JP2002215643A - Image classification program, computer readable recording medium recording image classification program, and method and device for classifying image - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an image classifying method allowing the appropriate classification of images while reducing a user's labor. SOLUTION: A person photographed in an image to be classified is extracted (S505), and whether the person is already registered in a classification table is determined (S507). If not registered yet, the image of the person is registered in a person table in the classification table (S509), and the file name of the image is registered correspondingly (S511). In the case the extracted person is already registered, the registration processing of the person is skipped. The same processing is carried out on all the extracted persons (S507-S513). When the registration processing is completed on all the images to be classified, summing processing of the registered results is performed (S519). The file names of the images with the persons photographed are thereby registered automatically for every person photographed in the image, and appropriately classified.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image classification program, a computer-readable recording medium storing the program, an image classification method, and an image classification device. The present invention relates to an image classification program that can be classified and totalized, a computer-readable recording medium storing the program, an image classification method, and an image classification device.

[0002]

2. Description of the Related Art In recent years, with the widespread use of digital cameras, there are increasing opportunities for taking images in various scenes using digital cameras. The captured image is
For example, it is taken into a personal computer, and the user prints out or mails the required number of copies.

[0003]

However, when the number of photographed images increases and a plurality of persons are transferred to each image, the images are classified and printed out for the necessary persons. The task of delivering mail was very cumbersome and took time and effort. In addition, a situation such as a print output error or a transmission error due to an error has occurred.

The present invention has been conceived in view of the above circumstances, and has as its object to reduce an operation labor and to appropriately classify an image, and to provide a computer-readable program storing the program. It is to provide a simple recording medium, an image classification method, and an image classification device.

[0005]

According to one aspect of the present invention to achieve the above object, an image classification program comprises:
An image acquisition step of acquiring an image to be classified, and a person extraction step of extracting a person from the acquired image,
A search step of searching for an image including each of a plurality of persons from an obtained image by referring to the extracted persons, and associating the specific information of the searched image with each of the plurality of persons. And causing the computer to execute a registration step of registering.

According to the present invention, when an image to be classified is obtained, a person is extracted from the image. With reference to the extracted person, an image including each of a plurality of desired persons is retrieved from the acquired images. Then, the specific information of the searched image is registered in association with each of the plurality of persons. Therefore, for a plurality of persons for which the user wants to classify the images, the images in which each person is photographed are appropriately classified and registered.

[0007] Therefore, it is possible to provide an image classification program capable of appropriately classifying images while reducing work labor.

Preferably, each of the plurality of persons is an extracted person.

According to the present invention, for each of a plurality of persons extracted from the image to be classified, an image of each person is appropriately extracted, and the specific information of the image is registered. This eliminates the need for the user to check the images and classify the images for each person in the images.

Preferably, the image classification program further causes the computer to execute a person obtaining step of obtaining a predetermined person in advance, and the plurality of persons are each the obtained predetermined person.

According to the present invention, only a plurality of predetermined persons for whom the user desires to classify images are acquired in advance. Then, when a person is extracted from the image to be classified, if the person is a previously acquired person, the image specific information is registered in association with the person. Since image classification processing is performed only for a plurality of persons acquired in advance,
Even if an unnecessary person is extracted from the image, the classification process for that person is not performed.

Therefore, the processing time can be reduced by omitting unnecessary processing. Further, it is not necessary for the user to check whether or not the person included in the image to be classified is a person to be classified and counted while looking at the image.

[0013] Preferably, the image classification program further causes the computer to execute an output step of outputting the corresponding image to each of the plurality of persons based on the specific information of the registered image.

According to the present invention, for each of a plurality of registered persons, an image corresponding to the person, that is, an image including the person is output. For this reason,
Unlike the output based on the classification and aggregation manually performed by the user, it is possible to appropriately and accurately output an image for each person.

Preferably, the image classification program further causes the computer to execute a selecting step of selecting a specific person from a plurality of persons, and the outputting step outputs an image corresponding to the selected person. Features.

According to the present invention, an image corresponding to a specific person selected from a plurality of registered persons is output. Therefore, the intention of the user is reflected, and it is possible to output an image only to a desired person.

