JP2021135811A - Character input support control device, character input support system, and character input support program - Google Patents

Abstract

To extract a character image from a display image based on image data already recorded on a recording medium to generate text data, and store image data of a captured image itself and the generated text data in association with each other.SOLUTION: A communication terminal device 12 reads recorded data already stored in a file server 14 or the like to display an image, the displayed image data is transmitted to an OCR server 16 via the file server 14, and characters included in the image are converted into text data and stored as a comment associated with the image data. By associating the characters displayed on the image as first text data with the image data, the characters can be used as search key words when a necessary image is searched for from a large amount of image files, and quick search processing can be achieved.SELECTED DRAWING: Figure 4

Description

The present invention relates to a character input support control device, a character input support system, and a character input support program for registering a file name and a comment by using utterance voice data at an imaging site.

For example, in a company that manages a vast factory such as the manufacturing industry, the situation at the site is recorded as a digital file using a digital camera or smart phone (sometimes called a smartphone) during daily inspection work and troubleshooting work. It is necessary to record the video. Further, in recent years, a wearable terminal typified by smart glasses may be used as an imaging device.

By the way, it was necessary to rename the object and the file name of the captured digital file on a computer after returning to the office, but it is laborious to remember the situation at the time of imaging from a similar video recording. Is on.

As a reference, the techniques of Patent Documents 1 to 3 have been proposed as techniques for automatically organizing captured digital files.

Patent Document 1 describes that the image data transferred or the image data read by a reading device is separated into areas and the resolution at the time of storage is changed depending on whether or not text is included. ..

Specifically, when the text is included, the resolution is set to maintain the reading accuracy by OCR (Optical Character Recognition), and when the text is not included, the resolution is set to reduce the storage occupied area.

Further, Patent Document 2 describes that a frame image corresponding to the best shot is extracted from a moving image with high accuracy, efficiency and high speed.

Further, Patent Document 3 describes that captured images are automatically sorted according to a pre-registered image pattern for recognition.

Japanese Unexamined Patent Publication No. 2007-31224 Japanese Unexamined Patent Publication No. 2016-225679 JP-A-2010-56884

However, in Patent Document 1, it is considered that the purpose is to store the image and the text at different appropriate resolutions, and to print the image and the text in almost the same state as the original when the next printout or the like is executed. There is no concept or suggestion that the image data is stored as text data separately from the captured image data, and the image data and the text data are displayed side by side, for example.

Further, as in Patent Document 2, image analysis technology such as automatically organizing a large amount of images or extracting only the best shots from similar images has existed conventionally and is provided as a service, but the above-mentioned problem (similarity). It does not solve the problem of increased labor when inputting by remembering the situation at the time of imaging from the video recording of.

In Patent Document 3, the captured images are automatically sorted according to the image pattern for recognition registered in advance, but the initial setting (registration of the image pattern for recognition) is indispensable, and various images are taken at the imaging site. I can't respond to changes in the situation.

The present invention extracts a character image from a display image based on image data already recorded on a recording medium to generate text data, and stores the image data of the captured image itself and the generated text data in association with each other. The purpose is to obtain a character input support control device, a character input support system, and a character input support program that can be used.

The character input support control device according to the present invention reads out the image data stored in the image storage area and extracts the display control unit to be displayed on the display unit and the character image in the image displayed on the display unit. A character recognition unit that generates character recognition text data, and a text data storage unit that stores the character recognition text data generated by the character recognition unit in association with the image data.
have.

According to the present invention, the display control unit reads out the image data stored in the image storage area and displays it on the display unit.

The character recognition unit extracts a character image from the image displayed on the display unit to generate character recognition text data. The text data storage unit stores the character recognition text data generated by the character recognition unit in association with the image data.

As a result, character images are extracted from the display image based on the image data already recorded on the recording medium to generate text data, and the image data of the captured image itself and the generated text data are stored in association with each other. Can be done.

The present invention is characterized in that a character image based on the character recognition text data is displayed as a comment of the captured image.

By displaying the character recognition text data as a comment together with the captured image, it becomes easy to identify and identify the captured image.

In the present invention, the voice recognition unit further includes a voice recognition unit that converts voice data spoken during image display by the display unit into voice recognition text data, and the text data storage unit performs voice recognition by the voice recognition unit. The text data is stored in association with the image data, and the voice recognition text data is displayed as at least one of the title and the comment of the image.

