JP6470071B2 - Image processing device - Google Patents

Description

  The present invention relates to an image processing apparatus, and more particularly to an image processing apparatus having an image reading function for reading an image of a document.

  As one type of image processing apparatus, an image forming apparatus (typically a copier) is introduced in many offices (company, office, etc.). Many of these image forming apparatuses, such as multifunction peripherals (MFPs), have a plurality of operation modes such as a copy mode, a network-compatible print mode, a scanner mode, and a facsimile mode. It has become to.

  The image processing apparatus has an image reading function for reading an image of a document as document image data. Some of such image processing apparatuses have a function of storing the read document image data as a file and transmitting the stored file to an external device. When document image data is stored, a file name is assigned to the document image data. File names are often entered manually by the user.

  Conventionally, a file name is automatically generated by combining the date and time when reading an image and the model name of the image processing apparatus (“date and time + machine specific information such as machine name”), and the original image data is generated with the file name. An image processing apparatus for storing is also known. However, it is difficult to grasp the contents of a file from the file name with a file name composed of a combination of date and time and model name. It is necessary to open the file in order to grasp the contents of the file, and this work is troublesome. Furthermore, when a file with such a file name is transmitted to an external device, the user who has received the file cannot grasp the contents of the file until the file is opened.

  In order to solve such a problem, Japanese Patent Application Laid-Open No. 2004-228561 discloses an image forming apparatus that automatically sets a file name in consideration of the content of the original image data for the read original image data. This image forming apparatus performs OCR (Optical Character Recognition) processing on the read original image data, and relatively large character strings, red character strings, special font characters that symbolize the contents of the original image data. Extract strings, character strings in the title area, and character strings that appear multiple times. Further, the image forming apparatus sets a character string obtained by combining the extracted character strings as a file name of the document image data and stores it in the storage unit.

JP 2011-155548 A

  The image forming apparatus disclosed in Patent Document 1 performs OCR processing on the read document image data, thereby extracting a character string symbolizing the content of the document image data. However, since the OCR process for extracting such a character string takes time, it takes a long time to set a file name in the document image data. In the technique described in Patent Document 1, the time until the read document image data is stored in the storage unit becomes long, so that there is a problem that the usability of the user is lowered.

  The present invention has been made to solve the above-described problems, and one object of the present invention is to store a read original image data with a file name while suppressing a decrease in usability. It is also possible to provide an image processing apparatus that can save the trouble of the user.

  An image processing apparatus according to an aspect of the present invention includes a document reading unit for reading an image of a document as document image data, and a partial area of the document image among the document image data read by the document reading unit. A character recognition unit for performing character recognition processing on image data corresponding to the image data, a generation unit for generating a file name of document image data based on a character string recognized by the character recognition unit, and a document reading unit Storage means for storing the original image data read by the generation means using the file name generated by the generation means.

  When the document reading unit reads an image of the document, character recognition processing is performed on image data corresponding to a partial area of the document image in the document image data read by the character recognition unit. When the character string is recognized by the character recognition process, the file name of the document image data is generated based on the recognized character string. Document image data read by the document reading unit is stored in the storage unit. At this time, the file name generated by the generation unit is used as the file name of the document image data. That is, the read document image data is stored with the file name generated by the generation unit.

  In this way, by performing character recognition processing on image data corresponding to a partial area of a document image, character recognition processing is performed as compared with a case where character recognition processing is performed on all areas of a document image at once. Can reduce the time it takes. Therefore, even when document image data is stored using the generated file name, the time until the document image data is stored can be shortened. Thereby, it can suppress that a user's usability falls. Since the file name attached to the read document image data is automatically generated by the generation unit, it is possible to save the trouble of manually inputting the file name. Furthermore, since the file name is generated based on the character string of the document image, it is easy to grasp the contents of the document image data (file) from the file name attached to the document image data. Since the necessity of performing an operation such as opening a file in order to grasp the contents of the file is reduced, this also saves the user's trouble.

  Preferably, the image processing apparatus further includes a determination unit for determining whether or not a character string sandwiched between predetermined blank areas has been recognized by the character recognition process as a character string to be a file name candidate, and a determination unit A recognition processing control means for controlling the character recognition means to perform character recognition processing on image data corresponding to another part of the original image in response to the negative determination result And the generation means includes a file name generation means for generating a file name of the document image data based on the recognized character string in response to the determination result of the determination means being affirmative.

  More preferably, the recognition processing control means sets the character recognition means so as to perform character recognition processing on image data corresponding to each area in order of area of a predetermined size from the beginning to the tail of the document image. Control.

  More preferably, the determination means excludes a predetermined character string and a character string having a predetermined number of characters or more from the file name candidates, and recognizes the character string as the file name candidate by the character recognition process. It includes character string determination means for determining whether or not it has been done.

  More preferably, the image processing apparatus further includes a setting unit for setting the excluded character string as a file name candidate in response to the determination result of the character string determining unit being negative. , Including alternative file name generation means for generating an alternative file name of the document image data based on the character string set by the setting means.

  More preferably, the image processing apparatus further includes a candidate number determination unit for determining whether or not a plurality of character strings as file name candidates are recognized in response to a positive determination result of the determination unit. And a selection means for causing the user to select one of a plurality of character strings as file name candidates in response to the determination result of the candidate number determination means being affirmative. A file name of the document image data is generated based on the recognized character string or a character string selected by the user via the selection unit among the recognized character strings in accordance with the determination result of the determination unit. .

  More preferably, the image processing apparatus further determines the number of candidates for determining whether or not a plurality of character strings are set as file name candidates in response to the determination result of the character string determining means being negative. And a selection means for causing the user to select one of a plurality of character strings that are file name candidates in response to the determination result of the candidate number determination means being affirmative. Based on the determination result of the candidate number determination means, the file name of the document image data is set based on the set character string or the character string selected by the user through the selection means among the set character strings. Generate.

  More preferably, the image processing apparatus further determines whether or not the character recognition processing for the original image data of the first original is completed in response to the reading of the images of the plurality of originals by the original reading unit. Processing stop means for determining and controlling the character recognition means to stop the character recognition processing according to the determination result is included.

  As described above, according to the present invention, an image processing apparatus that can store a read document image data with a file name while suppressing a decrease in usability and saves a user's trouble. Can be obtained.