Preferably, the output step includes an address acquisition step of acquiring addresses of a plurality of persons, and a distribution step of distributing an image corresponding to the acquired addresses.

According to the present invention, an image corresponding to a plurality of registered persons is delivered to addresses of the plurality of registered persons. For this reason, the corresponding image is appropriately and reliably delivered to each person.

Preferably, the output step includes a print output step of printing out a corresponding image by an image output device such as a printer.

According to the present invention, since the corresponding image is printed out, the target person can easily acquire the image.

Preferably, the outputting step includes a storing step of storing the corresponding image in a memory.

According to the present invention, the corresponding image is stored in the memory.
It becomes possible to perform file management of the corresponding image appropriately.

According to still another aspect of the present invention, a computer-readable recording medium records any one of the above-described image classification programs.

Therefore, it is possible to provide a computer-readable recording medium which records an image classification program capable of appropriately classifying images while reducing the work labor.

According to still another aspect of the present invention, an image classification method includes an image obtaining step of obtaining an image to be classified, a person extracting step of extracting a person from the obtained image, and a step of extracting the extracted person. A search step of searching for an image in which each of the plurality of persons is included in the acquired images, and a registration step of registering the specific information of the searched image for each of the plurality of persons in association with each other. including.

According to the present invention, when an image to be classified is obtained, a person is extracted from the image. With reference to the extracted person, an image including each of a plurality of desired persons is retrieved from the acquired images. Then, the specific information of the searched image is registered in association with each of the plurality of persons. Therefore, for a plurality of persons for which the user wants to classify the images, the images in which each person is photographed are appropriately classified and registered.

Therefore, it is possible to provide an image classification method capable of appropriately classifying images while reducing work labor.

According to still another aspect of the present invention, the image classification device includes: an image acquisition unit that acquires an image to be classified; a person extraction unit that extracts a person from the acquired image; Reference means for searching for an image in which each of the plurality of persons is included in the acquired image; and registration means for registering the specific information of the searched image for each of the plurality of persons in association with each other. including.

According to the present invention, it is possible to provide an image classifying apparatus capable of reducing the user's labor and appropriately classifying images.

[0030]

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

The image retrieval method according to the embodiment of the present invention is realized by executing an image classification program on a computer such as a personal computer or a workstation.

FIG. 1 is a diagram showing the appearance of a computer which is an example of the image classification device 100 according to the present embodiment. Referring to FIG. 1, image classification device 100 includes a main body 1.
1, a magnetic tape device 13, and a CD-ROM (Compact
Disc-Read Only Memory (LCD) device 17, display device 12 such as a CRT, keyboard 15, mouse 16, and modem 19. The magnetic tape device 13 has a magnetic tape 14 mounted thereon, and the CD-ROM device 17 has a CD-R
The OM 18 is mounted.

FIG. 2 shows the configuration of this computer in the form of a functional block diagram. Referring to FIG. 1, as is well known, a computer main body 11 includes a CPU (Central Process
ng Unit) 20 and ROM (Read Only Memory) 21
, A RAM (Random Access Memory) 22, and a hard disk drive 23. These are mutually connected by a bus.

The image classification program may be installed in a hard disk in a computer in advance, or may be recorded on a removable recording medium such as a CD-ROM or a magnetic tape. In any case, the image classification program is recorded on a computer-readable recording medium.

When the program is recorded on a removable recording medium, the recorded program is stored in the magnetic tape device 1.
3. The data is read from the recording medium by the CD-ROM device 17 or the like and temporarily stored in the hard disk device 23. Thereafter, the program is loaded from the hard disk device 23 to the RAM 22 in advance, and the CPU 20 controls the execution of the program.

As a computer-readable recording medium, a tape system such as a magnetic tape or a cassette tape, a magnetic disk (such as a flexible disk or a hard disk device) or an optical disk (CD-ROM / MO / MD) is used.
/ DVD, etc., a card system such as an IC card (including a memory card) or an optical card, or a mask ROM, EPROM, EEPROM, flash RO
A medium that fixedly holds the program, such as a semiconductor memory such as M, may be used.

