JP2014186580A - Authentication device, imaging device, registration method of authentication data, program, and storage medium - Google Patents

Abstract

An authentication apparatus capable of easily recognizing a group in which image data is registered when the user registers image data.
An authentication apparatus includes a storage unit that stores a plurality of first feature information and a plurality of first image data of the same subject in a plurality of groups, and a second image of the same subject acquired by an imaging unit. A calculation processing means for comparing the second feature information extracted from the data and the plurality of first feature information to calculate the similarity between the second feature information and each of the plurality of first feature information; and a second image Display means for displaying the data in association with the group having the highest similarity among the plurality of groups.
[Selection] Figure 2

Description

  The present invention relates to an authentication apparatus that performs personal authentication using authentication data.

  2. Description of the Related Art Conventionally, an authentication device that performs personal authentication by storing authentication data such as a plurality of human faces in advance as dictionary data, and comparing newly acquired data with data stored as dictionary data It has been known. When a face image is used for personal authentication, the accuracy of the personal authentication varies depending on the orientation and expression of the face and the captured light environment. For this reason, in order to improve the accuracy of personal authentication, it is necessary to store a plurality of types of face images in advance.

  In Patent Document 1, a face image is taken under a plurality of different light environments, and the taken face image is stored in dictionary data in advance, so that personal authentication can be performed with high accuracy even in different use environments. A possible personal authentication system is disclosed. Patent Document 2 discloses a method of registering face information by associating a face detected in the past by face detection with a past detection history.

Japanese Patent No. 04057501 JP 2007-6033 A

  According to the configurations of Patent Documents 1 and 2, it is possible to improve the accuracy of personal authentication by photographing a plurality of face images and registering them in dictionary data. Further, when registering a plurality of face images, a method of classifying the face images into subgroups to avoid erroneous authentication is also conceivable. However, in the configurations of Patent Documents 1 and 2, how to register the face image (face information) to be registered at the time of registration of the face image, that is, what kind of face image should be registered, It is difficult for the user to grasp.

  Therefore, the present invention provides an authentication device, an imaging device, an authentication data registration method, a program, and a storage medium that can easily recognize a group in which image data is registered when a user registers image data. .

  An authentication device according to one aspect of the present invention includes a storage unit that stores a plurality of first feature information and a plurality of first image data of the same subject in a plurality of groups, and the same subject acquired by an imaging unit The second feature information extracted from the second image data is compared with the plurality of first feature information, and the similarity between the second feature information and each of the plurality of first feature information is calculated. Processing means and display means for displaying the second image data in association with the group having the highest similarity among the plurality of groups.

  An imaging device as another aspect of the present invention includes the authentication device.

  According to another aspect of the present invention, there is provided a method for registering authentication data, wherein the authentication image data is stored in a storage unit that stores a plurality of first feature information and a plurality of first image data of the same subject in a plurality of groups. A method of registering authentication data to be registered, the step of acquiring second image data of the same subject by an imaging unit, second feature information extracted from the second image data, and the plurality of first feature information Comparing the second feature information with each of the plurality of first feature information, and calculating the second image data with the highest similarity among the plurality of groups. And displaying in association with the higher group.

  A program according to another aspect of the present invention is configured to cause a computer to execute the authentication data registration method.

  A storage medium according to another aspect of the present invention stores the program.

  Other objects and features of the present invention are illustrated in the following examples.

  According to the present invention, an authentication device, an imaging device, an authentication data registration method, a program, and a storage medium that can easily recognize a group in which image data is registered when a user registers image data are provided. can do.

It is a block diagram of the imaging device in each embodiment. It is a flowchart of the registration method of the data for authentication in 1st Embodiment. It is explanatory drawing of the registration method of the data for authentication in each embodiment. It is a flowchart of the data registration method for authentication in 2nd Embodiment. It is a flowchart of the data registration method for authentication in 3rd Embodiment. It is explanatory drawing of another data registration method for authentication in each embodiment. It is explanatory drawing of the database in each embodiment.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

(First embodiment)
First, the configuration of the imaging apparatus according to the first embodiment of the present invention is described with reference to FIG. FIG. 1 is a block diagram of an imaging apparatus 100 (digital camera) in the present embodiment. The imaging device 100 has a function as an authentication device (personal authentication device).

