JPH11203400A - CHARACTER INPUT DEVICE, CHARACTER INPUT METHOD, AND MACHINE-READABLE RECORDING MEDIUM RECORDING PROGRAM FOR CAUSING COMPUTER TO EXECUTE CHARACTER INPUT METHOD - Google Patents

Abstract

(57) [Summary] [PROBLEM] To improve the efficiency of character editing by converting to the original character size at the time of input, realizing automatic input with a font having the same shape and size as the input original image. SOLUTION: A holding unit 10 holds data such as an address of an image image area of a display unit such as a word or a phrase from a character image image / OCR erroneously recognized portion and erroneous recognition information.
1 and a keyboard input unit 20 for instructing a character editing mode
2, a built-in font memory 204 for storing each character font information, a font extraction unit 203 for extracting font data corresponding to a character to be converted, data stored in the storage unit 101, and the extracted font data And a font comparison unit 205 that outputs the font data closest to the held data, and a comparison result holding unit 2 that holds the compared and output font data.
06 and a display unit 201 for displaying the stored data and the stored font data.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention is used in an OCR, a word processor, etc.
A character input device and a character input method capable of correcting a character image portion or a misrecognized portion in data of a CR recognition result by kana-kanji conversion, and a machine readable recording a program for causing a computer to execute the character input method It relates to a recording medium.

[0002]

2. Description of the Related Art Conventionally, in general, when a character image is converted into code data by OCR software or the like, the character image is once converted into a character size determined by a corresponding document,
The operator was making corrections as needed.

In the case of kana-kanji conversion after character input in character recognition by a word processor or OCR, the character type (font) and character size are changed collectively.

As a reference technical document incorporating font information, for example, Japanese Patent Application Laid-Open No. Hei 9-127229 discloses "Multi-font device and multi-font synthesizing method".
Is disclosed. This publication makes it possible to synthesize a new multi-font reflecting input sample data corresponding to a handwriting of a character input user.

[0005]

However, in the conventional technique as described above, when the character to be converted differs from the original character size at the time of input, the conversion is performed according to the original character size. As a result, the character shape and character size change, and the position of the character and the number of lines of the sentence are disturbed, and the original image becomes difficult to see. For this reason, there is a problem that the character editing work is reduced.

The present invention has been made in view of the above, and realizes automatic input with a font having the same shape and the same size as an input original image by converting to an original character size at the time of input. An object is to improve processing efficiency in editing.

[0007]

According to a first aspect of the present invention, there is provided a character input device, comprising: a character image portion; In a character input device for converting and correcting Chinese characters, a data holding means for holding data such as an address of an image image area of a display unit such as a word or a phrase or erroneous recognition information from the character image image or the OCR erroneously recognized portion, Input means for inputting a character edit mode, a font memory containing various character font information, font extracting means for extracting font data corresponding to a character to be converted from the font memory, and holding in the data holding means Of the font data and the font data extracted by the font extraction means A font comparing unit that outputs the font data closest to the data held in the data holding unit; a comparison result holding unit that holds the font data output by the font comparing unit; And display means for displaying the font data compared and held by the comparison result holding means.

That is, according to the character input device of the present invention (claim 1), it is possible to automatically input a font having the same character shape and character size as the input original image, thereby improving the processing efficiency at the time of character editing. I do.

According to a second aspect of the present invention, there is provided a character input method for correcting a character image portion or a misrecognized portion in a character image image or OCR recognition result data by converting the character into kana-kanji. A first step of retaining an address of an image image area of a display unit such as a word / segment or an erroneous recognition information from an erroneously recognized portion of an image image or an OCR recognition result; A second step of performing the data retained in the first step, a third step of extracting all font data that matches the data code of the input edit data, and a step of extracting the data retained in the first step. A fourth step of comparing all the extracted data and searching for the extracted data closest to the data held in the first step; A fifth step of judging a character shape and a character size from the search result in the fourth step and holding the comparison result together with the edited data; and a sixth step of displaying the data stored in the fifth step. , Is included.

That is, according to the character input method of the present invention (claim 2), it is possible to input a font having the same character shape and character size as the input original image, and the processing efficiency at the time of character editing is improved.

According to a third aspect of the present invention, there is provided a machine-readable recording medium on which a program for causing a computer to execute the character input method according to the second aspect is recorded.

That is, according to the machine-readable recording medium of the present invention (claim 3), a program for causing a computer to execute the character input method described in claim 2 is recorded, whereby the operation of claim 2 is performed. Can be realized by a computer.

[0013]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS A character input device and a character input method according to the present invention and a machine-readable recording medium storing a program for causing a computer to execute the character input method will be described in detail with reference to the accompanying drawings. .

(Structure of Embodiment) First, the structure of a character input device according to this embodiment will be described. FIG.
FIG. 3 is an explanatory diagram illustrating an example of an image and a holding state thereof according to the embodiment. In the figure, reference numeral 101 denotes a holding unit as data holding means for holding an address of a character image or an image image area of a display unit (word, phrase, etc.) from an erroneously recognized portion and erroneous recognition information.

