JP6103706B2 - Authentication processing apparatus and authentication processing method - Google Patents

Description

  The present invention relates to an authentication processing apparatus and an authentication processing method for performing personal authentication of a person to be authenticated.

  In recent years, biometric authentication for performing personal authentication using information on human physical characteristics and behavioral characteristics has become widespread. One type of biometric authentication is voice authentication (see, for example, Patent Document 1 below).

Japanese Patent Application Laid-Open No. 2002-244697

  However, the above-described voice authentication is susceptible to environmental sounds, and there is a problem that the authentication accuracy may be lowered.

  The present invention has been made in view of such problems, and an object thereof is to provide a mechanism for realizing improvement in personal authentication accuracy.

The authentication processing device according to the present invention is configured so that the authentication registrant can open the mouth and at least the front teeth can be seen, and from the first mouth area image obtained by photographing the mouth area in the lateral direction of the authentication registrant's mouth. A first registered image that includes a plurality of teeth that are positioned on the right side with respect to the center position and that includes at least teeth that are adjacent in the vertical and horizontal directions, and a center position in the lateral direction of the mouth of the authentication registrant is positioned on the left side. Extracting a second registered image that includes at least teeth that are adjacent to each other in the vertical and horizontal directions and a third registered image that is an entire tooth region image based on the left and right mouth edges of the authentication registrant's mouth A registration image extracting means for performing the authentication, and the center of the authentication subject's mouth in the lateral direction from the second mouth region image obtained by photographing the mouth region with the mouth open and at least the front teeth visible A plurality of teeth positioned on the right side with respect to the position, the first authentication target image including at least the teeth adjacent to the top, bottom, left and right, and the center position of the authentication target person in the lateral direction is positioned on the left side A second authentication target image including at least teeth adjacent to each other in the vertical and horizontal directions; and a third authentication target image that is an entire tooth region image based on left and right mouth ends of the authentication target person's mouth; Authentication target image extracting means for extracting the first authentication target image, first verification processing for verifying the first authentication target image with the first registered image, and verification of the second authentication target image with the second registered image Verification processing means for performing second verification processing to be performed, and third verification processing for verifying the third authentication target image with the third registered image, a verification processing result in the first verification processing, In the second verification process Having a processing result based on the matching process results in the third collation processing, an authentication processing unit for performing authentication processing of the authentication subject.

The authentication processing method of the present invention is based on the first mouth area image obtained by photographing the mouth area in a state in which the authentication registrant opens his mouth and at least the front teeth are visible, in the lateral direction of the authentication registrant's mouth. A first registered image that includes a plurality of teeth that are positioned on the right side with respect to the center position and that includes at least teeth that are adjacent in the vertical and horizontal directions, and a center position in the lateral direction of the mouth of the authentication registrant is positioned on the left side. Extracting a second registered image that includes at least teeth that are adjacent to each other in the vertical and horizontal directions and a third registered image that is an entire tooth region image based on the left and right mouth edges of the authentication registrant's mouth A registration image extraction step, and a second mouth area image obtained by photographing the mouth area in a state where the person to be authenticated opens his mouth and at least the front teeth are visible, in the lateral direction of the mouth of the person to be authenticated A first authentication target image that includes a plurality of teeth that are positioned on the right side with respect to the center position and that includes at least teeth that are adjacent in the vertical and horizontal directions, and a center position in the lateral direction of the mouth of the authentication target person. A third authentication target image that is a whole tooth region image based on a second authentication target image that includes at least teeth that are adjacent to each other in the upper, lower, left, and right directions, and left and right mouth ends in the mouth of the authentication target person Authentication target image extraction step for extracting the first authentication target image with the first registered image, and the second registration target image with the second registered image. A matching process step for performing a second matching process for matching and a third matching process for matching the third authentication target image with the third registered image; and a matching process result in the first matching process; , The second verification process It has a matching process result based on the matching process results in the third collation processing, an authentication processing step of performing authentication processing of the authentication target person at.

  According to the present invention, it is possible to improve the accuracy of personal authentication.

It is a schematic diagram which shows an example of the external appearance of the authentication processing apparatus which concerns on embodiment of this invention. It is a schematic diagram which shows an example of a function structure of the authentication processing apparatus which concerns on embodiment of this invention. It is a flowchart which shows an example of the process sequence of the authentication processing method by the authentication processing apparatus which concerns on embodiment of this invention. FIG. 3 is a flowchart illustrating an example of a processing procedure of an authentication processing method performed by the authentication processing apparatus according to the embodiment of the present invention, following FIG. It is a figure which shows embodiment of this invention and shows an example of the 1st mouth area | region image received by step S103 of FIGS. It is a figure for showing an embodiment of the present invention and explaining an example of mouth end detection processing in Step S104 of Drawing 3-1. FIG. 9 is a diagram illustrating an example of the first registered image extraction process in step S105 in FIG. 3A and the second registered image extraction process in step S106 in FIG. is there. It is a figure for showing an embodiment of the present invention and explaining an example of the 3rd registration picture extraction processing in Step S107 of Drawing 3-1. It is a figure which shows embodiment of this invention and shows an example of the 2nd mouth area | region image received by step S202 of FIG. 3-2. It is a figure for showing an embodiment of the present invention and explaining an example of mouth end detection processing in Step S203 of Drawing 3-2. FIG. 4 is a diagram illustrating an embodiment of the present invention, illustrating an example of a first authentication target image extraction process in step S204 of FIG. 3-2 and a second authentication target image extraction process in step S205 of FIG. 3-2. FIG. It is a figure for showing an embodiment of the present invention and explaining an example of the 3rd authentication object picture extraction processing in Step S206 of Drawing 3-2. It is a figure which shows embodiment of this invention and shows an example of the table used when calculating | requiring a SIFT score in step S209 of FIG. 3-2. It is a figure for demonstrating embodiment of this invention and demonstrating the setting of an optimal threshold value.

