Area determination device, area determination method, and program

Abstract

To provide an area determination device, an area determination method, and a program capable of correctly determining a character area to be proofread from layout data in which character codes are embedded.SOLUTION: An area determination device includes an acquisition unit that acquires first layout data including character information corresponding to characters written in a layout image to be proofread, an extraction unit that extracts a character area described in the layout image on the basis of character information included in the first layout data, a generation unit that generates second layout data showing an image that does not include a region not extracted by the extraction unit, and a determination unit that uses the second layout data to determine an area indicating a section on the layout.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to an area determination device, an area determination method, and a program. [Background technology]

[0002] Proofreading is currently being carried out on text printed on product packages, such as the product name, content labeling, and handling instructions. In this case, for example, proofreading is carried out using data in Portable Document Format (PDF) format that corresponds to the layout (image) of the product package. Proofreading is carried out using software that has the function of automatically determining sections (areas) on the layout from the layout and proofreading the text written within each determined area.

[0003] As shown in FIG. 8, for example, if proofreading is performed without determining the sections (areas) on the layout, proofreading may be performed in an order that ignores sentence units, as shown by the symbol D. In this case, a set of characters that ignores the order of sentences, paragraphs, or words becomes the subject of proofreading, making it difficult to perform correct proofreading. On the other hand, as shown in FIG. 9, if the sections (areas) on the layout are determined and the text (characters) extracted from each determined area is the subject of proofreading, proofreading can be performed without changing the order in which the sentences, paragraphs, or words are written. In this way, a technique for determining sections (areas) on the layout before proofreading is necessary for correct proofreading.

[0004] Furthermore, Patent Document 1 discloses a technology for removing noise from an image read by a scanner, etc. When proofreading text within each area extracted from a printed matter, it is possible to improve the accuracy of proofreading by removing noise in that area. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Publication No. 9-247461 Summary of the Invention [Problem to be solved by the invention]

[0006] However, PDF is not a file format intended for proofreading, but for displaying or printing according to the layout. Therefore, even if character information such as character codes of characters is embedded in PDF, information such as line breaks indicating the boundaries of the text or paragraph areas to be proofread may not be included. In addition, printed matter often includes pictures or backgrounds. In such cases, it is difficult to extract the correct area to be proofread in the process of extracting areas from printed matter. As a result, for example, as shown in FIG. 10, an incorrect area E may be extracted from image G.

[0007] The present invention has been made in consideration of the above-mentioned circumstances, and aims to provide an area determination device, an area determination method, and a program that can correctly determine the area of ​​a character to be proofread from layout data in which character codes are embedded. [Means for solving the problem]

[0008] The area determination device of the present invention includes an acquisition unit that acquires first layout data including character information corresponding to characters written in a layout image to be proofread, an extraction unit that extracts an area of ​​the characters written in the layout image based on the character information included in the first layout data, a generation unit that generates second layout data indicating an image of the layout image including the area extracted by the extraction unit and not including an area not extracted by the extraction unit, and a determination unit that uses the second layout data to determine an area indicating a partition on the layout. The generating unit generates a color of a character included in the second layout data and a color of the background area based on a color of the background area of ​​the image corresponding to the second layout data. do.

[0009] The area determination method of the present invention is an area determination method performed by a computer, in which an acquisition unit acquires first layout data including character information corresponding to characters written in a layout image to be proofread, an extraction unit extracts an area of ​​the characters written in the layout image based on the character information included in the first layout data, a generation unit generates second layout data indicating an image of the layout image including the area extracted by the extraction unit and not including an area not extracted by the extraction unit, and a determination unit uses the second layout data to determine an area indicating a partition on the layout. The generating unit generates a color of a character included in the second layout data and a color of the background area based on a color of a background area of ​​the image corresponding to the second layout data, so that the color of the character included in the second layout data and the color of the background area are different colors. do.