Character recognition recognizes characters in an captured image and is limited information. On the other hand, for example, during image display by the display unit, the information envisioned in the head is uttered, and the uttered voice text data is displayed as at least one of the title and the comment, thereby further identifying and identifying the image. It will be easy.

The character input support system according to the present invention includes a communication terminal device having a display control unit that reads out image data stored in an image storage area and displays it on a display unit, and an image displayed on the display unit. A character recognition server equipped with a character recognition unit that extracts a character image and generates character recognition text data, and the image data of the image displayed on the display unit are associated with the character recognition text data generated by the character recognition unit. It has a data storage server provided with a text data storage unit for storing the data.

According to the present invention, a communication terminal device, a character recognition server, and a data storage server are linked via a network to construct a character input support system.

The display control unit of the communication terminal device reads out the image data stored in the image storage area and displays it on the display unit.

The character recognition unit of the character recognition server extracts the character image from the image displayed on the display unit and generates character recognition text data. In the data storage server, the character recognition text data generated by the character recognition unit is stored in the text data storage unit in association with the image data of the character recognition target stored in the image data storage unit.

Thereby, the character image can be extracted from the display image based on the image data already recorded on the recording medium to generate the text data, and the image data and the generated text data can be stored in association with each other.

The present invention is characterized in that a character image based on the character recognition text data is displayed as a comment of the captured image.

By displaying the character recognition text data as a comment together with the captured image, it becomes easy to identify and identify the captured image.

In the present invention, there is further a voice recognition server that converts voice data spoken during image display by the display unit into voice recognition text data, and the text data storage unit voice-recognizes voice recognition by the voice recognition server. The text data is stored in association with the image data, and the voice recognition text data is displayed as at least one of the title and the comment of the image.

Character recognition recognizes characters in an captured image and is limited information. On the other hand, for example, during image display by the display unit, the information envisioned in the head is spoken, and the spoken voice text data is displayed as at least one of the title and the comment, so that the captured image can be identified and identified. It will be easier.

The present invention is characterized in that the captured image captured by the imaging unit of the communication terminal device can be viewed in a state of being restricted to a specific communication terminal device for which permission has been obtained in advance after being stored in the data storage server. It is supposed to be.

Even if the data storage server can be accessed by an unspecified number of people, by restricting viewing on the communication terminal device, for example, even if the data storage server is an external storage that can secure storage capacity by contract, it is kept secret. Sex can be maintained.

The present invention is characterized in that it is equipped with a viewer function for listing stored frames, with a display area in which an image and text are set as one unit of frames.

By displaying the image and the text as a set, it becomes easy to sort the related images.

The character input support program according to the present invention is characterized in that the computer is operated as each part of the character input support control device according to any one of claims 1 to 3.

According to the present invention, a character image is extracted from a display image based on image data already recorded on a recording medium to generate text data, and the image data of the captured image itself is associated with the generated text data. Can be stored.

FIG. 5 is a network diagram showing a mutual connection state of a communication terminal device, a file server, and an OCR server constituting a character input support system according to the first embodiment. It is a control block diagram which shows the hardware composition of the communication terminal apparatus which concerns on 1st Embodiment. An example of a device applicable to the communication terminal device of the first embodiment, (A) is a perspective view of a smartphone, (B) is a perspective view of a digital camera, and (C) is a perspective view of a headset-type wearable camera. , (D) is a perspective view of a smart glass type wearable camera. The first embodiment is a communication protocol for executing character input support control in the character input support system according to the first embodiment. It is a front view of the monitor of the communication terminal apparatus which concerns on 1st Embodiment, (A) is an image at the time of shooting, (B) is an image at the time of OCR processing, (C) is a history list image, (D) is a function setting. It is an image. FIG. 5 is a network diagram showing a mutual connection state of a communication terminal device, a file server, and an OCR server constituting a character input support system according to the second embodiment. The second embodiment is a communication protocol for executing character input support control in the character input support system according to the second embodiment. It is a front view of the monitor of the communication terminal apparatus which concerns on 2nd Embodiment, (A) is an image at the time of shooting, (B) is an image at the time of OCR processing, (C) is a history list image, (D) is a function setting. It is an image.

"First embodiment"

FIG. 1 shows a schematic configuration diagram of a file character input support system 10 according to the first embodiment.

The file character input support system 10 is composed of a communication terminal device 12 owned by a user 11 who uses the file character input support system 10 and a file server 14, and can communicate with each other via a network 18. It has become. Further, the OCR server 16 is connected to the file server 14 via a communication line.

