JP2012065013A - Moving image file generation method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To solve the conventional problem in which a large load is imposed on an operator when generating a moving image file of scenes in which persons smile based on input video signals.SOLUTION: A smile determination part 105 of a processor 100 determines a smile degree on the basis of the feature amounts of persons detected from input video signals (S304). A file generation part 110 of the processor 100 generates a moving image file including the video signals of a period with a smile degree higher than a threshold among the input video signals (S312).

Description

  The present invention relates to a method of generating a moving image file having a period corresponding to a smile level.

  In recent years, various techniques using the recognition of a specific pattern from a subject image have attracted attention. Among them, digital cameras having an auto shutter function for recognizing a smile from a person image and determining a shooting timing are spreading.

  Patent Document 1 discloses generating an image with high user satisfaction by determining a smile point and synthesizing an image using the result.

JP 2008-198062 A

However, when trying to generate a moving image file of a scene where a person is smiling from an input video signal, a heavy load may be imposed on the operator.
For example, when an operator tries to generate a moving image file by cutting a scene in which a person is smiling from an input video signal for a long time, a heavy load may be applied to the operator.

  The present invention has been made in view of the above-mentioned problems, and its object is to satisfy the operator while reducing the burden on the operator when generating a moving image file of a scene where a person is smiling from an input video signal. It is to generate a high-quality video file.

  In order to achieve the above object, the processing apparatus of the present invention has the following configuration, for example. That is, an input unit that inputs a video signal, a determination unit that determines a smile level from a feature amount of a person detected from the input video signal, and a comparison unit that compares the determined smile level and a threshold value Generating means for generating a moving image file from a video signal in a period including a period in which the determined smile level is higher than the threshold value in the input video signal.

  According to the present invention, it is possible to generate a moving image file with a high degree of satisfaction while reducing the burden on the operator when generating a moving image file of a scene where a person is smiling from an input video signal.

It is a block block diagram of an image processing apparatus. It is a figure for demonstrating the relationship between a smile degree and the extraction part of a video signal. It is a flowchart figure for demonstrating the process of an image processing apparatus. It is the figure which showed the example of a screen display of a captured image. It is the figure which showed the network connection structure of the image processing apparatus.

  Hereinafter, the present invention will be described in detail based on preferred embodiments with reference to the accompanying drawings. The configurations shown in the following embodiments are merely examples, and the present invention is not limited to the illustrated configurations.

<First Embodiment>
FIG. 1 is a block diagram showing an image processing apparatus 100 (hereinafter referred to as a processing apparatus 100) according to this embodiment. In FIG. 1, an imaging unit 101 outputs a YUV format video signal obtained by subjecting an image signal captured by an imaging device such as a CMOS (Complementary Metal Oxide Semiconductor) to a color conversion unit 102. The video signal in this embodiment is a digital video signal. Further, the imaging unit 101 according to the present embodiment inputs a temporally continuous video signal in response to an instruction from the user. The imaging unit 101 may be configured differently from the processing device 100. In this case, the video signal obtained by the imaging apparatus is input to the processing apparatus 100 through a standard interface such as HDMI (High-Definition Multimedia Interface).
The color conversion unit 102 converts the YUV video signal from the imaging unit 101 into an RGB video signal. The face detection unit 103 performs face presence / absence detection and face position detection processing on the RGB video signal from the color conversion unit 102.

  The face detection unit 103 according to the present embodiment detects a face image from a video signal based on learning using a large number of face images (correct images) and non-face images (incorrect images) stored in advance. More specifically, the face detection unit 103 detects the position of the eyes, mouth, and face from the video signal based on learning using a face image (correct image) and a non-face image (incorrect image). However, the face image detection method is not limited to this method.

  The face tracking unit 104 tracks the face image detected by the face detection unit 103 in the screen using an optical flow or the like.

