JP2017152842A - Image processing system, image processing method and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To make it possible to adequately add information intended by a photographer to a photographed image.SOLUTION: Characters in a photographed image are recognized to acquire the character information thereof, and also a photographed position of a photographed image is specified to acquire information about the photographed position (steps A9, A10 in FIG. 5). This acquired character information and information about the photographed position are compared to determine whether they indicate the same object (steps A11, A12). On condition that they indicate the same object, recording is carried out by adding the information about the photographed position to the photographed image (steps A13, A14).SELECTED DRAWING: Figure 5

Description

  The present invention relates to an image processing apparatus, an image processing method, and a program for adding information to a captured image.

  As an image processing apparatus for adding predetermined information to a captured image, for example, a character indicating a place is recognized while analyzing the captured image, and a shooting location obtained based on the recognition result (character information) is recognized. There is known a technique in which the information is added to the photographed image and recorded (see Patent Document 1). In addition, a technique is known in which character information is recognized in continuously photographed images and position information at the time of photographing is added when a significant character string is detected (see Patent Document 2).

JP 2014-67302 A JP 2008-292279 A

  However, in each of the above-described patent document techniques, information obtained based on characters in a photographed image is added, but the photographed image has no relation to the photographing location. Since there is a possibility that various characters with no character are included, adding various information corresponding to all these characters also adds unnecessary information that is not intended by the user (photographer). Will end up.

  An object of the present invention is to appropriately add information intended by a photographer to a photographed image.

In order to solve the above-described problems, the present invention
First acquisition means for acquiring character information obtained by recognizing characters in a captured image;
Second acquisition means for specifying a shooting position of the shot image and acquiring information relating to the shooting position;
A discriminating unit that compares the character information acquired by the first acquiring unit with the information on the photographing position acquired by the second acquiring unit to determine whether or not the same target is indicated;
Of the character information acquired by the first acquisition unit and the information on the shooting position acquired by the second acquisition unit on the condition that the determination unit has determined that the same object is indicated, Information adding means for adding and recording at least one of the information to the captured image;
It is provided with.

  According to the present invention, information intended by a photographer can be appropriately added to a photographed image.

The block diagram which showed the basic component of the digital camera applied as an image processing apparatus. (1), (2) is the figure which illustrated the picked-up image image | photographed including the character. The figure for demonstrating the database 3d for landmarks. The flowchart which showed the operation | movement (characteristic operation | movement of this embodiment) started when the function which adds information to a picked-up image is started by user operation. The flowchart following the operation | movement of FIG. The flowchart which showed the operation | movement (characteristic operation of this embodiment) started execution when it switches to reproduction | regeneration mode. 9 is a flowchart illustrating an operation when information related to a shooting position is added to a captured image during reproduction of the captured image in <Modification 1> of the present embodiment. 10 is a flowchart illustrating an operation when information related to a shooting position is added to a captured image during shooting in <Modification 2> of the present embodiment.

Hereinafter, an embodiment of the present invention will be described with reference to FIGS.
This embodiment exemplifies a case where the present invention is applied to a digital camera as an image processing apparatus, and FIG. 1 is a block diagram showing basic components of the digital camera.
An image processing device (digital camera) captures information intended by a photographer in addition to an imaging function that can photograph a subject with high definition and an image reproduction function that arbitrarily reads and reproduces a recorded image that is recorded and stored. It has an information addition function to be added to the. The control unit 1 operates by supplying power from the power source unit (secondary battery) 2 and controls the overall operation of the camera according to various programs stored in the storage unit 3. 1 is provided with a CPU (central processing unit), a memory and the like (not shown).

  The storage unit 3 has a configuration including, for example, a ROM, a flash memory, and the like, and a program storing various programs and the like for realizing the present embodiment in accordance with the operation procedure shown in FIGS. A memory 3a, a work memory 3b for temporarily storing flags and the like, a character recognition database 3c configured to store character features (feature vectors, etc.) and character codes (text data) in association with each other; It has a mark database 3d and the like. The storage unit 3 may include a removable portable memory (recording medium) such as an SD card or a USB memory, and is connected to a network via a communication function (not shown). The state may include a storage area on a predetermined server device side.

