JP5230959B2 - Automatic document creation device and program - Google Patents

Description

The present invention relates to automatic document creation instrumentation 置及 beauty program to create a document associated with the image automatically.

  In recent years, so-called blogs (blog: abbreviation of weblog), which are easier to create than homepages, have become popular. There are also various ideas that make this blog easier to use.

  For example, many blogs are displayed in order from the newest uploaded content, and the appearance is similar to a diary. However, a system has been proposed that allows users to easily create such a blog as if they had a daily diary. Various services using these systems are also available.

  In addition, digital images are effectively used in blogs, and there are many articles such as photo collections in which only images are posted. In general, comments are often added in addition to images. However, it is troublesome for the user to take a picture using a digital camera and input a comment using a personal computer (hereinafter referred to as a PC). What is needed is a way to create a document.

As a proposal for a system that can easily create such a document with an image, for example, in Patent Document 1, a feature of an input image is extracted, and the feature is a feature corresponding to an adjective registered in a database in advance. By comparing, creating a document using the result, and outputting it, the evaluation of the input image can be expressed as a sensuous sentence using adjectives.
JP 2001-195579 A

  Here, since the method of Patent Document 1 creates a document based only on the features of the input image and the adjectives corresponding to the feature, its expressive power is limited, and a document that the user can always satisfy is created. It is not always possible.

The present invention has been made in view of the above circumstances, and an object thereof is to provide an automatic document creation instrumentation 置及 beauty program capable of creating an image with text various expressions easily.

To achieve the above object, the first automatic document creating apparatus aspect of the present invention, in the automatic document creating apparatus for creating automatically the relevant documents in the captured image, records the image data representing the captured image A reference information recording unit that records information including information about past image data generated at least at a time other than the time of shooting the image, information about the past image shooting time and the time of shooting the shot image, and the reference information Of the information recorded in the recording unit, the image part to which the user using the automatic document creation device pays attention is referred to according to the modifier of the corresponding sentence, and the document related to the image is automatically created. to a document automatic creation unit, the document automatic creation unit during shooting image data, among the information the reference recording unit is held, high photographing time and and similarity time period are the same at the time of photographing the photographic Compared to previous image data including, wherein the user has to automatically create a document to determine the image portion to pay attention.

According to the present invention, it is possible to provide a document automatic creation instrumentation 置及 beauty program capable of creating an image with text various expressions easily.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.
FIG. 1 is a diagram showing a configuration of an automatic document creation system including an automatic document creation apparatus according to an embodiment of the present invention. The automatic document creation system shown in FIG. 1 includes a digital camera 100, a server 200, and PCs 300 and 400. For example, the digital camera 100 is connected to the PC 300 using a USB or the like so that data communication is possible. The server 200 and the PCs 300 and 400 are connected to each other via a network 500 so that data communication is possible.

  FIG. 2 is a diagram illustrating a configuration of the digital camera 100 of FIG. As shown in FIG. 2, the digital camera 100 includes a control unit 101, an operation unit 102, an imaging unit 103, a focus adjustment unit 104, a clock unit 105, a position measurement unit 106, a recording unit 107, and a communication Part 108.

  The control unit 101 receives an operation input from the operation unit 102 and performs operation control of each unit illustrated in FIG. For example, when a shooting operation is performed, image processing (compression or the like) is performed on image data indicating an image obtained from the imaging unit 103 by shooting, and then the shooting date and time or shooting is performed on the image data subjected to the image processing. A series of processing is performed in which shooting information such as position is added and recorded in the recording unit 107.

  The operation unit 102 includes various operation units such as an operation unit for starting a shooting operation in the digital camera 100 and an operation unit for setting a shooting mode at the time of shooting. When any operation unit of the operation unit 102 is operated by the user, the control unit 101 controls various sequences according to the operation.

  The imaging unit 103 includes a photographic lens, an imaging element, an analog / digital converter (ADC), and the like. Then, an image of a subject (not shown) is formed on the light receiving surface of the image sensor by the photographing lens, and the image of the subject imaged on the light receiving surface is converted into an analog image signal by the image sensor, and obtained by the image sensor. The image signal is converted into a digital image signal (image data by the ADC and output to the control unit 101.

