JP2003046746A - Method and apparatus for processing image - Google Patents

Abstract

PROBLEM TO BE SOLVED: To solve the problem, in order to obtain an electronic form based on a printed document, of the need to first read the document by a scanner and to replace a character part with a background pixel, which has been a considerably difficult work. SOLUTION: A method for processing an image comprises the steps of inputting multi-valued original image data 101, based on a document image formed on a recording medium, binarizing the data using a binarizing unit 102, laying out the binarized image, and analyzing the image by a layout analyzer 104. The method further comprises the steps of solidly coating the character part of the image data by its peripheral color, based on a character region information and the binarized image data as a layout analyzed result in a character solid coating part 105, and thereby to form a first electronic form.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image processing apparatus and a method thereof, and more particularly to an image processing method and an image processing apparatus for creating an electronic form based on a print document.

[0002]

2. Description of the Related Art In recent years, document creation technology using electronic forms and electronic fixed forms has become widespread. For example, in a system for electronic ordering on the Web via the Internet, the user can make an electronic form satisfying other formats by performing the minimum necessary input, and further, if necessary, a laid-out form. An increasing number of systems are providing printing processes.

Alternatively, even when using so-called document creation software such as Microsoft Word, by using a standard form as a template for the format of a document and inserting one's own text in the standard form. It has become commonplace to create desired documents.

As described above, there is a great need for automatic creation processing of electronic forms in order to eliminate the need for the user to prepare the document format.

[0005]

Since the work of creating an electronic form is generally complicated, an already created form is often used. However, the existing form does not always exactly match what the user desires, and there is a considerable need to change the form.

For example, when the background image of an existing form is modified to a desired image, a great number of work steps are required. Therefore, there has been a demand for using a general print document as the background of the form.

Further, when there is only a printed matter of an electronic form created by the electronic form creating application, there is a demand to obtain electronic data (electronic form data) forming the front frame portion of the form.

However, in order to obtain an electronic form based on a document printed on a recording medium, first, the document is read by a scanner to form image data, and then unnecessary portions are deleted from the obtained image data. There is a need to.

Here, a character portion is often used as an unnecessary portion in forming an electronic form. In general,
The character part is important in the document, but when the document is to be converted into an electronic form, the character part is unnecessary, and rather, the background, the line, the drawing, and the like are to be reused.

In order to delete only the character part from the document image data, the character part is replaced with the pixel corresponding to the background image, but this work is usually done manually. Therefore, for example, when the background is a halftone image or the like, deleting only the character portion from the background image becomes a very difficult task.

The present invention has been made to solve the above problems, and an object of the present invention is to provide an image processing apparatus and a method thereof that can easily create an electronic form based on a printed document.

[0012]

As one means for achieving the above object, the image processing method of the present invention comprises the following steps.

That is, an image processing method for creating an electronic form based on a document image formed on a recording medium, the image inputting step of inputting multi-valued image data based on the document image formed on the recording medium. A binarizing step of binarizing the multi-valued image data to generate binary image data; an analyzing step of analyzing a layout of the document image based on the binary image data; a layout analysis result; A character filling step of creating a first electronic form by filling a character portion in the multi-valued image data with its surrounding color based on the binary image data;
It is characterized by having.

Further, based on the layout analysis result, a first form displaying step of displaying the first electronic form by marking its line area, and an arbitrary line on the displayed first electronic form. A selection step of selecting a region based on a user instruction, a vectorization process of creating line vector information by vectorizing a line portion in the selected line region, the layout analysis result and the binary image data A line filling step of creating background image data by filling a line portion in the first electronic form with its surrounding color, based on the line vector information and the background image data.
The electronic form of

Further, a table area filling step of filling the table area in the second electronic form composed of the line vector information and the background image data with a color similar to the background color, and the image data after the table area filling. A background deletion step of creating a third electronic form by deleting the background image data from the background image data, and the line vector information forming the table area in the third electronic form is the background color information. It is characterized by having.