  Although not shown, the operation unit 4 has a power key for turning on / off the power, a mode change key for switching between a mode capable of shooting (REC mode) and a mode for playing back a captured image (PLAY mode), Various keys such as a release key for instructing photographing are provided, and the control unit 1 performs, for example, a mode change process, a photographing process, and a reproduction process in response to the key operation. Although not shown, the imaging unit 5 is capable of photographing a subject with high definition by forming a subject image from an optical lens on an imaging element (CCD, CMOS, etc.). And various sensors, analog processing units, and digital processing units. The image captured by the imaging unit 5 is subjected to an image compression process for compressing the image into a file by the control unit 1 and then recorded and stored in a recording medium of the storage unit 3.

  The display unit 6 is configured by a high-definition liquid crystal display device or the like, and serves as a monitor screen (live view screen) that displays live view images in real time, or as a playback screen that plays back recorded and stored captured images. To do. The wireless communication unit 7 constitutes, for example, a WI-Fi (Wireless Fidelity), and is connected to a server device via a communication network (not shown) (public wireless communication network and the Internet). The map information or the like is received and the contents of the landmark database 3d are updated. A GPS (Global Positioning System) positioning unit 8 is a position measuring system that measures the current position using a terrestrial / satellite control station, and the control unit 1 receives position information received by the GPS positioning unit 8 during shooting. Is added to the file information (Exif information) of the photographed image as the photographing position.

FIG. 2 is a diagram illustrating a photographed image photographed including characters.
FIG. 2 (1) shows an example of an image of a person standing at the entrance (as a main subject) intended for an aquarium. In this captured image, “○ △ An aquarium and an entrance are included. FIG. 2 (2) illustrates an example of an image taken with the guide board installed near the aquarium as a main subject (as a main subject). ”,“ Dolphin Show ”,“ Starting from 13:00 ”, and so on.

  When the activation of a function for adding information to a captured image is instructed by a user operation, the control unit 1 reads out the captured image stored in the recording medium of the storage unit 3 and performs character recognition to be included in the captured image. Character recognition is performed by extracting the included character image. For example, in the case of the photographed image of FIG. 2 (1), the character strings “◯ △ aquarium” and “entrance” are extracted, and in the case of the photographed image of FIG. 2 (2), “entrance” and “dolphins”. Character strings of “show”, “starting from 13:00”,... Are extracted and character recognition is performed. In addition, in this embodiment, a character means the character in a broad sense including a symbol, an abbreviation, a foreign language character, etc. other than a general character.

FIG. 2 is a diagram for explaining the landmark database 3d.
The landmark database 3d stores information related to each point corresponding to each point such as a sightseeing spot. Each item of "point position", "landmark name", and "detailed information" is stored. Have. “Point location” is an item for storing location information for specifying a location, and stores longitude and latitude information as location information, but is not limited thereto, and stores location names and address information obtained based on longitude and latitude information. It may be. “Landmark name” refers to the name of the place that symbolizes the point (for example, the name of the facility, the name of the place, the address), the name of the event held at that point, the name of the guest who participates in the event, etc. Is an item for storing various names (including abbreviations and aliases).

  In the example shown in the figure, “Landmark name” corresponding to “Point X in Kanagawa Prefecture” stores “○ Δ Aquarium” as a character string (proprietary noun) indicating the facility name, and the facility “Event of the month” and “Dolphin show” are stored as character strings related to events held in the city. The “Landmark name” “Event of the month” and “Dolphin show” are information that indicates that the event held every month at the Aquarium is a dolphin show, and it is possible to identify the event. This is a typical name. In addition, in “Landmark name” whose “point location” corresponds to “point Y in Tokyo”, “Tachikawa station” is used as a character string (proprietary noun) indicating the facility name, and characters related to the event held at the facility “Setsubun” and “Taro XX” are stored as columns. The “landmark names” “Tachikawa Station” and “Taro Taro” are information that held a setsubun event on February 3 in front of Tachikawa Station and that “Taro Taro” is coming as a guest. This is a representative name that can identify the event.

