JP2008250830A - Attendance checking system and attendance checking method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an attendance checking system capable of alleviating checker's burden, eliminating a need for attendant's procedure at a site, and eliminating the need for an attendant to hold and manage a card, and so on. <P>SOLUTION: The attendance checking system comprises a first storage means with a face image of an attendant desiring to attend the room of an examination site, for example, prestored therein in association with location information of a seat designated for seating by the attendant; and a second storage means with location information of each seat in the room prestored therein. The attendance check system images an overall image of the room; acquires from the photographed the facial image of the attendant seating in each seat, based on the location information of each seat stored in the second storage section; compares the acquired face image with the face image acquired from the first storage section, based on the location information of the seat seated by the attendant from whom the face image is acquired; determines the attendant as being present, when a predetermined relation exists between the two facial images, and determines the attendant as being absent, when there is no predetermined relation established between the two facial images. <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

  The present invention relates to an attendance confirmation system and attendance confirmation method for automatically confirming attendance of attendees in a room (attendance target area) where attendees and seats need to match, for example, in a test venue where many people gather. .

Conventionally, as an attendance confirmation system of this type, attendance confirmation is performed by placing an IC card carried by an attendee over a wireless tag reader / writer in the vicinity of the seat, and from ID information and position information read from the IC card. It is known that an attendee status map is displayed on a display as an image (see, for example, Patent Document 1).
JP 2005-267355 A

However, in the known technique of Patent Document 1, the attendee needs to manage the IC card and bring it to the venue, which is not only a burden for the attendee but also requires a procedure at the venue.
In addition, when the IC card is lost, an extra procedure is required when the IC card is not carried. Furthermore, since the identity authentication is performed using an IC card, there is a problem that it is difficult to prevent fraud.

  Accordingly, the present invention provides an attendance confirmation system and attendance confirmation method that reduces the burden on the confirmation worker, eliminates the need for attendees at the venue, and eliminates the need for possession management of cards and the like. Objective.

  The attendance confirmation system according to the present invention provides a face image of an attendee who wishes to attend an attendance target area having a plurality of seats therein, and position information of the seat in which the attendee is designated to be seated in the attendance target area. First storage means stored in advance in correspondence with each other, second storage means storing in advance position information of each seat in the attendance target area, and at least each seat portion in the attendance target area And an image of the attendee seated in each seat on the basis of the position information of each seat stored in the second storage means from the image obtained from the imaging means Face image acquisition means, a face image acquired by the face image acquisition means, and a face image acquired from the first storage means based on position information of a seat where the attendee who acquired the face image is seated When Collating, when a predetermined relationship between the two face images is satisfied, it is determined that the attendance, if a predetermined relationship between the two face images is not satisfied is provided and determining matching means and absent.

  The attendance confirmation system according to the present invention also provides a face image of an attendee who wishes to attend an attendance target area having a plurality of seats therein, and the attendance of the seat designated by the attendee in the attendance target area. First storage means stored in advance corresponding to position information, second storage means storing in advance position information of each seat in the attendance target area, and an image including at least the faces of attendees A face image of an attendant seated in each seat is obtained by changing an imaging field of view of the imaging means based on position information of each seat stored in the second storage means Face image acquisition means, a face image acquired by the face image acquisition means, and a face image acquired from the first storage means based on position information of a seat where the attendee who acquired the face image is seated And match If a predetermined relationship between the two face images is satisfied, it is determined that the attendance, if a predetermined relationship between the two face images is not satisfied is provided and determining matching means and absent.

  The attendance confirmation system according to the present invention also provides a face image of an attendee who wishes to attend an attendance target area having a plurality of seats therein, and the attendance of the seat designated by the attendee in the attendance target area. A plurality of imaging units configured to capture images including at least faces of attendees seated in the seat, each of which is installed in each seat in the attendance target area; The face image acquired by the plurality of imaging means and the face image acquired from the first storage means based on the position information of the seat where the imaging means is installed. If a predetermined relationship is established between the two face images, a collation unit is provided, and if the predetermined relationship is not established between both face images, there is a verification unit that determines absence.

