JP2007058397A - Authentication system, registration system, and medium for certificate - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an authentication system of high precision using an ID card. <P>SOLUTION: A face authentication system 1 acquires a registered face characteristic amount EB2 having three-dimensional information and two-dimensional information of the face of a person recorded in the ID card 9, from ID information recorded in the ID card 9, and acquires an authentication face characteristic amount EC2 having three-dimensional information and two-dimensional information of the face of an authentication objective person HMb, based on two images (collation images EC1) acquired directly from the authentication objective person HMb, the authentication face characteristic amount EC2 is compared with the registered face characteristic amount EB2 to authenticate (collate) whether the authentication objective person HMb is the person same to the person recorded in the ID card 9 or not, and the high precise authentication is executed by this manner. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to a face authentication technique using a certification medium.

  In recent years, various services digitized by the development of network technology and the like have become widespread, and the need for non-face-to-face personal authentication technology that does not rely on people is increasing. Along with this, research on biometrics authentication technology (biometric authentication technology) for automatically identifying an individual based on a person's biometric features has been actively conducted. Face authentication technology, which is one of biometric authentication technologies, is a non-contact authentication method, and is expected to be applied in various fields such as security by a surveillance camera or image database search using a face as a key.

  On the other hand, when using a credit card, an ID card, etc., there is a need for accurately identifying whether the card owner is a legitimate owner, and the card possession is used as identification information for such identification. A technique for recording a person's face image and two-dimensional feature information of a representative part of the face on an ID card has been proposed (see Patent Document 1).

JP 2003-317036 A

  However, since the identification information is basically information based on the two-dimensional information of the face, there is a problem that the recognition accuracy using the identification information is not sufficiently high.

  Therefore, the present invention has been made in view of the above problems, and an object of the present invention is to provide a technique capable of performing authentication with higher accuracy than the case of using only two-dimensional face information.

  In order to solve the above-mentioned problem, the invention of claim 1 is an authentication system using a proof medium in which ID information for personal identification is recorded, the means for reading the ID information from the proof medium, Based on the ID information, means for obtaining first characteristic information representing the characteristics of the person recorded on the certification medium, and second characteristic information representing the characteristics of the person to be authenticated who possesses the certification medium An authentication operation as to whether or not the person recorded on the certification medium and the person to be authenticated are the same person using the obtaining means, the first feature information, and the second feature information And the first feature information and the second feature information are configured to include face three-dimensional information and face two-dimensional information, respectively, and the authentication means 3D information contained in the first feature information and the previous By collating the three-dimensional information included in the second feature information, and collating the two-dimensional information included in the first feature information with the two-dimensional information included in the second feature information, An authentication operation is performed.

  The invention of claim 2 is the authentication system according to claim 1, wherein the ID information includes three-dimensional coordinate information of a plurality of representative points in the face of a predetermined person registered in the certification medium, and the ID information. And at least one image obtained by photographing a face of a predetermined person.

  According to a third aspect of the present invention, in the authentication system according to the second aspect of the present invention, the at least one image is attached as a face photograph on the certification medium.

  According to a fourth aspect of the present invention, in the authentication system according to the second aspect of the invention, the at least one image is recorded as image data on the certification medium.

  The invention according to claim 5 is the authentication system according to claim 4, further comprising display means for visualizing and displaying the image data read from the certification medium.

  The invention of claim 6 is the authentication system according to any one of claims 2 to 5, wherein the ID information includes two-dimensional coordinates representing positions of the plurality of representative points on the image. It is characterized by that.

  The invention of claim 7 is the authentication system according to any one of claims 2 to 5, wherein the ID information is a parameter indicating a position and orientation of a camera when the at least one image is taken. It is characterized by including.

  The invention of claim 8 is a proof medium for recording personal proof information, and at least one piece of three-dimensional coordinate information of a plurality of representative points on the face of the predetermined person and the face of the predetermined person. The information including the image is recorded.

  Further, the invention of claim 9 is a registration system for registering face authentication information in a certification medium, wherein a plurality of images obtained by photographing a face of a person to be registered from different positions; Means for acquiring three-dimensional coordinate information of a plurality of representative points on the face of the person to be registered based on an image; and information including at least one image of the plurality of images and the three-dimensional coordinate information Means for recording on a medium.

  According to the first to seventh aspects of the invention, the authentication object that acquires the face three-dimensional information and the two-dimensional information from the ID information recorded on the certification medium and possesses the certification medium Whether the person to be authenticated is the same person as the person recorded on the certification medium by acquiring the three-dimensional information and the two-dimensional information of the face from the person and collating the three-dimensional information with the two-dimensional information. Since it is determined whether or not, authentication with high accuracy can be performed.

  According to the invention described in claim 8, information including three-dimensional coordinate information of a plurality of representative points on the face of the predetermined person and at least one image obtained by photographing the face of the predetermined person is stored in the certification medium. Since the information is recorded, high-accuracy authentication can be performed in an authentication system that can read and use the information.

  According to the invention of claim 9, a plurality of images obtained by photographing the face of the registration target person from different positions are acquired, and the three-dimensional coordinates of the plurality of representative points on the face of the registration target person are acquired from the plurality of images. Since information is acquired and information including at least one image and three-dimensional coordinate information among the plurality of images is recorded on the certification medium, high-accuracy authentication is performed in the certification system using the certification medium. Is possible.

  In particular, according to the third aspect of the present invention, since the face photograph is attached on the certification medium, it is possible to collate visually.

  In particular, according to the invention described in claim 5, since it is possible to visualize and display the image data read from the certification medium, it is possible to collate visually.

  In particular, according to the invention described in claim 6, since the ID information includes two-dimensional coordinates of a plurality of representative points of the face on at least one image obtained by photographing the face of the predetermined person, a plurality of representatives Since it is not necessary to perform processing for calculating the two-dimensional coordinates representing the position of the point on the image, the authentication operation can be speeded up.

  In particular, according to the seventh aspect of the invention, since the ID information includes a parameter indicating the position and orientation of the camera when at least one image is captured, the position of the plurality of representative points on the image is represented. Two-dimensional coordinates can be easily calculated, and the authentication operation can be speeded up.

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

<Embodiment>
<Overview of operation>
FIG. 1 is a diagram showing an overall operation of the face authentication system 1 according to the embodiment of the present invention.

  As shown in FIG. 1, the face authentication system 1 includes two subsystems, a face registration system SYS1 and a face matching system SYS2.

  In the face registration system SYS1, information in a predetermined format such as three-dimensional information (hereinafter also referred to as “ID information”) is generated based on two or more input images EB1 acquired from the person to be registered HMa. Then, the ID information is recorded on a certification information recording medium such as an ID card 9 (hereinafter also simply referred to as “certification medium”).