Further, the image classification program may be downloaded from a network via the communication modem 19. When the program is downloaded from the network as described above, the download program is stored in the computer main body 11 in advance, or is previously installed in the main body 11 from another recording medium or the like.

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

Next, referring to FIG.
The case where an image is input / output to / from the computer will be described.

Referring to this figure, control unit 300 corresponds to computer main body 11 of image classification device 100 shown in FIGS. Note that the storage unit 301 may be a memory in the computer main body 11 or an external memory. The storage unit 301 is provided with an image classification table in a predetermined area, and includes an image taken by the digital camera 31, an image read by the scanner 32, an image sent from the server 33 via a network, and the like. Is registered together with the face image. In addition, other PC
Alternatively, an image captured from a recording medium such as a CD-ROM may be registered.

The control unit 300 stores the image data in the storage unit 30
1 or search for registered image data. In addition to classifying and totaling the image data registered for search or the like, it also performs other necessary image processing.

The classified image data is displayed on the display 38 or the TV 39 or printed out to the printer 37 as required. Further, the data may be distributed to another personal computer (PC) 34 or transmitted to the server 35. Further, it may be distributed to the electronic album 36.

FIG. 4 shows the control unit 30 of the image classification device 100.
9 is a flowchart showing the flow of processing in the process No. 0.
As shown in the figure, first, in step S401, an initial menu is displayed. Next, step S40
At 3, the user selects a menu. For example, a menu for any desired processing is selected based on a selection screen on which image data registration processing, image data search processing, and other menus are displayed.

If the image data registration process is selected, the image data is stored in the storage unit 3 in step S405.
01 is performed. Then, in step S407, it is determined whether or not the registered images are to be classified and totalized.
It returns to the process of 01. In the case of classifying and totaling, the process proceeds to the image data classification and totaling process in S413.

If the image data search process is selected, a predetermined image search process based on a keyword or key image for search is performed in step S409.

When the image data classification and aggregation process is selected, first, in step S411, an image to be aggregated is specified. Then, in step S413, classification and aggregation processing of the target image data is performed.

When the classification and tallying is completed, step S415
In, a menu display for the result of classification and aggregation and output is performed. Then, in step S417, the user selects a menu.

When the correction processing of the classification total is selected,
In step S419, a necessary portion is corrected for the result of the classification and aggregation. Then, the process returns to step S417 again.

If the image data distribution process is selected, in step S421, the image data is distributed based on the result of the classification and aggregation. When the image data saving process is selected, in step S423, the image data is saved based on the result of the classification and aggregation. If the image data print output process is selected, in step S425, the image data is printed out to the printer 37 or the like based on the result of the classification and aggregation.

If another menu is selected in step S403, other processing such as image processing is performed in step S427. When the selected process is completed, the process returns to the initial menu screen display in step S401.

Next, classification and totaling processing of image data (step S413), classification and totaling correction processing of image data (step S419), and distribution processing of image data (step S42)
1) and image data saving processing (step S42)
Each process of 3) will be described in detail.

FIG. 5 is a flowchart showing details of the image data classification and aggregation process (step S413) of FIG. As shown in the figure, first, in step S501, an image to be classified and tabulated is read. Then, in step S503, it is determined whether or not a person is included in the read image.

If a person is not shown (step S
(“NO” in 503), in step S515, the image is determined to be a landscape image. And
The file name of the image is registered in the landscape table in the image classification table. When the registration is completed, step S5
Proceed to step 17.

On the other hand, if it is determined in step S503 that a person is captured (“Y” in step S503).
ES "), in step S505, a cutout process is performed on a person appearing in the image. When a plurality of people appear in the image, cutout is performed on all the people.

Next, in step S507, it is determined whether or not the cut-out person is a person already registered in the image classification table. If the person is not a registered person ("NO" in step S507), step S509
In, the image of the person is registered in the person table in the image classification table. Then, step S511
In, the file name of the current image including the person is registered in association with the target person.

On the other hand, if it is determined in step S507 that the target person is a registered person ("YES" in step S507), the process proceeds to step S50.
Step 9 is skipped, and the process proceeds to step S511.