[0016]

BEST MODE FOR CARRYING OUT THE INVENTION An embodiment of the present invention will be described in detail below with reference to the drawings.

<First Embodiment> Device Configuration FIG. 1 is a diagram showing a block configuration of an image processing device according to the present embodiment.

In the figure, 101 is an original image. 1
Reference numeral 02 denotes a binarization unit that performs optimal binarization on the original image 101, and outputs a binary image 103. A layout analysis unit 104 analyzes the layout of the binary image 103, and outputs a layout analysis result 108 including the character area coordinates of the detected character area.

Reference numeral 105 denotes a character filling section, which refers to the detected character area coordinates, deletes the black area in the binary image data 103 from the original image data 101, and fills it with the surrounding color so that the character is The erased image data A is created. This image A is the primary electronic form.

Then, the primary electronic form is reduced by the reduction unit 106.
Then, the reduced image data B is reduced to generate the reduced image data B, and the JPEG compression unit 107 further performs JPEG compression to generate the compression code X109 of the primary electronic form.

In the present embodiment, with the above configuration,
A character area is detected from the original image 101, and only the character in the character area is erased to leave only the base image. The base image is used as an electronic form (primary electronic form: corresponding to image data A), and its compression code X109 is registered.

The process of creating the primary electronic form in this embodiment will be described in detail below.

Character Area Detection Processing FIG. 2 is a flowchart showing the character area detection processing in this embodiment, which corresponds to the processing executed by the binarization unit 102 to the layout analysis unit 104 having the above-described configuration.

First, in step S201, the color original image 101 is input, and the luminance image is converted while thinning it to reduce the resolution, and a luminance image J is created. For example, if the original image 101 is composed of RGB components and has data of 8 bits and 300 dpi, Y = 0.299R + 0.587G + 0.114B is calculated for every 4 pixels in the vertical and horizontal directions to obtain a new image. When J is created, the image J is obtained as Y8 bit 75 dpi image data.

Then, in step S202, the brightness histogram of the image J is taken to calculate a binarization threshold value T, and in step S203, the brightness image J is binarized with the threshold value T, so that the binary image K A value image 103) is created.

Next, in step S204, all the black areas are labeled by tracing the contour lines of the black pixels in the binary image K. Then, in step S205, a character-like area is determined from the black area, and step S20
At 6, the black areas to be combined are combined based on the shape and position of the character-like areas.

A specific example of the character area detecting process shown in FIG. 2 will be described below. When the color image shown in FIG. 3 is used as the original image 101, the luminance histogram of the image J obtained by thinning and converting the original image 101 is as shown in FIG. A binarization threshold T = 150 is calculated based on the average, variance, etc. of the histogram, and binarization based on the threshold T yields a binary image K (binary image 103) as shown in FIG.

For the binary image K shown in FIG. 5, contour lines of black pixels are traced, all of them are labeled, and a set of black pixels whose width or height is equal to or smaller than a predetermined threshold is a character. A group of black pixels shown in 6 is determined as a character area. However, the example shown in FIG. 6 merely shows the concept of the character area, and such an image is not actually created. Then, if necessary, the group of black pixels shown in FIG. 6 is grouped based on various conditions such as the distance, width, and / or height matching, so that the 17 character regions shown in FIG. 701 to 718 are detected. The coordinate data of these character areas are held in a RAM or the like (not shown) in the device as character area coordinates.

Character Part Filling Process Hereinafter, with respect to the process in the character filling unit 105,
This will be described with reference to the specific example of FIG. 8 and the flowchart of FIG.

Assuming that the original image 101 is shown in FIG. 8A, in the process of detecting the character area for the original image, the whole binary image 103 including one character area as shown in FIG. 8B. Has been obtained.

Character filling processing of this embodiment (FIG. 9)
In step 1, the original image is divided into 32 × 32 pixel regions (hereinafter referred to as parts) (S901), and processing is performed for each part. FIG. 8C shows how the original image 101 is divided into parts.

