JP2006319610A - Camera - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a camera which enables acquisition of an image where a photographed person looks in the direction of the camera by one photographing. <P>SOLUTION: The camera is provided with an image input means for inputting an image of a person or a plurality of persons including a face image, an image processing means for determining whether or not the person looks in the direction of the camera by detecting the direction of the eye line of the person from the image inputted by the image input means, and a photographing means for storing the input image determined from the result of the image processing means that the person faces a designated direction. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to an imaging apparatus that photographs a subject.

  A conventional camera is provided with a shutter release button, a self-timer, and the like. When the photographer presses these shutter release buttons or when a time set by the self-timer is reached, the image of the subject is recorded on the recording medium. To be recorded. However, it takes considerable training for the photographer to shoot at an optimal timing using a camera that captures the moment. In particular, when the subject does not look at the camera by understanding the photographer's intentions, such as an infant or infant, or when the subject's line of sight is facing the camera, such as in a group photo. When it is difficult for the photographer to grasp whether or not it is instantaneous, it is difficult to determine the optimum shutter timing unless the person is skilled in such shooting.

  Even when the photographing timing can be accurately determined, there is a possibility that only an image different from the image at the timing desired by the photographer may be obtained due to the release time lag.

As a means for acquiring an image desired by a photographer with respect to such a problem, an image pickup apparatus that can easily check an acquired image after shooting and can retake it until an optimum image is obtained (for example, Patent Document 1). An imaging device that informs the non-photographer of the shutter timing by the flashing state of the flash (for example, Patent Document 2), detects a plurality of subjects' face areas from continuous images taken for a certain period of time, and detects the detected face state Image processing means that evaluates the face state of the photographed person in each image and combines the best face of each photographed person into a single image to obtain an image in which each photographed faces the camera direction (For example, Patent Document 3).
JP 2003-52038 A JP 2001-275353 A JP 2000-259833 A

  However, in the conventional imaging devices (for example, Patent Document 1 and Patent Document 2), when a subject who does not understand the photographer's intention is a target, the subject turns the camera in one shot. It has a problem that it is difficult to take a picture.

  Further, in the conventional image processing means (for example, Patent Document 3), since there is no guarantee that an optimal face state exists in a continuous image, which is unnatural because the acquired images are synthesized, There is a problem that an image facing a specified direction may not be acquired.

  SUMMARY OF THE INVENTION The present invention solves the above-described conventional problems, and is an image pickup apparatus in which one or a plurality of subjects, or specific subjects among a plurality of subjects acquire a camera or an image directed in a predetermined direction. The purpose is to provide.

  In order to solve the above-described conventional problems, an imaging apparatus according to the present invention includes an image input unit that inputs an image of one or more persons including a face image, and the line-of-sight direction of the person from the image input by the image input unit Image processing means for detecting whether or not the person is looking at the imaging device, and storage means for saving the input image determined from the result of the image processing means that the person is looking at the imaging device And comprising.

  With this configuration, it is possible to reduce the burden on the photographer and the photographed person by acquiring an image in which the line of sight of one or more photographed persons is directed to the camera or a specific direction in one shot.

  Further, the imaging apparatus of the present invention includes warning means for warning the photographer that there is a person who is not looking at the imaging apparatus from the output of the image processing means, and shooting time input means for the photographer to input a shooting command. Furthermore, it is an imaging apparatus provided.

  With this configuration, the photographer can call attention to the photographed person who is not looking at the camera. In addition to the determination of the image processing means, the photographer can take an image at any time according to the photographer's intention. It becomes possible.

  Further, the imaging apparatus of the present invention detects one or more persons from an image input means for inputting an image, a gaze direction designation means for designating the gaze direction of the person, and an image input by the image input means, An image processing means for detecting whether or not the person's line-of-sight direction is detected and looking at the direction designated by the line-of-sight direction designating means; and an input determined from the result of the image processing means that the person is looking at the imaging device It is an imaging device provided with storage means for storing images.