  Further, the attendance confirmation method of the present invention provides a face image of an attendee who wishes to attend an attendance target area having a plurality of seats therein, and the attendee's seat designated in the attendance target area. A first storage means for storing in advance corresponding to the position information; and a second storage means for storing in advance the position information of each seat in the attendance target area. An image including at least each seat portion is captured by the imaging unit, and the face image of the attendee seated in each seat based on the position information of each seat stored in the second storage unit from the captured image The acquired face image is compared with the face image acquired from the first storage means based on the position information of the seat where the attendee who has acquired the face image is seated, A predetermined relationship between If it is determined to attend, if a predetermined relationship between the two face images is not satisfied and judging the absence.

  Further, the attendance confirmation method of the present invention provides a face image of an attendee who wishes to attend an attendance target area having a plurality of seats therein, and the attendee's seat designated in the attendance target area. First storage means prestored in correspondence with the position information, and second storage means preliminarily storing position information of each seat in the attendance target area, the second storage Based on the position information of each seat stored in the means, the face image of the attendee seated in each seat is obtained by changing the imaging field of view of the imaging means for capturing an image including at least the face of the attendee The acquired face image is collated with the face image acquired from the first storage means based on the position information of the seat where the attendee who has acquired the face image is seated, and a predetermined value is set between both face images. If the relationship is established, attendance and Constant and, when a predetermined relationship between the two face images is not satisfied and judging the absence.

  Further, the attendance confirmation method of the present invention provides a face image of an attendee who wishes to attend an attendance target area having a plurality of seats therein, and the attendee's seat designated in the attendance target area. An image including at least a face of an attendee seated in the seat by an imaging means provided in each seat in the attendance target area, having first storage means stored in advance corresponding to position information And the face image acquired from the first storage unit based on the position information of the seat where the imaging unit is installed is collated, and a predetermined relationship is established between the two face images. If it is established, it is determined to be attended, and if a predetermined relationship is not established between both face images, it is determined to be absent.

  According to the present invention, automatic attendance confirmation reduces the burden on the confirmation worker, eliminates the need for attendees at the venue, and eliminates the need for possession management of cards, etc. Can provide system and attendance confirmation method.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.
First, the first embodiment will be described.
FIG. 1 schematically shows the configuration of an attendance confirmation system according to the first embodiment. In the following description, for example, a case where attendance of attendees is automatically confirmed in a room where the attendees and seats need to match, such as a test venue where many people gather, will be described.

  In FIG. 1, it is assumed that a room 20 as a venue is provided with, for example, two entrances 1 and 2. In the room 20, a large number of desks 3 for attendees are arranged, and each of these desks 3 is provided with a plurality (three in the figure) of seats 4. Assume that M is seated. In addition, a desk 5 for attendance checker N is provided in front of room 20. Here, it is assumed that each seat 4 is assigned a unique seat number (for example, 1, 2, 3,...) Sequentially.

  A video camera (hereinafter simply abbreviated as a camera) as an imaging means for capturing an image including at least each seat portion, in this example, an image of the entire room, at an intermediate position in the horizontal direction with respect to the drawing at a predetermined front portion of the room 20 6) is installed.

  The image captured by the camera 6 is sent to the face matching server 7. The face collation server 7 performs attendance confirmation processing, which will be described in detail later. The face image database (first storage means) 8, the seat database (second storage means) 9, and the attendance confirmation results are displayed. An attendance management memory 10 for storing and managing is provided.

  In the face image database 8, face images of attendees who wish to attend are registered (stored) in advance in correspondence with the position information of the seat 4 for which the attendee is designated to be seated. The face images of attendees who wish to attend are registered by the face image registration device 12 described later.

  The information to be registered in association with the face image is not limited to the seat position information, but the attendee's examination number (1D number) and name may be registered together. Further, the position information of each seat 4 is acquired by a method that will be described in detail later.