  “Detailed information” is detailed information regarding a point, and is an item that stores detailed information such as a URL (Uniform Resource Locator) for accessing information on the network, facility information, event information, and the like. In the example shown in the figure, “URL” and “facility information” of the aquarium are stored as “detailed information” of “location X” in “Kanagawa prefecture” and “landmark name” “Aquarium”. In this example, “landmark name” stores “date and time: **”, “charge: **”, etc. as “detailed information” of “this month's event” and “dolphin show”. Furthermore, the “URL” of the station is stored as “detailed information” of “point position in Tokyo” as “location Y in Tokyo”, and “landmark name” as “Tachikawa station”, and “landmark name” is set as “setsubun”. As “detailed information” of “Taro”, “date and time: station square ...”, “guest name: Taro ...”, and the like are stored.

  The landmark database 3d configured as described above is referred to during the operation of the information addition function described above, and the control unit 1 captures images from various characters included in the captured images. The landmark database 3d is referred to in order to select whether the information is necessary information intended by the person or unintended unnecessary information. That is, the control unit 1 recognizes a character in the captured image and acquires the character information, reads out GPS position information from the Exif information of the captured image, specifies a shooting position, and determines a landmark based on the shooting position. The “spot position” in the database 3d is searched, and the “landmark name” corresponding to this “spot position” is acquired as information regarding the shooting position.

  Then, the character information obtained by recognizing the characters in the captured image is compared with the “landmark name” acquired from the landmark database 3d, and the same object (for example, the same facility name, the same event name, etc.) ) To determine whether the information is necessary information intended by the photographer or unintended unnecessary information from among various characters included in the photographed image. Sort out. Here, if they indicate the same target, it is determined that the information on the shooting position is necessary information intended by the photographer, and the “landmark name” and “detailed information” are used as the Exif information of the shot image. After being added to, the captured image is recorded and saved.

  Next, the operation concept of the image processing apparatus (digital camera) in the present embodiment will be described with reference to the flowcharts shown in FIGS. Here, each function described in these flowcharts is stored in the form of a readable program code, and operations according to the program code are sequentially executed. Further, it is possible to sequentially execute the operation according to the above-described program code transmitted via a transmission medium such as a network. In other words, in addition to the recording medium, an operation unique to the present embodiment can be executed using a program / data supplied externally via a transmission medium. 4 and 5 are flowcharts showing an outline of the operation of the characteristic part of the present embodiment in the overall operation of the digital camera. When the flow of FIG. 4 and FIG. Return to the main flow (not shown).

4 and 5 are flowcharts showing an operation (characteristic operation of this embodiment) that is started when a function for adding information to a captured image is activated by a user operation.
First, the control unit 1 captures a captured image arbitrarily designated by a user operation as a processing target from among captured images stored in a recording medium of the storage unit 3 (step A1 in FIG. 4). Then, it is checked whether the GPS position information is stored in the EXIF information of the captured image (step A2). If the GPS position information is not stored (NO in step A2), the information is not added. 4 and FIG. 5, the GPS position information is acquired from the EXIF information (step A3) if the GPS position information is stored (YES in step A2).

  Then, a character image portion is extracted while analyzing the photographed image (step A4), and it is checked whether or not characters are included in the photographed image (step A5). If no character is included in the entire photographed image (NO in step A5), the “location of location” in the landmark database 3d is searched based on the acquired GPS location information, and the corresponding “ “Landmark name” and “detailed information” corresponding to “point position” are acquired as information on the shooting position of the shot image (step A7). In this case, if a plurality of “landmark names” are associated with “point position” in the landmark database 3d, the representative “landmark name”, that is, the “landmarks” listed first. "Name" and its "detailed information" are acquired. After adding the “landmark name” and “detailed information” thus acquired to the EXIF information of the photographed image, the photographed image is recorded and saved in the recording medium of the original storage unit 3 (step A8), and FIG. And the flow of FIG. 5 is exited.

  On the other hand, if a character is included in the photographed image (YES in step A5), the extracted character image is recognized for each character with reference to the character recognition database 3c, and character information ( Character code) is acquired (step A6). In this case, as shown in FIG. 2 (1), when the photographed image includes “◯ △ aquarium” and “entrance” as a plurality of character strings, the first extracted “◯ △ aquarium” "" Is recognized and its character information is acquired. Then, the process proceeds to step A9 in FIG. 5 to search the “point position” in the landmark database 3d based on the acquired GPS position information, and use the “landmark name” of the corresponding “point position” as information on the shooting position. Obtain (step A10). For example, when the “point location” is “point X in Kanagawa”, “landmark name” “○ △ aquarium”, “this month event”, “dolphin show” is acquired from the landmark database 3d. .

