JP2007004536A - Object-discriminating method and face-discriminating apparatus - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a face-discriminating method for robustly discriminating whether an object and a registered image coincide with each other, even if the object is not photographed in the same direction as that of the registered image, and for processing at a high speed. <P>SOLUTION: A face-discriminating apparatus 1 for discriminating whether the face of a person that is the object coincides with a registered face image TJK comprises a plurality of cameras 11a to 11d, of which the mutual position relation has been known and which are aimed at capturing images GDKs of the head of the object; an attribute value calculating unit 22 for calculating the matching degrees ZSs with the image TJK for each captured image; a maximum attribute value calculating unit 23 for calculating the maximum matching degree ZM that is matching degree, when the face of the person faces the direction closest to the direction of the image TJK, on the basis of the calculated plurality of matching degrees ZSs; and a discriminating means 24 for comparing the calculated matching degree ZM to a threshold Th, to discriminate whether the face of the person matches the image TJK. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to a subject discriminating device for discriminating whether or not a subject matches a registered image, and more particularly to a face discriminating device for discriminating whether or not a person's face matches a registered face image.

  In recent years, there has been an increasing demand for authentication in fields such as security. Among various authentication methods, the authentication method based on a person's face is supported by many applications in that there are few constraints on the person to be verified.

  In face authentication, an image obtained by photographing the face of a person who is a subject and a face image registered in advance are checked to determine whether or not they match, thereby identifying the person and determining the identity of the person. It is carried out. In the case of face authentication, there is a problem that the authentication accuracy is lowered because the face orientation, lighting conditions, and the like are different at the time of registration and at the time of collation, and the person itself may vary depending on changes over time.

  Now, regarding the face orientation, the front face is generally used as a registered image. This is because the front face is easier to match at the time of registration and collation, and images of each part of the face such as the eyes, nose and mouth can be acquired in a relatively good state. Further, in the case of authentication using cards, the registered image is often printed on the card as it is, so that it is often taken from the front that is easy for humans to see.

  Therefore, even at the time of collation, the camera is installed at a position and orientation that seems to be in front of the subject, and collation is performed between the image captured in that state and the registered face image.

  However, depending on the application, it may not be possible to request the subject to face the front accurately. Even if it can be done, the face direction and the line-of-sight direction do not necessarily match, so there is no guarantee that the face direction will match at the time of registration and at the time of matching. Therefore, it can be said that it is necessary to perform face discrimination on the assumption that the orientation of the face varies to some extent.

2. Description of the Related Art Conventionally, a technique for performing identity authentication and identity authentication for each image photographed under a plurality of conditions and comparing the results is disclosed (Patent Document 1). Further, a face authentication technique is disclosed in which a user's face area is extracted from images captured by a plurality of cameras, and the calculated feature quantity is compared with a pre-registered face feature quantity (Patent Document 2). .
JP 2003-178274 A JP2004-192378

  However, in the case of Patent Document 1, it is necessary to use a registered image every time shooting is performed under a plurality of conditions. As the number of registered images increases, the amount of data increases, and the processing takes time. .

  Further, in the case of Patent Document 2, the facial feature amounts detected by the respective cameras are spatially associated and collated in the feature space by KL expansion or the like for a plurality of images. Shooting information needs to be included. For this reason, the amount of data to be registered increases, and therefore processing takes time.

  The present invention has been made in view of the above problems, and even when the subject is not photographed in the same direction as the registered image, it is possible to robustly determine whether or not they match, In addition, it is an object to provide a subject discrimination method and a face discrimination device that can perform processing at high speed with a small amount of data such as a registered image.

  The method according to the present invention is a subject determination method for determining whether or not a subject matches registered information, and a plurality of cameras whose positional relationships are known to each other for a specific part of the subject. Acquiring a plurality of images, calculating an attribute value by comparing the acquired images with the registration information, and determining whether the subject is the registration information based on the plurality of calculated attribute values. A maximum attribute value that is the maximum value of the attribute value in the case of being closest to the image, and comparing the calculated maximum attribute value with a threshold value to determine whether or not the subject matches the registered information Performing steps.

