JP2005338902A - Document data structure, document conversion device, document restoration device, document conversion method, document restoration method, document conversion program, document restoration program and recording medium - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a document data structure obtaining a plurality of kinds of objects, or wherein a background is formed in a different plane and is integrated. <P>SOLUTION: In this structure of document data DD, three planes PLN(1), PLN(2), PLN(3) according to an encoding method are extracted from one original document 100, and the three planes are integrated as one document. The structure of the document data DD has the three planes and a reference image FEF having information for selecting one of the three planes in each pixel as three-gradation value. <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  The present invention relates to a technique for realizing a high compression rate by forming an image corresponding to the type of an object on a plurality of planes and selecting one of the planes according to a gradation value given to a reference image.

  2. Description of the Related Art Conventionally, an image processing method is known in which a plurality of images are collected and output as one sheet. For example, in the technique described in Japanese Patent Laid-Open No. 2003-163801, one aggregated image is created from a character image and a background image by an MRC (Mixed Raster Content) method.

  In the technique described in Japanese Patent Laid-Open No. 2003-087558, one image is divided into a background plane, a pattern brain, and a mask plane indicating a pattern position by the MRC method. The picture plane is reduced to reduce the amount of information, and the pixel value of the reduced picture plane is extended at the time of decoding. In this technique, there are substantially two types of image division: a pattern plane and a background plane.

Furthermore, the technique described in Japanese Patent Application Laid-Open No. 2003-281526 can prevent image deterioration caused by moire or the like when a digital image input from a scanner or the like is output to a display or the like. In this technique, a digital image is reduced, separated into a foreground image and a background image, and then a halftone dot pattern extracted as a background image is converted into continuous tone data.
JP2003-163801 JP 2003-087558 A JP 2003-281526 A

  However, in the techniques of Patent Documents 1, 2, and 3, basically, the screen division is only divided into two types of characters and background. For example, encoding of three or more types of objects in the original image is performed. Can not do.

  SUMMARY OF THE INVENTION An object of the present invention is to provide a document data structure that includes a plurality of types of objects or that is integrated by forming backgrounds in different planes.

  Another object of the present invention is to provide a document conversion apparatus, a document conversion method, and a document conversion capable of realizing a high compression ratio by dividing an image including a plurality of types of objects or further including a background into a plurality of planes To provide a program and a recording medium storing the program.

  Another object of the present invention is to provide a document restoration apparatus, a document restoration method, a document restoration program, and a document restoration program capable of restoring an image including a plurality of types of objects or further integrating and forming a background on different planes. It is to provide a recording medium in which a program is stored.

  The document data structure of the present invention is formed by extracting n planes from one original document and integrating the n planes as one document, and the n planes and each pixel. And a reference image having information for selecting one of the n planes as a value of m gradations.

  In the document data structure of the present invention, the original document may be extracted and divided into the n planes or may be extracted and extracted on the n planes and the reference image.

  In the document data structure of the present invention, at least one of the n planes can be encoded by an encoding method different from the encoding method of the other planes.

  In the document data structure of the present invention, the n planes can be encoded by a method according to the type of object on the original document.

  The document conversion apparatus according to the present invention includes a plane image extraction unit that extracts n planes from one original document, and an m gradation value is assigned to each pixel. Reference image creating means for creating a reference image for specifying any one of the planes, and encoding means for coding the n planes and the reference image are provided.

  In the document conversion apparatus of the present invention, the plane image extraction unit may extract the object on the original document by dividing it into the n planes, or may extract the objects on the n planes and the reference image. Can be configured.

  In the document conversion apparatus of the present invention, the encoding means may be configured to encode the n planes or further the reference image by a method according to the type of object on the original document.

  In the document conversion apparatus of the present invention, the encoding unit can encode at least one of the n planes by an encoding method different from the encoding method of the other planes.

  The document conversion apparatus according to the present invention may further include an integration unit that integrates the reference image encoded by the encoding unit and the n planes into a data set.

  The document conversion apparatus of the present invention can include processing means for performing image processing or image correction (resolution conversion, filtering processing, lightness correction, color tone correction, noise removal).