  The focus adjustment unit 104 adjusts the position of the photographic lens to focus the photographic lens. As a focusing method, for example, the contrast of the subject is obtained from image data obtained in the imaging unit 104 while sequentially changing the position of the photographing lens, and the position where the contrast is maximum is set as the focal position of the photographing lens. Well-known methods such as mountain climbing can be used. Here, the subject distance can also be measured from the position of the photographing lens when the focus is achieved. The subject distance measured by the focus adjustment unit 104 can also be added to the image data as shooting information.

  The clock unit 105 measures the date and time. The position measurement unit 106 measures the position of the digital camera 100 by positioning using, for example, GPS. When shooting is performed, shooting date / time information measured by the clock unit 105 and shooting position information measured by the position measurement unit 106 are added to the image data as part of the shooting information. Further, when the subject distance is measured, subject distance information is also added as part of the shooting information. In addition, an exposure condition at the time of shooting is added as shooting information.

  The recording unit 107 performs image processing in the control unit 101 during shooting and records image data to which various types of shooting information are added. The communication unit 108 transmits various data such as image data recorded in the recording unit 107 to the PC 300. The digital camera 100 may have a function of connecting to the network 600 so that data such as image data recorded in the recording unit 107 can be transmitted to the server 200 without using the PC 300.

A server 200 having a function as an automatic document creation apparatus includes a control unit 201, a communication unit 202, and a recording unit 203.
The control unit 201 controls the operation of each unit of the server 200 according to a predetermined program. When image data indicating an image is transmitted from the digital camera 100, a document relating to the content of the transmitted image data is automatically created.

  The communication unit 202 receives the image data transmitted from the PC 300 and transmits an image-added document automatically created in the server 200 to the PC 400.

  The recording unit 203 includes an image recording unit 203a, a reference information recording unit 203b, and a document recording unit 203c. The image recording unit 203a records the image data transmitted from the digital camera 100 in association with shooting information such as shooting date / time information, shooting position information, and subject distance information at the time of shooting. The reference information recording unit 203b records various types of reference information used in the automatic text data creation process by the control unit 201. As this reference information, for example, various image data such as plants, animals, people, landscapes, dishes, etc. for identifying what the subject is reflected in the image data recorded in the image recording unit 203a, and the shooting position Information acquired other than at the time of taking an image such as map data for specifying the location of the digital camera 100 from the information is included. In FIG. 1, three recording units are provided in the recording unit 203, but these may be configured as separate recording units or as a single recording unit.

  The PCs 300 and 400 are general personal computers in which software for browsing a web page is installed and an operation unit such as a mouse and a keyboard for performing various operations on the web page and a display unit such as a liquid crystal display. .

  Hereinafter, the operation of the document creation system shown in FIG. 1 will be described. Image data obtained by the digital camera 100 is recorded in the image recording unit 203a of the server 200 in association with shooting information such as shooting date and time and shooting position. The control unit 201 of the server 200 analyzes what the user is currently interested in from the changes in the image data recorded every day, converts it into text, and sends the created text via the PC 300. Record it in association with the incoming image. If there is an access from the PC 400, the image-added document 602 is displayed on the PC 400. The image-added document 602 includes an image 600 transmitted from the PC 300 and a sentence 601 created from the image 600.

  For example, when the sentence 601 is created from the image data 600 shown in FIG. 1, the fact that the subject in the image is “ginkgo” is compared with the plant image data recorded in the reference information recording unit 203b. Can be determined. In addition, when a plurality of ginkgo tree images photographed with the same composition are transmitted to the server 200, the newly transmitted image is compared with an image recorded in the past. Thus, it is possible to discriminate these images as images of the same ginkgo tree, discriminate changes in the subject reflected in the images, and describe them as sentences. For example, by detecting that the leaf color of the same ginkgo tree has changed to “yellow”, it is possible to add a sentence “the color of the leaf has become yellow” to the sentence “Ginkgo”. Furthermore, when image data of the same ginkgo tree is periodically transmitted to the server 200, a modifier such as “ordinary” can be added.

