the face area, even if multiple people (faces) are reflected in the image, highly accurate face recognition data of the target person can be generated. It becomes possible to generate. Note that the greater the number of times the facial authentication data registration process is executed before generating the facial authentication data (that is, the number of images stored in the storage unit 205), the more accurate the facial authentication data can be generated. If the number of times is large, it takes time to generate face authentication data (that is, to get into a state where face authentication can be performed). Therefore, the number of times the facial recognition data registration process is executed depends on the number of people using the authentication system and the environment in which the authentication system is used (in other words, the degree of accuracy required of the authentication system). , may be selected (determined) as appropriate.

In addition, in this embodiment, for example, when face authentication data of a target person is generated (registered), it is possible to perform face authentication processing for the target person based on the face authentication data. The authentication data may be configured to be updated periodically. Specifically, even after face recognition data is generated (that is, when face recognition is successful in the face recognition process executed in step S3 shown in FIG. 7), the process shown in step S5 is periodically performed. The face authentication data may be generated again by executing (face authentication data registration process).

In systems where general images are registered in advance, ambiguity remains in the facial recognition data (data representing facial feature points) generated from the images, but using the authentication system as described above According to a configuration that acquires images containing (the face) of the target person every day and continues to periodically update facial recognition data based on such images, the accuracy of facial recognition data (that is, face recognition processing) is improved. It becomes possible to do so.

Note that in the case of a configuration in which face authentication data registration processing is further executed after face authentication data is generated, each time a new image is stored in the storage unit 205, from the viewpoint of the capacity of the storage unit 205. The oldest image among the images already stored in the storage unit 205 (images associated with the target identification information) may be deleted from the storage unit 205. In order to realize such a configuration, each image may be stored in the storage unit 205 in association with the date and time when the image was captured by the imaging device 10.

Furthermore, in this embodiment, face authentication data is generated based on an image captured in the same environment (for example, angle, etc.) as an image captured when face authentication is actually performed. It is expected that accuracy will improve.

In addition, in this embodiment, the authentication device 20 (authentication system) has been described as being used when managing the entry and exit of a person to the work area, but the image captured when managing the entry and exit of a person The face authentication data generated based on the information may be used for personal authentication (face authentication) when using in-house infrastructure.

Further, in this embodiment, the color bit code is used as the optical recognition code, but other optical recognition codes (automatic recognition technology) such as barcodes can be used as the optical recognition code. I don't mind if it is used.

Furthermore, in this embodiment, the code authentication process using a color bit code (optical recognition code) has been described as being executed, but instead of the code authentication process, for example, authentication using a fingerprint authentication process, RFID, etc. It is possible to realize the authentication device 20 according to this embodiment even with a configuration in which an image is captured at the timing when processing is executed. In other words, in this embodiment, when an authentication process other than face recognition process is executed for a person using the authentication system, an image including the person is acquired (automatically registered), and the image is used to identify the person's face. Any configuration that executes authentication processing may be used.

Furthermore, although the present embodiment has been described assuming that face authentication processing is executed, this embodiment also includes authentication processing based on images (still images or moving images) corresponding to face authentication processing (e.g., foot recognition processing). The present invention may also be applied to an authentication device that executes (e.g., user authentication).

Furthermore, although the present embodiment has been described assuming that the subject whose image is captured by the imaging device 10 is a person, the present embodiment is based on the above-described face authentication process or an image equivalent to the face authentication process. The present invention may be applied to monitoring objects other than people (for example, animals) as long as they can be subject to authentication processing.

Further, in this embodiment, the authentication device 20 is described as being realized as one device, but the authentication device 20 according to this embodiment may be realized by a plurality of devices (devices). In this case, for example, the face authentication process and the code authentication process may be executed in separate devices. Furthermore, some or all of the units 201 to 205 shown in FIG. 6 may be included in the imaging device 10.

Note that the method described in the above-described embodiments can be applied to magnetic disks (floppy (registered trademark) disks, hard disks, etc.), optical disks (CD-ROM, DVD, etc.), magneto-optical disks (MO ), it can also be stored and distributed in a storage medium such as a semiconductor memory.

