JP3994625B2 - Image forming apparatus, image forming method, and computer-readable recording medium storing image forming program - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to an image forming technique for recognizing a character string from a character image included in a predetermined area of each page of a document composed of a plurality of pages and forming an image for a cover and / or a back cover.
[0002]
[Background Art and Problems to be Solved by the Invention]
An optical character reading (OCR) technique for reading a document with a scanner and recognizing a character string from a read image or recognizing a table layout is known. For example, Japanese Patent Application Laid-Open No. 9-231291 describes a technique for automatically generating a form format by recognizing a character string such as a date or name printed in advance on a document and creating layout information. .
[0003]
A facsimile apparatus described in Japanese Patent Laid-Open No. 11-289407 is known. This facsimile apparatus acquires sender information and destination information based on a key operation at the time of transmission, and adds a cover page on which a destination name and the number of transmissions are arranged to the first page for transmission.
[0004]
By the way, when storing a printed material obtained by copying a document in a file, a cover may be attached to the printed material or a back cover may be attached. In this case, in addition to the copy work, it is necessary to start the application software and create a cover and spine separately. The work of creating a cover sheet or the like is a very time-consuming work for the user. For this reason, there is a strong demand for simplifying the work of creating a cover and the like and improving the efficiency of office work.
[0005]
However, there is no prior art that takes into account the creation of a cover or spine using the OCR technique.
[0006]
SUMMARY OF THE INVENTION Accordingly, it is an object of the present invention to provide an image forming technique that can easily create a cover or a back cover using the OCR technique.
[0007]
[Means for Solving the Problems]
To achieve the above object, the present invention is configured as follows for each claim.
[0008]
(1) a character recognition unit for recognizing a character string from a character image included in a predetermined area on each page of a document composed of a plurality of pages;
Character strings recognized for each predetermined area on each page Comparison is made based on the arrangement of characters. When the type of character string with the same character arrangement is one, the character string is determined as one character string to be arranged, and the character arrangement with the same character arrangement is determined. When there are multiple types of characters, the character string with the same number of characters and the number of characters that is at least the maximum is set as one character string to be placed. A decision part to decide;
And an image forming apparatus including a forming unit that forms an image for a front cover and / or a back cover on which the determined character string is arranged.
[0010]
( 2 The character recognition unit is the image forming apparatus according to (1), which recognizes a character string representing a title, a company name, or a date.
[0011]
( 3 The image forming apparatus according to (1), wherein the predetermined area is a header area and / or a footer area of a document.
[0012]
( 4 The image forming apparatus according to (1), further including a size changing unit that changes a character size of the character string to be arranged in accordance with a region where the recognized character string is arranged.
[0013]
( 5 ) The size changing unit calculates the character size based on the size of the area and the number of characters of the character string to be arranged ( 4 ).
[0014]
( 6 The image forming apparatus according to (1), further including a setting unit configured to set a predetermined form in which areas for arranging recognized character strings are arranged.
[0015]
( 7 ) The setting unit is capable of selecting a form to be used from a plurality of stored forms. 6 ).
[0016]
( 8 ) A reading unit that reads the document,
The image forming apparatus according to (1), further including an output unit that outputs an image formed by the forming unit.
[0017]
( 9 And (b) further including a printing unit that prints an image output from the output unit. 8 ).
[0018]
( 10 The output unit further outputs an image of the document read by the reading unit ( 8 ) Or ( 9 ).
[0020]
(11) recognizing a character string from a character image included in a predetermined area on each page of a document composed of a plurality of pages;
Character strings recognized for each predetermined area on each page Comparison is made based on the arrangement of characters. When the type of character string with the same character arrangement is one, the character string is determined as one character string to be arranged, and the character arrangement with the same character arrangement is determined. When there are multiple types of characters, the character string with the same number of characters and the number of characters that is at least the maximum is set as one character string to be placed. A step to determine;
Forming an image for a cover and / or spine with the determined character string arranged thereon.
[0021]
(12) A procedure for recognizing a character string from a character image included in a predetermined area on each page of a document consisting of a plurality of pages;
Character strings recognized for each predetermined area on each page Comparison is made based on the arrangement of characters. When the type of character string with the same character arrangement is one, the character string is determined as one character string to be arranged, and the character arrangement with the same character arrangement is determined. When there are multiple types of characters, the character string with the same number of characters and the number of characters that is at least the maximum is set as one character string to be placed. Procedures to determine,
A computer-readable recording medium storing an image forming program having a procedure for forming an image for a cover and / or a back cover on which a determined character string is arranged.