  Also, a step of acquiring a plurality of images of a specific part of the subject by a plurality of cameras whose positional relationships are known, and a step of calculating a degree of coincidence between the acquired images and the registered image And a step of calculating a maximum matching degree that is a matching degree when the subject is oriented in the direction closest to the orientation of the registered image based on the plurality of calculated matching degrees, and a calculated maximum matching degree Comparing with a threshold value and determining whether or not the subject matches the registered image.

  The apparatus according to the present invention includes a plurality of cameras whose positional relationships are known for acquiring an image of a specific part of the subject and an attribute value for calculating an attribute value for each acquired image. A maximum attribute value that calculates a maximum attribute value that is a maximum value of the attribute value when the subject is facing the direction closest to the direction of the registered image, based on the calculated plurality of attribute values A calculating unit; and a determining unit that compares the calculated maximum attribute value with a threshold value to determine whether or not the subject matches the registered image.

  In addition, for each acquired image, a matching degree calculating unit that calculates a matching degree with the registered face image, and the face of the person is based on the plurality of matching degrees calculated by the matching degree calculating unit. Maximum matching degree calculating means for calculating a maximum matching degree that is a matching degree when facing the direction closest to the direction of the registered face image, and comparing the calculated maximum matching degree with a threshold value to compare the person Determining means for determining whether or not the face matches the registered face image.

  Preferably, the registered face image is a front average face image of a person.

  The maximum matching degree calculating means calculates a maximum point of a curve approximated by a plurality of points indicating the matching degree as the maximum matching degree.

  In addition, with respect to a curve approximated by a plurality of points indicating the degree of coincidence calculated by the degree-of-matching calculating means, the case where the subject is the person of the registered face image and the case where it is not the case are compared. Accordingly, there is provided a determination unit that determines whether or not the face of the person matches the registered face image.

  According to the present invention, even when the subject is not photographed in the same direction as the registered image, it is possible to robustly determine whether or not they match, and the processing is performed with a small amount of data such as the registered image. Can be performed at high speed.

[First Embodiment]
FIG. 1 is a block diagram showing a functional configuration of a subject discrimination device 1 according to the first embodiment of the present invention.

  In FIG. 1, the subject discrimination device 1 includes a plurality of cameras 11a to 11d, a processing device 12, a display device 13, an input device 14, a storage device 15, and the like.

  The cameras 11a to 11d are for obtaining an image (image data) GD for a specific part of the subject Q, and their positional relationships are known. For one subject Q, the cameras 11a to 11d photograph simultaneously to obtain a plurality of images GD at the same timing. Note that data indicating the positional relationship of the cameras 11a to 11d is stored, for example, in a memory of the processing device 12 or incorporated in a program.

  The processing device 12 obtains an attribute value for each of the images GD captured and acquired by the cameras 11a to 11d, and based on the obtained plural attribute values, the attribute value when the subject Q is closest to the registration information. A maximum attribute value that is the maximum value is calculated, and the calculated maximum attribute value is compared with a threshold value to determine whether or not the subject Q matches the registered information. The processing device 12 also performs other various processes. The processing device 12 includes a CPU (Central Processing Unit), ROM, RAM, other peripheral circuits, storage devices, interface circuits, and the like.

  The processing device 12 includes an attribute value calculation information storage unit 21, an attribute value calculation unit 22, a maximum attribute value calculation unit 23, a determination unit 24, a threshold value storage unit 25, and the like.

  The attribute value calculation information storage unit 21 stores information (registration information TJ) for calculating the attribute value ZS of each image GD acquired by the cameras 11a to 11d. As such registration information TJ, for example, when the attribute value ZS is defined as “image direction collation degree (matching degree)”, a specific part (for example, subject Q) photographed by the cameras 11a to 11d (for example, A standard image for (face) is used. Also, depending on what value the attribute value ZS is, information on the surface state, color, shape, etc. of a specific part of the subject Q can be registered information TJ.

  The attribute value calculation unit 22 calculates an attribute value ZS for each image GD acquired by the cameras 11a to 11d. The attribute value ZS is, for example, the degree of matching of face orientation (degree of matching) as described above. The attribute value calculation unit 22 is also provided with a memory area for storing the image GD, a memory area for storing data indicating the positional relationship of the cameras 11a to 11d, and the like.