  With this configuration, the photographer can photograph an image in which the subject is facing not only the camera direction but also any direction.

  In the imaging apparatus of the present invention, warning means for warning the photographer that there is a person who is not looking at the direction designated by the line-of-sight designation means from the output of the image processing means, and the photographer inputs a shooting command The imaging apparatus further includes a photographing time input unit.

  With this configuration, the photographer can smoothly advance photographing by calling attention to a subject who is not facing the designated direction or by giving an instruction for directing the designated direction. In addition to the determination of the image processing means, it is possible to take a picture at an arbitrary time according to the intention of the photographer.

  In the image pickup apparatus of the present invention, the image processing means detects a line-of-sight direction of one or more persons in the input image, and, based on the result of the line-of-sight detection means, the person is the image pickup apparatus or the previous line of sight. The imaging apparatus includes aptitude determination means for determining whether the designation means is looking in the designated direction.

  With this configuration, the line-of-sight detection means can be shared, and the image processing means of the image pickup apparatus of the present invention can be made only by changing the aptitude determination means. Therefore, the image pickup apparatus can be manufactured and supplied to the photographer quickly and inexpensively. Is possible.

  In the imaging apparatus of the present invention, the line-of-sight direction designating unit displays an input image, and a designation input unit that designates a target line-of-sight direction by designating an object, a region, and a direction in the input image. And an imaging device having designation recognition means for recognizing a designation direction from the input of the designation input means and the input image.

  With this configuration, the photographer can intuitively specify the line-of-sight direction, and the designation work is facilitated.

  In the image pickup apparatus of the present invention, the warning means outputs an image composition means for processing an image to represent a person who is determined not to look at the image pickup apparatus or the designated direction by the aptitude judgment means, and the image composition means outputs It is an imaging device which has a warning display means which displays the done image.

  With this configuration, the photographer can visually identify the photographed person and can easily identify the photographed person.

  As described above, according to the imaging apparatus of the present invention, the line of sight of one or a plurality of subjects is automatically directed to the camera or a specific direction without repeatedly checking the captured image. Images can be taken.

  In addition, when taking a group photo, the photographer can be alerted to the photographer by the warning display means that the photographer whose line of sight is not pointed at the camera can be taken. Can be completed.

  Embodiments of the present invention will be described below with reference to the drawings.

(Embodiment 1)
FIG. 1 is a block diagram showing a configuration of an imaging apparatus according to Embodiment 1 of the present invention.

  The imaging apparatus includes an image input unit 101 that inputs an image using an image sensor such as a CCD or a CMOS, an image processing unit 102 that determines whether or not shooting is possible, and a storage unit 103 that stores an image in a recording device such as a memory card or a hard disk drive. Is provided. The image processing unit 102 further includes a line-of-sight detection unit 104 that detects the line of sight of a person in the image, and an aptitude determination unit 105 that determines the optimality of the input image from the line-of-sight detection result.

  FIG. 2 shows an operation flow of the imaging apparatus. FIG. 3 shows an example of an input image when there is one person to be photographed, and FIG. 4 shows an example of an input image when there are a plurality of persons to be photographed.

  In FIG. 1 and FIG. 2, when the imaging apparatus starts a photographing operation (STEP 201), the image input unit 101 acquires an image projected on the imaging surface of the camera at regular intervals (STEP 202), and the image processing unit 102 Output to.

  Next, the gaze detection unit 104 of the image processing unit 102 detects the gaze direction of the person in the image from the image output from the image input unit 101 (STEP 203), and the gaze direction detection result is sent to the appropriate determination unit 105. Output.

  The appropriateness determining means 105 determines whether or not the line-of-sight direction is looking at the camera based on the line-of-sight direction detection result output from the line-of-sight detection means 104 (STEP 204), and outputs the appropriateness determination result to the storage means 103.