  Further, from the image transmitted to the server 200, the shooting date and time and the shooting theme (subject) at that time are managed in a table format as shown in FIG. 3, for example, and a sentence is created based on this information. You may do it. By performing such management in the server 200, it is possible to determine what kind of photography the user has (e.g., what time period of photography, what kind of images are many), etc. It is. And because of this management, it becomes easier to document such as “always taking pictures”, “taken before”, or “rarely taken at night”.

  For example, FIG. 3 shows a recording history of a subject in units of one day. Among them, the same thing as the scenery 1 which is the latest photographing result is photographed six days ago, and for example, a sentence such as “photographed six days later” can be added. Furthermore, if an image of the landscape 1 is periodically taken in a period shorter than 6 days and there is an interval of 6 days only this time, a sentence such as “taken for the first time in 6 days” can be added. By such a device, the monotonousness of the created sentence can be prevented.

  In creating the table as shown in FIG. 3, whether the subject of various themes photographed by the photographer corresponds to a landscape, a person, a pet, a dish, or the like depends on the subject itself in the image data. In addition to the discrimination, for example, the subject distance information at the time of shooting (short distance for landscapes, short distance for pets and dishes, etc.) and shooting mode settings (portrait mode for people, etc.) can be used.

Hereinafter, the operation of the automatic document creation system shown in FIG. 1 will be described in more detail.
FIG. 4 is a flowchart showing processing of the digital camera 100 in the automatic document creation system shown in FIG. In FIG. 4, the control unit 101 of the digital camera 100 determines whether or not a user has performed an image capturing operation (step S11).

  When a shooting operation is performed in the determination in step S11, the control unit 101 controls each unit to execute a shooting operation (step S12). After the end of the shooting operation, the control unit 101 determines whether or not the position information of the digital camera 100 at the time of shooting is acquired by the position measurement unit 106 (step S13). If the position information at the time of shooting has been acquired in the determination in step S13, the control unit 101 captures shooting position information, shooting time information, subject distance information, shooting mode setting information, and the like in the image data after image processing. Information is added and recorded in the recording unit 107 (step S14). On the other hand, when the position information at the time of shooting is not acquired, the control unit 101 adds shooting information other than the shooting position information to the image data after image processing and records the image data in the recording unit 107 (step S15). ).

  If it is determined in step S11 that no photographing operation has been performed, the control unit 101 determines whether or not a user has performed an image reproduction operation (step S16). If it is determined in step S16 that an image reproduction operation has been performed, the control unit 101 performs a reproduction operation for reproducing the image selected by the user on a display unit (not shown) (step S17).

  If it is determined in step S16 that no reproduction operation has been performed, the control unit 101 determines whether or not a user has performed an image data transmission operation (step S18). In the determination of step S18, when an image data transmission operation is performed, the control unit 101 transmits the image data selected by the user together with the shooting information to the PC 300 or the server 200, and among the user action history information, What has not yet been transmitted to the PC 300 or the server 200 is transmitted (step S19).

  Here, the user's action history information is information indicating an action other than when the user is photographing. More specifically, it is information that is detected and recorded in the recording unit 107 by sequentially detecting when and where the user is. By recording such information in the recording unit 107 and sending it to the server 200, it becomes possible to create more various sentences in the server 200. By sending the user's action history information to the server 200, for example, the server 200 can identify where the user has moved from where the image was taken to where it was taken. It is possible to create a sentence. However, if all the actions of the user other than at the time of shooting are transmitted, the amount of data becomes large. Therefore, when the user periodically transmits image data (upload to the server 200), Assuming that action history information is also uploaded, only unsent data is transmitted. For example, if you send an image on a business trip to Osaka the previous day, and if you want to send another image for another day, you need to send data indicating that you went to Osaka the previous day when sending the image for another day. There is no. However, for the text created in the server 200, referring to the action history information of the previous day, for example, a text such as “I went to Osaka yesterday but today is the usual ginkgo” may be created. good.