  The maximum attribute value calculation unit 23 calculates a maximum attribute value ZM that is the maximum value of the attribute value ZS when the subject Q is closest to the registration information TJ based on the calculated plurality of attribute values ZS.

  The determination unit 24 compares the calculated maximum attribute value ZM with the threshold value Th stored in the threshold value storage unit 25 to determine whether or not the subject Q matches the registration information TJ. .

  The display device 13 displays the result determined by the processing device 12, and displays other data, images, messages, and the like.

  The input device 14 inputs or sets variables and parameters necessary for processing in the processing device 12 and inputs various other data and commands.

  The storage device 15 stores images, variables, parameters, and the like necessary for processing in the processing device 12.

  Such a subject discrimination device 1 can be realized by a personal computer in which an appropriate program is stored. Then, it is possible to connect to an external network or server via a dedicated line, LAN, WAN, or the Internet.

  Next, an example in which the above-described subject determination device 1 is used for authentication with a human face will be described in detail.

  In the present embodiment, as the registration information TJ, a registered face image TJK previously captured with a fixed face orientation such as the front is used for the subject Q. Registered face images TJK for a plurality of persons are stored in the attribute value calculation information storage unit 21, and the person photographed by the cameras 11a to 11d is compared with a specific registered face image TJK to determine the degree of matching. . When it is determined that they match, this is displayed on the display surface of the display device 13. Further, when it is determined that they match, the person is authenticated. That is, face authentication is performed. Even when the orientation of the face of the subject Q cannot be accurately adjusted or controlled when the subject Q is captured by the cameras 11a to 11d, the discrimination accuracy or the authentication accuracy can be maintained robustly.

  2 is a diagram illustrating an example of the arrangement state of the cameras 11a to 11d with respect to the subject Q, FIG. 3 is a diagram illustrating an example of a head image GDKa to d of the subject Q photographed by the cameras 11a to 11d, and FIG. FIG. 5 is a diagram showing an example of the registered face image TJK, FIG. 5 is a diagram showing the matching degree between the images GDKa to d and the registered face image TJK in association with the position of each camera, and FIG. 6 is an image GDKa to d and the registered face image TJK. It is a figure of the other example which matches and shows the matching degree with the position of each camera.

  In FIG. 2, cameras 11 a to 11 d are installed so that images GDKa to d with different face orientations with respect to the subject Q can be obtained. In order to represent the shooting directions of the cameras 11a to 11d, the angle differences in the respective optical axis directions with respect to a certain reference direction KH are set to θa to θd, respectively. As shown in FIG. 2, the reference direction KH can be set to an arbitrary shooting direction. However, in order to facilitate later data processing, it is preferable to select appropriately such as matching with the optical axis direction of any of the plurality of cameras 11a to 11d or matching with the intermediate direction.

  For simplicity of explanation, the optical axes of the cameras 11a to 11d intersect at one point outside, and the size of the head of the subject Q is almost the same in each of the images GDKa to d. Assume that corners are set. However, when the relationship between the images GDKa to d and the relationship between the attribute values ZS detected by the cameras 11 a to 11 d are known in advance, the present invention is not limited to these. In FIG. 2, a camera 11x is an imaginary camera arranged at a position where the front face of the person who is the subject Q is photographed. In other words, the camera 11x is ideally located at this position, but actually this camera 11x does not exist.

  3A to 3D, the images GDKa to d are images taken simultaneously by the cameras 11a to 11d, respectively.

  As shown in FIG. 4, in the attribute value calculation information storage unit 21, a registered face image TJK1 is stored as registration information TJ. In the present embodiment, the registered face image TJK1 is an average front face created based on a number of face images for a certain person. Such a method of creating an average front face is known, for example, from Japanese Patent Application Laid-Open No. 2003-271958. However, the registration information TJ or the registered face image TJK is not limited to this. Further, the content of the attribute value ZS is not limited to the description here.

