JP6973267B2 - Image processing equipment and image processing program - Google Patents

Description

This disclosure relates to an image processing apparatus and an image processing program.

In recent years, as one of the functions of an image processing device (for example, an MFP), when a document read by an image reading unit (for example, a scanner unit) is transmitted to another device (for example, scanning transmission or fax transmission), a user It is known to detect a peculiar page based on the result of OCR analysis or image analysis in order to prevent an unintended manuscript from being transmitted by mistake.

For example, in Japanese Patent Application Laid-Open No. 2009-206678 (Patent Document 1), when it is desired to detect whether or not a plain (blank) page is included in a scanned manuscript, the image processing apparatus is used for each extracted page. It is disclosed that characters, figures, etc. are extracted from image data, and the absence of them is detected as a reference value. Further, when it is desired to detect whether or not an image that is slanted with respect to the recording sheet or a distorted image is included in the image of the scanned document, the image processing device uses the extracted image data for each page. It is disclosed to extract an edge from the image and detect whether the edge is tilted or distorted above a reference value.

Japanese Unexamined Patent Publication No. 2009-206678

However, the technique disclosed in Patent Document 1 compares the extracted items with the reference value and detects pages that deviate from the reference value, and can only make a judgment based on the reference value. For example, if a reference value for detecting whether or not a scanned document contains a document size other than A4 is set, the image processing device may read the A4 size document and send it by fax. , It is possible to detect that a B5 size document is erroneously mounted. However, when the image processing device wants to read a B5 size document and send it by fax, it does not change the reference value to detect whether or not a document size other than B5 is included, or the B5 of the scanned documents is desired to be transmitted. It is determined that the size of the original is erroneously mixed, and only the erroneously inserted A4 size original is transmitted. That is, the technique disclosed in Patent Document 1 has a problem that an erroneously mixed manuscript is erroneously transmitted in order to uniformly determine an erroneously mixed manuscript from a read manuscript based on a reference value.

The present disclosure has been made to solve the above-mentioned problems, and an image processing device and an image processing program capable of more reliably detecting a document that may be erroneously loaded from a scanned document. To provide.

According to a certain embodiment, the image processing apparatus meets the characteristic conditions set in advance from the image reading means capable of reading a document having a plurality of pages and the image of a predetermined unit of the document read by the image reading means. An extraction means for extracting feature information for each page, a classification means for classifying the manuscript of the predetermined unit into a plurality of groups for each page based on the difference between the pages of the feature information extracted by the extraction means, and the above. It includes a specific means for specifying a group having a small number of pages from the plurality of groups classified by the classification means, and a notification means for notifying a specific page corresponding to the group specified by the specific means.

Preferably, when the specific page corresponding to the group specified by the specific means is notified to the user by the notification means, the transmission permission receiving means for accepting the transmission permission of the document read by the image reading means is accepted. Based on the transmission permission, the transmission means for transmitting the document read by the image reading means is further provided.

Preferably, the deletion operation receiving means that accepts the deletion operation of the specific page corresponding to the group specified by the specific means, and the deletion means that deletes the specific page from the manuscript of the predetermined unit based on the received deletion operation. And further prepare.

Preferably, the automatic deletion means for automatically deleting the specific page corresponding to the group specified by the specific means and the original of the predetermined unit after the specific page is deleted by the automatic deletion means are automatically transmitted. Further provided with automatic transmission means.

Preferably, the notifying means notifies at least one of information indicating the position of the specific page in the manuscript of the predetermined unit and information indicating whether or not the specific page has been deleted from the manuscript of the predetermined unit. do.

Preferably, the feature condition is the presence or absence of fixed characters included in the page read by the image reading means, and the extraction means obtains information on the presence or absence of the fixed characters for each page from the manuscript of the predetermined unit. The classification means divides a page into a page having the fixed character and a page without the fixed character.

Preferably, the feature condition is used as the background of the page read by the image reading means, the extraction means extracts the background information for each page from the manuscript of the predetermined unit as the feature information, and the classification means Divide groups by pages that have different background information.

Preferably, the feature condition is a font of characters on a page read by the image reading means, and the extraction means extracts font information of characters for each page from the manuscript of the predetermined unit as the feature information and classifies the characters. The means divides a group for each page having a difference in the font information of characters.

Preferably, the feature condition is the color of the page read by the image reading means, the extraction means extracts color information for each page from the manuscript of the predetermined unit as the feature information, and the classification means is a color. Divide groups by pages that have different information.

Preferably, the feature condition is the information density of the page read by the image reading means, the extraction means extracts the information density for each page from the manuscript of the predetermined unit as the feature information, and the classification means is: Divide groups by pages that have different information densities.

Preferably, the feature condition is the manuscript size of the page read by the image reading means, and the extraction means extracts the manuscript size information for each page from the manuscript of the predetermined unit as the feature information, and the classification means. Divides a group for each page having a difference in the manuscript size information.

Preferably, when the date information included in each page of the manuscript of the predetermined unit is the same and the page numbers are continuous, the classification means may have a difference in the feature information extracted by the extraction means. The manuscripts of the predetermined unit are classified into the same group.

Preferably, when the extraction means is set to the document mixed loading mode for reading a plurality of documents having different document sizes, the setting of the document size is invalidated as the feature condition.

Preferably, a setting means capable of setting one or more of the characteristic conditions is further provided.

According to a certain embodiment, it is an image processing program executed in a computer that controls an image processing apparatus, and is preset in the computer from a step of reading a multi-page document and an image of a predetermined unit of the scanned document. A step of extracting the feature information that meets the feature conditions for each page, and a step of classifying the manuscript of the predetermined unit into a plurality of groups for each page based on the difference between the extracted feature information for each page. It includes a step of specifying a group having a small number of pages from the plurality of groups, and a step of notifying a specific page corresponding to the specified group.

