JP2002185908A - Computer-readable recording medium recording image extract program, image extract device and image extract method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To sequentially output a plurality of images according to a prescribed scenario. SOLUTION: The computer-readable recording medium recording an image extract program is a computer-readable recording medium recording an image extract program that is used to extract images from a storage section storing the images and allows a computer to execute a step (S1) where the input of scenario data respectively defining scenes and the sequence of the scenes is accepted, a step (S8) where images respectively corresponding to the defined scenes are extracted among the stored images, and a step (S13) where the extracted images are outputted according to the defined scene sequence.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a computer-readable recording medium storing an image extracting program, an image extracting apparatus, and an image extracting method. The present invention relates to a computer-readable recording medium that stores an image extraction program that can be determined as described above, an image extraction device, and an image extraction method.

[0002]

2. Description of the Related Art In recent years, digital cameras have rapidly become widespread. In addition, the capacity of recording media has increased, and several hundred images can be recorded on a memory card used at the time of shooting. Furthermore, if images are transferred from a digital camera to a personal computer and stored in a hard disk or the like of the personal computer, thousands or tens of thousands of images can be recorded.

[0003] On the other hand, the cost required for shooting and recording an image is sufficient for the cost of the recording medium. If this cost is converted into one photographing, it is very cheap as compared with the conventional silver halide print. Therefore, in photographing with a digital camera or the like, the number of images to be photographed tends to increase.

[0004]

However, as the number of captured images increases, it becomes difficult to browse the captured images. When browsing images stored in a large amount in a personal computer or the like in sequence, it wastes time to browse unnecessary images. For this reason, if a keyword is assigned to an image and stored, it is possible to search for a required image by using the keyword, so that a desired image can be searched in a short time and the browsing time can be shortened. it can. However, assigning a keyword to each of a large number of images is a complicated operation.

SUMMARY OF THE INVENTION The present invention has been made to solve the above-described problems. One of the objects of the present invention is to extract a small number of suitable images from a plurality of images and easily browse them. An object of the present invention is to provide a computer-readable recording medium storing an image extraction program, an image extraction device, and an image extraction method.

[0006] An appropriate image is an image according to a scenario or an image of a different scene.

[0007]

According to one aspect of the present invention, there is provided a computer-readable recording medium on which an image extraction program is recorded, wherein a computer-readable recording medium stores a plurality of images. A computer-readable recording medium storing an image extraction program for extracting an image, the method comprising: receiving input of scene data defining a plurality of scenes and an order of the plurality of scenes; and An image extraction program for causing a computer to execute a step of extracting an image corresponding to the extracted image from a plurality of stored images and a step of outputting the extracted image in accordance with a defined scene order.

According to the present invention, an image corresponding to each of a plurality of defined scenes is extracted from a plurality of stored images, and the extracted images are output in accordance with the order of the defined scenes. Therefore, a plurality of images are sequentially output according to a predetermined scenario. As a result, it is possible to provide a computer-readable recording medium that stores an image extraction program that extracts a small number of appropriate images from a plurality of images and allows easy viewing.

According to another aspect of the present invention, a computer readable recording medium storing an image extracting program is a computer readable recording medium storing an image extracting program for extracting an image from a storage unit storing a plurality of images. Categorizing a plurality of stored images into a plurality of groups according to a predetermined rule, extracting at least one image for each of the plurality of groups, and outputting the extracted images And an image extraction program for causing a computer to execute the above.

According to the present invention, a plurality of stored images are classified into a plurality of groups according to a predetermined rule, and at least one image is extracted and output for each of the plurality of groups. For this reason, since the images selected for each group are output, the number of images to be output is reduced without repeatedly outputting similar images. As a result, it is possible to provide a computer-readable recording medium that stores an image extraction program that extracts a small number of appropriate images from a plurality of images and allows easy viewing.

Preferably, the step of classifying includes a step of discriminating a scene of the image, and the discriminated scene complies with a rule of classifying the same image into the same group.

According to the present invention, images having the same scene are classified into the same group, so that images of the same scene can be thinned out and output.

Preferably, the plurality of images have time information, and the step of classifying follows a rule of classifying the stored images into a predetermined number of images in a time series.

According to the present invention, the stored images are classified into a predetermined number of images in a time series, so that the images can be thinned out and output in the order of photographing.

[0015] Preferably, the plurality of images have time information, and the step of classifying follows a rule of classifying every predetermined period.