When the file name of the image is registered in the person table in association with the target person, step S
At 513, it is determined whether the targeted person is the last person in the image. If it is not the last person ("NO" in step S513), the process returns to step S507, and the same processing is repeated for the next person in the image (steps S507 to S513).

If the person to be registered is the last person in the image ("YE" in step S513)
S ″), the process proceeds to step S517, and it is determined whether the currently registered image is the last image among the target images for classification and aggregation. ("NO" in step S517), the process returns to step S501, and the next image to be classified and counted is read again, and the same process is repeated (steps S501 to S51).
7).

When the classification is completed for the last image to be classified and counted (“YES” in step S517),
Proceeding to step S519, a predetermined tallying process is performed. Then, the subroutine ends, and the process returns to the main routine of FIG.

FIG. 6 is a diagram showing an example of an image classification table in which images are classified and counted according to the processing shown in FIG. Referring to this figure, the image classification table includes a person table in which an image file name is registered for each person's face image, and a landscape table in which a file name of a landscape image in which no person is included in the image is registered. Is done.

In the person table, the file name of the image including the person is registered in association with the face image of each person. For example, if an image contains the top person,
Images having file names such as “a.dbdb” and “b.dbdb”, and images including the second person from the top are images having file names such as “a.dbdb” and “c.dbdb”. It is.

Then, for each person, the total number of images including the person can be obtained (right end column). For example, there are a total of five images including the person at the top, and a total of seven images including the second person from the top. As described above, in the person table, the total number of images including the person is totaled for each person, so that it is clear how many images need to be output for each person.

Further, by looking vertically at the person table, it is possible to know how many persons are included in the same image file. For example, the image with the file name “a.dbdb” is registered for a total of two person images. For this reason, it can be seen that the image of “a.dbdb” includes two persons. The image with the file name “b.dbdb” is registered for one person image. Therefore, it can be seen that one person is included in this image. Similarly, it can be seen that one person is included in the image with the file name “c.dbdb”.

As described above, since the number of persons included in each image becomes clear, for example, an image is taken every certain time and the number of visitors per certain time is grasped from the image. In this case, the result of classification and aggregation can be used.

On the other hand, in the landscape table, file names of landscape images that do not include a person are sequentially registered. Therefore, how many landscape images exist can be known from the total number in the right end column.

FIG. 7 is a diagram showing an example of the tabulation result and menu display (step S415) screen of FIG. As shown in the figure, the face images of the registered persons are displayed at the top of the screen as a result of the classification and aggregation processing of the image data. Then, the total number of images in each person is displayed. The total number of landscape images is displayed below the number of images of each person.

At the right end of the screen, a menu for selecting an image output process based on the result of classification is displayed. The contents of the processing include storage, distribution, and printing of image data, and correction of the result of classification and aggregation. The user can make a desired menu selection while referring to the result of the classification and aggregation.

Next, referring to FIGS. 8 and 9, a description will be given of a case in which the classification and counting result is corrected. FIG.
FIG. 5 is a flowchart showing details of the classification tally correction process (step S419) of FIG. FIG. 9 is similar to FIG.
FIG. 6 is a diagram for explaining each process in the flowchart of FIG.

Referring to FIG. 8, in the classification and tallying correction process, first, in step S801, the same person is superimposed by drag and drop. That is, in the case where the counting is performed assuming that the same person is different from the same person looking at the screen on which the counting result is displayed, FIG.
As shown in (a), one face image of the same person is superimposed on the other face image by drag and drop.

Then, in step S 803, the classification and counting result is corrected. That is, the number of images of a person is added, and the number of landscape images is left as it was in the original. Specifically, as shown in FIG. 9B, the number of images of the left-end male image is added to each other, and the number is corrected to 7 by 5 + 2. Then, the number of landscape images is four as it is.

When the correction is completed, in step S805, the corrected classification and totalization result is displayed.
Then, the process returns to the menu selection processing of step S417 again.