(Communication terminal device 12)

As shown in FIG. 2, the communication terminal device 12 includes a microcomputer 20. The microcomputer 20 is composed of a CPU 20A, a RAM 20B, a ROM 20C, an input / output port 20D, and a bus 20E composed of a data bus, a control bus, and the like connecting them.

The I / O 20D is connected to the input / output device 22, the large-scale storage medium 24, the image pickup device 26, and the communication I / F 28 for connecting to the network 18.

The input / output device 22 includes a touch panel unit 22A that functions as a monitor and an input pad, a speaker 22B, and a microphone 22C.

The communication I / F 28 transmits / receives data to / from the network 18 via the wireless relay device 30 connected to the network 18. More specifically, the image data captured by the imaging device 26 is stored in the large-scale storage device 24 of itself (communication terminal device 12) and transferred to the file server 14 (see FIG. 1) via the network 18. It may be (sent). Further, the file may be transferred to an external storage connected to the network 18 and different from the file server 14. The imaging may be either a moving image or a still image.

In the case of moving images, the sound data recorded by the microphone 22C (environmental sound data described later) is included, and in the case of still images, there is no environmental sound data. Further, even in a still image, there is an imaging device having a function of recording audio data as it is in association with image data.

In the following, the term "imaging" simply includes moving images and still images. Further, in the following, the image data and the audio data are collectively referred to as "recorded data". That is, the file server 14 has a function of managing and controlling image data and audio data.

Further, in the following, in the case of simply referred to as voice data, in order to identify the ambient sound data at the time of capturing the moving image by the imaging device 26 and the target imaged by the administrator who manages (possessed) the communication terminal device 12. It is assumed that the utterance voice data to be uttered is included, and the environmental sound data and the utterance voice data will be described separately as necessary. Further, in the case of a still image, utterance voice data can be recorded.

(Application example of communication terminal device 12)

The communication terminal device 12 may have at least the above basic functions (input / output device function (particularly, microphone), image pickup device function, and communication I / F function). As an example, the smartphone 12SP shown in FIG. 3A can be applied as a typical communication terminal device 12. Normally, the smartphone 12SP has a call function, so that it may be in a different category from a tablet terminal having a relatively large screen size (about 7 to 10 inches) that does not have the call function. Since it has the same function as a device function, the term "smartphone 12SP" in the following includes a tablet terminal.

That is, as shown in FIG. 3A, the smartphone 12SP has a communication function (including the communication I / F28 shown in FIG. 2), the front surface of the housing 32 is a touch panel portion 22A, and the touch panel portion 22A. A speaker 22B and a microphone 22C are provided around the speaker. Further, on the front surface and the back surface of the housing 32, camera lenses 26F and 26R, which form a part of the imaging device, are provided, respectively.

Further, as an example of the other communication terminal device 12, the digital camera 12DC shown in FIG. 3B can be applied. In the case of the digital camera 12DC, even if the digital camera 12DC itself does not have a communication function, it can be applied as a communication terminal device 12 by using an SD card having a communication function (for example, WiFi function).

Further, as an example of the communication terminal device 12, as shown in FIG. 3C, a headset type wearable camera unit 12HS can be applied. In the headset-type wearable camera unit 12HS, the image pickup device 26 worn by the user on a helmet or the like and other devices (input / output device 22 and communication I / F 28, etc.) held by the user 11 are separated, and the cable 34 is used. It is connected with.

Further, as an example of the communication terminal device 12, as shown in FIG. 3D, a smart glass type in which some or all functions including the input / output device 22 and the image pickup device 26 are incorporated in the eyeglass-type wearing portion. It may be a wearable camera unit 12SG.

(File server 14)

As shown in FIG. 1, the file server 14 has a function as a microcomputer, and although not shown, it has a CPU, RAM, ROM, I / O, and a bus.

Further, the file server 14 includes a database 14A having an image data storage area and a text data storage area as a large-scale storage device. In the database 14A, the recorded data received from the communication terminal device 12 is stored as a file under the control of the file server 14.

(OCR server 16)

In the first embodiment, an OCR processing application program (hereinafter referred to as an OCR application) is set as an additional function of the image pickup device of the communication terminal device 12. This OCR application reads out the recorded data stored in the large-scale storage device 24 of the communication terminal device 12, the database 14A of the file server 14, and other external storage (not shown) connected to the network 18, and files. It has a function of sending to the OCR server 16 via the server 14, reading the characters included in the captured image, converting them into character information, and storing them in each storage area as attached information associated with the recorded data. ing. The attached information is stored in the comment area added to the recorded data.