According to the present invention, since a plurality of images are classified for each predetermined period, the images can be thinned out and output at predetermined intervals in the order of photographing.

Preferably, the step of classifying includes a step of recognizing a subject included in the image, and the recognized subject follows a rule of classifying the same image into the same group.

According to the present invention, since the subject follows the rule of classifying the same image into the same group, the image including the same subject is classified into the same group. it can.

According to another aspect of the present invention, an image extracting apparatus includes a storage unit for storing a plurality of images, a scene definition unit for defining a plurality of scenes in order, and a plurality of scenes corresponding to the plurality of defined scenes. Extraction means for extracting an image to be extracted from a plurality of stored images, and output means for outputting the extracted image in accordance with a defined scene order.

According to the present invention, an image corresponding to each of a plurality of defined scenes is extracted from a plurality of stored images. Then, the extracted images are output in the order of the defined scene. Therefore, a plurality of images are sequentially output according to a predetermined scenario. As a result, it is possible to provide an image extracting apparatus that extracts only a small number of appropriate images from a plurality of images and allows easy browsing.

According to still another aspect of the present invention, an image extracting apparatus includes a storage unit for storing a plurality of images, a classification unit for classifying the stored plurality of images into a plurality of groups according to a predetermined rule, An extraction unit for extracting at least one image for each of the plurality of groups, and an output unit for outputting the extracted images are provided.

According to the present invention, a plurality of stored images are classified into a plurality of groups according to a predetermined rule.
And at least one for each of the plurality of groups.
One image is extracted, and the extracted image is output. For this reason, since the images selected for each group are output, the number of images to be output is reduced without repeatedly outputting similar images. As a result, it is possible to provide an image extracting apparatus that extracts only a small number of appropriate images from a plurality of images and allows easy browsing.

According to still another aspect of the present invention, an image extracting method is an image extracting method for extracting an image from a storage unit in which a plurality of images are stored. Receiving input of the order of the plurality of scenes, extracting images corresponding to each of the plurality of scenes defined from the plurality of stored images, and order of the scenes defining the extracted images Outputting according to the following.

According to the present invention, an image corresponding to each of a plurality of defined scenes is extracted from a plurality of stored images. Then, the extracted images are output in the order of the defined scene. Therefore, a plurality of images are sequentially output according to a predetermined scenario. As a result, as a result, it is possible to provide an image extraction method that extracts a small number of appropriate images from a plurality of images and allows easy browsing.

According to yet another aspect of the present invention, an image extracting method is an image extracting method for extracting an image from a storage unit in which a plurality of images are stored. , A step of extracting at least one image for each of the plurality of groups, and a step of outputting the extracted images.

According to the present invention, a plurality of stored images are classified into a plurality of groups according to a predetermined rule, at least one image is extracted for each of the plurality of groups, and the extracted images are output. For this reason, since the images selected for each group are output, the number of images to be output is reduced without repeatedly outputting similar images. As a result, it is possible to provide an image extraction method capable of extracting a small number of appropriate images from a plurality of images and easily browsing the images.

[0027]

Embodiments of the present invention will be described below with reference to the drawings. The same reference numerals in the drawings denote the same or corresponding members, and description thereof will not be repeated.

[First Embodiment] FIG. 1 is a block diagram showing a schematic configuration of an image extracting apparatus according to a first embodiment of the present invention. Referring to FIG. 1, an image extraction device 10
Reference numeral 0 denotes a control unit 101 for controlling the entire image extraction apparatus 100 and an image input unit 103 for inputting a still image.
And an operation unit 105 for operating the image extraction device 100
A storage unit 109 for storing an image input by the image input unit 103, an output unit 107 for outputting predetermined information according to an instruction from the control unit 101, and an external storage device 1.
11 is included.

The image input unit 103 is a digital camera, a digital video camera, an image scanner, or the like.
The still image is output to the control unit 101 as digital data.

The control unit 101 stores the image received from the image input unit 103 in the storage unit 109. Operation unit 105
Is a keyboard or a mouse for operating the image extracting apparatus 100. By inputting a predetermined instruction from the operation unit 105, the image extraction device can be operated.

The storage unit 109 is a magnetic storage device such as a hard disk device. Further, a magneto-optical storage device may be used instead of the magnetic storage device. The output unit 107 is a CRT
Or a display such as a liquid crystal display device. Further, a printer may be used.