It is a control block diagram which shows the hardware constitutions of the image processing apparatus which concerns on the 1st Embodiment of this invention. It is a figure which shows the example of the system setting screen displayed with the image processing apparatus shown in FIG. It is a figure for demonstrating the automatic generation process of a file name. It is a figure for demonstrating the automatic generation process of a file name. It is a flowchart which shows the control structure of the program performed with the image processing apparatus shown in FIG. It is a flowchart which shows the control structure of the program performed with the image processing apparatus shown in FIG. It is a figure for demonstrating operation | movement of the image processing apparatus shown in FIG. It is a figure for demonstrating operation | movement of the image processing apparatus shown in FIG. It is a figure which shows the example of the selection screen displayed with the image processing apparatus shown in FIG. It is a flowchart which shows the control structure of the program performed with the image processing apparatus which concerns on the 2nd Embodiment of this invention. It is a flowchart which shows the control structure of the program performed with the image processing apparatus which concerns on the 2nd Embodiment of this invention. It is a figure which shows the example of the original document selection screen displayed with the image processing apparatus which concerns on the 3rd Embodiment of this invention. It is a figure for demonstrating operation | movement of the image processing apparatus which concerns on the 3rd Embodiment of this invention. It is a figure for demonstrating operation | movement of the image processing apparatus which concerns on the 3rd Embodiment of this invention. It is a figure which shows the example of the notification screen displayed with the image processing apparatus which concerns on the 3rd Embodiment of this invention.

  In the following embodiments, the same parts are denoted by the same reference numerals. Their functions and names are also the same. Therefore, detailed description thereof will not be repeated.

(First embodiment)
Referring to FIG. 1, an image processing apparatus 100 according to the present embodiment is a multi-function peripheral (MFP) having a plurality of operation modes such as a copy mode, a scanner mode, and a scan transmission mode. The image processing apparatus 100 has a so-called laser (electrophotographic) printing function that uses laser light for exposure. However, other types of printing functions may be provided.

  The image processing apparatus 100 has an image reading function for reading an image of a document as document image data. In the copy mode, the image processing apparatus 100 forms a multicolor or single color image on a recording sheet based on the read document image data. In the scanner mode, the image processing apparatus 100 stores the read document image data as a file in an internal storage device. In the scan transmission mode, the image processing apparatus 100 transmits the read document image data as a file to an external device (not shown) such as an information processing apparatus. A document name is assigned to document image data stored as a file or document image data transmitted as a file. The file name assigned (set) to the document image data is automatically generated by the image processing apparatus 100.

  The image processing apparatus 100 further has an OCR function for executing character recognition processing by OCR (hereinafter sometimes referred to as “OCR processing”) on the read document image data. The image processing apparatus 100 recognizes a character string that is a candidate for a file name from information (character group) obtained by the OCR process, and automatically generates a file name based on the recognized character string.

  In the present embodiment, the image processing apparatus 100 performs OCR processing on image data corresponding to a partial area of the document image in the document image data by the OCR function. When a character string that is a candidate for the file name is recognized from the information obtained by the OCR process, the image processing apparatus 100 generates a file name based on the recognized character string. When a character string that is a candidate for a file name is not recognized, the image processing apparatus 100 performs OCR processing on image data corresponding to another partial area of the document image.

  The image processing apparatus 100 repeats the OCR process until a character string that is a candidate for a file name is recognized (extracted) from one (first) document. When images of a plurality of documents are read, OCR processing is performed on the image data of the first document. However, if the first document is a blank document, the OCR process is not performed. In this case, a file name is automatically generated by combining the date and time at the time of image reading and unique information (for example, model name) of the image processing apparatus 100. In this embodiment, even when a character string that is a candidate for a file name is not recognized from one original, the date and time at the time of image reading and the image processing apparatus are the same as when the first original is a blank original. A file name combining 100 unique information (for example, model name) is automatically generated. Details of the file name generation process will be described later.

[Hardware configuration]
The image processing apparatus 100 includes a control unit 110, an operation unit 120, a document reading unit 130, an image processing unit 140, an image forming unit 150, a paper feeding unit 160, and a NIC (Network Interface Card) 170.

  The control unit 110 is substantially a computer, and includes a CPU (Central Processing Unit) 112 that controls the entire image processing apparatus 100, a ROM (Read-Only Memory) 114 for storing programs, and a volatile storage device. A RAM (Random Access Memory) 116 and a storage device 118. The storage device 118 is a non-volatile storage device that retains data even when power is cut off, and is, for example, a hard disk drive (HDD) or a flash memory. A BUS line 180 is connected to the CPU 112, and a ROM 114, a RAM 116, and a storage device 118 are electrically connected to the BUS line 180.

  The CPU 112 executes various computer programs in accordance with instructions from the operation unit 120 and the like, thereby executing desired processing such as operations of each unit of the image processing apparatus 100 and communication with an external device such as a personal computer (PC). To do. The various computer programs are stored in advance in the ROM 114 or the storage device 118, and are read from the ROM 114 or the storage device 118 and transferred to the RAM 116 when desired processing is executed. The CPU 112 reads and interprets a program instruction from an address in the RAM 116 specified by a value stored in a register called a program counter (not shown) in the CPU 112. The CPU 112 also reads data necessary for the operation from the address specified by the read instruction, and executes an operation corresponding to the instruction on the data. The execution result is also stored in an address specified by an instruction, such as a register in the RAM 116, the storage device 118, and the CPU 112.

  The ROM 114 or the storage device 118 performs OCR processing on the read original image data together with a computer program for realizing general operations of the image processing apparatus 100, and generates a file name of the original image data. A computer program for realizing the processing is stored. This computer program is written in the ROM 114 or the storage device 118 when the image processing apparatus 100 is manufactured. The computer program may be provided from an external device or the like via the NIC 170. Further, the computer program may be provided by a storage medium such as a DVD on which the computer program is recorded. That is, for example, a DVD as a computer program recording medium is loaded into a DVD drive (not shown) built in the image processing apparatus 100, and the computer program is read from the DVD and installed in the storage device 118. Also good. In addition, the storage device 118 stores various data such as document image data read by the document reading unit 130.

  Further, the operation unit 120, the document reading unit 130, the image processing unit 140, the image forming unit 150, the paper feeding unit 160, and the NIC 170 are electrically connected to the BUS line 180.