As an example, a comment area provided as a part of Exif (registered trademark "Exchangeable Image File Format") information can be used as the comment area. The Exif (registered trademark) information area is an area for recording information related to imaging (shooting date / time, manufacturer name, model name, resolution, shutter speed, aperture, ISO, flash presence / absence, focal length, thumbnail image, GPS information, etc.). Therefore, a comment area is provided as one of the information regarding this imaging.

By OCR processing, the character information read from the image is stored in the comment area, and when the image is viewed, the character information in the comment area is also displayed, so that the captured image can be sorted as compared with the image alone. Can be useful.

The operation of the first embodiment will be described below based on the communication protocol of FIG.

FIG. 4 is a communication protocol executed via the network 18 by the communication terminal device 12, the file server 14, and the OCR server 16 connected to the file server 14 shown in FIG.

When the image reading is instructed by the OCR application function of the communication terminal device 12 (step 100), the recorded data is read from the database 14A of the file server 14 (step 102). At this time, the target for reading the recorded data may be the large-scale storage device 24 of itself (communication terminal device 12) or the external storage connected to the network 18 (step 104).

The read recorded data is displayed on the touch panel unit 22A (monitor) of the input / output device 22 (step 106).

The image data of the displayed image is transmitted to the OCR server 16 via the file server 14 (step 108). The OCR server 16 performs OCR processing on the received image data and extracts a character image (step 110). The extracted character image is returned to the communication terminal device 12 as first text data (step 112). The "first" of the first text data is for distinguishing the second text data generated by the voice-character conversion, which will be described later.

The monitor of the communication terminal device 12 that has received the first text data is provided with a title display column and a comment display column together with an image. The communication terminal device 12 displays the received first text data in the comment display field (step 118).

Here, the user 11 selects the title display field or the comment display field (step 120), and manually edits the text data in the title display field or the text data in the comment display field (by key input operation of the input pad). (Step 122). In some cases, editing is not required.

In the communication terminal device 12, when there is a "confirmation" instruction by the operation of the user 11 (step 124), the text data in the title column and the comment column is associated with the original image data and stored in the storage area of the recorded data read destination. Store.

For example, when the read destination of the recorded data is the file server 14, the first text data is transmitted to the file server 14 (step 126), and the text data storage area is updated (step 128). Similarly, the first text data may be transmitted to the image data read destination in the communication terminal device 12 or other external storage, and the text data storage area of each image data may be updated.

FIG. 5 is a transition diagram of a display screen of the input / output device 22 (touch panel unit 22A) of the communication terminal device 12 to be displayed based on the execution of the communication protocol of FIG.

FIG. 5A shows a state in which the entire area of the touch panel unit 22A serves as the imaging screen display field 40 in step 102 of FIG. 4, and an image based on the read recorded data is displayed.

FIG. 5B is a first text data display screen of the displayed image. At this time, the touch panel unit 22A is divided into an imaging screen display field 42, a title display field 44, and a comment display field 46, and the first text data is displayed in the comment display field 46.

FIG. 5C is an example of history display of an image to which the first text data is added by performing OCR processing, and the entire area of the touch panel unit 22A is the history display field 48.

In the history display field 48, the communication terminal device 12 accesses the read destination storage (own large-scale storage device 24, file server 14, and other external storage connected to the network 18), and a designated file ( Recorded data, text data) are displayed in a list. In FIG. 5C, the title name, image, and comment are displayed in the history display field 48 in the frame for one file, and a maximum of three frames are displayed. However, by scrolling or switching, frames for other files are displayed. Can be displayed.

As shown in FIG. 5C, when the image is downloaded from the file server 14 or other external storage and displayed, the image may be limited to the communication terminal device 12 specified in advance from the viewpoint of security and confidentiality. preferable. For example, it is conceivable to enter a password to enable browsing, or to decide whether or not to browse by the default setting for each communication terminal device 12.

FIG. 5D shows various setting screen display fields 50 of the character input support application program installed in the communication terminal device 12, and is a setting for switching whether or not to execute the OCR process (whether or not the OCR application needs to be started). You can do it.

As described above, in the first embodiment, when the OCR application is started in the communication terminal device 12 and the image already stored in any of them is read and displayed, the displayed image data is displayed on the file server. It is sent to the OCR server 16 via 14, converts the characters included in the image into character information (first text data), and is stored as a comment associated with the image data.

By associating the characters displayed in this image with the image data as the first text data, it can be used as a search keyword when searching for a necessary image from a large number of image files, which is quick. Search processing can be realized.