  In the face matching system SYS2, the registered face feature quantity EB2 is acquired (generated) based on the three-dimensional information and the two-dimensional information obtained from the ID information recorded on the certification medium (ID card 9), and the authentication target The authentication face feature amount EC2 is acquired (generated) based on the three-dimensional information and the two-dimensional information obtained from two or more collation images EC1 directly acquired from the person HMb. Then, the three-dimensional information of the registered face feature quantity EB2 representing the characteristics of the person recorded on the certification medium is compared with the three-dimensional information of the authentication face feature quantity EC2 representing the characteristics of the person to be authenticated who possesses the certification medium. At the same time, the two-dimensional information of the registered face feature quantity EB2 and the two-dimensional information of the authentication face feature quantity EC2 are collated. As a result, authentication determination is performed to determine whether or not the authentication target person is the same person as the person recorded on the certification medium.

  As described above, the face authentication system 1 creates a certification medium (ID card 9) using ID information in a predetermined format acquired from the person to be registered HMa (face registration system SYS1), and uses the ID card. Then, the authentication operation of the ID card owner (authentication target person HMb) is executed (face matching system SYS2).

  Hereinafter, the face registration system SYS1 and the face collation system SYS2 will be described in detail in this order. In the face authentication system 1 according to the present embodiment, the ID card 9 is used as a proof medium.

<Outline of face registration system SYS1>
FIG. 2 is a configuration diagram showing the face registration system SYS1. As shown in FIG. 2, the face registration system SYS1 includes a controller 10a, two image photographing cameras (hereinafter also simply referred to as “cameras”) CA1 and CA2, and an ID card writer 9a.

  The camera CA1 and the camera CA2 are arranged so that the face of the registration target person HMa, which is a predetermined person, can be photographed from different positions. When a face image of the registration target person HMa is captured by the camera CA1 and the camera CA2, appearance information of the registration target person HMa obtained by the capturing, that is, two types of face images are transmitted to the controller 10a via a communication line. . Then, a predetermined format of information (ID information) to be recorded on the ID card 9 is generated by a predetermined process of the controller 10a, and the ID information is recorded (registered) on the ID card 9 by the ID card writer 9a. The data communication method between each camera or ID card writer 9a and the controller 10a is not limited to a wired method, and may be a wireless method.

  FIG. 3 is a diagram showing a configuration outline of the controller 10a. As shown in FIG. 3, the controller 10a includes a CPU 2, a storage unit 3, a media drive 4, a display unit 5 such as a liquid crystal display, an input unit 6 such as a keyboard 6a and a mouse 6b that is a pointing device, It is composed of a general computer such as a personal computer provided with a communication unit 7 such as a network card. The storage unit 3 includes a plurality of storage media, specifically, a hard disk drive (HDD) 3a and a RAM (semiconductor memory) 3b capable of processing at higher speed than the HDD 3a. The media drive 4 can read information recorded in a portable recording medium 8 such as a CD-ROM, a DVD (Digital Versatile Disk), a flexible disk, or a memory card. The information supplied to the controller 10a is not limited to being supplied via the recording medium 8, and may be supplied via a network such as a LAN and the Internet.

  Next, various functions provided in the controller 10a will be described.

  FIG. 4 is a block diagram illustrating various functions provided in the controller 10a.

  The various functions provided in the controller 10a conceptually indicate functions realized by executing a predetermined software program (hereinafter also simply referred to as “program”) using various hardware such as a CPU in the controller 10a. Is.

  As shown in FIG. 4, the controller 10 a includes an image input unit 11, a face area search unit 12, a face part detection unit 13, a three-dimensional reconstruction unit 14, and an output unit 15.

  The image input unit 11 has a function of inputting two images taken by the cameras CA1 and CA2 to the controller 10a.

  The face area search unit 12 has a function of specifying a face area from the input face image.

  The face part detection unit 13 has a function of detecting the position of a characteristic part (for example, eyes, eyebrows, nose, mouth) of the face from the specified face region.

  The three-dimensional reconstruction unit 14 has a function of calculating the three-dimensional coordinates of each part from the coordinates of the characteristic part of the face obtained from the input image. This three-dimensional coordinate calculation function is realized using camera information stored in the camera parameter storage unit 101 or the like.

  The output unit 15 is input to the image input unit 11 and information related to a three-dimensional configuration (hereinafter also referred to as “three-dimensional information”) composed of the three-dimensional coordinate values obtained by the three-dimensional reconstruction unit 14. It has a function of outputting the image etc. as ID information.

  Next, the ID card 9 will be described.

  FIG. 5A is an external view showing the configuration of the ID card 9, and FIG. 5B is a block diagram showing the functional configuration of the ID card 9.

  As shown in FIG. 5, the ID card 9 includes a face photograph 52 and a data input / output unit 55 such as an electrode terminal 53 on the surface thereof.

  Here, since the face photograph 52 is attached on the ID card 9, it is possible to collate with a third party (such as an entrance manager) by visual inspection. Specifically, it is possible to easily determine whether or not the person to be authenticated who owns the ID card 9 is the true owner of the ID card 9 without using the face authentication controller 10b (described later). Become. Alternatively, it is possible to perform a visual collating operation in a weighted manner together with collation using the controller 10b.

  Further, the ID card 9 has a recording unit 54 such as an IC chip inside. Thereby, the ID card 9 records (holds) ID information or the like from the data input / output unit 55 to the recording unit 54 via the ID card writer 9a and the like, and passes the ID card reader or the like from the data input / output unit 55. Can output the ID information.

  Below, the operation | movement implement | achieved by the face registration system SYS1 mentioned above is demonstrated.

<Operation of Face Registration System SYS1>
As shown in FIG. 1, the controller 10a in the face registration system SYS1 can generate ID information from two images (input images EB1) input from the cameras CA1 and CA2. As the ID information, as will be described later, at least one image (for example, one image) of the three-dimensional information EA1 including the three-dimensional coordinates of each feature point of the face calculated from the input image EB1 and the two input images EB1. The registered image EB1a) may be used. Further, information including supplementary information EP such as camera parameters may be used as ID information.

  Below, ID information generation operation | movement with which the controller 10a is provided is demonstrated.

  Specifically, a case where a registration operation is actually performed with a predetermined person photographed by the cameras CA1 and CA2 as a registration target person HMa will be described. Here, as an example, three-dimensional information using three-dimensional shape information measured according to the principle of triangulation using images from the cameras CA1 and CA2 is used, and texture (luminance) information is used as two-dimensional information.

  FIG. 6 is a flowchart showing the operation of the controller 10a in the face registration system SYS1. FIG. 7 is a diagram showing characteristic points (representative points) of characteristic parts in the face image. FIG. 8 is a schematic diagram showing how three-dimensional coordinates are calculated from feature points in a two-dimensional image using the principle of triangulation. 8 indicates the image G1 captured by the camera CA1 and input to the controller 10a, and the reference G2 indicates the image G2 captured by the camera CA2 and input to the controller 10a. A point Q20 in the images G1 and G2 corresponds to the right end of the mouth in FIG.

