JP2021096543A - Information processor, information processing method, and program - Google Patents

Abstract

To extract tables and cells with high accuracy even for a form image that have been skewed or distorted during scanning and to recognize each table as a separate table even when multiple tables share a ruled line and are adjacent to each other.SOLUTION: Straight lines that become candidates for ruled lines of a table are detected in an image, ruled lines that extend from each intersection point of the straight line candidates are identified, and an area of the table is estimated based on a direction in which the identified ruled lines extend.SELECTED DRAWING: Figure 1

Description

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

OCR (optical character recognition) exists as an aid to the work of reading information from a printed form and inputting it into a system. When OCR processing a form, it can be treated as a standard form in the case where the form issued by the company is collected and the entered contents are read, and it is easy to read the target information by extracting the rectangle with the predetermined coordinates. Is. However, it is not possible to specify in advance what kind of information is entered in the forms sent from an unspecified number of issuers such as invoices, and the layout of the forms is analyzed each time after receiving the forms. It is necessary to extract information. Such forms are generally called atypical forms.

In actual work, there are still many cases where atypical forms are handled, and improving the analysis accuracy of atypical forms greatly affects the productivity of data entry work.

In particular, in Japanese forms, tables using ruled lines are often used, and it is desired to extract the table area from the form image and the cells that are the contents thereof with high accuracy.

The method of extracting a table from a form by focusing on the ruled lines has existed for a long time, but the inclination and line distortion that occur during scanning, and the line blurring and breaks that occur due to conversion to a low-resolution binary image such as FAX. The issue is how to be robust against.

Japanese Unexamined Patent Publication No. 11-53466

Patent Document 1 describes a method for extracting a table even when a ruled line is interrupted.

However, the detection of ruled lines is performed on the basis of runs (pixels that are continuous with a certain length or longer), and there is a problem that the lines are vulnerable to fine fragmentation due to blurring.

In addition, especially in a table such as a Japanese invoice where the total amount and details of the quantity and amount are shown, the layout is such that the schedule with individual items and the subtotal table with the total amount are in contact with each other. In many cases, it is desired that such a schedule and a subtotal table can be recognized separately for data recognition processing.

Therefore, an object of the present invention is to provide a mechanism capable of accurately extracting a table or a cell even for a form image in which blurring or distortion occurs during scanning. Another object of the present invention is to provide a mechanism that can be recognized as separate tables even when a plurality of tables share a ruled line and are in contact with each other.

The information processing apparatus of the present invention has a straight line detection unit that detects a vertical or horizontal straight line that is a candidate for a table rule line in an image, and an intersection point that evaluates the shape of the rule line near the coordinates of each intersection of the straight line candidates. It is characterized by having an evaluation unit, a table extraction unit that estimates a table area from the evaluation results of intersections, and a cell extraction unit that decomposes the area inside the table into cells.

According to the present invention, it is possible to accurately extract tables and cells even for a form image in which blurring or distortion occurs during scanning. Further, even when a plurality of tables share a ruled line and are in contact with each other, they can be recognized as separate tables.

It is a figure which shows an example of the system structure of the table extraction system in embodiment of this invention. It is a block diagram which shows an example of the hardware composition of the PC in embodiment of this invention. It is a flowchart which shows the process of extracting the table and the cell from the form image in embodiment of this invention. It is a flowchart which shows the detail of the tablespace extraction process in embodiment of this invention. It is a flowchart which shows the detail of the tablespace extraction process in embodiment of this invention. It is a figure which shows the process of removing a character from a form image in embodiment of this invention. It is a figure which shows an example of the form which is the object of the table extraction processing in embodiment of this invention. It is a figure which shows the state which the straight line was detected by the Hough transform from the form image in embodiment of this invention. It is a figure which shows the process which the intersection evaluation part evaluates the state of an intersection in embodiment of this invention. It is a figure which shows an example of the tablespace extraction process in embodiment of this invention. It is a figure which shows the example which performs the detection of the subtotal table which was in contact with the specification table in embodiment of this invention. It is a figure which shows an example of the cell area extraction processing in embodiment of this invention. It is a flowchart which shows the detail of the cell area extraction processing in embodiment of this invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

FIG. 1 is a diagram showing an example of a configuration of an information processing system according to the present invention.

As shown in FIG. 1, an information processing device 101 that executes processing such as table extraction and a scanner 102 that scans a form and creates an image file are connected via a communication path.

