JP2000123112A - Character processor and character data processing method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To easily improve the character recognition ratio. SOLUTION: A range key is pushed (S1), a memory area is cleared (S2) and the current pointer coordinates are updated and displayed at an operating part when a cursor key is pushed (S5→S6→S7). Then a confirmation key is pushed and the current coordinates are set at the 1st coordinates if the 1st coordinates are not inputted yet (S8, S9 to S10). If the 1st coordinates are already inputted, the current coordinates are set at the 2nd coordinates and these set recognition ranges are written into an image buffer (S9, S11 to S12). Then a start key is pushed to start the copy processing (S3, S4 to S13).

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

The present invention relates to a character processing device and a method of processing character data, and more particularly to a character processing device such as a copying device that recognizes character data and a method of processing character data.

[0002]

2. Description of the Related Art With the improvement of computer technology and semiconductor technology in recent years, character data can be recognized by substantially real-time processing at about the copying speed used in low-speed copying machines. Further, in recent years, since a copy original to be copied is created by a document creation device such as a word processor or a personal computer, the recognition accuracy of the copy original has been improved, and practically, there is almost no problem. I have. Furthermore, a technique for recognizing a character size or character image data in a document, converting the character size or character image data into font image data and reproducing the same to prevent image deterioration even when copying operation is repeated. Has also been developed.

[0003]

However, in the above-mentioned prior art, although the character recognition has reached the practical level as described above, it is difficult to distinguish between similar characters, and for this reason, certain characters are recognized. In some cases, unrecognizable characters may remain, or the character recognition result may not be specified due to the presence of a plurality of candidate characters in character recognition. In such a case, conventionally, characters for which character recognition was not possible are processed as bitmap data of character data, so that there is a problem that image deterioration occurs when the copying operation is repeated.

The present invention has been made in view of such circumstances, and has as its object to provide a character processing apparatus and a character data processing method capable of easily improving the recognition rate of character recognition.

[0005]

In order to achieve the above object, a character processing apparatus according to the present invention comprises an image reading means for reading an original image, and character data in the original image read by the image reading means. Recognition range setting means for setting a recognition range, storage means for storing the recognition range set by the recognition range setting means, and recognition processing executing means for performing character recognition processing on the recognition range stored in the storage means And an output unit that outputs an execution result of the recognition processing execution unit.

According to the character data processing method of the present invention, a document image is read, a recognition range is set for character data in the document image, the set recognition range is stored, and then the stored recognition range is stored. It is characterized in that character recognition processing is performed on the recognition range and the execution result is output.

[0007] Other features of the present invention will be apparent from the following description of embodiments of the invention.

[0008]

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

FIG. 1 is a view showing the internal structure of a digital copying machine as a character processing apparatus according to an embodiment of the present invention. The operation unit 3 is buried in an appropriate position on the upper surface of the copying apparatus main body 2.

Thus, in the copying apparatus main body 2, the document illumination lamp 4 irradiates the document placed on the platen glass 5 as a document table while scanning perpendicularly to the longitudinal direction. The scattered light from the document due to the irradiation of the document illumination lamp 4 is reflected by the first to third mirrors 6 to 8,
To reach. At this time, the movable body 10 composed of the second mirror 7 and the third mirror 8
1 for scanning by the scanner 11 composed of
The lens 9 moves at a speed of / 2 and the distance from the document surface illuminated by the document illumination lamp 4 to the lens 9 is always kept constant. Then, the character data (original image) on the original paper
Forms an image on the light receiving portion of the image sensor 12 through the first to third mirrors 6 to 8 and the lens 9, and is sequentially photoelectrically converted by the image sensor 12 in line units. The image signal photoelectrically converted in this manner is subjected to signal processing in the image control unit 13, and is subjected to PWM (Pulse-Width Modulation).
lation) Modulated and output.

The exposure unit 14 is composed of a semiconductor laser, a polygon scanner, or the like.
The photosensitive drum 16 is irradiated with a laser beam 15 based on the WM-modulated image signal. At this time, the laser beam 15 is scanned in parallel with the axial direction of the photosensitive drum 16. Then, the photosensitive drum 16 receives the laser beam 15 while rotating, and an electrostatic latent image is formed on the surface thereof.
With a and 17b, visualization is performed with a developer (toner) of a predetermined color. The residual toner on the photosensitive drum 16 is cleaned by the cleaner device 18 before the laser beam 15 is irradiated, the remaining charge on the photosensitive drum 16 is removed by the pre-exposure lamp 19, and the primary charger 20 Photoconductor drum 1
6 is uniformly charged.