  As illustrated in FIG. 6, in the process from step SP1 to step SP4, the controller 10a generates ID information related to the registration target person HMa based on an image obtained by photographing the face of the registration target person HMa, and further includes step SP5. By outputting the ID information at, face registration to the ID card 9 is realized.

  First, in step SP1, face images (image G1 and image G2) of a predetermined person (registration target person HMa) photographed by the cameras CA1 and CA2 are input to the controller 10a via a communication line. The cameras CA1 and CA2 that capture a face image are each configured by a general imaging device that can capture a two-dimensional image. Further, camera parameters Bi (i = 1 ·· N) indicating the positions and orientations of the respective cameras CAi are known and stored in advance in the camera parameter storage unit 101 (FIG. 3). Here, N indicates the number of cameras. In the present embodiment, the case of N = 2 is illustrated, but N ≧ 3 may be used (three or more cameras may be used). The camera parameter Bi will be described later.

  Next, in step SP2, the area where the face exists is detected in each of the two images (image G1 and image G2) input from the cameras CA1 and CA2. As a face area detection technique, for example, a technique of detecting a face area from each of two images by template matching using a standard face image prepared in advance can be employed.

  Next, in step SP3, the position of the characteristic part of the face is detected from the face area image detected in step SP2. For example, eyes, eyebrows, nose or mouth may be considered as characteristic parts of the face. In step SP3, the coordinates of the characteristic points (representative points) Q1 to Q23 of the above parts as shown in FIG. Is calculated. The feature part can be detected by, for example, template matching performed using a standard template of the feature part. Further, the coordinates of the calculated feature points (representative points) are represented as coordinates on the images G1 and G2 input from the camera. For example, with respect to the feature point Q20 corresponding to the right end of the mouth in FIG. 7, as shown in FIG. 8, the coordinate values in each of the two images G1 and G2 are obtained. Specifically, the coordinates (x1, y1) of the feature point Q20 on the image G1 are calculated using the upper left end point of the image G1 as the origin O. Similarly, in the image G2, the coordinates (x2, y2) of the feature point Q20 on the image G2 are calculated.

In the next step SP4 (three-dimensional reconstruction process), two-dimensional coordinates Ui ^{(j) in} each image Gi (i = 1,..., N) of each feature point (representative point) Qj detected in step SP3. Based on the camera parameters Bi of the camera that captured each image Gi, the three-dimensional coordinates M ^(j) (j = 1... M ^{) of} each feature point Qj are calculated. Note that m indicates the number of feature points.

Hereinafter, the calculation of the three-dimensional coordinate M ^(j) will be specifically described.

The relationship between the three-dimensional coordinates M ^(j) of each feature point Qj, the two-dimensional coordinates Ui ^{(j) of} each feature point Qj, and the camera parameter Bi is expressed as in Expression (1).

  Note that μi is a parameter that indicates a change in the scale. The camera parameter matrix Bi is a value unique to each camera obtained by photographing an object with known three-dimensional coordinates in advance, and is represented by a 3 × 4 projection matrix.

For example, as a specific example of calculating the three-dimensional coordinates using the above formula (1), consider the case of calculating the three-dimensional coordinates M ⁽²⁰⁾ of the feature point Q20 with reference to FIG. Expression (2) shows the relationship between the coordinates (x1, y1) of the feature point Q20 on the image G1 and the three-dimensional coordinates (x, y, z) when the feature point Q20 is represented in a three-dimensional space. Similarly, Expression (3) represents the relationship between the coordinates (x2, y2) of the feature point Q20 on the image G2 and the three-dimensional coordinates (x, y, z) when the feature point Q20 is represented in a three-dimensional space. Show.

The unknowns in the above formulas (2) and (3) are a total of five of the two parameters μ1, μ2 and the three component values x, y, z of the three-dimensional coordinate M ⁽²⁰⁾ . On the other hand, since the number of equations included in the equations (2) and (3) is 6, each unknown, that is, the three-dimensional coordinates (x, y, z) of the feature point Q20 can be calculated. Similarly, three-dimensional coordinates M ^(j) for all feature points Qj can be acquired.

In step SP5, ID information is output. As described above, in this embodiment, as the ID information, three-dimensional information including the three-dimensional coordinates M ^(j) of each feature point Qj of the face of the person to be registered calculated in step SP4, and two pieces of information input from the camera are used. Since at least one image (for example, image G1) is used among the input images EB1, the three-dimensional information and the image data of at least one image (registered image EB1a) are in a predetermined format in the output step (step SP5). Output as ID information.

In addition to the above two types of information, information including the following supplementary information EP may be output as ID information. Examples of supplementary information include the camera parameter Ba of the camera that captured the registered image EB1a, and / or the two-dimensional coordinates U ^(j) of each facial feature point Qj in the registered image EB1a (calculated in step SP3). .

  The ID information output in this way is recorded on the ID card 9 by the ID card writer 9a or the like. The face photograph 52 is printed out on the ID card 9. The face photograph 52 attached to the surface of the ID card 9 is preferably the same image as the registered image EB1a.

  Further, the face photograph 52 may be attached on the ID card 9 by being directly printed on the ID card 9 as described above, or the ID may be obtained by attaching a printed matter on a separate sheet to the ID card 9. You may comprise as what was attached | subjected on the card | curd 9. FIG. In this embodiment, as will be described later, the image data stored in the ID card 9 is used for collation by the controller 10b, and the face photograph 52 itself is not used for collation by the controller 10b. The face photograph 52 attached to is not necessarily required to be elaborate and may have a resolution that can be visually identified.

  As described above, the face registration system SYS1 can record the face information of the person to be registered HMa used in the face collation system SYS2 described below on the ID card 9 as ID information in a predetermined format.

<Outline of face matching system SYS2>
Next, the face matching system SYS2 will be described. In the face collation system SYS2, as described above, an authentication (collation) operation is performed using the ID card created by the face registration system SYS1. In the following description, differences from the face registration system SYS1 will be mainly described, and common portions will be denoted by the same reference numerals and description thereof will be omitted.

  FIG. 9 is a configuration diagram showing the face matching system SYS2.

  In the configuration of the face matching system SYS2 shown in FIG. 9, the difference from the face registration system SYS1 is that an ID card reader 9b is connected to the controller 10b as an external device.

  The ID card reader 9b reads the ID information of the ID card 9 possessed by the person to be authenticated HMb and transmits it to the controller 10b. Then, in the controller 10b, face authentication (verification) of the ID card owner (authentication target person HMb) is performed using the two types of face images photographed by the cameras CA1 and CA2 and the ID information.

  Next, various functions provided in the controller 10b will be described.

  FIG. 10 is a diagram illustrating various functions provided in the controller 10b. FIG. 11 is a block diagram showing a detailed functional configuration of the personal authentication unit 21.