  In FIG. 5, the collation degree V with the registered face image TJK is shown on the vertical axis with the horizontal axis as the angular position of each of the cameras 11 a to 11 d. That is, here, the matching degree V is used as the attribute value ZS. The collation degrees of the respective images GDKa to d are Va to Vd, and the maximum value among them is Vb. However, since it is preferable to perform collation using the image GDKx photographed from the position of the imaginary camera 11x shown in FIG. 2, the threshold value Th used for comparison with the collation degree V at this time is It is set to be lower than the collation degree V with respect to the imaginary image GDKx by the imaginary camera 11x.

  That is, when the matching degree V is higher than the threshold value Th, it is assumed that the front face is detected, and when it is low, the front face is not detected. However, in FIG. 5, since the threshold value Th is higher than the maximum matching degree Vb, it is determined that there is no face as it is.

  Therefore, a curve LK passing through all four points (θa, Va) (θb, Vb) (θc, Vc) (θd, Vd) indicating the matching degree of the images GDKa to d is obtained, and the maximum value of the curve LK is obtained. To obtain the maximum value MaxV. Assuming that the maximum value MaxV is an image GDKx obtained by the camera 11x, that is, that it is a face image in front of the person, this is compared with the threshold value Th.

  Accordingly, the maximum value MaxV is compared with the threshold value Th after all, and the maximum value MaxV is larger than the threshold value Th, so that it is determined that the face of the person who is the subject Q matches the registered face image TJK. That is, face authentication for the person is performed, and the authentication result is “YES” or “OK”.

  Note that the maximum value MaxV here is the maximum matching degree, and corresponds to the maximum attribute value ZM in the present invention. Further, it is estimated that the virtual image GDKx corresponding to the maximum value MaxV is the front face of the person.

  Note that FIG. 5 shows a case where all four points are on one curve (parabola) LK, but four points are not always on one curve. It is also possible to calculate a parabola that minimizes the mean square error, calculate other types of curves, and use existing interpolation methods such as cubic convolution and spline functions.

  The algorithm for obtaining these maximum values MaxV may be determined according to the nature of the face orientation and the degree of change of the attribute value ZS, restrictions on the device configuration, such as processing speed, memory capacity, and type of computing unit. In addition, when the nature of the change degree of the attribute value ZS is not theoretically determined, the attribute value ZS may be statistically obtained from the results for a plurality of registered face images TJK.

  Further, in FIG. 6, in order to obtain the maximum value MaxV from four points, two straight lines LT1 respectively connecting two points (θa, Va) (θb, Vb), (θc, Vc) (θd, Vd). The intersection of LT2 is adopted. That is, the collation degree V at the intersection of the two straight lines LT1 and LT2 is set to the maximum value MaxV.

  It should be noted that a portion having a high probability of the matching degree V, that is, the attribute value ZS, for example, the entire head of a person, without performing processing on all four images GDKa to d obtained from the installed cameras 11a to 11d. Only a camera that is considered to be disposed in the vicinity of the front direction among a plurality of cameras that capture the image may be used. By doing so, it is possible to improve accuracy and improve processing speed. Further, the number and position of the cameras 11a to 11d may be limited, or may be selected from the whole and used.

  Next, an example of a processing operation by the subject discrimination device 1 will be described with reference to a flowchart.

  FIG. 7 is a flowchart of face discrimination processing in the subject discrimination device 1.

  In FIG. 7, images GDKa to d are sequentially input from the cameras 11 a to d to the processing device 12. First, for the first input image GDK (# 11), the image GDK is compared with the registered face image TJK. The degree V is calculated (# 12). The next image GDK is input (# 13), and steps # 11 to 13 are repeated until all the images GDK are input (# 14). Then, based on all the obtained matching degrees V, the maximum matching degree is estimated and obtained (# 15). The maximum matching degree is compared with the threshold value Th (# 16), it is determined whether or not they match by comparison (# 17), and the result is output (# 18).

  In the above embodiment, the cameras 11a to 11d are arranged only in the horizontal direction, but they may also be arranged in the vertical direction and the oblique direction. Further, as shown in FIG. 8, the cameras 11a, b, c, d, e... May be arranged in a three-dimensional space. When the relationship between the positions and angles between the cameras is known, the intervals at which the cameras are arranged may not be the same and may differ from camera to camera.