Reference numerals 21 and 22 denote detachable paper cassettes (upper cassette 21 and lower cassette 22), in which recording paper of a predetermined size is loaded and stored. The pickup rollers 23 and 24 lift the recording paper to the position of the pair of paper feed rollers 25 and 26 when the paper feed cassettes 21 and 22 are stored in the apparatus. Further, the paper feed roller pair 25, 26
Is driven by a motor (not shown) to select one of the sheet cassettes 21 and 22 to be fed.
In addition, torque is applied to one of the pair of paper feed rollers 25 and 26 in the direction opposite to the paper feed direction to prevent double feeding.

The transport roller pairs 27 and 28 transport the recording paper from the paper feed cassettes 21 and 22 to the registration roller pair 29. Then, the registration roller pair 29 feeds the recording paper so that the leading end of the character data formed on the photosensitive drum 16 and the leading end of the recording paper coincide.

Reference numeral 30 denotes a transfer / separation charger, which transfers the toner image developed on the photosensitive drum 16 to a recording sheet and then separates the recording sheet from the photosensitive drum 16.

The recording paper separated from the photosensitive drum 16 in this way is conveyed to a fixing section 32 via a conveyor belt 31, pressed and heated by the fixing section 32, and supplied to a conveying roller 33.

The first directional flapper 34 switches the recording paper conveyance direction according to the operation mode. That is, the recording sheet sent from the transport roller 33 is switched by the first directional flapper 34 to a recording mode (double-sided recording mode, multiplex recording mode) or a discharge mode.

If the recording paper is to be discharged without reversing when the paper discharge mode is set,
The recording paper is stacked and discharged from a discharge roller pair 35 to a paper discharge tray (not shown) via a first directional flapper 34. When the recording paper is to be inverted and discharged, the first directional flapper 34 is raised upward, the second directional flapper 36 is tilted rightward, and the recording paper is stacked and discharged from the discharge roller pair 35 to the discharge tray.

When the recording mode is set, the first directional flapper 34 is raised upward, and the recording paper on which the character data is formed is supplied to the re-feed tray 38 via the transport path 37. You. In this case, the second directional flapper 36 is switched between the double-sided recording mode and the multiple recording mode, and the recording sheets contained in the re-feeding tray 38 are fed one by one from the bottom by the sheet feeding roller pair 39 to the transport path 40. Is supplied to the registration roller pair 29 through

In this embodiment, a monochrome copying machine has been described. However, the present invention can be similarly applied to a color copying machine, and a color output or a monochrome output may be set according to a distribution destination.

FIG. 2 is a plan view of a main part of the operation unit 3.

Referring to FIG.
Is operated when performing character recognition, which will be described later, when copying, and the normal copy mode key 42 is operated when performing normal copying without performing character recognition processing. The recognition copy mode key 41 and the normal copy mode key 42 constitute a mode switching setting unit 43.

The display section 45 is an LCD (liquid crystal display).
For example, when the recognition copy mode is set, a character to be corrected or a character located around the correction target character is displayed in order to correct an uncertain character, and the normal copy mode is set. When it is present, the number of copies, the copy magnification, the copy paper size, and the like designated by a setting key group (not shown) are displayed.

The range key 46 is operated to specify a range for performing recognition copying when the recognition copying mode is set.

The up cursor key 47 is operated to display the upper character of a plurality of candidate characters on the screen for correcting an uncertain character when the recognition copy mode is set. The down cursor key 48 is operated when lower characters of a plurality of candidate characters are displayed on the correction screen for the uncertain character. The right cursor key 49 is used to move the character to be corrected to the next character in the lower right direction to display the next character when the original is horizontally written on the indeterminate character correction screen. In the case of, the character to be corrected is moved to the previous character in the upper right direction to operate the previous character. The left cursor key 50 moves the character to be corrected to the previous character in the upper left direction to display the previous character when the original is horizontal writing on the correction screen of the uncertain character,
When the original is a vertical document, the operation is performed when the character to be corrected is moved to the previous character in the lower left direction to display the previous character.

The confirmation key 51 is operated when the character to be corrected is determined by the currently displayed character.
The start key 52 is operated when a copy operation is commanded to the apparatus main body 2.