[0022]
DETAILED DESCRIPTION OF THE INVENTION
Hereinafter, embodiments of the present invention will be described with reference to the drawings.
[0023]
FIG. 1 is a configuration diagram illustrating a configuration of an image forming system.
[0024]
In the image forming system 10, a scanner 12 that reads a document, a printer 13 that prints an image, and a digital copying machine 14 are connected to each other via a network 11. The image read by the scanner 12 can be printed not only by the printer 13 but also by the digital copying machine 14. In addition to reading a document and printing an image, the digital copying machine 14 can output the read image to a printer 13 or a personal computer (not shown) via the network 11. The present invention is applied to the digital copying machine 14.
[0025]
[Embodiment 1]
FIG. 2 is a block diagram showing a schematic configuration of the digital copying machine 14.
[0026]
The digital copying machine 14 includes a reading unit 21 that reads a document, an image processing unit 22 that processes the read image, a printing unit 23 that prints the processed image, an operation panel unit 24 that is operated by a user, and a storage. And a control unit 26 that controls each unit.
[0027]
The reading unit 21 includes an automatic document feeder (ADF) 27. A plurality of originals stacked on the ADF 27 are conveyed one by one to a predetermined reading position. The user operates the operation panel unit 24 to switch the display screen and the copy mode, and input the number of copies.
[0028]
The image processing unit 22 includes a header / footer region extraction unit 31, an OCR unit 32, a determination unit 33, an adaptation unit 34, a synthesis processing unit 35, a copy processing unit 36, and a binarization unit 37. Have.
[0029]
The header / footer area extraction unit 31 extracts an image included in a portion corresponding to the header area and / or the footer area of the document from the image read from the document.
[0030]
The OCR unit 32 sequentially extracts character images from the extracted image, recognizes the character images, and converts them into character code data. Recognizable characters include all characters, numbers, and symbols to which character code data is assigned, and further includes external characters registered by the user as a pattern. The OCR unit 32 also recognizes the font and font size. The OCR unit 32 further determines the item represented by the recognized character string. The items include “title”, “company name”, and “date”. The OCR unit 32 adds the determined item to the character string as an attribute of the character string. The attributes include “title”, “company name”, and “date”. For example, when the OCR unit 32 determines that the recognized character string item is “title”, the OCR unit 32 adds an attribute “title” to the character string. In the case of a document composed of a plurality of pages, the OCR unit 32 performs character recognition and attribute addition for all pages.
[0031]
The determination unit 33 compares the recognized character strings and determines a character string to be used for the cover and / or the back cover for each attribute.
[0032]
The matching unit 34 calculates the optimum font size of the character string to be arranged based on the size of the area where the determined character string is arranged and the number of characters of the character string.
[0033]
The composition processing unit 35 arranges the character code data of the determined character string in the area using the calculated font size, and forms an image for the cover and / or the back cover.
[0034]
The copy processing unit 36 performs copy image processing such as smoothing and edge enhancement, and the binarization unit 37 performs binarization processing on the input image.
[0035]
The storage unit 25 stores parameters necessary for image processing. The storage unit 25 further stores a plurality of forms in which areas for arranging character strings are arranged. Forms include a cover form used for creating a cover and a back cover form used for creating a back cover. Each of the cover form and the back cover form has a plurality of patterns depending on the paper size, the arrangement of areas, and the like. The user can select a desired form from a plurality of forms.
[0036]
FIG. 3 is a diagram illustrating an example of the operation panel unit 24 on which a copy mode selection screen is displayed.
[0037]
The operation panel unit 24 includes a liquid crystal touch panel 41 on which various screens are displayed, a numeric keypad 42 for setting the number of copies, a start key 43 for instructing operation stop, and a stop key 44 for instructing operation stop. , Is provided. A copy mode selection screen is currently displayed on the liquid crystal touch panel 41. The digital copying machine 14 has four modes: a normal copy mode, a cover creation mode, a back cover creation mode, and a cover / back cover creation mode. The user can instruct any of the touch keys 45a to 45d in the liquid crystal touch panel 41 and select a desired mode. When the user does not select a mode, the normal copy mode is set as the default mode.
