JP2015153138A - information processing system, information processing method and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To allow, even in a case in which information described in accordance with an unregistered form is included in an acquired image, the information to be taken out easily.SOLUTION: An image analysis section 122 analyzes an image acquired by an image acquisition section 121. A form determination section 123 determines whether or not the image matches any of forms registered in prescribed form registration means on the basis of the analysis result. When it is determined that the image matches any of the forms, an information acquisition section 126 takes information out of the image in accordance with the matching form. When it is determined that the image does not match any of the forms, a form generation section 125 generates a new form on the basis of the analysis result by the image analysis section 122 and the information acquisition section 126 takes the information out of the image in accordance with the generated form.

Description

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

  2. Description of the Related Art Conventionally, an information processing system that acquires information on a plurality of items described therein from an image of a document described along a predetermined form is known. By using such an information processing system to read and process an image of a document, it is possible to automate the operation of inputting data entered in a form into a database.

In such an automation, it usually takes time and effort to define input items on the system. However, in order to save such trouble, a technique for generating an input form on a system based on a paper form is also considered and already known.
In Patent Document 1, an image of a completed form is analyzed to determine a frame area and a character area, and a frame area adjacent to a character string that matches an attribute name input by a user is determined as an attribute value frame. A configuration for generating a form definition from the result is disclosed.

However, even when the technique described in Patent Document 1 is used, in order to appropriately process the read form image, it is necessary to create a form definition in advance for all the forms to be used. However, in practice, there is a case where work using a form is gradually systemized, and it is sometimes burdensome to create form definitions in advance for all forms.
Such a problem occurs in the same manner even when information is taken from an image other than a form.

  The present invention has been made in view of such a background, and an object of the present invention is to make it possible to easily retrieve the information even if the acquired image includes information described according to an unregistered form. To do.

  In order to achieve the above object, an information processing system according to the present invention analyzes an image acquisition unit for acquiring an image and an image acquired by the image acquisition unit in an information processing system including one or more information processing apparatuses. An image analysis unit that performs determination based on an analysis result by the image analysis unit, and a determination unit that determines whether the image acquired by the image acquisition unit applies to any of the forms registered in a predetermined form registration unit; When it is determined that the determination unit is applicable to any form, a first information acquisition unit that extracts information from an image acquired by the image acquisition unit according to the applicable form, and the determination unit is not applicable to any form If determined, a new form is generated based on the analysis result by the image analysis means, According form generated by the is provided with a second information acquiring means for extracting information from an image by the image acquisition unit has acquired.

  According to the above configuration, even when the acquired image includes information described according to an unregistered form, the information can be easily extracted.

It is a figure which shows the structural example of the form processing system containing the data processing server which is one Embodiment of the information processing system of this invention. It is a figure which shows the hardware constitutions of the data processing server shown in FIG. It is a figure which shows the structure of the function with which the data processing server shown in FIG. 1 is provided. It is a flowchart of the process which CPU of the data processing server shown in FIG. 1 performs. It is explanatory drawing regarding this inclination and position shift correction of an image. It is explanatory drawing regarding correction | amendment of the size shift of an image. It is a figure which shows the example of frame definition data. It is a figure which shows the example of form data. It is a figure which shows the example of the comparison frame definition data. It is a figure which shows the example of form data. It is a figure which shows the example of form list data. It is a figure which shows the example of an input reception screen. It is a figure which shows the example of display element data. It is a figure which shows the example of the input reception screen to which display element data is applied.

FIG. 1 shows a configuration example of a form processing system including a data processing server 100 which is an embodiment of an information processing system of the present invention.
The form processing system 1 shown in FIG. 1 includes a data processing server 100, a scanner 200, and a terminal device 300, which are connected via a network 400.

  The data processing server 100 has a function of acquiring an image of a document such as a form, analyzing it, and specifying a form corresponding to the image. It also has a function of extracting information from an image acquired according to the form and registering it as input information related to the form. Regarding the image to be processed, an image obtained by reading can be acquired from an image reading device such as the scanner 200. It is also possible to obtain a pre-stored image or an image transmitted from an external device by e-mail or file transfer, and perform similar processing.