  The operation unit 120 receives an operation by a user. The operation unit 120 communicates with the CPU 112 via an input / output interface (not shown). The operation unit 120 includes an operation panel 122. The operation panel 122 includes a display panel constituted by a liquid crystal panel and the like, and a touch panel that is disposed on the display panel and detects a touched position. The display panel provides the user with various information such as information relating to the state of the image processing apparatus 100 and the state of various processes. The operation panel 122 provides an interactive operation interface (UI) to the user. This interactive operation interface receives a user instruction for the operation of the entire image processing apparatus 100 from the touch panel, displays the contents of the instruction on the display panel, and sends a control signal corresponding to the instruction to the control unit 110 and the like. Output.

  The document reading unit 130 includes a document scanning unit including a light source, a reflection mirror, an optical lens, and a CCD (Charge-Coupled Device) line sensor (all of which are not shown). The document scanning unit obtains a reflected light image by irradiating light from a light source onto the image surface of a document placed on a document placement table (not shown). The reflection mirror and the optical lens form the resulting reflected light image on the CCD line sensor. The CCD line sensor sequentially photoelectrically converts the formed reflected light image and outputs it to the image processing unit 140 as image data. That is, the document reading unit 130 reads image information from a document placed on a document placing table when copying or scanning a document, converts the read image information into an electrical signal, and converts the read image information into document image data. Output for.

  The image processing unit 140 includes an MPU (Micro Processing Unit, not shown). The image processing unit 140 performs various processes such as rasterization processing on the image data received from the document reading unit 130 or an external device, and creates print data of a predetermined gradation. During the printing process, the image processing unit 140 outputs the created print data to the image forming unit 150.

  The image forming unit 150 prints an image indicated by image data on a recording sheet in color or single color, and includes, for example, a photosensitive drum, a charging device, a laser scanning unit (LSU), a developing device, a transfer device, and a cleaning device. A device, a fixing device, a static eliminator, and the like. For example, the image forming unit 150 is provided with a conveyance path, and the recording paper fed from the paper feeding unit 160 is conveyed along the conveyance path.

  The paper feed unit 160 includes a paper feed tray (not shown) that stores recording paper. The paper feeding unit 160 pulls out the recording paper stored in the paper feeding tray one by one and sends the recording paper to the conveyance path of the image forming unit 150. While the recording paper is being transported along the transport path of the image forming unit 150, the recording paper passes between the photosensitive drum and the transfer device, and further passes through the fixing device to perform printing on the recording paper. It is.

  The photosensitive drum rotates in one direction, and its surface is cleaned by a cleaning device and a static eliminator and then uniformly charged by a charging device. The laser scanning unit modulates the laser beam based on the image data to be printed, and repeatedly scans the surface of the photosensitive drum in the main scanning direction with this laser beam to form an electrostatic latent image on the surface of the photosensitive drum. To do. The developing device supplies toner to the surface of the photosensitive drum to develop the electrostatic latent image, and forms a toner image on the surface of the photosensitive drum. The transfer device transfers the toner image on the surface of the photosensitive drum to a recording sheet passing between the transfer device and the photosensitive drum.

  The fixing device includes a heating roller for heating the recording paper and a pressure roller for pressing the recording paper. The recording sheet is heated by the heating roller and pressed by the pressure roller, whereby the toner image transferred onto the recording sheet is fixed on the recording sheet. The recording paper discharged (printed) from the fixing device is discharged to a paper discharge tray.

  The NIC 170 has an interface with the network 50. The image processing apparatus 100 can perform data communication according to a predetermined communication protocol with an external device or the like on the network 50 via the NIC 170. The image processing apparatus 100 can receive an instruction signal for instructing execution of various processes such as a print job from a PC or the like via the NIC 170.

[Automatic file name generation]
When the system setting screen 200 (see FIG. 2) displayed on the operation panel 122 is set to automatically generate a file name, OCR is performed when reading a document image (scanning) in the scanner mode or the scan transmission mode. Processing is performed.

  Referring to FIG. 2, a system setting screen 200 is used to select a check box 210 to be checked when setting to automatically generate file name candidates at the time of scanning, and an operation when there are a plurality of file name candidates. It includes a radio button 220 and a check box 230 that is checked to increase the accuracy of the file name candidate. When the check box 210 is checked, the OCR process is executed when the document image is read (scanning). The OCR processing is performed on the read image data when the control unit 110 reads image data corresponding to a partial area of the document image in the read document image data. When the OCR process is performed, a character string that is a candidate for a file name is recognized and extracted from information (character group) obtained by the OCR process.

  Specifically, a character group sandwiched by a predetermined blank area from a character group obtained by OCR processing is recognized as one character string. If the character string is written horizontally, a group of characters with a predetermined blank area on the left and right (front and back) is recognized as one character string. If the character string is written vertically, there is a predetermined blank area on the top and bottom (front and back). A character group is recognized as one character string. For the determination of horizontal writing or vertical writing, for example, a technique described in Japanese Patent Application Laid-Open No. 2009-98777 (determination technique for character recognition description direction) can be used. The predetermined blank area only needs to have a size capable of recognizing one character string from the character group obtained by the OCR process, and is preferably an area having a size of one character or more, for example. It is more preferable if the area has a size of 3 characters or more. When such a character string is recognized, a general character string and a character string greater than a predetermined number of characters (hereinafter referred to as “a certain number of characters”) are excluded from candidate characters. The general character string includes a fixed character string such as date, department name, or “confidential”. Such character strings are registered in the image processing apparatus 100 in advance. A character string having a certain number of characters or more is a character string exceeding the number of characters (for example, 30 characters) applicable to a file name, for example. By excluding general character strings and character strings exceeding a certain number of characters from recognized character strings, for example, character strings such as subject, title, or headline indicating the contents of the manuscript are extracted as file name candidates. Is done.

  A plurality of file name candidates may be extracted. In such a case, whether to select a file name automatically or manually select a file name is preset by the radio button 220. If the file name is set to be automatically selected, the character string located at the top of the file is selected as the file name. If the file name is set to be manually selected, a selection screen (to be described later) for allowing the user to select a character string as the file name is displayed on the operation panel 122.