  A document restoration apparatus according to the present invention is a document restoration apparatus that acquires document data having the above-described data structure and restores a document from the document, and decomposes the document data into the n planes and the reference image. A document decomposing / decoding unit that performs a decoding process on the plane and the reference image, a scanning unit that scans the pixels of the reference image, and an m-gradation value assigned to the pixel scanned by the scanning unit. Specified by the gradation value acquisition means to be acquired, the plane specifying means for specifying the plane corresponding to the value of the m gradation, and the plane specifying means corresponding to the pixel given to the pixel position of the reference image Pixel value extracting means for extracting a value on the generated plane, and the pixel value in the pixel on the image to be restored corresponding to each pixel of the reference image Characterized in that a document restoring means to restore the document by assigning pixel values extracted by the detection means.

  The document restoration apparatus of the present invention includes a plane excluding unit that designates one or a plurality of the n planes, and the designated plane is not included in the target of the specific processing by the plane specifying unit. Only the necessary objects can be displayed on the restored image.

  In the document conversion method of the present invention, a plane extraction step of extracting n planes from one original document, and m gradation values are given to each pixel, and the n sheets are assigned according to the m gradation values. A reference image creating step of creating a reference image for specifying any of the planes, and an encoding step of encoding the n planes and the reference image.

  In the document conversion method of the present invention, in the plane extracting step, an object on an original document is extracted by dividing it into the n planes, or extracted separately on the n planes and the reference image. Can do.

In the document conversion method of the present invention, in the encoding step, the n planes or further the reference image can be encoded by a method according to the type of object on the original document.
In the document conversion method of the present invention, in the encoding step, at least one of the n planes can be encoded by an encoding method different from the encoding method of other planes.

  The document conversion method of the present invention may include an integration step of integrating the reference image encoded in the encoding step and the n planes into a data set.

  The document conversion method of the present invention can further include a processing step for performing image processing or image correction (resolution conversion, filtering processing, lightness correction, color tone correction, noise removal).

  The document restoration method of the present invention is a document restoration method for obtaining a document having the above-described data structure and restoring the document from the document, wherein the document having the data structure is decoded into n planes and a reference image. A decoding step; a gradation value acquisition step of scanning pixels of the reference image and acquiring m gradation values given to the scanned pixels; and specifying the plane corresponding to the m gradation values And a document restoration step of extracting a pixel value given to the position of the pixel on the plane identified in the plane identification step and restoring a document.

  The document restoration method of the present invention includes a plane excluding step of designating one or a plurality of the n planes, and the designated plane is not included in a specific target by the plane specifying unit, Only necessary objects can be imaged.

  The document conversion program of the present invention can execute each step in the document conversion method described above, and the document recovery program of the present invention can execute each step in the image recovery method described above. These programs can be stored in a computer-readable recording medium.

  According to the present invention, it is possible to reduce the file size of a document related to a color image without significantly reducing the image quality. Further, in a reproduced document, the visibility of characters, ruled lines, graphics composed of a single color, etc. can be maintained, and it can be applied to an image having gradation. In addition, since the document image is divided into a plurality of planes and a reference image, only necessary objects can be displayed or transmitted.

[First Embodiment]
FIGS. 1A and 1B are explanatory diagrams showing the document data structure of the first embodiment.

  As shown in FIG. 1B, the document data DD is composed of n (n = 3 in this embodiment) planes PLN (1) and PLN (2) extracted from the original document 100 shown in FIG. , PLN (3) and the reference image REF are integrated.

  As shown in FIG. 1A, the original document 100 includes an 8-bit color image 101, blue filled characters and blue horizontal stripe filled characters 102, and a red dot pattern background 103.

  In the present embodiment, as shown in FIG. 1B, images displayed on the original document 100 are planes PLN (1), PLN (2), PLN (3) according to the objects described in the image. ) And extracted. In the reference image REF, information for selecting one of the planes PLN (1), PLN (2), and PLN (3) for each pixel is a value A1 of m gradations (m = 3 in this embodiment). , A2, A3. For example, A1: “00”, A2: “01”, and A3: “10” can be set.