  The controller 10b has the same hardware configuration as the controller 10a shown in FIG. The various functions of the controller 10b conceptually indicate functions realized by executing a predetermined software program (hereinafter also simply referred to as “program”) using various hardware such as a CPU in the controller 10b. It is.

  As shown in FIG. 10, the controller 10 b includes a personal authentication unit 21 and an authentication result output unit 22 in addition to various functions (image input unit 11, face area search unit 12, face part detection unit 13) provided in the controller 10 a. It has. In addition, the controller 10b having the above functions includes two images of the person to be authenticated HMb acquired from the two cameras (CA1, CA2), and ID information of the registrant recorded on the ID card 9. Is input, and the processing using each functional unit is performed on each input information.

  The personal authentication unit 21 is configured mainly for face authentication, and has a function of authenticating each individual using a face image. Details of the personal authentication unit 21 will be described below.

  The authentication result output unit 22 has a function of outputting the authentication result obtained by the personal authentication unit 21.

  Next, a detailed configuration of the personal authentication unit 21 will be described with reference to FIG.

  As shown in FIG. 11, the personal authentication unit 21 includes the above-described three-dimensional reconstruction unit 14, optimization unit 31, correction unit 32, feature extraction unit 33, information compression unit 34, and comparison unit 35. .

  The three-dimensional reconstruction unit 14 has the same function as the three-dimensional reconstruction unit 14 in the controller 10a, and calculates the three-dimensional coordinates of each part from the coordinates of the characteristic part of the face obtained from the input image. have.

  The optimization unit 31 uses a three-dimensional coordinate of a characteristic part of the face to store a standard three-dimensional model of the face (also referred to as “standard three-dimensional model” or “standard model”) stored in the three-dimensional model database 102. From this, it has a function of generating an individual model.

  The correction unit 32 has a function of correcting the generated individual model.

  Each of the input information is normalized by each of the processing units 14, 31, and 32 and converted into a state that can be easily compared with each other. Further, the individual model created by the function of each processing unit is formed as including both three-dimensional information and two-dimensional information. “3D information” is information related to a three-dimensional structure composed of 3D coordinate values, etc., and “2D information” is composed of surface information (texture information) and / or planar position information, etc. This is information related to the planar configuration.

  The feature extraction unit 33 has a feature extraction function for extracting three-dimensional information and two-dimensional information from the individual models created by the processing units 14, 31, 32.

  The information compressing unit 34 converts the three-dimensional information and the two-dimensional information extracted by the feature extracting unit 33 into appropriate face feature amounts for face authentication, so that the three-dimensional information used for face authentication (collation) is obtained. And two-dimensional information are compressed. This information compression function is realized by using information stored in the compressed information storage unit 103.

  The comparison unit 35 compares the registered face feature amount EB2 based on the ID information obtained by each function unit and the authentication face feature amount EC2 of the authentication target person HMb obtained directly from the authentication target person HMb by each function unit. And has a function of performing face authentication (collation).

<Operation of Face Matching System SYS2>
As shown in FIG. 1, the controller 10b in the face collation system SYS2 acquires three-dimensional information and two-dimensional information from the ID information recorded on the ID card 9, and generates a registered face feature amount EB2 (PHA1). . Further, the controller 10b generates an authentication face feature amount EC2 based on the three-dimensional information and the two-dimensional information obtained from the two images (collation image EC1) directly obtained from the authentication target person HMb, and the registered face feature amount. Authentication (collation) determination is performed by comparing EB2 and authentication face feature amount EC2 (PHA2).

  In the following, the overall operation of the controller 10b in the face matching system SYS2 will be broadly described as a registered face feature value generation operation PHA1 and an authentication (collation) operation PHA2.

  FIG. 12 is a flowchart showing the registered face feature value generation operation PHA1.

  As shown in FIG. 12, in the process from step SP11 to step SP16, the controller 10b acquires information used for model fitting based on the ID information, and further registers through the process from step SP17 to step SP20. Realize facial feature.

  First, in step SP11, the ID information recorded on the ID card 9 is read via the ID card reader 9b.

Next, in step SP12, it is determined whether or not the ID information read in step SP11 includes the two-dimensional coordinates U ^(j) of the facial feature point Qj in the registered image EB1a. If the two-dimensional coordinate U ^(j) is included, the process proceeds to step SP17. If not included, the process proceeds to step SP13 to calculate the two-dimensional coordinate U ^(j) . As described above, when the two-dimensional information U ^(j) of the facial feature point Qj is included in the ID information, the processing from step SP13 to step SP16 can be omitted, and the registered face feature value generation operation PHA1. Can be speeded up.

  In step SP13, it is determined whether the camera information Ba of the camera when the registered image EB1a is captured is included in the ID information read in step SP11. If the camera parameter Ba is included, the process proceeds to step SP14. As described above, when the camera information Ba of the camera when the registered image EB1a is captured is included in the ID information, the processing of step SP15 and step SP16 can be omitted, and the registered face feature value generation operation PHA1. Can be speeded up.

In step SP14, the two-dimensional coordinates U ^(j) of the facial feature point Qj in the registered image EB1a are calculated using the camera parameter Ba. Specifically, since the three-dimensional coordinates M ^(j) and the camera parameter Ba regarding the feature point Qj of the face of the owner of the ID card 9 included in the ID information are known, the equation used in step SP4 above is used. Using the relationship (1), the two-dimensional coordinates U ^(j) of the facial feature point Qj in the registered image EB1a can be calculated.

  On the other hand, if it is determined in step SP13 that the camera parameter Ba is not included, the process proceeds to step SP15.

  In step SP15, the registered image EB1a is subjected to the same processing as step SP2 described above, and the face area in the registered image EB1a is detected.

Further, in step SP16, the same processing as in step SP3 described above is performed. From the face area image detected in step SP15, the position of a characteristic part of the face, that is, each feature point of the face in the registered image EB1a. 2-dimensional coordinates Ui of Qj ^(j) is detected.

As described above, in the processes from step SP12 to step SP16, the two-dimensional coordinates Ui ^(j) of the facial feature points Qj in the registered image EB1a are acquired based on the ID information. Accordingly, the two-dimensional position of each facial feature point Qj on the registered image EB1a on the registered image EB1a and the three-dimensional position of each facial feature point Qj included in the three-dimensional information of the ID information in the three-dimensional space The two-dimensional information can be pasted in the model fitting described below.

In the next step SP17, model fitting is performed. This “model fitting” is a modification of “standard model of face”, which is a general (standard) face model prepared in advance, using ID information and information obtained from the ID information. Thus, an “individual model” in which the ID information recorded on the ID card 9 is reflected is generated. Specifically, processing for changing the three-dimensional information of the standard model using the three-dimensional coordinates M ^(j) included in the three-dimensional information of the ID information, and texture information to be described later obtained from the registered image EB1a of the ID information And processing for changing the two-dimensional information of the standard model.