  In FIG. 1, reference numeral 103 denotes a photographing lens including a focus lens, and 101 denotes a shutter having an aperture function. Reference numeral 122 denotes an imaging unit. The imaging unit 122 includes a photoelectric conversion element such as a CCD or a CMOS element that converts an optical image (subject image) into an electrical signal (analog signal). Reference numeral 123 denotes an A / D converter that converts an analog signal into a digital signal. The A / D converter 123 is used to convert an analog signal output from the imaging unit 122 into a digital signal. Reference numeral 102 denotes a barrier. The barrier 102 covers the imaging lens 103 and the imaging unit 122 in the imaging apparatus 100, thereby preventing the imaging system including the imaging lens 103, the shutter 101, and the imaging unit 122 from being dirty or damaged.

  Reference numeral 124 denotes an image processing unit. The image processing unit 124 performs various types of resizing processing such as predetermined pixel interpolation and reduction, and color conversion processing on the image data from the A / D converter 123 or the image data from the memory control unit 115. Perform image processing. The image processing unit 124 performs predetermined calculation processing using the captured image data. The system control unit 150 performs exposure control and distance measurement control based on the calculation result obtained by the image processing unit 124. Thereby, AF (autofocus) processing, AE (automatic exposure) processing, and EF (flash pre-emission) processing of the TTL (through-the-lens) method are performed. Further, the image processing unit 124 performs predetermined calculation processing using the captured image data, and also performs TTL AWB (auto white balance) processing based on the obtained calculation result.

  Data (image data) output from the A / D converter 123 is directly written into the memory 132 via the image processing unit 124 and the memory control unit 115 or via the memory control unit 115. The memory 132 stores image data obtained from the imaging unit 122 and converted into a digital signal by the A / D converter 123 and image data to be displayed on the display unit 128. The memory 132 has a storage capacity sufficient to store a predetermined number of still images, a moving image and audio for a predetermined time. The memory 132 also serves as an image display memory (video memory).

  Reference numeral 113 denotes a D / A converter. The D / A converter 113 converts the image display data stored in the memory 132 into an analog signal and supplies the analog signal to the display unit 128. With this configuration, the display image data written in the memory 132 is displayed on the display unit 128 via the D / A converter 113. The display unit 128 performs display in accordance with the analog signal from the D / A converter 113 on a display such as an LCD. As will be described later, the display unit 128 displays the second image data (image data to be registered) in association with the group having the highest similarity among the plurality of groups.

  The nonvolatile memory 156 is an electrically erasable and recordable memory. As the nonvolatile memory 156, for example, an EEPROM is used. The nonvolatile memory 156 stores constants and programs for operating the system control unit 150. Here, the program is a program for executing an authentication data registration method described later.

  Reference numeral 150 denotes a system control unit that controls the entire imaging apparatus 100. The system control unit 150 implements each process of this embodiment to be described later by executing a program stored in the nonvolatile memory 156. Reference numeral 152 denotes a system memory. For example, a RAM is used as the system memory 152. In the system memory 152, constants and variables for operation of the system control unit 150, programs read from the nonvolatile memory 156, and the like are expanded. Further, the system control unit 150 controls display of image data and the like by controlling the memory 132, the D / A converter 113, the display unit 128, and the like.

  The mode switch 160, the shutter button 161, the first shutter switch 162, the second shutter switch 163, and the operation unit 170 are operation means for inputting various operation instructions to the system control unit 150. The mode switch 160 switches the operation mode of the system control unit 150 so as to set, for example, one of a still image recording mode, a moving image recording mode, and a reproduction mode. The mode changeover switch 160 is also used for selecting a registration mode of an authentication face image described later.