  Then, the character information (for example, “◯ △ aquarium”) in the photographed image recognized by the character and the landmark name (for example, “◯ △ aquarium”, “this month's event”, “dolphins” acquired from the landmark database 3d). Show ") (step A11), and it is checked whether the character information matches the landmark name by a predetermined number of characters (for example, two characters) or more (step A12). In this case, for example, it is determined that the character information “○ △ Aquarium” in the photographed image does not match the landmark names “Event of the Month” and “Dolphin Show”, but the landmark name “○ “△ Aquarium” is judged to match.

  Note that even if the character information is not “◯ △ aquarium”, for example, when a part of the characters on the signboard is faint and all the characters cannot be recognized correctly, or a part of the character string is in the shooting range. Even if the character information is “◯ △” or “△ aquarium” due to the fact that it is out of the range, it is determined that it matches the landmark name “◯ △ aquarium”. In this match determination, in addition to the above, it may be checked whether the number of characters that do not match is equal to or less than a predetermined value, or whether the ratio of characters that do not match the match characters is equal to or greater than a predetermined value (or less). In addition, the user may arbitrarily set the number and ratio of characters that serve as a reference for determining a match.

  Similarly, if the “point location” is “point X in Kanagawa Prefecture” and the character information in the photographed image that has been character-recognized is “dolphin show”, the landmark names “○ △ Aquarium” and “ It is determined that the “event” does not match the character information, but the landmark name “Dolphin Show” matches. Even if the character information is not “Dolphin Show”, for example, if it is “Dolphin” or “Show”, it is determined that it matches the landmark name “Dolphin Show”.

  If the character information matches any landmark name (NO in step A12), "detailed information" corresponding to the "landmark name" is acquired from the landmark database 3d (step A13). . For example, when the character information matches the landmark name “Aquarium”, “URL, facility information” of the aquarium is acquired as the “detailed information”, and the character information is “landmark name“ If it matches the “Dolphin Show”, the “detailed information” of the “date and time, fee, etc.” of the event is acquired. Then, the process proceeds to the next step A14, where “landmark name” and “detailed information” are added to the EXIF information of the photographed image, and then the photographed image is recorded and stored in the recording medium of the original storage unit 3.

  Thereafter, the process proceeds to step A15, where it is checked whether other character images remain in the photographed image. Now, since “entrance” remains as another character in the photographed image shown in FIG. 2A (YES in step A15), the character string “entrance” is recognized and its character information is acquired. (Step A16). Returning to step A11, the character information “entrance” in the photographed image that has been recognized and the landmark names “◯ △ aquarium”, “this month's event”, “dolphins” acquired from the landmark database 3d are returned. The character information does not match all the landmark names (NO in step A12), and the process proceeds to step A15 to ignore the character information. In this case, since there are no characters other than “◯ Δ aquarium” and “entrance” in the photographed image (NO in step A15), the flow of FIG. 4 and FIG. 5 is exited.

FIG. 6 is a flowchart showing an operation (characteristic operation of the present embodiment) that is started when the playback mode is switched.
First, the control unit 1 selects an image to be reproduced from among the captured images stored in the recording medium of the storage unit 3 (step B1), and displays the selected captured image on the reproduction screen (step B2). Then, the EXIF information of the reproduced image is accessed to check whether the “landmark name” is added (step B3). If the “landmark name” is not stored (NO in step B3), the process proceeds to step B6. Check whether the playback mode has been canceled. If the playback mode remains unchanged (NO in step B3), the next playback target image is selected (step B1) and displayed on the playback screen (step B2).

  If the “landmark name” is added to the image to be reproduced (YES in step B3), the “detailed information” is acquired together with the “landmark name” from the EXIF information of the reproduced image (step B4). The “landmark name” and “detailed information” are displayed on the reproduction screen (step B5). For example, “landmark name” and “detailed information” are superimposed on the captured image or displayed in parallel. Then, the process proceeds to the next step B6, in which it is checked whether or not the reproduction mode has been released, and the above-described operation is repeated while sequentially selecting photographed images until the reproduction mode is released.