An image processing apparatus and an image processing program according to an embodiment more reliably detect a document that may be erroneously loaded by identifying a page having a difference from other pages from the scanned documents of a predetermined unit. be able to.

It is a schematic diagram which shows the appearance of the MFP in this embodiment. It is a block diagram which shows the outline of the hardware composition of the MFP in this embodiment. It is a block diagram for demonstrating the process performed by the CPU of the MFP in this embodiment. It is a flowchart for demonstrating the preset process in this embodiment. It is a figure which shows the display example of the operation panel of the MFP in this embodiment. It is a flowchart for demonstrating the document reading process of the MFP in this Embodiment. It is a flowchart for demonstrating the classification process of the MFP in this embodiment. It is a flowchart for demonstrating the notification processing of the classification result of the MFP in this embodiment. It is a figure which shows the display example of the operation panel of the MFP in this embodiment. It is a figure which shows the display example of the operation panel of the MFP in this embodiment. It is a figure which shows an example of the manuscript in this embodiment. It is a figure which shows an example of the manuscript in this embodiment. It is a figure which shows an example of the manuscript in this embodiment. It is a figure which shows an example of the manuscript in this embodiment. It is a figure which shows an example of the manuscript in this embodiment. It is a figure which shows an example of the manuscript in this embodiment. It is a figure which shows an example of the manuscript in this embodiment. It is a figure which shows an example of the manuscript in this embodiment.

Embodiments of the present invention will be described in detail with reference to the drawings. The same or corresponding parts in the drawings are designated by the same reference numerals and the description thereof will not be repeated.

FIG. 1 is a schematic view showing the appearance of the MFP in the present embodiment. In the present embodiment, in the MFP 100, in order to more reliably detect a document that may be erroneously mixed from the document read by the document reading unit 130, a reference value is not set and a uniform judgment is made. Feature information (for example, standard characters) is extracted from each page of the scanned document, and the manuscript is classified into a plurality of groups according to the difference in the extracted feature information to detect a document that may be erroneously loaded. Therefore, in the MFP 100, when reading a document having a plurality of pages, the content of the feature information extracted from each page is set in advance under the feature conditions. Specifically, the MFP 100 extracts feature information that meets the feature conditions from the image of a predetermined unit of the document (hereinafter, also referred to as a scanned document) read by the document reader 130 for each page, and extracts the feature information. Based on the difference between pages, the scanned originals are classified into multiple groups on a page-by-page basis. Further, in the MFP 100, a group having a small number of pages is specified from the plurality of classified groups, and the page corresponding to the specified group is displayed on the operation panel 180.

[1. Image processing device hardware configuration]
FIG. 2 is a block diagram showing an outline of the hardware configuration of the MFP in the present embodiment. The MFP 100 includes an image processing unit 110, an image forming unit 120, a document reading unit 130, a facsimile communication unit 140, a network interface 150, a ROM 160, a RAM 170, an operation panel 180, and a CPU 190.

The image processing unit 110 performs various processes including enlargement / reduction on the input image.

The image forming unit 120 is a laser printer and forms an image on recording paper. The image forming unit 120 forms an image output by the document reading unit 130 or an image transmitted from another device (for example, a computer, a smartphone, etc.) on a recording medium such as paper supplied from the paper feeding unit. To visualize. In the case of color printing, the image forming unit 120 forms an image with four color toners of yellow, magenta, cyan, and black. The image forming unit 120 may be an inkjet printer.

The document reading unit 130 generates image data of the document. The document reading unit 130 includes a photoelectric conversion element such as a CCD (Charge Coupled Device), optically reads a document transported from an automatic document transport device or a document placed on a glass surface, and outputs an image as electronic data. ..

The facsimile communication unit 140 transmits / receives image data by facsimile communication such as a modem.

The network interface 150 is an interface for connecting the MFP 100 to the network. The CPU 190 communicates with other devices connected to the network via the network interface 150, and transmits / receives data. The network interface 150 is connected to another device, can receive job data for printing from the other device, and can transmit the image data of the document generated by the document reading unit 130 to the other device. .. The network interface 150 is not limited to a wired LAN, but may be a wireless LAN.

The ROM 160 stores a program executed by the CPU 190 or various data necessary for executing the program. The RAM 170 is used as a work area when the CPU 190 executes a program. The RAM 170 temporarily stores image data continuously sent from the document reading unit 130.

The operation panel 180 includes a display as a display unit and a user interface as an operation unit. The display is, for example, a liquid crystal display device, a plasma display, or the like. The user interface is for receiving an operation input to the MFP 100, and is, for example, a touch sensor, a hardware button, or the like.

The CPU 190 is connected to an image processing unit 110, an image forming unit 120, a document reading unit 130, a facsimile communication unit 140, a network interface 150, a ROM 160, a RAM 170, an operation panel 180, and the like, and controls the entire MFP 100.

The medium for storing the program executed by the CPU 190 is not limited to a CD-ROM, but is an optical disk (MO (Magnetic Optical Disc) / MD (Mini Disc) / DVD (Digital Versaille Disc)), an IC card, an optical card, and a mask ROM. , EPROM (Erasable Project ROM), EEPROM (Electrically EPROM), or the like.

Further, the program executed by the CPU 190 is not limited to the program recorded on the CD-ROM, and the program stored in the auxiliary storage device (for example, HDD) may be loaded into the RAM 170 and executed. In this case, another computer connected to the network via the network interface 150 may rewrite the program stored in the auxiliary storage device of the MFP 100, or may add and write a new program. Further, the MFP 100 may download a program from another computer connected to the network via the network interface 150 and store the program in the auxiliary storage device. The program referred to here includes not only a program that can be directly executed by the CPU 190, but also a source program, a compressed program, an encrypted program, and the like.

[2. Processing performed by the CPU of the image processing device]
Next, with reference to FIG. 3, a process performed by the CPU 190 in carrying out the present invention will be described. FIG. 3 is a block diagram for explaining the processing performed by the CPU of the MFP in the present embodiment.

In the CPU 190, processing is performed by the extraction unit 191, the classification unit 192, the specific unit 193, the notification unit 194, the deletion unit 195, and the transmission unit 196.

The extraction unit 191 acquires the image data of the document generated by the document reading unit 130 and the feature conditions set by the preset processing shown in FIG. 4 from the ROM 160, and the feature information matching the feature conditions from the image of the scanned document. To extract. The feature condition is a condition for determining the content of the feature information to be extracted from the image of the scanned document. For example, the feature condition includes standard characters, a background, a font of characters, a color, an information density, and a document size. Become. Further, the feature information is information extracted from the image of the scanned document based on the feature conditions. For example, when the feature condition of fixed characters is set, the extraction unit 191 extracts fixed characters and the like commonly used in the scanned document as feature information. Further, when the feature condition of the background is set, the extraction unit 191 extracts the background information from the scanned document as the feature information. Further, when the feature condition of the character font is set, the extraction unit 191 extracts the character font information from the scanned document as the feature information. Further, when the feature condition of color is set, the extraction unit 191 extracts color information from the scanned document as feature information. Further, when the feature condition of information density is set, the extraction unit 191 extracts the information of information density from the scanned document as feature information. Further, when the feature condition of the original size is set, the extraction unit 191 extracts the information of the original size from the scanned original as the characteristic information. For example, when the extraction unit 191 reads the image data of the manuscript shown in FIG. 11 and sets the characteristic condition of "standard characters", the standard characters of "confidential" commonly used for each page. 51 is extracted as feature information.

The classification unit 192 compares the feature information extracted by the extraction unit 191 for each page, and classifies the manuscript into a plurality of groups on a page-by-page basis based on the difference. In the case of the manuscript shown in FIG. 11, the classification unit 192 classifies the scanned manuscript into a group (with group A) of pages (first page, second page, fourth page, fifth page) including the fixed character 51 "confidential". It is classified into a group (referred to as group B) of pages (referred to as group B) that do not include (referred to as).

The specific unit 193 identifies a group having a small number of pages from a plurality of groups classified by the classification unit 192. In the case of the manuscript shown in FIG. 11, the specific unit 193 identifies the group B having a small number of pages from the group A and the group B classified by the classification unit 192.

The notification unit 194 notifies the page corresponding to the group specified by the specific unit 193. In the case of the manuscript shown in FIG. 11, as shown in FIGS. 9 and 10, the notification unit 194 displays the third page corresponding to the group B specified by the specific unit 193 on the operation panel 180.

The deletion unit 195 automatically or according to the deletion instruction from the user, the image data of the page corresponding to the group specified by the specific unit 193 from the image data of the original generated by the document reading unit 130. delete. The deletion patterns include the case of deleting the image data of all the pages corresponding to the group specified by the specific part 193 and the image data of some pages in the pages corresponding to the group specified by the specific part 193. Sometimes only delete. In the case of the manuscript shown in FIG. 11, the deletion unit 195 deletes the third page corresponding to the group B specified by the specific unit 193 automatically or according to the deletion instruction from the user.

The transmission unit 196 transmits the image data of the document generated by the document reading unit 130 to a computer, another image processing device, or the like by means of the facsimile communication unit 140, the network interface 150, or the like. When transmitting by excluding the image data of the page specified by the specific unit 193 and deleted by the deletion unit 195 from the image data of the original document generated by the document reading unit 130, and when the original image generated by the document reading unit 130 is transmitted. In some cases, the image data of the page corresponding to the group specified by the specific unit 193 may be transmitted without being removed from the image data. In the case of the manuscript shown in FIG. 11, the image data of the other pages (1st page, 2nd page, 4th page, 5th page) other than the 3rd page specified by the specific unit 193 is transmitted and specified. The images of the first to fifth pages may be transmitted without excluding the image of the third page specified in the part 193.

By the above processing by each part of the CPU 190, a page having a difference from other pages is specified from the scanned document of a predetermined unit, and the specified page is deleted or transmitted to a set destination. As a result, it is possible to more reliably detect a document that may be erroneously loaded, and it is possible to delete or transmit it as necessary.

Next, with reference to FIGS. 4 and 5, the preset processing of the feature conditions acquired by the extraction unit 191 will be described. FIG. 4 is a flowchart for explaining the presetting process in the present embodiment. FIG. 5 is a diagram showing a display example of the operation panel of the MFP in this embodiment.

First, the CPU 190 displays a list of feature conditions on the operation panel 180 (S10). As shown in FIG. 5, it may be displayed on a screen for setting a destination or the like when scanning a document, or may be displayed on another screen, as long as it is a display prompting the user to set which condition is applied. good. Further, the display of the feature condition list 200 may be notified by voice instead of or together with this display. Further, instead of pressing by the user, an item may be selected by the user's utterance.

Next, the CPU 190 determines whether or not the condition selection by the user is completed (S12). When the condition selection by the user is completed (YES in S12), the CPU 190 stores the selected condition (S14) and ends the process. On the other hand, if the condition selection by the user is not completed (NO in S12), the CPU 190 repeats the process of S12 until the condition selection by the user is completed.

By the above processing by the CPU 190, the feature condition selected by the user is set.

[3. Processing from document scanning to detection of documents that may be misprinted]
Next, with reference to FIGS. 6 to 18, when a user sets a document in the MFP and issues a reading instruction, how the MFP 100 in the present embodiment may misprint the document. We will explain whether to detect and notify the user using a specific example. First, a process from reading a document to detecting a document having a possibility of erroneous loading will be described with reference to S20 to S26 of FIG. 6 and FIG. 7. FIG. 6 is a flowchart for explaining the document reading process of the MFP in the present embodiment. Further, FIG. 7 is a flowchart for explaining the classification process of the MFP in the present embodiment.

First, the CPU 190 acquires the transmission destination of the document set by the user (S20) and the feature conditions set by the preset process (S22). For example, when the document shown in FIG. 11 is set and a fixed character is selected as a characteristic condition, the CPU 190 acquires a destination and a characteristic condition of "fixed character".

Next, the document scanning process is performed by the document scanning unit 130, and the CPU 190 acquires an image of the scanned document (S24).

Next, the CPU 190 performs the classification process (S26) shown in FIG. 7 on the image of the scanned document based on the feature conditions acquired in S22. Through this classification process, documents that may be misprinted are detected. Therefore, the classification process of S26 will be described with reference to FIG. 7. The classification process is mainly performed by the extraction unit 191 of the CPU 190, the classification unit 192, and the specific unit 193.

First, the CPU 190 determines whether or not a fixed character is set as a feature condition (S40).

When the fixed character is set as the feature condition (YES in S40), the CPU 190 determines the fixed character commonly used in the image of the scanned predetermined unit of the original, and sets the fixed character for each page. Information on whether to include or not is extracted (S42). Next, the CPU 190 classifies the scanned document into a group of pages including fixed characters and a group of pages not including fixed characters (S44), and shifts to S46. For example, when the manuscript shown in FIG. 11 is set and the standard character is selected as the feature condition, the standard character 51 of "confidential" commonly used in the original is extracted and the standard character "confidential" is extracted. Classified into a group (referred to as group A) of pages containing the character 51 (1st page, 2nd page, 4th page, 5th page) and a group (referred to as group B) of pages (3rd page) not including the character 51. Then, the group B having a small number of pages is specified, and the process proceeds to S46.

On the other hand, when the fixed character is not set as the feature condition (NO in S40), the CPU 190 shifts to S46.

In S46, the CPU 190 determines whether or not the background is set as the feature condition.

When the background is set as the feature condition (YES in S46), the CPU 190 extracts the background information for each page from the image of the scanned document (S48). Next, the CPU 190 classifies the scanned documents into groups on a page-by-page basis according to the background pattern (S50), and shifts to S52. For example, when the manuscript shown in FIG. 12 is set and the background is selected as the feature condition, the information that the background is plain and the information that the background is not plain are extracted, and the background is plain. It is divided into a group (referred to as group C) of pages (1st to 3rd pages and 5th page) and a group (referred to as group D) of pages (4th page) whose background is not plain. Group D with a small number of pages is specified, and the process proceeds to S52.

On the other hand, when the background is not set as the feature condition (NO in S46), the CPU 190 shifts to S52.

In S52, the CPU 190 determines whether or not a character font is set as a feature condition.

When the character font is set as the feature condition (YES in S52), the CPU 190 extracts the character font information for each page from the image of the scanned document (S54). Next, the CPU 190 classifies the scanned document into groups on a page-by-page basis (S56) according to the difference in the font of the characters, and shifts to S58. For example, when the manuscript shown in FIG. 13 is set and the character font is selected as the feature condition, the information that the character font is the character font 56 and the character font is the character font 57. The group (referred to as group E) of the pages (1st page, 2nd page, 4th page, and 5th page) whose character font is the character font 56 and the character font are characters. It is classified into a group (referred to as group F) of a page (third page) having a font 57, a group F having a small number of pages is specified, and the process proceeds to S58.

On the other hand, when the character font is not set as the feature condition (NO in S52), the CPU 190 shifts to S58.

In S58, the CPU 190 determines whether or not a color is set as a feature condition.

When the color is set as the feature condition (YES in S58), the CPU 190 extracts the color information for each page from the image of the scanned document (S60). Next, the CPU 190 classifies the scanned documents into groups on a page-by-page basis (S62) according to the difference in color information, and shifts to S64. For example, when the original shown in FIG. 14 is set and a color is selected as a feature condition, the information that the color is color and the information that the color is monochrome are extracted, and the page that is the color (1 page). Classify into groups (referred to as group G) of eyes, pages 3 to 5) and groups of pages (second page) that are monochrome (referred to as group H), and identify group H with a small number of pages. Then, move to S64.

On the other hand, when the color is not set as the feature condition (NO in S58), the CPU 190 shifts to S64.

In S64, the CPU 190 determines whether or not the information density is set as a feature condition.

When the information density is set as the feature condition (YES in S64), the CPU 190 calculates the information density for each page from the image of the scanned document and extracts the information (S66). Next, the CPU 190 classifies the scanned documents into groups on a page-by-page basis according to the difference in information density (S68), and shifts to S70. For example, when the manuscript shown in FIG. 15 is set and the information density is selected as the feature condition, the information that the information density is 20, the information that the information density is 19, and the information density are Information that the information density is 18, information that the information density is 50, and information that the information density is 21 are extracted so that information having a relatively close information density are in the same group. A group of pages (1st to 3rd pages and 5th page) with a density of around 20 (referred to as group I) and a group of pages (4th page) with an information density of around 50 (referred to as group J). ), Identify the group J with a small number of pages, and move to S70.

On the other hand, when the information density is not set as the feature condition (NO in S64), the CPU 190 shifts to S70.

In S70, the CPU 190 determines whether or not the document mixed loading mode is set. The original mixed loading mode is a mode for reading a plurality of originals having different original sizes, and is set by selecting, for example, "mixed size loading" in the document size list 202 shown in FIG. When the document mixed loading mode is not set (YES in S70), the CPU 190 shifts to S72. On the other hand, when the document mixed loading mode is set (NO in S70), the process ends without performing the process of S72 or less. As a result, when the original mixed loading mode is set, even if the original size is set as a feature condition, the setting can be invalidated so as not to compare by the original size.

In S72, the CPU 190 determines whether or not the document size is set as a feature condition.

When the original size is set as a feature condition (YES in S72), the CPU 190 extracts the original size information for each page from the image of the scanned original (S74). Next, the CPU 190 classifies the scanned documents into groups on a page-by-page basis according to the difference in the document size (S76), and ends the process. For example, when the document shown in FIG. 16 is set and the document size is selected as a feature condition, the information that the document size is A4, the information that the document size is A3, and the document size are A group (referred to as group K) of pages (1st page, 2nd page, and 5th page) having a manuscript size of A4 and a page having a manuscript size of A3 are extracted from the information of B5. Group L (referred to as group L) of (third page) and group (referred to as group M) of pages (fourth page) having a manuscript size of B5 are classified, and group L and group M having a small number of pages are classified into groups L and group M. Identify and end the process.

On the other hand, if the original size is not set as a feature condition (NO in S72), the CPU 190 ends the process.

By the above processing by the CPU 190, the feature information that meets the feature conditions set by the user is extracted for each page, and the scanned document is classified into a plurality of groups for each page based on the difference between the extracted feature information for each page. From among them, a group with a small number of pages is identified. In this way, it is possible to more reliably detect a document having a difference from other pages and having a possibility of erroneous loading from among the scanned documents.

The above characteristic conditions are merely examples, and other characteristic conditions may be used. Further, the feature conditions may be stored in the ROM 160 at the time of shipment of the MFP and provided, or may be provided by distribution or the like after shipment.

Further, in the above example, the fixed character is "confidential", but the fixed character 51 is not limited to "confidential" and may be any one commonly used in the scanned document, for example, "secret". "Top secret", "public", "forbidden copy", "circulation", "approved", "rejected", company name, company slogan, these may be marked in other languages such as English. In addition, the standard characters are not limited to characters, and may be images such as company logos.

Further, in the above example, the background information is information that the background is plain and information that the background is not plain, but the background information is not limited to the information on the presence or absence of the background, and the background pattern. It may be information about the background and the color, and may be information that the background is a diagonal line pattern, information that the background is a dot pattern, information that the background is a lattice pattern, information that the background is blue, and the like. ..

In addition, the character font information is not limited to the character typeface information such as Mincho typeface and Gothic typeface, but also the character size information, the character thickness information, the character diagonal body information, and the full-width half-width character. Information etc. may be used.

Further, the color information may be any information regarding the color of the scanned document, and is not limited to information that the scanned document is monochrome or color, but may be information that the scanned document is a red-black binary value. ..

Further, the information density is a ratio of characters and figures per page of a manuscript, and can be calculated by using a known technique. For example, there is a method of calculating the ratio of colors other than the background color to the background color based on the color information of the scanned document.

Further, the document size information may be not only fixed size information such as A3, A4, B4, and B5, but also irregular size information.

In addition, as a result of classification, if there are multiple groups with a small number of pages, all the groups may be specified, or some criteria are set and only some of the groups are specified. May be good.

Further, a plurality of feature conditions may be set. For example, when the document shown in FIG. 17 is set and the standard characters and the document size are selected as the feature conditions, the standard characters 51 commonly used as "confidential" and the document size are A4. The information that there is and the information that the original size is B5 are extracted. After that, the group (referred to as group N) of the page (1st page, 2nd page, 4th page, 5th page) containing the fixed character 51 "confidential" and the page (3rd page) not including it. It is classified into a group (referred to as group O). Further, based on the information on the manuscript size, a group (referred to as group P) of pages having a manuscript size of A4 (pages 1 to 3 and 5) and a page having a manuscript size of B5 (page 4). It is classified into a group of eyes) (referred to as group Q). Then, the group O and the group Q having a small number of pages are specified. As described above, when a plurality of items are selected as the feature conditions, they may be classified and specified for each feature condition, but they may be classified and specified as shown below.

Specifically, the scanned document is referred to as a group (referred to as group R) of pages (first page, second page, and fifth page) containing the standard character 51 "confidential" and having a document size of A4. , The group (referred to as group S) of the page (4th page) having the standard character 51 of "confidential" and the original size is B5, and the standard character 51 of "confidential" are not included and the original size is A4. It may be classified into a group of pages (third page) (referred to as group T), and group S and group T having a small number of pages may be specified.

[4. Processing to notify the manuscript that may be erroneously loaded]
The flow of processing from reading a document to detecting a document that may be erroneously mixed has been described above. Next, with reference to S28 to S36 of FIG. 6 and FIGS. 8 to 10, a process of notifying the user of a document having a possibility of erroneous loading detected by the above process will be described.

First, with reference to S28 to S36 of FIG. 6, the CPU 190, which has completed the classification process of S26, is set to a mode in which it is not determined to be erroneously mixed when the date information is the same and the page numbers are continuous. (S28). This mode is for not performing the notification processing of S34 regardless of the result of the above classification processing when this is set and the date information is the same and the page numbers are continuous. For example, it is set when the corresponding item shown in FIG. 5 is selected.

When the mode that does not determine that the page numbers are erroneously mixed when the date information is the same and the page numbers are continuous is set (YES in S28), the CPU 190 inputs the date information and the page number to the image of the scanned document. The determination process is performed (S30), and the process proceeds to S32. In S32, the CPU 190 determines whether or not all the date information matches and the page numbers are serial numbers without omission (S32). When all the date information matches and the page numbers are serial numbers without omission (YES in S32), the CPU 190 displays all the images of the scanned document in S20 without notifying the result of the classification process in S26. It is transmitted to the destination acquired in (S36), and the process is terminated. As a result, the pages included in the group identified as having a difference from other pages in the classification process of S26 can be excluded from the manuscripts that may be misprinted. For example, when the manuscript shown in FIG. 18 is set and a mode in which it is not determined to be erroneously mixed, and a fixed character is selected as a feature condition, the date information 52 of "2018/4/1" and "1/5" are used. The page number 53, which is a serial number from "" to "5/5", is extracted, and the group of pages containing the fixed character 51 "confidential" and the group of pages not included are classified in S26. Eliminate and classify the scanned documents into the same group, and send all the images of the scanned documents to the destination.

In S28, when the mode for not determining mis-consolidation is not set when the date information is the same and the page numbers are continuous (NO in S28), or in S32, the date information does not match or the page numbers are continuous. If not (NO in S32), the CPU 190 performs a process (S34) for notifying the result of the classification process of S26, and ends the process.

Next, the process performed by the CPU 190 in S34 will be described with reference to FIGS. 8 to 10. The notification process is mainly performed by the notification unit 194, the deletion unit 195, and the transmission unit 196 of the CPU 190. FIG. 8 is a flowchart for explaining the notification processing of the classification result of the MFP in the present embodiment. 9 and 10 are diagrams showing a display example of the operation panel of the MFP in the present embodiment, and FIG. 9 is a display example in the notification processing of the classification result when the automatic deletion / transmission mode is set. FIG. 10 is a diagram showing a display example in the notification processing of the classification result when the automatic deletion / transmission mode is not set.

First, the CPU 190 determines whether or not the automatic deletion / transmission mode is set (S80). The automatic deletion / transmission mode is a mode in which the images of the pages corresponding to the group with a small number of pages are automatically deleted from the groups classified by the classification process of S26, and the images of the remaining originals are automatically transmitted. , For example, it is set when the corresponding item shown in FIG. 5 is selected.

When the automatic deletion / transmission mode is set (YES in S80), the CPU 190 deletes the image of the page corresponding to the group having a small number of pages from the groups classified by the classification process of S26 (S82). ), The images of the remaining pages are transmitted to the destination acquired in S20 (S84). Next, the CPU 190 displays the image of the page deleted in S82 on the operation panel 180 and displays that the transmission of the image of the remaining page is completed (S86), and ends the process.

For example, as shown in FIG. 9, the message 61 and the thumbnail display 64 are displayed on the operation panel 180. The message 61 displays the content that the image of the manuscript that may be erroneously loaded has been deleted and that the image of the remaining manuscript has been transmitted. The thumbnail display 64 displays the selected feature condition, the image of the deleted page, and the image of the page that has not been deleted. The deleted page is a page corresponding to the group specified by the above classification process, and is the third page in FIG. 9 which does not include the fixed character "confidential". By looking at the operation panel 180, the user can know that the image of the page that may be erroneously loaded has been deleted and the image of the remaining manuscript has been transmitted. In addition, the user can know which page is the deleted page that may be erroneously loaded by looking at the operation panel 180.

Further, in FIG. 9, the thumbnail display 64 displays the images of the manuscripts of the second to fourth pages, but when it is desired to view the images of the manuscripts of the first page and the fifth and subsequent pages, It can be viewed by pressing the key 62 or the key 63. Further, in FIG. 9, the image of the deleted page is displayed larger than the image of the page not deleted, but the image of the deleted page stands out more than the image of the page not deleted. It suffices if it is displayed, and only the image of the deleted page may be displayed in a manner surrounded by a red frame, or only the image of the deleted page may be displayed darkly. Also, only the image of the deleted page may be displayed, and the image of the page that has not been deleted may not be displayed. Further, the display of the message 61 and the thumbnail display 64 may be notified by voice in place of these displays or together with these displays. Further, both the information on which page is the page that may be erroneously loaded, which is notified by the thumbnail display 64, etc., and the information on whether or not the page is deleted, which is notified by the message 61 or the like, are both. Both may be displayed, or only one of them may be displayed.

On the other hand, when the automatic deletion / transmission mode is not set (NO in S80), the CPU 190 operates the operation panel to display the image of the page corresponding to the group having a small number of pages from the groups classified by the classification process of S26. Displayed on 180 (S88). Next, the CPU 190 displays the delete key and the transmission OK key on the operation panel 180 (S90).

Next, the CPU 190 determines whether or not the transmission OK key is pressed (S92). When the transmission OK key is pressed (YES in S92), the CPU 190 transmits the image of the original stored in the RAM 170 at the time of pressing among the images of the scanned document to the destination acquired in S20 (S98). ), End the process. On the other hand, if the transmission OK key is not pressed (NO in S92), the CPU 190 shifts to S94.

In S94, the CPU 190 determines whether or not the delete key has been pressed. When the delete key is pressed (YES in S94), the CPU 190 deletes the image of the corresponding page, that is, the image of the page displayed on the operation panel 180 as a page that may be erroneously loaded (S96). ), Move to S92. On the other hand, if the delete key is not pressed (NO in S94), the CPU 190 shifts to S92.

For example, as shown in FIG. 10, the message 71, the thumbnail display 74, the delete key 72, and the transmission OK key 73 are displayed on the operation panel 180. In the message 71, it is displayed that a manuscript that may be misprinted has been detected and that an instruction to delete or transmit is urged. The thumbnail display 74 displays the selected feature condition, an image of a page that may be erroneously loaded, and an image of a page that is not likely to be erroneously loaded. The page that may be misprinted is a page corresponding to the group specified by the above classification process, and in FIG. 10, it is a third page that does not include the fixed character "confidential". The user presses the delete key 72 when he / she wants to delete the page displayed on the operation panel 180 that may be erroneously loaded, and presses the transmission OK key 73 when he / she wants to send. As a result, the user can delete the image of the page that may be erroneously loaded from the image of the scanned document. Further, the user can confirm the image of the page that may be erroneously loaded from the image of the scanned document, and then transmit the image of the page without deleting it as there is no problem.

Further, in FIG. 10, the thumbnail display 74 displays the images of the manuscripts of the second to fourth pages, but when it is desired to browse the images of the manuscripts of the first page and the fifth and subsequent pages, It can be viewed by pressing the key 62 or the key 63. Further, in FIG. 10, the image of the page having the possibility of erroneous loading is displayed larger than the image of the page having no possibility of erroneous loading, but the image of the page having the possibility of erroneous loading is erroneously displayed. It suffices to be displayed in a more conspicuous manner than the image of the page where there is no possibility of mixed loading. Only the image on the page may be darkened. Further, only the image of the page where there is a possibility of erroneous loading is displayed, and the image of the page where there is no possibility of erroneous loading may not be displayed. Further, the display of the message 71 and the thumbnail display 74 may be notified by voice in place of these displays or together with these displays.

Further, the delete key 72 and the transmission OK key 73 are not limited to those displayed on the display of the operation panel 180, and may be hardware buttons or the like included in the operation panel 180. Further, the deletion or transmission instruction by the user may be executed by the user's utterance instead of pressing the deletion key 72 or the transmission OK key 73 by the user.

When the automatic deletion / transmission mode is set by the above processing by the CPU 190, the image of the page corresponding to the group specified in the classification processing of S26 is automatically deleted from the image of the scanned document, and the remaining image. Is sent. In addition, the image of the automatically deleted page is displayed on the operation panel. This allows the user to know which pages have been deleted as potentially misleading pages. In addition, the operation panel displays the fact that it was automatically deleted and sent. This allows the user to know that the image of the page that may be misprinted has been deleted and the image of the remaining page has been sent.

Further, when the automatic deletion / transmission mode is not set by the above processing by the CPU 190, the image of the page corresponding to the group specified in the classification processing of S26 is displayed on the operation panel. This allows the user to know which pages may be misprinted. In addition, the delete key and the send OK key are displayed on the operation panel. As a result, the user can delete the image of the unnecessary page from the displayed images and send the image of the required page.

As described above, in the image processing apparatus according to a certain embodiment, when a plurality of pages of a document are read, if feature conditions are set in advance, the feature conditions are met from the image of the scanned document of a predetermined unit. The feature information is extracted for each page, and the scanned manuscript of a predetermined unit is classified into a plurality of groups for each page based on the difference between the extracted feature information for each page. In addition, a group with a small number of pages is identified from a plurality of classified groups, and the page corresponding to the specified group is notified.

As a result, by identifying a page having a difference from other pages from the scanned documents of a predetermined unit, it is possible to more reliably detect and notify a document having a possibility of erroneous loading.

Further, when the page corresponding to the specified group is notified, the transmission permission may be accepted, and the image of the scanned original may be transmitted according to the received transmission permission.

As a result, the image of the scanned original can be transmitted according to the user's instruction even when the user is notified that there is a possibility of erroneous loading.

Further, the deletion operation of the page corresponding to the specified group may be accepted, and the image of the page may be deleted according to the accepted deletion operation.

This makes it possible to delete the image of the page notified that there is a possibility of erroneous loading.

Further, the pages corresponding to the specified group may be automatically deleted, and the remaining pages may be automatically sent.

This saves the trouble of deleting and transmitting operations.

In addition, at least one of the information indicating the position of the page corresponding to the specified group in the manuscript of the predetermined unit and the information indicating whether or not the page corresponding to the specified group has been deleted from the manuscript of the predetermined unit. May be notified.

This makes it possible to grasp which page may be misprinted. In addition, it is possible to grasp whether or not a page that may be misprinted has been deleted.

In addition, information on the presence or absence of standard characters is extracted for each page from the scanned image of the predetermined unit of the manuscript, and the scanned predetermined unit of the manuscript is divided into a group of pages having standard characters and a group of pages without standard characters. It may be divided into.

As a result, by comparing the presence or absence of fixed characters between pages, it is possible to identify a page that may be erroneously loaded based on the difference.

Further, the background information may be extracted for each page from the image of the scanned predetermined unit of the manuscript, and the scanned predetermined unit of the manuscript may be grouped for each page having a difference in the background information.

As a result, by comparing the background information between the pages, it is possible to identify the page that may be erroneously loaded based on the difference.

Further, the font information of characters may be extracted for each page from the image of the manuscript of the predetermined unit read, and the scanned manuscripts of the predetermined unit may be grouped for each page having a difference in the font information of the characters.

As a result, by comparing the font information of characters between pages, it is possible to identify a page that may be erroneously loaded based on the difference.

Further, the color information may be extracted for each page from the image of the scanned predetermined unit of the original, and the scanned predetermined unit of the original may be grouped for each page having a difference in the color information.

As a result, by comparing the color information between pages, it is possible to identify a page that may be erroneously loaded based on the difference.

Further, the information of the information density may be extracted for each page from the image of the scanned document of the predetermined unit, and the scanned document of the predetermined unit may be grouped for each page having a difference in the information density.

Thereby, by comparing the information of the information density between the pages, it is possible to identify the page where there is a possibility of erroneous loading based on the difference.

Further, the original size information may be extracted for each page from the image of the scanned predetermined unit of the original, and the scanned predetermined unit of the original may be grouped for each page having a difference in the original size information.

Thereby, by comparing the information of the original size between the pages, it is possible to identify the page where there is a possibility of erroneous loading based on the difference.

Further, when the date information included in each page of the scanned predetermined unit of manuscript is the same and the page numbers are consecutive, even if the extracted feature information is different, the predetermined unit of the manuscript is grouped in the same group. It may be classified into.

As a result, when the date information is the same and the page numbers are consecutive, even if there is a difference in the extracted feature information, it is not detected as erroneous loading.