The external storage device 111 is a magneto-optical storage device, and reads a program to be executed by the control unit 101 and digital data of a still image recorded on the recording medium 113, and records the data in accordance with an instruction from the control unit 101. Medium 11
3 can be written.

Recording media include tapes such as magnetic tapes and cassette tapes, magnetic disks (flexible disks and hard disks), and optical disks (CD-
Discs such as ROM / MO / MD / DVD), I
Card system such as C card (including memory card) and optical card, or mask ROM, EPROM, EEPROM
It is also possible to use a medium that fixedly carries a program, such as a semiconductor memory such as an M or flash memory. Alternatively, the medium may be a medium that carries the program fluidly so that the program or data is downloaded from the network.

The content stored in the recording medium 113 is not limited to a program but may be data.

In the image extracting device according to the present embodiment,
A plurality of still images are input in advance from the image input unit 103 and stored in the storage unit 109. The image stored in the storage unit 109 is, for example, an image of a scene of a sports day or the like. Athletic meet progresses according to a predetermined program. Therefore, the stored images include, for example, images of scenes of various competitions, such as images of scenes of entrance marches, images of scenes of balling competitions, images of tug-of-war competitions, and the like. Will be.

The image stored in the storage unit 109 is
Information on the time at which the still image was captured by the image input unit 103 is added and stored. For example, the time taken by the digital camera is added to the image data and input to the control unit 101, and the image and the time information are stored in the storage unit 109 in association with each other.

As described above, a plurality of still images input by the image input unit 103 are stored in the storage unit 109 in advance.

FIG. 2 is a flowchart showing a flow of an image extracting process executed by the image extracting apparatus according to the first embodiment. Referring to FIG. 2, in the image extraction processing, first, an image extraction condition is set (step S1). The image extraction conditions include a scenario, a date, and a hero. The scenario includes the composition of the scene and the order of the scene.

FIG. 3 is a diagram showing an example of an image extraction condition setting screen displayed by the image extraction device according to the first embodiment. Referring to FIG. 3, image extraction condition setting screen 20
0 includes an area 201 for inputting a scenario, an area 202 for inputting a date, and an area 203 for inputting a face image of the hero. In the area 201 for inputting a scenario, examples of the scenario are listed, and a scenario can be selected by selecting a number assigned to each. here,
1. Athletic meet, 2. Wedding, 3. The birthday party is an example of a scenario.

The date input area 202 includes a column for inputting a date. In the area 203 for inputting the hero's face image, a plurality of face images registered in advance are displayed as thumbnails. When thumbnails cannot be displayed on one screen, all images can be displayed as thumbnails by turning the page. The face image selected by the number from the face images displayed in the area 203 is selected as the main character.

As described above, in the image extraction condition setting process, the scenario, the date, and the face image of the main character are set.
The image selected as the hero's face image is stored in the storage unit 109 as a key image.

The hero face image set here need not be one, and a plurality of face images may be selected. That is, the main character is not limited to one, and a plurality of main characters can be selected. In addition, the face image set here may be a face image in an image stored in advance in storage unit 109, or may be a newly registered face image in step S1. The set face image of the hero is
In order to improve the accuracy of the processing described below, it is desirable that the image of the face has an area equal to or larger than a certain area and the face is facing the front.

In step S2, it is determined whether the face image set as the key image is appropriate. Whether or not the face image is appropriate is based on the condition that the face image is in a state in which the area is equal to or more than a certain value and the front is facing. If these two conditions are not satisfied, the process proceeds to step S1, and the image extraction condition setting process is repeated.

In step S3, an image with the same date as the date input in step S1 is selected from the images stored in the storage unit 109.

Then, an image including the key image set in step S1 is extracted from the selected images (step S4). As a technique for extracting an image including a face image set as a key image, see Japanese Patent Application Laid-Open No. 7-302337.
Japanese Patent Laid-Open No.
A technique used in a face image recognition device described in JP-A-3548 can be applied.

The scenario selected in step S 1 is composed of scenario data in which a scene number, a scene name, a composition example, and a hit image group are set as one set, and stored in the storage unit 109. Area 201 of image extraction condition setting screen 200
Are stored in the storage unit 109 in advance with the scene number, the scene name, and the composition example.

In the next step S5, the content of the currently set scenario is displayed by displaying the scenario setting screen. As a result, the user can confirm the contents of the currently set scenario.