FIG. 10 is a flowchart showing details of the image data distribution process (step S421) of FIG. In the image data distribution process, first, in step S1001, it is determined whether or not distribution of destinations has been established for all face images targeted for classification and aggregation. If all face images have been dealt with (“YES” in step S1001), step S1
At 003, a mail address for each face image is displayed at a predetermined position. Then, Step S1013
Processing proceeds to

On the other hand, if there is no correspondence between the face image targeted for classification and aggregation and the distribution destination (“NO” in step S1001), in step S1005, the face image that is not corresponded is determined. Is displayed at a predetermined position indicating that the mail address has not been registered.

FIG. 11 shows an example in which a message indicating that a mail address has not been registered is displayed. As shown in this figure, for example, an item called a mail address is provided at the bottom of the screen, and a mail address to which the person is distributed is displayed for each person image. In this example, the mail address of the male on the left is registered because it is registered, and the mail address of the female on the right is not registered because it is not registered.

When the mail address is registered on the Web site, the registered site may be displayed.

Returning to FIG. 10, when a message indicating that the mail address has not been registered is displayed, the user inputs the mail address in step S1007. For example, an address registered in the mail software can be selected by a pull-down menu.

Then, in step S1009, it is determined whether or not the face image is to be stored in association with the mail address of the distribution destination. For example, whether to save or not to save may be selected by the user, and the result may be selected.

If it is determined to save (step S
In step S1011, the mail address is stored in a predetermined area of the storage unit 301 in association with the face image in step S1011.

When all the target images are associated with the distribution destinations in this way, next, in step S1013, whether to distribute the images collectively or individually for each person is selected. FIG. 12 shows an example of a selection menu screen (step S1013) for selecting between batch distribution and individual distribution for each person. Referring to FIG. 12, when batch distribution is desired, a batch distribution button on the right end is clicked. Then, when the individual wants the distribution, the mail address of the person to whom the distribution is desired is clicked.

If batch distribution is selected, batch distribution processing is performed in step S1015. If individual distribution is selected, individual distribution processing is performed in step S1017. Then, the subroutine ends and the process returns to the main routine.

Subsequently, batch distribution processing (step S101)
5) will be described with reference to FIGS.
FIG. 13 shows the batch distribution process (step S101) of FIG.
It is the flowchart which showed the detail of 5). FIG.
FIG. 4 is a diagram for explaining each process in FIG.

Referring to FIG. 13, first, at step S13
At 01, an initial screen for batch distribution is displayed. Specifically, as shown in FIG. 14, a mail address which is a destination of each person and an image file name to be transmitted are displayed in correspondence with each other.

In FIG. 14, only one image file name is displayed for each destination. However, by clicking the scroll button at the right end of the image file name column, a plurality of A list of file names can be displayed.

When the initial screen is displayed, step S13
At 03, the user inputs a sentence as necessary. This is input when there is a message or the like to be transmitted with the image. For example, as shown in FIG. 14, the input sentence is displayed at the bottom of the screen.
The document input here is distributed to all distribution destinations together with the image data.

When the input of necessary text is completed and the transmission button is clicked (“YE in step S1305”)
S "), the corresponding image data is transmitted to all the displayed destinations. At this time, if a text is input, the text is also transmitted to all the destinations. End the subroutine and return to the main routine.

Note that the own distribution process in step S1017 of FIG. 10 also has the same processing flow as the flowchart shown in FIG. However, on the display screen as shown in FIG. 14, since the transmission is performed by the user, the destination address of only one person who desires the distribution is displayed.

FIG. 15 is a flowchart showing the details of the image data storing process (step S423) of FIG. In the image data saving process, first, in step S150
In 1, it is determined whether or not there is a correspondence between the target person's face image and the storage destination. If the answer is YES (“YES” in step S1501), the process proceeds to step S15.
At 03, an image corresponding to a predetermined storage destination corresponding to that is registered.

On the other hand, if there is no correspondence between the face image and the storage destination ("NO" in step S1501), it is determined in step S1505 whether a new folder for the face image is set. Whether or not to set a new folder is selected by the user.

FIG. 16 is a diagram showing an example of a screen displayed at the time of this new folder setting selection process. Here, since there is no folder for the upper left face image, it is asked whether a new folder is prepared. The user
If you want to set a new folder, enter the folder name for the corresponding image and click "YES" on the left.
Click the switch of. Then, in step S1507 in FIG. 15, a new folder for the corresponding face image is set.