  The storage unit 103 stores the input image if the determination result output from the aptitude determination unit 106 determines that the camera is facing the camera (STEP 205), and ends the photographing operation (STEP 206). If it is determined that the camera is not facing the camera direction, it is determined that the input image is inappropriate as a captured image, and the image projected on the imaging surface is retaken (STEP 202).

  Hereinafter, the operation of this apparatus will be described. First, the operation when photographing one person will be described.

  As shown in FIGS. 3A and 3B, an image in which one person 301 is shown is set as an input image. In FIGS. 3A and 3B, a person 301 and a person 302 are photographed persons. The shooting is performed according to the following procedure.

1) Image input 2) Face area detection 3) Pupil detection 4) Eye-gaze direction detection 5) Judgment of photographing availability 6) Photographing Details of each process are described below.

  At the start of the shooting operation, the imaging apparatus performs face area detection processing on the input image shown in FIG. The face area detection is performed by extracting features from the input image, comparing them with features representing the face areas prepared in advance, and detecting those having a high degree of similarity. For the face area, search for an area that has a high correlation of brightness with the template of the face area prepared in advance, or detect the area in the HSV color space where the hue in the HSV color space is close to the skin color hue specified in advance. , Model human faces as ellipses, detect ellipses by Hough transformation, and use statistical pattern identification techniques to find areas that have a close correlation with the feature space of the face learned in advance. You may detect by detecting.

  Next, a pupil is detected from the detected face area. The pupil detection is performed by using the fact that the pupil is projected on the image as an ellipse and detecting the ellipse from the face region using the Hough transform. In addition, an ellipse growth method that detects a circle that touches the edge by Hough transform, and repeatedly applies the circle to an ellipse, or an image area that has a high correlation with the feature space created by learning the pupil image as input in advance. A method of detecting as a pupil may be used. The pupil detection may be performed directly from the input of the image without using the face detection result.

  The detection of the line-of-sight direction is performed by calculating from the positional relationship between the center of the pupil obtained by pupil detection and the facial parts such as the corners of the eyes, the eyes, and the mouth. For example, first, the face direction is detected by the corners of the eyes, the eyes, and the mouth.

  Next, the direction of the line of sight with respect to the front of the face is detected based on the positional relationship between the corners of the eyes, the eyes, and the center of the pupil. Finally, the gaze direction is detected by combining the face direction and the gaze direction with respect to the face front. The detected pupil contour shape is a projected image of a circle rotated in a three-dimensional space, and the gaze direction is measured by obtaining the rotation angle, and the eyeball center is three-dimensionally determined from the positions of the corners of the eyes and the eyes. May be detected from the positional relationship between the center of the pupil and the center of the eyeball.

  Furthermore, the optimality of the image is determined using the detection result. The determination is performed using an angle formed by the camera direction and the line-of-sight direction, and when the angle is equal to or smaller than a predetermined threshold value, it is determined as an optimal image, and other cases are determined as inappropriate images. FIG. 4 shows a state in which a person 401 is photographed by the imaging apparatus 402 from above. In this case, an angle 405 formed by a straight line 403 connecting the imaging apparatus to the pupil and a straight line 404 representing the line of sight is evaluated. And That is, shooting is performed only when the corner 405 is equal to or smaller than the threshold value. However, the straight line 403 may be a part of the head or body, such as a facial part other than the pupil such as the nose or mouth, or the center of the left and right pupils. In the case of FIG. 3A, the person 301 is determined to be an inappropriate image because the angle formed between the line of sight and the camera is larger than the threshold value. In addition, if the time from the start of shooting work exceeds a certain time and it is likely that it will take a long time before the threshold is reached, set the threshold value higher than before to shorten the shooting time. For example, it may be determined dynamically.