  When the check box 230 is checked, when a character string that is a candidate for a file name is not extracted by excluding a general character string and a character string of a certain number of characters or more from the recognized character string, In order to improve the accuracy of the file name candidate, OCR processing is performed on image data corresponding to another part of the original image. If the check box 230 is not checked, a character string that is a candidate for a file name is not extracted by excluding a general character string and a character string of a certain number of characters or more from the recognized character string. The excluded character string is extracted (set) as a file name candidate.

  Referring to FIG. 3, the OCR process for the read document image data is first performed on the image data corresponding to the top region 250 of the document image. The leading area 250 is, for example, an area of 10% from the beginning of the document image (an area where the ratio of the size (L2) of the region 250 to the size (L1) of the document image is 10%). The size of the region 250 is preferably 10% or more and 50% or less with respect to the document image. When a character string that is a candidate for a file name is extracted in the first area 250, no further OCR processing is performed. Note that the character string on the boundary line of the region 250 is not recognized by the OCR process.

  Referring to FIG. 4, when a character string is not recognized in the leading area 252 (see FIG. 4A), OCR processing is performed on image data corresponding to another partial area 254 of the document image. It is executed (see FIG. 4B). The area 254 is an area next to the head area 252. The size of this area 254 is the same as the size of the top area 252. When a character string that is a candidate for a file name is extracted in the next area 254, no further OCR processing is performed. On the other hand, if no character string is extracted in the next area 254, OCR processing is further performed on the image data corresponding to the next area. As described above, the OCR process is executed on the image data corresponding to each region in order of a region having a predetermined size from the head of the document image to the tail (arrow Y direction). As described above, this process is repeated until a character string that is a candidate for a file name is extracted from one original. However, the OCR process described above is not executed for a blank document. Whether or not the read original is a blank original is determined based on the data size of the original image data.

  When a character string exists on the boundary line of the region where the OCR process is performed, it is recognized that the character string exists on the boundary line by the OCR process. In this case, when the OCR process is further executed, the next area is set to include the character string on the boundary line of the previous area. For example, if a character string exists on the boundary line of the leading area 252, the next area 254 is set to partially overlap the leading area 252 so that the character string on the boundary line of the leading area 252 is recognized. Is done.

Software configuration
With reference to FIGS. 5 and 6, a control structure of a computer program executed by the image processing apparatus 100 in order to automatically generate a file name to be set for the read document image data will be described. This program starts when the document image data reading process by the document reading unit 130 is started (scanning is started) with the check box 210 of the system setting screen 200 shown in FIG. 2 checked. To do.

  Referring to FIG. 5, the program determines whether or not the first document is blank based on the data size of the read document image data, and branches the control flow according to the determination result (step S1000). In step S1000, the process is executed when it is determined that the first document is not blank, and the image data corresponding to the first area of the first document is read, and the OCR process is executed on the image data. Step S1010 is executed, and after Step S1010, it is determined whether or not the character string is recognized by the OCR process, and the flow of control is branched according to the determination result. In Step S1020, the character string is recognized. If it is determined that the character string has been deleted, a general character string and a character string with a certain number of characters or more are extracted from the recognized character string. Step S1030 for excluding from name candidates, Step S1040 executed after step S1030, determining whether there is a character string that is a candidate for a file name after being excluded, and branching the control flow according to the determination result including.

  This program is further executed when it is determined in step S1040 that there are file name candidates, and it is determined whether there are a plurality of file name candidates, and the control flow is branched according to the determination result. This is executed when it is determined in step S1050 and step S1050 that there are a plurality of file name candidates. In the system setting screen 200, the “manually select file name” setting is set to ON (selected) Executed when it is determined in step S1060 that branches the control flow according to the determination result and in step S1060 that the “manually select file name” setting is ON. A selection screen is displayed on the operation panel 122, and a step for accepting a file name selection operation by the user is received. In step S1070 and step S1050, if it is determined that there are not a plurality of file name candidates, in step S1060, the “manually select file name” setting is not turned on, that is, “automatically select a file name”. When it is determined that the “select” setting is ON, or after step S1070, a recognized character string or a character string selected by the user is determined as a file name.

  Referring to FIG. 6, this program is further executed when it is determined in step S1040 (see FIG. 5) that there is no file name candidate. In step S1090 and step S1090, it is determined whether or not the setting is turned on, that is, whether or not the check box 230 is checked, and the control flow branches according to the determination result. Step S1100 is executed when it is determined that the setting of “improving the accuracy of name candidates” is not turned on, and a general character string excluded and a character string of a certain number of characters or more are set as file name candidates; If it is determined in step S1090 that the “increase accuracy of file name candidate” setting is ON In step S1110 to add the excluded general character string and the character string of a certain number of characters or more to the file name sub-candidate, and after step S1110 or in step S1020 (see FIG. 5), the OCR process This is executed when it is determined that the character string has not been recognized. Whether or not reading of the first document image data has been completed, that is, whether or not the OCR processing has been completed for all areas of the first document image. Step S1120 for determining whether or not and branching the flow of control according to the determination result.

  This program is further executed when it is determined in step S1120 that reading of the first document image data has not been completed, and image data corresponding to the next area of the first document image is read. Characters added as sub-candidates of file names that are executed when it is determined in step S1130 that executes OCR processing on the image data and in step S1120 that reading of the first document image data is completed. Step S1140 for determining whether or not there is a column and branching the flow of control according to the determination result, and when it is determined that there is a sub-candidate in step S1140, the sub-candidate is a candidate for a file name. If it is determined in step S1150 and step S1140 that there is no sub-candidate, In step S1000 (see FIG. 5), the process is executed when it is determined that the first document is blank, and a character string (“ Step S1160 of creating “date and time + machine specific information”) as a file name. When the process of step S1130 ends, control returns to step S1020 shown in FIG. When the process of step S1100 or step S1150 ends, control returns to step S1050 shown in FIG.

  Referring to FIG. 5 again, when the process of step S1080 or step S1160 shown in FIG. 6 ends, the program ends.

[Operation]
The image processing apparatus 100 according to the present embodiment operates as follows. In the following description, only the part related to the present invention in the operation of the image processing apparatus 100 will be described. Other operations are the same as those of the conventional image processing apparatus.

  Assume that the user of the image processing apparatus 100 reads the image of the document shown in FIG. 7 with the document reading unit 130 and stores the read document image data in the storage device 118. The user checks the check box 210 and the check box 230 on the system setting screen 200, and reads the image of the document in the scanner mode. When reading an image of a plurality of documents, the image processing apparatus 100 executes a file name generation process in parallel with the image reading process.