[0038]
FIG. 4 is a diagram showing an example of a document composed of a plurality of pages. FIG. 5 is a diagram illustrating an example of a predetermined area on each page of the document.
[0039]
As shown in FIG. 4, the title 53, company name 54, and creation date / time 55 of the document 50 are generally often described in a header area or a footer area. By performing OCR processing on character images included in the header area and footer area and recognizing character strings, it is possible to create a cover or spine cover. Therefore, as shown in FIG. 5, a header area 51 and a footer area 52 are set as predetermined areas on each page of the document 50. Default values are set for the dimensions of the areas 51 and 52. For example, the header area 51 is set in a range of 15 mm from the upper edge of the paper, and the footer area 52 is also set in a range of 15 mm from the lower edge of the paper. The user can freely specify the size of the header region 51 and the size of the footer region 52 by operating the operation panel unit 24. The dimensions of the header area 51 and the footer area 52 may be different.
[0040]
When the predetermined areas 51 and 52 are applied to the original 50 shown in FIG. 4, the header area 51 on the first page includes a character string representing the title 53 “ab proposal”. In the footer area 52, “ AAAA A character string representing a company name 54 “corporation” and a character string representing a date 55 “January 20, 2000” are included.
[0041]
FIG. 6A is a view showing an example of a cover form 61, and FIG. 6B is a view showing an example of a back cover form 62. FIG. FIG. 7A shows an example of a cover 71 created by applying the cover form 61 shown in FIG. 6A, and FIG. 7B shows a spine form shown in FIG. 6B. It is a figure which shows an example of the spine 72 created by applying 62. FIG.
[0042]
As shown in FIG. 6A, the cover form 61 has a title area 61a, a company name area 61b, and a date area 61c arranged in order from the top. The regions 61a to 61c are arranged in a center alignment along the width direction of the foam 61 (left and right direction in the figure). As shown in FIG. 6B, the spine form 62 also has a title area 62a, a company name area 62b, and a date area 62c arranged in order from the top. However, the areas 62 a to 62 c of the spine cover form 62 are smaller than the areas 61 a to 61 c of the cover form 61 and are arranged in the substantially left half of the form 62. The spine form 62 further includes a ruled line frame 63 surrounding the title area 62a, a ruled line frame 64 surrounding the company name area 62b and the year / month / day area 62c, and the two ruled line frames 63 and 64. And an outer ruled line frame 65 that surrounds.
[0043]
8 to 15 are flowcharts for explaining the operation of the present embodiment. FIG. 16 is an example showing the result of the OCR process. FIG. 17 is an example showing the result of the matching process.
[0044]
FIG. 8 shows a main flowchart. When the normal copy mode is selected (S11 “Yes”), the normal copy mode process is executed (S12). When the cover creation mode is selected (S13 “Yes”), a cover selection process is executed (S14), and then a cover creation mode process is executed (S15). When the spine creation mode is selected (S16 “Yes”), the spine selection process is executed (S17), and the spine creation mode process is executed (S18). When the cover / back cover creation mode is selected (S19 “Yes”), a cover / back cover selection process is executed (S20), and a cover / back cover creation mode process is executed (S21). If the user does not select a mode (S19 “No”), a default normal copy mode process is executed (S22).
[0045]
In the cover selection process (S14), the user selects what kind of cover 71 is to be created. Specifically, a list of cover forms 61 pre-stored in the storage unit 25 is displayed on the liquid crystal touch panel 41, and the user selects a desired cover form 61 from the list. Similarly, in the spine cover selection process (S17), the user selects a desired spine cover form 62. In the cover / back cover selection process (S20), the user selects the desired forms 61 and 62 for the front cover and the back cover. By using the forms 61 and 62, an image for a cover and / or a back cover can be easily and quickly formed.
[0046]
FIG. 9 is a flowchart showing the procedure of normal copy mode processing.
[0047]
The read image is subjected to copy image processing such as edge enhancement and smoothing (S31), binarized, and printed (S32). Steps S31 and S32 are repeated for all pages of the document 50 (S33).
[0048]
FIG. 10 is a flowchart showing the procedure of the cover creation mode process.
[0049]
First, images included in portions corresponding to the header area 51 and the footer area 52 of the document 50 are extracted from the image of each page (S41). The size of the image to be extracted is equal to the size set in the header area 51 and the footer area 52.
