JP6636406B2 - Image extraction system, image extraction method and program thereof - Google Patents

Description

  The present invention relates to an image extraction system, an image extraction method, and a program for controlling a computer of the image extraction system.

  Since digital cameras, smartphones, and the like have become popular, users can easily take pictures, and thus users often own a large number of images. Since it is very difficult for a user to extract an image from a large number of images and create an album, there is a method in which an image is automatically extracted to create an album.

  When automatically creating an album, if the number of photographic images taken by a particular individual becomes extremely large or small, it may cause unfairness. Therefore, the number of appearances of each person is counted, and the number of appearances is extremely small. There is one that does not have a bias (Patent Document 1). There is also a method in which the importance of an image is specified according to the selection frequency of each subject, and the layout of an album is determined (Patent Document 2). Furthermore, an album is created so as to have an appropriate number and layout based on the total number of albums (Patent Literature 3). In the case of creating a photo book photo book of an idol group, the appearance frequency of members constituting the group is determined. There is also one to determine (Patent Document 4).

JP 2010-57073 A JP 2009-223764 A JP 2006-74590 A Patent No.5838752

  However, when an album is created, unless the images included in the album are extracted according to the theme of the album, the album cannot be created according to the user's intention. For example, if the album is about the theme of child-raising, the number of images of children will be increased, if the album is about the theme of travel, images of the scenery of the travel destination will be increased, and if the album is about the theme of a wedding, memories of the wedding will be remembered Increasing the number of images will create an album that meets the user's intention. However, Patent Literature 1 adjusts the number of appearances of a specific individual, Patent Literatures 2 and 3 determine the layout of an album, and Patent Literature 4 merely determines the appearance frequency of members. . In any case, it is not considered to extract the images from the plurality of images so that the proportion of the images along the theme represented by the plurality of images is appropriate.

  An object of the present invention is to extract images from a plurality of images so that the proportion of the images along the theme represented by the plurality of images is appropriate.

  An image extraction system according to the present invention includes: an object determining unit that determines an object existing in an image for each of a plurality of images; It is preferable that the image processing apparatus further comprises a ratio calculating means for calculating, and an image extracting means for extracting an image from the plurality of images so that an object present in the image after the extraction has the presence ratio calculated by the ratio calculating means. Features.

  The present invention also provides an image extraction method suitable for an image extraction system. That is, in this method, the object determining means determines an object present in the image for each of the plurality of images, and the ratio calculating means determines, for each type of object, the object determined by the object determining means in the plurality of images. Is calculated, and the image extracting means extracts an image from the plurality of images such that the object present in the image after the extraction has the presence ratio calculated by the ratio calculating means. .

  The present invention also provides a computer-readable program for controlling the image extraction system and a recording medium storing the program.

  The object determining means may further include an important object determining means for determining an important object among the plurality of objects when the image includes a plurality of objects. In this case, it is preferable to determine an object included in each of the plurality of images based on the important object determined by the important object determining unit.

  The image processing apparatus may further include a theme determining unit that determines a theme that uses the image extracted by the image extracting unit, and an object type storing unit that stores a type of an object associated with the theme. In this case, the object determining means determines, for example, at least the object of the type of the object stored in the object type storing means in association with the theme determined by the theme determining means.

  The object determining means is capable of determining one or more objects existing in one image, and calculating an object evaluation value representing the likeness of each of the determined one or more objects for each of the plurality of images. Means and an object evaluation value adding means for adding the object evaluation value calculated by the object evaluation value calculating means for each type of object. In this case, for example, the ratio calculating unit sets the ratio of the added value for each type of object obtained by the object evaluation value adding and calculating unit to the existence ratio of the object determined by the object determining unit.

  The object determining means is capable of determining one or more objects existing in one image, and calculating an object evaluation value representing the likeness of each of the determined one or more objects for each of the plurality of images. Means and an object evaluation value adding means for adding the largest object evaluation value among the object evaluation values calculated by the object evaluation value calculating means for each type of object. In this case, the ratio calculating unit sets, for example, the ratio of the added value for each type of object obtained by the object evaluation value adding unit to the ratio of the existence of the object determined by the object determining unit.

  The image processing apparatus may further include a similar image detecting unit that detects a similar image among the plurality of images. In this case, the object evaluation value calculating means calculates, for example, a relatively high object evaluation value of an object existing in the similar image detected by the similar image detecting means.

  When a similar image detecting means for detecting a similar image among a plurality of images is further provided, the ratio calculating means may include, for example, only one image of the similar images among the similar images detected by the similar image detecting means. , The ratio of the existence of the object determined by the object determining means is calculated.

  The similar image detecting means detects, for example, a similar image for each image in which the object determined by the object determining means is the same.