  The first shutter switch 162 is turned on when a shutter button 161 provided in the imaging apparatus 100 is being operated, so-called half-press (shooting preparation instruction), and generates a first shutter switch signal SW1. The shutter switch signal SW1 starts operations such as AF (auto focus) processing, AE (auto exposure) processing, AWB (auto white balance) processing, and EF (flash pre-flash) processing. The second shutter switch 163 is turned on when the operation of the shutter button 161 is completed, so-called full press (shooting instruction), and generates a second shutter switch signal SW2. In response to the second shutter switch signal SW2, the system control unit 150 starts a series of shooting processing operations from reading a signal from the imaging unit 122 to writing image data on the recording medium 200.

  Each operation member of the operation unit 170 is appropriately assigned a function for each scene by selecting and operating various function icons displayed on the display unit 128, and functions as various function buttons. Examples of the function buttons include a menu button, an end button, a return button, an image advance button, a jump button, a narrowing button, and an attribute change button. For example, when a menu button is pressed, various settable menu screens are displayed on the display unit 128. The user can make various settings intuitively by using the menu screen displayed on the display unit 128, the four-way button, and the SET button.

  Reference numeral 180 denotes a power control unit. The power supply control unit 180 includes a battery detection circuit, a DC-DC converter, a switch circuit that switches a block to be energized, and the like, and detects whether or not a battery is attached, the type of battery, and the remaining battery level. The power supply control unit 180 controls the DC-DC converter based on the detection result and an instruction from the system control unit 150, and supplies a necessary voltage to each unit including the recording medium 104 for a necessary period.

  Reference numeral 130 denotes a power supply unit. The power supply unit 130 includes a primary battery such as an alkaline battery or a lithium battery, a secondary battery such as a NiCd battery, a NiMH battery, or a Li battery, or an AC adapter. Reference numeral 118 denotes an interface with the recording medium 104. The recording medium 104 is a semiconductor memory having a memory card, a magnetic disk having a hard disk, or the like. Reference numeral 172 denotes a power switch that switches the power on and off.

  In the present embodiment, the imaging apparatus 100 can perform shooting using central one-point AF or face AF. Here, the central one-point AF is to perform AF with respect to one central position in the shooting screen. The face AF is to perform AF on the face in the shooting screen detected by the face detection function.

  Reference numeral 190 denotes a face detection unit. The face detection unit 190 detects a feature portion of a person's face by detecting edges such as eyes and mouth from a subject (person) included in the image data. That is, the face detection unit 190 detects the data of the image area as face image data from the image area (face position and size) of the image data occupied by the face and the likelihood of the face (facial reliability). Perform processing and identification processing. The face image data is stored in the memory 132 as an image to be displayed on the display unit 128.

  Reference numeral 191 denotes a feature information extraction processing unit. The feature information extraction processing unit 191 extracts feature information (second feature information) necessary for authentication (personal authentication) from the face image data detected by the face detection unit 190. The characteristic information necessary for personal authentication is to set a small area centered on the organs of eyes, nose, and mouth from the face area, and calculate an LBP (Local Binary Pattern) for the set small area. It is information acquired by this. Since LBP is described in detail in, for example, Japanese Patent Application Laid-Open No. 2009-086926, description thereof is omitted here. In this embodiment, the feature information (first feature information, second feature information) is feature information of the face of the same subject.

  Reference numeral 192 denotes a dictionary data storage unit (storage means). The dictionary data storage unit 192 stores dictionary data (authentication data) used at the time of collation (at the time of authentication). The dictionary data includes feature information (first feature information) calculated by the feature information extraction processing unit 191. In the present embodiment, the dictionary data storage unit 192 stores a plurality of first feature information and a plurality of first image data of the same subject in a plurality of groups. Here, the dictionary data storage unit 192 stores a plurality of first feature information and a plurality of first image data in association with each other. Further, when the feature information is newly stored in the dictionary data storage unit 192, the face image data (second image data) detected by the face detection unit 190 is stored in association with the feature information (second feature information). The

  Reference numeral 193 denotes a similarity calculation processing unit (calculation processing means). The similarity calculation processing unit 193 includes feature information extracted by the feature information extraction processing unit 191 from the face image data detected by the face detection unit 190, and feature information of dictionary data stored in the dictionary data storage unit 192. Are compared by pattern matching, and the similarity is calculated. That is, the similarity calculation processing unit 193 includes the second feature information extracted from the image data (second image data) of the same subject acquired by the imaging unit 122 (imaging unit) and a plurality of first feature information (dictionary data storage). The first feature information stored in the unit 192 is compared. Then, the similarity calculation processing unit 193 calculates the similarity between the second feature information (registration information of image data to be registered) and each of the plurality of first feature information.