  As described above, in the present embodiment, the control unit 1 recognizes characters in a captured image and acquires character information thereof, specifies a shooting position of the captured image, acquires information regarding the shooting position, The acquired character information and information on the shooting position are compared to determine whether or not they indicate the same object, and on the condition that the same object is indicated, the information on the shooting position is determined as the captured image. Since the character information in the photographed image and the information regarding the photographing position are not the same target (for example, the same facility name, the same event name, etc.) If it is the same target, it can be determined that it is necessary information intended by the photographer, and even if various characters not related to the shooting position are included in the shot image, Shoot It is possible to appropriately adding the intended information's in the captured image.

  The control unit 1 acquires the name of the shooting place (for example, the name of the facility, the name of the place, and the address) from the landmark database 3d, compares the character information in the shot image with the name of the shooting place, and the same object (place) Therefore, it is possible to select character information indicating the shooting location from the captured image and add information related to the captured location to the captured image.

  When the character information in the captured image is compared with the name of the shooting location, the control unit 1 determines that the same object (location) is the same if the predetermined number of characters match. Even when a part of the place name is not photographed or characters cannot be recognized, it can be determined that the place is the same object (place).

  The landmark database 3d is a database that stores information about the location for each point, and the control unit 1 acquires information about the shooting location by searching the landmark database 3d based on the shooting position of the shot image. Thus, it is possible to easily obtain information regarding the shooting location by simply referring to the landmark database 3d.

  When displaying the captured image on the playback screen, the control unit 1 displays the “landmark name” and “detailed information” added to the captured image together with the playback screen. Thus, it is possible to know information about the shooting position at the time of reproducing the shot image.

  In the above-described embodiment, when no character image is included in the entire photographed image (NO in step A5 in FIG. 4), the “3” in the landmark database 3d is set based on the acquired GPS position information. "Point position" is searched, and information on the corresponding shooting position is added to the shot image (steps A7 and A8). If no characters are included in the shot image, information on the shooting position is shot. Steps A7 and A8 may not be executed so as not to be added to the image.

  Further, in the above-described embodiment, information is automatically added to and recorded on the captured image without notifying the user at the time of shooting, but what information is added when recording the shot image. This may be displayed to inform the user, or the user who sees it may be able to instruct whether to add each information. In addition, the user may be notified of the presence or absence of character detection in the captured image and the processing status of whether or not the detected character matches information in the database.

<Modification 1>
In the above-described embodiment, when a function for adding information to a photographed image is activated by a user operation, information regarding the photographing position is added to the photographed image, but this information addition function is activated independently. However, the present invention is not limited to this, and information may be added or displayed in conjunction with the reproduction operation of the captured image.
FIG. 7 is a flowchart showing an operation when information is added to a captured image when the captured image is reproduced. As in the above-described embodiment, the method of adding information to the captured image recognizes characters in the captured image and acquires the character information, specifies the shooting position of the captured image, and sets the shooting position. The information on the shooting position is added to the captured image on the condition that the acquired character information and the information on the shooting position are compared to indicate the same object.

  First, the control unit 1 selects an image to be reproduced from among the captured images stored in the recording medium of the storage unit 3 (step C1), and displays the selected captured image on the reproduction screen (step C2). As in the above-described embodiment, the character image portion is extracted while analyzing the captured image to perform character recognition (step C3), and the GPS position information is acquired from the EXIF information in the captured image to obtain the landmark. The “point position” in the database 3d is searched, and the “landmark name” corresponding to the “point position” is acquired (step C4). Then, the recognized character information is compared with the acquired landmark name (step C5), and it is checked whether the character information matches the landmark name by a predetermined number of characters or more (step C6).

  If the character information does not match the landmark name (NO in step C6), the process proceeds to step C9, where it is checked whether the reproduction mode has been released. If the reproduction mode remains (NO in step C9), the above steps are performed. Returning to C1, the next playback target image is selected. If the character information matches the landmark name (YES in step C5), the information “landmark name” and “detailed information” regarding the shooting position acquired from the landmark database 3d is added to the EXIF information of the shot image. "Is added (step C7). Then, the “landmark name” and “detailed information” are displayed on the reproduction screen (step C8). In this case, “landmark name” and “detailed information” are superimposed on the captured image or displayed in parallel. Thereafter, the above-described operation is repeated until the reproduction mode is canceled.

