JP2000324331A - Image processor and method therefor - Google Patents

Abstract

PROBLEM TO BE SOLVED: To reduce data quantity of a received document image for storing them, to read them and to reproduce the image data with high quality. SOLUTION: The image processor receives a document image 101, generates binary image data 105 from its document image, generates layout analysis data 107 in response to the attribute of an image included in the document image, generates and stores document image understanding data 111 denoting a result of analyzing the document image on the basis of the layout analysis data 107 of the document image. In this case, the attribute of each part image of the document image 101 is checked on the basis of the document image understanding data 111 and when the area indicates a text area, the image is stored as a binary image and when not so, the original image is entirely selected and stored. In the case of reproduction, synthesis/reproduction processing is executed depending on the image type of the partial image in the case of reproduction.

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 for inputting and storing a document image and reproducing the same, and a method therefor.

[0002]

2. Description of the Related Art Conventionally, as a device for inputting and processing a document image, for example, a copying machine that optically reads and inputs a document on which a document and an image are printed, and prints and outputs the document image, There has been a document database system for storing the optically input document image, a facsimile apparatus for transmitting the document image via a network or the like.

[0003]

However, such a conventional device cannot be adapted to digitization and networking. Specifically, if the original image is stored as it is by colorizing the original image or distributed via a network, the amount of the image data becomes enormous. Further, if the image data of the original image is compressed uniformly when compressing the image data, the image quality suitable for reuse cannot be maintained. Further, there is a problem that the image quality of the output image is deteriorated due to a difference between an output device for outputting the original image such as a monochrome printer and a color printer.

SUMMARY OF THE INVENTION The present invention has been made in view of the above conventional example, and provides an image processing apparatus and method capable of reducing the amount of data of an input document image, storing the data, reading the data, and reproducing the data with high quality. With the goal.

[0005]

In order to achieve the above object, an image processing apparatus according to the present invention has the following arrangement.
That is, image input means for inputting a document image, binary image creating means for creating binary image data from the document image input by the image input means, and binary image created by the binary image creating means A layout analysis unit configured to generate layout analysis data according to an attribute of an image included in the document image from data; and generate and store analysis data indicating a result of analyzing the document image based on the layout analysis data. It is characterized by comprising analyzing means, and document image reproducing means for reproducing the document image based on the analysis data analyzed and stored by the analyzing means.

In order to achieve the above object, the image processing method of the present invention comprises the following steps. That is, an image input step of inputting a document image, a binary image creation step of creating binary image data from the document image input in the image input step, and a binary image created in the binary image creation step A layout analysis step of generating layout analysis data according to an attribute of an image included in the document image from data; and generating and storing analysis data indicating a result of analyzing the document image based on the layout analysis data. An analysis step; and a document image reproduction step of reproducing the document image based on the analysis data analyzed and stored in the analysis step.

[0007]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Preferred embodiments of the present invention will be described below in detail with reference to the accompanying drawings.

FIG. 1 is a functional block diagram showing a functional configuration of the image processing system according to the first embodiment.

In FIG. 1, reference numeral 101 denotes an input document, which is a document manuscript including a printed matter and image data handled on a computer. An image input unit 102 includes, for example, a scanner, and reads the document 101 and inputs the document 101 as an image signal. Reference numeral 103 denotes original image data input from the image input unit 102. Reference numeral 104 denotes a binary image output unit which creates and outputs binary image data 105 from the image signal of the input document 101. Reference numeral 106 denotes a layout analysis unit, which outputs, based on the binary image data 105, information obtained by dividing the input document image into regions corresponding to various attributes such as figures, texts, and tables, that is, layout analysis data 107. . Reference numeral 108 denotes a document image understanding storage unit that stores document image understanding data while adaptively changing storage conditions from the input document original image 103 and the binary image data 105. A document image comprehension data output unit 109 reads and outputs the document image comprehension data 110 stored in the document image comprehension storage unit 108. A document image comprehension data input unit 111 inputs document image comprehension data 110 output from the document image comprehension data output unit 109. Reference numeral 112 denotes a document image understanding / reproduction unit.
A document image is created from the document image understanding data 110 while adaptively changing the reproduction conditions. Reference numeral 113 denotes a document image data to be reproduced, 114 denotes an image output unit that outputs the reproduced document image data 113, and 115 denotes an output document that is finally reproduced and output.

FIG. 2 is a conceptual diagram illustrating the configuration of the image processing system according to the first embodiment.