  In the embodiment described above, the registered face image TJK with the average front face is used as the registration information TJ. The registration information TJ may be stored in a state of being converted into a feature amount, and by registering information other than an image related to another registered image or a face image, various subject determination processes or It can be applied to face recognition processing. When a personal face image is used as the registration information TJ, the attribute value ZS obtained is the face matching level V or the authentication level. Further, for example, as the registration information TJ, information such as the threshold value Th2 of the skin color area ratio is registered instead of the registered face image TJK, and the skin color area ratio detected from each image GD obtained from the cameras 11a to 11d is registered. The skin color area ratio threshold Th2 may be compared. In this case, since the image GD photographed from the front direction of the face is a front face, the skin color area ratio is high, and the skin color area ratio decreases due to the influence of the hair as the image GD is photographed from an oblique direction. It is possible to perform front face detection using.

Further, the face orientation of the registered face image TJK is not limited to the front face. For example, a profile may be used. When the registered face image TJK is a side face, the matching degree V is high when the input image GD is a side face, and is low when the input face GD is a front face. In addition, the same effect as described above can be obtained if the attribute value changes with a high correlation with the difference in face orientation between the input image GD and the registered face image TJK. For example, regarding whether or not a face is a round face and what words are spoken from the shape of the mouth, it is easier to judge from the front side than from the side of the person. This is because in the case of a profile, it is difficult to obtain horizontal information about the contour of the face and the shape of the mouth. That is, for the attribute value ZS depending on the direction of the subject Q, for example, the utterance content, the face outline, etc., the effect of the subject discrimination device 1 of this embodiment is great.
[Second Embodiment]
In an application for security purposes, it is also necessary to deal with unauthorized access such as impersonation in which the subject Q is impersonated using a photograph instead of the person himself / herself. The following describes the subject discrimination device 1B that has dealt with such unauthorized access.

  Since the subject discrimination device 1B of the second embodiment is basically the same as the subject discrimination device 1 described above, only the differences will be described.

  FIG. 9 is a block diagram showing a functional configuration of the subject discrimination device 1B according to the second embodiment of the present invention, and FIG. 10 shows an example of pre-constructed subject Q images GDSa-d taken by the cameras 11a-d. FIG. 11 is a diagram showing curves LK2 and LK3 based on the respective matching degrees V of the person's image GD and the impersonated images GDSa to d, FIG. 12 is a diagram showing an example of the registered face image TJK2, and FIG. These are figures which show the other example of curve LK4, 5 based on each collation degree V with the image GD of the principal person, and the image GDSa-d impersonated.

  In FIG. 9, the processing device 12B of the subject discrimination device 1B includes a face image storage unit 21B, a matching degree calculation unit 22B, a discrimination unit 24B, a threshold value storage unit 25B, and the like.

  In the face image storage unit 21B, a face image is stored as a registered face image TJK. The matching level calculation unit 22B calculates the matching level V for each image GD obtained from the cameras 11a to 11d.

  The discriminating unit 24B determines whether or not the subject Q is the person of the registered face image TJK with respect to the curve approximated by the points indicating the plurality of collation degrees V calculated by the collation degree calculation unit 22B. By comparing, it is determined whether or not the face of the person matches the registered face image TJK.

  That is, FIG. 10 shows imperfect images GDSa to d when a photograph is used as the subject Q. In plane information such as a photograph, as shown in FIG. 10, the obtained images GDSa to d do not change greatly in the arrangement of the parts, and only the scales of the top, bottom, left and right change greatly as shown in FIG. 10. The image looks like this. Therefore, as shown in FIG. 11, a significant difference is generated between the curve LK2 based on the matching degree V of the person's image GD and the curve LK3 based on the matching degree V of the spoofed images GDSa to d.