The communication path can take the form of a wired LAN, a wireless LAN, a USB, or the like, depending on the physical interface of the scanner 102.

Further, the file server 103 may be placed on the communication path. As a method of importing the image scanned by the scanner 102 into the information processing device 101, a method of directly transmitting the image from the scanner 102 to the information processing device 101, an image file captured by the scanner 102 is temporarily stored in the file server 103, and the information processing device The 101 may take out an image file from the file server 103, or the like, but any method may be used.

FIG. 2 is a block diagram showing an example of the hardware configuration of the information processing device 101, the scanner 102, and the file server 103 of the present invention.

As shown in FIG. 2, the information processing apparatus 101 and the like include a CPU (Central Processing Unit) 201, a ROM (Read Only Memory) 202, a RAM (Random Access Memory) 203, an input controller 205, and a video controller via the system bus 204. The 206, the memory controller 207, and the communication I / F controller 208 are connected.

The CPU 201 comprehensively controls each device and controller connected to the system bus 204.

The ROM 202 or the external memory 211 is a control program executed by the CPU 201, such as a BIOS (Basic Input / Output System) or an OS (Operating System), a computer-readable and executable program for realizing the information processing method, and various necessary programs. Holds data (including data table).

The RAM 203 functions as a main memory, a work area, and the like of the CPU 201. The CPU 201 realizes various operations by loading a program or the like necessary for executing the process from the ROM 202 or the external memory 211 into the RAM 203 and executing the loaded program.

The input controller 205 controls input from an input device such as a keyboard 209 or a pointing device such as a mouse (not shown). When the input device is a touch panel, the user can give various instructions by pressing (touching with a finger or the like) the icon, the cursor, or the button displayed on the touch panel.

Further, the touch panel may be a touch panel such as a multi-touch screen that can detect the position touched by a plurality of fingers.

The video controller 206 controls the display on an external output device such as the display 210. The display shall include the display of a notebook computer integrated with the main body. The external output device is not limited to the display, and may be, for example, a projector. Further, as for the device capable of accepting the above-mentioned touch operation, an input device is also provided.

The video controller 206 can control a video memory (VRAM) for display control, can use a part of the RAM 203 as a video memory area, or can provide a separate dedicated video memory. It is possible.

The memory controller 207 controls access to the external memory 211. External memory is connected to an external storage device (hard disk), flexible disk (FD), or PCMCIA card slot that stores boot programs, various applications, font data, user files, edit files, various data, etc. via an adapter. Compact flash (registered trademark) memory and the like can be used.

The communication I / F controller 209 connects to and communicates with an external device via a network, and executes communication control processing on the network. For example, communication using TCP / IP, a telephone line such as ISDN, and communication using a 3G line of a mobile phone are possible.

The CPU 201 enables display on the display 210 by, for example, executing an outline font expansion (rasterization) process in the display information area in the RAM 203. Further, the CPU 201 enables a user instruction with a mouse cursor or the like (not shown) on the display 210.

Next, the table extraction process executed by the information processing apparatus 101 according to the embodiment of the present invention will be described with reference to the flowchart of FIG.

The flowchart of FIG. 3 is a process in which the CPU 201 of the information processing apparatus 101 reads and executes a predetermined control program, and is a flowchart showing a process of extracting a table and a cell from a form image.

In step S301, the input of the form image is accepted, and the instruction to extract the table area from the form image is accepted. The form image is an image scanned by the scanner 102, and may be acquired once stored in the file server 103, or may be acquired directly from the scanner 102.

In step S302, a process for correcting the inclination generated during scanning (skew correction) is executed as a preprocessing for the tablespace extraction process. The skew correction is performed by using a known technique, and as an example, a correction using a Hough transform is known. Specifically, a straight line is detected by the Hough transform, and a horizontal straight line is selected from the detected straight line. Then, the average angle of the straight line in the horizontal direction is acquired, and the correction is performed by rotating the entire image based on the acquired average angle.
In step S303, the characters included in the form image are removed. The process of removing characters will be described with reference to FIG.

FIG. 6 shows a process of removing characters from a form image.

601 of FIG. 6 is an example of a form image acquired in step S301 and subjected to skew correction in step S302.