FIG. 3 is a block diagram showing a control system of the character processing apparatus according to the present invention. The character processing apparatus includes an image reading section 54 for reading an original image 53, and an image reading section 54. An image processing unit 55 for performing predetermined image processing on the character data read by the image processing unit 55; an image recording unit 56 for recording the character data processed by the image processing unit 55; An image recognizing unit 57 for performing recognition processing on character data, an image buffer 59 for temporarily storing a recognition result of the image recognizing unit 57, the operation unit 3 for performing a mode switching command, and the like; And a CPU 60 for controlling the entire apparatus.

The image reading section 54 includes a lens 61 into which an optical signal from the original image 53 enters, and a lens 6.
An image sensor 62 composed of a CCD which forms an optical signal transmitted through the CCD 1 and converts the optical signal into an electric signal, and an A / A which converts an analog electric signal output from the image sensor 62 into a digital electric signal. And a D converter 63.

The image processing unit 55 also has a shading correction unit 64 for performing shading correction on the electric signal output from the A / D converter 63 and a shading correction unit 64 according to the input result to the mode switching setting unit 43 of the operation unit 3. A mode switching unit 65 for switching the mode of the electric signal output from the shading correction unit 64; a light density conversion unit 66 for converting luminance data into recording data;
And an image editing section 67 for editing character data based on a command from the CPU 60 in response to an output signal from the CPU.

Further, the image recognizing section 57 includes a pattern recognizing section 68 for recognizing a character pattern in the character data,
A character recognizing unit 69 for generating a character code based on the character pattern recognized by the pattern recognizing unit 68; a pointer display processing unit 70 for displaying a correction target character (pointer); An image data conversion unit that converts a character code into image data based on the recognition result;

The CPU 60 has a ROM 72 in which a control program such as a character recognition processing program is stored.
It incorporates a RAM 73 that temporarily stores the calculation results and is used as a work area.

In the character processing apparatus thus constructed, the original image 53 is imaged by the image sensor 62 via the lens 61, and is photoelectrically converted by the image sensor 62 into an electric signal. Then, the photoelectrically converted image signal (electric signal) is converted into a digital signal by the A / D converter 63, subjected to shading correction by the shading correction unit 64, and input to the mode switching unit 65.

The mode switching unit 65 switches the mode between the recognition copying mode and the normal copying mode as necessary according to the input result to the mode switching setting unit 43 of the operation unit 3.

When the normal copy mode is set by the operation unit 3, the luminance data from the shading correction unit 64 is converted into recording data by the light density conversion unit 66, and then output to the image editing unit 67.

The image editing section 67 performs editing processing according to the processing contents of the image processing stored in the RAM 73,
The edited character data is output to the image recording unit 56,
Next, a series of recording operations such as exposure, exposure, and fixing are performed by the image recording unit 56, and character data is recorded on recording paper.

On the other hand, when the recognition copy mode is set by the operation section 3, the pattern recognition section 68 performs pattern recognition. In other words, areas such as a pattern for re-inputting unrecognizable characters, option patterns of a plurality of candidates, and marking of a display request for a plurality of candidates are recognized.

The character recognizing section 69 stores a dictionary for character recognition. The character recognizing section 69 cuts out an image (character pattern) for one character from the input character data and performs character recognition. Do. The character recognition unit 6
The recognition result recognized in step 9 is stored in the image buffer 59 and supplied to the image data conversion unit 71, where the character code is converted into an output image, and the output image is stored in the image buffer 59. In this case, the image buffer 59
For an unrecognizable character, the image information is stored as it is, and for a character having a plurality of candidates, a plurality of character code information is stored in the order of higher recognition rate. When correcting an uncertain character, the pointer display processing unit 70 adds on a pointer image which is a correction target character, and
Is processed to be displayed on the display unit 45.

The output image converted by the image data conversion unit 71 is sent to the image recording unit 5 via the image editing unit 67.
6 and the character data is output on recording paper.

FIG. 4 is a flowchart showing a first embodiment of the processing procedure for character data in the character processing apparatus. This processing procedure is processed by the image recognition section 57 under the control of the CPU 60. In this embodiment, it is assumed that the document image is composed of vertical writing.

In step S1, it is determined whether or not the range key 46 of the operation unit 3 has been pressed to specify the recognition range. If the range key 46 has been pressed, the memory area of the image buffer 59 in which the recognition range information is stored. Is cleared, a desired key input is performed (step S3), and it is determined whether or not the input key is the start key 52 (step S4). If it is determined that the input key is not the start key 52, it is determined whether or not the cursor keys 47 to 50 have been pressed (step S5). When it is determined that the cursor keys 47 to 50 have been pressed, the pointer coordinates indicating the current coordinates are updated (step S6).
The pointer coordinates are displayed on the display unit 45 (step S7),
It returns to step S3.