  FIG. 13 is a diagram illustrating a standard model of a three-dimensional face.

  The standard model of the face shown in FIG. 13 includes vertex data and polygon data, and is stored in the storage unit 3 of the controller 10b as the three-dimensional model database 102 (FIG. 11). The vertex data is a set of coordinates of the vertices (hereinafter also referred to as “standard control points”) COj of the feature parts in the standard model, and the three-dimensional coordinates of each feature point Qj of the face included in the three-dimensional information of the ID information. There is a one-to-one correspondence. The polygon data is obtained by dividing the surface of the standard model into minute polygons (for example, triangles) and expressing the polygons as numerical data. FIG. 13 exemplifies a case where the vertices of each polygon are also constituted by intermediate points other than the standard control point COj, and the coordinates of the intermediate point are appropriately complemented using the coordinate values of the standard control point COj. Can be obtained by:

  Here, the model fitting process which comprises an individual model from a standard model is explained in full detail.

First, the vertex (standard control point COj) of each feature part of the standard model is moved to each feature point Qj of the face included in the three-dimensional information of the ID information. Specifically, the three-dimensional coordinate value of each feature point Qj is substituted as the three-dimensional coordinate value of the corresponding standard control point COj, and the moved standard control point (hereinafter also referred to as “individual control point”) Cj obtain. As a result, the standard model can be transformed into an individual model represented by the three-dimensional coordinates M ^(j) . Note that the coordinates of intermediate points other than the individual control points Cj in the individual model can be obtained by an appropriate interpolation method using the coordinate values of the individual control points Cj.

  Further, the scale, inclination, and position of the individual model based on the standard model used in step SP18 described later can be obtained from the amount of movement of each vertex due to this deformation (movement). Specifically, the position change of the individual model with respect to the standard model can be obtained from the deviation amount between the predetermined reference position in the standard model and the corresponding reference position in the individual model after deformation. In addition, a change in the inclination of the individual model with respect to the standard model is determined by the amount of deviation between the reference vector connecting the two predetermined points in the standard model and the reference vector connecting the corresponding two points in the individual model after deformation. And a change in scale can be determined. For example, the position of the individual model is obtained by comparing the coordinates of the midpoint QM of the right eye feature point Q1 and the left eye feature point Q2 with the coordinates of the point corresponding to the midpoint QM in the standard model. Furthermore, the scale and inclination of the individual model can be calculated by comparing the midpoint QM with other feature points.

  The following equation (4) represents a conversion parameter (vector) vt that represents the correspondence between the standard model and the individual model. As shown in the equation (4), the conversion parameter (vector) vt includes a scale conversion index sz of both, a conversion parameter (tx, ty, tz) indicating translational displacement in the orthogonal three-axis directions, and a rotational displacement (inclination). ) Representing a conversion parameter (φ, θ, ψ).

As described above, the process of changing the three-dimensional information of the standard model using the three-dimensional coordinates M ^(j) included in the three-dimensional information of the ID information is performed.

  In addition, the luminance value of each pixel in the region having each feature point as a vertex in the registered image EB1a is acquired as information (hereinafter, also referred to as “texture information”) included in each region. It is pasted (mapped) on the corresponding area (polygon) above. Note that regions corresponding to each other between the individual model and the registered image EB1a are specified using the correspondence relationship using the feature point Qj as described above.

  Each region (polygon) to which texture information is pasted on a three-dimensional model (individual model or the like) is also referred to as a “patch”.

  As described above, the model fitting process (step SP17) is performed.

  In the next step SP18, the individual model is corrected based on the standard model. In this step, position (alignment) correction relating to three-dimensional information and texture correction relating to two-dimensional information are executed.

  The alignment (face orientation) correction is performed based on the scale, inclination, and position of the individual model based on the standard model obtained in step SP17. More specifically, by converting the coordinates of the individual model using the conversion parameter vt (see Expression (4)) indicating the relationship between the standard model and the individual model when the standard model is used as a reference, A three-dimensional face model having the same posture can be created. That is, the alignment correction can appropriately normalize the three-dimensional information of the ID information.

  Next, texture correction will be described. In texture correction, normalization of texture information is performed.

  The texture information normalization is a process of standardizing the texture information by obtaining the correspondence between each individual control point (feature point) of the individual model and each corresponding point (corresponding standard position) in the standard model. As a result, the texture information of each patch in the individual model can be changed to a state that is not easily affected by changes in patch shape (specifically, changes in facial expression) and / or changes in facial posture.

  Here, a case where a stereo model in which texture information of each patch in an individual model is pasted to the original standard model (used for creating the individual model) is generated as a sub model separately from the individual model. To do. The texture information of each patch attached to the submodel has a state in which the shape of each patch and the posture of the face are normalized.

  More specifically, the individual control points (feature points) of the individual model are moved to the corresponding points in the original standard model, and then the texture information regarding the person to be authenticated is standardized. More specifically, the position of each pixel in each patch in the individual model is normalized based on the three-dimensional coordinates of the individual control point Cj of the patch, and the corresponding position in the corresponding patch in the original standard model is obtained. The brightness value (texture information) of each pixel of the individual model is pasted.

  FIG. 14 is a conceptual diagram showing normalization of texture information in a predetermined patch. The normalization of texture information will be described in more detail with reference to FIG.

  For example, it is assumed that the patch KK2 in a certain individual model corresponds to the patch HY in the original standard model. At this time, the position γK2 in the patch KK2 in the individual model is a linear sum of independent vectors V21 and V22 connecting two different sets of individual control points Cj (j = J1, J2, J3) of the patch KK2. Expressed. Further, the position γHY in the patch HY in the standard model is expressed by the linear sum of the corresponding vectors V01 and V02 using the same coefficient as each coefficient in the linear sum of the vectors V21 and V22. As a result, the correspondence relationship between the positions γK1 and γHY is obtained, and the texture information of the position γK2 in the patch KK2 can be pasted to the corresponding position γHY in the patch HY. When such texture information pasting processing is executed for all the texture information in the patch KK2 of the individual model, the texture information in the patch in the individual model is converted into texture information in the patch in the sub model and normalized. It will be obtained in the state.

  The two-dimensional information (texture information) of the face in this sub-model has a characteristic that it is not easily affected by changes in facial posture, facial expression changes, and the like. For example, when postures and expressions in two individual models relating to the same person are different from each other, when normalization of the texture information described above is not performed, the correspondence between patches in both individual models (for example, in FIG. Etc.) cannot be obtained accurately, and there is a high possibility of being erroneously determined that the person is a different person. On the other hand, if the texture information is normalized as described above, the posture of the face is unified, and the corresponding positional relationship of each patch can be obtained more accurately, so that it is less affected by the posture change. Further, according to the above-described normalization of the texture information, the shape of each patch constituting the face surface is the same as the shape of each corresponding patch in the standard model (see FIG. 14), so the shape of each patch is unified. (Normalized) and less affected by facial expression changes. For example, an individual model of a smiling person is converted into a non-laughing sub model and standardized by using a standard model that is not smiling (no expression). According to this, the influence of the texture information change (for example, the mole position change) due to the smile is suppressed. Thus, the above-mentioned normalized texture information becomes information effective for personal authentication (collation).