  The image processing apparatus may further include an album generating unit that generates an album using the image extracted by the image extracting unit.

  The album generating means generates an album by pasting the image extracted by the image extracting means to the album so as to have a size corresponding to the ratio calculated by the ratio calculating means.

  In the facing pages of the album, the album generating means generates an album by pasting the images extracted by the image extracting means to the album so as to have a size corresponding to the ratio calculated by the ratio calculating means. Is also good.

  In the entire album, the album generating means, for example, converts the images extracted by the image extracting means so as to have an area ratio corresponding to the ratio of the existence of the object for each type of object calculated by the ratio calculating means. Create an album by pasting it on the album.

  The album generating means generates the album by pasting the images extracted by the image extracting means to the album, for example, according to the priority according to the ratio of the existence of the object for each type of object calculated by the ratio calculating means. .

  The album generating means generates an album by using the images extracted by the image extracting means, for example, according to the image capturing order.

  According to the present invention, an object existing in an image is determined for each of the plurality of images. For each of the determined object types, the ratio of the presence of the object in the plurality of images is calculated, and the images are extracted from the plurality of images so that the objects existing in the extracted image have the calculated ratio of the presence. Is done. By extracting the images in this manner, the ratio of the images according to the theme represented by the plurality of images becomes appropriate.

FIG. 2 is a block diagram illustrating an electrical configuration of the image extraction system. It is a flowchart which shows the processing procedure of an image extraction system. 4 shows an image stored on a memory card. It is an example of an image. It is an example of an image. It is an example of an image. It is an example of an image. It is an example of an object table. It is an example of the facing page which comprises an album. It is a flowchart which shows an object determination processing procedure. It is an example of an object table. It is a flowchart which shows an object determination processing procedure. It is an example of an object type storage table. 9 is a flowchart illustrating a procedure for calculating a ratio of the presence of an object. It is an example of an object table. It is a flowchart which shows the calculation processing procedure of an object evaluation value. 9 is a flowchart illustrating a procedure for calculating a ratio of the presence of an object. It is an example of the facing page which comprises an album. It is an example of the facing page which comprises an album.

[Example 1]
FIG. 1 shows an embodiment of the present invention, and is a block diagram showing an electrical configuration of an image extraction system 1.

  The overall operation of the image extraction system 1 is controlled by a CPU (Central Processing Unit) 2.

  The image extraction system 1 includes a keyboard 3 and a mouse 4 as input devices for giving commands and the like to the image extraction system 1. Commands and the like from the keyboard 3 and the mouse 4 are given to the CPU 2 via the input control device 5. The image extraction system 1 includes a memory 8 for temporarily storing data, a hard disk 7, a hard disk drive 6 for accessing the hard disk 7, a display device 10, and a display control device for controlling the display device 10. 9 are included.

  The image extraction system 1 further includes a memory card reader / writer 11 for accessing the memory card 12, a CD-ROM drive 13 for accessing a CD-ROM (Compact Disc Read Only Memory), and the Internet. And a communication device 15 for connecting to the network.

  A CD-ROM 14 (recording medium) storing a program for controlling an operation described later is read by the CD-ROM drive 13, and the read program is installed in the image extraction system 1. Such a program may be stored in a portable recording medium such as the memory card 12 other than the CD-ROM 14, or may be installed in the image extraction system 1 in advance. Alternatively, the program may be received by the communication device 15 via a network such as the Internet, and the received program may be installed in the image extraction system 1.

  FIG. 2 is a flowchart illustrating a processing procedure of the image extraction system 1.

  The processing procedure shown in FIG. 2 is for extracting images from a plurality of images stored in a designated storage location and generating an album using the extracted images.

  On the display screen of the display device 10, a storage location specifying image for specifying a storage location where a plurality of images are stored is displayed. Using the storage location specification image, the user can specify a storage location such as the hard disk 7, the CD-ROM 14, the memory card 12, or a storage area on the network. If a USB (Universal Serial Bus) memory (not shown) can be connected to the image extraction system 1, a USB memory can be specified as a storage location. The user uses the keyboard 3 or the mouse 4 to specify the storage location of the image used to generate the album (step 21). In this embodiment, it is assumed that the memory card 12 has been designated by the user as an image storage location.

  FIG. 3 shows an image stored in the memory card 12 designated as a storage location of the image.

  It is assumed that the memory card 12 stores 500 image files represented by image file names from IMG001 to IMG500. However, the image file names need not be consecutive. For example, the user brings the memory card 12 and goes on a trip, and 500 images are stored in the memory card 12 by shooting at the travel destination.

  4 to 7 show images 31 to 34 represented by some of the 500 image files stored in the memory card 12. FIG.

  FIG. 4 is an example of the image 31 represented by the image file name IMG001. The image 31 is an example of an image including a mountain, a river, and the sun.