If the answer in step S5 is negative (No),
That is, when it is determined that the cursor keys 47 to 50 have not been pressed, the process proceeds to step S8, and it is determined whether the confirmation key 51 has been pressed. When it is determined that the confirmation key 51 has been pressed, a character recognition range setting operation is performed.

That is, first, the process proceeds to step S9, and FIG.
As shown in (1), it is determined whether or not the upper left end coordinate of the recognition range for performing character recognition (hereinafter, the upper left end coordinate is referred to as “first coordinate”) is input. If the first coordinates have not been input yet, the current coordinates are set to the first coordinates (X1, Y1), and the process returns to step S3.

On the other hand, the answer to step S9 is affirmative (Yes).
, That is, when the first coordinates (X1, Y1) have been input, the current coordinates are changed to the second coordinates (X
2, Y2) (see FIG. 7). Thus, the first coordinates (X1, Y1) and the second coordinates (X2, Y1)
The character recognition range of the rectangular shape is designated by 2), these information are written in the image buffer 59, and the process returns to step S3.

When the range in which the character recognition is to be performed is designated in this way, the start key 52 is pressed, so that the answer in step S4 becomes affirmative (Yes), and the flow advances to step S13 to execute the copying process. The process ends.

If it is determined in step S1 that the range key 46 has not been pressed, the flow immediately proceeds to step S13 to execute the copying process, and ends the process.

FIG. 5 is a flowchart of the copy processing routine executed in step S13.

That is, in step S21, the character direction of the document is determined from the input character data based on the presence or absence of an image in the vertical direction (for example, a histogram), and the line width h of the character line is calculated.

Next, character patterns are cut out according to the presence or absence of a horizontal image (for example, a histogram) for each of the calculated character lines, and the character width W of each character pattern is extracted.
(I) and the position coordinates x (i) of the character are stored in the RAM 73.

Next, in step S23, the character width W
(I) The standard character width W is calculated based on the line width h and the like. That is, the character width W (i) that satisfies Expression (1)
Is calculated, and the standard character width W is calculated by simply averaging the character width W (i).

H−Δa ≦ W (i) ≦ h + Δa (1) where Δa is a predetermined allowable value for the row width h.

Next, in step S24, the character width W (i)
It is determined whether or not the character pattern having satisfies Expression (2).

W + Δb <W (i) (2) where Δb is a predetermined allowable value of the standard character width W.

Then, the answer to step S24 is affirmative (Ye).
s), that is, the character width W that satisfies Expression (2)
If it is determined that there is a character pattern having the character pattern (i), the process proceeds to step S25 to include a character pattern having a standard character width W before and after the character pattern, that is, including a character pattern satisfying Expression (2). In addition, a histogram is created by projecting a character pattern sandwiched between character patterns having a standard character width W closest to the character pattern in the X-axis direction (horizontal direction).

Next, in step S26, the coordinate position on the horizontal axis is x, the number of dots on the vertical axis is y, a threshold value z is set for the dot number y, and the minimum position of the character pattern number i is set as (x = 0), a coordinate position x near the standard character width W and smaller than the threshold value z is obtained.

When the interval between the coordinate positions is Δx, the middle of the process of obtaining the coordinate position x is cut off by a substantially standard character width W,
Moreover, when the last cut width is substantially the standard character width W, the answer in step S26 is affirmative (Yes), and the obtained coordinate position x
In step S28, the process proceeds to step S28 to execute the character recognition process.

If it is determined that there is no coordinate position x that satisfies step S26, that is, if a break cannot be found in the vicinity of the standard character width W while the coordinate position x is being obtained, or if the cut has been completed to the end. If the character width w (i) having the last character pattern does not satisfy Expression (2), the process proceeds to step S28 to immediately execute the character recognition process.

FIG. 6 is a flowchart of the character recognition processing routine executed in step S28.

In step S31, character recognition is performed, and in subsequent step S32, it is determined whether or not the character has been determined.
When the character is determined, the process proceeds to step S33,
After storing the character code in the image buffer 59, in step S34, the character code is converted into image data.
In step S35, the image data is stored in the image buffer 59.
And the process ends.