  The scanner 200 is an image reading apparatus including an image reading unit that reads an image of a document and acquires the image data. Then, the image processing apparatus 100 has a function of transmitting the read image data to the data processing server 100. This reading and transmission of image data may be performed according to a user operation on the scanner 200, according to control from the data processing server 100, or according to an instruction from another external device such as the terminal device 300. Here, it is assumed that both of these are possible. Further, the scanner 200 may be a device having a function other than reading, such as an MFP (digital multifunction peripheral).

The terminal device 300 is an information processing device operated by a user, and can be configured by a PC (personal computer), for example. The terminal device 300 has a function of causing the scanner 200 to read an image and transmit image data to the data processing server 100 according to a required application installed. In addition, a function of accepting an instruction for confirming input information acquired by the data processing server 100 or correcting information registered in the data processing server 100 from a user and performing a necessary instruction to the data processing server 100 according to the instruction. Prepare.
The network 400 is a communication path for connecting each device constituting the form processing system 1, and can use any standard regardless of wired or wireless. It may be the Internet or a LAN (local area network).

Next, FIG. 2 shows a hardware configuration of the data processing server 100 shown in FIG.
As shown in FIG. 2, the data processing server 100 includes a CPU 101, a ROM 102, a RAM 103, an HDD (hard disk drive) 104, a communication I / F 105, a display unit 106, and an operation unit 107, which are connected via a system bus 108. It is said.

  The CPU 101 controls the entire data processing server 100 by executing a program stored in the ROM 102 or the HDD 104 using the RAM 103 as a work area, and implements various functions including those described later with reference to FIG. To do. For example, it is a function for acquiring and analyzing an image or specifying a form corresponding to the acquired image.

The ROM 102 and the HDD 104 are non-volatile storage media (storage means) and store various programs executed by the CPU 101 and various data described later.
The communication I / F 105 is an interface for communicating with external devices such as the scanner 200 and the terminal device 300 via the network 400.
The display unit 106 is a presentation unit for presenting the operation state and setting contents of the data processing server 100 to the user, and includes a liquid crystal display, a lamp, and the like.

The operation unit 107 is an operation unit for receiving an operation from the user. In addition to various buttons and switches, a touch panel may be provided.
In addition, when the data processing server 100 does not need to directly receive an operation from the user (it is only necessary to operate from an external device such as the terminal device 300), the display unit 106 and the operation unit 107 may not be provided.

The scanner 200 has a known configuration including a control unit including a CPU, a ROM, a RAM, a communication I / F, and the like corresponding to each unit illustrated in FIG. 2 and a scanner engine for reading an image as hardware. Good.
The terminal device 300 may be a known computer including a CPU, a ROM, a RAM, a communication I / F, and the like corresponding to each unit illustrated in FIG. 2 as hardware.
Here, detailed description of the hardware of the scanner 200 and the terminal device 300 is omitted.

Next, FIG. 3 illustrates a configuration of functions included in the data processing server 100 related to image processing, information extraction from an image, and handling of a form. The functions shown in FIG. 3 are realized by controlling various hardware shown in FIG. 2 by the CPU 101 executing a required program.
As shown in FIG. 3, the data processing server 100 includes an image acquisition unit 121, an image analysis unit 122, a form determination unit 123, a form registration unit 124, a form generation unit 125, an information acquisition unit 126, an information registration unit 127, and an information input. A reception unit 128 and a form editing unit 129 are provided.

  Among these, the image acquisition unit 121 has a function of acquiring image data of an image to be processed in the data processing server 100 and corresponds to an image acquisition unit. As described above, this acquisition can be performed by reception from the scanner 200, reading from a predetermined or user-specified image registration unit, reception from other external devices, and the like.

  The image analysis unit 122 has a function of analyzing the image data acquired by the image acquisition unit 121 and corresponds to an image analysis unit. This process is a process for acquiring information necessary for comparing with form data defining a form or newly generating form data from image data. More specifically, it includes processing for specifying the position of the frame included in the image data and the area in which characters are described in the image data. It also includes various correction processes for removing the influence of various noises that occurred during image reading. Details thereof will be described later.