  FIG. 5 is an example of the image 32 represented by the image file name IMG002. The image 32 is an example of an image including a flower and a cloud.

  FIG. 6 is an example of the image 33 represented by the image file name IMG003. The image 33 is an example of an image including a person, a mountain, a cloud, and a flower.

  FIG. 7 is an example of the image 34 represented by the image file name IMG004. The image 34 is an example of an image including dishes and flowers.

  Returning to FIG. 2, for each of the plurality of images stored in the storage location (the memory card 12 in this embodiment) designated by the user, the object existing in the image is determined by the CPU 2 (object determining means). Is performed (step 22). The CPU 2 may specify a shooting period and determine an object object existing in the image shot during the shooting period among the images stored in the storage location. The type of object to be determined is determined in advance (it does not need to be determined in advance), and in this embodiment, landscapes, flowers, people, and dishes are predetermined as objects. If an object existing in the image is recorded in the header included in the image file, the recorded object may be determined to be an object existing in the image.

  In this embodiment, an object (subject) included in an image is detected, and an object (target represented by the image) existing in the image is determined by the CPU 2 from the detected object. In the case of the image 31 shown in FIG. 4, the object of the mountain, the river, and the sun is detected from the image 31, and the object existing in the image 31 is “landscape” from the detected objects of the mountain, the river, and the sun. Is determined. The detected object (mountain, river, sun) itself may be determined as an object existing in the image. Similarly, in the case of the image 32 shown in FIG. 5, the object of the flower and the cloud is detected from the image 32, and the object existing in the image 32 is called “flower” from the detected object of the flower and the cloud. It is determined to be "landscape". In the case of the image 33 shown in FIG. 6, an object of a person, a mountain, a cloud, and a flower is detected from the image 33, and an object existing in the image 33 is extracted from the detected object of the person, the mountain, the cloud, and the flower. Are determined to be "person", "landscape", and "flower". Further, in the case of the image 34 shown in FIG. 7, objects of food, drink, and flower are detected from the image 34, and the object existing in the image 34 is “cooking” from the detected objects of food, drink, and flower. "And" flower ". Objects existing in the images are similarly determined for the images having image file names IMG005 to IMG500 other than the image file names IMG001 to IMG004.

  FIG. 8 is an example of the object table.

  The object table shown in FIG. 8 stores objects determined as objects existing in the image represented by the image file names corresponding to the image file names from IMG001 to IMG500.

  Returning to FIG. 2, when an object present in the image is determined, the CPU 2 (ratio calculating means) calculates the ratio of the object present in the plurality of images for each type of the determined object (step twenty three). For example, of the 500 images, 250 objects of the "landscape" type, 150 objects of the "flower" type, 50 objects of the "person" type, and 50 objects of the "cooking" type Assuming that there are 50 objects, the proportions of the objects of the type “landscape”, the object of the type “flower”, the object of the type “person”, and the object of the type “cooking” are 5: 3: 1: It becomes 1.

  When the ratio of the presence of the object in the plurality of images is calculated, the CPU 2 (image extracting unit) converts the image from the plurality of images so that the object existing in the image after the extraction has the calculated ratio of the presence. It is extracted (step 24). The number of images to be extracted may be determined by the user or may be predetermined. When the number of images to be extracted is 100, the determined object is 50 images of "landscape", the determined object is 30 images of "flower", and the determined object is "person" Are extracted from 10 images of which the determined object is “cooking” and 500 images represented by the image files stored in the memory card 12. Even when the number of images to be extracted is other than 100, the objects existing in the image after the extraction are determined by the CPU 2 by the image file stored in the memory card 12 so as to have the calculated existence ratio. Extracted from the 500 images represented.

  When there are a plurality of types of objects existing in the image, such as the objects “flower” and “landscape” corresponding to the image file name IMG002 stored in the object table of FIG. Otherwise, one of the plurality of types of objects may be determined as the object of the image. Further, the CPU 2 (object evaluation value calculating means) may calculate an object evaluation value indicating the object-likeness of the object existing in the image, and may or may not extract the image from the object having the higher object evaluation value. Images may be extracted so that the intervals between the shooting dates and times of the images are equal, or an image evaluation value that indicates whether the image itself is good (whether the brightness of the image, the degree of focusing, etc. are appropriate). ) May be calculated, and the image may be extracted from the one with the highest image evaluation value, or the image may be simply extracted at random.

  Using the extracted images, an album (electronic album) is generated by the CPU 2 (album generating means) (step 25).

  FIG. 9 is an example of a double-page spread forming the generated album.

  Images 31-36 and the like are extracted, and the extracted images 31, 32, and 34 are pasted on the left side page 41 of the facing pages forming the album, and the extracted images 33, 35, and 36 are attached to the facing pages forming the album. Affixed to page 42 on the right. The size and position of the image attached to the album may be determined in any manner.