In FIG. 2, reference numeral 201 denotes a computer for performing a process of understanding a document image.
4. It corresponds to the layout analysis unit 106 and the like. 202
Is a storage device for storing data, which corresponds to the document image understanding storage unit 108 in FIG. A scanner 203 reads a document image and photoelectrically inputs the image. 204
Is a color printer. 205 is facsimile, 20
Reference numeral 6 denotes a digital color copying machine that performs input and output of color images in a combined manner. 207 is a printer 208
Is a printer server, and 208 is a monochrome printer. Reference numeral 209 denotes a file server for managing a database; 210, a database; and 211, a digital copying machine that performs composite input and output of monochrome images. A network 212 connects the above-described digital devices. In this configuration, the image input unit 10
Reference numeral 2 also corresponds to a scanner unit such as the scanner 203 and the copiers 206 and 211, and a document reading unit of the facsimile apparatus 205. The image output unit 114 corresponds to the printer units of the printers 204 and 208, the copying machines 206 and 211, and the facsimile apparatus 205.

Next, the flow of processing in the image processing system according to the present embodiment will be described.

FIG. 3 is a flowchart illustrating the flow of processing in the image processing system according to the present embodiment.

In the present embodiment, a 24-bit multi-valued image is input from a scanner 203, a copying machine 206, or the like, and distributed via a network 212. The monochrome printer 208, the copying machine 211, or the facsimile machine 20
5 and the like.

First, in step S301, the image input unit 10
A document image is input as a multi-value image from the scanner 203, which is a second image. Next, the process proceeds to step S302, where the multi-valued image data is converted into the binary image data 1 by the binary image output unit 104.
Convert to 05. In step S303, based on the binary image data 105, the layout analysis unit 106 divides the figures, texts, tables, and the like included in the document image into regions for each attribute, and
(See FIG. 4).

4A and 4B, the layout analysis data 107 includes the number n of the divided areas, the X and Y coordinates, the width, the height, and the attributes (text = 1, line graphic = 2, picture / photograph = 3, table = 4) are stored.

Next, the flow advances to step S304, where the layout analysis data 107 is stored in the document image understanding and storage unit 108.
The document image comprehension data 110 is created and stored from the multivalued image 103 and the binary image data 105, which are the original images of the input document, while adaptively changing the storage conditions.
Then, the process proceeds to step S305 to output the document image understanding data 110.

The details of each of the above processes will be described below.

FIG. 5 is a flowchart showing an example of the document image comprehension storage processing according to the present embodiment.

First, in step S501, the layout analysis data 107 of each divided area is analyzed to determine the area attribute of each area. Next, the process proceeds to step S502, where the region attribute is determined. If the attribute is "text", the process proceeds to step S503, where the binary image data 105 is selected as the entire image to be cut out.
The partial image is cut out using the coordinate data of each area designated by 07. In step S505, the partial image thus cut is stored as document image understanding data 110 (see FIG. 6).

FIGS. 6A and 6B are diagrams showing the structure of the document image comprehension data 110 according to the present embodiment.

In FIG. 6, the appearance order of the target partial image data in the layout analysis data 107 is defined as the ID of the layout area data, and the cut width, cut height, image type, image size, and the cut image are determined. Is stored as the partial image data.

If it is determined in step S502 that the area attribute is not "text", the flow advances to step S506 to select a multivalued image as an original image as the entire image to be cut out.
The partial image is cut out using the coordinate data of the area data of No. 7. Then, the process proceeds to step S505, in which the cut-out partial image is stored as the document image understanding data 110 (FIG. 6).

Next, in S507, it is checked whether or not the remaining divided area exists. If there is, the process returns to S501, and the above processing is repeated for the remaining divided area. If the remaining divided area does not exist in step S507, the document image comprehension / save processing ends.

Further, in this embodiment, the document image comprehension data 110 created and stored in the document image comprehension storage unit 108 is output to the network 212 by the document comprehension data output unit 109, and the network 2
The information is distributed to the user via the server 12.

The processing at the destination where the document image comprehension data is distributed in this way will be described with reference to the flowchart of FIG.

As shown in FIG. 7, first, at step S401
In step S402, the document image comprehension data input unit 111 inputs the document image comprehension data 110.
, The document image data 11 to be reproduced from the document image comprehension data 110 while adaptively changing the reproduction conditions.
Then, a reproduced image is output as an output document from the monochrome printer, which is the image output unit 114, based on the document image data 113 (S403).