The form determination unit 123 has a function of determining whether an image to be processed corresponds to one of the forms registered in the form registration unit 124 based on the analysis result by the image analysis unit 122, and corresponds to a determination unit. . This determination is performed by comparing the position of the frame in the image with the position of the frame defined in each form data, details of which will be described later.
The form registration unit 124 has a function of registering an arbitrary number of form data defining a form, and corresponds to a form registration unit.

  When the form determination unit 123 determines that the processing target image does not apply to any registered form, the form generation unit 125 creates a new image corresponding to the processing target image based on the analysis result of the image analysis unit 122. It has a function to generate form data. In addition, a function for registering the generated form data in the form registration unit 124 is provided. Details of the generation of the form data will be described later.

  The information acquisition unit 126 has a function of extracting information on items defined in the form data from the processing target image based on the form data to which the processing target image applies. The form data to be used is the form data of the form when the form determination unit 123 determines that the image to be processed applies to any of the registered forms. If it is determined that neither of these applies, it is new form data generated by the form generation unit 125. In the former case, the information acquisition unit 126 corresponds to the first information acquisition unit. In the latter case, the form generation unit 125 and the information acquisition unit 126 correspond to the second information acquisition unit.

  The information registration unit 127 has a function of registering the information extracted by the information acquisition unit 126 as input information related to the form in association with the form to which the processing target image applies, and corresponds to an information registration unit. At this time, identification information indicating which image the information is derived from is attached to the information to be registered. The information registration unit 127 also has a function of registering the information received by the information input receiving unit 128 in the same manner. This information may be registered with identification information indicating manual input.

The information input accepting unit 128 has a function of accepting input of information related to a form selected by the user from among the forms registered in the form registering unit 124, and corresponds to an input accepting unit. The information input receiving unit 128 also has a function of causing the information registration unit 127 to register the input information in association with the form used for input reception when the user inputs necessary information and instructs registration. Prepare.
The form editing unit 129 has a function of editing form data registered in the form registration unit 124 in accordance with a user instruction.

Next, FIG. 4 shows a flowchart of processing relating to image processing and information extraction from the image, which is executed by the CPU 101 of the data processing server 100.
When instructed by the user, application, external device, or the like to extract information from the image and register it in the information registration unit 127, the CPU 101 starts the process shown in the flowchart of FIG. The start trigger may be that image data of an image to be extracted is received.

  In the process of FIG. 4, the CPU 101 first acquires image data of an image to be processed (S11). The specific acquisition method is as described above. This process is a process corresponding to the function of the image acquisition unit 121, and is a process of an image acquisition procedure.

  Next, the CPU 101 corrects the positional deviation caused by the inclination and the parallel movement of the image in the acquired image data (S12). If the image data is obtained by reading a paper document, the frame in the image data may be tilted or misaligned due to misalignment when the paper is placed in the image reader. It can be considered. In the first place, when a form is printed on paper, it is also conceivable that tilt or misalignment occurs. In this case, when the misprinted paper is read, even if it is arranged without misalignment in the image reading unit, misalignment occurs in the image data.

  If such a deviation remains, the position of the frame in the image data does not match the position of the frame indicated by the form data even though an image corresponding to one of the forms is processed. there is a possibility. Therefore, before specifying the position of the frame, first, the positional deviation caused by the inclination and translation of the image is corrected.

FIG. 5 shows the concept of this inclination and misalignment correction.
For inclination correction, as shown in FIG. 5A, first, the longest frame line (the line above the frame of the item “zzz” indicated by a thicker line in the figure) is extracted from the image data. . Then, if the frame line extends in the vertical direction, the entire image data is rotated so that the frame line becomes vertical, and if it extends in the horizontal direction, the frame line becomes horizontal. As a result, it is possible to eliminate the influence of the inclination of the frame line due to an error in the document arrangement and the printing direction.

  As for misalignment correction, as shown in FIG. 5B, the plain portion is cut from each of the upper, lower, left and right ends of the image data. However, to prevent the border lines and characters from being cut, a solid portion is left at a certain rate. Since the positional relationship between the frame line and characters remaining in the center should be constant regardless of whether or not translation is performed, this eliminates the effects of translational displacement caused by document placement or printing displacement. Can do.