The character parts are not included in the six parts "00" to "10" shown in FIG. 8C, so that no processing is performed by the branch in step S903, and "1" is set.
The process is step S904 at the time of processing the “1” part.
Proceed to. Whether or not the part includes a character area is determined based on the character area coordinates held as the layout analysis result 108.

In step S904, in the binary image shown in FIG. 8B, the part (binary part) located at the same position as the part "11" is referred to, and the white pixel part in the binary part is corresponded. Then, the average value ave_color of the RGB values of the portion of the original image shown in FIG. 8A is calculated.

Next, in step S905, the ave_color is substituted as a pixel value forming a portion of the original image shown in FIG. 8A corresponding to the black pixel portion in the binary part.

The above-mentioned processing is performed for "1" when the character area exists.
By executing this for each part of "2", "13", "21", "22", and "23", the part where the character was present in the original image is filled with the average value of the surrounding pixels. be able to.

The image in which the character portion has been filled in as described above is the primary electronic form in this embodiment.

First created by filling character area
The next electronic form is reduced by the reduction unit 106 by, for example, simple thinning. This reduction processing is, for example, 300 dp
This is executed to reduce the image size and make it easier to handle by setting the image of i to 150 dpi.

The execution order of the character filling processing and the reduction processing may be reversed. However, when the reduction processing is performed first, the positional deviation between the binary image and the color image due to the reduction is taken into consideration. There is a need.

By the method described above, it is possible to obtain a form image (primary electronic form) in which a character portion of a color image obtained by scanning a printed matter is erased while leaving only the background. That is, the form image shown in FIG. 10 is obtained based on the scan data of the printed matter shown in FIG. In this form image, parts (ruled lines, textures, images, etc.) other than the characters of the original printed matter (FIG. 3) are left as a background, and by writing new characters in the form image, the form image You can create an original document using.

When the primary electronic form is created, it is possible to correct the location where the layout is erroneously recognized by using ordinary retouching software. For example, if a character portion is left in the obtained form image, it may be erased by overwriting surrounding pixels in the character portion using the pixel correction function of retouching software. This operation is far easier than the case of manually erasing the entire character portion of an image obtained by scanning a printed matter, and thus can be said to be sufficiently practical.

As described above, according to this embodiment,
An image (original image) printed on a sheet can be diverted to generate a primary electronic form that takes advantage of the background. If it is sufficient for the user to handle the original image simply as a background image, this primary electronic form can be treated as image data.

The data format of the original image 101 is not limited to RGB, and the present invention can be applied to other formats such as YUV.

Since the image data A output from the character filling unit 105 has already been completed as the primary electronic form, for example, when it is desired to directly use it, reduction processing or JPEG compression processing is performed. No need.

<Second Embodiment> The second embodiment of the present invention will be described below.
An embodiment will be described.

In the second embodiment, a first background image of the original image generated in the first embodiment is used.
The secondary electronic form is registered as a secondary electronic form, further including vectorized information for each attribute such as a line portion, a surface portion, and a frame portion.

[Device Configuration] FIG. 11 shows a block configuration for creating a secondary electronic form in the second embodiment, which is the first configuration.
In the embodiment, it is provided subsequent to the configuration shown in FIG. That is, the layout analysis result 108 and the compression code X109 of the primary electronic form shown in the block 1A in FIGS. 1 and 11 are used when the secondary electronic form is created.

In FIG. 11, reference numeral 1501 is the compressed code X.
This is a JPEG decompression unit that decompresses 109 to generate a primary electronic form image 1502. Reference numeral 1503 denotes a rectangular frame display portion, which is based on the coordinate information of the line, frame, and table in the layout analysis result 108 and is used for the primary electronic form image 1
A rectangular frame is superimposed and displayed on 502. The rectangular frame display unit 1503 allows the user to select a desired frame for the displayed rectangular frame. The selected rectangular frame is line-vectorized by the line-vectorization unit 1506 on the basis of the attribute information such as the line and the frame in the layout analysis result 108.
507 is generated.