  FIG. 11 shows a curve LK3 in the case of a matching algorithm in which the matching degree V is greatly influenced by the arrangement of the parts, and a more rapid change appears than the curve LK2 for a real person. In this case, by calculating the curvature of the curve LK at the position where the maximum matching degree is obtained and comparing it with a normal curvature estimated value obtained empirically, it is possible to determine whether or not it is impersonated. The empirical curvature estimation value may be an average value calculated from the degree of matching near the front face for a large number of sample persons, or if the person himself understands that shooting from various angles, The curvature may be calculated and used for images taken from various angles. Moreover, what is necessary is just a thing which can detect the difference of a change even if it is not a curvature. For example, it is also possible to use a difference with the matching degree of the image GD by an adjacent camera.

  Further, in the case of a collation algorithm that relies on the head contour or the like rather than the arrangement of the parts, it is the reverse of the case of FIG. 11, and a curvature that is abnormally smaller than the original curvature can be obtained at the position of the maximum collation degree. It becomes.

  A registered face image TJK2 illustrated in FIG. 12 is an image obtained by reducing the scale of the front face image of a person in the left-right direction. When face discrimination is performed using such a registered face image TJK2, in the case of impersonation, it is checked against images GD photographed by the cameras 11a and d at positions close to the ends like the cameras A and D. The degree V increases.

  That is, as shown in FIG. 13, a significant difference occurs between the curve LK4 based on the matching degree V of the person's image GD and the curve LK5 based on the matching degree V of the spoofed images GDSa to d. In the case of the curve LK5, the matching degree is considerably high at the end, and the difference from the case of the curve LK4 becomes large. As described above, by using the difference between the two curves LK4 and LK5, it is possible to determine whether or not it is impersonated. Thereby, impersonation impersonation in person face authentication can be prevented.

The feature points in each embodiment described above can be organized as follows.
(1) Face recognition is performed using a plurality of cameras and a single registered face image.
(2) Face discrimination or face recognition for an image is performed only for each individual camera. Relationships between face images obtained by a plurality of cameras are associated with the results of face discrimination or face recognition.
(3) When the matching level V with the registered face image TJK is the attribute value ZS, the attribute value ZS for the face photographed in the direction close to the face direction of the registered face image TJK and the face photographed in the far direction The attribute value ZS is calculated for an image taken in the same direction as the face direction of the registered face image TJK, using the property that the value is larger in the case of the close direction. The attribute value ZS is estimated from a limited number of images, and recognition is performed using the estimated attribute value ZS (maximum attribute value ZM). Any type of face recognition can be used as long as it recognizes information correlated with the direction of the face. For example, it can be applied to face authentication, age estimation, facial expression discrimination, and the like.

Therefore, each embodiment described above has the following advantages.
(1) Discrimination and recognition are possible even if the orientation of the camera relative to the subject Q is not necessarily the same as that of the registered face image TJK, and the robustness of discrimination and recognition is improved.
(2) Only one two-dimensional image is required for the registered face image TJK for one person.
(3) The information handled in an integrated manner in the subject discrimination device is a subject discrimination result (a face discrimination result or a face recognition result), not an image. Therefore, the data amount is small, the processing speed is fast, and the configuration of the subject discrimination device is simplified.
(4) The subject discrimination device can be applied to applications other than face discrimination, face recognition, face authentication, etc., and can have a general-purpose configuration.

  Thus, according to the embodiment described above, even when the subject Q is not photographed in the same direction as the registered image, it is possible to robustly determine whether or not they match. In addition, the amount of data such as registered images is small, and processing can be performed at high speed.

  In the above-described embodiment, the structure, configuration, shape, dimensions, number, contents of image, contents and order of processing, timing, etc. of the whole or each part of the cameras 11a to 11d, the processing device 12, the subject discrimination device 1, etc. These can be appropriately changed in accordance with the spirit of the present invention.

  The present invention can be used for authentication by a human face for security or the like.

It is a block diagram which shows the function of the to-be-photographed object determination apparatus of the 1st Embodiment of this invention. It is a figure which shows the example of the arrangement | positioning state of the camera with respect to a to-be-photographed object. It is a figure which shows the example of the image of the head of the to-be-photographed object image | photographed with each camera. It is a figure which shows the example of a registration face image. It is a figure which shows the collation degree with an image and a registration face image in association with the position of each camera. It is a figure which shows the other example similar to FIG. 5 is a flowchart of face discrimination processing in the subject discrimination device. It is a figure which shows the example which has arrange | positioned the camera in three-dimensional space. It is a block diagram which shows the function of the to-be-photographed object identification apparatus of the 2nd Embodiment of this invention. It is a figure which shows the example of the image of the impersonated subject image | photographed with each camera. It is a figure which shows the curve based on the person's image and the impersonated image. It is a figure which shows the example of a registration face image. It is a figure which shows the other example of the curve based on the person's image and the impersonated image.