The smile determination unit 105 determines the smile level from the feature amount of the face image detected by the face detection unit 103 and tracked by the face tracking unit 104. The smile determination unit 105 of this embodiment extracts eyebrows, eyes, and lips from the face image. The smile determination unit 105 determines that the smile level is higher as the outer edge of the eyebrows is lowered. The smile determination unit 105 determines that the smile level is higher as the pupil of the eye is opened. The smile determination unit 105 determines that the smile level is higher as both ends of the lips are raised with respect to the center. However, the smile degree determination method is not limited to the above method.
The smile determination unit 105 inputs a control signal to the switch unit 109 according to the determination result of the smile level by the smile determination unit 105. Based on the control signal from the smile determination unit 105, the switch unit 109 switches whether to pass the YUV video signal from the imaging unit 101 to the file generation unit 110. That is, the switch unit 109 responds to an input from the smile determination unit 105 so that a video signal during a period in which the smile degree of the face image is determined to be higher than the threshold is passed to the file generation unit 110. Whether to transfer the video signal from the file generation unit 110 is switched.

  The frame specifying unit 106 specifies a frame including the face image determined by the smile determination unit 105 as the highest smile degree among the frames of the moving image file period. That is, the frame specifying unit 106 receives the smile level and the specific information of the frame for which the smile level is determined from the smile determination unit 105. Then, when the smile level received from the smile determination unit 105 is higher than the other smile levels received after the start of the video file period, the frame specifying unit 106 selects the frame of which the smile level is determined. The specific information is output to the frame cutout unit 107. For example, the frame specifying unit 106 outputs the specific information of the first frame to the frame cutout unit 107 immediately after the start of the moving image file period. If it is determined that the smile level of the second frame is higher than the smile level of the first frame, the frame specifying unit 106 outputs the specifying information of the second frame. On the other hand, when it is determined that the smile level of the second frame is lower than the smile level of the first frame, the frame specifying unit 106 does not output the specific information of the second frame to the frame cutout unit 107. In addition, when the period of the moving image file ends, the frame specifying unit 106 notifies the frame cutout unit 107 of that.

  The frame cutout unit 107 cuts out the frame specified by the frame specifying unit 106 from the YUV video signal from the imaging unit 101 and temporarily holds the frame. For example, the frame cutout unit 107 temporarily holds the video signal of the first frame immediately after the start of the moving image file period. For example, when the smile level of the second frame is higher than the smile level of the first frame, the video signal of the second frame is temporarily held instead of the video signal of the first frame.

  At this time, the processing apparatus 100 has a buffer that takes into account the delay time required for processing performed by the frame specifying unit 106 from the color conversion unit 102, so that the frame cutout unit 107 holds the frame specified by the frame specifying unit 106. can do. When the moving image file period ends, the frame cutout unit 107 outputs the video signal of the held frame to the thumbnail generation unit 108. The video signal output by the frame cutout unit 107 at this time is a video signal of a frame having the highest smile degree determined by the smile determination unit 105 among the frames in the moving image file period.

  The thumbnail generation unit 108 generates a thumbnail image of a moving image file from the video signal output from the frame cutout unit 107. With such a configuration, the thumbnail generation unit 108 is based on the second moving image frame having the second smile degree higher than the first smiling degree of the first moving image frame (first frame) in the moving image file period. To generate a thumbnail of the video file.

  The file generation unit 110 receives the video signal from the imaging unit 101 via the switch unit 109 and generates a moving image file based on a format such as AVCHD (Advanced Video Code High Definition). That is, the file generation unit 110 generates a moving image file from a video signal in a period including a period in which the determined smile level is higher than a threshold among the input video signals.

Next, the operation of the processing apparatus 100 of this embodiment will be described using the flowchart of FIG. In this embodiment, an example in which processing of each unit of the processing device 100 is performed by dedicated hardware will be described. It is also possible to read and execute. In this embodiment, the process of FIG. 3 is started when the smile file generation mode is selected. However, it may be started in, for example, a normal moving image shooting mode.
In S301 (input procedure) of FIG. 3, the imaging unit 101 performs imaging and inputs the obtained video signal. Note that the imaging unit 101 may be an imaging device different from the processing device 100. In this case, a video signal from the imaging device is input in S301.

  In S302, the control unit (not shown) of the processing apparatus 100 determines whether or not the end of moving image shooting has been instructed. When it is determined that the end of moving image shooting is not instructed, the process proceeds to S303, and when it is determined that the end of moving image shooting is instructed, the processing of FIG. 3 ends.

  In step S <b> 303, the color conversion unit 102 performs color conversion from a YUV video signal obtained by imaging by the imaging unit 101 to an RGB video signal. The RGB video signal is output to the face detection unit 103. In this embodiment, the YUV video signal and the RGB video signal are both digital video signals. Also, the video signal input in this embodiment is a temporally continuous video signal.