Returning to the description of FIG. 4, the CPU 101 next extracts a frame area and a character area from the image data after the correction in step S12 (S13). This extraction may be appropriately performed by a known method, and for example, a method described in JP-A-2009-31937 can be used. The frame area is an area where a frame is arranged in the image data, and the character area is an area where characters exist in the image data.
Further, the CPU 101 divides the corrected image data into a predetermined number of equal-sized blocks (S14). Thereafter, frame definition data defining the position of the frame region extracted in step S13 is generated according to the block classification created in step S14 (S15).

  Here, the block division is performed in order to correct a size shift caused by enlargement / reduction of an image included in the image data. When the image data is obtained by reading a paper document, it is conceivable that a size shift occurs in addition to the above-described inclination and position shift. However, the size here refers to the number of dots of image data. Accordingly, in addition to the case where the paper sizes are different, the size deviation also occurs when the reading resolution and the magnification setting for reading are different.

  However, even when such a size shift occurs, the percentage of each frame or character at what percentage from the top of the image and what percentage from the left does not change. Therefore, as shown in FIG. 6, the image data is divided into a predetermined number of equal-sized blocks, and the position and size of each frame are counted on the basis of the number of blocks, thereby eliminating the influence of the size shift. it can.

For example, when an image is divided into 400 blocks in each of vertical and horizontal directions, the horizontal size of the image data after the correction in step S12 is X, the vertical size is Y, and (n-1) X / 400 is horizontal. The start coordinate of the nth block of (n-1) Y / 400 may be set as the start coordinate of the nth block in the vertical direction. Of course, the number of blocks may be different between the vertical direction and the horizontal direction. Further, as long as the horizontal direction and the vertical direction are respectively divided at equal intervals, the horizontal length and the vertical length of each block may be different.
In the frame definition data generated in step S15, the position of the left end, the position of the upper end, the height, and the width of each frame are counted based on the number of blocks.

FIG. 7 shows an example of the frame definition data.
In this example, six frames are detected in the image data, and the frame ID is identification information for identifying the frame. The value of the item “left” indicates the number of the left end of the frame included from the left end of the blocks arranged in the horizontal direction. The value of the item “upper” indicates the number of the upper end of the frame included from the top of the blocks arranged in the vertical direction. The value of the item “height” indicates how many blocks in the vertical direction the height of the frame (range in the vertical direction) is. The value of the item “width” indicates the number of blocks arranged in the horizontal direction (the range in the horizontal direction).
Note that the height and width may be obtained by dividing the number of pixels by the number of pixels per block, or by counting how many blocks the frame exists over.

As described above, when the frame definition data is created based on the number of blocks, the influence of the size shift can be removed, and a slight positional shift error can be absorbed. Even if the displacement due to the inclination or the parallel movement cannot be completely removed by the correction in step S12, if the error is such that the position of the frame does not deviate from the original block, the value of the generated frame definition data is It is because it becomes the same. As described below, when a hash value is used for comparison with form data, even if the value is different, a determination result of “does not match” is generated if the value is different. The effect of being able to be absorbed is great. Therefore, it is desirable to reduce the number of blocks as much as possible within a range in which a resolution necessary for expressing a difference between forms can be obtained.
The processing in steps S12 to S15 described above is processing corresponding to the function of the image analysis unit 122, and is processing of an image analysis procedure.

  Returning to the explanation of FIG. 4, the CPU 101 next obtains a hash value of the frame definition information generated in step S15 (S16). Then, it is determined whether there is a form having the same hash value as the hash value obtained in step S16 among the forms registered in the form registration unit 124 (S17).

Here, FIG. 8 shows an example of form data indicating a form registered in the form registration unit 124.
FIG. 8 shows form data for one form. The form ID is identification information for identifying the form. The item ID is identification information for identifying an item included in the form. The item name is the name of the corresponding item. The item type is the data type of the corresponding item. The values of the items “left”, “top”, “height”, and “width” indicate the position and size of the frame that describes the information of the corresponding item, and the frame definition data shown in FIG. As with, the value is counted based on the number of blocks.

  Accordingly, if the image to be processed is an image of the form indicated by the form data, the frame definition information generated in step S15 should match the frame information included in the corresponding form data. It can be expected that these pieces of information are completely coincident after the above-described correction of the inclination, the positional deviation, and the size deviation.