"Second embodiment"

The second embodiment of the present invention will be described below.

The first embodiment is characterized in that the character image in the captured image is converted into text data (first text data) by OCR processing and the first text data is stored in the comment display field. there were.

On the other hand, in the second embodiment, in addition to the OCR server 16 that executes the OCR process, a voice recognition server 36 having a spoken voice-character conversion control function is connected on the network 18, and the communication terminal device 12 and Communication with the file server 14 is possible.

That is, in the second embodiment, the user 11 who sees the image sends the voice (spoken voice data) emitted in relation to the image to the voice recognition server 36 at the imaging site immediately after the image capture, and character information. It is characterized in that it is converted into (second text data) and stored in the title display column or comment display column.

The file name is generally automatically assigned and set with a regular number, date, etc. (for example, "DVC01012020-001").

In the second embodiment, in the imaging base where the imaging by the communication terminal device 12 is executed, when the imaging is a moving image, it is used during the preview display during imaging (mainly moving image) or after imaging (mainly still image). The voice (spoken voice data) spoken by the person 11 (user, see FIG. 1) was converted into character information and used as the title name of the recorded data.

When the image is a still image, the voice (spoken voice data) spoken by the user 11 (see FIG. 1) is used as character information while the still image is preview-displayed for a certain period of time after the still image is captured. It was converted and used as the title name of the recorded data.

The second text data may be used as the title name, or instead of the title name, may be stored in the comment display field in the same manner as the first text data converted by the OCR process.

The operation of the second embodiment will be described below based on the communication protocol of FIG.

FIG. 7 is a communication protocol executed via the network 18 by the communication terminal device 12, the file server 14, and the OCR server 16 connected to the file server 14 shown in FIG.

When the image reading is instructed by the OCR application function of the communication terminal device 12 (step 100), the recorded data is read from the database 14A of the file server 14 (step 102). At this time, the target for reading the recorded data may be the large-scale storage device 24 of itself (communication terminal device 12) or the external storage connected to the network 18 (step 104).

The read recorded data is displayed on the touch panel unit 22A (monitor) of the input / output device 22 (step 106).

The image data of the displayed image is transmitted to the OCR server 16 via the file server 14 (step 108). The OCR server 16 performs OCR processing on the received image data and extracts a character image (step 110A). The extracted character image is returned to the communication terminal device 12 as first text data (step 112). The "first" of the first text data is for distinguishing the second text data generated by the voice-character conversion, which will be described later.

The monitor of the communication terminal device 12 that has received the first text data is provided with a title display column and a comment display column together with an image. The communication terminal device 12 displays the received first text data in the comment display field (step 118).

The above is the communication protocol related to OCR processing, which is the same as that of the first embodiment.

Next, a communication protocol related to voice recognition processing will be described.

When the first text data is displayed in the comment field (step 118 described above), the user 11 then selects a title or comment as voice input (step 150). After selecting the title or comment, the user 11 speaks at the imaging site and executes voice input (step 152).

The voice data of the invention is transmitted from the communication terminal device 12 to the voice recognition server 36 (step 154).

The voice recognition server 36 executes voice recognition processing, converts voice data into character information, and generates second text data (step 156).

The second text data is returned from the voice recognition server 36 to the communication terminal device 12 (step 158) and displayed in the title column or the comment column (step 160).

Here, the user 11 selects the title display field or the comment display field (step 120), and manually edits the text data in the title display field or the text data in the comment display field (by key input operation of the input pad). (Step 122). In some cases, editing is not required.

In the communication terminal device 12, when there is a "confirmation" instruction by the operation of the user 11 (step 124), the text data in the title column and the comment column is associated with the original image data and stored in the storage area of the recorded data read destination. Store.

For example, when the read destination of the recorded data is the file server 14, the first text data is transmitted to the file server 14 (step 126), and the text data storage area is updated (step 128). Similarly, the first text data may be transmitted to the image data read destination in the communication terminal device 12 or other external storage, and the text data storage area of each image data may be updated.

FIG. 8 is a transition diagram of a display screen of the input / output device 22 (touch panel unit 22A) of the communication terminal device 12 to be displayed based on the execution of the communication protocol of FIG. 7.

FIG. 8A shows a state in which the entire area of the touch panel unit 22A serves as the imaging screen display field 40 in step 102 of FIG. 4, and an image based on the read recorded data is displayed.