[0010] A program of the present invention is a program for operating as the above-described area determination device, and is a program for causing the computer to function as each unit of the area determination device. Effect of the Invention

[0011] According to the present invention, the area of ​​the character to be proofread can be correctly determined from the layout data in which the character code is embedded. [Brief description of the drawings]

[0012] [Figure 1] 1 is a block diagram showing an example of the configuration of a calibration device 10 according to an embodiment. [Diagram 2] FIG. 1 is a diagram showing an example of layout data 120 according to an embodiment. [Diagram 3] FIG. 13 is a diagram showing an example of a layout image G according to an embodiment. [Figure 4] 2A to 2C are diagrams illustrating a process performed by the calibration device 10 according to the embodiment. [Diagram 5] 2A to 2C are diagrams illustrating a process performed by the calibration device 10 according to the embodiment. [Figure 6] 4 is a flowchart showing the flow of processing performed by the calibration device 10 according to the embodiment. [Figure 7] FIG. 13 is a diagram illustrating a modified example of the embodiment. [Figure 8] FIG. 1 is a diagram illustrating a conventional example. [Figure 9] FIG. 1 is a diagram illustrating a conventional example. [Figure 10] FIG. 1 is a diagram illustrating a conventional example. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0014] FIG. 1 is a block diagram showing an example of the configuration of a proofreading device 10 according to an embodiment. The proofreading device 10 is a computer device that proofreads character strings written on a layout image in which a product package or the like is designed. For example, a server device, a cloud, a PC (Personal Computer), or the like can be applied as the proofreading device 10. The proofreading device 10 is an example of an "area determination device."

[0015] In the following description, a case will be described in which the proofreading device 10 performs proofreading using layout data in PDF format in which character codes (one example of "character information") are embedded. However, the present invention is not limited to this. For proofreading by the proofreading device 10, data in any file format can be used as long as the layout data includes at least character information.

[0016] The calibration device 10 includes, for example, a communication unit 11, a storage unit 12, and a control unit 13. The communication unit 11 communicates with an external device via a communication network or the like. The communication unit 11 receives layout data to be calibrated, for example, from an external server device. The communication unit 11 also transmits the results of the calibration to the external server device or the like.

[0017] The storage unit 12 is configured by a storage medium such as a hard disk drive (HDD), a flash memory, an electrically erasable programmable read only memory (EEPROM), a random access read / write memory (RAM), a read only memory (ROM), or a combination of these. The storage unit 12 stores programs for executing various processes of the calibration device 10, and temporary data used when performing the various processes. The storage unit 12 stores, for example, layout data 120. The layout data 120 is information related to a layout image to be calibrated.

[0018] The control unit 13 is realized by causing a central processing unit (CPU) provided as hardware in the calibration device 10 to execute a program. The control unit 13 comprehensively controls the calibration device 10. The control unit 13 includes, for example, an acquisition unit 130, an extraction unit 131, a generation unit 132, a determination unit 133, a calibration unit 134, and a device control unit 135.

[0019] The acquiring unit 130 acquires the first layout data. The first layout data is information indicating a layout image to be proofread. The first layout data is data including character information corresponding to characters written in the layout. The first layout data is layout data in PDF format in which character codes are embedded.

[0020] For example, the acquisition unit 130 acquires the first layout data from an external server device or the like via the communication unit 11. The acquisition unit 130 stores the acquired first layout data in the layout data 120. The acquisition unit 130 also outputs the acquired first layout data to the extraction unit 131.

[0021] The extraction unit 131 extracts an area of ​​a character written in a layout (image) based on character information included in the first layout data. The extraction unit 131 acquires attribute information of a character written in a layout image based on, for example, a character code included in the first layout data. The character attribute information here is information about a character, such as information indicating a position where the character is written, and information indicating a character code, font, size, style, color, etc. of the written character.

[0022] The extraction unit 131 specifies an area in which a character is shown based on information indicating the position where the character is written and information indicating the size of the written character, etc., and extracts the specified area. For example, the extraction unit 131 extracts an area in which the character is shown for each character. The extraction unit 131 outputs information indicating the extracted character area to the generation unit 132.

[0023] Generating unit 132 generates second layout data. The second layout data is data of a layout including the character region extracted by extracting unit 131. The second layout data is data of a layout not including the region of the first layout data that was not extracted as a character region by extracting unit 131.

[0024] The generating unit 132 generates the second layout data by, for example, transferring a character area extracted from the first layout data to the second layout data. The generating unit 132 copies (duplicates) the character area extracted from the layout of the first layout data. Then, the generating unit 132 pastes (attaches) the copied character area into a layout image corresponding to the second layout data.

[0025] On the other hand, the generating unit 132 does not include in the layout of the second layout data an area that is not extracted as a character area from the layout image of the first layout data. An area that is not extracted as a character area from the layout image of the first layout data is an area other than a character area that includes character information, for example, an area in which a picture is shown, an area of ​​a logo shown as an image, or an area in which only a background is shown, to which no character information is associated. The generating unit 132 stores the generated second layout data in the layout data 120.

[0026] The determination unit 133 uses the second layout data to determine a section (area) on the layout. The determination unit 133 may determine the area using any conventional method. For example, the determination unit 133 determines the area based on a contrast difference or a color difference in the layout image. The determination unit 133 outputs the result of determining the area to the proofreading unit 134.

[0027] The proofreading unit 134 performs proofreading for each area determined by the determination unit 133. For example, the proofreading unit 134 determines whether or not the area determined by the determination unit 133 is an area in which characters are written, and if it is an area in which characters are written, the proofreading unit 134 proofreads the group of characters written in that area as a string of characters with connections to a sentence, a paragraph, or words.

[0028] The proofreading unit 134 may proofread the character string using any conventional method. For example, the proofreading unit 134 performs proofreading by dividing the character string into phrases and judging whether the connections and dependencies between phrases are correct, whether there is any spelling variation, and the like. The judgment unit 133 outputs the proofreading result. The proofreading unit 134 transmits the proofreading result to an external server device or the like via the communication unit 11, for example.

[0029] The device control unit 135 performs overall control of the calibration device 10. For example, the device control unit 135 outputs the first layout data received by the communication unit 11 to the acquisition unit 130. The device control unit 135 outputs the calibration result calibrated by the calibration unit 134 to the communication unit 11 and transmits it to an external server device.

[0030] 2 is a diagram showing an example of layout data 120 according to an embodiment. The layout data 120 is generated for each layout image, for example. The layout data 120 includes items such as a layout number, first layout data, and second layout data. The layout number is identification information such as a number that uniquely identifies a layout image to be proofread. The first layout data is layout data for a layout image identified by the layout number. The second layout data is layout data generated by the generation unit 132 based on the layout image identified by the layout number.

[0031] 3 is a diagram showing an example of a layout image G according to an embodiment. As shown in FIG. 3, the layout image G to be proofread includes, for example, an image G1 of a product description, an image G2 of a pattern, and an image G3 of a logo. The part in which the product description is written is designed with a column layout, a frame, and the like. The pattern includes an image of corn and corn soup, and a design in which the logo of "corn potage" is surrounded by a rectangular area.

[0032] Such rectangular areas surrounding a logo are often designed to make the logo more eye-catching, for example by creating a contrast between the frame of the rectangle and its surroundings. In area determination, such areas with differences in contrast are often recognized as the boundaries of the areas. If a character string is written near the logo, the logo area and the character string area may be determined to be the same area. In such cases, it may not be possible to extract the correct area to be proofread (see area E in Figure 10).

[0033] Fig. 4 is a diagram for explaining the process performed by the proofreading device 10 according to the embodiment. Fig. 4 shows an example of a layout image G corresponding to the second layout data. As shown in the example of Fig. 4, a character area extracted from the first layout data is pasted onto the layout image G corresponding to the second layout data.

[0034] Layout image G corresponding to the second layout data shows the character area extracted from the first layout data, for example, image G1# of product description image G1 with characters embedded with character codes. For example, image G2 excludes image portions of product description image G1, such as one-dimensional barcodes, two-dimensional codes, and recycling marks. This is because character codes are not associated with images of codes, marks, etc.

[0035] Moreover, the layout image G corresponding to the second layout data does not show areas other than the character area extracted from the first layout data, such as the pattern image G2 and the logo image G3. This is because the images G2 and G3 are not associated with character codes. Moreover, the layout image G corresponding to the second layout data shows an image G4 of the character area extracted from the first layout data. This is because the characters written in the image G4 are associated with character codes.

[0036] Fig. 5 is a diagram for explaining the processing performed by the calibration device 10 according to the embodiment. Fig. 5 shows the result of determining the sections (areas) on the layout in the layout image G corresponding to the second layout data. As shown in the example of Fig. 5, a correct area to be calibrated is extracted from the layout image G corresponding to the second layout data. This is because the area of ​​the logo shown in the original layout (first layout data) is no longer included in the second layout data, and as a result, there is no longer any erroneous determination that the area of ​​the logo and the area of ​​the character string are the same area.

[0037] 6 is a flowchart showing a flow of processing performed by the proofreading device 10 according to the embodiment. The proofreading device 10 acquires first layout data (step S10), and extracts a character region from the acquired first layout data (step S11). The proofreading device 10 extracts the character region using character information included in the first layout data.

[0038] The proofreading device 10 generates second layout data (step S12). The proofreading device 10 generates the second layout data by pasting the character area extracted in step S11 onto a layout image corresponding to the second layout data. The proofreading device 10 determines sections (areas) on the layout using the layout image corresponding to the second layout data (step S13). For each area determined in step S13, the proofreading device 10 proofreads the character strings shown in that area (step S14). The proofreading device 10 transmits the proofreading results to, for example, an external server device.

[0039] As described above, the calibration device 10 of the embodiment includes the acquisition unit 130, the extraction unit 131, the generation unit 132, and the determination unit 133. The acquisition unit 130 acquires the first layout data. The first layout data is information indicating a layout image to be calibrated, and is information including character codes (an example of character information) corresponding to characters described in the layout image. The extraction unit 131 extracts an area of ​​the characters described in the layout image based on the character codes included in the first layout data. The generation unit 132 generates the second layout data. The second layout data is information indicating an image that includes an area extracted by the extraction unit 131 and does not include an area not extracted by the extraction unit 131, of the layout image to be calibrated. The determination unit 133 uses the second layout data to determine an area indicating a section on the layout.

[0040] As a result, the proofreading device 10 of the embodiment can determine the sections (areas) on the layout using image information (second layout data) in which only the character areas are extracted from the layout image. Therefore, area determination can be performed without being influenced by the design of the picture or logo in a state in which the design of the picture or logo has been removed from the layout image. Therefore, the area in which the character string to be proofread is written can be correctly determined.

[0041] Next, a modified example of the embodiment will be described. This modified example differs from the above-described embodiment in that second layout data is generated so that the determination unit 133 determines the area more accurately.

[0042] (First Modification of the Embodiment) The generating unit 132 generates the second layout data so that the color of the characters written in the area extracted by the extracting unit 131 is different from the background color in the second layout data. As shown in the example of Fig. 5, layout image G often has a pattern or the like shown in the background. In this case, the characters may be shown in white against a colored background.

[0043] On the other hand, since the image corresponding to the second layout data is an image in which only the text area is pasted, in most cases no background color is set. In such a case, for example, the background color of the image corresponding to the second layout data will be white on the display.

[0044] In this case, if the white characters extracted from the first layout data are directly reflected in the image of the second layout data, the background color and the character color will become the same color, which makes it difficult for the determining unit 133 to correctly determine the area.

[0045] To address this issue, in this modification, if the color of the character extracted from the first layout data is the same as the background color of the second layout data, the generating unit 132 changes the color of the extracted character to a color different from the background color and pastes the color-changed character onto the second layout data. This creates a contrast between the character pasted onto the second layout data and the background, allowing the determining unit 133 to correctly determine the area.

[0046] (Modification 2 of the embodiment) The generation unit 132 determines the attributes of the first character in the second layout data based on the relative relationship between a character (hereinafter referred to as the first character) written in the area extracted by the extraction unit 131 and a character (hereinafter referred to as the second character) in the area extracted around the character (hereinafter referred to as the second character).

[0047] Here, it is assumed that there is no character between the first character and the second character. The positional relationship between the first character and the second character is a positional relationship in which a boundary of an area can be set between the first character and the second character when determining the area.

[0048] For example, in the case of a layout in which an area boundary is set between the first character and the second character, the font of the characters is often different between the area in which the first character is written and the area in which the second character is written, so that a user viewing the layout image can easily recognize the division of a sentence or paragraph. In this modified example, such a part designed to make the division aware by changing the color or font of the characters is reflected in the second layout data.

[0049] Specifically, when the fonts of the first character and the second character are different, the generating unit 132 generates the second layout data so that the fonts of the first character and the second character in the second layout data are different without unifying them, in order to enable the determining unit 133 to correctly determine the boundary between the first character and the second character, which may exist between the first character and the second character, such as a sentence, a paragraph, or a column.

[0050] Furthermore, if there is a space of a predetermined size or more between the first character and the second character, the generating unit 132 may make the fonts of the first character and the second character different in the second layout data. This is because the space between the first character and the second character may indicate a line break or a column boundary between the first character and the second character, and this boundary can be correctly determined by the determining unit 133.

[0051] The predetermined size of the blank space may be set arbitrarily according to the design of the layout image. For example, when a blank space having a size of one character or 1.5 characters or more of the character size of the first character or the second character exists between the first character and the second character, the font of the first character and the second character in the second layout data may be different.

[0052] On the other hand, when the fonts of the first character and the second character are the same, the generating unit 132 sets the fonts of the first character and the second character in the second layout data to be the same, in order to prevent the determining unit 133 from erroneously setting a boundary between the first character and the second character, since it is unlikely that a boundary between the first character and the second character exists.

[0053] When the first character and the second character are far away (not close to each other), the generating unit 132 may set the fonts of the first character and the second character in the second layout data to be the same or different, regardless of whether the fonts of the first character and the second character are different or the same. In this case, the difference in font between the first character and the second character is unlikely to affect the determination by the determining unit 133 as to whether or not to set the boundary between the areas.

[0054] In this case, for example, when the first character and the second character are far away (not close to each other) and the fonts of the first character and the second character are different, the generating unit 132 makes the fonts of the first character and the second character in the second layout data the same. This makes it possible to reduce the number of fonts embedded in the second layout data and prevent an increase in data capacity.

[0055] In the above, the case where the second layout data is generated based on the difference in the font of the characters and the presence or absence of spaces has been described as an example, but the present invention is not limited to this. The second layout data may reflect the difference in any information related to the characters, not limited to the font of the characters. The any information related to the characters is a character attribute, such as the size, style, color, brightness, the presence or absence of an underline, and the color of the underline if there is an underline. For example, when the character colors of the first character and the second character are different, the generating unit 132 may generate the second layout data such that the colors of the characters corresponding to the first character and the second character are different in the second layout data.

[0056] Furthermore, when the character attributes of a first character and a second character adjacent thereto are different, the generating unit 132 may at least reflect in the second layout data that these character attributes are different. For example, when the fonts of the first character and the second character are different, the generating unit 132 may generate the second layout data such that the character attributes other than the fonts of the first character and the second character in the second layout data (for example, the color and size of the character) are different.

[0057] Furthermore, when the character attributes of a first character and a second character adjacent thereto are different, the generating unit 132 may at least reflect in the second layout data that these character attributes are different. For example, when the fonts of the first character and the second character are different, the generating unit 132 may generate the second layout data such that the character attributes other than the fonts of the first character and the second character in the second layout data (for example, the color and size of the character) are different.

[0058] FIG. 7 is a diagram for explaining a modified example of the embodiment. FIG. 7 shows an image G in the case where the color of the characters extracted from the first layout data is reflected in the second layout data without being unified as it is. As shown in the example of FIG. 7, an image G5 of the text "Please make sure to give us an IC tag..." is shown in a color different from the color of the surrounding text. Also, an image G6 of the text "This is an IC tag. Please use it in the microwave..." is shown in a color different from the color of the surrounding text. Also, an image G6 of the text "Sweet corn mellow... enclosed" is shown in a color different from the color of the surrounding text.

[0059] In this way, a character string shown in a different color from the surrounding characters is often a group of character strings that is appropriate as a unit of proofreading, such as a sentence that calls attention. A character string that is a different color from the surrounding characters is likely to be determined as a group of characters that are included in the same area as a section (area) on the layout. For this reason, by directly reflecting the color of the characters extracted from the first layout data in the second layout data, it is expected that the determination unit 133 will correctly determine an appropriate boundary as a unit of proofreading.

[0060] Specifically, the generating unit 132 acquires position coordinates of the first region in the layout image of the first layout data. The position coordinates include information indicating, for example, the position coordinates of the center of gravity, the horizontal length, and the vertical length. Based on the position coordinates of the first coordinates, the generating unit 132 sets the position of the second region in the second layout data to the same position as the position of the first region in the first layout data.

[0061] In layout images of product packages and the like, each element of the product description, such as the product name, ingredients, and nutritional information, is often arranged so that the user can easily read it. The generating unit 132 reflects the arrangement designed in the original layout image in the second layout data without changing it. This allows the judging unit 133 to correctly judge the boundary.

[0062] (Modification 3 of the embodiment) The generating unit 132 may determine an area (hereinafter, referred to as a second area) in the second layout data that corresponds to the first area (hereinafter, referred to as a first area) extracted from the first layout data, based on position information of the first area.

[0063] Specifically, the generating unit 132 acquires position coordinates of the first region in the layout image of the first layout data. The position coordinates include information indicating, for example, the position coordinates of the center of gravity, the horizontal length, and the vertical length. Based on the position coordinates of the first coordinates, the generating unit 132 sets the position of the second region in the second layout data to the same position as the position of the first region in the first layout data.

[0064] In layout images of product packages and the like, each element of the product description, such as the product name, ingredients, and nutritional information, is often arranged so that the user can easily read it. The generating unit 132 reflects the arrangement designed in the original layout image in the second layout data without changing it. This allows the judging unit 133 to correctly judge the boundary.

[0065] (Fourth Modification of the Embodiment) The generating unit 132 may make the background of the image corresponding to the second layout data a striped pattern. The striped pattern here is a pattern in which one color (called a first color) and another color (called a second color) are alternately repeated along a predetermined direction (vertical, horizontal, diagonal, etc.).

[0066] For example, consider a case where the background of the image corresponding to the second layout data is a black and white striped pattern. If the color of the characters extracted from the first layout data is white, even if the characters are pasted as is onto the image corresponding to the second layout data, the contrast is created in the black parts of the striped pattern, making it possible to recognize the presence of the characters. If the color of the characters extracted from the first layout data is black, even if the characters are pasted as is onto the image corresponding to the second layout data, making it possible to recognize the presence of the characters in the white parts of the striped pattern. Therefore, a contrast is created between the background and the characters, making it possible for the determination unit 133 to correctly determine the area.

[0067] The calibration device 10 in the above-described embodiment may be realized in whole or in part by a computer. In that case, a program for realizing this function may be recorded in a computer-readable recording medium, and the program recorded in the recording medium may be read into a computer system and executed to realize the function. The term "computer system" as used herein includes hardware such as an OS and peripheral devices. The term "computer-readable recording medium" refers to portable media such as flexible disks, optical magnetic disks, ROMs, and CD-ROMs, and storage devices such as hard disks built into a computer system. The term "computer-readable recording medium" may also include a medium that dynamically holds a program for a short period of time, such as a communication line when a program is transmitted via a network such as the Internet or a communication line such as a telephone line, and a medium that holds a program for a certain period of time, such as a volatile memory inside a computer system that is a server or client in that case. The above-described program may be a program for realizing a part of the above-described function, or may be a program that can realize the above-described function in combination with a program already recorded in the computer system, or may be a program that is realized using a programmable logic device such as an FPGA.

[0068] Although an embodiment of the present invention has been described in detail above with reference to the drawings, the specific configuration is not limited to this embodiment, and designs that do not deviate from the gist of the present invention are also included. [Explanation of symbols]

[0069] 10...Calibration device 130…Acquisition Department 131...Extraction part 132...Generation section 133…Judgment section 134…Proofreading Department

Claims

1. an acquisition unit that acquires first layout data including character information corresponding to characters written in a layout image to be proofread; an extraction unit that extracts an area of ​​characters written in the layout image based on character information included in the first layout data; a generating unit that generates second layout data representing an image of the layout image that includes the area extracted by the extracting unit and does not include the area not extracted by the extracting unit; a determination unit that determines an area indicating a partition on a layout by using the second layout data; Equipped with the generation unit makes a color of a character included in the second layout data different from a color of a background area that is a background of an image corresponding to the second layout data, based on a color of the background area of ​​the image corresponding to the second layout data; Area determination device.

2. an acquisition unit that acquires first layout data including character information corresponding to characters written in a layout image to be proofread; an extraction unit that extracts an area of ​​characters written in the layout image based on character information included in the first layout data; a generating unit that generates second layout data representing an image of the layout image that includes the area extracted by the extracting unit and does not include the area not extracted by the extracting unit; a determination unit that determines an area indicating a partition on a layout by using the second layout data; Equipped with When the extraction unit extracts a plurality of regions and the regions have different character attributes, the generation unit generates the second layout data so that the characters corresponding to the regions have different attributes. Area determination device.

3. the generating unit causes attributes of characters corresponding to the respective areas included in the second layout data to be different when the distances of the respective areas in the first layout data are close to each other; The area determination device according to claim 2 .

4. The attribute is a font of a character or a color of a character. The area determination device according to claim 2 or 3.

5. an acquisition unit that acquires first layout data including character information corresponding to characters written in a layout image to be proofread; an extraction unit that extracts an area of ​​characters written in the layout image based on character information included in the first layout data; a generating unit that generates second layout data representing an image of the layout image that includes the area extracted by the extracting unit and does not include the area not extracted by the extracting unit; a determination unit that determines an area indicating a partition on a layout by using the second layout data; Equipped with the generation unit sets, in the second layout data, an area corresponding to the extracted area at the same position as the extracted area extracted in the first layout data, based on position coordinates of the area extracted by the extraction unit. Area determination device.

6. an acquisition unit that acquires first layout data including character information corresponding to characters written in a layout image to be proofread; an extraction unit that extracts an area of ​​characters written in the layout image based on character information included in the first layout data; a generating unit that generates second layout data representing an image of the layout image that includes the area extracted by the extracting unit and does not include the area not extracted by the extracting unit; a determination unit that determines an area indicating a partition on a layout by using the second layout data; Equipped with the generation unit sets a striped pattern as a color of a background region in the second layout data; Area determination device.

7. A region determination method performed by a computer, comprising the steps of: The acquisition unit acquires first layout data including character information corresponding to characters written in a layout image to be proofread; an extraction unit extracts an area of ​​characters written in the layout image based on character information included in the first layout data; a generating unit generating second layout data representing an image of the layout image including the area extracted by the extracting unit and not including the area not extracted by the extracting unit; a determination unit that determines an area indicating a section on a layout by using the second layout data; the generation unit makes a color of a character included in the second layout data different from a color of a background area that is a background of an image corresponding to the second layout data, based on a color of the background area of ​​the image corresponding to the second layout data; Area determination method.

8. A program for causing a computer to operate as the area determination device according to claim 1 , the program causing the computer to function as each unit included in the area determination device.

Images