  According to the first embodiment, the ratio of the presence of the object in the plurality of images is calculated, and the image is extracted from the plurality of images such that the object existing in the image after the extraction has the calculated ratio of the presence of the object. Therefore, it is possible to extract an image reflecting a theme represented by a ratio of the existence of a plurality of types of objects in a plurality of images.

[Example 2]
10 and 11 show the second embodiment.

  FIG. 10 is a flowchart showing the object determination processing procedure (the processing procedure of step 22 in FIG. 2).

  Objects (mountains, rivers, flowers, people, dishes, etc.) included in the image are detected by the CPU 2 (step 51), and the CPU 2 determines whether or not a plurality of objects are included in the image (step 52). When the object included in the image is recorded in the header included in the image file, the object may be read. If the image contains a plurality of objects (YES in step 52), the important object is determined by the CPU 2 (important object determining means) from the plurality of objects (step 53). Whether an object is important is determined by the position in the image (for example, the closer to the center of the image, the more important the object), the object evaluation value (the higher the object evaluation value, the more important the object), the brightness, the degree of focus, etc. Objects that are evaluated as images (objects with higher image ratings are considered important objects), objects that match specific themes (for example, travel, weddings, etc.) If so, it can be determined based on whether the dress, ring, bouquet, etc.). If the image does not include a plurality of objects (NO in step 52), the processing in step 53 is skipped.

  If the image contains more than one object, the objects present in the image are determined based on the important objects, and if the image does not contain more than one object, the objects are determined based on the detected objects. It is determined that the object exists in the image (step 54).

  FIG. 11 is an example of an object table obtained by the processing procedure of FIG.

  In the object table shown in FIG. 8, a plurality of objects are defined corresponding to the image file names IMG002 to IMG004, but in the object table shown in FIG. 10, one object corresponds to the image file names IMG002 to IMG004. One object (an object that is determined based on important objects). When the number of objects existing in the image is determined to be one, using the determined object, the CPU 2 determines the proportion of the object present in the plurality of images for each type of object as described above (see FIG. 2). Step 23).

  Since one object is determined for each image in the image, the subsequent image extraction processing is relatively easy.

  According to the second embodiment, since important objects are determined, it is possible to extract a more natural image reflecting the theme represented by the ratio of existence of important objects when paying attention to important objects in a plurality of images. .

[Example 3]
12 and 13 show a third embodiment.

  FIG. 12 is a flowchart showing an example of the object determination processing procedure (the processing procedure of step 22 in FIG. 2).

  In this embodiment, the theme of the image to be extracted is determined by the CPU 2 (theme determining means) (step 61). By analyzing a plurality of images stored in the specified image storage location, the theme represented by the plurality of images may be determined, or some themes may be displayed on the display screen of the display device 10. And the theme may be determined using the mouse 4 (theme determining means) or the user may determine the theme using the keyboard 3 (theme determining means).

  FIG. 13 is an example of the object type storage table.

  The object type storage table shown in FIG. 13 stores a plurality of object types corresponding to themes. Themes include travel, weddings, and entrance ceremonies. The travel theme stores types of objects such as landscapes, flowers, and dishes. The wedding theme stores types of objects such as dresses, rings, bouquets, and dishes. In the theme of the entrance ceremony, types of objects such as school bags and school gates are stored. Similarly, the types of objects corresponding to the other themes are stored. Such an object type storage table is stored in the memory 8 (object type storage means) in advance.

  Returning to FIG. 12, when the theme is determined, as shown in FIG. 13, the type of the object associated with the determined theme is determined at least as an object existing in the image (step 62). For example, if “Travel” is determined as the theme, “Landscape”, “Flower”, “Cooking”, etc., stored corresponding to the travel, as described above, are set as a plurality of objects existing in the image. It will be determined for each of the images. The object determined in this way is stored in the object table shown in FIG. 8 or FIG.

  According to the third embodiment, an object is determined for an object of the type stored in association with the determined theme. Therefore, the theme represented by the proportion of the object present when focusing on the stored type of object is determined. It is possible to extract a more natural image that reflects the reflection.

[Example 4]
14 and 15 show a fourth embodiment.

  FIG. 14 is a flowchart showing a processing procedure for calculating the ratio of the presence of an object in a plurality of images for each type of object (the processing procedure of step 23 in FIG. 2). FIG. 15 corresponds to FIG. 8 and is an example of an object table.

  When the object existing in the image is determined as shown in step 22 in FIG. 2, the object is stored in the object table corresponding to the image file name representing the image as shown in FIG.