  Therefore, each value may be compared one by one, but in order to speed up the processing, the entire frame definition information is converted into a hash value which is one value uniquely corresponding to the information, The hash value of the included frame information is compared. In this way, although it is necessary to perform hash processing, it is only necessary to compare one value for each form data, so that the processing load can be reduced.

  For the form data registered in the form registration unit 124, as shown in FIG. 9, a hash value may be calculated in advance and registered as comparison frame definition data in association with the form ID. Of course, the hash value of the frame definition information and the hash value of the frame information in the form data are obtained by the same algorithm. Note that the frame ID may or may not be subject to hash processing.

  Returning to the description of FIG. 4, if Yes in step S <b> 17, it can be seen that there is a form in which the image to be processed and the frame position match. Therefore, the CPU 101 determines whether there is one matched form (S18). If it is one, it can be determined that the image to be processed applies to the matched form, and therefore the matched form is selected as the form to be used for extracting information (S19).

On the other hand, if the number is not one (a plurality) in step S18, it is not yet possible to specify which form the image to be processed is, so the item names are compared. That is, the CPU 101 performs OCR (optical character recognition) processing on the character region extracted in step S13 from the processing target image. Then, the character string obtained as a result is compared with the item name included in the form data of each form whose hash value matches in step S17 (S20). Based on the comparison result, the CPU 101 determines that the image to be processed falls into the form having the highest ratio of the item name character string included in the character string of the OCR result. Then, this form is selected as a form used for extracting information (S21).
The processes in steps S16 to S21 described above are processes corresponding to the functions of the form determination unit 123, and are determination procedure processes. The process of step S21 is an example of a process for selecting a form whose item name most closely matches the OCR result.

  In any case, the CPU 101 next extracts information on characters in each frame from the image data corrected in step S12 in accordance with the form data of the form selected in step S19 or step S21 (S22). For this extraction, an OCR process for detecting handwritten characters may be performed on the area of each frame indicated by the form data. Further, the character string obtained by the OCR process is converted for each item into a data type indicated by the item type of the item.

FIG. 10 shows an example of information extracted in step S22. The information shown in FIG. 10 is called “form data” in the sense of information extracted from one form.
FIG. 10 shows the result of performing the OCR process for each frame with the item IDs 1 to 3 in accordance with the form data shown in FIG. 8. As a result, “001234”, “Taro Rikko” and “2013/08 / This is an example when the character string “12” is obtained. According to the item type of each item, “001234” is extracted as a numerical value and “2013/08/12” is extracted as a date.
The process in step S22 is a process corresponding to the function of the information acquisition unit 126. If the process proceeds from step S19 or S21, the process is a first information acquisition procedure.
Thereafter, the CPU 101 registers the information extracted in step S22 in the information registration unit 127 in association with the form used for extraction (S23), and ends the process.

FIG. 11 shows an example of information registration status in the information registration unit 127. The information shown in FIG. 11 is called “form list data” in the sense of a list of information extracted from a plurality of forms.
In FIG. 11, the form ID is the form ID of the form used to extract information. The data ID is identification information for uniquely identifying an image to be processed. The item ID is an item ID included in the form data of the form used for extracting information. The value is the value of the corresponding item extracted from the image data in step S22.
That is, in step S23, a unique data ID is attached to the form data shown in FIG. 10, and the form data is associated with the form ID and added to the form list data.

  On the other hand, in the case of No in step S17, that is, when there is no form having the same hash value, the CPU 101 performs processing for newly creating form data of a form that applies to the processing target image. Specifically, first, OCR processing is performed on the character area adjacent to each frame indicated by the frame definition information generated in step S15, and the obtained character is acquired as an item name corresponding to each frame (S24). Then, new form data is generated from the frame definition information and the acquired item name and registered in the form registration unit 124 (S25). The format of the form data is the same as that already registered in the form registration unit 124 as shown in FIG.

  At this time, the form ID is appropriately assigned so as not to overlap with other forms. Item IDs are appropriately assigned so that they do not overlap within one form data. For the frame information included in the form data, the frame definition information acquired in step S15 may be copied. As the item type, an item type to be set for each value of the item name is determined in advance, and when the item name does not correspond to any of the item types, a default value may be considered. For example, if the item name is “No.”, “numerical value”, if “xxx day” is “date”, the default value is “character string”, and the like.