  When reproducing the captured image as described above, it is determined whether or not the character information in the captured image is compared with the information on the captured position acquired from the landmark database 3d to indicate the same object. If the information added to the captured image is displayed on the playback screen on condition that they indicate the same object, the information can be added at the time of playback of the captured image, and the information is given to the user. Can be confirmed on the playback screen.

<Modification 2>
In <Modification 1> described above, information is added in conjunction with the reproduction operation of the photographed image. However, the present invention is not limited to this, and information may be added in conjunction with the photographing operation.
FIG. 8 is a flowchart showing an operation when information is added to the photographed image when the release key is operated. As in the above-described embodiment, the method of adding information to the captured image recognizes characters in the captured image and acquires the character information, specifies the shooting position of the captured image, and sets the shooting position. The information on the shooting position is added to the captured image on the condition that the acquired character information and the information on the shooting position are compared to indicate the same object.

  First, the control unit 1 performs a photographing process for developing the image acquired in response to the release key operation (step D1). The character image portion is extracted while analyzing the photographed image to perform character recognition (step D2), and the GPS position information is acquired from the GPS positioning unit 8, and the landmark database 3d is stored based on the GPS position information. “Point position” is searched and “landmark name” corresponding to the “point position” is acquired (step D3). Next, as in the above-described embodiment, the recognized character information is compared with the acquired landmark name (step D4) to check whether the character information matches the landmark name by a predetermined number of characters or more (step D4). Step D5).

  If the character information does not match the landmark name (NO in step D5), the process proceeds to step D7, where normal information such as GPS position information and shooting date is added to the EXIF information of the shot image, and then the shot is taken. The image is recorded and saved on the recording medium of the original storage unit 3. If the character information matches the landmark name (YES in step D5), the EXIF information of the captured image includes normal information such as GPS position information and shooting date, and from the landmark database 3d. After adding the information “landmark name” and “detailed information” regarding the acquired shooting position, the shot image is recorded and stored in the recording medium of the original storage unit 3 (step D6). Thereafter, the flow of FIG. 8 is exited.

  As described above, the character information in the photographed image at the time of photographing is compared with the information on the photographing position acquired from the landmark database 3d to determine whether or not the same object is indicated, and the same object is indicated. If information about the shooting position is added to the captured image and recorded and saved on the condition that it is, information about the shooting position is added to the captured image together with GPS position information, shooting date, and the like at the time of shooting. be able to.

<Modification 3>
In the above-described embodiment, when the shooting position of the shot image cannot be specified, that is, when the GPS position information is not stored in the EXIF information of the shot image in Step A2 of FIG. ) A method is adopted in which information about the shooting position is not added to the shot image. However, the present invention is not limited to this. (B) Character recognition in the shot image is performed without referring to the landmark database 3d. A method of adding the character information thus obtained to the EXIF information of the photographed image, or a method of adding information on the photographing position acquired from the landmark database 3d based on the character recognition result (C) may be adopted. Further, any one of the methods (A), (B), and (C) described above may be arbitrarily selected by a user operation.

  For example, if the above-described method (C) is the specific mode selected by the user operation, the character image in the photographed image is extracted and character recognition is performed, and for the landmark based on the character information of the recognition result. The "landmark name" in the database 3d is searched, the character information is compared with the "landmark name", and if the character information matches the "landmark name" by a predetermined number of characters or more, the "landmark name" is searched. And “detailed information” may be acquired from the landmark database 3d and added to the EXIF information of the photographed image.

  In this way, if the shooting position of the shot image cannot be specified, and if in the specific mode, information on the shooting position is acquired from the character information and added to the shot image, the same as in the above-described embodiment. The information intended by the photographer can be appropriately added to the photographed image.

  In the above-described embodiment, information “landmark name” and “detailed information” related to the photographing position acquired from the landmark database 3d are added to the photographed image and recorded when they are the same target. Character information obtained by recognizing characters in the photographed image may be added to the photographed image and recorded as information on the photographing position.