Further, when the original mixed loading mode for scanning a plurality of originals having different original sizes is set, the original size setting may be invalidated as a feature condition.

As a result, when the document mixed loading mode is set, the document size information does not have to be compared between pages.

Further, one or more feature conditions may be set.

As a result, it is possible to more flexibly detect a document that may be erroneously mounted from among documents having various characteristics.

The various processes described above are supposed to be realized by one CPU, but are not limited to this. These various functions include a semiconductor integrated circuit such as at least one processor, at least one application specific integrated circuit (ASIC), at least one DSP (Digital Signal Processor), and at least one FPGA (Field Programmable). It can be implemented by a Gate Array) and / or a circuit with other arithmetic functions.

These circuits may perform the various processes described above by reading one or more instructions from at least one tangible readable medium.

Such media take the form of magnetic media (eg, hard disks), optical media (eg, compact discs (CDs), DVDs), volatile memory, and any type of memory, such as non-volatile memory. It is not limited to the form.

The volatile memory may include a DRAM (Dynamic Random Access Memory) and a SRAM (Static Random Access Memory). The non-volatile memory may include ROM, NVRAM.

It should be considered that the embodiments disclosed this time are exemplary in all respects and not restrictive. The scope of the present invention is shown by the scope of claims rather than the above description, and is intended to include all modifications within the meaning and scope equivalent to the scope of claims.

100 MFP, 130 document reader, 160 ROM, 170 RAM, 180 operation panel, 190 CPU, 191 extraction unit, 192 classification unit, 193 specific unit, 194 notification unit, 195 deletion unit, 196 transmission unit.

Claims (15)

An image reading means that can read multi-page documents,
An extraction means for extracting feature information that meets preset feature conditions for each page from an image of a predetermined unit of a document read by the image reading means, and an extraction means.
A classification means for classifying the manuscript of the predetermined unit into a plurality of groups on a page-by-page basis based on the difference between pages of the feature information extracted by the extraction means.
A specific means for identifying a group having a small number of pages from the plurality of groups classified by the classification means, and
An image processing apparatus comprising: a notifying means for notifying a specific page corresponding to a group specified by the specific means. A transmission permission receiving means for accepting transmission permission of a document read by the image reading means when the notification means notifies the user of the specific page corresponding to the group specified by the specific means.
The image processing apparatus according to claim 1, further comprising a transmission means for transmitting a document read by the image reading means based on the received transmission permission. A deletion operation receiving means that accepts a deletion operation of the specific page corresponding to the group specified by the specific means, and
The image processing apparatus according to claim 1 or 2, further comprising a deletion means for deleting the specific page from the document of the predetermined unit based on the received deletion operation. An automatic deletion means that automatically deletes the specific page corresponding to the group specified by the specific means, and
The image processing apparatus according to any one of claims 1 to 3, further comprising an automatic transmission means for automatically transmitting the original of the predetermined unit after the specific page is deleted by the automatic deletion means. .. The notifying means notifies at least one of information indicating the position of the specific page in the manuscript of the predetermined unit and information indicating whether or not the specific page has been deleted from the manuscript of the predetermined unit. The image processing apparatus according to claim 4, which is characterized. The feature condition is the presence or absence of standard characters included in the page read by the image reading means.
The extraction means extracts information on the presence or absence of the fixed characters for each page from the manuscript of the predetermined unit as the feature information.
The image processing apparatus according to any one of claims 1 to 5, wherein the classification means divides a page into a page having the fixed characters and a page without the fixed characters. The characteristic condition is used as the background of the page read by the image reading means.
The extraction means extracts background information for each page from the manuscript of the predetermined unit as the feature information.
The image processing apparatus according to any one of claims 1 to 6, wherein the classification means divides a group into pages having differences in background information. The feature condition is used as a font of characters on the page read by the image reading means.
The extraction means extracts the font information of characters for each page from the manuscript of the predetermined unit as the feature information.
The image processing apparatus according to any one of claims 1 to 7, wherein the classification means divides a group into pages having a difference in font information of characters. The characteristic condition is the color of the page read by the image reading means.
The extraction means extracts color information as the feature information for each page from the manuscript of the predetermined unit.
The image processing apparatus according to any one of claims 1 to 8, wherein the classification means divides a group into pages having a difference in color information. The characteristic condition is defined as the information density of the page read by the image reading means.
The extraction means extracts the information density for each page from the manuscript of the predetermined unit as the feature information.
The image processing apparatus according to any one of claims 1 to 9, wherein the classification means divides a group into pages having a difference in information density. The characteristic condition is the original size of the page read by the image reading means.
The extraction means extracts the manuscript size information for each page from the manuscript of the predetermined unit as the feature information.
The image processing apparatus according to any one of claims 1 to 10, wherein the classification means divides a group into pages having a difference in document size information. When the date information included in each page of the manuscript of the predetermined unit is the same and the page numbers are continuous, the classification means has the predetermined unit even if there is a difference in the feature information extracted by the extraction means. The image processing apparatus according to any one of claims 1 to 11, wherein the manuscripts are classified into the same group. The eleventh aspect of claim 11, wherein the extraction means invalidates the setting of the original size as the characteristic condition when the original mixed loading mode for reading a plurality of originals having different original sizes is set. Image processing device. The image processing apparatus according to any one of claims 1 to 13, further comprising a setting means capable of setting one or more of the feature conditions. An image processing program executed by a computer that controls an image processing device.
On the computer
Steps to read a multi-page document and
A step to extract feature information for each page that meets preset feature conditions from the scanned image of a predetermined unit of manuscript, and
Based on the difference between the pages of the extracted feature information, the steps of classifying the manuscript of the predetermined unit into a plurality of groups on a page-by-page basis, and
A step to identify a group with a small number of pages from the plurality of classified groups,
An image processing program comprising a step of notifying a specific page corresponding to a specified group.

Images