  Further, the texture information pasted on the sub model can be further changed to a projection image as shown in FIG. 15 so that the comparison can be easily performed.

  FIG. 15 shows an image obtained by projecting texture-corrected texture information, that is, texture information pasted on a sub model, onto a cylindrical surface arranged around the sub model. Since the texture information of the projection image is normalized and has a characteristic that it does not depend on the shape and posture, it is very useful as information used for personal identification.

  As described above, in step SP18, the three-dimensional information and the two-dimensional information based on the ID information recorded on the ID card 9 are generated in a normalized state.

  In the next step SP19 (FIG. 12), three-dimensional shape information (three-dimensional information), texture information (two-dimensional information), and information representing features based on the registrant's ID information recorded on the ID card 9 Is extracted.

As the three-dimensional information, three-dimensional coordinate vectors of m individual control points Cj in the individual model are extracted. Specifically, as shown in Expression (5), a vector h having three-dimensional coordinates (Xj, Yj, Zj) of m individual control points Cj (j = 1,..., M) as elements. ^S (hereinafter also referred to as “three-dimensional coordinate information”) is extracted as three-dimensional information (three-dimensional shape information).

  Further, as the two-dimensional information, texture (luminance) information (hereinafter, referred to as a patch or a group of patches (local region) in the vicinity of an individual control point, that is, a characteristic part of a face that is important information for personal authentication (collation) "Local 2D information") is extracted. Here, information mapped to the above-described submodel is used as texture information (local two-dimensional information).

The local two-dimensional information is, for example, a group GR (individual control points C20, C22, and C23 having a vertex at the individual control points C20, C22, and C23) and individual control points C21, C22 in FIG. And the luminance information of each pixel included in each local region such as a region composed of patches R2) having C23 as vertices or a region composed of only one patch. The local two-dimensional information h ^(k) (k = 1,..., L; L is the number of local regions) is represented by n as the number of pixels in the local region and BR1 as the luminance value of each pixel. , BRn, it is expressed in a vector format as shown in Equation (6). In addition, information ^obtained by collecting local two-dimensional information h ^(k) for L local regions is also expressed as comprehensive two-dimensional information.

  As described above, in step SP19, three-dimensional shape information (three-dimensional information) and texture information (two-dimensional information) are included as information representing features based on the registrant's ID information recorded on the ID card 9. Extracted.

  In the next step SP20, the information compression processing described below is performed to convert the information extracted in step SP19 into a state suitable for authentication.

The information compression processing is performed using the same method for each of the three-dimensional shape information h ^S and each local two-dimensional information h ^(k) . Here, for the local two-dimensional information h ^(k) , A case where information compression processing is performed will be described in detail.

The local two-dimensional information h ^(k) is calculated in advance by KL expansion of the average information (vector) have ^{(k) of the} local area acquired in advance from a plurality of sample face images and the plurality of sample face images. Using the matrix P ^(k) (described below) expressed by the set of eigenvectors of the local region, it can be expressed in the form of basis decomposition as shown in Equation (7). As a result, the local two-dimensional face information amount (vector) c ^(k) is acquired as compressed information about the local two-dimensional information h ^(k) .

As described above, the matrix P ^(k) in the equation (7 ⁾ is calculated from a plurality of sample face images. Specifically, the matrix P ^(k) is obtained as a set of several eigenvectors (base vectors) having large eigenvalues among a plurality of eigenvectors obtained by KL expansion of a plurality of sample face images. These basis vectors are stored in the compressed information storage unit 103. By expressing the face image using an eigenvector indicating a larger feature of the face image as a base vector, it is possible to efficiently express the feature of the face image.

For example, consider a case where the local two-dimensional information h ^(GR) of the local region composed of the group GR shown in FIG. 16 is expressed in a basis-decomposed format. Assuming that the set P of eigenvectors of the local region is expressed as P = (P1, P2, P3) by three eigenvectors P1, P2, and P3, the local two-dimensional information h ^(GR) The average information have ^(GR) and the set of eigenvectors P1, P2, and P3 are used to express the equation (8). The average information have ^(GR) is a vector obtained by averaging a plurality of local two-dimensional information (vectors) for various sample face images for each corresponding element. In addition, what is necessary is just to use the standard several face image which has moderate dispersion | variation as several sample face images.

Further, the above equation (8) indicates that the original local two-dimensional information can be reproduced by the face information amount c ^(GR) = (c1, c2, c3) ^T. That is, it can be said that the face information amount c ^(GR) is information obtained by compressing the local two-dimensional information h ^(GR) of the local region including the group GR.

The local two-dimensional face information amount c ^(GR) acquired as described above may be used for the authentication operation as it is, but in this embodiment, further information compression is performed. Specifically, a process of converting the feature space represented by the local two-dimensional face information amount c ^(GR) into a partial space that increases separation between individuals is further performed. More specifically, consider a transformation matrix A that reduces the local two-dimensional face information amount c ^(GR) of the vector size f to the local two-dimensional feature amount d ^(GR) of the vector size g as expressed in Expression (9). . Thereby, the feature space represented by the local two-dimensional face information amount c ^(GR) can be converted into the partial space represented by the local two-dimensional feature amount d ^(GR) , and the difference in information between individuals is remarkable. become.

  Here, the transformation matrix A is a matrix having a size of f × g. Using a multiple discriminant analysis (MDA) method, the transformation matrix A is determined by selecting g principal components having a large ratio (F ratio) between intra-class variance and inter-class variance from the feature space. Can do.

In addition, by executing the same processing as the information compression processing performed on the local two-dimensional information h ^(GR) described above for all other local regions, the local two-dimensional face feature amount d ^(k) for each local region is also ^{obtained. )} can be acquired. Further, by applying the same method to the three-dimensional shape information h ^S , the three-dimensional face feature value d ^S can be acquired.

The face feature amount d obtained by combining the three-dimensional face feature amount d ^S and the local two-dimensional face feature amount d ^(k) acquired through the step SP20 can be expressed as a formula (10) in a vector format. .

  In the steps SP11 to SP20 described above, the face feature amount d based on the ID information registered in the ID card 9 is generated as the registered face feature amount EB2 from the ID information.

  Then, in the following authentication (collation) operation PHA2, face authentication (collation) of the person HMb to be authenticated who owns the ID card 9 is performed using the registered face feature amount EB2.

  Next, the authentication (collation) operation PHA2 will be described.

  FIG. 17 is a flowchart showing the authentication (collation) operation PHA2. In the following description of the authentication (collation) operation PHA2, the description of the same process as that described above will be omitted.