  In the seat database 9, the position information of each seat 4 in the room 20 is registered (stored) in advance in association with the seat number. The position information of each seat 4 is acquired by a method that will be described in detail later.

Connected to the face matching server 7 are an output device 11 and a face image registration device 12 for displaying or printing out the result of attendance confirmation.
The face image registration device 12 is for registering the face images of attendees who wish to attend, and the registration method is, for example, by using a dedicated terminal device installed in a university or in the city, or by applying on the Internet. To do. When applying with a dedicated terminal device, it is done with a terminal device having a camera and a face registration system. When applying with the Internet, a face image captured by a mobile phone or a digital camera is transferred over the Internet, so that the face matching server 7 Registered in the image database 8.

  Here, the 1st acquisition method which acquires the positional information on each seat 4 is demonstrated. The first acquisition method is to manually measure the distance from the installation position of the camera 6 to the seat 4 (the face of the attendee M), and the orientation of the camera 6 (imaging field of view) at that time, and measure the measured value. 4 is registered in the seat database 9 together with the seat number.

  Next, the 2nd acquisition method which acquires the positional information on each seat 4 is demonstrated. The second acquisition method is automatically performed by the face matching server 7, and the processing procedure is shown in the flowchart of FIG. First, it is assumed that a seal as a mark is pasted on the desk 3 corresponding to each seat 4 in advance.

  In this state, the entire room 20 is imaged by the camera 6 (step S1). Next, the sticker provided on the desk 3 is detected using the captured whole image (step S2). Next, by using the entire captured image, the distance from the detected seal position (the face of the attendee M) to the installation position of the camera 6 and the direction of the camera 6 (imaging field of view) at that time are determined. The measurement is automatically performed (step S3). Next, the measured value is registered in the seat database 9 together with the seat number as position information of the seat 4 (step S4). The processes from step S2 to S4 are repeated for each seat 4 (step S5).

  Next, the 3rd acquisition method which acquires the positional information on each seat 4 is demonstrated. The third acquisition method is also performed automatically by the face matching server 7, and the processing procedure is shown in the flowchart of FIG. First, it is assumed that a face image of a person as a sample is registered in the face image database 8 in advance.

  In this state, a person who actually becomes a sample is seated in a certain seat 4, and the face image of the person is taken by manually adjusting the direction of the camera 6 (steps S11 and S12). Next, the photographed face image is collated with a face image of a person as a sample registered in advance in the face image database 8 (step S13).

  As a result of this collation, if a predetermined relationship is not established between both face images, in this example, if both face images do not match (step S13), the process returns to step S11 and the same processing is repeated, If a predetermined relationship is established between the two face images in this example (step S13), it is determined that the orientation and distance of the camera 6 with respect to the seat 4 are appropriate, and from the installation position of the camera 6 The distance to the seat 4 and the direction of the camera 6 at that time are measured, and the measured value is registered in the seat database 9 together with the seat number as the position information of the seat 4 (step S15). The process from step S11 to S16 is repeated for each seat 4 (step S16).

  Next, the flow of attendance confirmation processing according to the first embodiment in such a configuration will be described with reference to the flowchart shown in FIG. First, the entire room 20 is imaged by the camera 6 (step S21). Next, the position information of each seat 4 registered in advance in the seat database 9 is read (step S22).

  Next, from the imaged image of the entire room, portions that are considered to be facial images in each seat 4 are sequentially extracted based on the position information of each seat 4 read from the seat database 9 (step S23). That is, after detecting a person-like appearance in each seat 4 based on the position information of the seat 4 from the imaged image of the entire room, the eyes and nose are searched from the person image and feature information is extracted to perform face detection processing. By doing so, it is determined that the person is a person, and it is detected that the attendee M is seated on the seat 4.

  Note that the extraction of the part that seems to be a face image in step S23 may be performed by the image processing as described above. For example, an image of the entire imaged room is displayed on the display, and on the display screen, a staff member is displayed. May indicate the face image of the attendee M using a touch pen or the like.