  In the present embodiment, the plane PLN (1) is, for example, an 8-bit color image and is encoded by a method suitable for compression of a photograph or the like, and the plane PLN (2) is a character (an image image or an image represented by a text code). ) And is encoded by a method suitable for character compression, and the plane PLN (3) is an image representing a background and is encoded by a method suitable for background compression. For example, when the reference image REF is a black and white image, MMR compression or the like is convenient in terms of compression efficiency. Also, since the plane PLN (1) is a color image, a method such as JPEG or JPEG2000 is suitable. Furthermore, since the plane PLN (2) is a character image, it is preferable to perform MMR compression.

  FIG. 2 is a block diagram illustrating the document conversion apparatus according to the first embodiment. Document data DD having the structure illustrated in FIG. 1B can be created by the document conversion apparatus.

  In FIG. 2, the document conversion apparatus 11 includes a plain image extraction unit 111, a reference image creation unit 112, a processing unit 113, an encoding unit 114, and an integration unit 115.

  The plain image extraction unit 111 can extract three planes PLN (1), PLN (2), and PLN (3) from the original document 100 according to the encoding method.

  In the present embodiment, the plane PLN (1) is a color image. Further, when the color of the object on PLN (2), PLN (3) on the original document 100 is a single color, the object on the PLN (2), PLN (3) is set to a single color. Or a black and white image. When PLN (2) and PLN (3) are color images, the reference image REF is a monochrome image. When PLN (2) and PLN (3) are black and white images, a single color is defined for the gradation values A2 and A3 for selecting PLN (2) and PLN (3) of the reference image REF.

  In the present embodiment, a color photograph or the like is extracted from the plane PLN (1), characters are extracted from the plane PLN (2), and a background is extracted from the plane PLN (3). The technique of distinguishing objects (extracting characters, extracting backgrounds) is well known and will not be described.

  The reference image creation unit 112 can create a reference image REF.

  The processing means 113 can perform image processing or image correction (resolution conversion, filtering processing, lightness correction, color tone correction, noise removal). Normally, this processing increases the compression rate during encoding.

  For example, since the plane PLN (2) only needs to know the character color on the restored document 100 ', the resolution of the dot pitch on the plane PLN (2) and the monochromatic color are defined on the plane PLN (2). In this case, the color gradation resolution can be lowered. Since the object of the plane PLN (2) is a character, the resolution is lowered and the visibility is not lowered so much. Further, if a character recognition process is performed on the plane PLN (2), a text code can be obtained. By associating this with a series of data sets to be finally generated (usually including text data in the data set), it is possible to search the restored document 100 ′ by text codes.

  Further, image processing for increasing the resolution may be performed by interpolation processing or the like. When the file size is large but the photo part is important, the image quality is improved. The reference image REF is not changed in the dot pitch in this embodiment, but can be changed.

  With respect to the plane PLN (2) and the reference image REF, noise can be removed by a method such as erasing the connected components of minute black pixels, thereby increasing the compression rate at the time of encoding.

  Note that the processing of each plane can be appropriately determined according to how the document is used. For example, if the photograph is considered important, the resolution of the plane PLN (1) should not be lowered. Conversely, if the photograph is not so important, the resolution of the plane PLN (1) should be lowered. However, the resolution of the plane PLN (2) may be increased. Since these are trade-offs between image quality and final information size, they are determined according to the application.

  The encoding means 114 is a method (a method suitable for compressing the object) that uses the planes PLN (1), PLN (2), PLN (3), and the reference image REF according to the type of object on the original document 100. , Different for each plane).

  The integration unit 115 can integrate the reference image REF encoded by the encoding unit 113 and the n planes PLN (1), PLN (2), and PLN (3) into a data set. It should be noted that at the time of integration, information about what attributes each plane has (for example, bitmap images such as photographs, information on characters, backgrounds, etc.) is included in the data set, for example, as described later. At the time of document restoration, planes unnecessary for the operator can be excluded using the plane exclusion unit 213. As a result, only a specific plane can be seen in the image representation. In this case, unnecessary information becomes invisible, so that the document can be easily viewed. Further, when data communication is performed, planes that are considered unnecessary are appropriately excluded from the data set, so that the amount of data to be transmitted / received can be reduced (thus shortening the transmission / reception time).