FIG. 8 is a flowchart showing the document image comprehension / reproduction processing in step S402 in FIG.

First, in step S701, an image serving as a base of a reproduced document image is created so as to serve as a white base. Next, the process proceeds to step S702, where partial image data is extracted from the document image comprehension data 110, and step S70 is performed.
In step 3, based on the extracted partial image and its coordinate data, the reproduced partial image data 1 is synthesized with a white background image.
13 is created. In step S704, it is determined whether or not the processing for all the partial images has been completed. If the processing has not been completed, the process returns to step S702, and the above-described processing is repeatedly performed.

FIG. 9 is a flowchart showing the reproduced image synthesizing process in step S703 in FIG.

First, in step S801, the image type of a partial image is extracted from the document image comprehension data 110,
Next, the process proceeds to step S802, where it is determined whether the image type is a “binary image type”. If so, the process proceeds to step S803, where the black and white pixels of the binary image
A pseudo 24-bit conversion process of converting the bit multi-valued image into black and white pixels is performed. Here, the black pixel of the binary image is “1”, the white pixel is “0”, the black pixel of the 24-bit multi-valued image is R = 0, G = 0, B = 0, and the white pixel is R =
255, G = 255, B = 255 (R is a red component, G is a green component, and B is a blue component and has an 8-bit value).

If it is determined in step S802 that the image type of the partial image is "24-bit multi-valued image type", the flow advances to step S804 to use the partial image as it is for synthesis. In this way, in step S804, a logical operation is performed on each pixel of the partial image on the base image and the partial image to create a composite image.

In the present embodiment, the white pixels (R
= 255, G = 255, B = 255) and a black pixel (R = 0, G = 0, B = 0) of the partial image is a black pixel (R
= 0, G = 0, B = 0).

[Second Embodiment] Next, a second embodiment of the present invention will be described. In the second embodiment, in the document image comprehension saving processing in step S304 in FIG. 3, the image data is compressed when the image data is stored, and the compression method is adaptively changed according to the difference in the image type. I am trying to do it.

Hereinafter, the flow of the document image understanding / storing process according to the present embodiment will be described with reference to the flowchart of FIG.

First, in step S601, the layout analysis data 107 of each divided area is analyzed to determine the attribute of each area. Next, the process proceeds to step S602 to check whether the attribute is “text”.
To the binary image data 10 as the whole image to be cut out.
5 is selected, and the process advances to step S605 to cut out a partial image using the coordinate data of each area of the layout analysis data 107.

If the attribute of the partial image is not "text" in step S602, the process proceeds to step S604.
In step S605, a partial image is cut out using the coordinate data of each area of the layout analysis data 107 in step S605. Up to this point, the processing is the same as the processing in FIG. 5 (Embodiment 1).

Then, the flow advances to step S606 to check the image type of the cut-out partial image. If the image type is a binary image, the flow advances to step S607 to perform compression processing of the binary image (for example, MMR or the like). Step S
In step 609, the document image is stored as the document image understanding data 110 (FIG. 11). At this time, the document image comprehension data 110 includes
By recording the compression method of compressing the image data, in the process of reproducing the document image comprehension data,
The compressed image can be decoded.

If the result checked in step S606 is a multi-valued image, the flow advances to step S608, and
A compression process for a multi-valued image is performed (for example, JPEG or the like), and the compressed partial image is converted into document image understanding data 110 (FIG. 1).
Save as 1). Next, the process proceeds to step S610, where it is determined whether or not there is a remaining divided region. If there is, the process returns to step S601, and the above processing is repeated for the remaining divided region. If the remaining divided areas do not exist, the document image comprehension storage processing ends.

FIG. 11 is a view for explaining an example of the document image comprehension data 110 according to the second embodiment of the present invention.

The appearance order of the target layout area data in the layout analysis data 107 is used as the ID of the layout area data, and the cut width, cut height, image type, compression method, image size, and the compressed The cut image is stored as partial image data. Here, the image type is classified into a binary image "1" and a 24-bit multi-valued image "2", and the compression methods are MMR (for binary image) "1" and JPEG (for multi-valued image) "2". It is classified into.

Third Embodiment Next, a third embodiment of the present invention will be described. In the third embodiment, each partial image of the document image understanding data 110 is output as one image.

FIG. 12 is a flowchart for explaining the document image understanding and reproducing process (corresponding to the process of step S402 in FIG. 7) according to the third embodiment.