  Even after image data is transmitted or when image data is not transmitted, the control unit 101 acquires position information of the digital camera 100 at the time of image transmission by the position measurement unit 106, and Current time information is acquired by the clock unit, and the acquired position information and time information are recorded in the recording unit 107 as user action history information (step S20). By recording the action history information in this manner, the action history information of the user can be transmitted together with the image data when the image is output in step S19, and a table as shown in FIG. Is possible.

  FIG. 5 is a flowchart showing processing of the server 200 in the automatic document creation system shown in FIG.

  First, the control unit 201 of the server 200 determines whether image data has been received directly from the digital camera 100 or from the PC 300 (step S21). When the image data is received in the determination in step S21, the control unit 201 records the received image data in the image recording unit 203a of the recording unit 203 together with the shooting information, and the user action history received together with the image data. The information is recorded in the reference information recording unit 203b (step S22).

  Next, the control unit 201 determines whether or not shooting position information is added to the image data (step S23). When the shooting position information is added to the image data in the determination of step S23, the control unit 201 writes a sentence from the transmitted image data and the shooting date / time information and shooting position information associated with the image data. Is created (step S24). On the other hand, if the shooting position information is not added to the image data in the determination of step S23, the control unit 201 creates a sentence from the image data and the shooting date / time information without considering the shooting position information (step S25). ). The sentence creation processing in steps S24 and S25 will be described later.

  Next, the control unit 201 compares the sentence data created in step S24 or step S25 with the sentence data created in the past and recorded in the document recording unit 203c, and the same sentence data continues for a predetermined number of times. It is determined whether it has been created (step S26). If it is determined in step S26 that the same sentence data is continuously created a predetermined number of times or more, the control unit 201 records the sentence created in step S24 or step S25 in the reference information recording unit 203b of the recording unit 203. Arrangement is performed using the data of the collected sentence examples (step S27).

  For example, even if you write a sentence about the same "blue flower", you might just use the word "blue flower", "I saw a blue flower", "I had a blue flower", Various variations such as “blue flowers were beautiful”. In order to make a variation even for such a sentence, a large number of sentence plans are recorded in the reference information recording unit 203b, and a new sentence is created by appropriately selecting them. For example, when the subject in the image is a “blue flower”, a sentence is first created using only the “blue flower”. Then, when the sentence of only “blue flowers” is created continuously a predetermined number of times or more, a sentence “I saw a blue flower” is created next. Similarly, if the same sentence continues multiple times, another sentence is created. As a result, even for sentences on the same subject, only the same sentence is not created, and the user is not bored.

  After step S26 or step S27, the control unit 201 records the created text data in the document recording unit 203c in association with the image data recorded in the image recording unit 203a (step S28). As a result, an image-added document is created. Thereafter, the processing of FIG.

  Further, the server 200 can record not only automatically created sentences but also sentences created by the user himself / herself. For this reason, when image data is not received in step S21, the control unit 201 determines whether or not an article such as a diary (here, an article with an image in particular here) has been received (step S29). In step S29, when an article is received, the control unit 201 causes the document recording unit 203c and the image recording unit 203a to record the text data and image data of the received article. Then, the process of FIG. 5 ends. The sentence created by the user himself may include more detailed information than the sentence automatically created in the server 200. For example, even with the shooting position information alone, you can create a sentence such as “Ginkgo biloba where”, but you cannot create a sentence such as “Nostalgic ginkgo” or “It is a memorable ginkgo”. Such expressions may be quoted later when similar image data is sent. For example, when a similar image is sent using a similar image search function, it is possible to create a sentence such as “I took a picture of a nostalgic ginkgo”.

  If no article has been received in the determination in step S29, the control unit 201 determines whether an instruction to reproduce the image has been given by the user (step S30). If it is determined in step S30 that the user gives an instruction to reproduce an image, the image selected by the user and the text associated with the image are displayed on the display of the PC 400 (step S31). Thereafter, the process of FIG.