  FIG. 3 is an explanatory diagram illustrating the document conversion method according to the first embodiment. This document conversion method can be implemented using the document conversion apparatus 11 of FIG.

  In FIG. 3, first, three planes PLN (1), PLN (2), and PLN (3) corresponding to the encoding method are extracted from the original document 100 (plane extraction step: S101). In this plane extraction step S101, the object on the original document 100 is extracted by dividing it into three planes PLN (1), PLN (2), and PLN (3).

Next, three gradation values A1, A2, and A3 are assigned to each pixel, and one of the three planes PLN (1), PLN (2), and PLN (3) according to the three gradation values. A reference image REF for identifying the reference image is created (reference image creation step: S102). ,
Further, image processing or image correction (resolution conversion, filtering processing, lightness correction, tone correction, noise removal) is performed on the three planes PLN (1), PLN (2), and PLN (3) (processing step: S103). ).

  Thereafter, the three planes PLN (1), PLN (2), PLN (3) and the reference image REF are encoded (encoding step: S104). In the encoding step S104. The three planes PLN (1), PLN (2), PLN (3) and the reference image REF are encoded by a method according to the type of object on the original document 100. In the present embodiment, the three planes are encoded by different encoding methods.

  Then, the reference image REF encoded in the encoding step S104 and the three planes PLN (1), PLN (2), and PLN (3) are integrated into a data set.

It should be noted that the pixel values of the unreferenced areas of the planes PLN (1), PLN (2), and PLN (3) can be replaced with predetermined pixel values (for example, white, black, etc.). Thereby, the compression efficiency can be improved during encoding. When only the plane PLN (1) is referred to during image reproduction, a predetermined pixel value is assigned to the pixel corresponding to the character of the reference image REF on the plane PLN (1) using surrounding pixels. can do. When only the plane PLN (2) is referred to during image reproduction, the pixels other than the characters of the reference image REF on the plane PLN (2) have colors that make it easy to see the characters and reduce the compression efficiency. Pixel values that are not allowed to be applied can be given.

FIG. 4 is an explanatory diagram illustrating the document restoration apparatus according to the first embodiment.

  In FIG. 4, the document restoration device 21 includes a document decomposition / decryption unit 211, a gradation value acquisition unit 212, a plane exclusion unit 213, a plane identification unit 214, and a document restoration unit 215. In the present embodiment, the document restoration device 21 can acquire the document data DD and restore the original document 100 from the document data.

  The document decomposition / decryption unit 211 can decrypt the document data DD to generate three plane planes PLN (1), PLN (2), PLN (3) and a reference image REF.

  The gradation value acquisition unit 212 scans the pixels of the reference image REF, and can acquire any of the three gradation values A1, A2, and A3 given to the scanned pixels.

  The plane excluding unit 213 can exclude one or two of the three planes PLN (1), PLN (2), and PLN (3) from the processing target. The planes excluded by the plane excluding unit 213 are not included in the specific target by the plane identifying unit 214, so that only necessary objects can be displayed on the reproduced image 100 ′.

  The plane specifying unit 214 can specify the planes PLN (1), PLN (2), and PLN (3) corresponding to the three gradation values A1, A2, and A3.

  The document restoration unit 215 extracts the value on the plane specified by the plane identification unit 214 corresponding to the pixel given to the pixel position of the reference image REF, restores the document, and restores the restored document 100 ′. Can be obtained.

  In the case where a single color is defined for the objects on the planes PLN (2) and PLN (3), when the gradation value of the pixel of the reference image REF is A2 or A3, the restored document 100 ′ includes the plane PLN ( 2) Reflects the color defined on PLN (3). In addition, when a single color is defined corresponding to the gradation values A2 and A3 without previously defining colors in the planes PLN (2) and (3), these single colors are reflected in the restored image. Is done.