First, in step S901, partial image data is extracted from the document image comprehension data 110, and then the process proceeds to step S902, where the extracted partial image is
The image for the page is stored in the output buffer.
Next, the process advances to step S903 to check whether or not the remaining partial image exists.
And the above process is repeated for the remaining partial images. If it is determined in step S903 that the remaining partial image does not exist, the document image understanding and reproducing process ends.

[Fourth Embodiment] Next, a fourth embodiment of the present invention will be described. In the fourth embodiment, when each partial image of the document image comprehension data is output as one image, selection is made based on the attribute of the partial image.

FIG. 13 is a flowchart for explaining the document image understanding and reproducing process (corresponding to the process of step S402 in FIG. 7) according to the fourth embodiment.

First, in step S1001, a partial image is extracted from the document image comprehension data 110, and the process advances to step S1002 to check the attribute of the partial image.
If the attribute is "text", the process advances to step S1003 to execute a one-page image creation process, and stores the extracted partial image as an image of one page in an output buffer. If the attribute is not “text” in step S1002, the process proceeds to step S1004,
The processing is not performed on the partial image, and the process proceeds to the next processing. In this way, in step S1004, it is checked whether or not the remaining partial image exists. If there is, the process returns to step S1001 to repeat the above processing for the remaining partial image. When the processing for all the partial images is completed in this way, the document image understanding and reproducing processing is ended.

[Fifth Embodiment] Next, a fifth embodiment of the present invention will be described. In the fifth embodiment, the reproduction level is set before the document image comprehension / save processing, and it is possible to select whether to combine the partial images into one page or to output each page separately.

FIG. 14 shows a fifth embodiment according to the present invention.
9 is a flowchart illustrating a process at a destination to which document image understanding data has been distributed.

First, in step S1101, a setting is made as to whether a partial image of the document image comprehension data 110 is to be combined into one page or to be output separately for each page (hereinafter referred to as a reproduction level). In this case, if "level 1", it is output as being synthesized into one page, and if "level 2", it is output as one page for each partial image.

Next, in step S1102, the document image understanding data 1
Then, in step S1103, document image data 113 to be reproduced is created from the document image comprehension data 110 while adaptively changing reproduction conditions, and an image output unit 114 is generated based on the document image data 113. The reproduced image is output as an output document from the monochrome printer (S1104).

FIG. 15 is a flowchart showing the document image understanding / reproduction processing in step S1103 according to the fifth embodiment.

First, in step S1201, the reproduction level set in step S1101 is checked.
If "Level 1" (one-page composite output), step S
Proceeding to step 1202, a base image of the reproduced document image is created so as to be a white base. Next, in step S1203, partial image data is extracted from the document image understanding data 110, and in step S1204, a reproduced image is created by combining the extracted partial image and the coordinate data with a white background image. Then, in step S1205,
It is checked whether the processing has been completed for all the partial images. If not, the process returns to step S1203 to execute the above-described processing. When the processing for all the partial images is completed in this way, the document image understanding and reproducing processing is ended. The processing in steps S1202 to S1205 is the same as that in FIG.
Is the same as the processing of steps S701 to S704.
Therefore, as an example of the reproduction synthesis processing in step S1204, as shown in FIG.
In step S1, the image type of the partial image is extracted from the document image storage data. If the image type is "binary image type" in step S802, the process proceeds to step S803.
A pseudo 24-bit conversion process is performed to convert the black and white pixels of the binary image into the black and white pixels of the 24-bit multi-valued image.

If it is determined in step S1201 that the reproduction level is "level 2" (for each partial image), the flow advances to step S1206 to extract partial image data from the document image understanding data 110. In step S1207, the extracted partial image data is extracted. Is stored in the output buffer as an image for one page. In step S1208, it is determined whether or not the remaining partial image exists. If the remaining partial image exists, the process returns to step S1206, and the above processing is repeated for the remaining partial image. Thus, step S1
If there is no remaining partial image in 205 or step S1208, this document image understanding and reproducing process is ended. Note that these steps S1206 to S120
The processing of No. 8 is the same as the processing of steps S901 to S903 in the above-described flowchart of FIG. 12 (Embodiment 3).

Even if the present invention is applied to a system including a plurality of devices (for example, a host computer, an interface device, a reader, a printer, etc.), a device including one device (for example, a copying machine, a facsimile machine, etc.) ) May be applied.