  The control unit 110 of the image processing apparatus 100 determines whether or not the first document is blank based on the data size of the read document image data. Since the first document 260 shown in FIG. 7 is not a blank document, control unit 110 determines that first document 260 is not a blank document (NO in step S1000 shown in FIG. 5). . The control unit 110 reads image data corresponding to the first area 270 of the first document 260 and performs OCR processing on the image data (step S1010). The control unit 110 determines whether or not a character string is recognized by the OCR process. Since the character string 262 and the character string 264 sandwiched between predetermined blank areas exist in the first area 270, the control unit 110 determines that the character string has been recognized (YES in step S1020). Note that the character string 266 is not recognized by the OCR process because it is located on the boundary line of the head region 270. The control unit 110 excludes a general character string and a character string of a certain number of characters or more from the recognized character strings from file name candidates (step S1030). The character string 262 is a date, and the character string 264 is a department name. These are registered in advance as general character strings. The character string 262 and the character string 264 are excluded from file name candidates.

  The control unit 110 determines whether there is a character string that is a candidate for the file name after the character string 262 and the character string 264 are excluded. Since there is no character string that becomes a candidate for the file name in the first area 270 after exclusion, the control unit 110 determines that there is no character string that becomes a candidate for the file name (NO in step S1040). Since the check box 230 of the system setting screen 200 is checked, the control unit 110 determines that the “increase the accuracy of the file name candidate” setting is ON (YES in step S1090 shown in FIG. 6). ). The control unit 110 adds the excluded character string 262 and character string 264 to the file name sub-candidate (step S1110), and determines whether reading of the first document image data is completed. This is because reading of the first document image data has not been completed (NO in step S1120). The control unit 110 reads image data corresponding to the next area 272 of the first original 260 and performs OCR processing on the image data (step S1130). Since the character string 266 exists on the boundary line of the leading area 270, the next area 272 is set so as to partially overlap the leading area 270 so that the character string 266 is recognized. The control unit 110 determines whether or not a character string is recognized by the OCR process. Since the character string 266 and the character string 268 sandwiched between predetermined blank areas exist in the next area 272, the control unit 110 determines that the character string has been recognized (YES in step S1020 shown in FIG. 5).

  The control unit 110 excludes a general character string and a character string of a certain number of characters or more from the recognized character strings from file name candidates (step S1030). Since the character string 266 is fixed, it is assumed that it is registered in advance as a general character string. The character string 266 is excluded from file name candidates. The control unit 110 determines whether there is a character string that is a candidate for the file name after the character string 266 is excluded. Since there is a character string 268 that becomes a file name candidate after exclusion in the next area 272, the control unit 110 determines that there is a character string that becomes a file name candidate (YES in step S1040). Since there is only one character string 268 as a file name candidate (NO in step S1050), this character string 268 is determined as the file name (step S1080).

  The control unit 110 sets the file name generated in this way as the file name of the read document image data, and stores the document image data in the storage device 118. A character string 268 (“with respect to Δ □ ○”) is the subject of the first original and indicates the content of the read original image data. By using the file name generated based on the character string 268 as the file name of the document image data, it becomes easy to grasp the contents of the document image data from the file name.

  On the other hand, when the check box 230 on the system setting screen 200 is not checked, the control unit 110 determines that the “increase the accuracy of file name candidates” setting is not turned on (step S1090 shown in FIG. 6). NO). The control unit 110 sets the character string 262 and the character string 264 excluded in the head area 270 as file name candidates (step S1100). Control unit 110 determines that there are a plurality of file name candidates (YES in step S1050), and determines whether the “manually select file name” setting is ON. When the “manually select file name” setting is ON, the control unit 110 displays a selection screen on the operation panel 122 and selects a character string to be used for the file name from among a plurality of file name candidates. The user is selected (step S1070). That is, the user is allowed to select which one of the character string 262 and the character string 264 is the file name. The control unit 110 determines the character string selected by the user as the file name of the document image data (step S1080), and stores the document image data in the storage device 118 with the file name.

  When the “manually select file name” setting is not turned on (NO in step S1060), that is, when the “automatically select file name” setting is turned on, the control unit 110 displays the character Of the column 262 and the character string 264, the character string (in this case, the character string 262) located at the foremost side of the file (in this case, the character image 262) is determined as the file name of the document image data (step S1080). If the excluded character string is a character string having a certain number of characters or more, the character string is set as a file name candidate. Since this character string exceeds the number of characters applicable to the file name, when this character string is used as the file name, the number of characters applicable to the file name from the first character of the character string is set as the file name.

  Thus, the generated file name may differ depending on whether or not the check box 230 on the system setting screen 200 is checked. By checking the check box 230, a file name that makes it easier to grasp the contents of the document image data is generated. When the check box 230 is not checked, the time required for the OCR process is further shortened compared to when the check box 230 is checked.

  If the first document is blank (YES in step S1000), control unit 110 generates a file name composed of “date and time + machine specific information” without executing the OCR process (step S1160). The read document image data is stored in the storage device 118 with the generated file name.

  Further, if a character string that is a candidate for the file name is not extracted by the time the OCR process is completed for the entire area of the first document (YES in step S1120), the control unit 110 causes the file name sub-candidate. It is determined whether or not a character string is added. If there is no sub-candidate (NO in step S1140), control unit 110 generates a file name composed of “date and time + machine specific information”, and stores document image data read with the generated file name in storage device 118. . On the other hand, if there is a sub candidate (YES in step S1140), control unit 110 sets the sub candidate as a file name candidate (step S1150). If there is one character string as a file name candidate (NO in step S1050 shown in FIG. 5), that character string is determined as the file name of the document image data (step S1080). If there are a plurality of character strings as file name candidates (YES in step S1050), the character string selected automatically or manually is determined as the file name of the document image data (step S1080).

  When the original read by the original reading unit 130 is the original shown in FIG. 8, the file name is stored in the next area 282 of the first original 280 after the character string 266 that is a general character string is excluded. There are a plurality of candidate character strings (character string 284 and character string 286). Control unit 110 determines that there are a plurality of character strings as file name candidates (YES in step S1040 and YES in step S1050). When the “manually select file name” setting is set to ON, the control unit 110 displays a selection screen 300 (see FIG. 9) on the operation panel 122 and selects a file from a plurality of file name candidates. The user is allowed to select a character string used for the name (step S1070).