  In this embodiment, the CPU 2 (object evaluation value calculation means) calculates an object evaluation value indicating the likeness of an object for each determined object (step 71). A large number of data representing the shape, color, and the like of a general material determined to be an object are stored in the memory 8, and an object evaluation value is calculated by calculating the degree of coincidence with the data. For example, in the case of a "landscape" object, a large number of data representing mountains, rivers, plateaus, lakes, the sea, clouds, the sun, the sky, their arrangement, and the like are stored. Based on the degree of coincidence with these data, " An object evaluation value representing the likeness of an object of "landscape" is calculated by the CPU 2 (object evaluation value calculation means). When the object evaluation value is calculated for the object existing in the image, the calculated object evaluation value is stored in the object table shown in FIG. Although the object evaluation value is set to a value of 100 or less, it is not always necessary to set such a value.

  Referring to FIG. 15, the object existing in image 31 (see FIG. 4) represented by image file name IMG001 is determined to be “landscape”, and its object evaluation value is calculated to be “100”. The objects existing in the image 32 (see FIG. 5) represented by the image file name IMG002 are determined to be “flower” and “landscape”, the object evaluation value of “flower” is calculated as “90”, and “landscape” Is calculated as "20". Similarly, the objects existing in the image 33 (see FIG. 6) represented by the image file name IMG003 are determined to be “person”, “landscape” and “flower”, and the object evaluation value of “person” is “80” The object evaluation value of “landscape” is calculated as “70”, and the object evaluation value of “flower” is calculated as “25”. The objects existing in the image 34 (see FIG. 7) represented by the image file name IMG004 are determined to be “dish” and “flower”, the object evaluation value of “dish” is calculated as “100”, and “flower” Is calculated as “30”.

  Returning to FIG. 14, when the object evaluation value is calculated, the object evaluation value is added by the CPU 2 (object evaluation value adding means) for each type of object (step 72). For example, in the case of an object of “landscape”, all the calculated object evaluation values of “landscape” are added, and an added value of the object evaluation value of “landscape” is obtained. Similarly, an addition value of the object evaluation value of “flower”, an addition value of the object evaluation value of “person”, and an addition value of the object evaluation value of “food” are obtained.

  The ratio of the added value of the object evaluation values for each type of object obtained in this manner is set as the ratio of the existence of the object (step 73). For example, the addition value of the object evaluation value of "landscape" is N1, the addition value of the object evaluation value of "flower" is N2, the addition value of the object evaluation value of "person" is N3, and the addition value of the object evaluation value of "food" is Assuming that the value is N4, the proportion of objects existing in a plurality of images stored in the storage location is “landscape”: “flower”: “person”: “cooking” = N1: N2: N3: N4. Become.

  When the proportion of the objects existing in the plurality of images is determined, as shown in step 24 in FIG. 2, the objects existing in the extracted image are stored in the storage location so as to have the calculated proportion of the existence. An image is extracted from the plurality of stored images.

  In the above-described embodiment, the object evaluation value is added for each type of object to calculate the added value of the object evaluation value. However, the largest object evaluation value among the object evaluation values of the objects determined to be present in the image. The value may be calculated by the CPU 2 (object evaluation value calculation means) for each type of object.

  For example, the object existing in the image 31 (see FIG. 4) represented by the image file name IMG001 is only "landscape", and the maximum object evaluation value is "100" of the "landscape". The objects existing in the image 32 (see FIG. 5) represented by the image file name IMG002 are “flower” and “landscape”, and the object evaluation value of “flower” is calculated as “90”. The object evaluation value is calculated as “20”. The maximum object evaluation value is “90”, which is the object evaluation value of “flower”. Similarly, the objects existing in the image 33 (see FIG. 6) represented by the image file name IMG003 are “person”, “landscape” and “flower”, and the object evaluation value of “person” is “80”. The object evaluation value of “landscape” is calculated as “70”, and the object evaluation value of “flower” is calculated as “25”. The maximum object evaluation value is “80” which is the object evaluation value of “person”. The objects existing in the image 34 (see FIG. 7) represented by the image file name IMG004 are “dish” and “flower”, and the object evaluation value of “dish” is calculated as “100”. The object evaluation value is calculated as “30”. The maximum object evaluation value is “100” for “dish”.

  In this way, of the object evaluation values calculated for each image, the largest object evaluation value is added by the CPU 2 for each type of object evaluation value (object evaluation value adding means), and the added value for each type of object is calculated. can get. Object evaluation values other than the maximum object evaluation value are not subject to addition. For example, the objects present in the image 32 (see FIG. 5) represented by the image file name IMG002 are “dish” and “flower”, and the object evaluation value of “dish” is calculated as “100”, and “food” is calculated. Is calculated as “30”, and among these object evaluation values, the object evaluation value “100” of “Cooking”, which is the largest object evaluation value, is the object evaluation value for each object type. , And the object evaluation value “30” of “flower” is not added.