  FIG. 6 is a flowchart showing details of the process in step S24 of FIG. First, the control unit 201 reads user action history information from the reference information recording unit 203b (step S41). From such a record, the positioning of the image (whether the image was obtained on the way to where it was taken, whether it was obtained by shooting where it always goes, or obtained at the place where I came from time to time) Can be determined). In order to make this determination, the control unit 201 detects the shooting date / time information A of the transmitted image data (step S42). Further, the control unit 201 detects shooting position information of the transmitted image data (step S43). Then, the control unit 201 compares the shooting position information with the action history information read in step S41, and determines whether or not the transmitted image data is obtained by shooting after a long distance movement. Is determined (step S44). This can be determined based on whether or not the difference between the shooting position information of the transmitted image and the position information (obtained from the action history information) at the time before the shooting date and time of this image is greater than a predetermined distance.

  If it is determined in step S44 that the image is obtained by shooting after moving a long distance, it is determined that shooting has been performed at a special place. Therefore, the control unit 201 collates the image capturing position with the map data recorded in the reference information recording unit 203b, and determines the place name B corresponding to the image capturing position (step S45). Next, the control unit 201 calculates a travel time C from the difference between the shooting time information and the travel start time (step S46), and a sentence that describes the place name B in a form that incorporates the travel time C (see FIG. 6). Is created (step S47). Thereafter, the process of FIG. 6 is terminated. Here, in the example of step S47 in FIG. 6, the travel time is included in the text, but the travel distance itself may be included.

  In the determination in step S44, if the moving distance is small, the shooting is performed in the user's sphere of life. Therefore, the place name is not important. Rather, the subject in the image and the shooting time are more important. judge. In this case, the control unit 201 determines the subject D in the image (step S48). This determination can be performed, for example, by collating the subject in the image with the subject type image recorded in the reference information recording unit 203b.

  After determining the subject D, the control unit 201 determines whether or not image data shot in the same time zone as the transmitted image data is recorded in the image recording unit 203a (step S49). When it is determined in step S49 that image data shot in the same time zone as the transmitted image data is recorded in the image recording unit 203a, the control unit 201 transmits the transmitted image data and the transmitted image data. Comparison is made between the image data thus obtained and image data taken in the same time period, and image data having similar image features such as the shape and composition of the subject is searched (step S50). The image comparison in step S50 can be performed by, for example, extracting contour components between images to be compared and matching the extracted contour components. In matching, it is desirable to allow a slight difference in composition by providing a certain allowable range for the identity of the shape of the subject in the images to be compared.

  After searching for similar image data in step S50, the control unit 201 determines whether there is image data of the same theme as the transmitted image data (that is, a subject having a high degree of similarity such as shape and composition) (step S50). Step S51). If it is determined in step S51 that there is image data of the same theme, the control unit 201 creates a sentence to be compared with the image of the previous shooting date E (step S52). By creating such a sentence, it is possible to present the user up to a date that the user has forgotten and to promote comparison. Note that, instead of a sentence that prompts comparison, a change in color or the like may be detected and converted into a sentence.

  If there is no image of the same theme in the determination in step S51, the control unit 201 detects the color F of the subject in the transmitted image data (step S53). Thereafter, the control unit 201 determines whether or not the subject color is vivid, that is, whether the color saturation is high (step S54). If it is determined in step S54 that the color feature of the subject has been determined, the control unit 201 creates a text indicating that the color is vivid as the subject feature (step S55). On the other hand, if it is determined in step S55 that there is no feature in the color, the control unit 201 creates only the photographed subject and the photographing date and time as text (step S56).

  FIG. 7 is a flowchart showing details of the process in step S25 of FIG. First, the control unit 201 detects the shooting date / time information G of the transmitted image data (step S61). Next, the control unit 201 determines the subject H in the image (step S62). After determining the subject H, the control unit 201 searches the image recording unit 203a for image data having similar image characteristics such as the transmitted image data and the shape and composition of the subject (step S63).

  After searching for similar image data in step S63, the control unit 201 determines whether there is image data with a high degree of similarity such as the shape and composition of the subject (step S64). If it is determined in step S64 that there is no image data with high similarity, the control unit 201 creates only the photographed subject and the shooting date and time as text (step S71).