  Referring to FIG. 9, selection screen 300 includes a selection key 310 for selecting character string 284, a selection key 320 for selecting character string 286, and keys operated when a file name is manually input. 330 is included. When the key 330 is operated, the screen display changes to a file name input screen. When the user operates the selection key 310 or the selection key 320, a character string is selected according to the key operation, and the selected character string is determined as the file name of the document image data (step S1080).

  In the scan transmission mode, the file name generated as described above is set as the file name of the read document image data and temporarily stored in the storage device 118. The stored file (original image data) is transmitted to an external device via the NIC 170 and the network 50.

[Effects of the present embodiment]
As is clear from the above description, the following effects can be obtained by using the image processing apparatus 100 according to the present embodiment.

  The image processing apparatus 100 performs OCR processing by performing OCR processing on image data corresponding to a partial area of the document image, compared to performing OCR processing on all areas of the document image at once. This time can be shortened. Therefore, even when document image data is stored using the generated file name, the time until the document image data is stored can be shortened. Thereby, it can suppress that a user's usability falls. Since the file name attached to the read document image data is automatically generated, it is possible to save the trouble of manually inputting the file name. Further, since the file name is generated based on the character string in the document image, it is easy to grasp the contents of the document image data (file) from the file name attached to the document image data. Since the necessity of performing an operation such as opening a file in order to grasp the contents of the file is reduced, this also saves the user's trouble.

  The image processing apparatus 100 further recognizes a character string made up of a character group sandwiched between predetermined blank areas as a character string that becomes a file name candidate. When such a character string is not recognized, the image processing apparatus 100 performs a character recognition process on image data corresponding to another part of the original image. When such a character string is recognized, the image processing apparatus 100 generates a file name of the document image data based on the recognized character string. Further, the OCR process is performed on the image data corresponding to each area in order of a predetermined size from the beginning to the tail of the document image. This makes it easy to generate a file name that takes into account the contents of the document image data. Therefore, it becomes easier to grasp the contents of the document image data (file) from the file name attached to the document image data.

  Further, by excluding general character strings set in advance and character strings exceeding the predetermined number of characters from the file name candidates, a character string such as a subject, title, or heading indicating the contents of the document is filed. It becomes easy to extract as a name candidate. This makes it easier to generate a file name considering the content of the document image data. A character string such as a subject, title, or headline indicating the content of a document is generally written on the relatively upper side (first side) of the document. Therefore, such a character string can be extracted without performing the OCR process on the entire area of the document image, so that the time required for the OCR process can be effectively shortened.

(Second Embodiment)
When the image processing apparatus according to the present embodiment continuously reads an image of a plurality of originals, the image processing apparatus performs processing on image data of the second and subsequent originals until a character string as a file name candidate is extracted. However, it differs from the image processing apparatus 100 according to the first embodiment in that OCR processing is performed. In other respects, each image processing apparatus has the same configuration.

Software configuration
In the image processing apparatus according to the present embodiment, the program shown in FIGS. 10 and 11 is executed instead of the program shown in FIGS. The programs in FIGS. 10 and 11 include steps S2000 to S2060 instead of steps S1000, S1010, S1120, and S1130 in FIGS. The processes in steps S1020 to S1110 and steps S1140 to S1160 in FIGS. 10 and 11 are the same as the processes in each step shown in FIGS. Hereinafter, different parts will be described.

  Referring to FIG. 10, this program is executed after step S2000 for substituting “1” for variable n indicating the number of originals read, and read original image data. Based on the data size of step S2010, it is determined whether or not the nth document is a blank sheet, and the flow of control is branched according to the determination result. In step S2010, the nth document is not a blank sheet. Step S2020, which is executed when it is determined, reads image data corresponding to the leading area of the nth document and executes OCR processing on the image data. When the process of step S2020 ends, control proceeds to step S1020.

  Referring to FIG. 11, this program is further executed after step S1110, and whether or not reading of the nth original image data is completed, that is, OCR is performed on the entire area of the nth original image. It is determined whether or not the processing is completed, and the flow of control is branched according to the determination result, and when it is determined in step S2030 that the reading of the nth original image data is not completed. Step S2040 that is executed, reads image data corresponding to the next area of the nth original image, and executes OCR processing on the image data. If it is determined in step S2030 that reading of the nth document image data has been completed, control proceeds to step S1140. When the process of step S2040 ends, control returns to step S1020 shown in FIG.

  This program is further executed when it is determined in step S1140 that there is no sub-candidate, or when it is determined in step S2010 (see FIG. 10) that the nth document is blank, and n sheets. It is determined whether or not the eye document is the document of the last page, and the flow of control is branched according to the determination result. In steps S2050 and S2050, it is determined that the nth document is not the document of the last page. Step S2060, which is executed if the variable n is incremented by one. If it is determined in step S2050 that the nth document is the last page, control proceeds to step S1160. When the process of step S2060 ends, control returns to step S2010 shown in FIG.

[Operation]
The image processing apparatus according to the present embodiment operates as follows. Note that operations other than the operation of performing OCR processing on the image data of the second and subsequent originals are the same as those in the first embodiment. Therefore, detailed description of similar operations will not be repeated.

  The image processing apparatus reads an image of one or a plurality of originals and automatically generates a file name of the read original image data. When reading an image of a plurality of documents, the image processing apparatus executes a file name generation process in parallel with the image reading process.

  The image processing apparatus determines whether or not the first document is blank based on the data size of the read document image data. If the first document is blank (YES in step S2010), it is determined whether or not the first document is the last page. If the first document is not the last page document (NO in step S2050 shown in FIG. 11), the image processing apparatus determines whether the second document is blank (step S2060 and FIG. 10). Step S2010). As described above, when the read document includes a blank document, the image processing apparatus skips the blank document. If it is determined that the nth document is not blank (NO in step S2010), the image processing apparatus reads image data corresponding to the top area of the nth document and performs OCR on the image data. Processing is performed (step S2020). When the character string is recognized by the OCR process (YES in step S1020), the image processing apparatus excludes a general character string and a character string having a certain number of characters or more from the recognized character string from file name candidates ( Step S1030). When there is a character string that becomes a candidate for a file name after excluding a general character string and a character string that exceeds a certain number of characters (YES in step S1040), the image processing apparatus is based on the character string that is a candidate for a file name. The file name is determined (generated) (step S1080).

  On the other hand, if there is no character string that is a candidate for a file name after excluding a general character string and a character string that exceeds a certain number of characters (NO in step S1040), the image processing apparatus may It is determined whether or not the setting is ON. When it is ON, the image processing apparatus adds the excluded character string to the file name sub-candidate and determines whether or not reading of the nth original image data is completed. Even when the character string is not recognized by the OCR processing (NO in step S1020), the image processing apparatus determines whether reading of the nth original image data is completed. If the reading of the nth original image data has not been completed (NO in step S2030), the image processing apparatus reads image data corresponding to the next area of the nth original and reads the image data. OCR processing is performed (step S2040).

  If the reading of the nth original image data has been completed (YES in step S2030), that is, until the OCR processing for the entire area of the nth original is completed, a character string that is a file name candidate is displayed. If not extracted, the image processing apparatus determines whether or not a character string as a sub candidate of the file name has been added. If there is a sub candidate (YES in step S1140), the image processing apparatus sets the sub candidate as a file name candidate (step S1150). If there is no sub candidate (NO in step S1140), the image processing apparatus determines whether or not the nth document is the last page. If the nth document is not the last page document (NO in step S2050), the above process is repeated for the next document (n + 1th document). If the nth document is the document of the last page (YES in step S2050), the image processing apparatus generates a file name consisting of “date and time + machine specific information” (step S1160), and uses the generated file name. The read document image data is stored in the storage device 118.

  As described above, the image processing apparatus according to the present embodiment sequentially removes a blank document from the first region of the document image in units of a predetermined region until each character string as a file name candidate is extracted. OCR processing is performed on the corresponding image data. Therefore, for example, even if a character string that is a candidate for a file name is not extracted from the first document, it is possible to extract a character string that is a candidate for a file name from the second and subsequent documents. This makes it possible to effectively generate a file name that takes into account the content of the read document image data.

(Third embodiment)
The image processing apparatus according to the present embodiment is different from the image processing apparatus 100 according to the first embodiment in that a notification screen that prompts the user to change the document setting direction is displayed on the operation panel. In other respects, each image processing apparatus has the same configuration.

  In the present embodiment, the image processing apparatus displays a document selection screen 400 (see FIG. 12) on the operation panel to allow the user to select in advance what kind of document is read by the document reading unit. The user inputs via the document selection screen 400 whether the document to be scanned is a horizontally written document or a vertically written document. Referring to FIG. 12, document selection screen 400 includes a plurality of selection keys for selecting the type of document to be scanned. A plurality of selection keys include a “horizontal writing (1)” key 410 for selecting a horizontally written document, a “horizontal writing (2)” key 412 for selecting a horizontally written document in which two pages are combined into one sheet, A “vertical writing (1)” key 414 for selecting a vertically written document and a “vertical writing (2)” key 416 for selecting a vertically written document in which two pages are combined into one sheet are included.

  The image processing apparatus includes a sensor (not shown) that detects a setting direction of a document when a document to be read is set. The image processing apparatus determines the scanning direction of the document based on the detected setting direction. The image processing apparatus further determines the timing for performing the OCR processing based on the type of document selected via the document selection screen 400 and the scan direction of the set document.

  Referring to FIG. 13, when “horizontal writing (1)” key 410 is operated on original selection screen 400 (see FIG. 12) and an original is set to be scanned in the longitudinal direction (in the case of a1), or When the “horizontal writing (2)” key 412 is operated and an original is set to be scanned in the short direction (in the case of d1), the reading of the original image data for one sheet is completed before reading the area 420 or OCR processing can be performed on the region 426. Therefore, in these cases, the OCR processing is set to be performed before the reading of the original image data for one sheet is completed.

  On the other hand, when the “horizontal writing (1)” key 410 is operated on the original selection screen 400 (see FIG. 12) and the original is set to scan in the short direction (in the case of b1), 2) ”key 412 is operated and the original is set to be scanned in the longitudinal direction (in the case of c1), the area 422 or the area 424 is read before the reading of the original image data for one sheet is completed. When the OCR process is performed, it is difficult to recognize the character string. Therefore, in these cases, the OCR process is set to be performed after the reading of the document image data for one sheet is completed.

  The same applies to the case where the “vertical writing (1)” key 414 or the “vertical writing (2)” key 416 is operated on the document selection screen 400. Referring to FIG. 14, when “vertical writing (1)” key 414 is operated on original selection screen 400 and the original is set to be scanned in the longitudinal direction (case a2), or “vertical writing (2) ) ”Key 416 is operated and the document is set to scan in the short direction (in the case of d2), the reading of the image data of one sheet is completed with respect to the area 430 or the area 432 OCR processing can be performed. Therefore, in these cases, the OCR processing is set to be performed before the reading of the original image data for one sheet is completed.

  When the “vertical writing (1)” key 414 is operated on the original selection screen 400 and the original is set to scan in the short direction (in the case of b2), or the “vertical writing (2)” key 416 is operated. When the original is set to be scanned in the longitudinal direction (in the case of c2), if the OCR process is performed on the area 432 or the area 434 before the reading of the original image data for one sheet is completed, the character string It becomes difficult to recognize. Therefore, in these cases, the OCR process is set to be performed after the reading of the document image data for one sheet is completed.

  By performing the OCR process before the reading of one document image data is completed, the file name generation process can be performed more quickly. When the image processing apparatus is set to perform the OCR process after the reading of one sheet of document image data is completed, the image processing apparatus displays a notification screen 500 (see FIG. 15) on the operation panel to inform the user of the document. Prompt to change the set direction. Referring to FIG. 15, the notification screen 500 displays, for example, a display area 510 that displays a message “The file name automatic generation processing is accelerated by rotating the document setting direction by 90 °”, and the processing is continued. “YES” key 520 that is operated when the document is continued, and “NO” key 530 that is operated when the document setting direction is changed.

  When “YES” key 520 is operated, the image processing apparatus maintains a setting for performing OCR processing after reading of one sheet of document image data is completed. On the other hand, when the “NO” key 530 is operated, the image processing apparatus determines whether or not the document setting direction has been changed. When the document setting direction is changed, the image processing apparatus changes the setting to a setting for performing OCR processing before reading of one sheet of document image data is completed.