In step S6, it is determined whether or not the currently set scenario is changed by adding or deleting a scene (step S6). If it is to be changed, the process proceeds to step S7; otherwise, the process proceeds to step S8.

After editing the scenario, that is, adding a scene to the scenario or deleting a scene from the scenario in step S7, the contents of the edited scenario are displayed in step S5 (step S5).

FIG. 4 is a diagram showing an example of a scenario setting screen displayed on the image extracting device according to the first embodiment. Referring to FIG. 4, a scenario setting screen 210 exemplifying an athletic meet scenario is shown. The scenario setting screen 210 includes an area 211 for displaying a scenario, a date and a face image (key image) of the hero, which are the image extraction conditions set in step S1, an area 212 for displaying a scene included in the scenario, and a An area 213 for inputting a scene to be added and an area 214 for inputting a scene to be deleted from the scenario are included.

In the area 211, the image extraction conditions input in step S1 are displayed. In the area 212, scenes stored in the storage unit 109 in advance for the selected scenario are displayed. Here, an entrance march as scene 1, an opening ceremony as scene 2, a balling in as scene 3, a team competition (dance) as scene 4, a class opposition relay as scene 5, and a closing ceremony as scene 6. Scene.

By inputting the scene number of the scene to be added to area 213 in order to change the scene stored in advance in storage section 109, a scene can be additionally inserted after the input scene number. . In this case, a scene name and a composition example are input separately from the scene number. As the composition example, it is sufficient to draw a contour line of a person in a specific posture or a characteristic shape of an object using drawing software or the like.

In the area 214, the number of the scene to be deleted among the scenes displayed in the area 212 is input.
The scene of the number input here is deleted from the scenario.

In this way, the edited scenario is
It is stored in the storage unit 109 as scenario data. FIG.
FIG. 3 is a diagram illustrating an example of scenario data stored in the image extraction device according to the first embodiment. Referring to FIG. 5, an example in which the scenario is an athletic meet is shown. The scenario data includes a scene name 23 for each scene number 231.
2. Data of the composition example 233 and the hit image group 234 are stored as one set. For example, in the scene number “1”, the scene name 232 is “entrance march”, the composition example 233 is a plurality of composition examples indicating the composition of the entrance march, and the hit image group 234.
Is the data of the file names of the selected images.

In step S8, an image having a composition similar to the composition stored in the scenario data is selected from the images selected in step S4. The selection of an image is performed for each scene number, and an image having a composition similar to the composition example corresponding to the scene number is selected. When there are a plurality of composition examples, images having similar compositions are selected for all composition examples. The file name of the selected image is stored in association with the scene number.

The selection of an image based on the composition is performed by extracting a contour line by subjecting the image to be processed to a secondary differential filter process or the like.
This is performed by comparing the similarity between the extracted outline and the outline drawn in the composition example. Further, the search is performed by comparing the color distribution of an image to be searched, the color of a specific portion, and the like with the color distribution drawn in the composition example.

When a plurality of images are selected in one scene in step S8, the order of the images is determined in the order of the date or time of the image file.

In step S8, the order in which the images selected for each scene using the composition example are arranged in the order of the scenario number is compared with the order in which the selected images are arranged in the order of the date or time associated therewith. (Step S9), and it is determined whether the order is different (step S10). If the order is different, the process proceeds to step S11; otherwise, the process skips step S11 and proceeds to step S12.

If the order of the scenario is opposite to the order of the file date or time, the order of the images is determined according to the order of the file date or time. Therefore, the scenario order is changed (step S11). Since the scenario order is defined by the scene number, the scene numbers are exchanged. The scenario order follows the order of the date or time of the file in order to give priority to the order that actually occurred.

Note that, by the scene search in step S8,
If the corresponding image is not selected as a result of the composition search, the scene is automatically deleted from the scenario.

Next, the scenario data is stored in the storage unit 109 (step S12). In the next step S13, the images of the hit image group are arranged and displayed in a list in the order of the scene numbers of the scenario data, or are output from the output unit 107 one by one in order. When the images are displayed in a list, the images are displayed in order by thumbnails.

In the image extracting apparatus according to the first embodiment, an image is extracted using a scenario prepared in advance or a scenario obtained by editing the scenario.
The scenario is not limited to a scenario prepared in advance, and a scenario newly created by defining a scene number, a scene name, and a composition example may be used.