  Hereinafter, embodiments (embodiments) for carrying out the present invention will be described with reference to the drawings.

FIG. 1 is a schematic diagram illustrating an example of an appearance of an authentication processing apparatus according to an embodiment of the present invention.
As shown in FIG. 1, the authentication processing device 100 according to the present embodiment includes a photographing device 110, an operation input device 120, an information processing device 130, a display device 140, and an electric lock device 150. ing.

  The photographing device 110 is a device that photographs the mouth region 210 in a state where the authentication registrant or the person to be authenticated (200) opens his mouth and at least the front teeth (211) can be seen based on the control by the information processing device 130. In the present embodiment, for example, a digital video camera is used as the imaging device 110, but other imaging devices can also be used.

  The operation input device 120 is operated when an operator such as a security administrator inputs information to the information processing device 130, for example. The operation input device 120 includes, for example, a keyboard 120a and a mouse 120b that is a pointing device.

  The information processing apparatus 130 controls the overall operation of the authentication processing apparatus 100.

  The display device 140 displays an image photographed by the photographing device 110 or displays various information based on control by the information processing device 130.

  The electric lock device 150 performs locking / unlocking of, for example, a door based on control by the information processing device 130.

  FIG. 2 is a schematic diagram illustrating an example of a functional configuration of the authentication processing apparatus according to the embodiment of the present invention. Here, in FIG. 2, the same components as those in FIG. 1 are denoted by the same reference numerals, and detailed description thereof is omitted.

The information processing apparatus 130 has functional configurations of a mode setting unit 131, an image receiving unit 132, a registration unit 133, and an authentication unit 134.
In the present embodiment, for example, the mode setting unit 131 includes a program recorded in the CPU and ROM of the information processing apparatus 130. In addition, for example, the image receiving unit 132 includes a program recorded in the CPU and ROM of the information processing apparatus 130 and a communication interface. Further, for example, a registration unit 133 and an authentication unit 134 are configured from a program recorded in the CPU and ROM of the information processing apparatus 130 and an external memory.

  For example, the mode setting unit 131 performs processing for setting an operation mode in the authentication processing device 100 based on an operation input from the operation input device 120. Here, in this embodiment, it is assumed that two operation modes of “registration mode” and “authentication mode” can be set.

The image receiving unit 132 performs processing for receiving a mouth area image related to the mouth area 210 of the authentication registrant or the person to be authenticated (200) photographed by the photographing apparatus 110.
Here, when the operation mode set by the mode setting unit 131 is “registration mode”, the image receiving unit 132 determines that the mouth area 210 of the authentication registrant (200) has been shot by the shooting device 110. The mouth area image obtained by photographing by the photographing apparatus 110 is received as a “first mouth area image” and is sent to the registration unit 133. Further, when the operation mode set by the mode setting unit 131 is “authentication mode”, the image receiving unit 132 determines that the mouth area 210 of the person to be authenticated (200) has been shot by the shooting device 110, and The mouth area image obtained by photographing by the photographing apparatus 110 is received as a “second mouth area image” and is sent to the authentication unit 134.

The registration unit 133 performs a registration process of the authentication registrant (200) when the “registration mode” is set by the mode setting unit 131.
Specifically, the registration unit 133 has each functional configuration of a first mouth end detection unit 1331, a registered image extraction unit 1332, and a registered image storage unit 1333. The registered image storage unit 1333 includes a storage memory 1333a.

  The first mouth end detection unit 1331 of the registration unit 133 performs processing for detecting the left and right mouth ends of the mouth of the authentication registrant (200) from the first mouth region image received by the image receiving unit 132.

The registered image extraction unit 1332 of the registration unit 133 has a plurality of positions located on the right side of the first mouth area image received by the image receiving unit 132 with reference to the center position in the horizontal direction of the mouth of the authentication registrant (200). A first registered image including at least teeth adjacent in the vertical and horizontal directions, and a plurality of teeth positioned on the left side with respect to the center position in the lateral direction of the mouth of the authentication registrant (200). The second registration image including at least the teeth adjacent to and the third registration image that is the tooth region image of the authentication registrant (200) is extracted.
Here, the registered image extraction unit 1332 performs a process of extracting a third registered image based on the left and right mouth ends detected by the first mouth end detection unit 1331.

  The registered image storage unit 1333 of the registration unit 133 stores, for each authentication registrant (200), the first registered image, the second registered image, and the third registered image extracted by the registered image extracting unit 1332 in association with each other. 1333a is stored and registered.

When the “authentication mode” is set by the mode setting unit 131, the authentication unit 134 performs an authentication process for the person to be authenticated (200).
Specifically, the authentication unit 134 has functional configurations of a second mouth end detection unit 1341, an authentication target image extraction unit 1342, a verification processing unit 1343, and an authentication processing unit 1344.