  FIG. 5 is an explanatory diagram illustrating the document restoration method according to the first embodiment. This document restoration method can be implemented using the document restoration apparatus 21 of FIG.

  In FIG. 5, document data DD is first decomposed into three planes PLN (1), PLN (2), PLN (3) and reference image REF, and these are subjected to decoding processing (document decomposition / decoding step). : S201).

  The pixels of the reference image REF are scanned to acquire the three gradation values A1, A2, and A3 assigned to each pixel (gradation value acquisition step: S202).

  A plane to be a predetermined target is excluded (plane exclusion step: S203).

  A plane corresponding to the three gradation values A1, A2, A3 is specified (plane specifying step: S204).

The pixel value given to the pixel position on the plane specified in the plane specifying step S204 is extracted to generate the restored document 100 ′ (document restoring step: S205).
[Second Embodiment]
6A and 6B are explanatory diagrams showing the document data structure of the second embodiment.

  In this embodiment, as shown in FIG. 6A, the original document 200 is the same as the original document 100 of the first embodiment (see FIG. 1A), and an 8-bit color image 201 and blue And a blue horizontal stripe filled character 202, and a red dot pattern background 203.

  Further, the document data DD is referred to n (n = 3 in this embodiment) planes PLN (1), PLN (2), PLN (3) extracted from the original document 200 shown in FIG. The image REF is integrated and configured as in the first embodiment, and the reference image REF is one of the planes PLN (1), PLN (2), and PLN (3) for each pixel. It is the same as in the first embodiment that the information for selecting is stored as values A1, A2, and A3 of m gradations (m = 3 in this embodiment).

  However, the plane PLN (2) and the reference image REF in FIG. 6B are different from the plane PLN (2) and the reference image REF (see FIG. 1B) in the first embodiment. A blue filled character and a blue horizontal stripe filled character 202 are described in the reference image REF, and a portion corresponding to the character 202 of the plane PLN (2) has a black fill and a black stripe fill figure B1. (See the plane PLN (2) in FIG. 7).

  The document data DD having the structure shown in FIG. 6B can be created by the document conversion apparatus 11 in FIG. 2, and can be restored by the document restoration apparatus 12 in FIG.

  FIG. 7 is an explanatory diagram illustrating a document conversion method according to the second embodiment. This document conversion method is basically the same as the document conversion method in the first embodiment. However, in the plane extraction step S101, in the first embodiment, the object on the original document 200 is extracted by being divided into three planes PLN (1), PLN (2), and PLN (3). Then, the object on the original document 100 is extracted by being divided into two planes PLN (1), PLN (3) and a reference image REF.

FIG. 8 is an explanatory diagram showing a document restoration method according to the second embodiment. This document restoration method is basically the same as the document restoration method in the first embodiment, and the restored document 200 'is restored in substantially the same manner as in the first embodiment. However, in the plane specifying step S204, in the first embodiment, the character 202 is restored by filling the reference image REF and the character object on the plane PLN (2). However, in the second embodiment, the character 202 is restored on the reference image REF. The character 202 is restored by painting the character object and the plane PLN (2).
[Third Embodiment]
9A and 9B are explanatory diagrams showing the document data structure of the third embodiment.

  In the present embodiment, as shown in FIG. 9A, an original document 300 is composed of an 8-bit color image 301 and filled characters in which the upper and lower sides are separately painted in blue and green (the upper region is denoted by reference numeral 302 and the lower part The area is indicated by reference numeral 303), a table 304 represented in black, and a background 305 with a red dot pattern.

  Further, the document data DD is the n (n = 4 in this embodiment) planes PLN (1), PLN (2), PLN (3), PLN (extracted from the original document 300 shown in FIG. 9B. 4) and the reference image REF are integrated. The reference image REF includes information for selecting one of the planes PLN (1), PLN (2), PLN (3), and PLN (4) for each pixel in m gradations (in this embodiment, m = 5) as values A1, A2, A3, A4, A5. That is, in this embodiment, n <m.