  In step S304, the face detection unit 103 detects a human face image from the RGB video signals. The face detection unit 103 according to the present embodiment detects a face image from a video signal based on learning using a large number of face images (correct images) and non-face images (incorrect images) stored in advance. The face detection unit 103 outputs the coordinate data of the four vertices of the rectangle corresponding to the detected face image region and the RGB video signal to the face tracking unit 104. FIG. 4 shows an example of the area of each face image when three face images are detected.

  In step S <b> 304, the face tracking unit 104 performs tracking processing of the face image detected by the face detection unit 103 based on the coordinate data from the face detection unit 103. The face images of the same person among the face images detected in the immediately preceding frame and the current frame are associated by the tracking process of the face detection unit 103. Further, the face tracking unit 104 performs a smoothing process in the time axis direction so that the size of the associated face image does not change greatly for each frame. That is, the face tracking unit 104 corrects the coordinate data of the face image output from the face detection unit 103. Further, the face tracking unit 104 outputs the result of the smoothing process to the smile determination unit 105 in association with the ID of the face image. For example, as shown in FIG. 4, when face images (persons 1, 2, 3) of three persons are detected by the face detection unit 103, the face tracking unit 104 determines the ID of the person 1 and the person 1 The coordinate data after smoothing processing of the rectangular area is output in association with it. Similarly, the face tracking unit 104 associates the ID of the person 2 with the coordinate data after the smoothing process of the rectangular area of the person 2, and also coordinates the ID of the person 3 with the coordinate data after the smoothing process of the rectangular area of the person 3. Are output in association with each other.

  In this way, by managing a person by ID, for example, it is possible to generate a video file during a period when one or more persons specified by the user are smiling, or a person who has been photographed for a long time. For example, you can create a video file for the period when you are smiling. When generating a moving image file during a period in which the person designated by the user is smiling, the person is based on designation information from an input unit included in the processing device 100 or a terminal device connected to the processing device via a network. Can be specified. That is, the processing apparatus 100 includes a designation unit (not shown) that designates a person to be used for smile level determination from a plurality of detected persons. In addition, by separating the persons according to the ID, it is possible to create a composite photograph of a smile or to create a smile icon for each person.

  In S304 (determination procedure), the smile determination unit 105 determines the smile level of each face image based on the face image ID, the coordinate data, and the video signal output from the face tracking unit 104. . The smile determination unit 105 of this embodiment extracts eyebrows, eyes, and lips from the face image specified by the coordinate data. The smile determination unit 105 determines that the smile level is higher as the outer edge of the eyebrows is lowered. The smile determination unit 105 determines that the smile level is higher as the pupil of the eye is opened. The smile determination unit 105 determines that the smile level is higher as both ends of the lips are raised with respect to the center. The smile determination unit 105 determines the smile level of each face image in the range of 0 to 1.4 according to the state of the eyebrows, eyes, and lips. When the determination of the smile level by the smile determination unit 105 is completed, the process proceeds to S305.

In S305 (comparison procedure), the smile determination unit 105 compares the smile level determined in S304 with a threshold value. If it is determined by this comparison that the smile level is higher than the threshold value, the process proceeds to S306, and the generation of the moving image file is started. If the smile level is higher than the threshold value, the generation of the moving image file is also continued. . On the other hand, if it is determined that the smile level is not higher than the threshold value, the process proceeds to S309. If a moving image file is being generated, the moving image file generation is terminated and the process proceeds to S311. If yes, the process returns to S301.
Here, the relationship between the smile level and the period of the moving image file will be described.

  First, the first mode is a mode in which a smile level is determined for each of a plurality of face images, and a moving image file in a period in which at least one of the determined smile levels exceeds a threshold value is generated. FIG. 2 shows the relationship between the change in the smile level of each face image and the period of the moving image file when three face images are detected in the first mode. In this embodiment, the threshold value to be compared with the smile level of the face image is set to 0.6. As shown in FIG. 2, recording of a moving image file is started from the timing when the smile degree of one of the three persons (person 2) exceeds 0.6, and the smile degrees of all persons are 0.6. The video file recording ends at a lower timing.