  When the user gives an instruction to start reading a document image, the image processing apparatus controls the document reading unit to read the document image data from the set document. When the OCR processing is set to be performed before the reading of one document image data is completed, when the image processing apparatus reads the image data of the first area of the document image, the image data is subjected to OCR. Perform processing. When the OCR processing is set to be performed after the reading of one sheet of document image data is completed, the image processing apparatus extracts image data corresponding to the first area of the document image from the read document image data, OCR processing is performed on the image data.

  As described above, according to the present embodiment, by prompting the user to change the document setting direction, the file name generation process can be performed more quickly.

(Modification)
In the above-described embodiment, an example in which the present invention is applied to a multifunction peripheral that is one type of image processing apparatus has been described, but the present invention is not limited to such an embodiment. As long as it has an image reading function for reading an image of a document as document image data, the image processing device may be, for example, a scanner device other than a multifunction peripheral.

  In the above embodiment, an example in which the OCR process for image data is performed by the control unit has been described. However, the present invention is not limited to such an embodiment. For example, an OCR processing unit may be provided in the image processing unit, and the OCR processing unit may perform OCR processing.

  In the above-described embodiment, an example in which the read document image data is stored in the internal storage device has been described. However, the present invention is not limited to such an embodiment. For example, a removable external storage medium such as a USB (Universal Serial Bus) memory may be mounted on the image processing apparatus, and the read document image data may be stored in the mounted external storage medium.

  In the above embodiment, an example of a character string that exceeds the number of characters applicable to the file name as a character string of a certain number of characters excluded from the file name candidates has been shown, but the present invention is not limited to such an embodiment. It is not limited. The character string having a certain number of characters may be a character string having the number of characters applicable to the file name. The number of characters in the character string can be arbitrarily set.

  In the first embodiment, an example of generating a file name composed of “date and time + machine specific information” when the first document is blank has been described. However, the present invention includes such an embodiment. Is not limited. When a plurality of originals are continuously read, even if the first original is a blank sheet, a file name is generated by performing OCR processing on the second and subsequent non-blank originals. Also good. That is, file name generation processing by OCR processing may be performed on a single document excluding a blank document.

  Embodiments obtained by appropriately combining the techniques disclosed above are also included in the technical scope of the present invention.

  The embodiment disclosed herein is merely an example, and the present invention is not limited to the embodiment described above. The scope of the present invention is indicated by each claim of the claims after taking into account the description of the detailed description of the invention, and all modifications within the meaning and scope equivalent to the wording described therein are included. Including.

DESCRIPTION OF SYMBOLS 100 Image processing apparatus 110 Control part 112 CPU
114 ROM
116 RAM
118 Storage Device 120 Operation Unit 130 Document Reading Unit 140 Image Processing Unit 150 Image Forming Unit 160 Paper Feeding Unit 200 System Setting Screen 300 Selection Screen 400 Document Selection Screen 500 Notification Screen

Claims (9)

A document reading means for reading a document image as document image data;
Character recognition means for performing character recognition processing on image data corresponding to a partial area of the original image among original image data read by the original reading means;
Depending on the setting direction of the document and the arrangement direction of the characters on the document, the character recognition process by the character recognition unit is performed after the reading of the document image data by the document reading unit is completed, or before the completion. Setting means for setting whether to perform;
A notification means for notifying the user in response to the setting means being set to perform the character recognition processing by the character recognition means after the reading of the document image data by the document reading means is completed;
Generating means for generating a file name of the document image data based on a character string recognized by the character recognition means;
An image processing apparatus comprising: storage means for storing original image data read by the original reading means using a file name generated by the generating means. In response to the setting means having been set to perform character recognition processing by the character recognition means after the reading of the original image data by the original reading means has been completed by the setting means, The image processing apparatus according to claim 1, wherein notification is made to change the set direction of the image. The image processing apparatus further includes:
A determination means for determining whether or not a character string sandwiched between predetermined blank areas has been recognized by the character recognition process as a character string as a file name candidate;
Recognition for controlling the character recognition means to perform character recognition processing on image data corresponding to another part of the original image in response to a negative determination result of the determination means. Processing control means,
The generation unit includes a file name generation unit for generating a file name of the document image data based on a recognized character string in response to a positive determination result of the determination unit. The image processing apparatus according to claim 1 or 2 . The recognition processing control unit controls the character recognition unit to perform character recognition processing on image data corresponding to each area in order of a predetermined size from the beginning to the tail of the document image. The image processing apparatus according to claim 3 . The determination means excludes a character string that is a preset character string and a predetermined number of characters from the file name candidates, and the character string that is the file name candidate is recognized by the character recognition process. or it contains the string determination means for determining the image processing apparatus according to claim 3 or claim 4. The image processing apparatus further includes a setting unit configured to set the excluded character string as a file name candidate in response to the determination result of the character string determination unit being negative.
The generating means further comprises a hand stage for generating a file name of the original image data based on the set character string by said setting means, the image processing apparatus according to claim 5. The image processing apparatus further includes:
In response to the determination result of the determination means being affirmative, a candidate number determination means for determining whether or not a plurality of character strings as file name candidates have been recognized;
In response to the determination result of the candidate number determination means being affirmative, a selection means for causing the user to select one of a plurality of character strings that are file name candidates,
The generating means is based on a recognized character string or a character string selected by the user via the selecting means among a plurality of recognized character strings according to the determination result of the candidate number determining means. generates a file name of the original image data, the image processing apparatus according to any one of claims 3 to 6. The image processing apparatus further includes:
In response to the determination result of the character string determination means being negative, candidate number determination means for determining whether or not a plurality of character strings are set as file name candidates;
In response to the determination result of the candidate number determination means being affirmative, a selection means for causing the user to select one of a plurality of character strings that are file name candidates,
The generation unit is configured based on a character string selected by the user via the selection unit among a set character string or a plurality of set character strings according to the determination result of the candidate number determination unit. The image processing apparatus according to claim 6 , wherein a file name of the document image data is generated. The image processing apparatus further determines whether or not the character recognition processing for the document image data of the first document is completed in response to the images of a plurality of documents read by the document reading unit. in accordance with the determination result, including processing stop means for controlling said character recognition means so as to stop the character recognition processing, the image processing apparatus according to any one of claims 1 to 8.

Images