On the other hand, 1504 is a line-filled portion,
Similar to the character filling unit 105 shown in FIG. 1, the surrounding pixels of the line area are filled. Here, the line filling unit 1504 actually needs to refer to the binary image 103 (FIG. 1) used when creating the primary electronic form, but this is omitted in FIG. 11. 1505
Is an image in which the line area is filled and only the background is displayed.
JPE that creates compressed code Y1508 by PEG compression
It is a G compression unit.

In the second embodiment, with the above configuration, the line vector information 1507 about the desired line portion in the primary electronic form and the compression code Y1508 of the background image in which the line portion is erased from the primary electronic form are provided. , Register as a secondary electronic form.

The process of creating the secondary electronic form in the second embodiment will be described below with reference to the flowchart of FIG.

First, in step S1201, JPE
Display the primary electronic form after G extension. Here, that is, the image as shown in FIG. 10 is displayed. Then, in step S1202, lines, frames, and rectangles of table attributes are displayed on the display image. Since only the frame attribute is detected in the form example shown in FIG. 10, only the frame frame is displayed as shown in FIG. In the example shown in FIG. 10, rectangular display is performed with the frame attribute information.

Next, in step S1203, the user arbitrarily selects a region for which line vector conversion is to be executed.
The processing of steps S1201 to S1203 is performed by the rectangular frame display unit 1503.

Then, in steps S1204 and S1205, with respect to the area selected in step S1203, similarly to the character area filling processing shown in FIG.
Performs line area filling processing. As a result, the line drawing in the selected area is erased.

Then, in step S1206, the selected area is subjected to line vectorization processing using information on attributes such as lines and frames, and the created lines (including frames and tables) are displayed on the form.

Here, the line attribute means, at the time of layout analysis,
It is the information of the line added to each area of the line, the frame, and the table, and includes, for example, the following information (1) to (4).

(1) Start position and end position of line (2) Line type (solid line, broken line, etc.) (3) Line thickness (4) Oblique line (upward to the right, upward to the left) In many cases, it is not faithful to the original image. However, since the post-correction is performed by the user in step S1207, the second created finally
The next electronic form does not cause much problem in use. The post-correction is a process of arbitrarily making corrections when the line vectorization process is not faithful to the original image or when the user wants to make a desired change such as thickening the line. .
The post-correction process is the same as the editing function of a normal document creation application.

In step S1208, the form created by vectorizing the line portion desired by the user while the background of the primary electronic form is utilized by the processing of steps S1201 to S1207 is converted into the secondary form. Register as an electronic form. That is, as the secondary electronic form, not only the background image (compression code Y1508) of the primary electronic form, but also line information that constitutes a frame area and a table area is held as vector information (line vector information 1507). be able to.

The secondary electronic form is composed of the background image of the original image and the line vector. If the background image is unnecessary as a form, the secondary electronic form is erased to create an electronic form composed of only the line vector. You can create a form.

As described above, according to this embodiment,
Based on the primary electronic form created in the first embodiment, it is possible to further generate a secondary electronic form in which desired line portions in the form are vectorized.

If it is sufficient for the user to handle the original image simply as the background image, the processing can be terminated at the time when the primary electronic form is created, and the primary electronic form can be used. If it is desired to use even more detailed line areas as a form, a secondary electronic form that is closer to the electronic form format can be created by line vectorization.

If it is not necessary to register the primary electronic form and only the secondary electronic form is to be created and registered, the character filling unit 105 shown in FIG.
The image data A output from the
It may be used as the next electronic form image 1502.

<Third Embodiment> The third embodiment of the present invention will be described below.
An embodiment will be described.

In the above-described first and second embodiments, the example in which the primary electronic form that is the background form of the original image and the secondary electronic form that further includes the line vector are created has been described. In the third embodiment, the entire secondary electronic form is further vectorized to create a third electronic form.
Register as the next electronic form.