  The ratio of the added value of the object evaluation values for each type of object obtained in this manner is set as the ratio of the existence of the object (step 73), as described above.

  According to the fourth embodiment, the ratio of the added value for each type of object is defined as the ratio of the existence of the object. Therefore, in a plurality of images, both the object of the type having the largest object evaluation value and the object evaluation value of that type are displayed. , It is possible to extract a more natural image reflecting the theme represented by the proportion of the existence of the object when focusing on.

[Example 5]
FIG. 16 shows the fifth embodiment, and is a flowchart showing the procedure for calculating the object evaluation value (the procedure of step 71 in FIG. 14).

  In this embodiment, a similar image is detected by the CPU 2 (similar image detecting means) among a plurality of images stored in a storage location designated by the user (step 81). The detection of similar images is performed based on the degree of matching by matching processing between images, but may be performed by another method.

  If there is a similar image, the object existing in the similar image can be regarded as important by the user. Therefore, when a similar image is detected, the CPU 2 calculates an object evaluation value such that the object evaluation value of the object determined as an object existing in the similar image becomes relatively high (step 82). Since the object evaluation value is relatively high, the rate at which images containing the object are extracted increases. The calculated object evaluation value may be multiplied by a coefficient larger than 1 to increase the object evaluation value.

  As described above, the calculation of the object evaluation value such that the object evaluation value is relatively high is performed not only when the maximum object evaluation value is added to obtain the added value, but also when the calculated object evaluation value is obtained. May be performed in any case in which is added for each type of object to obtain an added value. If the object evaluation value is calculated when the important object is determined in step 53 of FIG. 10, even if the object evaluation value of the object existing in the similar image is relatively high in the calculation of the object evaluation value. Good.

  According to the fifth embodiment, the ratio of the added value for each type of object is set as the ratio of the existence of the object. Therefore, the ratio of the existence of the plurality of types of objects and the intention to adopt more similar images in the plurality of images. It is possible to extract a more natural image reflecting the theme represented by the ratio of the existence of the object when focusing on both.

[Example 6]
FIG. 17 shows the sixth embodiment, and is a flowchart showing the procedure for calculating the ratio of the presence of an object (the procedure of step 23 in FIG. 2).

  Also in this embodiment, a similar image is detected by the CPU 2 (similar image detecting means) from a plurality of images stored in a storage location designated by the user (step 91).

  If there is a similar image, as described with reference to FIG. 16, the objects present in the similar image can be considered to be important by the user, but conversely, the objects considered to be important are not. Not always. For this reason, for similar images, the CPU 2 calculates the ratio of the presence of the object in a plurality of images for each object type for one image among the similar images (step 92). For example, when it is determined that the image 31 shown in FIG. 4 and the image 33 shown in FIG. 6 are similar images, for one of the images 31 and 33, a plurality of images are provided for each type of object. Is calculated (step 92). Thus, even when there are a plurality of similar images, the images can be extracted without being affected by the plurality of similar images.

  According to the sixth embodiment, for a similar image, the ratio of the existence of the object is calculated for only one image. Therefore, the existence of a plurality of types of objects and the similar image in a plurality of images are only one image. It is possible to extract a more natural image that reflects the theme represented by the ratio of the presence of the object when focusing on both intentions to emphasize.

[Example 7]
FIG. 18 shows the seventh embodiment, which is an example of facing pages forming an album, and corresponds to FIG.

  Images 31 and 32 are pasted on the left page 101, and images 33 to 36 are pasted on the right page 102. The album may be an electronic album displayed on the display screen of the display device 10 or a paper album.

  The image attached to the facing page of the album shown in FIG. 18 has a size corresponding to the ratio calculated as described above on the facing page of the album. For example, assuming that the proportion of the object in a plurality of images is “landscape”: “flower”: “person”: “cooking” = 5: 3: 1: 1, “landscape” exists as an object. When the size of the image 31 and the image 35 is 5, the size of the images 32 and 36 in which “flower” exists as an object is 3, and the image 33 and the “dish” in which “person” exists as an object are the objects. Assuming that the size of the image 36 existing as “1” is 1, the images 31 to 36 are pasted on the facing pages of the album.