As described above, the image extracting apparatus according to the first embodiment defines a composition corresponding to each scene of a scenario, and selects an image having a composition similar to the composition. Therefore, by defining the composition of the scene and the order of the scene as a scenario, a plurality of images can be extracted and displayed according to the scenario.

Also, a face image of a person can be specified as a key image, and an image including the same person as the person of the face image specified as the key image is selected, so that only a specific person is included. Images can be selected and output.

Further, even if the same scenario is used, by making the key images different from each other, it is possible to create a scenario for each person shown in each key image. Therefore, different scenarios can be created from the same image group only by changing the key images.

[Second Embodiment] The image extracting apparatus according to the first embodiment selects an image from an image group according to a scenario. However, the image extracting apparatus according to the second embodiment uses a scenario. For example, it is possible to efficiently and effectively automatically edit, for example, an image of a panorama of a daily scene. About the same part as the image extraction device in the first embodiment,
Do not repeat the description.

FIG. 6 is a flowchart showing a flow of an image extracting process executed by the image extracting apparatus according to the second embodiment. Referring to FIG. 6, operation unit 1 by the operator
By the operation at 05, a period is input (step S21). The period has a start period and an end period, each of which is input in the date. The time may be included in the date. Then, among the images included in the period input in step S21, the attribute of each image is determined (step S22). The attribute determination processing will be described later in detail.

Further, one or more images are selected from the images included in each attribute based on the determined attributes (step S23). Images with the same attribute often represent the same scene. Therefore, by selecting images having different attributes, images having different scenes can be selected. For this reason, by selecting at least the images that have changed in the situation, the situation in the predetermined period can be browsed with a small number of images.

In the next step S24, step S23
The image selected in is displayed. For display, a plurality of selected images are arranged in chronological order as thumbnail images and displayed. Also, by displaying the selected images in chronological order, a display such as a slide show can be obtained.

FIG. 7 is a flowchart showing the flow of the image attribute determining process performed in step S22 of FIG. Referring to FIG. 7, the image attribute determination process is performed in step S
This is performed on the images included in the period input at 21. The first image is read out of the images included in the period (step S31). The first image may be the image with the earliest date or the image with the latest date. Any one is selected.

Then, it is determined whether or not the read image is an unnecessary image (step S32). The determination as to whether or not the image is an unnecessary image is performed as to whether or not the image has failed to be captured. For example, a camera shake image, an out-of-focus image, or the like corresponds to an image for which shooting failed. In the determination of the camera shake image or the blurred image, for example, the contrast of the image is obtained, and when the contrast is low, the image is determined to be the camera shake image or the blurred image. If it is determined that the image is a camera shake image or an out-of-focus image, the process proceeds to step S38; otherwise, the process proceeds to step S34.

In step S34, it is determined whether the image is an image taken indoors or an image taken outdoors. For example, by analyzing the light source color temperature from the color histogram of the image, it is determined whether the image is indoor or outdoor.

Next, it is determined whether or not a person is included in the image (step S35). The presence or absence of a person is determined by determining whether or not there is a flesh-colored area in the image, extracting edges from the image, and determining whether the shape of the contour formed by the extracted edges is similar to the shape of the person. For example, a method of judging whether or not can be used. Then, step S35
(Step S3)
6). If it is determined that a person is included in the image,
The person tallying process is performed (step S37), and when it is determined that the person does not exist, the person tallying process is skipped and the process proceeds to step S38.

In the person tallying process, the difference between persons included in the image is distinguished (step S37). Here, since only the difference between the persons is distinguished without specifying the person, an appropriate label is defined for each person. Then, in the person tallying process, the label is added to the image. This will be described in detail later.

Then, in the next step S38, it is determined whether or not there is an image to be processed next. If there is an image, the process proceeds to step S32, and the above processing is repeated. To end.

FIG. 8 is a flowchart showing the flow of the person tallying process performed in step S37 of FIG. Referring to FIG. 8, a region of a person is extracted from the image (step S41). At this time, if the region of the person is too small or the shape of the region is determined to be a profile, the process ends without cutting out the region of the person.

If a plurality of persons have been cut out in step S41, one of the cut out persons is selected as the first person, and the region in which the first person is represented is set as the region to be processed ( Step S42). If there is one cut-out person, that person is set as the first person.