If the user does not want to set a new folder, the user clicks the “NO” switch shown in FIG. Then, in step S1509 in FIG. 15, the target image is discarded. Then, control goes to a step S1511.

If a new folder is set in step S1507, the process advances to step S1503 to register an image in a predetermined storage destination, that is, a newly created folder. Then, in step S1511, it is determined whether the face image to be saved is the last face image.

If it is not the last face image (step S1)
"NO" in 511), the process returns to the step S1501, and the same process is repeated (steps S1501 to S1511). Then, when the saving or discarding process for all the corresponding images is completed (“YES” in step S1511), the saving result is displayed in step S1513.

FIG. 17 is a diagram showing an example of a case where the storage result is displayed on a screen. As shown in the figure, each face image is displayed in a reduced size, and the folder name set for the face image is displayed. Then, the number of images stored for each person is displayed on the right end.

When the display of the storage result is completed, the subroutine ends and the process returns to the main routine.

As described above, according to the image classification method in the embodiment of the present invention, the person included in each image is automatically extracted, and the file name of the image data including the person corresponds to the person. In addition, it is recorded in the person table of the image classification table. Further, image data of a landscape that does not include a person is separately recorded in a landscape table of an image classification table.

Therefore, the user does not need to confirm the persons included in each image and perform the work of counting the required number of copies. Therefore, work labor is reduced. Further, since output processing such as printer output is performed based on the image classification table, it is possible to prevent occurrence of mistakes due to mistakes.

In the embodiment shown this time,
As shown in the flowchart of FIG. 5 and the like, a person is cut out from the image to be classified, and all the cut out images of the person are registered in the image classification table. However, a person who does not need to perform classification and aggregation may be included in the image. In particular, the number of people included in the image is large,
In the case where a large number of unnecessary persons appear, for example, according to the processing shown in FIG. Therefore, the processing time required for the classification and aggregation also becomes longer.

For this reason, a necessary person to be classified may be registered in the table first, and the image may be classified only for that person.

FIG. 18 is a flow chart showing the flow of image data classification and aggregation processing in the case of performing image classification and aggregation only for persons registered in the image classification table. Referring to this drawing, here, unlike the flowchart shown in FIG. 5, the process of registering a person in the person table (step S509) is omitted. Other processes are the same as those in the flowchart shown in FIG.

That is, when all of the persons are cut out from the image including the persons (step S505), it is determined whether or not the persons are persons registered in the person table (step S507). If the person is a registered person, the image file name is registered for that person (step S511). If you are not a registered person,
Step S511 is skipped, and no registration work is performed. That is, it is determined that the person is unnecessary and is not subjected to classification and aggregation.

As described above, since the image file name is registered only for the person registered in the person table in advance, it is possible to avoid a situation where it takes a long time for unnecessary processing. In addition, it is possible to prevent inconvenience in subsequent processing such as output of an unnecessary person.

In FIG. 18, whether or not the person is a person to be classified and tabulated is determined based on whether or not the person is registered in the person table in advance. But,
The present invention is not limited to such a case. For example, a person to be classified and aggregated may be recorded in a predetermined area different from the person table, or a user who is a target for each classification and aggregation process may be recorded. It may be specified.

In FIG. 18, when it is determined that all the persons cut out from the image are not the persons registered in the person table, the image is registered not only in the person table but also in the landscape table. Absent. However, in such a case, the information may be registered in the landscape table.

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 an image classification device 1 according to an embodiment of the present invention.
FIG. 10 is a diagram illustrating an appearance of a computer as an example of 00.

FIG. 2 is a functional block diagram showing a configuration of the computer shown in FIG.

FIG. 3 is a diagram illustrating a case where an image is input and output to and from the image classification device 100.

FIG. 4 is a flowchart showing a processing flow in a control unit 300 of the image classification device 100.

FIG. 5 shows the image data classification and aggregation process (step S
413) is a flowchart illustrating details of the process.