[Device Configuration] FIG. 14 shows a block configuration for creating a tertiary electronic form in the third embodiment.
In the embodiment, it is provided after the configuration shown in FIG. 11. That is, the line vector information 1507 and the compression code Y1508 shown in the block 1B in FIGS. 11 and 14 (that is, the secondary electronic form).
Is used when the third electronic form is created.

In FIG. 14, reference numeral 1509 denotes a JPEG decompression unit, which is a compression code Y150 in the secondary electronic form.
8 is expanded to generate a secondary electronic form image 1510. Reference numeral 1511 denotes a display unit that displays the secondary electronic form based on the secondary electronic form image 1510 and the line vector information 1507 in the secondary electronic form.

Reference numeral 1512 denotes a filling section which, in addition to performing the filling processing with the background color inside the area having the table attribute, receives the correction processing of the line vector by the user. Note that the filling processing here is performed on the area surrounded by the frame, and it is possible to perform painting with a color similar to the background color or pattern painting. Reference numeral 1513 denotes a background image erasing unit that erases a background image from the filled secondary electronic form to generate line vector information 1514.

In the third embodiment, with the above configuration, the line vector information 1514 obtained by erasing the background image after the front part in the secondary electronic form is filled with the background color is converted into the tertiary electronic form. Register as.

The process of creating the tertiary electronic form in the third embodiment will be described below with reference to the flowchart of FIG.

First, in step S1401, the secondary electronic form is displayed. FIG. 16B shows an example of this display. A display example of the primary electronic form corresponding to FIG. 16A is shown.

Next, in step S1402, the line vector information having the table attribute is subjected to the layout misrecognition correction and the user's arbitrary correction as in the line vector correction (S1207) shown in the first embodiment. .

Then, in step S1403, the background color of the table area is converted. That is, as shown in FIG. 16C, the inside of the table area (table frame and inside table) is converted (filled) into a color equivalent to the background color. As a result, in the secondary electronic form, not only the pixels in the table area of the background image data but also the color information included in the line vector indicating the table frame is converted into the background color.

Finally, in step S1404, the background image is erased. This is because it is sufficient for the tertiary electronic form that only the color information of the background image remains in the front frame. FIG. 16D shows an example in which the background image is deleted, that is, an example of the created third electronic form. According to the figure, it can be seen that the form is composed only of line vectors.

As described above, according to the third embodiment, based on the secondary electronic form created in the second embodiment, the frame area is converted into the background color and the background image is further erased. In particular, a tertiary electronic form is created in which only the frame is left. Therefore, since the tertiary electronic form is composed of only line vectors, the file size of the form can be small.

When only the tertiary electronic form is created, the secondary electronic form output from the line filling unit 1504 shown in FIG. 11 is directly converted to the secondary electronic form image 1510 shown in FIG. May be used as

If it is not necessary to make the layout correction shown in step S1402, the secondary electronic form in the preceding stage and the correction processing (S1401 and S14) are performed.
02) can be skipped and the background color conversion processing in step S1403 can be directly performed.

<Other Embodiments> The present invention can be applied to a system composed of a plurality of devices (for example, host computer, interface device, reader, printer, etc.), but an apparatus consisting of one device ( For example, it may be applied to a stereoscopic image printer).

Further, an object of the present invention is to supply a storage medium (or recording medium) recording a program code of software for realizing the functions of the above-described embodiment to a system or apparatus, and to supply a computer of the system or apparatus ( Alternatively, by the CPU or MPU) reading and executing the program code stored in the storage medium,
It goes without saying that it will be achieved. In this case, the program code itself read from the storage medium realizes the functions of the above-described embodiments, and the storage medium storing the program code constitutes the present invention.
Further, by executing the program code read by the computer, not only the functions of the above-described embodiments are realized, but also based on the instruction of the program code,
An operating system (OS) running on the computer does some or all of the actual processing,
It goes without saying that the processing includes the case where the functions of the above-described embodiments are realized.