  In the example shown in FIG. 18, the size of the image is adjusted on the facing pages forming the album. However, the size of the image may be adjusted on the entire album, not on the facing pages forming the album. . When the size of the image is adjusted in the entire album, the extracted image is divided for each object existing in the image, and the ratio of the total area of all the images divided for each object is calculated as described above. And the size according to the ratio calculated. For example, assuming that the ratio of the existence of an object in a plurality of images is “landscape”: “flower”: “person”: “cooking” = 5: 3: 1: 1, the total number of extracted images is Assuming that 40 images are used to generate one album from these 40 images, 20 images have "landscape" as an object, 12 images have "flower" as an object, and "person" Are present as objects, and there are four images in which "cooking" is present as an object. Then, the total area of 20 images in which “landscape” exists as an object, the total area of 12 images in which “flower” exists as an object, and the total area of four images in which “person” exists as an object. The ratio of the area to the total area of the four images in which “dish” exists as an object is 5: 3: 1: 1, as in the case of the ratio of the object in a plurality of images. The extracted 40 images are pasted on the album.

  Such image size adjustment is performed by the CPU 2 (image size adjustment means) to generate an album. When a paper album is generated, it goes without saying that the printer is controlled by the CPU 2.

  As described above, an album may be generated by pasting the extracted image onto the album so that the size of the image is determined according to the calculated ratio of the presence of the object.

  According to the seventh embodiment, since the images are pasted on the album so as to have a size corresponding to the calculated ratio, the existence of the object when attention is paid to the ratio of the existence of the plurality of types of objects in the plurality of images. By reflecting the ratio on the size of the album, the album can be generated more naturally.

Example 8
FIG. 19 shows an eighth embodiment, which is an example of a facing page forming an album, and corresponds to FIGS. 9 and 19.

  In the facing page shown in FIG. 19, the image 31 and the image 35 are pasted on the left page 111, and the images 37 to 39 are pasted on the right page 112.

  In the example shown in FIG. 19, the extracted images are pasted on the album in a priority order according to the ratio of the existence of the object calculated as described above. For example, assuming that the ratio of the presence of the object in a plurality of images is “landscape”: “flower”: “person”: “cooking” = 5: 3: 1: 1, the priority order according to these ratios As an example, among the extracted images, the image in which the object of "landscape" exists is continuously attached to the album, the image in which the object of "flower" exists continuously is attached to the album, and then the " The images in which the object of "person" exists are continuously attached to the album, and the images in which the object of "cooking" exists are continuously attached to the album. Also, five consecutive images with the object “landscape” are pasted to the album, and then three images with the object “flower” are consecutively pasted on the album. One image containing the object may be pasted on the album, and then the image containing the object of "cooking" may be pasted on one album, and thereafter, the pasting of the image may be repeated in the same manner.

  In this embodiment, when an image is pasted on a two-page spread, if the number of images to be pasted on the two-page spread is smaller than the sum of the numerical values indicating the existence ratio of the object, the object having a higher proportion of the object exists The image where is present is preferentially pasted.

  For example, in the case of the example shown in FIG. 19, as a result of adjusting the numerical value indicating the existence ratio so that when all the existence ratios of the objects are added up to 10, the image in which the “landscape” object is present becomes 5 images. Three consecutive images with the object "Flower" are pasted on the album, and then one image with the object "People" is pasted on the album. Thereafter, a priority order is generated in which an image including the object of “cooking” is pasted to one album.

  Then, since five images are to be attached to the double-page spread in the example shown in FIG. 19, five images including the “landscape” object are pasted to the album in succession, and the other images are attached. As a result, the image in which the object exists is not pasted.

  Further, the extracted images may be pasted on the facing pages forming the album in a priority order according to the calculated ratio of the presence of the object. For example, assuming that the proportion of the object in a plurality of images is “landscape”: “flower”: “person”: “cooking” = 5: 3: 1: 1, the left page 111 and the right page 112 In the double-page spread consisting of five images with the "landscape" object attached to the double-page spread, three images with the "flower" object attached to the double-page spread, and the "person" One image including the object may be pasted on a double-page spread, and one image including the “cooking” object may be pasted on the double-page spread. An image may be similarly attached to another facing page, or an extracted image may be attached to another facing page by a different configuration. Also, the order of pasting in the facing pages may be in accordance with the ratio of the presence of the object in the plurality of images.

  Further, the extracted images may be attached to an album in accordance with the image capturing order. Images may be pasted in the entire album in accordance with the image capturing order, or images may be pasted in the facing pages forming the album in the image capturing order.

  In the above-described embodiment, although “person” is not distinguished as an object existing in an image, “person” is included in a plurality of images stored in a specified storage location. 2 and a non-human image that does not include a "person". The non-human image is subjected to the processing from step 22 onward in FIG. 2 to extract images from a plurality of non-human images. Good. Further, the plurality of images stored in the specified storage location are divided into a plurality of image groups in accordance with the imaging order, and the plurality of images included in the divided image groups are described in FIG. Subsequent processing may be performed.

  According to the eighth embodiment, the extracted images are pasted to the album according to the priority according to the calculated ratio. Therefore, even when the pasting area of the album is limited, the image including the object with the higher priority is prioritized. Pasted into the album.