On the other hand, if it is determined in step S32 that the character has not been determined, the flow advances to step S36 to determine whether there are a plurality of candidate characters for determining the character. If it is determined that there are a plurality of candidate characters, the process proceeds to step S37, where the character codes of the plurality of candidate characters are stored in the image buffer 59, and then in step S38, the first one of the plurality of candidate characters is selected from among the plurality of candidate characters. A candidate character is selected and the first candidate character is converted into image data. Then, in step S39, a pointer indicating uncertainty is added,
After storing the first candidate image data in the image buffer 59, the process ends.

If it is determined in step S36 that there is no candidate character, the process proceeds to step S40, where the character code of a specific mark (for example,?) Indicating an unknown character is stored in the image buffer 59. In S41, the image range of the uncertain character is read and converted into image data, the image data is stored in the image buffer 59, and the process is terminated.

The above processing is repeated by the number of characters to generate one page of character code data and output character data, and output the output character data to recording paper.

As described above, in the present embodiment, the recognition rate is improved by performing the character recognition by designating the range in which the character is to be recognized. Can be obtained.

Further, a desired reproduced image can be obtained without giving any image deterioration due to erroneous recognition of characters to a graphic region or a photograph region outside the range specified as the recognition range in the same document.

Although the first embodiment has been described with respect to a horizontally written document image, when the text to be recognized is a vertically written document image, the “character width” in FIG. 5 is changed to the “character height”.
Thus, the same can be applied.

FIG. 8 is a flowchart showing a second embodiment of the character data processing procedure in the character processing apparatus. In the second embodiment, character recognition is performed using a digitizer.

As in the first embodiment, step S
At 51, it is determined whether or not the range key 46 of the operation unit 3 has been pressed.
At 52, the memory area of the image buffer 59 where the recognition range information is stored is cleared.

Next, in step S53, an input operation is performed on the digitizer. Then, in step S54, it is determined whether or not coordinates have been input to the digitizer. If coordinates have been input, the pointer coordinates specified by the digitizer are displayed in step S55. Then, in step S56, the first coordinates (character recognition range) It is determined whether or not the (upper left corner coordinate) has already been input. If it is determined that the first coordinates have not been input yet, the current coordinates are set to the first coordinates in step S57, and the process returns to step S53. On the other hand, if it is determined in step S56 that the first coordinates have already been input, the flow advances to step S58 to set the current coordinates input to the digitizer to the second coordinates,
The portion corresponding to the range specified in step S59 is written in the image buffer 59, and the process returns to step S3.

Then, after the range in which character recognition is performed is determined, the answer to step S60 is negative (No), and a desired key input is performed in step S60. Then
In step S61, the input key is the start key 52
If it is determined that the input key is not the start key 52, the process returns to step S3,
If it is determined in step S61 that the start key 52 has been pressed, the flow advances to step S62 to execute the above-described copying processing (FIGS. 5 and 6), and ends the processing.

If it is determined in step S51 that the range key 46 has not been depressed, the process immediately proceeds to step S62 to execute the copying process, similarly to the first embodiment, and terminates the process.

As described above, in the case of performing character recognition using a digitizer, the recognition rate of character recognition can be improved by specifying the range in which character recognition is performed, as in the first embodiment. It is possible to obtain a character processing device in which more accurate character recognition is performed.

FIG. 9 is a plan view of a main part of an operation unit 3 according to a third embodiment of the present character processing apparatus. The operation unit 3 includes numeral keys 74, alphabetic keys 75, kanji keys 76, A character type setting key group 79 including a key 77 and a photo key 79
Are provided to perform a character recognition process according to the character type. That is, for example, alphabet key 7
5 is selected to form an alphabetic area 80 and perform recognition processing for alphabetic characters, while the numeric key 74 is selected to form a numeric area 81 and perform recognition processing for numbers.

FIG. 10 is a flowchart showing a procedure for processing character data according to the third embodiment.

In steps S1 to S10, the same processing as in the first embodiment is performed. On the other hand, if it is determined in step S8 that the confirmation key 51 has not been pressed, the flow advances to step S71 to proceed to the character type setting key group. It is determined whether any one of the keys 79 has been pressed. And
When the answer is negative (No), the process returns to step S3, and when the answer is affirmative (Yes), the process proceeds to step S72, and the recognition process is performed according to the type of the pressed character type setting key group 79. The character type is set, and the process returns to step S3.