The form data generated in this way may be presented to the user before registration so that an editing operation can be accepted. Also, as disclosed in Japanese Patent Application Laid-Open No. 2009-31937, designation of an item name is received from the user in advance, and a frame adjacent to the character string of the item name is recognized as a frame for the item name item. It may be.
Although not shown, when registering the form data in the form registration unit 124, a hash value of the frame information included in the form data is calculated, and the form is used as the comparison frame definition data shown in FIG. Register in association with the ID.

The processing in steps S24 and S25 described above is processing corresponding to the function of the form generation unit 125, and is part of the processing of the second information acquisition procedure.
After the above, the CPU 101 selects the form registered in step S25 as a form used for extracting information (S26), and proceeds to step S22. The processing after step S22 is the same as the case where the processing proceeds from steps S19 and S21. However, when the process proceeds from step S26, the process of step S22 is a part of the process of the second information acquisition procedure.

With the processing shown in FIG. 4 described above, the data processing server 100 performs processing according to the applicable form when the processing target image matches any of the registered forms based on the analysis result of the processing target image. Information can be extracted from the target image. If none of the registered forms is applicable, a new form can be generated based on the analysis result, and information can be extracted from the processing target image according to the generated form.
Therefore, even if an image such as a form processed by the data processing server 100 conforms to a form that is not yet registered in the data processing server 100, a new form is generated according to the contents of the image. Therefore, information can be easily acquired from the image.

In addition, since the generated form is registered in the form registration unit 124, information can be acquired according to the registered form when an image of the same form is subsequently processed.
In addition, whether or not the image to be processed applies to the form is determined by comparing the position of the frame in the image with the position of the frame included in the form, so this comparison can be performed with a small processing load. Also, if the information on the position of the frame in the image is replaced with a value uniquely corresponding to that information, and the information on the position of the frame included in the form is compared with the value converted by the same conversion procedure, The frame positions can be compared with a smaller processing load.

  When comparing the position of the frame, it is possible to perform comparison with higher accuracy by correcting the inclination of the frame line in the processing target image, the position shift due to the parallel movement of the frame line, and the size shift due to the enlargement / reduction of the image. It can be carried out. If it is determined that the image to be processed does not apply to any of the registered forms, a new form will be created, which is a great way to improve the accuracy of comparison between the image to be processed and the form. It can be said that there is a meaning.

  In addition, when a plurality of forms whose frame positions match the image to be processed are found, it is determined that the form whose item name most closely matches the character string in the image is the form to which the image to be processed applies. I have to. Thus, even when there are a plurality of forms having the same frame position, it is possible to distinguish these and search for a form to which the image to be processed applies.

In the process of FIG. 4, the data processing server 100 automatically extracts and registers information from the processing target image. However, the data processing server 100 inputs information according to a registered form. It is also possible to accept from a user without using an image. The information input receiving unit 128 is as described above.
This input reception generates screen data including a field for receiving input for each item included in the corresponding form according to the form data of the form selected by the user, and transmits the data to the terminal device 300 to display the screen. Can be displayed.

FIG. 12 shows an example of this screen. 12 includes a title 501, input fields 502 to 504 for each item, a send button 505, and a cancel button 506.
When the user operates the terminal device 300 to access the data processing server 100, selects one of the forms registered in the form registration unit 124, and instructs to input data according to the form, the information The input reception unit 128 generates data for the input reception screen 500.

  The information input receiving unit 128 first creates a title 501 and input fields 502 to 504 for each item according to the form data of the selected form. The title 501 is created based on the form ID. For the input fields 502 to 504, a title corresponding to the item name and an input field corresponding to the item type may be provided. The example of FIG. 12 shows a screen according to the form data shown in FIG. 8. Input fields 502 and 503 for “No.” and “Name” accept text input, and input field 504 for “Date”. Accepts date input. The “■” mark is an icon for instructing display of a date designation calendar. However, a common input field may be used regardless of the item type. These display contents can be edited as will be described later.

  The send button 505 and the cancel button 506 are provided in common regardless of the contents of the form data. A send button 505 is a button for confirming the input content and instructing the data processing server 100 to register it, and a cancel button 506 is a button for instructing to discard the input content without registering it.