  The second mouth end detection unit 1341 of the authentication unit 134 performs processing for detecting left and right mouth ends of the mouth of the person to be authenticated (200) from the second mouth region image received by the image receiving unit 132.

The authentication target image extraction unit 1342 of the authentication unit 134 includes a plurality of images located on the right side of the second mouth area image received by the image reception unit 132 with reference to the center position in the horizontal direction of the mouth of the authentication target person (200). A first authentication target image including at least teeth adjacent to each other in the vertical and horizontal directions, and a plurality of teeth located on the left side with respect to the center position in the lateral direction of the mouth of the authentication target person (200). A process of extracting a second authentication target image including at least teeth adjacent in the vertical and horizontal directions and a third authentication target image that is a tooth region image of the authentication target person (200) is performed.
Here, the authentication target image extraction unit 1342 performs a process of extracting a third authentication target image based on the left and right mouth ends detected by the second mouth end detection unit 1341.
Specifically, in the present embodiment, the first authentication target image and the second authentication target image are extracted as follows. That is, in this embodiment, the right half image of the mouth as viewed from the authentication target person (200) in the second mouth area image is extracted as the first authentication target image, and the authentication target person in the second mouth area image. The image on the left half of the mouth as viewed from (200) is extracted as the second authentication target image.

The verification processing unit 1343 of the authentication unit 134 includes first verification processing for verifying the first authentication target image extracted by the authentication target image extraction unit 1342 with the first registered image stored in the storage memory 1333a, and authentication. A second collation process for collating the second authentication target image extracted by the target image extraction unit 1342 with the second registered image stored in the storage memory 1333a; and a third verification process extracted by the authentication target image extraction unit 1342. A third matching process for matching the authentication target image with the third registered image stored in the storage memory 1333a is performed.
Specifically, in the present embodiment, the matching processing unit 1343 performs, for example, the first matching process and the second matching process using template matching, and performs the third matching process using SIFT (Scale Invariant Feature Transform). To do.

The authentication processing unit 1344 of the authentication unit 134 is based on the verification processing result in the first verification processing, the verification processing result in the second verification processing, and the verification processing result in the third verification processing ( 200).
Specifically, in the present embodiment, the authentication processing unit 1344 acquires, for example, the first correlation value by template matching as the matching process result in the first matching process, and as the matching process result in the second matching process. The second correlation value by template matching is acquired, the number of corresponding points by SIFT is acquired as the matching processing result in the third matching processing, and the first correlation value and the second correlation value are multiplied and template matching is performed. While calculating a score, the SIFT score based on the number of corresponding points by SIFT is calculated | required, and an authentication object person (200) authentication process is performed using a template matching score and a SIFT score. More specifically, the authentication processing unit 1344 compares the multiplication result obtained by multiplying the template matching score and the SIFT score as a total score with a threshold, and if the total score is equal to or greater than the threshold, the authentication target person (200) is authenticated. A process of permitting is performed, and when the total score is less than the threshold value, a process of disabling the authentication of the person to be authenticated (200) is performed. For example, the authentication processing unit 1344 performs a process for unlocking the electric lock device 150 as a process for permitting authentication of the authentication target person (200), and a process for disallowing authentication of the authentication target person (200). Then, a process of locking the electric lock device 150 is performed. Further, the authentication processing unit 1344 performs processing for displaying the result of the authentication processing on the display device 140 as necessary.

  Next, an example of the processing procedure of the authentication processing method by the authentication processing apparatus 100 will be described.

  FIG. 3A is a flowchart illustrating an example of a processing procedure of the authentication processing method by the authentication processing apparatus according to the embodiment of the present invention.

  When the process of FIG. 3A is started, first, in step S101, the mode setting unit 131 determines whether or not the set operation mode is “registration mode”.

  As a result of the determination in step S101, when the set operation mode is not “registration mode” (in this embodiment, “authentication mode”), the process proceeds to the flowchart illustrated in FIG.

On the other hand, if it is determined in step S101 that the set operation mode is “registration mode”, the process proceeds to step S102.
In step S102, the imaging device 110 performs processing for imaging the mouth region 210 in a state where the authentication registrant (200) opens his mouth and at least the front teeth (211) can be seen based on the control by the information processing device 130. Through the processing in step S102, the imaging device 110 generates a mouth area image (in this embodiment, “first mouth area image”).

  Subsequently, in step S103, the image receiving unit 132 performs a process of receiving the mouth area image obtained by photographing in step S102 as a first mouth area image. Here, a specific example of step S103 will be described with reference to FIG.

FIG. 4 is a diagram illustrating an example of the first mouth area image received in step S103 of FIG. 3A according to the embodiment of the present invention.
A first mouth area image 400 shown in FIG. 4 is an image obtained by photographing the mouth area in a state where the authentication registrant (200) opens his mouth and at least the front teeth can be seen.

Here, the description returns to FIG. 3-1.
When the process of step S103 in FIG. 3A ends, the process proceeds to step S104.
In step S104, the first mouth end detection unit 1331 of the registration unit 133 detects left and right mouth ends of the authentication registrant (200) mouth from the first mouth region image received in step S103. I do. Here, a specific example of step S104 will be described with reference to FIG.