[0050]
Next, the extracted character image is subjected to OCR processing, and a character string representing a title, company name, and date is recognized (S42). As a rule for creating the document 50, it is predetermined that the title 53 is described in the header area 51 and the company name 54 and the date 55 are described in the footer area 52. An attribute “title” is added to a character string recognized as a title. Similarly, an attribute “company name” is added to the character string recognized as the company name, and an attribute “year / month / day” is added to the character string recognized as the date. In the OCR process, the font and font size of the character string are also recognized. An example of the result of the OCR process is as shown in FIG.
[0051]
The read image including the header area 51 and the footer area 52 is subjected to copy image processing (S43), and then binarized and printed (S44) as in the normal copy mode processing.
[0052]
Steps S41 to S44 are repeated for all pages of the document 50 (S45). Thereafter, a determination process for determining a character string to be arranged on the cover form 61, that is, a title, a company name, and a date is executed (S46), and the decided character string is arranged on the cover form 61 to create a cover 71. A cover creation process is executed (S47).
[0053]
FIG. 13 is a flowchart illustrating the procedure of the determination process.
[0054]
When it is determined that the character string to which the attribute “title” is added is one type (S71 “Yes”), it is determined that the character string is a recognition result of the attribute “title” (S72). . Similarly, when the character string of the attribute “company name” is one type (S71 “Yes”), it is determined that the character string is a recognition result of the attribute “company name” (S72). When the character string of the attribute “year / month / day” is one type (S71 “Yes”), it is determined that the character string is the recognition result of the attribute “year / month / day” (S72).
[0055]
As a case where there is only one type of character string to which the same attribute is added, specifically, (1) when there is only one document, (2) it is a document consisting of a plurality of pages and the title 53 is the same. (3) In the case of a so-called 2-in-1 original and the title 53 and the like are the same.
[0056]
On the other hand, if it is determined that there are two or more character strings to which the same attribute is added (S71 “No”), the number of recognized character strings is counted for each character string having the same attribute. (S73). For example, when it is determined that there are two types of character strings to which the attribute “company name” is added, “abc (stock)” and “abcd (stock)”, the sum of the character strings “abc (stock)” And the total sum of the character string “abcd (stock)”.
[0057]
When it is determined that there is only one type of character string having the maximum sum (S74 “Yes”), it is determined that the character string is a recognition result of the attribute (S75). When it is determined that there are two or more character strings having the maximum sum (S74 “No”), it is determined that the first recognized character string is the recognition result of the attribute (S76). In the above example, when the character string having the maximum sum is “abc (stock)”, the company name is determined to be abc (stock). When the sum of the character string “abc (stock)” and the character string “abcd (stock)” is the maximum and the same number, and the character string “abcd (stock)” is recognized first, the company name Is determined to be abcd.
[0058]
More specifically, there are two or more types of character strings to which the same attribute is added. Specifically, when (1) a document consisting of a plurality of pages and a plurality of titles 53 exist, (2) a 2-in-1 document If there are a plurality of types of titles 53, etc.
[0059]
FIG. 14 is a flowchart showing the procedure of the cover creation process.
[0060]
First, cover adaptation processing for adapting the determined character strings to the areas 61a to 61c of the cover form 61 is executed (S81). The cover adaptation process is a process of changing the font size of each character string to be arranged in accordance with each of the areas 61a to 61c. Specifically, the font size of the character string to be arranged is calculated based on the sizes of the regions 61a to 61c and the number of characters of the character string to be arranged. For example, when the recognition result of the attribute “title” is a character string including five characters, the maximum font size that can arrange five characters in the title area 61a is calculated. An example of the result of the matching process is as shown in FIG. For example, for the attribute “title”, the font size of the document 50 is 10 points, but the font size when arranged in the area 61a is calculated as 18 points. As the font of the character string when arranged in the areas 61a to 61c, the font recognized by the OCR process, that is, the font of the document 50 is used. By automatically changing the font size, a good-looking cover and / or spine image can be easily and quickly formed.
[0061]
Next, a cover composition process for pasting each character string subjected to the adaptation process to the corresponding areas 61a to 61c of the cover form 61 is executed, the formed cover image is output, and the cover 71 is printed (S82). .
[0062]
FIG. 11 is a flowchart showing the procedure of the spine cover creation mode process.