Further, after the program code read from the storage medium is written in the memory provided in the function expansion card inserted in the computer or the function expansion unit connected to the computer, based on the instruction of the program code. , The CPU provided in the function expansion card or the function expansion unit performs some or all of the actual processing,
It goes without saying that the processing includes the case where the functions of the above-described embodiments are realized.

[0079]

As described above, according to the present invention, an electronic form based on a printed document can be easily created.

[Brief description of drawings]

FIG. 1 is a diagram showing a block configuration of an image processing apparatus in a first embodiment.

FIG. 2 is a flowchart showing a character area detection process in the first embodiment.

FIG. 3 is an example of an original image showing a specific example of a character area detection process in the first embodiment.

FIG. 4 is a luminance histogram of the original image shown in FIG.

5 is a binary image created from the original image shown in FIG.

FIG. 6 is a binary image of only the character area in the original image shown in FIG.

7 is a diagram showing an example of a character area in which black pixels in the binary image shown in FIG. 6 are grouped.

FIG. 8 is a diagram showing a specific example of character part filling processing according to the first embodiment.

FIG. 9 is a flowchart showing a character part filling process according to the first embodiment.

FIG. 10 is a diagram showing an example of a primary electronic form created in the first embodiment.

FIG. 11 is a diagram showing a block configuration for creating a secondary electronic form in the second embodiment.

FIG. 12 is a flowchart showing a secondary electronic form creation process in the second embodiment.

FIG. 13 is a frame frame display example on the primary electronic form in the second embodiment.

FIG. 14 is a diagram showing a block configuration for creating a tertiary electronic form in the third embodiment.

FIG. 15 is a flowchart showing a tertiary electronic form creating process in the third embodiment.

FIG. 16 is a diagram showing a specific example of a tertiary electronic form creation process in the third embodiment.

[Explanation of symbols]

101 Original image 102 Binarization unit 103 binary image 104 Layout analysis section 105 character fill part 106 Reduction unit 107 JPEG compression unit 108 Layout analysis result 109 Compressed code X 1501 Vector decompression unit 1502 Primary electronic form image 1503 Rectangular frame display area 1504 Line fill part 1505 JPEG compression unit 1506 Line vectorization unit 1507 line vector information 1508 Compressed code Y 1509 JPEG extension section 1510 Secondary electronic form image 1511 display 1512 Line fill part 1513 Background image erasing section 1514 line vector information

Front page continuation (51) Int.Cl. ⁷ Identification code FI theme code (reference) H04N 1/46 H04N 1/46 Z 5L096 F term (reference) 2C087 AA15 BA14 BB10 BD06 BD31 BD40 CA02 5B021 AA01 LA01 5C076 AA03 AA22 AA40 BA06 5C077 LL17 MP05 MP07 PP19 PP20 PP21 PP27 PP46 PP58 PP65 PP68 PQ08 PQ19 RR02 RR11 RR18 RR21 5C079 HB01 HB04 LA06 LA26 LA31 LA34 LA37 LA39 NA27 PA00 5L096 AA02 AA06 BA08 BA17 CA18 DA01 EA44 GA34 FA34 EA34 FA34 EA37

Claims (19)