  That is, the switch unit 109 passes the YUV video signal during a period in which at least one person's smile level exceeds 0.6 to the file generation unit 110, and the smile level of any person does not exceed 0.6. Do not pass the video signal to the file generator. As described above, the switch unit 109 controls the recording of the YUV video signal from the imaging unit 101 based on the control signal according to the comparison result between the smile level from the smile determination unit 105 and the threshold value. In other words, the smile determination unit 105 compares the smile level of a first person with a high smile level with a threshold among a plurality of persons (for example, the first person and the second person) detected from the video signal. . Then, the switch unit 109 passes the video signal during a period in which the smile level of the first person having a high smile level is higher than the threshold value to the file generation unit 110. In addition, for example, a threshold value may be compared with a facial image having the highest smile degree among facial images larger than a predetermined size.

  The second mode is a mode in which a smile level is determined for each of a plurality of face images, and a moving image file is generated during a period in which the total value of the determined smile levels exceeds a threshold value. That is, the smile determination unit 105 compares the total value of the detected smile levels of a plurality of persons with a threshold value. Then, the switch unit 109 passes the video signal during a period in which the total smile level of the plurality of persons is higher than the threshold value to the file generation unit 110. In the second mode, the threshold setting method can be further divided into two. That is, a mode in which the threshold is changed according to the number of face images, and a mode in which the threshold is constant regardless of the number of face images. According to the second mode, it is possible to determine the period of the moving image file in consideration of the overall smile level as compared with the first mode.

  The third mode is a mode in which a smile level is determined for each of a plurality of face images, and a moving image file is generated during a period in which the average value of the determined smile levels exceeds a threshold value. That is, the smile determination unit 105 compares the average value of smile levels of a plurality of detected persons with a threshold value. Then, the switch unit 109 passes the video signal during a period in which the average smile level of a plurality of persons is higher than the threshold value to the file generation unit 110. According to the third mode, the period of the moving image file can be determined by simple processing rather than changing the threshold according to the number of face images. By enabling the user to select each of the above modes according to the number of face images and the moving image file to be acquired, a moving image file with higher satisfaction can be generated.

  In the above embodiment, an example is described in which the period of the video file is started after the smile level exceeds the threshold value. For example, the video file is started from a timing before the timing when the smile level exceeds the threshold level. The period may start. By doing so, the possibility of generating a moving image file including the cause of the increased smile level is improved.

  Further, in the above embodiment, an example is described in which the period of the video file is immediately ended when the smile level falls below the threshold value. For example, the video is moved after a predetermined time elapses after the smile level falls below the threshold level. The file period may be terminated. By doing so, it is possible to reduce the possibility of being divided into a plurality of moving image files when the smile level is lowered for a short period of time and then the smile level is increased immediately.

  In addition, for example, when the moving image file period is started and the person turns sideways or faces down, the face image feature amount acquisition is interrupted, so that the smile level cannot be determined. Can be considered. In such a case, the smile determination unit 105 according to the present exemplary embodiment does not include the moving image while there is a person whose feature amount acquisition is interrupted even though it is known to exist in the screen by face tracking. Do not end the file period.

  In other words, when the acquisition of the feature amount for determining the smile level of the detected person is interrupted after the period of the moving image file starts according to the smile level of the person, The transmission of the control signal is controlled so that a moving image file including the video signal of the period is generated. By doing so, it is possible to reduce the possibility that the period of the moving image file ends even though the smile is actually continued. Further, for example, when a plurality of persons are detected, the smile level of the person whose feature amount acquisition is interrupted may be set as the average value of smile levels of other persons.

  In the above embodiment, the threshold value to be compared with the smile degree is described as an example of the same value (0.6) at the start and end of the period of the video file. For example, the start of the video file is determined. The threshold value may be higher than the threshold value that determines the end of the moving image file. This improves the possibility that the cause of the smile can be included in the period of the moving image file. Further, for example, the threshold value for determining the start of the moving image file may be set lower than the threshold value for determining the end of the moving image file. In this way, the possibility of being divided into a plurality of moving image files can be reduced when the smile level decreases for a short period of time and then the smile level increases immediately.

  That is, the smile determination unit 105 starts the period of the moving image file in response to the smile level reaching the first threshold value, and the smile level has reached a second threshold value different from the first threshold value. Terminate accordingly. Further, the file generation unit 110 has a period from when the smile level of the person detected from the video signal reaches the first threshold value until the smile level of the person reaches a second threshold value different from the first threshold value. Generate a video file from the video signal. In this way, the threshold value for determining the start of the movie file period and the threshold value for determining the end of the movie file period are set to different values, so that the operation taking into account the hysteresis of the smile degree numerical value can be performed. It becomes possible.