  Reference numeral 194 denotes an authentication determination unit. The authentication determination unit 194 compares the similarity calculated by the similarity calculation processing unit 193 with a preset authentication threshold (predetermined threshold). When the similarity is equal to or greater than the threshold, the authentication determination unit 194 identifies that the face image detected by the face detection unit 190 is a person stored in the dictionary data storage unit 192, that is, determines that personal authentication has succeeded. .

  Reference numeral 195 denotes a classification information setting unit (determination control means). The classification information setting unit 195 controls to classify the plurality of first feature information and the plurality of first image data (face image data) related to the same subject (the same person) into a plurality of groups (a plurality of subgroups). . When the feature information is stored in the dictionary data storage unit 192, the classification information setting unit 195 includes the similarity (each of a plurality of similarities) calculated by the similarity calculation processing unit 193 and a threshold for classification (predetermined threshold). And compare. When at least one similarity is greater than or equal to the threshold, the classification information setting unit 195 associates the feature information to be stored in the dictionary data storage unit 192 with the subgroup having the highest similarity. On the other hand, when all the similarities are less than the threshold, a new group (new subgroup) is created, and feature information to be registered in the dictionary data storage unit 192 is associated with the new subgroup.

  The configuration of the imaging apparatus 100 described with reference to FIG. 1 is an example, and the present embodiment is not limited to the configuration illustrated in FIG. 1 as long as the operation described below can be performed.

  Next, with reference to FIG. 2, FIG. 3, and FIG. 7, the display processing (control method of the authentication device) at the time of dictionary data registration by the imaging device 100 will be described. FIG. 2 is a flowchart of the display process (control method of the authentication device) at the time of dictionary data registration. Each step in FIG. 2 is mainly executed based on a command from the system control unit 150 of the imaging apparatus 100 (authentication apparatus). FIG. 3 is an explanatory diagram of display processing at the time of dictionary data registration. FIG. 7 is an explanatory diagram of the database 700 (dictionary data) stored in the dictionary data storage unit 192.

  The database 700 of this embodiment stores (registers) a registered name 701, a subgroup 702 (group), feature information 703, and face image data 704 (image data). In FIG. 7, information regarding two subjects (persons “A” and “B”) is stored as a registered name 701. The database 700 also includes a registered name 701, face image data 704 detected by the face detection unit 190, feature information 703 extracted by the feature information extraction processing unit 191, and subgroups set by the classification information setting unit 195. 702 are stored in association with each other. For example, a set of five feature information 703 and face image data 704 is stored as data related to the person A. Further, the data related to the person A is classified into three subgroups (subgroups 1, 2, and 3) according to the similarity of the feature information 703. Sub-group 1 stores two feature information, sub-group 2 stores one feature information, and sub-group 3 stores two feature information in association with corresponding face image data.

  First, in step S201 in FIG. 2, when the user selects the registration mode of the authentication face image, the registration mode starts. In step S 202, the user is allowed to select a subject (person) to be registered in the dictionary data from among the registered names 701 in the database 700 stored in the dictionary data storage unit 192.

  Subsequently, in step S203, face image data associated with the registered name (person) selected in step S202 is read from the dictionary data storage unit 192. However, when face image data is stored in the memory 132, the face image data is read from the memory 132. The read image (face image data) is combined with the EVF display image by processing in the memory control unit 115 and the image processing unit 124. The composite image is displayed on the display unit 128 via the D / A conversion unit 113 as shown in FIG.