  On the other hand, if it is determined in step S64 that there is image data with a high degree of similarity, the control unit 201 displays the shooting date / time information I of the image data recently acquired from the image data with a high degree of similarity. Detection is performed with reference to the table 3 (step S65). Next, the control unit 201 calculates a date / time difference J between the shooting date / time information G and the shooting date / time information I (step S66).

  Next, the control unit 201 determines whether there is an image difference such as a color difference between the image data transmitted this time and the previous image data having a high degree of similarity (step S67). This is performed, for example, by comparing pixel values of both image data. If it is determined in step S67 that there is an image difference, the control unit 201 determines whether the image difference is a color difference (step S68). If it is determined in step S68 that the image difference is a color difference, the control unit 201 detects the color K of the image data transmitted this time (step S69). And the control part 201 produces the text which shows the color change of the to-be-photographed object H as shown in FIG. 7 (step S70).

  On the other hand, if there is no image difference in the determination in step S67, or if the image difference is not a color difference in the determination in step S68, the control unit 201 covers the eyes of the viewer as shown in FIG. A sentence is created (step S72).

  As described above, according to the present embodiment, a user can create a sentence about a supplementary description of an image simply by uploading the image. As a result, even if it is troublesome to write a sentence, it is possible to create an article with an image like a person just by uploading an image, and make it an article easy for a reader to read.

[Modification]
Here, a modified example of the above-described embodiment will be described. In the embodiment described above, the shooting position, shooting date and time, features, and the like of an image are detected and combined to create a sentence. However, it is not necessary for the server 200 to create all sentences. That is, at first, the tendency of a sentence created by the user may be learned in the server 200, and the system may be modified to create a sentence based on the learning result.

  FIG. 8 is a flowchart showing the sentence creation process in the modification. In FIG. 8, the control unit 201 of the server 200 determines whether or not an article creation mode has been selected by the user (step S101). When the article creation mode is selected in the determination in step S101, the control unit 201 determines whether or not the user has learned a tendency of an image that can be easily selected when creating an article (step S102). .

  If it is determined in step S102 that the tendency of an image that can be easily selected by the user has not been learned, the control unit 201 waits for input of text (step S103) and input of an image (step S104) by the user. When a sentence and an image are input by the user, the control unit 201 associates the sentence input in step S103 with the image input in step S104 and causes the document recording unit 203c and the image recording unit 203a to record them in association ( Step S105).

  If it is determined in step S101 that the article creation mode is not set, the control unit 201 determines whether or not a predetermined number of articles have been created (step S106). If it is determined in step S106 that a predetermined number or more articles have not been created, the processing in FIG. 8 is terminated.

  On the other hand, if many articles are created, the determination in step S106 branches to No. In this case, the control unit 201 determines a sentence corresponding to the image in the article created by the user (step S107). This can be performed, for example, by determining a subject in the image based on the reference information recorded in the reference information recording unit 203b and determining a sentence portion corresponding to the determined subject. Thereafter, from the result of step S107, the control unit 201 learns the image selection tendency for the sentence (step S108). For example, if a user is interested in clothes color, he / she learns that an image showing clothes and a sentence about clothes colors are a set.

  This is the state shown in FIG. Of the articles shown in FIG. 9, “insufficient to sleep” and “going out” are not directly related to the image, and are not subject to learning. On the other hand, based on modifiers that are easily attached to images such as “color”, “shape”, “beautiful”, “cute”, and the like, it is determined what image portion the user tends to pay attention to.

  In the determination of step S102, when learning the tendency of an image that can be easily selected by the user, the control unit 201 waits only for an image input by the user (step S110). When an image is input by the user, the control unit 201 searches the image recording unit 203a for an image similar in shape and composition to the image input by the user, and extracts a sentence portion corresponding to the searched image. (Step S111). Then, a new sentence is created by quoting the extracted sentence part (step S112). Thereafter, the newly created text and the image input by the user are associated with each other and recorded in the document recording unit 203c and the image recording unit 203a, respectively.