  Next, the detected face image is collated with the face image retrieved from the face image database 8 based on the position information of the seat 4 where the face image is detected (step S24). As a result of this collation, when a predetermined relationship is established between both face images, in this example, when both face images match (step S25), it is determined that a regular attendee M is present ( In step S26), when a predetermined relationship is not established between both face images, in this example, if both face images do not match (step S25), it is determined that the regular attendee M is absent (step S26). In S27, the determination result is stored and managed in the attendance management memory 10 together with the corresponding seat number and the like, and is output by the output device 11 (step S28). Needless to say, if no face image is detected, it is determined that the attendee M is absent.

  The processing from step S23 to S28 is repeated for each seat 4 (step S29). For example, it is assumed that the seat number is sequentially repeated from the smallest seat number to the largest seat number.

  As described above, according to the first embodiment, automatic attendance confirmation reduces the burden on the confirmation worker, eliminates the need for attendees at the venue, and provides a card. There is no need to manage the possession. In addition, a system can be constructed for each room, and attendance confirmation can be realized at low cost.

  Furthermore, fraud such as card reuse can be prevented by performing face matching while seated. In addition, the attendee's face images can be stored and reused for a certain period of time, and the pre-registration procedure can be omitted. In addition, it is possible to grasp the entry / exit situation by periodically taking a picture of the sitting situation with a camera.

Next, a second embodiment will be described.
Since the system configuration is the same as that of the first embodiment described above, a description thereof will be omitted, and only the parts different from the first embodiment will be described in detail.
First, in the second embodiment, it is assumed that the camera 6 can variably control the direction (imaging field of view).

  Next, the flow of attendance confirmation processing according to the second embodiment will be described with reference to the flowchart shown in FIG. First, the position information of each seat 4 registered in advance in the seat database 9 is read (step S31).

  Next, based on the position information of each seat 4 read from the seat database 9, a face image is acquired by sequentially imaging the camera 6 in accordance with the direction (imaging field of view) of each seat 4 (step S32). That is, after detecting a person-like appearance from the imaged image of the seat 4, the eyes and nose are searched from the person image, and feature information is extracted and face detection processing is performed, and it is determined that the person is a person. It is detected that the attendee M is seated on the seat 4.

  Next, the detected face image is collated with the face image retrieved from the face image database 8 based on the position information of the seat 4 where the face image is detected (step S33). As a result of this collation, when a predetermined relationship is established between both face images, in this example, when both face images match (step S34), it is determined that a regular attendee M is present ( In step S35), when a predetermined relationship is not established between both face images, in this example, if both face images do not match (step S34), it is determined that the regular attendee M is absent (step S35). S36) The determination result is stored and managed in the attendance management memory 10 together with the corresponding seat number and the like, and is output by the output device 11 (step S37). Needless to say, if no face image is detected, it is determined that the attendee M is absent.

  The process from step S32 to S37 is repeated for each seat 4 (step S38). For example, it is assumed that the seat number is sequentially repeated from the smallest to the largest.

  As described above, according to the second embodiment, automatic attendance confirmation reduces the burden on the confirmation worker, eliminates the need for attendees at the venue, and provides a card. There is no need to manage the possession. In addition, a system can be constructed for each room, and attendance confirmation can be realized at low cost.

  Furthermore, since each attendee is imaged individually, individual correspondence can be performed as compared with the first embodiment. Also, by performing face matching while seated, fraud such as card reuse can be prevented. In addition, the attendee's face images can be stored and reused for a certain period of time, and the pre-registration procedure can be omitted. In addition, it is possible to grasp the entry / exit situation by periodically taking a picture of the sitting situation with a camera.

  In the first and second embodiments, the case where one camera 6 is used has been described. However, a plurality of cameras, for example, cameras 6 are installed at the four corners of the room 20 as shown in FIG. By doing so, the room 20 may be divided into four equal parts, and the attendance confirmation process may be divided and performed.