Further, an object of the present invention is to supply a storage medium (or a recording medium) in which a program code of software for realizing the functions of the above-described embodiments is recorded to a system or an apparatus, and to provide a computer (a computer) of the system or the apparatus. Alternatively, this can be achieved by a CPU or an MPU) reading and executing the program code stored in the storage medium. In this case, the program code itself read from the storage medium implements the functions of the above-described embodiment, and the storage medium storing the program code constitutes the present invention. By executing the program code read by the computer, not only the functions of the above-described embodiments are realized, but also an operating system (OS) running on the computer based on the instruction of the program code. This also includes a case where some or all of the actual processing is performed and the functions of the above-described embodiments are realized by the processing.

Further, after the program code read from the storage medium is written into the memory provided in the function expansion card inserted into the computer or the function expansion unit connected to the computer, the program code is read based on the instruction of the program code. This also includes the case where the CPU provided in the function expansion card or the function expansion unit performs part or all of the actual processing, and the processing realizes the functions of the above-described embodiments.

As described above, according to the present embodiment, the data amount at the time of storing a document image can be reduced. It is possible to reduce the load on network traffic when a document image is distributed. When storing and distributing document images, high image quality suitable for reuse can be maintained. It is possible to prevent the image quality of the document image from deteriorating and the loss of information at the time of output. This has the effect of facilitating reuse of electronic documents such as DTP (desktop publishing).

[0059]

As described above, according to the present invention, there is an effect that the data amount of an input document image is reduced, stored, read out, and reproduced with high quality.

[Brief description of the drawings]

FIG. 1 is a functional block diagram showing a functional configuration of an image processing system according to an embodiment of the present invention.

FIG. 2 is a conceptual diagram illustrating a configuration of an image processing system according to the present embodiment.

FIG. 3 is a flowchart showing processing from image input to document image understanding data output in the image processing system according to the present embodiment.

FIG. 4 is a diagram illustrating a configuration of layout analysis data according to the present embodiment.

FIG. 5 is a flowchart showing a document image understanding and saving process (S304) according to the first embodiment.

FIG. 6 is a diagram illustrating a configuration of document image comprehension data according to the present embodiment.

FIG. 7 is a flowchart illustrating processing from input of document image understanding data to output of a reproduced image according to the present embodiment.

FIG. 8 shows a document image understanding / reproduction process (S
It is a flowchart which shows 402).

FIG. 9 is a flowchart showing a reproduced image combining process in step S703 according to the present embodiment.

FIG. 10 is a flowchart showing a document image understanding and saving process (S304) according to the second embodiment.

FIG. 11 is a diagram illustrating a configuration of document image understanding data according to the second embodiment.

FIG. 12 is a flowchart showing a document image understanding and reproducing process (S402) according to the third embodiment.

FIG. 13 is a flowchart showing a document image understanding and reproducing process (S402) according to the fourth embodiment.

FIG. 14 is a flowchart showing processing from input of document image understanding data to output of a reproduced image according to the fifth embodiment.

FIG. 15 is a flowchart showing a document image understanding and reproducing process (S1103) according to the fifth embodiment.

Continued on the front page F-term (reference)

Claims (22)