602 of FIG. 6 shows a form image of 601 that has been binarized, inverted, and then subjected to a morphology operation in the horizontal direction. By performing the Morphology operation, it is possible to remove a line segment that does not reach a certain length or longer. That is, only line segments having a certain length or longer remain, such as ruled lines, and line segments having a length less than a certain length, such as line segments constituting characters, are removed. As a result, characters are removed and only ruled lines are left. It will remain. If the threshold value of the length of the line segment to be removed is set too large, the original ruled line may be removed. Therefore, the threshold value of the length of the line segment to be removed is set to be slightly larger than the character size. It is desirable to keep it.

FIG. 603 of FIG. 6 shows a form image of 601 that has been binarized, inverted, and then subjected to a morphology operation in the vertical direction.

604 of FIG. 6 is the sum of the processed image 602 and the processed image 603. The processing after step S304 is the processing to be executed on the processed image of 604 in FIG.

In step S304, a straight line having horizontal and vertical directions, which is a candidate for a ruled line, is detected from the processed image of 604 in FIG. It should be noted that what is detected here is not a line segment having a fixed start point and end point, but a straight line.

The Hough transform is used to detect a straight line. According to the straight line detection using the Hough transform, if a certain number of pixels or more are present on the same straight line, they are detected as a straight line even if they are not continuous. As a result, it is possible to robustly detect a straight line even when blurring occurs during scanning or when a part of the ruled line is missing in step S303.

For example, when the processes of steps S302 to S304 are executed on the form image shown in 701 of FIG. 7, the result as shown in FIG. 8 is obtained.

FIG. 8 is a diagram in which a straight line is detected by the Hough transform on the processed image in which the characters are removed by the processing in step S303. In the example of FIG. 8, vertical straight lines v8001 to v8007 and horizontal straight lines h8001 to h8007 are detected.

In this embodiment, a grid composed of these vertical straight lines and horizontal straight lines will be described as a ruled line candidate grid 802.

In this embodiment, as described above, a white ruled line is used on a black background, but here, for convenience, a figure in which a black ruled line is used on a white background will be described.

In step S305, the state of the intersection is evaluated for each intersection on the ruled line candidate grid 802 (that is, the intersection of the vertical straight line and the horizontal straight line). Details of the evaluation of the intersection state will be described with reference to FIG.

Although the straight line detection process using the Hough transform is performed in step S304, the straight line detected by the Hough transform is information expressed by two parameters of the angle and the distance from the origin, and is the information of the start point and the end point. It is a straight line with no information. Therefore, although the ruled line candidate grid 802 forms a rectangular grid, in order to determine in which range the actual line segment exists on the ruled line candidate grid, each of the ruled line candidate grids is formed. It is necessary to evaluate the intersection.

FIG. 9 is a diagram for explaining the details of the intersection evaluation.

What is shown by 801 on the left side of FIG. 9 is an enlarged view of FIG. What is shown by 901 on the right side of FIG. 9 is a processed image corresponding to the region shown by the broken line of C901 in 801.

The size of the area of C901 is dynamically determined so as to be cut as large as possible within a range that does not interfere with the intersections of the top, bottom, left and right in the ruled line candidate grid 802. This is because distortion may remain in the image itself even after skew correction, and a positional deviation may occur between the straight line detected by the Hough transform and the actual pixel. Even in such a case, the pixels that are the intersections of the ruled lines should be cut out as large as possible so that they can be captured within the image side.

Next, a fragment of the ruled line is detected from the processed image 901. For the concrete bank, it is assumed that the continuous region of pixels in the processed image 901 having the largest area is a fragment of a ruled line. In the example of 901 in FIG. 9, the “┏” type region 902 is detected as a fragment of a ruled line.

Next, the direction in which the region 902 is in contact with the outer circumference of the processed image 901 is evaluated. In the example of FIG. 9, it touches "bottom" and "right". In another example, when the intersection is T-shaped, it is "left", "right", and "bottom", and when it is cross-shaped, it is "left", "right", "top", and "bottom". If the number of directions in contact with the outer periphery is one or less, it is regarded as noise that is not a ruled line and is excluded from the evaluation targets of the table area and cell extraction described later.

Then, as a result of the intersection evaluation, information such as the center coordinates of the cut rectangular area, the size, and the direction in which the ruled line extends (the direction in which the area is in contact with the outer circumference) is stored for each intersection.

The above is the details of the intersection evaluation process in step S305.

Next, in step S306, the area of the table is specified and extracted from the ruled line candidate grid 802.

The details of the tablespace extraction process in step S306 will be described with reference to the flowcharts of FIGS. 4 and 5.

The process shown in the flowchart of FIG. 4 is a process of sequentially executing the processes of S402 to S409 for the horizontal ruled line candidates (S401). In this embodiment, the horizontal ruled line candidates located at the upper part of the processed image are sequentially processed.