Next, a third embodiment will be described.
Since the basic system configuration is the same as that of the first embodiment described above, description thereof will be omitted, and only parts different from those of the first embodiment will be described in detail.
First, in the third embodiment, for example, as shown in FIG. 7, a camera 6 is installed in each part corresponding to each seat 4 on each desk 3, and a face image of each attendee M is individually captured. It shall be.

  Next, the flow of attendance confirmation processing according to the third embodiment will be described with reference to the flowchart shown in FIG. First, the position information of each seat 4 registered in advance in the seat database 9 is read (step S41).

  Next, based on the position information of the seat 4 read from the seat database 9, a face image is acquired by sequentially capturing images of each seat 4 with the camera 6 installed for each seat 4 (step S42). . That is, after detecting a person-like appearance from the imaged image of the seat 4, the eyes and nose are searched from the person image, and feature information is extracted and face detection processing is performed, and it is determined that the person is a person. It is detected that the attendee M is seated on the seat 4.

  Next, the detected face image is collated with the face image searched from the face image database 8 based on the position information of the seat 4 where the camera 6 that detects the face image is installed (step S43). As a result of this collation, when a predetermined relationship is established between both face images, in this example, when both face images match (step S44), it is determined that the regular attendee M is present ( In step S45), when a predetermined relationship is not established between both face images, in this example, when both face images do not match (step S44), it is determined that the regular attendee M is absent (step S44). S46), the determination result is stored and managed in the attendance management memory 10 together with the corresponding seat number and the like, and is output by the output device 11 (step S47). Needless to say, if no face image is detected, it is determined that the attendee M is absent.

  The processing from step S42 to S47 is repeated for each camera 6 (each seat 4) (step S48). For example, it is assumed that the seat number is sequentially repeated from the smallest to the largest.

  As described above, according to the third embodiment, automatic attendance confirmation reduces the burden on the confirmation worker, eliminates the need for attendee procedures at the venue, and provides a card. There is no need to manage the possession. In addition, a system can be constructed for each room, and attendance confirmation can be realized at low cost.

  In addition, since each attendee is imaged, individual correspondence can be performed as compared with the first embodiment. In addition, since the camera is installed for each seat, the setting of the camera position and orientation is simpler than in the first embodiment, the attendee's face image can be taken from below, and accurate imaging is possible. Easy.

  Furthermore, fraud such as card reuse can be prevented by performing face matching while seated. In addition, the attendee's face images can be stored and reused for a certain period of time, and the pre-registration procedure can be omitted. In addition, it is possible to grasp the entry / exit situation by periodically taking a picture of the sitting situation with a camera.

The schematic diagram which shows schematically the structure of the attendance confirmation system which concerns on the 1st Embodiment of this invention. The flowchart explaining the 1st acquisition method which acquires the positional information on a seat. The flowchart explaining the 2nd acquisition method which acquires the positional information on a seat. The flowchart explaining the flow of the attendance confirmation process which concerns on the 1st Embodiment of this invention. The flowchart explaining the flow of the attendance confirmation process which concerns on the 2nd Embodiment of this invention. The schematic diagram explaining the modification of the attendance confirmation system which concerns on the 1st, 2nd embodiment of this invention. The schematic diagram which shows schematically the principal part structure of the attendance confirmation system which concerns on the 3rd Embodiment of this invention. The flowchart explaining the flow of the attendance confirmation process which concerns on the 3rd Embodiment of this invention.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 20 ... Room (Attendance object area), 1, 2 ... Entrance / exit, 3, 5 ... Desk, 4 ... Seat, M ... Attendee, 6 ... Camera (imaging means), 7 ... Face collation server, 8 ... Face image database ( (First storage means), 9 ... seat database (second storage means), 10 ... attendance management memory, 11 ... output device, 12 ... face image registration device.