  The plane PLN (1) in FIG. 9B is composed of an 8-bit color image 301. In addition, the plane PLN (2) is composed of monochrome filled characters, the plane PLN (3) is composed of a monochrome table, and the plane PLN (4) is composed of a monochrome dot pattern.

  Further, as described above, the reference image REF is composed of areas of five gradation values A1, A2, A3, A4, and A5. The region having the gradation value A1 is formed corresponding to the color image 301 of the plane PLN (1). The region having the gradation value A2 is formed corresponding to the character upper region 302 on the plane PLN (2), and the region having the gradation value A3 is formed on the plane PLN (2). It is formed corresponding to the lower region 303. The region having the gradation value A4 is formed corresponding to the table 304 of the plane PLN (3), and the region having the gradation value A5 corresponds to the background 305 of the dot pattern of the plane PLN (4).

  The document data DD having the structure shown in FIG. 6B can be created by the document conversion apparatus 11 in FIG. 2, and can be restored by the document restoration apparatus 12 in FIG.

  In the present embodiment, the plane PLN (1) is displayed with pixel values on PLN (1). In the present embodiment, the planes PLN (2), (3), and (4) are not defined in color, and the reference image REF has colors corresponding to A2, A3, A4, and A5, respectively. Is defined. Therefore, the object (character in this embodiment) on the plane PLN (2) is defined in advance in the color defined in the gradation A2 area (in this case, blue) or in the gradation A3 area. Displayed in color (green here). The object of the plane PLN (3) (table in this embodiment) is displayed in a color (here black) defined in advance in the area of the gradation A3, and the object of the plane PLN (4) (this embodiment) In the form, a dot pattern) is displayed in a color (here, red) defined in advance in the area of gradation A4.

  The planes PLN (2), PLN (3), and PLN (4) can also be displayed with pixel values on the planes PLN (2), PLN (3), and PLN (4). In this case, colors are defined for objects on the planes PLN (2), PLN (3), and PLN (4).

  The document data DD having the structure shown in FIG. 9B can be created by the document conversion apparatus 11 shown in FIG. 2, and can be restored by the document restoration apparatus 12 shown in FIG.

  FIG. 10 is an explanatory diagram illustrating a document conversion method according to the third embodiment. This document conversion method is basically the same as the document conversion method in the first embodiment. However, in the reference image creation step S102, the character is associated with one gradation value A2, but in this embodiment, the character is associated with two gradation values A2 and A3. In this embodiment, since the table is added as an object to the original document 300, the number of planes is four in total.

FIG. 11 is an explanatory diagram illustrating a document restoration method according to the third embodiment. This document restoration method is basically the same as the document restoration method in the first embodiment, and the restoration document 300 ′ is restored in substantially the same manner as in the first embodiment. However, in the plane specifying step S204, the character 102 is restored by filling the reference image REF and the character object on the plane PLN (2) in the first embodiment, but in the third embodiment, the character 102 is restored on the reference image REF. The character upper region 302 and the character lower region 303 are restored by filling the two color character objects indicated by the gradation values A2 and A3 and the plane PLN (2).
[Fourth Embodiment]
12A and 12B are explanatory diagrams showing the document data structure of the fourth embodiment.

  In this embodiment, as shown in FIG. 12A, the original document 400 includes characters 401 decorated with gray gradation and a background 402 with a red dot pattern.

  Further, the document data DD is obtained by integrating n (n = 2 in this embodiment) planes PLN (1) and PLN (2) extracted from the original document 400 shown in FIG. 12B and the reference image REF. Has been configured. The reference image REF uses information for selecting one of the planes PLN (1) and PLN (2) for each pixel as values A1, A2,... Of m gradations (m = 16 in this embodiment).・ It has as A16. That is, in this embodiment, n <m.

  As described above, the reference image REF is composed of 16 gradation values A1, A2,..., A16. The pixel value on the corresponding plane PLN (1) is assigned to the pixel in the region having the gradation value A1. In addition, “white” is defined in the region having the gradation value A2, “black” is defined in the region having the gradation value A16, and stepwise is provided in the region having the gradation values A3 to A15. A gray color close to “white” to a gray color close to “black” is defined.