  If it is determined that the image is inappropriate, the input image is taken again, and the processing is repeated until it is determined that the camera is facing the camera direction based on the determination. For example, like the person 302 in FIG. 3B, when it is determined that the camera is facing the camera, the input image is saved in a memory card, a hard disk drive, or the like, and the shooting operation is terminated. In addition, after the input image is stored, the shooting operation may be started and continuous shooting may be performed.

  Next, an operation when photographing a plurality of persons will be described. As shown in FIGS. 5A and 5B, an image in which a plurality of persons 501 are shown is set as an input image. 5A and 5B, a person 501, a person 502 and a person 503 in FIG. 5A, and a person 504 in FIG.

  At the start of the photographing operation, the imaging device performs face area detection processing and pupil detection processing similarly to FIG. 3A, and then performs gaze direction detection to determine the optimality of the image. The determination is performed using the angle formed by the camera direction and the line-of-sight direction of the person 501, person 502, and person 503 as an evaluation criterion. A case where the angles of all of the persons 501, 502, and 503 are equal to or smaller than a predetermined threshold value is determined as an optimal image, and other cases are determined as inappropriate images. For example, in FIG. 4A, the aptitude determination unit 105 determines that the person 501 and the person 503 are facing the camera direction, but the person 502 determines that the person 502 is not facing the camera direction. It is determined that the image is not suitable for shooting. The determination may be performed by the following method.

  When the ratio of the subject who is determined to be facing the camera to the total subject is equal to or greater than a predetermined ratio, it is determined to be optimal, and the other is determined to be inappropriate.

  Only when a specific subject is facing the camera, it is determined to be optimal, and the other is determined to be inappropriate.

  A weight is set for each person to be photographed, and the product of the evaluation value and weight with the angle between the camera direction of each person to be photographed and the line of sight as a parameter is the evaluation value for each person to be photographed. If it is better than the threshold value, it is determined as an optimal image, and the other images are determined as inappropriate images.

  In addition, if the time since the start of the shooting operation exceeds a certain time, the threshold value is reset to a larger value, or the gaze direction history of each subject is shortened to a value below the smaller threshold value. If it is predicted that it will fit in time, it may be determined dynamically, for example, by setting a smaller value.

  If it is determined that the image is inappropriate, the input image is taken again, and the above-described processing is repeated until the determination result is optimal, such as the person 501, person 504, and person 503 in FIG. If the determination result is not optimal within a certain time or number of times, the photographing operation may be terminated.

  When the determination result is optimum, the input image is saved and the photographing operation is terminated. In addition, after the input image is stored, the shooting operation may be started and continuous shooting may be performed.

  As described above, the present embodiment has an effect that it becomes easy for the person to be photographed to capture an image facing the camera direction.

(Embodiment 2)
FIG. 6 is a block diagram showing a configuration of the imaging apparatus according to Embodiment 2 of the present invention. In FIG. 6, the same components as those in FIG.

  The imaging apparatus includes an image input unit 101, an image processing unit 102, a storage unit 103, a warning unit 601, and a photographing timing input unit 604. The warning unit 601 includes an image composition unit 602 and a warning display unit 603.

  In FIG. 6, the second embodiment is different from FIG. 1 in that a warning unit 601 and a photographing time input unit 604 are added.

  FIG. 7 shows an operation flow of the imaging apparatus. In FIG. 7, the same components as those in FIG.

  The image composition unit 602 detects a person who is not facing the camera direction from the output of the suitability determination unit 105 (STEP 701), and the image input unit 101 displays an image indicating the person's area so that the photographer can recognize the person. The image is combined with the output image and output to the warning display means 603 (STEP 702). Further, if all the members are facing the camera direction, the image composition unit 602 may process the image so as to indicate that all the members are facing.

  The warning display means 603 such as a liquid crystal display or a finder displays the image output by the image composition means 602 (STEP 703).

  The above processing is repeated until the photographing time input means 604 outputs photographing permission (STEP 704). If the photographing permission is output, the image input from the image input means 101 is saved (STEP 205), and the process ends (STEP 206). Further, the image may be stored automatically when it is determined in the line-of-sight direction determination (STEP 701) that all the members are viewing the designated direction.