Then, when the confirmation key 51 is depressed, a process of defining the recognition range by the first coordinates and the second coordinates is executed as in the first embodiment (step S9).
After that, the start key 52 is depressed, and the copying process is executed.

As described above, in the third embodiment, since the character recognition process is performed by specifying the character type to be recognized, for example, the numeral 1 (Ichi) and the alphabetical character I (Ai) or Character recognition can be performed without being confused with 1 (lowercase ell).

[0075]

As described above in detail, according to the present invention, a character processing apparatus capable of performing more accurate character recognition by specifying a range in which character recognition is performed and improving the recognition rate of character recognition. Obtainable.

Moreover, a desired reproduced image can be obtained without deteriorating the image due to erroneous character recognition in an area outside the range specified as the recognition range in the same document.

Further, by performing a character recognition process by specifying a character type to be recognized, for example, the numeral 1
Character recognition can be performed without confusing (ichi) with the alphabetic characters I (eye) and l (lowercase ell).

[Brief description of the drawings]

FIG. 1 is an internal structural diagram showing an embodiment of a digital copying machine as a character processing device according to the present invention.

FIG. 2 is a plan view of a main part of an operation unit.

FIG. 3 is a block diagram showing a control system of the character processing apparatus.

FIG. 4 is a flowchart showing a first embodiment of a character data processing method according to the present invention.

FIG. 5 is a flowchart of a copy processing routine.

FIG. 6 is a flowchart of a character recognition processing routine.

FIG. 7 is a plan view of a main part of an operation unit in a recognition copying mode.

FIG. 8 is a flowchart illustrating a character data processing method according to a second embodiment of the present invention.

FIG. 9 is a plan view of a main part of an operation unit according to a third embodiment of the present invention.

FIG. 10 is a flowchart showing a third embodiment of the character data processing method according to the present invention.

[Explanation of symbols]

56 Image recording unit (output unit) 59 Image buffer (storage unit) 69 Character recognition unit (character data identification unit, character recognition execution unit, recognition range setting unit)

 ──────────────────────────────────────────────────続 き Continuing on the front page (72) Inventor Makoto Kobayashi 3-30-2 Shimomaruko, Ota-ku, Tokyo Inside Canon Inc. (72) Inventor Junnosuke Kataoka 3- 30-2 Shimomaruko, Ota-ku, Tokyo Canon Incorporated (72) Inventor Izumi Horiuchi 3-30-2 Shimomaruko, Ota-ku, Tokyo F-term in Canon Inc. (reference) 2C087 AA09 AB01 AC08 BA05 BB10 BD13 BD14 CB16 5B029 AA01 BB02 CC22 CC25 5C076 AA01 AA13 AA16 BA03 CA02 CA04 CA10

Claims (12)

[Claims] An image reading unit that reads an original image; a recognition range setting unit that sets a recognition range for character data in the original image read by the image reading unit; Storage means for storing a recognition range; recognition processing executing means for performing character recognition processing on the recognition range stored in the storage means; and output means for outputting an execution result of the recognition processing executing means. A character processing device characterized by the above-mentioned. 2. The character processing apparatus according to claim 1, wherein the setting of the recognition range by said recognition range setting means is performed on a display screen. 3. The character processing apparatus according to claim 1, wherein the setting of the recognition range by said recognition range setting means is performed using a digitizer. 4. The character processing device according to claim 1, wherein the character recognition executing unit executes the character recognition in accordance with a character type. 5. The character processing device according to claim 4, wherein the character type is at least one of an alphabetic character, a Chinese character, and a number, or a combination thereof. 6. The recognition processing executing means converts character data in a document image into a predetermined character code, and the output means converts the character code into image data and outputs the image data. The character processing device according to claim 1. 7. A document image is read, a recognition range is set for character data in the document image, the set recognition range is stored, and then a character recognition process is performed on the stored recognition range. And outputting the execution result. 8. The method according to claim 7, wherein the setting of the recognition range is performed on a display screen. 9. The method according to claim 6, wherein the setting of the recognition range is performed using a digitizer. 10. The character data processing method according to claim 7, wherein the character recognition processing is executed according to a character type. 11. The method according to claim 10, wherein the character type is at least one of an alphabetic character, a kanji character, and a number, or a combination thereof. 12. The apparatus according to claim 7, wherein the character data in the document image is converted into a predetermined character code, and the character code is converted into image data and output.
A method for processing character data according to any one of claims 11 to 11.