  1 image extraction system, 2 CPU, 3 keyboard, 4 mouse, 5 input control device, 6 hard disk drive, 7 hard disk, 8 memory, 9 display control device, 10 display device, 11 memory card reader / writer, 12 memory・ Card, 13 CD-ROM drive, 14 CD-ROM, 15 communication device, 31-39 image, 41 left page, 42 right page, 101 left page, 102 right page, 111 left page, 112 right page, IMG001-IMG005 Image file name

Claims (17)

Object determining means for determining an object existing in each of the plurality of images,
For each type of the object, a ratio calculating unit that calculates a ratio of the existence of the object determined by the object determining unit in the plurality of images, and an object that exists in the extracted image is calculated by the ratio calculating unit. Image extracting means for extracting an image from the plurality of images so as to have a proportion of the presence determined
An image extraction system comprising: The object determining means is
Important object determining means for determining an important object among the plurality of objects when the image includes a plurality of objects;
Determining an object included in an image for each of the plurality of images based on the important object determined by the important object determining means;
The image extraction system according to claim 1. A theme determining means for determining a theme using the image extracted by the image extracting means,
Object type storage means for storing the type of the object associated with the theme,
The object determining means is
For objects of the type stored in the object type storage means associated with the theme determined by the theme determination means, at least object determination is performed.
The image extraction system according to claim 1. The object determining means is
One or more objects existing in one image can be determined,
An object evaluation value calculating means for calculating the determined object evaluation value of each of the one or more objects for each of the plurality of images; and an object evaluation value calculated by the object evaluation value calculating means. Further comprising an object evaluation value adding means for adding for each type of object;
The above ratio calculating means is:
The ratio of the added value for each type of object obtained by the object evaluation value adding unit is defined as the ratio of the existence of the object determined by the object determining unit.
The image extraction system according to claim 1. The object determining means is
One or more objects existing in one image can be determined,
An object evaluation value calculating means for calculating the determined object-likeness of each of the one or more objects for each of the plurality of images; and an object evaluation value calculated by the object evaluation value calculating means. , Further comprising an object evaluation value adding means for adding the maximum object evaluation value for each type of object,
The above ratio calculating means is:
The ratio of the added value for each type of object obtained by the object evaluation value adding unit is defined as the ratio of the existence of the object determined by the object determining unit.
The image extraction system according to claim 1. A similar image detecting means for detecting a similar image among the plurality of images;
The above object evaluation value calculating means comprises:
Calculating a relatively high object evaluation value of an object existing in the similar image detected by the similar image detecting means;
The image extraction system according to claim 4. A similar image detecting means for detecting a similar image among the plurality of images;
The above ratio calculating means is:
For similar image detected by the upper Symbol such similar image detection means, among the similar image, the only one image, and calculates the ratio of existence of the object determined by the object determination unit,
The image extraction system according to claim 1. The above similar image detecting means includes:
The object determined by the object determining means detects a similar image for each identical image,
The image extraction system according to claim 7. Album generating means for generating an album using the images extracted by the image extracting means,
The image extraction system according to any one of claims 1 to 8, further comprising: The album generating means,
Generating an album by pasting the image extracted by the image extracting means on the album so as to have a size corresponding to the rate calculated by the rate calculating means;
The image extraction system according to claim 9. In the two-page spread page of the album, the album generating means pastes the image extracted by the image extracting means onto the album so as to have a size corresponding to the ratio calculated by the ratio calculating means. Produces
The image extraction system according to claim 9. In the whole album, the album generating means is extracted by the image extracting means so as to have an area ratio corresponding to the ratio of the existence of the object for each type of the object calculated by the ratio calculating means. Paste the images into the above album to generate an album,
The image extraction system according to claim 9. The album generating means,
Generating the album by pasting the images extracted by the image extracting means to the album in accordance with the priority according to the ratio calculated by the ratio calculating means for each type of the object;
The image extraction system according to claim 9. The album generating means,
Generating an album using the images extracted by the image extracting means in accordance with the image capturing order;
The image extraction system according to claim 9. Object determining means for determining an object existing in the image for each of the plurality of images;
A ratio calculating unit that calculates, for each type of the object, a ratio of the existence of the object determined by the object determining unit in the plurality of images;
An image extracting means for extracting an image from the plurality of images so that an object present in the image after the extraction has the presence ratio calculated by the ratio calculating means;
An image extraction method comprising: A computer readable program of the image extraction system,
For each of the plurality of images, the object existing in the image is determined,
For each type of object, calculate the percentage of the determined object in the plurality of images,
A program of an image extraction system for extracting an image from a plurality of images so that an object present in the extracted image has a calculated ratio of existence.   17. A recording medium storing the program according to claim 16.

Images