  FIG. 8A shows the warning display means 603 of the warning means 601 when there is a person who is not looking at the camera. The image displayed on the warning display means shows the area of the person so that the photographer can see the person who is not looking at the camera. In FIG. 8A, the person 801 and the person 803 in the input image. Is facing the camera, but the person 802 is not facing the camera. At this time, the image synthesizing unit 502 synthesizes the parenthesis-shaped image 804 indicating the area of the person 702 with the input image and displays it on the warning display unit 603. The image 804 may be a symbol, a character, or a picture.

  FIG. 8B shows the warning display means 603 of the warning means 601 when everyone is looking at the camera. In FIG. 8B, it is determined that the person 801, the person 805, and the person 803 are all facing the camera direction. At this time, the image composition unit composes the image 806 with the input image and displays it on the warning display unit 603. Further, the direction in which the person is facing or the angle between the facing direction and the camera direction may be displayed. The image 806 may be a symbol, a character, or a picture.

  As described above, the present embodiment has an effect that the photographer can easily know the person to be photographed who is not facing the camera, and the photographing can be smoothly advanced such as calling attention.

(Embodiment 3)
FIG. 9 is a block diagram showing a configuration of the imaging apparatus according to Embodiment 3 of the present invention. 9, the same components as those in FIG. 1 are denoted by the same reference numerals, and description thereof is omitted.

  The imaging apparatus includes an image input unit 101, an image processing unit 102, a storage unit 103, and a line-of-sight direction specifying unit 901. The line-of-sight direction designating unit 901 includes an image display unit 902, a designation input unit 903, and a designation recognition unit 904.

  10, the third embodiment is different in that a line-of-sight direction designating unit 1001 is added to FIG.

  FIG. 10 shows an operation flow of the imaging apparatus. 10, the same components as those in FIG. 2 are denoted by the same reference numerals and description thereof is omitted.

  The image display means 902 such as a liquid crystal display or a finder displays the input image (STEP 1001). At this time, the object and direction in the input image are input by the designation input means 903 such as a mouse, a touch panel, or a cross key (STEP 1002). The designation recognizing unit 904 recognizes the object and direction of the line of sight from the output of the designation input unit 903, and determines the line-of-sight direction from the positional relationship with the person (STEP 1003). The image display unit 902 displays an image representing the designated object and direction (STEP 1004).

  FIGS. 11A and 11B show the image display unit 902 in the case where the line-of-sight direction is designated by designating an object in the image, and FIG. 11A shows the image display unit 902 before the line-of-sight direction is designated. FIG. 11B shows the image display means 902 after the line-of-sight direction is designated. The person 1101 in the image before the line-of-sight direction is specified is the subject, and the object 1102 is the subject of the subject's line of sight at the time of shooting. As shown in FIG. 11A, when an input image is displayed on the image display unit 902, the photographer moves the image 1103 with an input device such as a mouse, a cross key, voice, a touch panel, and designates an object. Thereafter, the line-of-sight direction designating unit obtains the positional relationship between the designated object 1102 and the person 1101 from the focal length when each has a focal point, and determines the designated line-of-sight direction using it. The determination method is a factorization method in which the camera is moved, the feature points of the person 1101 and the object 1102 are tracked, and the matrix composed of the coordinates of the feature points is deformed to restore the three-dimensional positions of the feature points and the camera motion. May be used.

  After the designated line-of-sight direction is determined, an image 1104 showing the object 1102 is combined with the input image and displayed on the image display unit 902 as shown in FIG. The image 1104 may be a symbol, a character, or a picture. When there are a plurality of subjects, the line-of-sight direction may be designated for each person. Further, when the line-of-sight direction has been specified in the past, the line-of-sight direction need not be specified.