FIG. 5 shows the embodiment of the present invention and is a diagram for explaining an example of the mouth end detection process in step S104 of FIG. 3-1.
FIG. 5 shows the first mouth area image 400 shown in FIG. For example, the first mouth edge detection unit 1331 detects, as the left and right mouth edges 401 and 402, from the first mouth area image 400, the darkest point (black dot) and the point located at the left and right edges. Perform the process.

Here, the description returns to FIG. 3-1.
When the process of step S104 in FIG. 3-1 ends, the process proceeds to step S105.
In step S105, the registered image extraction unit 1332 of the registration unit 133 moves from the first mouth area image received in step S103 to the right with reference to the center position in the horizontal direction of the mouth of the authentication registrant (200). A process of extracting a first registered image including at least a plurality of teeth that are adjacent in the vertical and horizontal directions is performed. Here, a specific example of step S105 will be described with reference to FIG.

FIG. 6A illustrates an embodiment of the present invention, and an example of the first registered image extraction process in step S105 of FIG. 3-1 and the second registered image extraction process in step S106 of FIG. It is a figure for demonstrating.
FIG. 6A illustrates the first mouth area image 400 illustrated in FIGS. 4 and 5. The registered image extraction unit 1332 first, from the first mouth region image 400, has a plurality of teeth that are located on the right side with respect to the center position 403 in the lateral direction of the mouth of the authentication registrant (200). A process of extracting the first registered image 410 shown in FIG. 6B including at least adjacent teeth is performed. At this time, the registered image extraction unit 1332 may extract the first registered image 410 in relation to the positions of the left and right mouth edges 401 and 402 shown in FIG. 5 detected in step S104.

Here, the description returns to FIG. 3-1.
When the process of step S105 in FIG. 3A ends, the process proceeds to step S106.
In step S106, the registered image extraction unit 1332 of the registration unit 133 moves leftward from the first mouth area image received in step S103 with reference to the center position in the horizontal direction of the mouth of the authentication registrant (200). A process of extracting a second registered image including at least a plurality of teeth that are adjacent vertically and horizontally is performed. Here, a specific example of step S106 will be described with reference to FIG.

  Next, the registered image extraction unit 1332 is located on the left side of the first mouth area image 400 shown in FIG. 6A with reference to the center position 403 in the lateral direction of the mouth of the authentication registrant (200). A process of extracting the second registered image 420 shown in FIG. 6C, which includes a plurality of teeth and includes at least teeth adjacent in the vertical and horizontal directions. At this time, the registered image extraction unit 1332 may extract the second registered image 420 in relation to the positions of the left and right mouth edges 401 and 402 shown in FIG. 5 detected in step S104.

Here, the description returns to FIG. 3-1.
When the process of step S106 in FIG. 3-1 ends, the process proceeds to step S107.
In step S107, the registered image extraction unit 1332 of the registration unit 133 determines the authentication registrant (200) based on the left and right mouth edges detected in step S104 from the first mouth region image received in step S103. A process of extracting a third registered image that is a tooth area image of the first tooth region is performed. Here, a specific example of step S107 will be described with reference to FIG.

FIG. 6-2 is a diagram illustrating an example of the third registered image extraction process in step S107 of FIG. 3A according to the embodiment of this invention.
Next, the registered image extraction unit 1332 performs a process of extracting the third registered image 430 illustrated in FIG. 6-2 from the first mouth area image 400 illustrated in FIGS. 4, 5, and 6-1 (a). Do. At this time, for example, the registered image extraction unit 1332 sets the width of the third registered image 430 from the mouth edge 401 to the mouth edge 402 shown in FIG. 5 and sets the width of the third registered image 430 as shown in FIG. From the first mouth area image 400 shown in FIGS. 4, 5, and 6-1 (a) by taking a predetermined distance in the vertical direction with respect to the straight line connecting the end 401 and the mouth end 402. A third registered image 430 shown in 6-2 is extracted.

Here, the description returns to FIG. 3-1.
When the process of step S107 in FIG. 3-1 ends, the process proceeds to step S108.
In step S108, the registered image storage unit 1333 of the registration unit 133 associates the first to third registered images extracted in steps S105 to S107 with each authentication registrant (200) and stores them in the storage memory 1333a. And register it.

  When the process of step S108 ends, the process of the flowchart shown in FIG. If there are a plurality of authentication registrants, the process shown in the flowchart of FIG. 3A is performed for each authentication registrant, and the first to third registration images are associated with each authentication registrant. And stored in the storage memory 1333a and registered.

As described above, when the set operation mode is not “registration mode” (in the case of the present embodiment, “authentication mode”) as a result of the determination in step S101 of FIG. 3A, FIG. -2 transitions to the flowchart shown.
Here, FIG. 3-2 is a flowchart illustrating an example of a processing procedure of the authentication processing method by the authentication processing apparatus according to the embodiment of the present invention, following FIG. 3-1.

  When transitioning to the authentication mode shown in FIG. 3-2, first, in step S <b> 201, based on the control by the information processing device 130, the imaging apparatus 110 opens the mouth of the person to be authenticated (200) and sees at least the front teeth (211). A process of photographing the mouth area 210 in the state is performed. Through the processing in step S201, the photographing apparatus 110 generates a mouth area image (“second mouth area image” in the present embodiment).