[Claims] 1. An image processing method for creating an electronic form based on a document image formed on a recording medium, the image inputting step of inputting multi-valued image data based on the document image formed on the recording medium. A binarizing step of binarizing the multi-valued image data to generate binary image data; an analyzing step of analyzing the layout of the document image based on the binary image data; A character filling step of creating a first electronic form by filling a character portion in the multi-valued image data with a surrounding color based on the binary image data, the image processing method. 2. The character filling step includes a dividing step of dividing the multi-valued image data into blocks of a predetermined size; a character area detecting step of detecting a block including a character area based on the layout analysis result; 2. The image according to claim 1, further comprising: a replacing step of replacing a pixel of the character portion with a pixel equivalent to a peripheral pixel of the detected block based on a corresponding region of the binary image data. Processing method. 3. The replacing step comprises: an average color calculating step of calculating average color data of multi-valued image data corresponding to white pixels in the binary image data in the block; An average color replacement step of replacing multi-valued image data corresponding to black pixels in the value image data with the average color data, the image processing method according to claim 2. 4. The image processing method according to claim 1, wherein in the analyzing step, the character area information is created by grouping black pixels of the binary image data. 5. A reduction step of reducing the first electronic form, and a compression step of compressing the reduced first electronic form,
The image processing method according to claim 1, further comprising: 6. The image processing method according to claim 1, further comprising an editing step of editing the first electronic form based on a user instruction. 7. A first form displaying step of displaying the first electronic form by marking a line area thereof on the basis of the layout analysis result, and an arbitrary line on the displayed first electronic form. A selection step of selecting an area based on a user instruction; a vectorization step of creating line vector information by vectorizing a line portion in the selected line area; and a layout analysis result and the binary image data. A line filling step of creating background image data by filling a line portion in the first electronic form with its surrounding color, based on the second electronic form of the line vector information and background image data. The image processing method according to claim 1, wherein the image processing method is a form. 8. The image processing method according to claim 7, wherein the line area is an area having any one of attributes of a line, a frame, and a table. 9. The image processing method according to claim 8, wherein in the form displaying step, the line area is displayed in a rectangular shape. 10. The image processing method according to claim 9, wherein in the form displaying step, a rectangle is displayed with attribute information of the line area. 11. The image processing method according to claim 7, further comprising a background removing step of deleting the background image data from the second electronic form. 12. A table area filling step of filling a table area in the second electronic form composed of the line vector information and the background image data with a color similar to the background color, and image data after the table area filling. And a background deletion step of creating a third electronic form by deleting the background image data from the line vector information constituting the table area in the third electronic form. The image processing method according to claim 7, wherein the image processing method includes information. 13. The image processing method according to claim 12, wherein the line vector information forming the table area includes the background color information. 14. A second form displaying step of displaying the second electronic form, and an editing step of editing an arbitrary line area on the displayed second electronic form based on a user instruction. 13. The image processing method according to claim 12, wherein the frame area filling step is executed for the edited second electronic form. 15. An image processing apparatus for creating an electronic form based on a document image formed on a recording medium, comprising image input means for inputting multi-valued image data based on the document image formed on the recording medium. A binarizing unit that binarizes the multi-valued image data to generate binary image data; an analyzing unit that analyzes the layout of the document image based on the binary image data; A character filling unit that fills a character portion in the multi-valued image data with its surrounding color based on the binary image data, and a first holding that holds the multi-valued image data after the character filling as a first electronic form. An image processing device comprising: 16. Based on the layout analysis result,
First form displaying means for displaying the first electronic form by marking its line area, and selecting means for selecting an arbitrary line area on the displayed first electronic form based on a user instruction, Vectorizing means for creating line vector information by vectorizing a line part in the selected line area, and a line part in the first electronic form based on the layout analysis result and the binary image data. Line painting means for creating background image data by painting with the surrounding color, and second holding means for holding the line vector information and the background image data as a second electronic form, and The image processing apparatus according to claim 15, further comprising: 17. A table area filling means for filling a table area in the second electronic form, which is composed of the line vector information and the background image data, with a color similar to the background color, and a second area after the table area is filled. Background deleting means for extracting only the line vector information by deleting the background image data from the electronic form, and a third holding means for holding the line vector information extracted by the background deleting means as a third electronic form. The image processing apparatus according to claim 16, further comprising: and the line vector information forming the table area in the third electronic form includes the background color information. 18. A program for executing the image processing method according to claim 1, which is executed by a computer. 19. A recording medium on which the program according to claim 18 is recorded.