  FIGS. 12A and 12B show the image display means 902 in the case where the line-of-sight direction is designated by designating the direction in the image, and FIG. 12A shows the image display means 902 before the line-of-sight direction is designated. FIG. 12B shows the image display means 902 after the line-of-sight direction is designated. A person 1201 in the image before the line-of-sight direction is specified is a subject.

  As shown in FIG. 12A, when an image is input, the designation input unit 903 detects the face of the person 1201 from the input image, and an image 1202 that serves as a direction reference for the face position and an image 1203 that designates the direction. The image 1204 indicating the direction is combined with the input image and displayed on the image display means 902. After the display, the image 1203 is moved by an input device such as a mouse, a cross key, voice, or a touch panel, the designated gaze direction is determined from the positional relationship between the image 1203 and the eyes of the person 1201, and the image 1204 is displayed. Thereby, the photographer can specify the direction more intuitively than directly specifying the angle with respect to the camera direction.

  After the determination, the image 1205 is combined with the input image as shown in FIG. 12B and displayed on the image display device 902. The direction indicated by the image 1205 does not change after determination. Note that the image 1202, the image 1203, the image 1204, and the image 1205 may be symbols, characters, and pictures, and when there are a plurality of subjects, the line-of-sight direction may be designated for each person. Further, when the line-of-sight direction has been specified in the past, the line-of-sight direction need not be specified.

  FIG. 12C shows an example of a display method when displaying the image 1202 of FIG. When the imaging apparatus detects the person 1201 from the image, the imaging apparatus estimates the approximate position of the head of the person 1201 from the focal length, the size on the image, and the like. Thereafter, two arcs with arrows at both ends are vertically installed so as to surround the estimated head, and an image projected on the imaging surface of the imaging device is defined as an image 1202. To do. Note that the image 1203 moves on a spherical surface including two arcs of the image 1202, and the image 1204 displays an arrow to point from the estimated eye position of the head to the three-dimensional position represented by the image 1203. To do.

  As described above, the present embodiment has an effect that the photographed person can easily photograph an image directed to any designated object or direction.

(Embodiment 4)
FIG. 13 is a block diagram showing a configuration of an imaging apparatus according to Embodiment 4 of the present invention. In FIG. 13, the same components as those in FIG.

  The imaging apparatus includes an image input unit 101, an image processing unit 102, a storage unit 103, a warning unit 1301, a photographing time input unit 604, and a line-of-sight direction designation unit 901. The warning unit 1301 includes an image composition unit 1302 and a warning display unit 1303.

  In FIG. 13, the fourth embodiment is different in that a warning unit 1301 is added to FIG.

  The warning display unit 1303 of the warning unit 1301 may use the same device as the image display unit 902 of the line-of-sight direction specifying unit 901.

  FIG. 14 shows an operation flow of the imaging apparatus. In FIG. 13, the same components as those in FIG.

  After starting the photographing operation, the camera inputs an input image to the line-of-sight direction designating unit 901 and designates the line-of-sight direction. Thereafter, line-of-sight detection is performed, the line-of-sight direction is determined, a person not facing the designated direction is detected based on the line-of-sight direction, and the person is output to the warning display means 1302. The image synthesizing unit 1302 synthesizes an image 1205 indicating the designated direction and an image 804 indicating a person who is not facing the designated direction with the input image.

  Further, the direction in which the person is facing or the angle between the facing direction and the specified direction may be displayed. Note that the image 1205 may not be combined, and only the image 804 may be combined. The warning display unit displays the image combined by the image combining unit 1302. When the photographing time input means 604 such as a shutter release button or a self-timer gives permission to save, or when it is determined as a result of the line-of-sight detection that all are facing the designated direction, the input image is saved and the photographing is terminated. In addition, after the input image is stored, the shooting operation may be started and continuous shooting may be performed.

  As described above, in the present embodiment, there is an effect that the photographer can easily know any designated object or the person who is not facing the direction, and can smoothly proceed with photographing such as calling attention. .