  Subsequently, in step S202, the image receiving unit 132 performs a process of receiving the mouth area image obtained by photographing in step S201 as the second mouth area image. Here, a specific example of step S202 will be described with reference to FIG.

FIG. 7 is a diagram illustrating an example of the second mouth area image received in step S202 of FIG. 3-2 according to the embodiment of the present invention.
A second mouth area image 700 shown in FIG. 7 is an image obtained by photographing the mouth area in a state where the person to be authenticated (200) opens the mouth and at least the front teeth can be seen.

Here, it returns to description of FIG. 3-2 again.
When the process of step S202 of FIG. 3-2 ends, the process proceeds to step S203.
In step S203, the second mouth end detection unit 1341 of the authentication unit 134 detects left and right mouth ends in the mouth of the person to be authenticated (200) from the second mouth area image received in step S202. I do. Here, a specific example of step S203 will be described with reference to FIG.

FIG. 8 shows the embodiment of the present invention and is a diagram for explaining an example of the mouth end detection process in step S203 of FIG. 3-2.
FIG. 8 shows a second mouth area image 700 shown in FIG. For example, the second mouth edge detection unit 1341 detects, as the left and right mouth edges 701 and 702, from the second mouth area image 700, the darkest point (black dot) and the point positioned at the left and right edges. Perform the process.

Here, it returns to description of FIG. 3-2 again.
When the process of step S203 in FIG. 3-2 ends, the process proceeds to step S204.
In step S204, the authentication target image extraction unit 1342 of the authentication unit 134 selects the right side of the second mouth area image received in step S202 with reference to the center position in the lateral direction of the mouth of the authentication target person (200). A process of extracting a first authentication target image including at least teeth adjacent to each other in the vertical and horizontal directions is performed. Here, a specific example of step S204 will be described with reference to FIG.

FIG. 9A illustrates an embodiment of the present invention. The first authentication target image extraction process in step S204 in FIG. 3-2 and the second authentication target image extraction process in step S205 in FIG. 3-2. It is a figure for demonstrating an example.
Specifically, in the present embodiment, the authentication target image extracting unit 1342 first displays an image on the right half of the mouth as viewed from the authentication target person (200) in the second mouth area image 700 shown in FIGS. , Extraction processing as the first authentication target image 710 shown in FIG. At this time, the authentication target image extraction unit 1342 detects the relationship between the positions of the left and right mouth ends 701 and 702 shown in FIG. 8 (for example, the mouth ends 701 and 702 shown in FIG. 8). The first authentication target image 710 may be extracted using the midpoint of the connecting straight line as a reference).

Here, it returns to description of FIG. 3-2 again.
When the process of step S204 of FIG. 3-2 ends, the process proceeds to step S205.
In step S205, the authentication target image extraction unit 1342 of the authentication unit 134 determines, from the second mouth area image received in step S202, the left side with respect to the center position in the horizontal direction of the mouth of the authentication target person (200). The second authentication target image including at least teeth adjacent to each other in the vertical and horizontal directions is extracted. Here, a specific example of step S205 will be described with reference to FIG.

  Specifically, in the present embodiment, the authentication target image extraction unit 1342 then displays an image of the left half of the mouth as viewed from the authentication target person (200) in the second mouth area image 700 shown in FIGS. , Extraction processing as the second authentication target image 720 shown in FIG. At this time, the authentication target image extraction unit 1342 detects the relationship between the positions of the left and right mouth ends 701 and 702 shown in FIG. 8 (for example, the mouth ends 701 and 702 shown in FIG. 8). The second authentication target image 720 may be extracted based on the position of the midpoint of the connecting straight line).

Here, it returns to description of FIG. 3-2 again.
When the process of step S205 in FIG. 3-2 ends, the process proceeds to step S206.
In step S206, the authentication target image extraction unit 1342 of the authentication unit 134 determines the authentication target person (200 based on the left and right mouth edges detected in step S203 from the second mouth area image received in step S202. ) To extract a third authentication target image which is a tooth region image. Here, the specific example of step S206 is demonstrated using FIGS. 9-2.

FIG. 9-2 illustrates the embodiment of the present invention, and is a diagram for describing an example of the third authentication target image extraction process in step S206 of FIG. 3-2.
Next, the authentication target image extracting unit 1342 performs processing for extracting the third authentication target image 730 illustrated in FIG. 9B from the second mouth area image 700 illustrated in FIGS. 7 and 8. At this time, for example, the authentication target image extraction unit 1342 sets the horizontal width of the third authentication target image 730 from the mouth end 701 to the mouth end 702 shown in FIG. 8 and the vertical width of the third authentication target image 730 shown in FIG. 9-2, from the second mouth area image 700 shown in FIGS. 7 and 8, by taking a predetermined distance in the vertical direction with respect to the straight line connecting the mouth edge 701 and the mouth edge 702 shown in FIG. A third authentication target image 730 is extracted.