The person represented in the area to be processed is
It is determined whether or not the image is similar to an image of a person whose label is already defined (step S43). If the label is similar to the image of the defined person, step S
It proceeds to step S45, otherwise proceeds to step S44. In step S44, a new label is created, and a new person is associated with the label (step S4).
4). The label here may be a symbol for distinguishing the person from other people, and for example, a serial number can be used. One label is associated with the same person.

The label of the person represented in the area to be processed is given to the image currently being processed (step S45). Then, the number of persons is counted up (step S46), and the process proceeds to step S47.
The count-up of the number of persons indicates the number of persons included in the image to be processed.

In step S47, it is determined whether or not there is another cutout area (step S47). If there is another cutout area, that area is set as a processing target area in step S43. Otherwise, to step S48.

In step S48, the number of persons counted up in step S46 is added to the image to be processed.

FIG. 9 is a diagram showing an example of the relationship between the image and the attributes totaled by the person totaling process shown in FIG.
Referring to FIG. 9, the attributes include items of “indoor 0 / outdoor 1”, “there is a person”, “number of people”, “person A”, “person B”, and “person C”. For example, the attribute of "image 1"
The item “Indoor 0 / Outdoor 1” is “1”, and “Image 1”
Indicates that the image is taken indoors. Then, since the item of "there is a person" is set to "1", it indicates that the image of "image 1" includes a person. Further, since the item of “number of persons” is set to “3”, it is indicated that the image of “image 1” includes three persons.

"Person A", "Person B" and "Person C"
Is a label, and “1” is assigned to each. This indicates that the image of "image 1" includes a person associated with each label. That is, “image 1” includes the person labeled “person A”, the person labeled “person B”, and the person labeled “person C”.

In this way, the attribute is obtained for each image, and the image is associated with the attribute.

FIG. 10 is a flowchart showing the flow of the image selection process performed in step S23 of FIG.
Referring to FIG. 6, the image selection process is a process of extracting an image using attributes based on the relationship between the image created by the person tallying process and the attributes. First, using the attributes “indoor 0 / outdoor 1” and “with a person” as attributes, the respective images “indoor-less and indoor image” and “outdoor-less image” are selected. Then, one or several images are selected from the selected images. That is, in the image of “without a person and indoors”, an image in which the item of “indoor 0 / outdoor 1” is “1” and the item of “with a person” is “0” is selected and selected. At least one image is further selected from the images. As for the “image without person and outdoors”, an image in which the attribute “indoor 0 / outdoor 1” of the attribute is “1” and the item of “with person” is “0” is selected. At least one image is further selected from the selected images.

Next, by using the item "number of persons" of the attribute, the image of the attribute having the largest value in this item is extracted (step S52). This is because the number of selected images is reduced as much as possible by including as many people as possible in one image.

In the next step S53, a step S52
An image of a person not shown in the image selected in step is selected from the remaining images. Even in this case, an image having an attribute in which the value of the item “number of persons” is as large as possible is selected.
By repeatedly performing the process of step S53, an image can be selected such that the person included in any of the images selected in step S51 is included in any of the selected images.

The input period may be further divided into a plurality of periods, and the image extraction processing may be performed in each of the divided periods. For example, when a period of several days is specified, the image extraction processing is performed every day, and when a period of one year is specified, the image extraction processing is performed every month. Good.

As described above, in the image extracting apparatus according to the second embodiment, a plurality of images are classified according to the presence or absence of a person or included persons, and at least one image is classified from the classified images. I tried to extract. Therefore, the number of images including the same person can be reduced as much as possible, and a smaller number of images can be selected.

Further, the person included in the image is one for the same person.
Since the two labels are provided, it is possible to minimize the possibility that images including the same person are repeatedly selected.

Next, a modified example of the image extracting process of the image extracting apparatus according to the second embodiment will be described.

<First Modification> FIG. 11 is a flowchart showing a flow of a first modification of the image extracting process executed by the image extracting apparatus according to the second embodiment. FIG.
Referring to FIG. 1, in step S61, a period is input. The term has a starting term and an ending term, each of which is entered as a date.

Then, in step S62, step S
The images within the period input at 61 are extracted for each predetermined number in order of date and time (step S62). For example, if 100 images are selected within the period input in step S61, and if the predetermined number is 10, the oldest image is 1
An image is extracted for every zero image, and the images are selected in the order of the first old image, the eleventh old image, and the twenty-first old image.

Then, in step S63, step S
The image selected at 62 is displayed.