  In FIG. 3A, 311, 312, 321, 331, and 332 are face image data read from the dictionary data storage unit 192 (or the memory 132), respectively. The face image data 311 and 312 are associated with the subgroup 310 (ID1), the face image data 321 is associated with the subgroup 320 (ID2), and the face image data 331 and 332 are associated with the subgroup 330 (ID3). In the present embodiment, the sub-group (group) in which the face image data of the person 300 registered in the dictionary data storage unit 192 (or the memory 132) is associated with the classification information setting unit 195 together with the subject (person 300) currently being photographed. ) Is displayed.

  Next, in step S204, the face detection unit 190 performs face detection processing on the face included in the captured image (image data). The face detected at this time becomes a face stored in association with the feature information in the dictionary data storage unit 192, and as shown in FIG. 3B, the face of the person 300 is detected as a face to be stored together with the feature information. . In the present embodiment, a face frame 340 is displayed on the face detected by the face detection unit 190 as shown in FIG.

  Subsequently, in step S205, the system control unit 150 determines whether or not the user has input (designated) a detected face registration instruction using a predetermined operation member. When a registration instruction is input by the user, the process proceeds to step S206. On the other hand, if the registration instruction is not input by the user, the process returns to step S204, and the face detection unit 190 performs the face detection process again. In step S206, the feature information extraction processing unit 191 extracts feature information to be stored in the dictionary data storage unit 192 from face image data (image data) instructed to be registered by the user. Here, the feature information extracted by the feature information extraction processing unit 191 is set as second feature information.

  In step S207, one feature information is selected from a plurality of feature information (a plurality of first feature information) extracted from the face of the person 300 stored in the dictionary data storage unit 192. For example, as shown in FIG. 3B, one feature information (first feature information) is selected from the subgroups 310, 320, and 330 of the person 300 to be registered.

  Next, in step S208, the similarity calculation processing unit 193 calculates the one feature information (first feature information) selected from the dictionary data storage unit 192 and the feature information extraction processing unit 191 in step S206. The degree of similarity with the second feature information is calculated. The similarity calculation processing unit 193 includes all of the first feature information extracted from the face of the person 300 stored in the dictionary data storage unit 192 and the second feature information (registration) extracted in step S206. The similarity to the feature information extracted from the target face is calculated.

  In step S209, the system control unit 150 has a similarity to the second feature information for each of all the feature information (a plurality of first feature information) of the person 300 stored in the dictionary data storage unit 192. It is determined whether or not it has been calculated. If all the similarities are not calculated, steps S207 to S209 are repeated until all similarities are calculated. For example, in FIG. 3B, the feature information of the person 300 (second feature information) and each of the plurality of feature information (plural first feature information) classified into the subgroups 310, 320, and 330 All similarities are calculated.

  After calculating all the similarities, the process proceeds to step S210. In step S210, the system control unit 150 selects the highest similarity from the plurality of similarities calculated in step S208. In addition, the system control unit 150 selects the feature information with the highest similarity (the subgroup related to the feature information with the highest similarity). For example, in FIG. 3B, the feature information having the highest similarity with the feature information (second feature information) of the person 300 extracted in step S206 is the feature information of the image data classified into the subgroup 310. Suppose that

  Subsequently, in step S211, the classification information setting unit 195 compares the similarity (highest similarity) obtained in step S210 with the classification threshold (first threshold). If it is determined that the highest similarity is greater than the threshold for classification (first threshold), in step S212, the classification information setting unit 195 detects the detected face (in the subgroup including the feature information with the highest similarity ( Second image data to be registered) is registered. That is, the second image data is registered in association with the subgroup including the feature information having the highest similarity. Thereby, the display unit 128 displays the second image data (image data to be registered) in association with the subgroup having the highest similarity (the group having the highest similarity) among the plurality of subgroups (the plurality of groups). Is done.

  In step S213, the system control unit 150 recognizes to the user that the detected face (image data to be registered) is registered in the subgroup 310, as shown in FIGS. 3 (c) and 3 (d). It is displayed on the display unit 128 as possible. For example, as shown in FIG. 3C, an arrow 341 is added to the face frame 340 so that the arrow 341 indicates the direction of the subgroup 310. Alternatively, as shown in FIG. 3D, the detected face is inserted into a frame indicating the subgroup 310.