  The document data DD having the structure shown in FIG. 12B can be created by the document conversion apparatus 11 shown in FIG. 2, and can be restored by the document restoration apparatus 12 shown in FIG.

  In the present embodiment, the pixel value on PLN (1) corresponding to the pixel having the gradation value A1 on the reference image REF is displayed with the value of the pixel on the reference image REF. For the plane PLN (2), no color is defined, and white, gray, and black appear in the restored image corresponding to the gradation values A2 to A16 given to the pixels on the reference image REF, respectively.

  The planes PLN (2), PLN (3), and PLN (4) can also be displayed with pixel values on the planes PLN (2), PLN (3), and PLN (4). In this case, colors are defined for objects on the planes PLN (2), PLN (3), and PLN (4).

  The document data DD having the structure shown in FIG. 12B can be created by the document conversion apparatus 11 shown in FIG. 2, and can be restored by the document restoration apparatus 12 shown in FIG.

  FIG. 13 is an explanatory diagram illustrating a document conversion method according to the fourth embodiment. This document conversion method is basically the same as the document conversion method in the first embodiment. FIG. 14 is an explanatory diagram showing a document restoration method according to the fourth embodiment. This document restoration method is basically the same as the document restoration method according to the first embodiment, and is substantially the same as the first embodiment. The restored document 400 ′ is restored in the same manner as described above.

  In the fourth embodiment, it is preferable to employ a method suitable for multi-valued images for decoding the reference image REF. In the fourth embodiment, for example, an image in which a boundary between a graphic and a background is continuously changed is preferably used for an image when the gradation is frequently used.

It is explanatory drawing which shows the document data structure of 1st Embodiment, (A) is a figure which shows an original document, (B) is a figure which shows the document data by which each plane and the reference image were integrated. It is a block diagram which shows the document conversion apparatus of 1st Embodiment. It is explanatory drawing which shows the document conversion method of 1st Embodiment. It is explanatory drawing which shows the document restoration apparatus of 1st Embodiment. It is explanatory drawing which shows the document restoration method of 1st Embodiment. It is explanatory drawing which shows the document data structure of 2nd Embodiment, (A) is a figure which shows an original document, (B) is a figure which shows the document data by which each plane and the reference image were integrated. It is explanatory drawing which shows the document conversion method of 2nd Embodiment. It is explanatory drawing which shows the document restoration method of 2nd Embodiment. It is explanatory drawing which shows the document data structure of 3rd Embodiment, (A) is a figure which shows an original document, (B) is a figure which shows the document data by which each plane and the reference image were integrated. It is explanatory drawing which shows the document conversion method of 3rd Embodiment. It is explanatory drawing which shows the document restoration method of 3rd Embodiment. It is explanatory drawing which shows the document data structure of 4th Embodiment, (A) is a figure which shows an original document, (B) is a figure which shows the document data by which each plane and the reference image were integrated. It is explanatory drawing which shows the document conversion method of 4th Embodiment. It is explanatory drawing which shows the document restoration method of 4th Embodiment.

Explanation of symbols

11 Document conversion device 21 Document restoration device 100, 200, 300, 400 Original document
100 ', 200', 300 ', 400' Restored document 101, 201, 301 Color image 102, 202 Characters 103, 203, 305, 402 Background 111 Plain image extraction means 112 Reference image creation means 113 Correction means 114 Encoding means 115 Integration means 211 Document decomposition / decoding means 212 Tone value acquisition means 213 Plane exclusion means 214 Plane identification means 215 Document restoration means 302, 303, 404 Fill 304 Table Ax (x is a positive integer) Tone value DD Document data PLN (x) (x is a positive integer) Plane REF Reference image

Claims (23)