  In the embodiment described above, the case where the landmark database 3d is provided on the camera side is illustrated. However, for example, the landmark database 3d is provided on the server device (not shown) connected via the wireless communication network. It may be the case. In this case, the camera side transmits GPS position information to the server side, and the server side searches the landmark database 3d based on the received GPS position information, and transmits information regarding the corresponding shooting position to the camera side. What should I do?

  In the above-described embodiments, the case where the present invention is applied to a digital camera as an image processing device has been described. However, a personal computer, a PDA (personal portable information communication device), a tablet terminal device, a mobile phone such as a smartphone, an electronic game, music It may be a player.

  Further, the “apparatus” and “unit” shown in the above-described embodiments may be separated into a plurality of cases by function, and are not limited to a single case. In addition, each step described in the above-described flowchart is not limited to time-series processing, and a plurality of steps may be processed in parallel or separately.

The embodiment of the present invention has been described above. However, the present invention is not limited to this, and includes the invention described in the claims and the equivalent scope thereof.
Hereinafter, the invention described in the claims of the present application will be appended.
(Appendix)
(Claim 1)
The invention described in claim 1
First acquisition means for acquiring character information obtained by recognizing characters in a captured image;
Second acquisition means for specifying a shooting position of the shot image and acquiring information relating to the shooting position;
A discriminating unit that compares the character information acquired by the first acquiring unit with the information on the photographing position acquired by the second acquiring unit to determine whether or not the same target is indicated;
Of the character information acquired by the first acquisition unit and the information on the shooting position acquired by the second acquisition unit on the condition that the determination unit has determined that the same object is indicated, Information adding means for adding and recording at least one of the information to the captured image;
It is provided with.
(Claim 2)
The invention according to claim 2 is the image processing apparatus according to claim 1,
The second acquisition means acquires the name of the shooting location as information on the shooting position by searching a database storing the name of the location for each position,
The determination means determines whether or not the same information is indicated by comparing the character information acquired by the first acquisition means with the name of the shooting location acquired by the second acquisition means.
It is characterized by that.
(Claim 3)
The invention according to claim 3 is the image processing apparatus according to claim 2,
When the character number acquired by the first acquisition unit and the name of the shooting location acquired by the second acquisition unit are compared with each other, if the predetermined number of characters matches, the determination unit Determine that they are the same target,
It is characterized by that.
(Claim 4)
The invention according to claim 4 is the image processing apparatus according to claim 2 or 3,
The database stores information about the location for each location,
The second acquisition means specifies the shooting position of the shot image, and acquires information related to the shooting location by searching the database based on the shooting position.
It is characterized by that.
(Claim 5)
The invention according to claim 5 is the image processing apparatus according to any one of claims 1 to 4,
Display means;
Display control means for displaying the photographed image on the display means;
Further comprising
The display control means controls the display means to display the information added by the information addition means when displaying the captured image on the display means.
It is characterized by that.
(Claim 6)
The invention according to claim 6 is the image processing apparatus according to claim 5,
The discriminating means includes the character information acquired by the first acquisition means and the information on the imaging position acquired by the second acquisition means when the display control means displays the captured image on the display means. Compare to see if they show the same object,
The display control means performs control to display the information added by the information addition means on the display means on the condition that the determination means indicates that the same object is indicated.
It is characterized by that.
(Claim 7)
The invention according to claim 7 is the image processing apparatus according to any one of claims 1 to 6,
Photographing means for photographing the photographed image;
Position specifying means for specifying the shooting position of the shot image;
Further comprising
The second acquisition unit acquires information related to the shooting position based on the shooting position specified by the position specifying unit during shooting by the shooting unit.
It is characterized by that.
(Claim 8)
The invention according to claim 8 is the image processing apparatus according to any one of claims 1 to 7,
Setting means for setting to a specific mode;
Further comprising
If the second acquisition unit cannot set the shooting position of the shot image and is set to the specific mode by the setting unit, the character information acquired by the first acquisition unit Obtaining information about the shooting position by searching the database based on
It is characterized by that.
(Claim 9)
The invention according to claim 9 is:
An image processing method in an image processing apparatus,
Processing to acquire character information that recognizes characters in the captured image;
A process of identifying the shooting position of the shot image and acquiring information related to the shooting position;
A process of comparing the acquired character information and the acquired information on the shooting position to determine whether or not the same object is indicated;
Recorded by adding at least one of the acquired character information and information regarding the acquired photographing position to the photographed image on the condition that the same object is determined. Processing to
It is characterized by including.
(Claim 10)
The invention according to claim 10 is:
For the computer of the image processing device,
A function to acquire character information by recognizing characters in a captured image;
A function of identifying a shooting position of the shot image and acquiring information related to the shooting position;
A function of comparing the acquired character information and the acquired information on the shooting position to determine whether the same object is indicated;
Recorded by adding at least one of the acquired character information and information regarding the acquired photographing position to the photographed image on the condition that the same object is determined. Function to
It is a program for realizing.