  As shown in FIG. 17, in the process from step SP31 to step SP38, the controller 10b authenticates the authentication face feature amount EC2 of the authentication target person HMb based on the two collation images EC1 directly acquired from the authentication target person HMb. Further, in the processes from step SP39 to step SP40, authentication (verification) of the authentication target person HMb is realized by comparing the registered face feature amount EB2 and the authentication face feature amount EC2.

  First, in step SP31, the face image (image G11 and image G12) of the person to be authenticated HMb photographed by the cameras CA1 and CA2 as in step SP1 is input to the controller 10b via the communication line.

  Next, in step SP32, processing similar to that in step SP2 is performed, and a region where a face exists is detected in each of the two input images (image G11 and image G12).

In step SP33, processing similar to that in step SP3 is performed. From the face area image detected in step SP32, the position of the characteristic part of the face, that is, the two-dimensional coordinates in each of the two images of each feature point Qj. U ^(j) is detected.

In the next step SP34, processing similar to that in step SP4 is performed, and the three-dimensional coordinates M ^{(j) of} each feature point Qj are calculated.

  In step SP35, the same process as step SP17 is performed, and an individual model reflecting input information related to the face of the person HMb to be authenticated is generated from the standard model.

  In step SP36, the same processing as in step SP18 is performed, and the three-dimensional information and the two-dimensional information of the individual model are appropriately normalized, and become information effective for authentication (collation).

  In the next step SP37, processing similar to that in step SP19 is performed, and three-dimensional shape information (three-dimensional information) and texture information (two-dimensional information) are extracted as information representing the characteristics of the person to be authenticated HMb. .

  In the next step SP38, as in step SP20, information compression processing for converting the information extracted in step SP37 into a state suitable for authentication is performed, and the face feature amount d of the person HMb to be authenticated is the authentication face feature. Generated as quantity EC2.

  In the next steps SP39 to SP40, authentication (collation) is performed using the authentication face feature quantity EC2.

Specifically, the total similarity Re, which is the similarity between the authentication face feature amount EC2 of the person to be authenticated HMb and the registered face feature amount EB2 based on the ID information of the registrant recorded on the ID card 9, is calculated ( Step SP39), and thereafter, a comparison (determination) operation between the person to be authenticated HMb and the ID information (step SP40) is performed based on the total similarity Re. The overall similarity Re is three-dimensional and 3-dimensional similarity Re ^S calculated from the face feature amount d ^S, a local two-dimensional similarity Re ^(k) calculated from the local 2-dimensional face feature amount d ^(k) In addition, the weighting coefficient (hereinafter also simply referred to as “weighting coefficient”) that defines the weight between the three-dimensional similarity Re ^S and the local two-dimensional similarity Re ^(k) is calculated. Note that predetermined values determined in advance are used as the weighting factors WT and WS in the present embodiment.

In step SP39, the registered face feature amount EB2 based on the ID information generated in the registered face feature amount generation operation PHA1 is similar to the authentication face feature amount EC2 of the person to be authenticated HMb calculated through steps SP31 to SP38. Sexuality assessment is performed. Specifically, it is similar between the registered face feature quantity EB2 (d ^SM and d ^{(k) M} ) registered and the authentication face feature quantity EC2 (d ^SI and d ^{(k) I} ) of the person to be authenticated HMb. The degree calculation is executed, and the three-dimensional similarity Re ^S and the local two-dimensional similarity Re ^(k) are calculated.

The three-dimensional similarity Re ^S is obtained by obtaining the Euclidean distance Re ^S between corresponding vectors as shown in Expression (11).

Further, the local two-dimensional similarity Re ^(k) is obtained by obtaining the Euclidean distance Re ^(k) for each vector component of the feature quantities in the corresponding local regions as shown in Expression (12). .

Then, as shown in Expression (13), the three-dimensional similarity Re ^S and the local two-dimensional similarity Re ^(k) are synthesized using the weighting factors WT and WS, and the person to be authenticated HMb and ID The total similarity Re that is the similarity with the registrant recorded on the card 9 can be acquired.

  Next, in step SP40, authentication (collation) determination is performed based on the total similarity Re.

  Specifically, since it is only necessary to determine whether or not the input face (face of the person to be authenticated HMb) is the same as the face of the person (registrant) recorded in the ID card 9, the ID information By comparing the similarity Re between the registered face feature amount EB2 based on the authentication face feature amount EC2 of the authentication target person HMb with a certain threshold value, the authentication target person HMb and the person recorded on the ID card 9 are identical. Sex is determined. Specifically, when the similarity Re is smaller than a certain threshold TH1, it is determined that the person to be authenticated HMb is the same person as the person recorded on the ID card 9.

  As described above, the controller 10b generates the registered face feature amount EB2 from the ID information recorded on the ID card 9, and based on the two images (collation image EC1) directly acquired from the authentication target person HMb. Authentication face feature amount EC2 is generated, and by comparing the registered face feature amount EB2 with the authentication face feature amount EC2, it is authenticated whether or not the person to be authenticated HMb is the same person as the person recorded on the ID card 9 (Verification) can be performed.

  Here, assuming that the registered face feature quantity EB2 is the first feature information and the authentication face feature quantity EC2 is the second feature information, the controller 10b authenticates using the first feature information and the second feature information. It can be expressed that the operation can be performed.

  As described above, the face authentication system 1 records the three-dimensional information and two-dimensional information of the face of the person to be registered HMa in the face registration system SYS1 as ID information in a predetermined format on the ID card 9, and the face matching system SYS2 The authentication (collation) operation is performed using the three-dimensional information and the two-dimensional information obtained from the ID information, so that highly accurate authentication can be performed.

<Modification>
Although the embodiments of the present invention have been described above, the present invention is not limited to the contents described above.

  For example, in the above embodiment, the luminance value of each pixel in the patch is used as the two-dimensional information. However, the color of each patch may be used as the two-dimensional information.

  Further, in the above embodiment, the similarity calculation is performed using the authentication face feature amount EC2 obtained by one photographing, but the present invention is not limited to this. Specifically, whether the value of the acquired authentication face feature amount EC2 is appropriate by photographing the authentication target person HMb twice and calculating the similarity between the face feature amounts obtained by the two photographing operations. It can be determined whether or not. As a result, when the acquired value of the authentication face feature amount EC2 is inappropriate, it is possible to perform imaging again.

  Moreover, in the said embodiment, although MDA method was used as a method of determining the transformation matrix A in step SP19 and step SP38, it is not limited to this, For example, between class dispersion and intraclass dispersion from predetermined feature space An EM (Eigenspace Method) method for obtaining a projection space in which the difference is large may be used.