A document data structure obtained by extracting n planes from one original document and integrating the n planes as one document,
The n planes;
A reference image having information for selecting one of the n planes for each pixel as a value of m gradations;
A document data structure characterized by comprising:   2. The object on the original document is extracted by being divided into the n planes, or is divided and extracted on the n planes and the reference image. Document data structure.   3. The document data structure according to claim 1, wherein the n planes are encoded by a method according to a type of an object on the original document.   4. The document data structure according to claim 3, wherein at least one of the n planes is encoded by an encoding method different from an encoding method of other planes. Plane image extraction means for extracting n planes from one original document;
Reference image creation means for creating a reference image for specifying any of the n planes according to the value of m gradations, each pixel having a value of m gradations,
Encoding means for encoding the n planes and the reference image;
A document conversion apparatus comprising:   6. The plane image extracting unit extracts an object on an original document by dividing it into the n planes, or extracting the object on the n planes and the reference image. The document conversion device described.   7. The document conversion apparatus according to claim 5, wherein the encoding unit encodes the n planes or further the reference image by a method according to a type of an object on the original document. .   8. The encoding unit according to claim 5, wherein the encoding unit encodes at least one of the n planes by an encoding method different from an encoding method of other planes. 9. Document conversion device.   9. The document conversion apparatus according to claim 5, further comprising an integration unit that integrates the reference image and the n planes encoded by the encoding unit into a data set.   10. The document conversion apparatus according to claim 5, further comprising processing means for performing image processing or image correction. A document restoration device that acquires document data having the data structure according to claim 1 and restores the document from the document,
Document decomposition / decoding means for decomposing the document data into the n planes and the reference image, and performing decoding processing on the plane and the reference image;
Scanning means for scanning pixels of the reference image;
Gradation value acquisition means for acquiring m gradation values given to the pixels scanned by the scanning means;
Plane specifying means for specifying the plane corresponding to the value of the m gradation;
Pixel value extracting means for extracting a value on the plane specified by the plane specifying means corresponding to the pixel given to the pixel position of the reference image;
Document restoration means for restoring a document by assigning the pixel value extracted by the pixel value extraction means to the pixel on the image to be restored corresponding to each pixel of the reference image;
A document restoration apparatus comprising: Plane exclusion means for designating one or more of the n planes;
12. The document restoration apparatus according to claim 11, wherein the designated plane is not included in the target of the specific processing by the plane specifying unit, so that only necessary objects are displayed on the restored image. A plane extraction step of extracting n planes from one original document;
A reference image creating step for creating a reference image for specifying any of the n planes according to the value of the m gradation, wherein each pixel is provided with an m gradation value;
An encoding step of encoding the n planes and the reference image;
A document conversion method comprising:   14. In the plane extraction step, an object on an original document is extracted by being divided into the n planes, or is extracted by being divided into the n planes and the reference image. The document conversion method described.   The document conversion according to claim 13 or 14, wherein, in the encoding step, the n planes or the reference image is encoded by a method according to a type of an object on the original document. Method.   16. The document conversion method according to claim 15, wherein in the encoding step, at least one of the n planes is encoded by an encoding method different from an encoding method of other planes.   17. The document conversion method according to claim 13, further comprising an integration step of integrating the reference image and the n planes encoded in the encoding step into a data set.   The document conversion method according to claim 13, further comprising a processing step of performing image processing or image correction. A document restoration method for obtaining a document having the data structure according to claim 1 and restoring the document from the document,
Decoding a document having the data structure into n planes and a reference image;
A gradation value acquisition step of scanning pixels of the reference image and acquiring m gradation values given to the scanned pixels;
A plane specifying step for specifying the plane corresponding to the value of the m gradation;
A document restoration step of restoring a document by extracting a pixel value given to the position of the pixel on the plane identified in the plane identification step;
A document restoration method comprising: A plane excluding step of designating one or more of the n planes,
19. The document restoration method according to claim 18, wherein the designated plane is not included in a specific target by the plane specifying means, so that only a necessary object is imaged.   The document conversion program which performs each step in the document conversion method in any one of Claims 13-18.   21. A computer-readable document restoration program that executes each step in the image restoration method according to claim 19 or 20.   A computer-readable recording medium storing the document conversion program according to claim 21 and / or the document restoration program according to claim 22.