FIG. 12 is a diagram showing an example of an output in a first modified example of the image extracting process executed by the image extracting apparatus according to the second embodiment. Referring to FIG. 12, output screen 220 includes area 221 for displaying a calendar, area 224 for outputting an image, forward button 223, return button 222, and full screen display button 225.

By pointing the forward button 223 or the return button 222 with a pointing device such as a mouse, the month displayed in the area 221 is switched to the next month or the previous month. By pointing the date displayed in this area 221 with a pointing device, the beginning and end of the period can be input.

When the input of the period is completed and the image extracting power is executed, the extracted images are displayed in the area 224 in order. The date associated with the image displayed in the area 224 is also displayed. The display is automatically switched after a predetermined time has elapsed. Also, send button 2
The image can be manually switched using the button 23 and the return button 222. Full screen display button 225
Is pointed by the pointing device,
24 is displayed in the same size as the display screen, and the image displayed in the area 224 is displayed on the entire screen.

It is convenient to extract an image every day and specify a day in an area 221 so as to display an image extracted from an image corresponding to the date of the day.

In the case of the first modified example, since a predetermined number of images in a designated period are extracted and extracted, the browsing time can be shortened.

<Second Modification> FIG. 13 is a flowchart showing a flow of a second modification of the image extracting process executed by the image extracting apparatus according to the second embodiment. FIG.
Referring to FIG. 3, in step S71, first, a period is input. The period has a start period and an end period, each of which is input in the date. The time can be included in the date.

In step S72, the number m of pages to be browsed is input. In step S73, the images in the period input in step S71 are totaled, and the total number is set as the image number n.

In step S74, of the images within the period input in step S71, images are selected for every n / m sheets in chronological order. Then, the selected image is displayed (step S75).

The number of images n = 100 and the number of browsing m = 5
In this case, images are selected and displayed every 20 images. Therefore, the first old image, 21
The images are selected and displayed in the order of the oldest image and the 41st image.

In the case of the second modification, the number of pages to be viewed can be specified, which is effective when there is a restriction on the viewing time of the viewer.

<Third Modification> FIG. 14 is a flowchart showing the flow of a third modification of the image extracting process executed by the image extracting apparatus according to the second embodiment. FIG.
Referring to FIG. 4, first, a period is input (step S81). The period has a starting period and an ending period, and each is entered as a date. The time can be included in the date.

In step S82, the period input in step S81 is divided into equally spaced periods (step S8).
2). Then, one image included in the divided period is selected (step S83). Then, the selected image is displayed (step S83).

For example, when the designated period is from 8:00 am to 1:00 pm, and divided at an interval of one hour, 8:00 to 9:00, 9:00 to 10:00, 10 to 11:00, 11
One image included in each of the time periods from 12:00 to 12:00 and from 12:00 to 1:00 is selected.

Note that the number of images selected from each period is not limited to one, but may be two or more.

In the third modification, a period is divided and an image is extracted from each period. Usually, when the shooting time is close, the same scenery or scene is often shot in many cases, and by dividing the period into equal intervals, the probability of selecting the same scene decreases.

The embodiments disclosed this time are to be considered in all respects as illustrative and not restrictive. The scope of the present invention is defined by the terms of the claims, rather than the description above, and is intended to include any modifications within the scope and meaning equivalent to the terms of the claims.

[Brief description of the drawings]

FIG. 1 is a block diagram illustrating a schematic configuration of an image extracting device according to a first embodiment of the present invention.

FIG. 2 is a flowchart illustrating a flow of an image extraction process performed by the image extraction device according to the first embodiment.

FIG. 3 is a diagram illustrating an example of an image extraction condition setting screen displayed by the image extraction device according to the first embodiment.

FIG. 4 is a diagram illustrating an example of a scenario setting screen displayed on the image extraction device according to the first embodiment.

FIG. 5 is a diagram illustrating an example of scenario data stored in the image extraction device according to the first embodiment.

FIG. 6 is a flowchart illustrating a flow of an image extraction process performed by the image extraction device according to the second embodiment.

FIG. 7 is a flowchart showing a flow of an image attribute determination process performed in step S22 of FIG.

FIG. 8 is a flowchart showing a flow of a person tallying process performed in step S37 of FIG. 7;

FIG. 9 is a diagram illustrating an example of a relationship between an attribute and an image aggregated by a person aggregation process.