  Moreover, in the said embodiment, although the three-dimensional shape information of the face is acquired using the several image input from several cameras, it is not limited to this. Specifically, the reflected light of the laser irradiated by the laser light emitting portion L1 is measured by the camera LCA using a three-dimensional shape measuring instrument constituted by the laser light emitting portion L1 and the camera LCA as shown in FIG. By doing so, the three-dimensional shape information of the face of the person to be registered HMa or the person to be authenticated HMb may be acquired. However, according to the method of acquiring three-dimensional shape information using an input device including two cameras as in the above embodiment, a three-dimensional shape can be obtained with a relatively simple configuration compared to an input device using laser light. Shape information can be acquired.

  Further, in the above embodiment, the face photograph 52 is attached on the ID card 9 and the image data of the face image (input image EB1) is recorded in the ID card 9 as ID information related to texture information. It is not limited to.

  For example, the image data of the face image may be recorded in the ID card 9 as the ID information regarding the texture information without attaching the face photograph 52 on the ID card 9. In this case, the image data of the registered image EB1a included in the ID information may be visualized and displayed as a face photograph on the display unit 5 or the like (see FIG. 9) of the controller 10b. According to this, verification by a third party can be performed without using the face photograph 52 on the ID card 9. In detail, it is possible to easily determine whether or not the person to be authenticated who owns the ID card 9 is the true owner of the ID card 9.

  Or, conversely, without recording image data related to texture information in the ID card 9, the face photo attached to the ID card 9 by printing or the like is recorded on the ID card 9 as ID information related to the texture information. You may do it. In this case, two-dimensional information can be acquired from the face photograph by reading the face photograph on the surface of the ID card 9 with a scanner or the like built in the ID card reader 9b. According to this, since it is not necessary to record the image data on the ID card, it is effective when the storage capacity (memory capacity) of the ID card 9 is small. In order to acquire highly accurate two-dimensional information, the face photograph attached to the ID card 9 is preferably a fine (high resolution) image.

In the above embodiment, the three-dimensional coordinates of each feature point of the face calculated from the input image EB1 are used as the three-dimensional information EA1 of the ID information. However, the present invention is not limited to this. Specifically, functional units similar to the optimization unit 31 (FIG. 11), the correction unit 32, the feature extraction unit 33, and the information compression unit 34 described above are provided in the controller 10a, and steps SP17 to SP20 shown in FIG. Processes similar to the above-described processes may be executed by the controller 10a, and pre-compressed information (such as the three-dimensional face feature amount d ^S ) may be recorded on the ID card 9 as the three-dimensional information EA1. .

Moreover, in the said embodiment, although registration image EB1a was used as ID information, it is not limited to this. Specifically, functional units similar to the optimization unit 31, the correction unit 32, the feature extraction unit 33, and the information compression unit 34 are provided in the controller 10a, and each process from step SP17 to step SP20 shown in FIG. The controller 10a may execute the same processing as that described above, and two-dimensional information (local two-dimensional face feature amount d ^(k), etc.) compressed in advance may be recorded on the ID card 9.

  In the above embodiment, the ID information is recorded on the recording unit 54 such as an IC chip inside the ID card 9. However, the present invention is not limited to this, and the ID information is encoded on the surface of the ID card 9 and printed. Alternatively, it may be recorded on a magnetic stripe or the like.

  In the above embodiment, the ID card 9 is used as a proof information recording medium (proof medium) for holding (registering) ID information. However, the present invention is not limited to this, and an IC tag or the like may be used. .

It is a conceptual diagram which shows the face authentication system which concerns on embodiment of this invention. It is a block diagram which shows a face registration system. It is a figure which shows the structure outline | summary of a controller. It is a block diagram which shows the various functions with which a controller is provided. It is a figure which shows the structure of ID card. It is a flowchart which shows operation | movement of a face registration system controller. It is a figure which shows the feature point of the characteristic site | part in a face image. It is a schematic diagram which calculates a three-dimensional coordinate from the feature point in a two-dimensional image. It is a block diagram which shows a face collation system. It is a figure which shows the various functions with which a controller is provided. It is a block diagram which shows the detailed functional structure of a personal authentication part. It is a flowchart which shows registration face feature-value production | generation operation | movement. It is a figure which shows the standard model of a three-dimensional face. It is a conceptual diagram which shows normalization of the texture information in a predetermined patch. It is a figure which shows texture information. It is a figure which shows the individual control point of the characteristic site | part after normalization. It is a flowchart which shows authentication (collation) operation | movement. It is a figure which shows the three-dimensional shape measuring device comprised from a laser beam emission part and a camera.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Face authentication system SYS1 Face registration system SYS2 Face collation system 52 Face photograph 53 Electrode terminal 9 ID card 9a Card writer 9b Card reader CA1 Camera CA2 Camera HMa Registration person HMb Authentication person

Claims (9)

An authentication system using a certification medium in which ID information for personal identification is recorded,
Means for reading the ID information from the proof medium;
Means for obtaining first feature information representing a feature of a person recorded on the proof medium based on the ID information;
Means for acquiring second characteristic information representing characteristics of a person to be authenticated who possesses the certification medium;
Authentication means for performing an authentication operation as to whether or not the person recorded on the certification medium and the person to be authenticated are the same person using the first feature information and the second feature information; ,
With
The first feature information and the second feature information are each configured to include face three-dimensional information and face two-dimensional information,
The authentication means collates the three-dimensional information included in the first feature information with the three-dimensional information included in the second feature information, and the two-dimensional information included in the first feature information An authentication system, wherein the authentication operation is performed by collating with two-dimensional information included in the second feature information. The authentication system according to claim 1,
The ID information includes three-dimensional coordinate information of a plurality of representative points on the face of the predetermined person registered in the certification medium and at least one image obtained by photographing the face of the predetermined person. Authentication system. The authentication system according to claim 2,
The authentication system according to claim 1, wherein the at least one image is attached as a face photograph on the certification medium. The authentication system according to claim 2,
The authentication system, wherein the at least one image is recorded as image data in the certification medium. The authentication system according to claim 4,
Display means for visualizing and displaying image data read from the proof medium;
An authentication system further comprising: In the authentication system according to any one of claims 2 to 5,
2. The authentication system according to claim 1, wherein the ID information includes two-dimensional coordinates representing positions of the plurality of representative points on the image. In the authentication system according to any one of claims 2 to 5,
2. The authentication system according to claim 1, wherein the ID information includes a parameter indicating a position and orientation of a camera when the at least one image is taken. A proof medium for recording personal proof information,
An information medium for recording information including three-dimensional coordinate information of a plurality of representative points on a face of a predetermined person and at least one image obtained by photographing the face of the predetermined person. A registration system for registering face authentication information in a certification medium,
Means for acquiring a plurality of images obtained by capturing the face of the person to be registered from different positions;
Means for acquiring three-dimensional coordinate information of a plurality of representative points on the face of the person to be registered based on the plurality of images;
Means for recording information including at least one image of the plurality of images and the three-dimensional coordinate information on the proof medium;
A registration system comprising: