JP3976802B2 - Image processing apparatus and image processing method - Google Patents

Description

[0001]
[Industrial application fields]
The present invention relates to an image processing apparatus and an image processing method for creating a table of contents based on heading information and page number information in a document .
[0002]
[Prior art]
Conventionally, in character recognition using OCR, character clearing, translation processing, and the like are mainly performed.
[0003]
[Problems to be solved by the invention]
However, a function for automatically editing a table of contents using characters recognized by OCR has not been proposed. Also, it has been difficult to edit the table of contents of a manuscript whose pages are disjoint or a manuscript with no page number.
[0004]
The present invention has been made to solve the above-described problems , and provides an image processing apparatus and an image processing method that automatically and quickly creates a table of contents arranged in the order of page numbers to improve user convenience. The purpose is to provide.
[0005]
[Means for Solving the Problems]
In order to achieve the above object, the image processing apparatus of the present invention, determination means for determining whether there is title information for each page of the document from the page it is determined that there is header information by said determining means Extracting means for extracting the header information; and acquiring means for acquiring page number information based on a page number described in a page including the extracted header information when the header information is extracted by the extracting means; A storage unit that stores the header information extracted by the extraction unit and the page number information of the page including the header information acquired by the acquisition unit in association with each other, and the determination unit determines that there is no heading information. wherein the terms pages, control means for the page number of the page is controlled so as not to acquire, and the title information stored by the storage means And sorted by the over-di number information in the page number information associated with each heading information, characterized in that it has a creating means for creating a table of contents.
[0011]
In order to achieve the above object, an image processing method of the present invention, a determination step of determining whether there is title information for each page of the document, it determines that there is a header information at the determination step acquired from the page, an extraction step of extracting該見out information, if the header information in the extraction step is extracted, to obtain a page number information based on the page number on the page containing the headline information the extracted Determining that there is no heading information in the determination step, a storage step of storing the process, the heading information extracted in the extraction step, and the page number information of the page including the heading information acquired in the acquisition step in association with each other the respect to the page, a control step of the page number of the page is controlled so as not to get the the title information stored in the storage step and said page number information Sorted on the basis of the page number information associated with each heading information, characterized in that it has a creation step of creating a table of contents.
[0015]
【Example】
Hereinafter, a preferred embodiment of the present invention will be described in detail with reference to the drawings.
[0016]
[First embodiment]
First, the principle of OCR will be described with reference to FIG.
[0017]
In the figure, a document 101 is scanned by an exposure system 102 of an image reading unit 104, imaged on a CCD 106 via a mirror 103 and a lens 105, binarized by an A / D converter 107, and then image processing unit 108. Is input. Next, in the image processing unit 108, the binarized data is stored in the image memory 110, and an image (character pattern) for each character is cut out from the binarized data by the one-character cutting unit 111, and the character recognition unit 112 is cut out. Character recognition. The image processing unit 108 has a built-in dictionary for character recognition. Then, the character that has been converted character by character is edited by the editing unit 113.
[0018]
FIG. 2 is a sectional view showing the structure of the image copying apparatus in the first embodiment. In the figure, reference numeral 1 denotes a document feeder (DF) serving as a document feeder, which feeds placed documents one by one or two consecutively to a predetermined position on the platen glass surface 2. A scanner 3 includes a lamp, scanning mirrors 5 to 7 and the like. When the original is placed on the original table glass surface 2 by the original feeder 1, the scanner 3 is reciprocally scanned in a predetermined direction, and the original reflected light passes through the lens 8 via the scanning mirrors 5-7. An image is formed on the image sensor unit 9. An exposure control unit 10 includes a laser scanner unit (not shown) and the like, and irradiates the photoconductor 11 with a light beam modulated based on image data output from an image signal control unit (not shown) of the controller unit. Is done. Reference numerals 12 and 13 denote developing units that visualize the electrostatic latent image formed on the photoconductor 11 with a developer (toner) of a predetermined color. Reference numerals 14 and 15 denote transfer paper stacking portions on which fixed-size recording media are stacked and stored, and the recording media are fed to the position where the registration rollers are arranged by driving the feeding rollers, and are formed on the photoconductor 11. Are fed again in a state where the image leading edge alignment timing is taken.
[0019]
A transfer separation charger 16 transfers the toner image developed on the photoconductor 11 onto a transfer paper, and then separates the toner image from the photoconductor 11 and conveys it via a conveyance belt. Reference numeral 17 denotes a fixing unit 17 that fixes the toner image transferred to the transfer paper. Reference numeral 18 denotes a paper discharge roller that stacks and discharges the transfer paper on which image formation has been completed onto the tray 20. Reference numeral 19 denotes a direction flapper which switches the transport direction of the transfer-receiving paper on which image formation has been completed to the paper discharge port and the internal transport direction, and prepares for a multiplex / double-side image forming process.
[0020]
<Description of operation unit>
FIG. 3 is a diagram illustrating a configuration of the operation unit in the embodiment. In FIG. 3, reference numeral 301 denotes a power switch for controlling energization to the image forming apparatus. Reference numeral 302 denotes a reset key which operates as a key for returning to the standard mode during standby. Reference numeral 303 denotes a copy start key. A clear key 304 is used to clear a numerical value. Reference numeral 305 denotes an ID key. The ID key 305 allows a specific operator to perform a copying operation, and other operators can prohibit the copying operation unless an ID is input using the ID key. It becomes. Reference numeral 306 denotes a stop key, which is used when the copying is interrupted or stopped. Reference numeral 307 denotes a guide key, which is used when it is desired to know each function. Reference numeral 308 denotes an up cursor key, which is a key for moving the pointer upward on each function setting screen. Reference numeral 309 denotes a down cursor key, which is a key for moving the pointer down on each function setting screen. A right cursor key 310 is a key for moving the pointer to the right in each function setting screen. Reference numeral 311 denotes a left cursor key, which is a key for moving the pointer to the left on each function setting screen. Reference numeral 312 denotes an OK key which is pressed on each function setting screen when this is acceptable. In the function setting screen 313, the user presses this key when executing the output to the lower right of the display screen described later.
[0021]
A standard size reduction key 314 is used to reduce the standard size to another standard size. Reference numeral 315 is used to select the same size copy. A standard enlargement key 316 is used to enlarge the standard size to another standard size. Reference numeral 317 denotes a cassette selection key for selecting a cassette stage to be copied. Reference numeral 318 denotes a copy density adjustment key for decreasing the density. Reference numeral 319 denotes an AE key, which automatically adjusts the copy density with respect to the density of the original. 320 is a copy density adjustment key for increasing the density. Reference numeral 321 denotes a key for designating the operation of the sorter. A preheat key 322 is used to turn on / off the preheat mode. Reference numeral 323 denotes an interrupt key which is pressed to perform interrupt copying during copying. Reference numeral 324 denotes a numeric keypad which is used when inputting numerical values.
[0022]
Reference numeral 325 denotes a marker processing key, which sets trimming, masking, and partial processing (contour processing, halftone processing, shadowing processing, and negative / positive processing). Reference numeral 326 denotes a patterning processing key, which is used when a color is expressed in a pattern or a color is expressed by a density difference. A color deletion key 327 is used when a specific color is to be deleted. Reference numeral 328 denotes an image quality key, which is used to set image quality. A negative / positive key 329 is used when performing negative / positive processing. An image create key 330 is used when performing contour processing, shadowing processing, halftone processing, italic, mirror processing, and repeat processing. Reference numeral 331 denotes a trimming key, which is used to designate an area and perform trimming. A masking key 332 is used to specify an area and perform masking. A partial processing key 333 designates an area, and then designates partial processing (contour processing, halftone processing, shadowing processing, negative / positive processing). Reference numeral 334 denotes a frame erase key which is used when performing frame erase according to the mode. Modes include sheet frame erase (creates a frame for the sheet size), document frame erase (creates a frame that matches the document size, document size is specified), and book frame erase (for book spread size) In addition, a blank is created in the frame and the center. The book spread size is specified.).
[0023]
A binding margin key 335 is used when it is desired to create a binding margin at one end of the sheet. Reference numeral 336 denotes a movement key which is used when a movement is desired. The movement includes parallel movement (up / down / left / right), center movement, corner movement, and designated movement (point designation). Reference numeral 337 denotes a zoom key, which can set the copy magnification from 25% to 400% in increments of 1%. Also, main scanning and sub-scanning can be set independently. Reference numeral 338 denotes an automatic scaling key which automatically enlarges / reduces according to the size of the copy paper. In addition, the main scanning and sub-scanning can be automatically changed automatically. Reference numeral 339 denotes an enlargement continuous shooting key which is used when one original is enlarged to a plurality of sheets for copying. Reference numeral 340 denotes a reduction layout key which is used when a plurality of originals are enlarged and reduced to be copied. Reference numeral 343 denotes a continuous key, which is used to perform continuous copying in which the copy area on the platen glass surface is divided into left and right parts and automatically copied to two sheets (page continuous shooting, double-sided continuous shooting). Reference numeral 344 denotes a double-sided key, which is used when both-side output is desired (single-sided double-sided, page continuous double-sided, double-sided double-sided).
[0024]
Reference numeral 345 denotes a multiplex key which is used when multiplexing is desired (multiplexing, page continuous shooting multiplexing). A memory key 346 is used when a mode using a memory is desired (memory synthesis, area synthesis, watermark synthesis). A projector key 347 is used when the projector is used. Reference numeral 348 denotes a printer key, which is used for setting at the time of printer. A document mixed key 350 is used when copying using the feeder and when document sizes are mixed. Reference numeral 351 denotes a mode memory key, which is used when registering a copy mode for which copying has been set and for calling up a registered copy mode. Reference numeral 352 denotes a key for switching between the copy mode and the table of contents creation mode. Reference numeral 360 denotes a display screen that displays the status of the apparatus, the number of copies, the copy magnification, and the copy paper size, and displays the contents to be set when the copy mode is set.
[0025]
FIG. 4 is a block diagram showing the configuration of the embodiment constituted by the OCR and the image copying apparatus. Hereinafter, the operation for automatically creating the table of contents will be described with reference to FIG.
[0026]
First, a document with a page number for which a table of contents is to be created is sent to the scanner unit 402 by the DF 401, and the sent document is read by the scanner unit 402. The image read by the scanner unit 402 is recognized by the OCR 403, and the document headline and page number are extracted from the recognized characters. If there is a heading in the document, the heading and page number are stored in the memory 405 as a pair. Next, the image processing unit 404 arranges the headings stored in the memory 405 in page order, and the printer unit 406 outputs the organized headings as a table of contents. When organizing the headings, if it is necessary to rewrite the table of contents to be output, the rewrite is performed by inputting the operation unit 407 attached thereto.
[0027]
Next, the processing of the above-described image processing unit 404 will be described with reference to the flowchart shown in FIG.
[0028]
First, in step S101, it is checked whether or not there is a document. If there is a document, the process proceeds to step S102, where the document is input by the scanner unit 402 in FIG. Recognize. Next, in step S104, it is checked whether or not there is a heading in the character data of the document. If there is a heading in the character data of the document, the heading is extracted, and in step S105, the page number is present. Check whether or not. If there is a page number, the process advances to step S108, and the extracted heading and page number are registered in the memory 405 as a pair. The above-described headline extraction and page number extraction will be further described later with reference to FIGS.
[0029]
If there is no page number in step S105, the process proceeds to step S106, an error is displayed on the display unit of the operation unit 407, and the page number is corrected (input) by the operation unit 407 in the next step S107. . When the correction is completed, the process proceeds to step S108, and the above-described registration process is performed.
[0030]
On the other hand, if there is no heading in the character data of the document in step S104 described above, if the registration process is completed in step S108, the process proceeds to step S109, where the document is exchanged. The document replacement is performed by a DF (document feeder) 401 in FIG. Then, by returning to the document presence check in step S101, the next document is input.
[0031]
As a result of the above processing, when all the reading of the document is completed, the process proceeds to step S110, where it is checked whether or not there is data of a heading and a page number in the memory 405. If there is headline and page number data, the process proceeds to step S111, and the page numbers registered in the memory 405 are sorted in ascending order to create data for creating a table of contents. In step S112, the table of contents is output by sending data to the printer unit 406, and the process ends. If there is no headline and page number data in the memory 405 in step S110, the process proceeds to step S113, indicating that a table of contents cannot be created on the display unit of the operation unit 407, and the process ends.
[0032]
Next, the correction process described above will be described below according to the flowchart shown in FIG.
First, in step S201, data to be corrected is read from the memory 405, and in the next step S202, a headline and a page number are corrected by the operation unit 407. Thereafter, when the table of contents correction is completed, the correction contents are re-registered in the memory 405 in step S203, and the correction process is ended.
[0033]
Next, the headline extraction process described above will be described below according to the flowchart shown in FIG.
[0034]
First, in step S301, a histogram of character data recognized by the OCR 403 is taken, and in a subsequent step S302, character strings that are equal to or larger than the average character size of the histogram are extracted. Thereafter, when the extraction is completed, in step S303, the extracted character strings are checked. If the left and right spaces between the extracted character strings, that is, the space between the character strings in the histogram is within a certain standard, the processing ends. If the space between the character strings in the histogram is more than a certain standard, the process proceeds to step S304 to check the line of the extracted character string.
[0035]
Here, a specific description will be given with reference to the sample document shown in FIG. In the figure, 502 and 503 indicate the case where the upper and lower line spaces of the character string of the histogram are more than a certain reference, and 504 indicates the case where the space is within a certain reference. That is, in step S304, as shown in 502 and 503 in FIG. 9, when the upper and lower line spaces of the histogram character string are more than a certain standard, the process proceeds to step S305, and each extracted character string is set as a separate character string. recognize. If the upper and lower line spaces are within a certain standard as indicated by reference numeral 504 in FIG. 9, the process proceeds to step S306, and each extracted character string is recognized as one character string.
[0036]
When the recognition process described above is completed, the process proceeds to step S307, where registration is performed in the memory 405, and in-step character string check is performed in step S308. This process is a process for checking each memory registration character string and checking whether there is a difference (size) in the histogram. If there is no difference (size) between the histograms, the process ends. If there is a histogram, the process proceeds to step S309, and the process ends with the levels in descending order of the histogram of characters. Here, the level represents the relationship between 602 and 602 shown in FIG.
[0037]
Next, the page number extraction process described above will be described below in accordance with the flowchart shown in FIG.
[0038]
First, in step S401, similarly to the above-described headline extraction, a histogram of character data recognized by the OCR 403 is taken. Next, in step S403, a matrix check of the extracted numbers is performed, and if the upper, lower, left, and right spaces of the extracted numbers, that is, the space between the character strings in the histogram is more than a certain standard, the process proceeds to step S404 and the page number is stored in the memory 405. Register with. If the upper, lower, left, and right spaces of the extracted numbers are not more than a certain standard, the process proceeds to step S405, and an error is displayed on the display unit.
[0039]
In addition, when there are two or more headings on the same document due to the level setting of the headline extraction process as indicated by 601 and 602 shown in FIG. 10, the level-set headlines as shown by 603 shown in FIG. Output page number.
[0040]
[Second Embodiment]
Next, a second embodiment according to the present invention will be described below with reference to the drawings.
[0041]
In the second embodiment, a case where a table of contents is created for a document having no page number will be described as an example. In this case, first, a copy operation of the original is performed, and an add-on which is one of the functions of the copying machine is performed on the copied original, that is, a page number is set in a predetermined position by multiplexing (multiple copy operations are performed). To record. In the case of a copying apparatus having a page memory, the copy image and page number data are combined on the memory and copied in a single scan. The apparatus configuration is the same as that of the first embodiment described above, and a description thereof will be omitted.
[0042]
FIG. 11 is a flowchart showing the processing of the image processing unit 404 in the second embodiment.
[0043]
First, in step S501, it is checked whether or not there is a document. If there is a document, the process proceeds to step S502, and the page counter is incremented by one to take correspondence with the page number. Next, in step S503, the document is input by the scanner unit 402, and in step S504, character recognition of the document is performed by the OCR 403. In step S505, it is checked whether or not there is a heading in the character data of the document. If there is a heading in the character data of the document, the heading is extracted. In step S506, the heading and the number of pages are calculated. A page number by counting is registered in the memory 405 as a pair. If no headline is found in step S505, or if memory registration is completed in step S506, the process advances to step S507 to replace the document. Then, the process returns to the document presence check in step S501, and the next document is input.
[0044]
When all the reading of the original is completed by the above processing, the process proceeds to step S508, where it is checked whether or not there is a headline and page number data in the memory 405. If there is a headline and page number data, the process proceeds to step S509. Then, the heading and page number data in the memory 405 are sent to the printer unit 406 to start outputting the table of contents. In step S508, if there is no headline and page number data, the process proceeds to step S510, a message indicating that the table of contents cannot be created is displayed on the display unit of the operation unit 407, and the process ends.
[0045]
According to the above-described embodiment, for example, even when a page with a page number is divided or when a page has no page number, it is possible to easily create a table of contents simply by inputting a document for which a table of contents is to be created. Is possible.
[0046]
The present invention may be applied to a system composed of a plurality of devices or an apparatus composed of a single device. Needless to say, the present invention can also be applied to a case where the object is achieved by supplying a program to a system or apparatus.
[0047]
【The invention's effect】
As described above, according to the present invention, it is possible to control not to acquire the page number of a page for which it is determined that there is no heading information, thereby speeding up the processing. Since the table of contents is created by sorting in order, the table of contents can be created in the order of page numbers even if the order in which the document images are read is different. Even if there is a missing page in the document image, the page number information obtained by character recognition is used, so that the correspondence between the heading information and the page number information does not shift.
[0048]
[Brief description of the drawings]
FIG. 1 is a diagram for explaining the principle of OCR.
FIG. 2 is a cross-sectional view showing the structure of the image copying apparatus in the embodiment.
FIG. 3 is a diagram illustrating a configuration of an operation unit of the image copying apparatus.
FIG. 4 is a block diagram showing a configuration in an embodiment including an OCR and an image copying apparatus.
FIG. 5 is a flowchart illustrating processing of an image processing unit in the first embodiment.
FIG. 6 is a flowchart showing correction processing in the embodiment.
FIG. 7 is a flowchart illustrating headline extraction processing in the embodiment.
FIG. 8 is a flowchart showing page number extraction processing in the embodiment.
FIG. 9 is a diagram illustrating a sample document.
FIG. 10 is a diagram showing a table of contents for creating a sample.
FIG. 11 is a flowchart illustrating processing of an image processing unit in a second embodiment.
[Explanation of symbols]
401 DF
402 Scanner unit 403 OCR
404 Image processing unit 405 Memory 406 Printer unit 407 Operation unit

Claims (12)

Determining means for determining whether or not there is heading information for each page of the manuscript;
Extraction means for extracting the heading information from the page determined by the determination means as having heading information;
When the header information is extracted by the extraction means, an acquisition means for acquiring page number information based on a page number described in a page including the extracted header information;
Storage means for storing the header information extracted by the extraction means and the page number information of the page including the header information acquired by the acquisition means in association with each other;
With respect to the page determined by the determination means that there is no heading information, control means for controlling not to acquire the page number of the page;
Image processing comprising: creation means for sorting the heading information and the page number information stored by the storage means based on page number information associated with each heading information to create a table of contents apparatus.   The image processing apparatus according to claim 1, wherein the extraction unit extracts the heading information using a character recognition function.   The image processing apparatus according to claim 2, wherein the extraction unit extracts the heading information based on a histogram of character data of the document that has been character-recognized.   The image processing apparatus according to claim 1, further comprising a correcting unit that corrects the table of contents created by the creating unit.   2. The image processing apparatus according to claim 1, further comprising notifying means for notifying that it is impossible to create a table of contents.   The image processing apparatus according to claim 1, further comprising an input unit that performs correction input of a page number when the acquisition unit cannot acquire the page number information by character recognition. A determination step for determining whether there is heading information for each page of the manuscript;
An extraction step of extracting the heading information from the page determined to have the heading information in the determination step ;
When heading information is extracted in the extraction step, an acquisition step of acquiring page number information based on the page number described in the page including the extracted heading information;
An accumulation step of associating and accumulating the header information extracted in the extraction step and the page number information of the page including the header information acquired in the acquisition step;
For a page determined to have no heading information in the determination step, a control step for controlling not to acquire the page number of the page;
An image processing method comprising: a creation step of sorting the heading information and the page number information stored in the storage step based on page number information associated with each heading information to create a table of contents .   The image processing method according to claim 7, wherein the extraction step extracts the heading information using a character recognition function.   9. The image processing method according to claim 8, wherein the extraction step extracts the heading information based on a histogram of character data of the document that has been character-recognized.   The image processing method according to claim 7, further comprising a correction step of correcting the table of contents created in the creation step.   The image processing method according to claim 7, further comprising a notifying step for notifying that a table of contents cannot be created. The acquisition step, the character if it can not acquire the page number information by the recognition, the claims and further comprising an input step of acquiring the page number information by causing the correction input of the page number to the user 8. The image processing method according to 7.

Images