[0063]
The back cover creation mode process is substantially the same as the above-described cover creation mode process except that the form used is different. In steps S51 to S55, processing similar to that in steps S41 to S45 shown in FIG. 10 is executed, and determination processing for determining a character string to be placed on the spine form 62 is executed (S56). A spine cover creation process for creating the spine cover 72 by placing it on the spine form 62 is executed (S57). The determination process is executed according to the procedure shown in FIG.
[0064]
FIG. 15 is a flowchart showing a procedure of spine cover creation processing.
[0065]
First, a spine cover adaptation process is performed to adapt the determined character strings to the areas 62a to 62c of the spine cover form 62 (S91). Based on the sizes of the areas 62a to 62c and the number of characters of the character string to be arranged, the font size of the character string to be arranged is calculated. Next, a spine cover synthesis process for pasting each character string subjected to the adaptation process to the corresponding regions 62a to 62c is executed, the formed spine cover image is output, and the spine cover 72 is printed (S92).
[0066]
FIG. 12 is a flowchart showing a procedure of cover / back cover creation mode processing.
[0067]
The cover / back cover creation mode process uses both the cover and back cover forms 61 and 62, and is substantially the same as the above-described cover creation mode process and spine cover creation mode process. In steps S61 to S65, processing similar to that in steps S41 to S45 shown in FIG. 10 is executed, and determination processing for determining character strings to be arranged on both forms 61 and 62 is executed (S66). Next, a cover creation process for creating the cover 71 by placing the determined character string on the cover form 61 is executed (S67). Further, a spine cover creation process for creating the spine cover 72 by placing the determined character string on the spine form 62 is executed (S68). The determination process, the cover creation process, and the back cover creation process are executed according to the procedures shown in FIGS. 13, 14, and 15, respectively.
[0068]
As described above, according to the first embodiment, the cover 71 and / or the back cover 72 attached to the document 50 is automatically created and printed at the same time when the document 50 is copied. 14 can be provided. Furthermore, the user does not have to bother to create the cover by starting the application software, saving the user's trouble and improving the efficiency of office work.
[0069]
[Embodiment 2]
FIG. 18 is a flowchart showing the procedure of the cover creation mode process according to the second embodiment of the present invention.
[0070]
In the first embodiment, a character string is converted into a character code by OCR processing, and an image for the cover 71 and / or spine 72 is formed. On the other hand, in the second embodiment, the character string is not converted into the character code, and the image for the cover 71 and / or the back cover 72 is formed as it is. As shown in FIG. 4, it is predetermined that a title 53 is described in the header area 51 and a company name 54 and a date 55 are described in the footer area 52. Further, the date 55 is determined in advance as described on the right side of the company name 54.
[0071]
First, images included in portions corresponding to the header area 51 and the footer area 52 of the document 50 are extracted from the image of each page (S101). Images included in these areas are cut out by a rectangle circumscribing a character string representing a title, a rectangle circumscribing a character string representing a company name, and a rectangle circumscribing a character string representing a date. Each extracted image is not subjected to OCR processing. In steps S102 to S104, processing similar to that in steps S43 to S45 shown in FIG. 10 is executed.
[0072]
Next, a cover creation process is performed in which the extracted image is placed on the cover form 61 to create the cover 71 (S105, S106). Also in the cover creation processing of the second embodiment, first, cover adaptation processing for adapting the extracted image to the respective areas 61a to 61c of the cover form 61 is executed (S105). The cover adaptation process is a process of changing the size of the image to be arranged in accordance with each of the areas 61a to 61c. Specifically, the magnification for enlarging / reducing the image to be arranged is calculated based on the sizes of the regions 61a to 61c and the sizes of the images to be arranged.
[0073]
Next, a cover composition process for pasting the adapted image to the corresponding regions 61a to 61c is executed, the formed cover image is output, and the cover 71 is printed (S106).
[0074]
Although description is omitted, the back cover creation mode process and the cover / back cover creation mode process are also executed in the same procedure.
[0075]
Also with the digital copying machine 14 of the second embodiment, the cover 71 and / or the back cover 72 attached to the original 50 is automatically created and printed at the same time when the original 50 is copied, saving the user's trouble. , Increase the efficiency of office work. Further, an image that cannot be subjected to OCR processing, for example, a cover 71 and / or a spine 72 on which a company emblem or mark is arranged can be created.