Here, it returns to description of FIG. 3-2 again.
When the process of step S206 in FIG. 3-2 ends, the process proceeds to step S207.
In step S207, the verification processing unit 1343 of the authentication unit 134 stores the first authentication target image (first authentication target image 710 shown in FIG. 9-1 (a)) extracted in step S204 in the storage memory 1333a. First collation processing for collating with the stored first registered image (first registered image 410 shown in FIG. 6B), and the second authentication target image extracted in step S205 (FIG. 9). -1 (b) is collated with the second registered image (second registered image 420 shown in FIG. 6-1 (c)) stored in the storage memory 1333a. 2 collation processing is performed.
Specifically, in the present embodiment, the matching processing unit 1343 performs, for example, the first matching process and the second matching process using template matching. In this case, the matching processing unit 1343 performs a first matching process on the first authentication target image using the first registered image and template matching to obtain the first correlation value, and the second authentication target image. Are subjected to a second matching process using the second registered image and template matching to obtain a second correlation value.

Subsequently, in step S208, the verification processing unit 1343 of the authentication unit 134 stores the third authentication target image (third authentication target image 730 shown in FIG. 9B) extracted in step S206 in the storage memory 1333a. A third matching process for matching with the third registered image (third registered image 430 shown in FIG. 6B) is performed.
Specifically, in the present embodiment, the collation processing unit 1343 performs, for example, the third collation process using SIFT. In this case, the matching processing unit 1343 performs a third matching process on the third authentication target image using the third registered image and SIFT to obtain the number of corresponding points by SIFT.

  Subsequently, in step S209, the authentication processing unit 1344 of the authentication unit 134 first obtains a first correlation value based on template matching as a collation processing result in the first collation processing from the collation processing unit 1343. The second correlation value obtained by template matching is acquired as a matching process result in the matching process, and the number of corresponding points by SIFT is acquired as the matching process result in the third matching process. Next, the authentication processing unit 1344 calculates a template matching score by multiplying the first correlation value and the second correlation value, and obtains a SIFT score based on the number of corresponding points by SIFT. Here, a specific example of how to obtain the SIFT score in step S209 will be described with reference to FIG.

FIG. 10 is a diagram illustrating an example of a table used for obtaining a SIFT score in step S209 of FIG. 3-2 according to the embodiment of this invention. The table shown in FIG. 10 is stored, for example, inside the authentication processing unit 1344 of the authentication unit 134.
In step S209, the SIFT score is obtained according to the number of corresponding points by SIFT acquired from the matching processing unit 1343 with reference to the table shown in FIG. When the table shown in FIG. 10 is used, when the number of corresponding points by SIFT acquired from the collation processing unit 1343 is 0, the SIFT score is obtained as 0.0, and the corresponding points by SIFT acquired from the collation processing unit 1343 SIFT score is determined to be 0.1 when the number of points is 1, and SIFT score is determined to be 0.4 when the number of corresponding points by SIFT acquired from the verification processing unit 1343 is 2, and the verification processing unit When the number of corresponding points by SIFT acquired from 1343 is 3, the SIFT score is obtained as 0.6, and when the number of corresponding points by SIFT acquired from the collation processing unit 1343 is 4, the SIFT score is 0. .9 and the SIFT score is obtained when the number of corresponding points by SIFT acquired from the collation processing unit 1343 is 5 or more. Calculated as 1.0.

  Subsequently, in step S210, the authentication processing unit 1344 of the authentication unit 134 multiplies the template matching score obtained in step S209 and the SIFT score, and sets the multiplication result as an overall score.

  If registered images of a plurality of authentication registrants are stored in the storage memory 1333a, the processing in steps S207 to S210 is performed for each authentication registrant, and a total score is calculated for each authentication registrant. .

Subsequently, in step S211, the authentication processing unit 1344 of the authentication unit 134 determines whether or not the total score calculated in step S210 is greater than or equal to a predetermined threshold value.
Here, when registered images of a plurality of authentication registrants are stored in the storage memory 1333a, for example, the total score having the largest value among the total scores for each authentication registrant calculated in step S210 is used. It is determined whether or not the threshold value is exceeded.

As a result of the determination in step S211, when the total score calculated in step S210 is equal to or greater than the threshold value, the process proceeds to step S212.
In step S212, the authentication processing unit 1344 of the authentication unit 134 performs processing for permitting authentication of the authentication target person. For example, the authentication processing unit 1344 performs a process of unlocking the electric lock device 150 as a process for permitting authentication of the authentication target person so that the authentication target person can enter the room by opening a door or the like. Further, the authentication processing unit 1344 performs processing for displaying the result of the authentication processing (indicating that authentication is OK) on the display device 140 as necessary.
Thereafter, the process of the flowchart of FIG.

On the other hand, if it is determined in step S211 that the total score calculated in step S210 is not equal to or greater than the threshold (that is, the total score calculated in step S210 is less than the threshold), the process proceeds to step S213.
In step S213, the authentication processing unit 1344 of the authentication unit 134 performs processing for disallowing authentication of the person to be authenticated. For example, the authentication processing unit 1344 may perform a process of locking (maintaining locking) the electric lock device 150 as a process for disabling authentication of the authentication target person, and the authentication target person may open a door or the like. Make it impossible to enter the room. Further, the authentication processing unit 1344 performs a process of displaying the result of the authentication process (indicating authentication NG) on the display device 140 as necessary.
Thereafter, the process of the flowchart of FIG.