  On the other hand, if the highest similarity is not more than the threshold for classification (below the first threshold) in step S211, the classification information setting unit 195 creates a new subgroup (new group) in step S214. In step S215, the system control unit 150 (classification information setting unit 195) registers the detected face (second image data to be registered) in the new subgroup. Subsequently, in step S216, the system control unit 150 displays on the display unit 128 so that the user can recognize that the detected face is registered in the new subgroup, as shown in FIG. .

  In step S217, the system control unit 150 determines whether to end the registration mode. If image data is to be continuously registered, the process returns to step S204, and face detection processing by the face detection unit 190 is performed. On the other hand, if it is not necessary to register image data continuously, this flow ends.

  According to the present embodiment, in an authentication apparatus that classifies image data to be registered (detected faces) into a plurality of subgroups (groups) to improve authentication accuracy, the user has a face at the timing designated by the user himself / herself. Which subgroup is registered can be easily identified. For this reason, the user can grasp the trend regarding which subgroup the face specified for registration is classified into, and can perform the registration process effective for improving the authentication accuracy more smoothly. is there.

(Second Embodiment)
Next, with reference to FIG. 4, a display process (control method of the authentication device) at the time of dictionary data registration according to the second embodiment of the present invention will be described. FIG. 4 is a flowchart of a display process (control method of the authentication device) at the time of dictionary data registration. Each step in FIG. 4 is mainly executed based on a command from the system control unit 150 of the imaging apparatus 100 (authentication apparatus).

  In this embodiment, the schematic configuration of the imaging apparatus 100, the display at the time of registering dictionary data, and the database 700 are the same as those in the first embodiment described with reference to FIGS. 1, 3, and 7, respectively. Since these are the same, their description is omitted. Further, steps S401 to S404 and steps S405 to S409 of the present embodiment are the same as steps S201 to S204 and steps S206 to S210 of the first embodiment described with reference to FIG. Is also omitted.

  In step S410, the classification information setting unit 195 compares the highest similarity selected in step S409 with the classification threshold (first threshold). When the highest similarity is larger than the classification threshold (first threshold), the process proceeds to step S411. On the other hand, when the highest similarity is not more than the threshold for classification (below the first threshold), the process proceeds to step S414.

  In step S411, the system control unit 150 displays the detected face (image data to be registered) on the display unit 128 in association with the subgroup (group) including the feature information having the highest similarity. Subsequently, in step S412, the system control unit 150 determines whether or not the user has designated and registered the detected face in the associated subgroup. When the user designates registration, in step S413, the detected face is registered in the associated subgroup. On the other hand, if registration is not designated by the user in step S412, the process proceeds to step S418.

  In step S414, the classification information setting unit 195 compares the similarity selected in step S409 (the highest similarity) with the registration threshold (second threshold). If the highest similarity is greater than the registration threshold (second threshold), the classification information setting unit 195 creates a new subgroup (new group) in step S415. Subsequently, in step S416, the system control unit 150 causes the display unit 128 to display the detected face in association with the new subgroup. In step S417, the system control unit 150 (classification information setting unit 195) automatically registers the detected face (second image data) in the new subgroup. On the other hand, if the highest similarity is equal to or lower than the registration threshold (second threshold or lower) in step S414, the process proceeds to step S418.

  In step S418, the system control unit 150 determines whether to end the registration mode. If image data is to be continuously registered, the process returns to step S404, and face detection processing by the face detection unit 190 is performed. On the other hand, if it is not necessary to register image data continuously, this flow ends.

  According to the present embodiment, in an authentication apparatus that classifies image data to be registered (detected faces) into a plurality of subgroups (groups) to improve authentication accuracy, the user has a face at the timing designated by the user himself / herself. Which subgroup is registered can be easily identified. For this reason, the user can grasp the trend regarding which subgroup the face specified for registration is classified into, and can perform the registration process effective for improving the authentication accuracy more smoothly. is there. Further, according to the present embodiment, since the faces classified into the new subgroup are automatically registered, improvement in authentication accuracy can be expected even when the timing for registration designation by the user is missed.