FIG. 8B is a first text data display screen of the displayed image. At this time, the touch panel unit 22A is divided into an imaging screen display field 42, a title display field 44, and a comment display field 46, the first text data is displayed in the comment display field 46, and the second text data is displayed. It is displayed in the title display field 44 and / or the comment display field 46.

FIG. 8C is an example of history display of an image to which the first text data is added by performing OCR processing, and the entire area of the touch panel unit 22A is the history display field 48.

In the history display field 48, the communication terminal device 12 accesses the read destination storage (own large-scale storage device 24, file server 14, and other external storage connected to the network 18), and a designated file ( Recorded data, text data) are displayed in a list. In FIG. 5C, the title name, image, and comment are displayed in the history display field 48 in the frame for one file, and a maximum of three frames are displayed. However, by scrolling or switching, frames for other files are displayed. Can be displayed.

As shown in FIG. 8C, when the image is downloaded from the file server 14 or other external storage and displayed, the image may be limited to the communication terminal device 12 specified in advance from the viewpoint of security and confidentiality. preferable. For example, it is conceivable to enter a password to enable browsing, or to decide whether or not to browse by the default setting for each communication terminal device 12.

FIG. 8D shows various setting screen display fields 50 of the character input support application program installed in the communication terminal device 12, and it is possible to switch and set whether to execute the voice recognition process and the OCR process. It has become like.

As described above, in the second embodiment, in addition to extracting character information from the image by OCR processing, spoken voice data is sent to the voice recognition server 36, and the spoken voice data is used as character information (second text data). Is converted to and stored as a title or comment associated with the image data.

By associating the characters displayed in this image with the image data as the second text data, it can be used as a search keyword when searching for the required image from a large number of image files, which is quick. Search processing can be realized.

In the second embodiment, since the recorded data already stored is subjected to OCR processing, voice recognition is also performed together with OCR processing, but the timing of voice recognition by utterance is different from OCR processing. , It may be immediately after imaging.

10 Character input support system for files 11 Users 12 Communication terminal equipment 12SP Smartphone 12DC Digital camera 12HS Headset type wearable camera unit 12SG Smart glass type wearable camera unit 14 File server 14A Database 16 OCR server 18 Network 20 Microcomputer 20A CPU
20B RAM
20C ROM
20D I / O port 20E bus 22 I / O device 22A Touch panel 22B Speaker 22C Microphone 24 Hard disk 26 Imaging device 28 Communication I / F
30 Wireless relay device 32 Housing 34 Cable 36 Voice recognition server 40 Imaging screen display column 42 Imaging screen display column 44 Title display column 46 Comment display column 48 History display column

Claims (9)

A display control unit that reads out the image data stored in the image storage area and displays it on the display unit.
A character recognition unit that extracts a character image from the image displayed on the display unit to generate character recognition text data, and a character recognition unit.
A text data storage unit that stores character recognition text data generated by the character recognition unit in association with the image data, and a text data storage unit.
Character input support control device with. A character image based on the character recognition text data is displayed as a comment of the captured image.
The character input support control device according to claim 1. It further has a voice recognition unit that converts voice data uttered during image display by the display unit into voice recognition text data.
The text data storage unit stores the voice recognition text data voice-recognized by the voice recognition unit in association with the image data, and at the same time.
The voice recognition text data is displayed as at least one of the title and the comment of the image.
The character input support control device according to claim 1 or 2. A communication terminal device equipped with a display control unit that reads out image data stored in the image storage area and displays it on the display unit.
A character recognition server equipped with a character recognition unit that extracts a character image from the image displayed on the display unit and generates character recognition text data.
A data storage server provided with a text data storage unit that stores the character recognition text data generated by the character recognition unit in association with the image data of the image displayed on the display unit.
Character input support system with. A character image based on the character recognition text data is displayed as a comment of the captured image.
The character input support system according to claim 4. It also has a voice recognition server that converts voice data spoken during image display by the display unit into voice recognition text data.
The text data storage unit stores the voice recognition text data voice-recognized by the voice recognition server in association with the image data, and at the same time.
The voice recognition text data is displayed as at least one of the title and the comment of the image.
The character input support system according to claim 5. After being stored in the data storage server, the captured image captured by the imaging unit of the communication terminal device can be viewed in a state of being restricted to a specific communication terminal device for which permission has been obtained in advance.
The character input support system according to any one of claims 4 to 6. Equipped with a viewer function that lists the stored frames, with the display area where the image and text are set as one unit frame.
The character input support system according to any one of claims 4 to 7. Computer,
Operate as each part of the character input support control device according to any one of claims 1 to 3.
Character input support program.

Images