Next, setting of the optimum threshold value in the present embodiment will be described.
FIG. 11 shows an embodiment of the present invention, and is a diagram for explaining an optimal threshold value setting.
FIG. 11 shows the overall score (◇) calculated when the authentication target person is the same person (person) as the authentication registrant using the authentication processing apparatus 100 according to this embodiment, and the authentication target person is registered for authentication. It shows an example in which the total score (●) calculated when a person different from the person (other person) is obtained by actual experiment. Here, in the characteristic diagram of FIG. 11, the vertical axis indicates the total score, and the horizontal axis indicates the sample data.
From the results shown in FIG. 11, it can be seen that if the threshold is set within the range of 0.35 to 0.65 for the total score, the person can be identified from the other person.

Here, for example, the threshold is set to 0.5.
For example, in step S207 in FIG. 3-2, the first correlation value is obtained as 0.90, the second correlation value is obtained as 0.94, and further, in step S208 in FIG. It is assumed that the number of corresponding points is obtained as 13. In this case, the template matching score is calculated as 0.90 × 0.94 = 0.85, and the SIFT score is calculated as 1.0 from FIG. Therefore, the total score is 0.85 × 1.0 = 0.85. In this case, since the SIFT score is 0.85 that is 0.5 or more which is the threshold value, it is determined that the person is the person in Step S211 of FIG. 3-2 (S211 / YES), and the authentication permission process (S212) is performed. Will be done.
Further, for example, in step S207 of FIG. 3-2, the first correlation value is obtained as 0.52, the second correlation value is obtained as 0.56, and further, in step S208 of FIG. 3-2, It is assumed that the number of corresponding points by SIFT is obtained as 0. In this case, the template matching score is calculated as 0.52 × 0.56 = 0.29, and the SIFT score is calculated as 0.0 from FIG. Therefore, the total score is 0.29 × 0.0 = 0.00. In this case, since the SIFT score is 0.00 which is less than the threshold value of 0.5, it is determined in step S211 of FIG. 3-2 that it is another person (S211 / NO), and the authentication non-permission process (S213). Will be done.

In the authentication processing apparatus 100 according to the present embodiment, an image obtained by extracting a first authentication target image, which is an image on the right half of the mouth as viewed from the person to be authenticated, in the second mouth area image from the first mouth area image. A first registered image that includes at least a tooth that is adjacent to the upper, lower, left, and right sides of the authentication registrant's mouth and is matched using template matching to obtain a first correlation value, and a second mouth area image 2, the second authentication target image, which is an image of the left half of the mouth as viewed from the authentication target person, is an image extracted from the first mouth area image and adjacent to the left, right, top, bottom, left and right of the authentication registrant The second registered image including at least the tooth to be used is compared with the template matching to obtain the second correlation value, and the template matching score is calculated by multiplying the first correlation value and the second correlation value (Fig. 3 2 of the S207, S209). In the authentication processing apparatus 100 according to the present embodiment, the third authentication target image that is the tooth region image of the authentication target person is collated with the third registration image that is the tooth region image of the authentication registrant using SIFT. Thus, the number of corresponding points by SIFT is obtained, and SIFT scores based on the number of corresponding points by SIFT are obtained (S208 and S209 in FIG. 3-2). Then, in the authentication processing apparatus 100 according to the present embodiment, the multiplication result (total score) obtained by multiplying the template matching score and the SIFT score is compared with a threshold value, and when the total score is equal to or greater than the threshold value, the authentication target person is authenticated. (S210 to S212 in FIG. 3-2).
According to such a configuration, the person to be authenticated performs the authentication process by lining up and meshing his / her teeth without uttering voice, and thus the accuracy of personal authentication can be improved. In particular, in the authentication processing apparatus 100 according to the present embodiment, the first registered image including at least teeth adjacent to the upper, lower, left, and right positions on the right side of the authentication registrant's mouth, and the left side of the authentication registrant's mouth. Since the authentication process is performed using the second registered image including at least the teeth that are adjacent in the vertical and horizontal directions, the accuracy of personal authentication can be particularly improved from the viewpoint of gaps and meshing between the vertical and horizontal adjacent teeth. Furthermore, according to the authentication processing apparatus 100 according to the present embodiment, authentication processing is performed based on the multiplication result (total score) obtained by multiplying the template matching score and the SIFT score. Compared with the case where it performs and an authentication process only with a SIFT score, personal authentication precision can be improved more. Further, the person to be authenticated can perform the authentication process without contact.

(Other embodiments)
The present invention can also be realized by executing the following processing.
That is, the software (program) for realizing the functions of the above-described embodiment of the present invention is supplied to a system or apparatus via a network or various storage media, and a computer (or CPU, MPU, etc.) of the system or apparatus is programmed. Is read and executed.
This program and a computer-readable recording medium storing the program are included in the present invention.

  Note that the above-described embodiments of the present invention are merely examples of implementation in practicing the present invention, and the technical scope of the present invention should not be construed as being limited thereto. It is. That is, the present invention can be implemented in various forms without departing from the technical idea or the main features thereof.