FIG. 10 is a flowchart showing a flow of an image selection process performed in step S23 of FIG.

FIG. 11 is a flowchart illustrating a flow of a first modified example of the image extraction processing executed by the image extraction device according to the second embodiment.

FIG. 12 is a diagram illustrating an example of an output in a first modified example of the image extraction processing executed by the image extraction device according to the second embodiment.

FIG. 13 is a flowchart illustrating a flow of a second modified example of the image extraction processing executed by the image extraction device according to the second embodiment.

FIG. 14 is a flowchart illustrating a flow of a third modified example of the image extraction processing executed by the image extraction device according to the second embodiment.

[Explanation of symbols]

Reference Signs List 100 image extraction device, 101 control unit, 103 image input unit, 105 operation unit, 107 output unit, 109 storage unit, 111 external storage device, 113 recording medium, 20
0 image extraction condition setting screen, 210 scenario setting screen, 231 scene number, 232 scene name, 233
Composition example, 234 hit image group.

Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI Theme coat II (reference) H04N 5/76 H04N 5/91 N 5L096 F term (reference) 5B050 AA09 BA06 BA11 CA04 CA07 DA04 DA10 EA03 EA18 FA02 FA09 FA12 FA13 FA19 GA08 5B075 KK33 KK38 MM11 ND07 ND12 ND14 ND23 ND34 NK06 NK13 NK24 NK42 PP02 PP03 PP12 PP13 PQ02 PQ04 PQ12 PQ44 PQ46 QS01 QS03 UU40 5C052 AA01 AC08 DD04 5C053 FA08 FA14 LA04 A03A01 A03A02A01 CA25 DA04 GA34

Claims (10)

[Claims] 1. A computer-readable recording medium storing an image extraction program for extracting an image from a storage unit in which a plurality of images are stored, comprising: a scene data defining each of a plurality of scenes; Receiving an input of an order; extracting an image corresponding to each of the plurality of defined scenes from the plurality of stored images; and ordering the extracted images in the defined scene. And a computer-readable recording medium on which an image extraction program for causing a computer to execute the step of outputting according to the above is recorded. 2. A computer-readable recording medium storing an image extraction program for extracting an image from a storage unit in which a plurality of images are stored, wherein said plurality of images are stored in a plurality of groups according to a predetermined rule. A computer-readable recording recording an image extraction program for causing a computer to execute the steps of: classifying the plurality of groups; extracting at least one image for each of the plurality of groups; and outputting the extracted images. Medium. 3. The classifying step includes a step of determining a scene of the image, and the determined scene follows a rule of classifying the same image into the same group.
A computer-readable recording medium on which the image extraction program described in 1 is recorded. 4. The image according to claim 2, wherein the plurality of images have time information, and the classifying step follows a rule of classifying the stored images into a predetermined number in a time series. A computer-readable recording medium recording an extraction program. 5. The computer-readable recording apparatus according to claim 2, wherein the plurality of images have time information, and the classifying step complies with a rule for classifying the images at predetermined time intervals. recoding media. 6. The computer-readable storage medium according to claim 2, wherein the classifying step includes a step of recognizing a subject included in the image, and the recognized subject follows a rule for classifying the same image into the same group. A recorded computer-readable recording medium. 7. A storage unit for storing a plurality of images, a scene definition unit for defining a plurality of scenes in order, and an image corresponding to each of the plurality of defined scenes is stored in the plurality of stored images. An image extracting apparatus, comprising: extracting means for extracting the extracted image from the image; and outputting means for outputting the extracted image in accordance with the defined sequence of scenes. 8. A storage unit for storing a plurality of images, a classification unit for classifying the stored plurality of images into a plurality of groups according to a predetermined rule, and extracting at least one image for each of the plurality of groups. An image extraction device, comprising: an extraction unit; and an output unit that outputs the extracted image. 9. An image extraction method for extracting an image from a storage unit in which a plurality of images are stored, the method comprising: receiving input of scene data defining each of a plurality of scenes and an order of the plurality of scenes; Extracting an image corresponding to each of the plurality of defined scenes from the plurality of stored images, and outputting the extracted images in accordance with the order of the defined scenes. Extraction method. 10. An image extraction method for extracting an image from a storage unit in which a plurality of images are stored, wherein the step of classifying the plurality of stored images into a plurality of groups according to a predetermined rule; An image extraction method, comprising: extracting at least one image for each group; and outputting the extracted image.