  The imaging device according to the present invention has a function of detecting a line of sight with respect to a subject, and is useful as an imaging device that can easily acquire an image of a subject looking at a camera or a specific direction. In addition, by designating a specific object in advance, it can be applied to uses such as a monitoring device that can photograph only a person who is gazing at the object.

1 is a block diagram illustrating a configuration of an imaging apparatus according to Embodiment 1 of the present invention. The flowchart showing the flow of a process of the imaging device in Embodiment 1 of this invention The figure explaining the operation example at the time of one person to be imaged in Embodiment 1 of the present invention The figure explaining the operation example at the time of the to-be-photographed person in Embodiment 1 of this invention in multiple numbers The figure explaining the operation example at the time of the to-be-photographed person in Embodiment 1 of this invention in multiple numbers The block diagram showing the structure of the imaging device in Embodiment 2 of this invention FIG. 5 is a flowchart showing the flow of processing of the imaging apparatus according to Embodiment 2 of the present invention. The figure explaining the operation example in Embodiment 2 of this invention The block diagram showing the structure of the imaging device in Embodiment 3 of this invention Flow chart showing the flow of processing of the imaging apparatus according to Embodiment 3 of the present invention. The figure explaining the operation example in Embodiment 3 of this invention. The figure explaining the operation example in Embodiment 3 of this invention. FIG. 6 is a block diagram illustrating a configuration of an imaging apparatus according to Embodiment 4 of the present invention. Flow chart showing the flow of processing of the imaging apparatus in Embodiment 4 of the present invention

Explanation of symbols

DESCRIPTION OF SYMBOLS 101 Image input means 102 Image processing means 103 Storage means 104 Eye gaze detection means 105 Aptitude judgment means 601 Warning means 602 Image composition means 603 Warning display means 604 Shooting time input means 901 Gaze direction designation means 902 Image display means 903 designation input means 904 designation Recognizing means 1301 Warning means 1302 Image composition means 1303 Warning display means

Claims (7)

An image input means for inputting an image;
Image processing means for detecting one or a plurality of persons from the image input by the image input means, and detecting whether the person is looking at an imaging device by detecting a gaze direction of the person;
Storage means for storing an input image determined from the result of the image processing means that the person is looking at the imaging device;
An imaging apparatus comprising: Warning means for warning the photographer that there is a person who is not looking at the imaging device from the output of the image processing means;
A shooting time input means for the photographer to input a shooting command;
The imaging apparatus according to claim 1, further comprising: An image input means for inputting an image;
Gaze direction designating means for designating the gaze direction of the person;
Image processing means for detecting one or a plurality of persons from the image input by the image input means, detecting the direction of the line of sight of the person and determining whether the line of sight direction designating means is looking;
Storage means for storing an input image determined from the result of the image processing means that the person is looking at the imaging device;
An imaging apparatus comprising: Warning means for warning the photographer that there is a person who is not looking at the direction designated by the line-of-sight designation means from the output of the image processing means;
A shooting time input means for the photographer to input a shooting command;
The imaging apparatus according to claim 3, further comprising: The image processing means includes line-of-sight detection means for detecting the line-of-sight direction of one or more persons in the input image;
From the result of the line-of-sight detection means, the person has aptitude determination means for determining whether the person is looking at the direction specified by the imaging device or the first-line gaze designation means,
The imaging device according to claim 1. The line-of-sight direction specifying means includes an image display means for displaying an input image;
A designation input means for designating a target line-of-sight direction by designating an object, a region, and a direction in the input image; and a designation recognition means for recognizing a designation direction from the input of the designation input means and the input image.
The imaging device according to claim 3 or 4. The warning means includes an image composition means for processing an image to represent a person who is determined not to look at the imaging device or the designated direction by the suitability determination means;
Warning display means for displaying an image output by the image composition means;
The imaging device according to claim 5 or 6.

Images