[Claims] An image input unit for inputting a document image; a binary image generating unit for generating binary image data from the document image input by the image input unit; A layout analysis unit configured to generate layout analysis data corresponding to an attribute of an image included in the document image from the binary image data; and generating analysis data indicating a result of analyzing the document image based on the layout analysis data. An image processing apparatus, comprising: an analysis unit configured to store and store the document image; and a document image reproduction unit configured to reproduce the document image based on the analysis data analyzed and stored by the analysis unit. 2. The image processing apparatus according to claim 1, wherein the analyzing unit selects one of an input document original image and a binary image as a cut-out destination image for each area of the document image divided based on the layout analysis data. Selection means, partial image cutting means for cutting a partial image from the image selected by the cut destination selection means, and image storage means for saving the partial image cut by the partial image cutting means. Item 2. The image processing device according to Item 1. 3. The image processing apparatus according to claim 2, wherein the analysis unit performs compression processing on the image of each area according to an attribute of each area of the document image divided according to the layout analysis data, and stores the image. The image processing device according to claim 1. 4. The analysis data includes: a number of a plurality of regions obtained by dividing the document image according to the layout analysis data;
4. The image processing apparatus according to claim 1, further comprising information on a size of each area, an image type, and a compression method thereof. 5. The document image reproducing means includes: a whole background image creating unit that creates a white background image; and an image combining unit that combines the created background image with a partial image obtained from the analysis data. The image processing apparatus according to claim 1, further comprising: 6. The image processing apparatus according to claim 5, wherein the image synthesizing unit converts a binary image into pseudo multi-valued image data and synthesizes it with the base image. 7. The image processing apparatus according to claim 1, wherein the document image reproducing unit reproduces each partial image of the document image as an image of one page. 8. The document image reproducing means selects whether or not to reproduce each of the partial images of the document image based on the analysis data, and converts each of the selected partial images into a one-page image. The image processing apparatus according to claim 1, wherein the image is reproduced. 9. A reproduction level setting unit for setting a reproduction condition of each of the partial images, wherein the document image reproduction unit synthesizes and reproduces a background image according to the set reproduction level. The image processing apparatus according to claim 1, wherein it is determined whether or not each partial image of the document image is reproduced and output as a one-page image. 10. An image inputting step of inputting a document image, a binary image creating step of creating binary image data from the document image input in the image inputting step, and a binary image creating step of creating the binary image data. From the binary image data, a layout analysis step of generating layout analysis data according to an attribute of an image included in the document image, and generating analysis data indicating a result of analyzing the document image based on the layout analysis data. An image processing method, comprising: an analyzing step of storing and storing the document image; and a document image reproducing step of reproducing the document image based on the analysis data analyzed and stored in the analyzing step. 11. The method according to claim 11, wherein the analyzing step includes selecting a source image or a binary image as an image to be cut out for each region of the document image divided based on the layout analysis data. A selection step, a partial image cutout step of cutting out a partial image from the image selected in the cutout destination selection step, and an image saving step of saving the partial image cutout in the partial image cutout step. Item 10
The image processing method according to 1. 12. The method according to claim 1, wherein the analyzing step performs a compression process on the image of each area according to an attribute of each area of the document image divided according to the layout analysis data and stores the image. The image processing method according to claim 10. 13. The method according to claim 1, wherein the analysis data includes information on the number of a plurality of areas obtained by dividing the document image in accordance with the layout analysis data, the size of each area, an image type, and a compression method thereof. Items 10 to 12
The image processing method according to any one of the above. 14. The document image reproducing step includes: a base whole image forming step of forming a white base image; and an image synthesizing step of combining the generated base image and a partial image obtained from the analysis data. The image processing method according to claim 10, further comprising: 15. The image processing method according to claim 14, wherein in the image synthesizing step, a binary image is converted into pseudo multi-valued image data and synthesized with the base image. 16. The image processing method according to claim 10, wherein in the document image reproducing step, each partial image of the document image is reproduced as an image of one page. 17. The document image reproducing step selects whether or not to reproduce each of the partial images of the document image based on the analysis data, and converts each of the selected partial images into a one-page image. The image processing method according to claim 10, wherein the image is reproduced. 18. A reproduction level setting step of setting a reproduction condition of each of the partial images, wherein the document image reproduction step synthesizes and reproduces and outputs a base image according to the set reproduction level. 11. The image processing method according to claim 10, wherein it is determined whether or not each partial image of the document image is reproduced and output as an image of one page. 19. A computer-readable storage medium storing a program for executing an image processing method for inputting and saving a document image and reproducing the document image, comprising: an image input step module for inputting a document image; A binary image creation step module for creating binary image data from the document image input by the image input step module; and a binary image data created by the binary image creation step module, the binary image data being included in the document image. A layout analysis step module for generating layout analysis data according to an attribute of an image; an analysis step module for generating and storing analysis data indicating a result of analyzing the document image based on the layout analysis data; and A document image reproducing unit that reproduces the document image based on the analysis data stored by being analyzed by the module; Storage medium and a step module. 20. The image processing apparatus according to claim 1, wherein the analyzing step module selects one of an input document original image and a binary image as a cut-out destination image for each area of the document image divided based on the layout analysis data. A pre-selection step module, a partial image cut-out step module for cutting out a partial image from the image selected in the cut-out destination selection step module, and an image storage step module for saving the partial image cut out in the partial image cut-out step module 20. The storage medium according to claim 19, wherein: 21. The analysis process module according to claim 1, wherein the image of each area is compressed and stored in accordance with an attribute of each area of the document image divided according to the layout analysis data. The storage medium according to claim 19, wherein 22. The analysis data according to claim 22, wherein the analysis data includes information on the number of a plurality of areas obtained by dividing the document image in accordance with the layout analysis data, the size of each area, an image type, and a compression method thereof. Items 19 to 21
The storage medium according to claim 1.