Further, this storage medium may be in any storage format as long as it can store a program and is readable by a computer.

In addition, the OS (operating system), MW (middleware) such as database management software, network software, etc. that are running on the computer based on the instructions of the program installed on the computer from the storage medium realize this embodiment. A part of each process may be executed.

Furthermore, the storage medium in the present invention is not limited to a medium independent of a computer, but also includes a storage medium in which a program transmitted via a LAN, the Internet, etc. is downloaded and stored or temporarily stored.

Further, the number of storage media is not limited to one, and a case where the processing in this embodiment is executed from a plurality of media is also included in the storage medium in the present invention, and the medium configuration may be any configuration.

Note that the computer in the present invention executes each process in the present embodiment based on a program stored in a storage medium, and may include a single device such as a personal computer, or a system in which multiple devices are connected via a network. It may be any configuration such as.

Furthermore, the computer in the present invention is not limited to a personal computer, but also includes arithmetic processing units, microcomputers, etc. included in information processing equipment, and is a general term for devices and devices that can realize the functions of the present invention through programs. .

It should be noted that the present invention is not limited to the above-described embodiments as they are, and can be embodied by modifying the constituent elements within the scope of the invention at the implementation stage. Moreover, various inventions can be formed by appropriately combining the plurality of components disclosed in the above embodiments. For example, some components may be deleted from all the components shown in the embodiments. Furthermore, components from different embodiments may be combined as appropriate.

DESCRIPTION OF SYMBOLS 10... Imaging device, 20... Authentication device, 21... Bus, 22... Non-volatile memory, 23... CPU, 24... Main memory, 25... Wireless communication device, 30... Network, 110... Optical recognition code, 120... Cell, 201... Image acquisition section, 202... Face authentication processing section, 203... Code authentication processing section, 204... Face authentication data generation section, 205... Storage section.

Claims (3)

a first acquisition means for acquiring a first image including the subject to which an optical recognition code representing identification information for identifying the subject is attached;
code authentication means for performing code authentication processing on the optical recognition code included in the acquired first image;
When identification information represented by an optical recognition code included in the first image is obtained by executing the code authentication process, the first image is stored in association with the obtained identification information. storage means;
determining means for determining whether the number of the plurality of first images reaches a threshold value when the plurality of first images are stored in the storage means;
When it is determined that the number of the plurality of first images has reached a threshold, a generating means for generating face authentication data based on the plurality of first images;
a second acquisition means for acquiring a second image including the subject;
An authentication device comprising: face authentication means for performing face authentication processing on a subject included in the second image using the generated face authentication data when the second image is acquired. acquiring a first image including the subject to which an optical recognition code representing identification information for identifying the subject is attached;
performing code authentication processing on the optical recognition code included in the acquired first image;
When identification information represented by an optical recognition code included in the first image is obtained by executing the code authentication process, storage means stores the first image in association with the obtained identification information. a step of storing it in
When a plurality of first images are stored in the storage means, determining whether the number of the plurality of first images reaches a threshold;
If it is determined that the number of the plurality of first images has reached a threshold, generating face authentication data based on the plurality of first images;
acquiring a second image including the subject;
A method comprising: when the second image is acquired, performing face authentication processing on a subject included in the second image using the generated face authentication data . A program executed by a computer,
to the computer;
acquiring a first image including the subject to which an optical recognition code representing identification information for identifying the subject is attached;
performing code authentication processing on the optical recognition code included in the acquired first image;
When identification information represented by an optical recognition code included in the first image is obtained by executing the code authentication process, storage means stores the first image in association with the obtained identification information. a step of storing it in
When a plurality of first images are stored in the storage means, determining whether the number of the plurality of first images reaches a threshold;
If it is determined that the number of the plurality of first images has reached a threshold, generating face authentication data based on the plurality of first images;
acquiring a second image including the subject;
and, when the second image is acquired, performing a face authentication process on a subject included in the second image using the generated face authentication data .

Images