  In S307 of FIG. 3, the frame specifying unit 106 determines whether the smile level of the current frame recorded in S306 is higher than the smile level of other frames after the start of the moving image file period. If the frame identification unit 106 determines that the smile level of the current frame is higher than the highest smile level of the frames after the start of the moving image file, the frame identification unit 106 outputs the specific information of the frame to the frame cutout unit 107. .

  In S <b> 308, the frame cutout unit 107 that has received the specific information from the frame specifying unit 106 acquires the YUV digital video signal of the frame corresponding to the specific information from the imaging unit 101 and temporarily stores it.

  If the smile determination unit 105 determines in S305 that the smile level is not higher than the threshold value, the process proceeds to S309 and determines whether or not the moving image is currently being recorded. If it is determined that the moving image is not being recorded, the process returns to S301. If it is determined that the moving image is being recorded, the process proceeds to S310.

  In S310, the smile determination unit 105 outputs a control signal indicating the end of the moving image file period to the switch unit 109, and the switch unit 109 ends the output of the video signal to the file generation unit 110.

  In step S <b> 311, the frame cutout unit 107 passes the YUV video signal of the frame corresponding to the frame identification information output from the frame identification unit 106 to the thumbnail generation unit 108. Then, the thumbnail generation unit 108 generates a thumbnail image from the video signal of the frame passed from the frame cutout unit 107 according to a format such as JPEG, for example. The thumbnail generation unit 108 outputs the generated thumbnail image to the file generation unit 110.

  As shown in FIG. 2, the frame in which the person 2 is determined to have a smile level of 1.2 among the frames of the moving image file period is identified as the frame with the highest smile level. The thumbnail generation unit 108 of this embodiment generates a thumbnail image from the video signal of the frame in which the person 2 is determined to have a smile level of 1.2. However, for example, a thumbnail image may be generated from a frame having the highest total value or average value of smile levels of a plurality of persons.

  In S 312 (generation procedure), the file generation unit 110 generates a moving image file based on the video signal passed from the switch unit 109. For example, the file generation unit 110 converts the YUV video signal from the switch unit 109 to H.264. A video signal in AVCHD format is generated by compressing and multiplexing the audio signal to H.264 using Dolby (registered trademark). The file generation unit 110 associates and outputs the generated moving image file and the thumbnail image generated by the thumbnail generation unit 108.

  As described above, the processing apparatus 100 according to the present embodiment generates a moving image file from a video signal in a period including a period in which the smile level of a face image detected from the video signal is higher than a threshold value. By doing so, it is possible to generate a moving image file with a high degree of satisfaction while reducing the load on the creator of the moving image file.

  In the above-described embodiment, the description has focused on an example in which a moving image file is generated from a video signal including a period from a timing at which the smile degree is determined to be higher than the threshold to a timing at which the smile is determined to be lower than the threshold. However, it is not limited to this example. For example, a moving image file may be generated from a video signal in a period from a timing when it is determined that the smile level is higher than a threshold to a predetermined time (for example, after 5 seconds). In this case, the file generation unit 110 generates a moving image file from a video signal in a period from when the determined smile level is higher than the threshold to a predetermined time later.

  In addition, when it is determined in S302 that moving image recording has ended after moving image recording is started in S306 of FIG. 3, the processing may be ended after generating a moving image file. In this case, a thumbnail is also generated.

  FIG. 5 is a network connection configuration diagram when the processing apparatus 100 of the present embodiment is connected to the home network 400. In FIG. 5, an example in which the processing device 100 is realized by a digital video camera will be described. However, the present invention is not limited to this. Further, although an example in which the processing apparatus 100 of this embodiment is connected to the home network 400 via a wireless LAN will be described, a wired connection may be used. The media player 200 receives the moving image file distributed from the processing device 100, decodes it, and outputs it to the television monitor 201. The display device 202 is a display device having a media player function, and is a digital photo frame, for example. The router 300 is a router with a wireless access point, and performs wireless communication with the processing apparatus 100 and mediates connection with the home network 400. The router 300 also has a gateway function to the Internet 401. The numbers of the processing device 100, the media player 200, the television monitor 201, and the display device 202 are not limited as in the example of FIG. 5, and a large number may exist. The home network 400 may also be a network such as the Internet or an intranet that has sufficient bandwidth to pass packet data. The physical connection form to the home network 400 may be not only wired but also wireless, but the physical form is not particular as long as it is connected in a protocol manner. Further, the media player 200, the television monitor 201, and the display device 202 can be realized by the same device.