DESCRIPTION OF SYMBOLS 1 Control part 3 Memory | storage part 3a Program memory 3c Database for character recognition 3d Database for landmark 5 Imaging part 7 Wireless communication part 8 GPS positioning part

Claims (10)

First acquisition means for acquiring character information obtained by recognizing characters in a captured image;
Second acquisition means for specifying a shooting position of the shot image and acquiring information relating to the shooting position;
A discriminating unit that compares the character information acquired by the first acquiring unit with the information on the photographing position acquired by the second acquiring unit to determine whether or not the same target is indicated;
Of the character information acquired by the first acquisition unit and the information on the shooting position acquired by the second acquisition unit on the condition that the determination unit has determined that the same object is indicated, Information adding means for adding and recording at least one of the information to the captured image;
An image processing apparatus comprising: The second acquisition means acquires the name of the shooting location as information on the shooting position by searching a database storing the name of the location for each position,
The determination means determines whether or not the same information is indicated by comparing the character information acquired by the first acquisition means with the name of the shooting location acquired by the second acquisition means.
The image processing apparatus according to claim 1. When the character number acquired by the first acquisition unit and the name of the shooting location acquired by the second acquisition unit are compared with each other, if the predetermined number of characters matches, the determination unit Determine that they are the same target,
The image processing apparatus according to claim 2. The database stores information about the location for each location,
The second acquisition means specifies the shooting position of the shot image, and acquires information related to the shooting location by searching the database based on the shooting position.
The image processing apparatus according to claim 2, wherein the image processing apparatus is an image processing apparatus. Display means;
Display control means for displaying the photographed image on the display means;
Further comprising
The display control means controls the display means to display the information added by the information addition means when displaying the captured image on the display means.
The image processing apparatus according to claim 1, wherein the image processing apparatus is an image processing apparatus. The discriminating means includes the character information acquired by the first acquisition means and the information on the imaging position acquired by the second acquisition means when the display control means displays the captured image on the display means. Compare to see if they show the same object,
The display control means performs control to display the information added by the information addition means on the display means on the condition that the determination means indicates that the same object is indicated.
The image processing apparatus according to claim 5. Photographing means for photographing the photographed image;
Position specifying means for specifying the shooting position of the shot image;
Further comprising
The second acquisition unit acquires information related to the shooting position based on the shooting position specified by the position specifying unit during shooting by the shooting unit.
The image processing apparatus according to claim 1, wherein the image processing apparatus is an image processing apparatus. Setting means for setting to a specific mode;
Further comprising
If the second acquisition unit cannot set the shooting position of the shot image and is set to the specific mode by the setting unit, the character information acquired by the first acquisition unit Obtaining information about the shooting position by searching the database based on
The image processing apparatus according to claim 1, wherein the image processing apparatus is an image processing apparatus. An image processing method in an image processing apparatus,
Processing to acquire character information that recognizes characters in the captured image;
A process of identifying the shooting position of the shot image and acquiring information related to the shooting position;
A process of comparing the acquired character information and the acquired information on the shooting position to determine whether or not the same object is indicated;
Recorded by adding at least one of the acquired character information and information regarding the acquired photographing position to the photographed image on the condition that the same object is determined. Processing to
An image processing method comprising: For the computer of the image processing device,
A function to acquire character information by recognizing characters in a captured image;
A function of identifying a shooting position of the shot image and acquiring information related to the shooting position;
A function of comparing the acquired character information and the acquired information on the shooting position to determine whether the same object is indicated;
Recorded by adding at least one of the acquired character information and information regarding the acquired photographing position to the photographed image on the condition that the same object is determined. Function to
A program to realize

Images