(Third embodiment)
Next, with reference to FIG. 5, a display process (control method of the authentication apparatus) at the time of dictionary data registration according to the third embodiment of the present invention will be described. FIG. 5 is a flowchart of a display process (control method of the authentication device) at the time of dictionary data registration. Each step in FIG. 5 is mainly executed based on a command from the system control unit 150 of the imaging apparatus 100 (authentication apparatus).

  In this embodiment, the schematic configuration of the imaging apparatus 100, the display at the time of registering dictionary data, and the database 700 are the same as those in the first embodiment described with reference to FIGS. 1, 3, and 7, respectively. Since these are the same, their description is omitted. Further, steps S501 to S509 of the present embodiment are the same as steps S401 to S409 (steps S201 to S204, S206 to S210 of FIG. 2) of the second embodiment described with reference to FIG. These descriptions are also omitted.

  In step S510, the classification information setting unit 195 compares the similarity selected in step S509 (the highest similarity) with the registration threshold (second threshold). When the highest similarity is larger than the registration threshold (second threshold), the process proceeds to step S511. On the other hand, when the highest similarity is equal to or lower than the registration threshold (second threshold) in step S510, the process returns to step S504. At this time, the similarity calculation processing unit 193 calculates the similarity again.

  In step S211, the classification information setting unit 195 compares the similarity obtained in step S509 (the highest similarity) with the classification threshold (first threshold). When the highest similarity is larger than the threshold for classification (first threshold), the system control unit 150 (classification information setting unit 195) is detected in the subgroup including the feature information with the highest similarity in step S512. The face (second image data to be registered) is automatically registered. Subsequently, in step S513, the system control unit 150 displays on the display unit 128 so that the user can recognize that the detected face has been registered in the subgroup.

  On the other hand, if the highest similarity is not more than the threshold for classification in step S211, the classification information setting unit 195 creates a new subgroup (new group) in step S514. Subsequently, in step S515, the system control unit 150 (classification information setting unit 195) automatically registers the detected face in the new subgroup. In step S516, the system control unit 150 causes the display unit 128 to display so that the user can recognize that the detected face has been registered in association with the new subgroup.

  According to the present embodiment, in an authentication apparatus that classifies registration target image data (detected faces) into a plurality of subgroups (groups) to improve authentication accuracy, detection is performed when the similarity exceeds a registration threshold. The face is automatically classified and registered into subgroups. For this reason, the user can perform a registration operation for improving the authentication accuracy without requiring a complicated operation.

  In each embodiment, the display method shown in FIG. 3 is used at the time of dictionary data registration, but the present invention is not limited to this. Instead of the display method of FIG. 3, the display method shown in FIG. 6 may be used. FIG. 6 is an explanatory diagram of another display method in each embodiment.

  In this case, one of the face image data (a plurality of image data) related to the feature information read from the dictionary data storage unit 192 is used as a representative face image 610 as shown in FIG. Display. In the present embodiment, one image selected from a subgroup including image data (registration information) having the highest degree of similarity with the face-detected image (image data) is set as the representative face image 610. The representative face image 610 is selected from, for example, one image determined in each subgroup. The selection method of the representative face image of each subgroup can be arbitrarily determined by the user. Alternatively, it may be automatically determined according to the order stored in the dictionary data storage unit 192.

  For example, in FIG. 6A, the detected face image 611 (image data to be registered) and the representative face image 610 are displayed on the display unit 128 in association with each other. When a new face image is registered in the same subgroup by continuing the registration mode, a newly detected face image 612 and a face image 611 detected before that are listed as shown in FIG. 6B. Display. Further, when the detected face image is associated with a new subgroup, as shown in FIG. 6C, a display is made so that it can be recognized that a new subgroup has been created.

  If all the face image data associated with the dictionary data is displayed, the display becomes complicated and may hinder the user's registration work. However, by selecting and displaying the representative face images as shown in FIGS. 6A and 6B, complicated display can be avoided, and the user can perform registration while confirming the classification of the subgroups. Become.

(Other embodiments)
The object of the present invention can also be achieved as follows. That is, a storage medium in which a program code of software in which a procedure for realizing the functions of the above-described embodiments is described is recorded is supplied to the system or apparatus. A computer (or CPU, MPU, etc.) of the system or apparatus reads out and executes the program code stored in the storage medium. In this case, the program code itself read from the storage medium realizes the novel function of the present invention, and the storage medium and program storing the program code constitute the present invention.

  Examples of the storage medium for supplying the program code include a flexible disk, a hard disk, an optical disk, and a magneto-optical disk. Further, a CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD-R, magnetic tape, nonvolatile memory card, ROM, or the like can also be used.

  Further, by making the program code read by the computer executable, the functions of the above-described embodiments are realized. Furthermore, when the OS (operating system) running on the computer performs part or all of the actual processing based on the instruction of the program code, the functions of the above-described embodiments are realized by the processing. Is also included.

  Furthermore, the following cases are also included. First, the program code read from the storage medium is written in a memory provided in a function expansion board inserted into the computer or a function expansion unit connected to the computer. Thereafter, based on the instruction of the program code, the CPU or the like provided in the function expansion board or function expansion unit performs part or all of the actual processing.

  In addition, the present invention is not limited to an apparatus mainly intended for shooting such as a digital camera. The present invention can be applied to any device with a built-in or externally connected imaging device, such as a mobile phone, personal computer (laptop type, desktop type, tablet type, etc.), game machine, and the like. Therefore, the “imaging device” in this specification is intended to include any electronic device having an imaging function.

  As mentioned above, although preferable embodiment of this invention was described, this invention is not limited to these embodiment, A various deformation | transformation and change are possible within the range of the summary.

100 imaging device 128 display unit 192 dictionary data recording unit 193 similarity calculation processing unit

Claims (10)

Storage means for classifying and storing a plurality of first feature information and a plurality of first image data of the same subject into a plurality of groups;
The second feature information extracted from the second image data of the same subject acquired by the imaging means is compared with the plurality of first feature information, and the second feature information and the plurality of first feature information are compared. Calculation processing means for calculating the degree of similarity with each;
And a display unit configured to display the second image data in association with the group having the highest similarity among the plurality of groups.   The authentication apparatus according to claim 1, wherein the first feature information and the second feature information are feature information of a face of the same subject.   The authentication apparatus according to claim 1, wherein the storage unit stores the plurality of first feature information and the plurality of first image data in association with each other. A determination control means for determining whether or not the highest similarity is greater than a first threshold;
The determination control means includes
If the similarity is greater than the first threshold, register the second image data in the group with the highest similarity,
4. The method according to claim 1, wherein, when the similarity is equal to or less than the first threshold value, a new group is created and the second image data is registered in the new group. 5. Authentication device. The determination control means further determines whether or not the similarity is greater than a second threshold value,
The determination control means creates the new group and assigns the second image data to the new group when the similarity is not more than the first threshold and the similarity is larger than the second threshold. The authentication apparatus according to claim 4, wherein the authentication apparatus is automatically registered. The determination control means further determines whether or not the similarity is greater than a second threshold value,
If the similarity is greater than the second threshold, the determination control means determines whether the similarity is greater than the first threshold;
The authentication apparatus according to claim 4, wherein when the similarity is equal to or less than the second threshold, the calculation processing unit calculates the similarity again.   An imaging apparatus comprising the authentication apparatus according to claim 1. An authentication data registration method for registering authentication data in storage means for classifying and storing a plurality of first feature information and a plurality of first image data of the same subject into a plurality of groups,
Obtaining second image data of the same subject by an imaging means;
Comparing the second feature information extracted from the second image data with the plurality of first feature information;
Calculating a similarity between the second feature information and each of the plurality of first feature information;
And a step of displaying the second image data in association with the group having the highest similarity among the plurality of groups.   A program configured to cause a computer to execute the authentication data registration method according to claim 8.   A storage medium storing the program according to claim 9.