  In the case of the above configuration, the file generation unit 110 of the processing device 100 records the thumbnail image generated by the thumbnail generation unit 108 as metadata of the generated moving image file. In addition, the file generation unit 110 of the processing device 100 can record a person name corresponding to the detected face image in the metadata of the moving image file by providing a function of recognizing the person of the face image. is there. In this way, a moving image file to be played back by the media player 200 can be selected more easily.

  For example, the processing device 100 uses a content directory service (CDS: Content Directory Service) which is a function of UPnP-AV (Universal Plug and Play Audio Visual), for example, “smile video of OO”. A playlist including various titles is transmitted to the media player 200 in advance. Thereby, the user of the media player 200 can grasp the contents of the moving image file recorded in the processing device 100 connected via the home network 400.

  The present invention can also be realized by executing the following processing. That is, software (program) that realizes the functions of the above-described embodiments is supplied to a system or apparatus via a network or various storage media, and a computer (or CPU, MPU, or the like) of the system or apparatus reads the program. It is a process to be executed.

Claims (12)

An input means for inputting a video signal;
Determination means for determining a smile degree from a feature amount of a person detected from the input video signal;
A comparing means for comparing the determined smile level with a threshold;
A processing apparatus comprising: generating means for generating a moving image file from a video signal in a period including a period in which the determined smile level is higher than the threshold among the input video signals. The comparing means compares a total value of smile levels of a plurality of persons detected from the input video signal with the threshold;
The processing apparatus according to claim 1, wherein the generation unit generates a moving image file from a video signal in a period including a period in which a total value of smile levels of the plurality of persons is higher than the threshold value. The comparing means compares an average value of smile levels of a plurality of persons detected from the input video signal with the threshold value,
The processing device according to claim 1, wherein the generation unit generates a moving image file including a video signal of a period in which an average value of smile levels of the plurality of persons is higher than the threshold value.   The comparing means compares the threshold of the first person and the second person detected from the input video signal with the threshold value of the first person who has a high smile degree. The processing apparatus according to claim 1. Designating means for designating a person from a plurality of persons detected from the input video signal;
The processing apparatus according to claim 1, wherein the comparison unit compares a smile level of the person designated by the designation unit with the threshold value.   The generation means includes a period of time from when the smile level of the person detected from the video signal reaches a first threshold value until the smile level of the person reaches a second threshold value different from the first threshold value. The processing apparatus according to claim 1, wherein a moving image file is generated from the video signal.   A feature amount for determining the smile level of the person detected from the input video signal after starting a period for generating the video file according to the smile level of the detected person. The processing apparatus according to any one of claims 1 to 6, wherein when the acquisition is interrupted, the generation unit generates a moving image file including a video signal in the interrupted period.   The generation unit is configured to generate the moving image file based on a second moving image frame having a second smile degree that is higher than a first smiling degree of the first moving image frame in a period for generating the moving image file. The processing apparatus according to any one of claims 1 to 7, wherein a thumbnail image is generated.   The generation unit generates a moving image file from a video signal in a period from when the smile level reaches the threshold value until a predetermined time after the smile level becomes lower than the threshold value. The processing apparatus according to 1.   The processing apparatus according to claim 1, wherein the generation unit generates a moving image file from a video signal in a period from a time when the determined smile level is higher than the threshold to a predetermined time. A method of generating a video file performed by a processing device,
An input process for inputting a video signal;
A determination step of determining a smile level from a feature amount of a person detected from the input video signal;
A comparison step of comparing the determined smile level with a threshold;
And a generating step of generating a moving image file from a video signal in a period including a period in which the determined smile level is higher than the threshold value in the input video signal. On the computer,
Input procedure for inputting video signal,
A determination procedure for determining a smile degree from a feature amount of a person detected from the input video signal;
A comparison procedure for comparing the determined smile level with a threshold;
A program for executing a generation procedure for generating a moving image file from a video signal in a period including a period in which the determined smile level is higher than the threshold among the input video signals.

Images