  The information input reception unit 128 transmits the data of the above input reception screen 500 to the terminal device 300 and displays the data on the display. When the terminal device 300 detects that the transmission button 505 has been operated, the terminal device 300 requests the data processing server 100 to register the input information, and the information input reception unit 128 responds to the request by the information registration unit. 127 to perform registration. The registration may be performed on the form list data shown in FIG. 11 without being distinguished from the registration by the processing of FIG. However, the data ID may be a value that can be identified as manual input.

  As described above, data can be input to the data processing server 100 in the same manner as when the form is read by the scanner 200 without using a form, and the flexibility of the work can be expanded. Note that the user may be able to edit data once registered in the information registration unit 127 through the input reception screen 500.

The data processing server 100 can also edit the input reception screen 500 corresponding to each form data. The form editing unit 129 is as described above.
FIG. 13 shows an example of display element data that is data related to the display content of the input reception screen 500 stored in the data processing server 100.
Display element data is prepared corresponding to each form ID. Further, although not shown in FIG. 8, the display element data regarding each form ID is a part of the form data. When the form data is registered in the form registration unit 124, the form generation unit 125 automatically creates it.

  In the display element data, for each item ID, a character string (item name for replacement) to be displayed in the input column of the item is defined. The meaning of the item ID is the same as that shown in FIG. “-” Indicates that the item name shown in FIG. 8 is used as it is without replacement. The initial value of the display element data is “−”. The item name for the item ID = 0 indicates a character string used as the title 501.

FIG. 14 shows an example in which the display element data shown in FIG. 13 is reflected on the input reception screen shown in FIG.
In this input reception screen 500 ′, according to the display element data of form ID = 121, the title 501 ′ is “XX reception slip” and the title of the input field 504 ′ is “reception date”. Other portions are the same as in the example of FIG.

The user can access the data processing server 100 from the terminal device 300 and edit the display element data. As a result, data can be input on a screen on which the user can easily understand the contents.
Note that the user may be able to edit the item name included in the form data shown in FIG. Even if it does in this way, the same effect is acquired.

This is the end of the description of the embodiment. In the present invention, the specific configuration of each device, the specific processing procedure, the number of devices to be used, the configuration of data to be used, etc., are those described in the embodiment. It is not limited to.
For example, in the above-described embodiment, the example in which the data processing server 100 registers the information extracted from the processing target image in the information registration unit 127 is described. However, this is not essential. The extracted information may be transmitted to the outside without being registered.
Also, the image handled by the data processing server 100 is not limited to a form image. The data processing server 100 need not have all the functions described above. The configuration and the effects described in the above embodiment can be obtained even when the configuration is applied alone unless otherwise specified.

In the above-described embodiment, the example in which the form registration unit 124 and the information registration unit 127 are in the data processing server 100 has been described. However, the form registration unit 124 and the information registration unit 127 may be provided in an external device of the data processing server 100. When referring to and registering each of these units, the external device may be accessed.
Furthermore, the functions of the data processing server 100 in the above-described embodiment may be distributed and provided in a plurality of information processing devices, for example, some of the functions may be provided in an external device. In this case, the plurality of devices constitute an information processing system. Further, the scanner 200 or the terminal device 300 may be the plurality of information processing apparatuses.

The embodiment of the program of the present invention is a program for causing a computer to control required hardware to realize the functions of the data processing server 100 in the above-described embodiment. It also includes the case where a plurality of computers cooperate to realize their functions.
Such a program may be stored in a ROM or other nonvolatile storage medium (flash memory, EEPROM, etc.) provided in the computer from the beginning. However, it can also be provided by being recorded on an arbitrary nonvolatile recording medium such as a memory card, CD, DVD, or Blu-ray disc. Each procedure described above can be executed by installing the program recorded in the recording medium in a computer and executing the program.

Furthermore, it is also possible to download from an external device that is connected to a network and includes a recording medium that records the program, or an external device that stores the program in a storage unit, and install and execute the program on a computer.
In addition, it goes without saying that the configurations of the embodiments, operation examples, and modifications described above can be arbitrarily combined and implemented as long as they do not contradict each other.