6 is a diagram illustrating an example of an image classification table in which images are classified and counted according to the processing illustrated in FIG. 5;

FIG. 7 is a diagram showing an example of a tally result and menu display (step S415) screen of FIG. 4;

FIG. 8 is a flowchart showing a process for correcting the classification and aggregation shown in FIG.
It is a flowchart which showed the detail of 9).

FIG. 9 is a diagram for explaining each process in the flowchart of FIG. 8;

FIG. 10 shows the image data distribution process of FIG. 4 (step S4).
It is a flowchart which showed the detail of 21).

FIG. 11 is a diagram illustrating an example in which a message indicating that a mail address is not registered is displayed.

FIG. 12 is a selection menu screen (step S101) for selecting whether to perform batch distribution or individual distribution for each person.
It is the figure which showed an example of 3).

FIG. 13 shows a batch distribution process of FIG. 10 (step S101).
It is the flowchart which showed the detail of 5).

FIG. 14 is a diagram for explaining each process in the flowchart of FIG. 10;

FIG. 15 shows the image data saving process of FIG. 4 (step S4);
It is a flowchart which showed the detail of 23).

FIG. 16 is a diagram showing an example of a screen displayed at the time of a new folder setting selection process.

FIG. 17 is a diagram illustrating an example of a case where a storage result is displayed on a screen.

FIG. 18 is a flowchart illustrating a flow of image data classification and aggregation processing in a case where image classification and aggregation is performed only for persons registered in the image classification table.

[Explanation of symbols]

11 computer main body, 12 display device, 13 magnetic tape device, 14 magnetic tape, 17 CD-ROM device, 18 CD-ROM, 20 CPU, 21 RO
M, 22 RAM, 23 hard disk drive, 31
Digital camera, 32 scanner, 34 PC (P
C), 33, 35 servers, 37 printers, 100
Image search device, 300 control unit, 301 storage unit.

 ──────────────────────────────────────────────────続 き Continued on the front page F term (reference) 5B050 BA12 CA06 CA07 CA08 EA03 EA18 GA08 5B075 ND08 ND23 NK10 NR12 5L096 EA35 HA07 KA03 KA09 KA11

Claims (11)

[Claims] An image acquisition step of acquiring an image to be classified; a person extraction step of extracting a person from the acquired image; and A search step of searching a plurality of persons for an image that includes each of the plurality of persons, and a registration step of registering the plurality of persons with the specific information of the searched image in association with each of the plurality of persons. Image classification program. 2. The image classification program according to claim 1, wherein each of the plurality of persons is the extracted person. 3. The computer according to claim 1, further comprising: causing a computer to execute a person acquiring step of acquiring a predetermined person in advance, wherein each of the plurality of persons is the acquired predetermined person. Image classification program. 4. The method according to claim 1, further comprising the step of causing a computer to execute an output step of outputting a corresponding image to each of the plurality of persons based on the specific information of the registered image. Image classification program described in Crab. 5. The method according to claim 1, further comprising: causing a computer to execute a selecting step of selecting a specific person from the plurality of persons, wherein the outputting step outputs an image corresponding to the selected person. The image classification program according to claim 4. 6. The method according to claim 4, wherein the output step includes an address acquisition step of acquiring addresses of the plurality of persons, and a distribution step of distributing an image corresponding to the acquired addresses. Image classification program as described. 7. The image classification program according to claim 4, wherein the output step includes a print output step of printing out a corresponding image by an image output device such as a printer. 8. The method according to claim 4, wherein the outputting step includes a storing step of storing a corresponding image in a memory.
Image classification program described in. 9. A computer-readable recording medium in which the image classification program according to claim 1 is recorded. 10. An image acquiring step of acquiring an image to be classified, a person extracting step of extracting a person from the acquired image, and a step of referring to the extracted person in the acquired image. An image classification method, comprising: a search step of searching for an image including each of a plurality of persons from a plurality of persons; and a registration step of registering the plurality of persons in association with specific information of the searched image. 11. An image acquisition unit for acquiring an image to be classified, a person extraction unit for extracting a person from the acquired image, and An image classification device, comprising: a search unit configured to search for an image including each of a plurality of persons from a plurality of persons; and a registration unit configured to register the plurality of persons in association with specific information of the searched image.