[0076]
The digital copying machine 14 of the first and second embodiments described above always prints the image of the read original 50, but the mode for printing only the created cover 71, the mode for printing only the back cover 72, or the cover. 71 and a mode of printing only the spine 72 can be provided.
[0077]
The digital copying machine 14 can start printing after reading the entire document 50. Therefore, the cover image may be output first and the cover 71 may be printed on the first sheet.
[0078]
Although the form which prints the image for a cover and / or a back cover was shown, this invention is not limited to this form. After forming the cover image or the like, the image can be modified to be output and stored in a storage medium in, for example, a PDF file format, for example, instead of printing the image. In this case, the cover image stored in the storage medium is transmitted to the user by e-mail or the like in response to a use request from the user. As a result, the user can post-edit the cover and / or back cover image to create a favorite cover 71 and / or spine 72.
[0079]
Although the first embodiment in which items to be described in the header area 51 and the footer area 52 are determined in advance has been described, it can be modified as follows. For example, when a character string such as “corporation”, “(stock)”, or “company” is recognized by the OCR process, it may be determined that the character string represents a company name. In addition, for example, a character string of “year”, “month”, or “day” is recognized by OCR processing, or a character string of “(any number) year (any number) month (any number) day” is recognized. For example, it may be determined that the character string represents a date. Thus, the specific form for recognizing the title, date, and company name can be variously modified. Furthermore, the character string to be recognized is not limited to the character string representing the title 53, the company name 54, or the date 55. Depending on the type of document 50, character strings representing other items are to be recognized.
[0080]
The font used for the cover 71 and / or the back cover 72 need not be limited to the font recognized by the OCR process. The font to be used may be set in advance in each form 61, 62. According to such a configuration, even when the fonts used in the respective originals 50 are different, the cover 71 and the back cover 72 with unified fonts can be created. For example, the front cover 71 and / or the back cover 72 can be created in a single font for each of one original 50 having a Gothic font and another original 50 having a Mincho style. Different fonts may be set for the respective areas 61a to 61c and 62a to 62c of the forms 61 and 62. You may be able to select the font to use
The forms 61 and 62 may be downloaded to the storage unit 25 from the outside via the network 11 or the like. The user can create a favorite cover 71 and spine 72 using desired forms 61 and 62.
[0081]
【The invention's effect】
According to the present invention described above, the following effects are obtained for each claim.
[0082]
Claims 1, 2 And 3 According to the image forming apparatus described in (1), since a cover image and / or an image for a back cover of a plurality of pages are automatically formed, a very convenient image forming apparatus can be provided. Furthermore, the user does not have to bother to create the cover by starting the application software, saving the user's trouble and improving the efficiency of office work.
[0083]
Claim 4 and 5 According to the image forming apparatus described in the above, it is possible to form an image for a good-looking cover and / or back cover.
[0084]
Claim 6 and 7 According to the image forming apparatus described in the above, it is possible to easily and quickly form an image for a cover and / or a back cover by using a form.
[0085]
Claim 8 , 9 and 10 According to the image forming apparatus described in the above, it is possible to output or print a cover and / or spine cover image or an image obtained by reading a document.
[0087]
Claim 11 According to the image forming method described in the above, it is possible to automatically form an image for a front cover and / or a back cover of a plurality of pages. Furthermore, the user does not have to bother to create the cover by starting the application software, saving the user's trouble and improving the efficiency of office work.
[0088]
Claim 12 According to the computer-readable recording medium storing the image forming program described in 1), the program stored in the recording medium is read by a computer and executed, thereby enabling the cover and / or back cover of a document consisting of a plurality of pages. Since the image is automatically formed, it is possible to improve the efficiency of office work by saving the user's trouble.
[Brief description of the drawings]
FIG. 1 is a configuration diagram illustrating a configuration of an image forming system.
FIG. 2 is a block diagram illustrating a schematic configuration of a digital copying machine.
FIG. 3 is a diagram illustrating an example of an operation panel unit on which a copy mode selection screen is displayed.
FIG. 4 is a diagram illustrating an example of a document including a plurality of pages.
FIG. 5 is a diagram illustrating an example of a predetermined area on each page of a document.
6A is a diagram showing an example of a cover form, and FIG. 6B is a diagram showing an example of a back cover form.