  Here, if there is a difference in the color or the like of the subject between the image input by the user and the searched similar image during the processing in step S111, that portion needs to be changed. For example, in a sentence previously created by a user, there is a sentence touching the color of clothes such as “light blue clothes” as shown in FIG. 9, and the face of the same person as the image associated with this sentence is shown. When an image is input, the color feature of the clothes is extracted from the image, and a sentence that is arranged to the contents that the user is interested in is created, such as “Today's clothes color is yellow”. . This method can be created by imitating the text created by the person, imitating the style by replacing only the words, or preparing several example sentences and selecting an appropriate one from them. May be. Moreover, since the same sentence will get tired every day, even if the theme is the same as the previous day, you may devise it to change the sentence. It is only necessary to select a different one of several sentence examples.

  With the modification described above, it is possible to create a sentence reflecting the lifestyle and values of each user.

  Although the present invention has been described above based on the embodiments, the present invention is not limited to the above-described embodiments, and various modifications and applications are naturally possible within the scope of the gist of the present invention. For example, in the above-described embodiment, an example in which a sentence is automatically created in the server 200 based on image data, action history information, and the like transmitted from the digital camera 100 has been described. Alternatively, by providing the digital camera 100 with the function of the reference information recording unit 203b, a sentence may be automatically created in the digital camera 100.

  Further, the above-described embodiments include various stages of the invention, and various inventions can be extracted by appropriately combining a plurality of disclosed constituent elements. For example, even if some configuration requirements are deleted from all the configuration requirements shown in the embodiment, the above-described problem can be solved, and this configuration requirement is deleted when the above-described effects can be obtained. The configuration can also be extracted as an invention.

1 is a diagram showing a configuration of an automatic document creation system including an automatic document creation device according to an embodiment of the present invention. It is a figure which shows the structure of the digital camera of FIG. It is a figure which shows an example of the table | surface for managing imaging | photography date and a photography theme. It is a flowchart shown about the process of the digital camera in the automatic document creation system shown in FIG. It is a flowchart shown about the process of the server in the automatic document production system shown in FIG. FIG. 6 is a flowchart illustrating details of a process in step S <b> 24 of FIG. 5. FIG. 6 is a flowchart showing details of the process in step S25 of FIG. 5. FIG. It is the flowchart shown about the text creation process in a modification. It is a figure for demonstrating learning of a selection image tendency.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 100 ... Digital camera 101 ... Control part 102 ... Operation part 103 ... Imaging part 104 ... Focus adjustment part 105 ... Clock part 106 ... Position measurement part 107 ... Recording part 108 ... Communication part 200 ... Server , 201 ... control unit, 202 ... communication unit, 203 ... recording unit, 203a ... image recording unit, 203b ... reference information recording unit, 203c ... document recording unit, 300, 400 ... personal computer (PC), 500 ... network

Claims (4)

In an automatic document creation apparatus that automatically creates a document related to a captured image, an image recording unit that records image data indicating the captured image, at least past image data generated at a time other than when the image is captured, and the image data Of the information recorded in the reference information recording unit, the reference information recording unit that records information including information relating to the past image shooting time and the shooting time of the shot image, the user who uses the automatic document creation device is careful. A document automatic creation unit that automatically creates a document related to the image with reference to the image portion to be paid;
The automatic document creation unit compares the image data at the time of photographing with the past image data including a subject having the same time and the same time zone as the time of photographing among the information held by the reference recording unit. Then, an automatic document creation apparatus characterized in that an image part to which the user pays attention is determined and a document is automatically created.

Information about the time of shooting of the image, automatic document creation apparatus according to claim 1, characterized in that it comprises a position and time information had the photographer at the time of shooting of the image. The document automatic creation unit, based on an image taken at a time other than the time of shooting the image and information on the time of shooting, the image was taken after the photographer moved a long distance The document automatic creation apparatus according to claim 1 , wherein when it is determined, a document relating to a movement time or a movement distance is created.   The automatic document creation unit refers to the information recorded in the reference information recording unit, obtains the correspondence between the characteristics of the artificially created document and the image by learning, and the information obtained by the learning The document automatic creation apparatus according to claim 1, wherein the document is automatically created based on the document.

Images