FIG. 2 is a block diagram showing a system configuration of the character input device according to the embodiment. In the figure, 2
Reference numeral 01 denotes a display unit as a display unit for displaying data stored in the storage unit 101 (see FIG. 1), and 202 denotes a keyboard input as an input unit for performing various input instructions (for example, a character editing mode) by an operator. Department, 203
Is a font extracting unit as a font extracting means for extracting a character font stored in the built-in font memory 204 corresponding to the input specific character; 204 is a built-in font memory storing various character font information;
Reference numeral 20 denotes a font comparing unit as a font comparing unit for comparing data held in the holding unit 101 (see FIG. 1) with font data extracted by the font extracting unit 203;
Reference numeral 6 denotes a comparison result holding unit as a comparison result holding unit that holds data compared by the font comparison unit 205.

(Operation of the Embodiment) Next, the operation of the character input device configured as described above will be described with reference to the flowchart shown in FIG. When this operation is started, first, the address of the image image area of the display unit (word, phrase, etc.) and the misrecognition information are linked to the holding unit 101 from the character image or the OCR misrecognition location (S301). This linked data is referred to as data 1.

Subsequently, it is determined whether or not an instruction to enter the character editing mode has been issued by the operator via the keyboard input unit 202 (S302). If it is determined that an instruction to enter the character editing mode has been issued by the operator, the data 1 is displayed on the display unit 201 (S30).
3).

Next, the editing data is input from the keyboard input unit 202 by the operator (S304). Further, the font extraction unit 203 extracts all the font data in the built-in font memory 204 that matches the data code of the edit data (S305). The extracted data is referred to as data 2.

Subsequently, the font comparing unit 205 compares all of the data 1 and the data 2 and finds the data 2 closest to the data 1 (the data stored in the holding unit 101).
Is searched (S306). Further, in step S30
Judge the character shape and character size from the search result in step 6,
It is stored in the comparison result holding unit 206 together with the edited data (S
307). This stored data is referred to as data 3. Then, the data 3 is displayed on the display unit 201 (S30).
8).

As a result, font data having the same character shape and character size is automatically input to the input original image, so that the efficiency of editing work is improved.

The present invention can be realized by software other than the above-described embodiment. FIG. 4 shows a configuration example of a computer system when the present invention is realized by software.

In FIG. 4, reference numeral 401 denotes a CPU for controlling the entire apparatus based on a control program; 402, a ROM in which the control program is stored; 403, a RAM used as a work memory, for example; A display device for displaying a state or the like; 405, a hard disk; 406, a keyboard used to input a character string to be recognized; and 407, a CD-RO
A CD-ROM drive 408 for driving M is a CD-ROM as a computer-readable recording medium, in which a program for realizing the character input method of the present invention is recorded.

In the computer system configured as described above, a program for realizing the character input method of the present invention is recorded on the CD-ROM 408. CPU40
1, the above program is read, and when the program is started, the input data is stored in the hard disk 405 or the R.
It is read from the AM 403, executes the same character input processing as described above, and outputs the result to the display device 404 or the like.

[0024]

As described above, according to the character input device of the present invention (claim 1), it is possible to automatically input a font having the same character shape and character size as the input original image. Processing efficiency during editing is improved.

Further, according to the character input method of the present invention (claim 2), it is possible to input a font having the same character shape and character size as the input original image, thereby improving the processing efficiency at the time of character editing. .

According to a third aspect of the present invention, there is provided a computer-readable recording medium storing a program for causing a computer to execute the character input method according to the second aspect. The operation can be realized by a computer.

[Brief description of the drawings]

FIG. 1 is an explanatory diagram showing an example of an image image according to an embodiment and a holding state thereof.

FIG. 2 is a block diagram showing a system configuration of the character input device according to the embodiment.

FIG. 3 is a flowchart showing a character input method according to the embodiment.

FIG. 4 is a block diagram illustrating a configuration example of a computer system according to the embodiment.

[Explanation of symbols]

 Reference Signs List 101 holding unit 201 display unit 202 keyboard input unit 203 font extraction unit 204 built-in font memory 205 font comparison unit 206 comparison result holding unit

Claims (3)

[Claims] 1. A character input device for correcting a character image portion or an erroneously recognized portion in data of a character image image or an OCR recognition result by converting the character image image or the OCR erroneously recognized portion into a word, a phrase or the like. A data holding unit for holding data such as an address of an image area of a display unit and misrecognition information, an input unit for inputting at least a character editing mode, a font memory containing various character font information, and a A font extracting unit for extracting font data corresponding to a character from the font memory, and comparing the data held in the data holding unit with the font data extracted by the font extracting unit, and holding the data in the data holding unit. Output the font data closest to the data Font comparing means, font data output by the font comparing means, and data stored in the data storing means and font data compared and stored by the comparing result storing means are displayed. A character input device comprising: 2. A character input method for correcting a character image portion or an erroneously recognized portion in data of a character image image or an OCR recognition result by kana-kanji conversion to correct a word / word from the erroneously recognized portion of the character image image or the OCR recognition result. A first step of holding the address of the image area of the display unit such as a phrase and misrecognition information, and a second step of, when an instruction to enter the character editing mode is issued, the data held in the first step. And a third step of extracting all font data that matches the data code of the input edit data; and comparing all the data held in the first step with the extracted data to obtain the first data. A fourth step of searching for the extracted data closest to the data held in the step, and a character shape and a character based on the search result in the fourth step. A character input method, comprising: a fifth step of judging a size and holding a comparison result together with the edited data; and a sixth step of displaying data stored in the fifth step. 3. A machine-readable recording medium on which a program for causing a computer to execute the character input method according to claim 2 is recorded.