7A is a view showing an example of a cover created by applying the cover form shown in FIG. 6A, and FIG. 7B is a spine shown in FIG. 6B. It is a figure which shows an example of the spine created by applying the business form.
FIG. 8 is a main flowchart for explaining the operation of the present embodiment.
FIG. 9 is a flowchart illustrating a procedure of normal copy mode processing.
FIG. 10 is a flowchart illustrating a procedure of a cover creation mode process.
FIG. 11 is a flowchart showing a procedure of spine cover creation mode processing.
FIG. 12 is a flowchart showing a procedure of cover / back cover creation mode processing;
FIG. 13 is a flowchart illustrating a procedure of determination processing.
FIG. 14 is a flowchart illustrating a procedure of a cover creation process.
FIG. 15 is a flowchart showing a procedure of spine cover creation processing.
FIG. 16 is an example showing a result of OCR processing;
FIG. 17 is an example showing a result of the matching process;
FIG. 18 is a flowchart showing a procedure of a cover creation mode process according to the second embodiment of the present invention.
[Explanation of symbols]
14 ... Digital copier (image forming device)
21: Reading unit
22. Image processing unit
23. Printing section
24. Operation panel section (setting section)
25. Storage unit
26. Control unit (output unit)
31 ... Header / footer area extraction unit (extraction unit)
32 ... OCR part (character recognition part)
33 ... Determining part
34 ... Applicable part (size changing part)
35. Composition processing section (formation section)
50 ... Original
51. Header area (predetermined area)
52 ... Footer area (predetermined area)
53 ... Title
54 ... Company name
55 ... Date
61 ... Cover form (form)
62 ... Back cover form (form)
61a to 61c, 62a to 62c ... Areas where recognized character strings are arranged

Claims (12)

A character recognition unit for recognizing a character string from a character image included in a predetermined area of each page of a multi-page document;
Character strings recognized for each of the predetermined areas of each page are compared based on the arrangement of characters, and when the number of character strings having the same character arrangement is one, the character string is A determination unit that determines as a character string and, when there are a plurality of types of character strings that have the same character arrangement, determines a character string that has at least the maximum number of the same character arrangement as one character string to be arranged When,
An image forming apparatus comprising: a forming unit that forms an image for a cover and / or a back cover on which the determined character string is arranged. The image forming apparatus according to claim 1, wherein the character recognition unit recognizes a character string representing a title, a company name, or a date . The image forming apparatus according to claim 1, wherein the predetermined area is a header area and / or a footer area of a document . The image forming apparatus according to claim 1, further comprising a size changing unit that changes a character size of the character string to be arranged in accordance with a region in which the recognized character string is arranged . The image forming apparatus according to claim 4 , wherein the size changing unit calculates the character size based on a size of the area and a number of characters of a character string to be arranged . The image forming apparatus according to claim 1 , further comprising a setting unit configured to set a predetermined form in which areas for arranging recognized character strings are arranged . The image forming apparatus according to claim 6 , wherein the setting unit is capable of selecting a form to be used from a plurality of stored forms. A reading unit that reads the document;
The image forming apparatus according to claim 1 , further comprising: an output unit that outputs an image formed by the forming unit. The image forming apparatus according to claim 8 , further comprising a printing unit that prints an image output from the output unit. The image forming apparatus according to claim 8, wherein the output unit further outputs an image of a document read by the reading unit. Recognizing a character string from a character image included in a predetermined area of each page of a multi-page document;
Character strings recognized for each of the predetermined areas of each page are compared based on the arrangement of characters, and when the number of character strings having the same character arrangement is one, the character string is Determining as a character string and, when there are a plurality of types of character strings having the same character arrangement, determining a character string having at least the maximum number of the same character arrangement as one character string to be arranged; and ,
Forming an image for a cover and / or spine on which the determined character string is arranged. A procedure for recognizing a character string from a character image included in a predetermined area of each page of a multi-page document;
Character strings recognized for each of the predetermined areas of each page are compared based on the arrangement of characters, and when the number of character strings having the same character arrangement is one, the character string is A procedure for determining as a single character string to be arranged, a character string that is determined as a character string, and when the number of character strings having the same character arrangement method is plural, and the number of characters having the same character arrangement is at least the maximum ; ,
A computer-readable recording medium storing an image forming program having a procedure for forming an image for a cover and / or a back cover on which the determined character string is arranged.

Images