Claims (6)

A face image of an attendee who wants to attend an attendance target area having a plurality of seats is stored in advance in association with position information of the seat in which the attendee is seated in the attendance target area. First storage means,
Second storage means for storing in advance position information of each seat in the attendance target area;
Imaging means for capturing an image including at least each seat portion in the attendance target area;
Face image acquisition means for acquiring a face image of an attendee seated in each seat based on positional information of each seat stored in the second storage means from an image obtained from the imaging means;
The face image acquired by the face image acquisition means is compared with the face image acquired from the first storage means based on the position information of the seat where the attendee who has acquired the face image is seated, A collating means for determining attendance when a predetermined relationship is established between images and determining absence when a predetermined relationship is not established between both face images;
An attendance confirmation system characterized by comprising: A face image of an attendee who wishes to attend an attendance target area having a plurality of seats is stored in advance in association with position information of the seat in which the attendee is seated in the attendance target area. First storage means,
Second storage means for storing in advance position information of each seat in the attendance target area;
Imaging means for capturing an image including at least a face of the attendee;
Face image acquisition means for acquiring a face image of an attendee seated in each seat by changing an imaging field of view of the imaging means based on position information of each seat stored in the second storage means;
The face image acquired by the face image acquisition means is compared with the face image acquired from the first storage means based on the position information of the seat where the attendee who has acquired the face image is seated, A collating means for determining attendance when a predetermined relationship is established between images and determining absence when a predetermined relationship is not established between both face images;
An attendance confirmation system characterized by comprising: A face image of an attendee who wants to attend an attendance target area having a plurality of seats is stored in advance in association with position information of the seat in which the attendee is seated in the attendance target area. First storage means,
A plurality of imaging means installed at each seat in the attendance target area, for capturing images including at least faces of attendees seated in the seat;
The face image acquired by the plurality of image pickup means is compared with the face image acquired from the first storage means based on the position information of the seat where the image pickup means is installed, and a predetermined value is set between both face images. If the relationship is established, it is determined to be attending, and if the predetermined relationship is not established between both face images, collation means for determining absence,
An attendance confirmation system characterized by comprising: A face image of an attendee who wishes to attend an attendance target area having a plurality of seats is stored in advance in association with position information of the seat in which the attendee is seated in the attendance target area. First storage means, and second storage means for storing in advance position information of each seat in the attendance target area,
Taking an image including at least each seat portion in the attendance target area by an imaging means,
Acquire face images of attendees seated in each seat based on the position information of each seat stored in the second storage means from the captured image,
The acquired face image is collated with the face image acquired from the first storage unit based on the position information of the seat where the attendee who has acquired the face image is seated, and a predetermined image is provided between the two face images. If the relationship is established, it is determined to be attended, and if the predetermined relationship is not established between the two face images, it is determined to be absent.
An attendance confirmation method characterized by that. A face image of an attendee who wants to attend an attendance target area having a plurality of seats is stored in advance in association with position information of the seat in which the attendee is seated in the attendance target area. First storage means, and second storage means for storing in advance position information of each seat in the attendance target area,
Based on the position information of each seat stored in the second storage means, by changing the field of view of the imaging means for capturing an image including at least the face of the attendee, the attendees sitting in each seat Get a face image,
The acquired face image is collated with the face image acquired from the first storage unit based on the position information of the seat where the attendee who has acquired the face image is seated, and a predetermined image is provided between the two face images. If the relationship is established, it is determined to be attended, and if the predetermined relationship is not established between the two face images, it is determined to be absent.
An attendance confirmation method characterized by that. A face image of an attendee who wants to attend an attendance target area having a plurality of seats is stored in advance in association with position information of the seat in which the attendee is seated in the attendance target area. Having first storage means
Taking an image including at least the face of the attendee seated in the seat by the imaging means installed in each seat in the attendance target area,
When the captured face image is collated with the face image acquired from the first storage unit based on the position information of the seat where the imaging unit is installed, and a predetermined relationship is established between the two face images Is determined to be present, and if a predetermined relationship is not established between both face images, it is determined to be absent.
An attendance confirmation method characterized by that.

Images