Explanation of symbols

1,1B Subject discrimination device (face discrimination device)
11 Camera 12, 12B Processing device 21, 21B Attribute value calculation information storage unit ()
22, 22B Attribute value calculation unit (attribute value calculation means, coincidence degree calculation means)
23 Maximum attribute value calculation unit (maximum attribute value calculation means, maximum matching degree calculation means)
24, 24B Discriminator (discriminating means)
25 Threshold value storage section Q Subject ZS Attribute value V Verification degree (attribute value)
ZM Maximum attribute value (maximum degree of matching)
Th threshold GD image TJ registration information (registered image, registered face image)
TJK registered face image LK curve

Claims (7)

A subject determination method for determining whether or not a subject matches registration information,
Acquiring a plurality of images of a specific part of the subject by a plurality of cameras whose positional relationships are known; and
Calculating an attribute value by comparing with the registration information for each acquired image;
Calculating a maximum attribute value that is a maximum value of the attribute value when the subject is closest to the registration information based on the plurality of calculated attribute values;
Comparing the calculated maximum attribute value with a threshold value to determine whether or not the subject matches registration information;
A method for discriminating a subject characterized by comprising: A subject determination method for determining whether or not a subject matches a registered image,
Acquiring a plurality of images of a specific part of the subject by a plurality of cameras whose positional relationships are known; and
Calculating a degree of coincidence with the registered image for each acquired image;
Calculating a maximum degree of coincidence, which is a degree of coincidence when the subject is facing the direction closest to the direction of the registered image, based on the plurality of calculated degree of coincidence;
Comparing the calculated maximum matching degree with a threshold value to determine whether or not the subject matches the registered image;
A method for discriminating a subject characterized by comprising: A subject determination device for determining whether a subject matches a registered image,
A plurality of cameras whose positional relationships are known to acquire an image of a specific part of the subject;
Attribute value calculating means for calculating an attribute value for each acquired image;
A maximum attribute value calculating means for calculating a maximum attribute value that is a maximum value of the attribute value when the subject is oriented in the direction closest to the orientation of the registered image, based on the plurality of calculated attribute values;
A determining means for comparing the calculated maximum attribute value with a threshold value to determine whether or not the subject matches a registered image;
A subject discrimination device characterized by comprising: A face discriminating device for discriminating whether or not a face of a person as a subject matches a registered face image,
A plurality of cameras whose positional relationships are known to obtain an image of the head of the subject;
A degree of coincidence calculating means for calculating a degree of coincidence with the registered face image for each acquired image;
Based on the plurality of coincidence degrees calculated by the coincidence degree calculating unit, a maximum coincidence degree that is a coincidence degree when the person's face is oriented in the direction closest to the orientation of the registered face image is calculated. A matching degree calculation means;
A determining unit that compares the calculated maximum matching degree with a threshold value to determine whether the face of the person matches the registered face image;
A face discriminating apparatus characterized by comprising: The registered face image is a front average face image of a person.
The face discrimination device according to claim 4. The maximum matching degree calculating means calculates a maximum point of a curve approximated by a plurality of points indicating the matching degree as the maximum matching degree;
The face discrimination device according to claim 4 or 5. A face discriminating device for discriminating whether or not a face of a person as a subject matches a registered face image,
A plurality of cameras whose positional relationships are known to obtain an image of the head of the subject;
A degree of coincidence calculating means for calculating a degree of coincidence with the registered face image for each acquired image;
For a curve approximated by a plurality of points indicating the degree of coincidence calculated by the coincidence degree calculating means, by comparing the case where the subject is the person of the registered face image with the case where it is not, Determining means for determining whether the face of the person matches the registered face image;
A face discriminating apparatus characterized by comprising: