JP2019195117A - Information processing apparatus, information processing method, and program - Google Patents

Abstract

To determine whether a PDF file is a scanned PDF with high accuracy.SOLUTION: An information processing apparatus includes: first determination means for determining whether a PDF file is a scan PDF created from a scanned image obtained by scanning a document on the basis of whether an image of the same size as the page size specified in the PDF file is included in the PDF file; deriving means for deriving the number of character areas in the image included in the PDF file; and a second determination unit for determining whether the PDF file is a scanned PDF on the basis of the number of the character areas derived by the deriving means.SELECTED DRAWING: Figure 5

Description

  The present invention relates to an information processing apparatus, an information processing method, and a program.

  There are various methods for creating a PDF format file (hereinafter referred to as a PDF file). For example, there is an application (for example, Microsoft Word or PowerPoint (trademark), etc.) that can be directly saved as a PDF file by specifying PDF as a format for saving the file. In addition, even in an application in which a PDF cannot be specified when saving a file, a method for converting print data to be output to a PDF file by selecting a PDF conversion driver instead of a printer driver when executing print processing is also available. is there. Furthermore, some devices such as copiers can store an image obtained by reading a paper document with a scanner (hereinafter referred to as a scanned image) in a PDF format. Hereinafter, an application that can be directly saved as a PDF file is referred to as PDF creation software. A PDF file created from a scanned image is called a scan PDF.

  The scan PDF includes an image corresponding to the paper size (an image having a size equivalent to the page size defined in the PDF file) in the PDF file. FIG. 3 is a diagram illustrating an example of a scan PDF. The PDF file 301 includes an image 302 corresponding to the paper size. However, the size of the image included in the PDF file is not always the same as the paper size. As in the case of FIG. 3, the image size may be smaller than the paper size by the margin. A character string such as “Invoice” in the PDF file 301 is all part of a picture in the image, and no character code information is included in the PDF file 301.

  Conventionally, there is software (so-called PDF editing software) that performs editing, image conversion, printing, and the like on an input PDF file. Some PDF editing software determines whether or not an input PDF file is a scan PDF, and changes subsequent processing and modules to be used according to the determination result.

  For example, when creating a scan PDF, there is a possibility that a scan image obtained when a paper document is read by a scanner is tilted or noisy. Therefore, some PDF editing software determines whether the input PDF file is a scan PDF, and automatically performs image processing such as tilt correction and noise removal when the input PDF file is a scan PDF. There is. Therefore, a technique for accurately determining whether a PDF file is a scanned PDF is required. The reason is that if a PDF file created using the PDF creation software is erroneously determined as a scan PDF and image processing such as tilt correction and noise removal is performed, useless processing is executed. Because.

  Patent Document 1 discloses whether a PDF file is genuine or non-genuine (that is, PDF created using Adobe software) based on the creator's information (specifically, the Producer value) included in the PDF file. A technique for determining whether the file is a file is described.

JP 2007-156903 A

  However, the technique described in Patent Document 1 cannot accurately determine whether a PDF file is a scan PDF. The reason is that the creator information included in the PDF file indicates the name of software or the like used for conversion to the PDF format, and does not indicate whether a scanned image is included.

  In view of the above problems, an object of the present invention is to accurately determine whether a PDF file is a scanned PDF.

  The present invention creates a PDF file from a scanned image acquired by scanning a document based on whether the PDF file includes an image having a size equivalent to the page size specified by the PDF file. A first determination unit for determining whether the scanned PDF is a scanned PDF, a deriving unit for deriving the number of character regions in the image included in the PDF file, and the number of the character regions derived by the deriving unit An information processing apparatus comprising: a second determination unit configured to determine whether the PDF file is a scan PDF based on the second file.

  According to the present invention, it is possible to accurately determine whether a PDF file is a scanned PDF.

1 is a block diagram showing a configuration of a copying machine 100 according to a first embodiment. The block diagram which shows the structure of the information processing apparatus 200 in 1st Embodiment. An example of scan PDF An example of a PDF file created using the PDF file creation software Flowchart of PDF determination process in the first embodiment The figure which shows the result of having performed the area division processing on the image Example of high compression PDF Flow chart of PDF determination processing in the second embodiment Diagram explaining the method for specifying the character area

[First Embodiment]
Embodiments of the present invention will be described below with reference to the drawings. The following embodiments do not limit the present invention. In addition, not all combinations of features described in the following embodiments are essential as means for solving the problems of the present invention.

<Configuration of copier and information processing apparatus>
The system according to this embodiment includes a copying machine 100 and an information processing apparatus 200. FIG. 1 is a block diagram showing the configuration of the copying machine 100 according to this embodiment. The copier 100 includes a scanner unit 101, a transmission / reception unit 102, a printer unit 103, and a control unit 104.

  FIG. 2 is a block diagram illustrating a configuration of the information processing apparatus 200 according to the present embodiment. An information processing apparatus 200 connected to the copying machine 100 is, for example, a personal computer (PC) or the like, and has a CPU, a ROM, and a RAM inside. The program of the information processing apparatus 200 stored in the ROM is expanded in the RAM, and the CPU executes the expanded program, whereby processing in each component shown in FIG. 2 is executed. The reception unit 205 that receives a user instruction generally includes a keyboard and a mouse, but is not limited thereto. In FIG. 2, the display unit and the reception unit are separate components, but the display unit and the reception unit may be integrated components such as a touch panel.

<Flow for creating scan PDF from scanned image>
When the scanner unit 101 of the copying machine 100 scans a document, a scanned image (also referred to as scanned image data) is generated. The control unit 104 converts the generated scan image into a scan PDF, and the transmission / reception unit 102 transmits the scan PDF to the information processing apparatus 200. Then, the transmission / reception unit 201 of the information processing apparatus 200 receives the scan PDF, and the control unit 203 stores the received scan PDF in the storage unit 202. In addition to the scanned PDF, the storage unit 202 stores a PDF file created by the user using the PDF creation software.

  The user selects one PDF file from one or a plurality of PDF files stored in the storage unit 202 via the reception unit 205. Then, the control unit 203 displays the PDF file on the display unit 204.

  At this time, when displaying the PDF file on the display unit 204, the control unit 203 determines whether the PDF file selected by the user is a scan PDF. If this determination result is true, that is, if the PDF file selected by the user is a scan PDF, the control unit 203 executes image processing such as black point removal and inclination correction on the image included in the PDF file. Alternatively, in this case, a message for confirming whether or not to execute such image processing may be displayed on the display unit 204 to allow the user to select whether or not to execute the image processing.

<Regarding area division processing>
In the present embodiment, a region division technique is used to specify a character region in an image. Hereinafter, each process of area division will be described in detail.

(1) Binarization The control unit 203 obtains a binary image composed of black pixels and white pixels by binarizing the scan image. By binarization, a pixel having a density value equal to or higher than a predetermined threshold in the scanned image is a black pixel, and a pixel having a density value lower than the predetermined threshold is a white pixel. In the following description, it is assumed that the scanned image is 100 DPI, but it goes without saying that the resolution of the scanned image is not limited to this resolution.

(2) Detection of black pixel block The control unit 203 tracks the outline of black pixels connected by 8-connection to the binary image, thereby collecting black pixel blocks that exist continuously in any of the eight directions. (A black pixel block) is detected. Eight connected means that pixels of the same color (black in this case) are continuous in any one of the eight directions of upper left, left, lower left, lower, lower right, right, upper right, and upper. . On the other hand, 4-connection means that pixels of the same color are continuous in any of the four directions of left, bottom, right, and top. In the processing of (2) black pixel block detection in this embodiment, a single black pixel in which none of the eight adjacent pixels existing in the eight directions is a black pixel is detected. On the other hand, a black pixel in which a black pixel exists in any one of eight adjacent pixels existing in the eight directions is detected as a black pixel block together with the adjacent black pixels. Reference numeral 901 in FIG. 9 indicates an example of a black pixel block detected by the control unit 203.

  In addition, the control unit 203 derives position information of the circumscribed rectangle of the detected black pixel block, specifically, the X coordinate and the Y coordinate of each of the four vertices of the circumscribed rectangle. It is assumed that the X axis extends in the right direction and the Y axis extends in the downward direction. Reference numeral 902 in FIG. 9 indicates a circumscribed rectangle of the black pixel block 901. In this specification, “width” refers to the length in the X-axis direction, and “height” refers to the length in the Y-axis direction. In addition, when expressed as “rectangular” in the present specification without any particular notice, an oblique rectangle is not included, and all four sides represent a rectangle parallel to either the X axis or the Y axis.

(3) Detection of Table Area The control unit 203 determines whether or not all of the following three conditions are satisfied for each detected black pixel block, and configures a black pixel block that satisfies all three conditions as a table frame The black pixel block is determined.

  The first condition is that the width of the circumscribed rectangle of the black pixel block is equal to or greater than a predetermined threshold value, and the height of the circumscribed rectangle is equal to or greater than the predetermined threshold value. Here, as an example, it is determined whether both the width and the height are 0.25 cm or more corresponding to 100 pixels.

  The second condition is that the filling rate of the black pixel block inside the circumscribed rectangle is not more than a predetermined threshold value. Here, as an example, it is determined whether the ratio of the black pixel block to the circumscribed rectangle is 20% or less.

  The third condition is that the difference between the maximum width of the black pixel block and the width of the circumscribed rectangle and the difference between the maximum height of the black pixel block and the height of the circumscribed rectangle are both small. That is, the difference between the maximum width of the black pixel block and the width of the circumscribed rectangle is equal to or smaller than a predetermined threshold value, and the difference between the maximum height of the black pixel block and the circumscribed rectangle is equal to or smaller than the predetermined threshold value. That is. Here, as an example, the difference between the maximum width of the black pixel block and the width of the circumscribed rectangle and the difference between the maximum height of the black pixel block and the height of the circumscribed rectangle are both 10 pixels or less. Shall be determined.

  The control unit 203 determines whether each of the black pixel blocks satisfies all the above first to third conditions, thereby determining whether the black pixel block is a black pixel block constituting the table frame. The position information of the circumscribed rectangle of the black pixel block constituting the frame line is stored in the storage unit 202. A circumscribed rectangular area having position information stored in this manner is called a table area. In the case shown in FIG. 9, as a result of the detection of the table area, the black pixel block 901 is determined as the black pixel block constituting the table frame line, and the circumscribed rectangle 902 area is detected as the table area. In the present embodiment, a black pixel block that satisfies all of the first to third conditions described above is determined as a black pixel block that forms a table frame line, but the determination condition is not limited to this. For example, a black pixel block that satisfies at least one of the first to third conditions may be determined as a black pixel block that forms a front frame.

(4) Identification cell recognition The control unit 203 identifies a recognition cell inside the table area. Here, the “recognition cell” is a circumscribed rectangle of the white pixel block inside the table area. In order to identify the recognition cell, it is necessary to detect a white pixel block by tracking the outline of the white pixel in the table area. Then, the control unit 203 determines whether or not each of the detected white pixel blocks satisfies the following three conditions, and identifies a circumscribed rectangle of the white pixel block that satisfies all the three conditions as a recognition cell.

  The first condition is that the width of the circumscribed rectangle of the white pixel block is equal to or greater than a predetermined threshold value, and the height of the circumscribed rectangle is equal to or greater than the predetermined threshold value. Here, as an example, it is determined whether both the width and the height are 20 pixels or more.

  The second condition is that the filling rate of the black pixel block inside the circumscribed rectangle is not more than a predetermined threshold value. Here, as an example, it is determined whether the ratio of the black pixel block to the circumscribed rectangle is 20% or less.

  The third condition is that the difference between the maximum width of the white pixel block and the width of the circumscribed rectangle and the difference between the maximum height of the white pixel block and the height of the circumscribed rectangle are both small. That is, the difference between the maximum width of the white pixel block and the width of the circumscribed rectangle is equal to or smaller than a predetermined threshold value, and the difference between the maximum height of the white pixel block and the circumscribed rectangle is equal to or smaller than the predetermined threshold value. That is. Here, as an example, the difference between the maximum width of the white pixel block and the width of the circumscribed rectangle and the difference between the maximum height of the white pixel block and the height of the circumscribed rectangle are both 5 pixels or less. To determine.

  Reference numerals 903 and 904 in FIG. 9 indicate recognition cells identified by the control unit 203. The control unit 203 stores the position information of the identified recognition cell in the storage unit 202.

  In this embodiment, the circumscribed rectangle of the white pixel block that satisfies all the above first to third conditions is specified as the recognition cell, but the determination condition is not limited to this. For example, a circumscribed rectangle of a white pixel block that satisfies at least one of the first to third conditions may be specified as the recognition cell.

(5) Identification of Character Area in Recognition Cell The control unit 203 determines whether there is a black pixel block surrounded by a white pixel block inscribed in each recognition cell inside each recognition cell. When it is determined that there is a black pixel block, a circumscribed rectangle is set for all the black pixel blocks determined to be present.

  Further, when a plurality of circumscribed rectangles are set in one recognition cell, the control unit 203 detects circumscribed rectangles having the closest distance based on the distance between the circumscribed rectangles. Specifically, the control unit 203 selects circumscribed rectangles one by one, and detects circumscribed rectangles whose distance from the selected circumscribed rectangle is equal to or less than a predetermined threshold. Here, as an example, it is determined whether the distance between circumscribed rectangles is 0.05 cm or less corresponding to 20 pixels.

  Furthermore, when such a circumscribed rectangle is detected, the control unit 203 integrates the selected circumscribed rectangle and the circumscribed rectangle detected with respect to the selected circumscribed rectangle. That is, the control unit 203 sets a new circumscribed rectangle that circumscribes both of these circumscribed rectangles, and deletes the selected circumscribed rectangle and the detected circumscribed rectangle.

  After setting the new circumscribed rectangle and completing the deletion of the two circumscribed rectangles, the control unit 203 again selects the circumscribed rectangles in the recognition cell one by one from the beginning, and the distance between them is equal to or less than a predetermined threshold value. Integrate circumscribed rectangles. The above processing is repeated. That is, the integration of circumscribed rectangles is repeated until there is no circumscribed rectangle whose distance between each other is equal to or less than a predetermined threshold.

  As described above, in this embodiment, circumscribing rectangles existing in one recognition cell are integrated, but circumscribing rectangles straddling the recognition cells are not integrated.

  The circumscribed rectangle that has been set after the above processing is called a character area. The above processing is called identification of the character area in the recognition cell. The control unit 203 stores the position information of the character area existing inside the recognition cell in the storage unit 202 in association with the recognition cell.

  In the case of FIG. 9, reference numerals 905 and 906 indicate character areas. The position information of the character area 905 is stored in the storage unit 202 in association with the recognition cell 903. Further, the position information of the character region 906 is stored in the storage unit 202 in association with the recognition cell 904.

<About PDF judgment processing>
In this embodiment, in order to determine whether or not the PDF file is a scanned PDF, the PDF file includes an image having a size equivalent to the paper size specified by the header of the PDF file, that is, an image corresponding to the paper size. Determine if it is. If an image corresponding to the paper size is included in the PDF file, the image is divided into regions to specify character regions. Then, based on the information of the character area, it is determined whether the PDF file is a scan PDF. The “paper size” referred to here is a value such as CropBox or Mediabox set for each page in the PDF format. Hereinafter, processing for determining whether or not a PDF file is a scan PDF (referred to as PDF file determination processing) in the present embodiment will be described with reference to FIG.

  In step S501, the control unit 203 analyzes the determination target PDF file. By the analysis in this step, information about objects such as images, character strings, graphics, etc. included in the PDF file is acquired. Hereinafter, “step S˜” is simply abbreviated as “S˜”.

  In step S502, the control unit 203 determines whether an image corresponding to the paper size is included in the PDF file. Specifically, the page width x [mm] and height y [mm] are obtained based on values such as CropBox and Mediabox, and then the width is x-5 [mm] or more and the height is y-5. It is determined whether an image of [mm] or more is included in the PDF file. Here, 5 is a buffer (that is, an allowable error). If the determination result of this step is false, the process proceeds to S503, whereas if the determination result is true, the process proceeds to S504.

  Hereinafter, the reason for determining whether an image corresponding to the paper size is included in the PDF file in S502 will be described. Consider a case where a scan PDF is created by simply specifying a PDF format from a scan image in a device such as a multifunction peripheral. In this case, a PDF file is usually created in which only one image object corresponding to the paper size exists in the PDF file and no other objects exist. Therefore, if it is determined whether or not the scanned PDF is based on an object included in the PDF file, a determination condition may be considered as to whether an image object corresponding to the paper size is included in the PDF file. Therefore, in this embodiment, it is determined in S502 whether an image corresponding to the paper size is included in the PDF file.

  However, it should be noted that some PDF files created using PDF creation software such as Microsoft's PowerPoint (trademark) include images corresponding to the paper size. FIG. 4 is a diagram illustrating an example of a PDF file created using PowerPoint (trademark). As shown in FIG. 4B, the PDF file 401 includes an image 405 corresponding to the paper size as a background image. Reference numerals 402 to 404 in FIG. 4A indicate character strings having character code information, not images.

  Here, suppose a case where it is determined whether or not the PDF file is a scan PDF based only on the condition that an image (object) corresponding to the paper size is included in the PDF file. In this case, since the PDF file 401 includes an image 405 corresponding to the paper size, the PDF file 401 is erroneously determined as a scan PDF. Therefore, in this embodiment, in addition to the determination process of S502, the subsequent determination process of S507 is provided to improve the determination accuracy.

  In the present embodiment, the possibility of a blank space is taken into consideration when creating a PDF file from a scanned image. That is, even if the page size and the image size do not completely match, if the image having a size close to the page size is included to some extent, it is considered that the scanned image is included in the PDF file. Here, the allowable error is set to 5 [mm], but this value may be appropriately changed according to the scanning environment of the user.

  In step S503, the control unit 203 determines that the determination target PDF file is not a scan PDF, and the series of processing ends.

  In step S504, the control unit 203 extracts an image determined to be equivalent to the paper size in step S502 from the PDF file.

  In step S505, the control unit 203 executes the above-described region division process on the image acquired in step S504. FIG. 6 shows an example of the result of executing the area division processing. In FIG. 6, a rectangle drawn with a broken line indicates an area determined as a character area as a result of the area division process. For example, the character area 601 of “Invoice”. Similarly, reference numerals 602 to 605 also indicate character areas, and some rectangles drawn by broken lines without other reference numerals also indicate character areas.

  In step S506, the control unit 203 counts the number of character areas in the image. For example, in the case of FIG. 6, the number of character areas to be counted is 28.

  In step S507, the control unit 203 determines whether the number of character areas acquired in step S506 is equal to or greater than a predetermined number. Here, as an example, the predetermined number is the threshold value 5. The predetermined number used in this step may be changed as appropriate according to the user's environment. When the determination result of this step is true (that is, when the number of character areas is a predetermined number or more), the process proceeds to S508. On the other hand, when the determination result of this step is false (that is, when the number of character areas is less than the predetermined number), the process proceeds to S509. For example, in the case of the PDF file shown in FIG. 6, since the number of character areas is 28 ≧ the predetermined threshold value 5, the result of the determination in this step is that of S508.

  In step S508, the control unit 203 determines that the determination target PDF file is a scan PDF, and the series of processing ends.

  In step S509, the control unit 203 determines that the determination target PDF file is not a scan PDF, and the series of processing ends.

  S507 to S509 will be described in detail. In the case of scan PDF, a plurality of character areas are often included in an image as in the case shown in FIG. In particular, in the case of a scan PDF created by scanning a form or the like, a plurality of character areas are included in the image.

  On the other hand, in the case of a PDF file created using PDF creation software, as shown in the case of FIG. 4, an image corresponding to the paper size is a background image for improving the appearance, and a character area is included in the image. Often not included. For example, the character strings 402 to 404 in FIG. 4A are not stored in the image but are stored in the PDF file as objects including character code information. That is, when a certain number of character areas are included in an image corresponding to the paper size included in the PDF file, it is considered that the PDF file is highly likely to be a scanned PDF. Therefore, in the present embodiment, the processes of S507 to S509 are performed.

  In the above-described embodiment, when there are five or more character areas in the image corresponding to the paper size, the PDF file is determined to be a scan PDF (YES in S507 → S508), and a certain amount of buffer is provided. Yes. The reason for this is that there is a possibility that some character areas are also included in the image of the PDF file created using the PDF creation software.

  The above is the content of the PDF file determination process in the present embodiment.

<About the effect of this embodiment>
According to the present embodiment, it is possible to determine whether a PDF file is a scanned PDF with high accuracy.

[Second Embodiment]
In the first embodiment, a case has been described where the number of images included in the PDF file is one (image 302 in FIG. 3 and image 405 in FIG. 4B). On the other hand, in the present embodiment, it is assumed that the number of images included in the PDF file is plural.

  When creating a scan PDF using a copying machine, a scan image may be divided into a plurality of parts and stored in a file. FIG. 7 is a diagram illustrating an example of a case where the scan image is divided into a plurality of images. In the scan PDF acquired when the same original as the original scanned when the PDF file 301 illustrated in FIG. 3 is acquired is scanned. A plurality of images included in FIG.

  In the case shown in FIG. 3, the image included in the PDF file 301 that is a scanned PDF is only the image 302 that is a scanned image. On the other hand, in the case shown in FIG. 7, the image included in the scan PDF is a background image 701 that is an image corresponding to the paper size as shown in FIG. 7A and the image shown in FIG. It is divided into character images 702 to 705.

  The reason for dividing the image stored in the file in this way is to reduce the file size of the scan PDF while not degrading the image quality of the character string when rendering based on the scan PDF. is there. As shown in FIG. 7, the scanned image is separated into a background image and a character image, and only the background image is compressed at a high compression rate. By doing so, the file size can be reduced while maintaining the readability of the character string. The scan PDF compressed in this manner is hereinafter referred to as “high compression PDF”. A copier that supports high-compression PDF may create a high-compression PDF according to the user's selection.

  In the present embodiment, a method for determining whether a PDF file is a scan PDF when the PDF file is a highly compressed PDF will be described.

<About PDF judgment processing>
Hereinafter, the PDF file determination processing in the present embodiment will be described with reference to FIG.

  S801 to S803 are the same as S501 to S503 (FIG. 5) of the first embodiment. However, in this embodiment, when the determination result of S802 is true, the process proceeds to S804.

  In step S804, the control unit 203 extracts all images from the PDF file. For example, in the case shown in FIG. 7, a background image 701 and character images 702 to 705 are extracted.

  In step S805, the control unit 203 creates one image by merging all the images extracted in step S804.

  In step S806, the above-described region division processing is executed on the image created in step S805. S806 to S810 are the same as S505 to S509 (FIG. 5) of the first embodiment. The above is the content of the PDF file determination process in the present embodiment.

<Reasons for merging multiple images>
Hereinafter, the reason for merging a plurality of images in S805 will be described.

  In high-compression PDF, a scanned image is separated into a background image and a character image. However, the separation accuracy is not 100%. For example, noise may be included in the image during scanning, and the character string may be divided due to the noise, and a part of the character string may be included in the background image. In this case, there is a possibility that the accuracy of specifying the character area is deteriorated.

  In the case of an image including a table, the ruled lines of the table are included in the background image. However, when the ruled line of the table and the character string in the table are merged, the accuracy of character region identification by region division may increase.

  For these reasons, the images are merged in step S805 for the purpose of improving the accuracy of character area specification by area division.

<Effects and Modifications of the Present Embodiment>
According to the present embodiment, even when the PDF file is a highly compressed PDF, it is possible to accurately determine whether the PDF file is a scan PDF.

  In the above-described form, the character region is specified by performing region division processing on one image obtained by merging a plurality of images extracted from the PDF file, and based on the number of the specified character regions, It is determined whether the PDF file is a scan PDF. However, the present embodiment is not limited to the above-described form. For example, the character region is specified by performing region division processing on each of the images extracted from the PDF file. Then, based on the sum derived by summing up the number of character areas corresponding to each of the images, a mode in which it is determined whether the PDF file is a scan PDF can be considered.

  Further, in the high-compression PDF, in addition to expressing the character part as shown in FIG. 7 as a plurality of images, the scanned image is separated into the character part and the background, and then the separated character part is expressed as one image. There are also things. The present embodiment is also applicable when the PDF file is such a highly compressed PDF.

[Other Embodiments]
The present invention supplies a program that realizes one or more functions of the above-described embodiments to a system or apparatus via a network or a storage medium, and one or more processors in a computer of the system or apparatus read and execute the program This process can be realized. It can also be realized by a circuit (for example, ASIC) that realizes one or more functions.

Claims (10)

Based on whether the PDF file includes an image having a size equivalent to the page size defined in the PDF file, the PDF file is a scanned PDF created from a scanned image acquired by scanning a document. First determination means for determining whether or not
Deriving means for deriving the number of character areas in the image included in the PDF file;
An information processing apparatus comprising: a second determination unit that determines whether the PDF file is a scan PDF based on the number of the character areas derived by the deriving unit. When the PDF file does not include an image having a size equivalent to the page size defined in the PDF file, the determination result by the first determination unit is true,
The information processing apparatus according to claim 1, wherein when the PDF file includes an image having a size equivalent to a page size defined by the PDF file, the determination result is false.   When the determination result by the first determination unit is false and the number of images included in the PDF file is 1, the character region in the image is specified by performing region division processing on the image The information processing apparatus according to claim 1, further comprising a specifying unit that performs the processing.   In the case where the determination result by the first determination unit is false and the number of images included in the PDF file is plural, a creation unit is further provided for creating one image by merging the plurality of images. The information processing apparatus according to claim 1 or 2.   5. The information according to claim 4, further comprising specifying means for specifying a character area in the one image by performing region division processing on the one image created by the creating means. Processing equipment.   The information processing apparatus according to claim 3, wherein the deriving unit derives the number of character areas by counting the character areas specified by the specifying unit. When the number of the character areas is equal to or greater than a predetermined number, the second determination unit determines that the PDF file is a scan PDF,
The said 2nd determination means determines with the said PDF file not being a scanning PDF when the number of the said character area is less than the said predetermined number, The any one of Claim 1 thru | or 6 characterized by the above-mentioned. Information processing device.   The image having a size equivalent to the page size defined by the PDF file includes an image having the same size as the page size and an image smaller than the page size. The information processing apparatus according to item. Based on whether the PDF file includes an image having a size equivalent to the page size defined in the PDF file, the PDF file is a scanned PDF created from a scanned image acquired by scanning a document. A step of determining whether or not
Deriving the number of character regions in the image included in the PDF file;
And determining whether the PDF file is a scanned PDF based on the derived number of character regions.   A program for causing a computer to execute the method according to claim 9.

Images