100: Authentication processing device, 110: Imaging device, 120: Operation input device, 130: Information processing device, 131: Mode setting unit, 132: Image receiving unit, 133: Registration unit, 1331: First mouth end detection unit, 1332: Registered image extraction unit, 1333: Registered image storage unit, 1333a: Storage memory, 134: Authentication unit, 1341: Second mouth end detection unit, 1342: Authentication target image extraction unit, 1343 collation processing unit, 1344: Authentication Processing unit, 140: display device, 150: electric lock device, 210: mouth area

Claims (6)

From the first mouth area image obtained by photographing the mouth area in a state where the authentication registrant opens his mouth and at least the front teeth are visible, the position is on the right side with respect to the center position in the lateral direction of the mouth of the authentication registrant. A first registered image including at least teeth adjacent to each other in the vertical and horizontal directions; and a plurality of teeth positioned on the left side with respect to the center position in the lateral direction of the mouth of the authentication registrant. A registered image extracting means for extracting a second registered image including at least teeth adjacent to the image and a third registered image that is an entire tooth region image based on the left and right mouth edges of the mouth of the authentication registrant;
From the second mouth area image obtained by photographing the mouth area with the mouth open and at least the front teeth visible, the right person is positioned on the right side with respect to the center position in the lateral direction of the mouth of the person to be authenticated. A plurality of teeth that are at least left and right adjacent to the first authentication target image including teeth that are adjacent to the upper, lower, left, and right, and a center position in the lateral direction of the mouth of the authentication target person. Authentication target image extraction for extracting a second authentication target image including at least teeth adjacent to the left and right, and a third authentication target image that is a whole tooth region image based on the left and right mouth ends of the mouth of the authentication target person Means,
A first matching process for matching the first authentication target image with the first registered image; a second matching process for matching the second authentication target image with the second registered image; Verification processing means for performing a third verification process for verifying the third authentication target image with the third registered image;
An authentication process for performing the authentication process for the person to be authenticated based on the verification process result in the first verification process, the verification process result in the second verification process, and the verification process result in the third verification process Means,
An authentication processing device comprising: Storage means for storing the first registered image, the second registered image, and the third registered image in association with each other for each authentication registrant;
The collation processing unit collates the first authentication target image extracted by the authentication target image extraction unit in the first collation processing with the first registered image stored in the storage unit, and In the second verification process, the second authentication target image extracted by the authentication target image extraction unit is compared with the second registered image stored in the storage unit, and in the third verification process, the authentication target 2. The authentication processing apparatus according to claim 1, wherein the third authentication target image extracted by the image extraction unit is collated with the third registered image stored in the storage unit. The first authentication target image is an image on the right half of the mouth as viewed from the authentication target person in the second mouth region image;
The second authentication target image is an image of the left half of the mouth as viewed from the authentication target person in the second mouth region image;
The collation processing means performs the first collation processing and the second collation processing using template matching, and performs the third collation processing using SIFT (Scale Invariant Feature Transform),
The authentication processing means acquires a first correlation value based on the template matching as a matching processing result in the first matching processing, and a second correlation value based on the template matching as a matching processing result in the second matching processing. And the number of corresponding points by the SIFT is acquired as a matching process result in the third matching process, and a template matching score is calculated by multiplying the first correlation value and the second correlation value. And obtaining an SIFT score based on the number of corresponding points by the SIFT, and performing authentication processing of the person to be authenticated using the template matching score and the SIFT score. Authentication processing device.   The authentication processing means compares the multiplication result obtained by multiplying the template matching score and the SIFT score with a threshold value, and permits the authentication of the person to be authenticated when the multiplication result is equal to or greater than the threshold value. The authentication processing device according to claim 3, wherein First mouth end detecting means for detecting left and right mouth ends of the authentication registrant's mouth from the first mouth region image;
Second mouth end detecting means for detecting left and right mouth ends of the authentication subject's mouth from the second mouth region image;
Further comprising
The registered image extracting means extracts the third registered image based on the left and right mouth edges detected by the first mouth edge detecting means;
5. The authentication object image extracting unit extracts the third authentication object image based on left and right mouth ends detected by the second mouth end detecting unit. The authentication processing device according to item 1. From the first mouth area image obtained by photographing the mouth area in a state where the authentication registrant opens his mouth and at least the front teeth are visible, the position is on the right side with respect to the center position in the lateral direction of the mouth of the authentication registrant. A first registered image including at least teeth adjacent to each other in the vertical and horizontal directions; and a plurality of teeth positioned on the left side with respect to the center position in the lateral direction of the mouth of the authentication registrant. A registered image extracting step of extracting a second registered image including at least teeth adjacent to the tooth and a third registered image that is a whole tooth region image based on the left and right mouth edges of the mouth of the authentication registrant;
From the second mouth area image obtained by photographing the mouth area with the mouth open and at least the front teeth visible, the right person is positioned on the right side with respect to the center position in the lateral direction of the mouth of the person to be authenticated. A plurality of teeth that are at least left and right adjacent to the first authentication target image including teeth that are adjacent to the upper, lower, left, and right, and a center position in the lateral direction of the mouth of the authentication target person. Authentication target image extraction for extracting a second authentication target image including at least teeth adjacent to the left and right, and a third authentication target image that is a whole tooth region image based on the left and right mouth ends of the mouth of the authentication target person Steps,
A first matching process for matching the first authentication target image with the first registered image; a second matching process for matching the second authentication target image with the second registered image; A collation processing step for performing a third collation process for collating three authentication target images with the third registered image;
An authentication process for performing the authentication process for the person to be authenticated based on the verification process result in the first verification process, the verification process result in the second verification process, and the verification process result in the third verification process Steps,
An authentication processing method characterized by comprising:

Images