1: form processing system, 100: data processing server, 101: CPU, 102: ROM, 103: RAM, 104: HDD, 105: communication I / F, 106: display unit, 107: operation unit, 108: system bus, 121: Image acquisition unit, 122: Image analysis unit, 123: Form determination unit, 124: Form registration unit, 125: Form generation unit, 126: Information acquisition unit, 127: Information registration unit, 128: Information input reception unit, 129 : Form editing unit, 200: Scanner, 300: Terminal device, 400: Network, 500: Input acceptance screen, 501: Title, 502-504: Input field, 505: Send button, 506: Cancel button

JP 2009-31937 A

Claims (12)

An information processing system including one or more information processing devices,
Image acquisition means for acquiring images;
Image analysis means for analyzing the image acquired by the image acquisition means;
A determination unit that determines whether the image acquired by the image acquisition unit applies to any of the forms registered in a predetermined form registration unit based on the analysis result by the image analysis unit;
A first information acquisition unit that extracts information from an image acquired by the image acquisition unit according to a corresponding form when the determination unit determines that it applies to any form;
When the determination unit determines that it does not apply to any form, a new form is generated based on the analysis result by the image analysis unit, and information is extracted from the image acquired by the image acquisition unit according to the generated form An information processing system comprising: a second information acquisition unit. The information processing system according to claim 1,
An information processing system comprising means for registering the form generated by the second information acquisition means in the form registration means. The information processing system according to claim 1 or 2,
The image analysis means comprises means for analyzing the position of a frame in the acquired image,
The information processing system according to claim 1, wherein the determination unit performs the determination by comparing the position of the frame in the form with the position of the frame obtained by the analysis by the image analysis unit. The information processing system according to claim 3,
The image analysis means comprises means for converting the information on the positions of a plurality of frames obtained by the analysis into values uniquely corresponding to the information,
The determination unit performs the determination by comparing a value uniquely corresponding to position information of a plurality of frames in the form and a value obtained by conversion by the image analysis unit. Information processing system. The information processing system according to claim 3 or 4,
The image analysis means includes means for acquiring a character string in the acquired image,
When the determination unit finds a plurality of forms whose frame positions match the image acquired by the image acquisition unit, the form whose item name best matches the character string acquired by the image analysis unit is determined as the image. An information processing system that determines that an image acquired by an acquisition unit is a corresponding form. An information processing system according to any one of claims 3 to 5,
The information processing system, wherein the image analysis means includes means for correcting the inclination of a frame line included in the image acquired by the image acquisition means. The information processing system according to any one of claims 3 to 6,
The information processing system, wherein the image analysis unit includes a unit that corrects a positional shift caused by a parallel movement of a frame line included in the image acquired by the image acquisition unit. An information processing system according to any one of claims 3 to 7,
The information processing system according to claim 1, wherein the image analysis unit includes a unit that corrects a size shift caused by enlargement / reduction of an image acquired by the image acquisition unit. An information processing system according to any one of claims 1 to 8,
Means for registering the information extracted by the first information acquisition means and the second information acquisition means in the information registration means as input information relating to the form used for the extraction;
Based on the form registered in the form registration means, input receiving means for receiving input information according to the form from the user;
An information processing system comprising: means for registering information received by the input receiving means in the information registration means as input information according to the form used for the reception. An information processing system according to any one of claims 1 to 9,
An information processing system comprising editing means for editing form information registered in the form registration means in accordance with a user operation. An information processing method executed by one information processing apparatus or a plurality of information processing apparatuses in cooperation with each other,
An image acquisition procedure for acquiring images;
An image analysis procedure for analyzing the image acquired in the image acquisition procedure;
A determination procedure for determining whether the image acquired in the image acquisition procedure is applicable to any of the forms registered in a predetermined form registration unit based on the analysis result of the image analysis procedure;
A first information acquisition procedure for extracting information from the image acquired in the image acquisition procedure according to the applicable form when the determination procedure determines that it applies to any form;
When it is determined in the determination procedure that it does not apply to any form, a new form is generated based on the analysis result of the image analysis procedure, and information is extracted from the image acquired in the image acquisition procedure according to the generated form An information processing method comprising: a second information acquisition procedure. )
One computer or multiple computers working together
The program for functioning as an information processing system as described in any one of Claims 1 thru | or 10.

Images