In step S402, the flag indicating the detection status of the left end point is set to No. That is, it is recorded that the left end point is not detected. The left end point means "an intersection corresponding to the upper left corner of the table" and "an intersection corresponding to the lower left corner of the table".

In step S403, the processes of steps S404 to S408 are sequentially executed for the intersections on the horizontal ruled line candidates to be processed. In this embodiment, the intersections on the horizontal ruled line candidates are sequentially processed from left to right.

In step S404, it is determined whether the left end point has been detected.

If it has been detected (S404: YES), the process proceeds to step S408.

If it has not been detected yet (S404: NO), the process proceeds to step S405.

In step S405, it is determined whether the intersection to be processed is the left end point. The determination as to whether or not the point is the left end point is made by using the information related to the "direction in which the ruled line extends" among the contents evaluated in step S305. Specifically, when the "direction in which the ruled line extends" is only two directions, "" right "and" bottom "", it is determined that the left end point is the upper left corner of the table. If the "direction in which the ruled line extends" is only two directions, "" right "and" top "", it is determined that the corner is the lower left corner of the table and is the left end point.

If it is the left end point (S405: YES), the process proceeds to step S406.

If it is not the leftmost point (S405: NO), the process proceeds to step 410, and the process proceeds to the next intersection.

In step S406, the flag indicating the detection status of the left end point is set to YES. That is, it is recorded that the left end point has been detected.

In step S407, the scanning direction of the table is acquired. The scanning direction of the table is a parameter for evaluating by assuming that the table is in the vertical direction from here. For example, in c1001 of FIG. 10, since the ruled lines extend to the right and downward, the scanning direction is downward. Further, in c1101 of FIG. 11, since the ruled lines extend to the right and upward, the scanning direction is upward.

In step S408, it is determined whether the intersection to be processed is the right end point. The determination as to whether or not the point is the right end point is made by using the information related to the "direction in which the ruled line extends" among the contents evaluated in step S305. Specifically, when the "direction in which the ruled line extends" is only two directions, "" left "and" bottom "", it is determined that the right end point is the upper right corner of the table. If the "direction in which the ruled line extends" is only two directions, "" left "and" top "", it is determined that the corner is the lower right corner of the table and is the right end point.

If it is the right end point (S408: YES), the process proceeds to step S409.

If it is not the rightmost point (S408: NO), the process proceeds to step S410, and in step S409, which proceeds to the process for the next intersection, the tablespace is scanned. The details of the process of step S409 will be described with reference to the flowchart of FIG.

The flowchart of FIG. 5 is a process for determining a horizontal ruled line (horizontal ruled line that is the opposite side of the table) that is paired with the horizontal ruled line acquired in the flowchart of FIG. 4, and is a process for determining the horizontal ruled line candidate. Then, the processes of steps S502 to S504 are sequentially executed in the direction of the table scan acquired in step S407 (step S501).

In step S502, it is determined whether the horizontal ruled line candidate to be processed is in contact with another table that has already been determined (whether it is determined as an edge forming another table).

When it interferes with another table (step S502: YES), the process shifts to step S505, and the area scanned so far (the horizontal ruled line acquired in the process of FIG. 4 and the determination of YES in S502). The area formed by the horizontal ruled lines) is determined and stored as a table area.

If it does not interfere with other tables (step S502: NO), the process proceeds to step S503.

In step S503, it is determined whether or not the intersection of the corner points is included in the horizontal ruled line to be processed. The corner points are the intersections that form the four corners of the table, and among the contents evaluated in step S305, the information related to the "direction in which the ruled line extends" is "only" right "and" bottom "" (upper left). Corner point), "Only" left "and" bottom "" (upper right corner point), "Only" right "and" top "(lower left corner point)," Only "left" and "top" (right) It means one of the lower corner points).

When the corner points are included (step S503: YES), the process proceeds to step S505, and the area scanned so far (the horizontal ruled line acquired in the process of FIG. 4 and YES in S503) are determined. The area formed by the horizontal ruled lines) is determined and stored as a table area.

If the corner points are not included (step S503: NO), the process proceeds to step S504.

In the example of FIG. 10, when the corner point c1004 is found, the area 1001 (the area indicated by the dotted line) is determined as the table area. Here, the intersection c1003 is not evaluated as a corner point because the ruled line extends not only to "" left "and" top "" but also to "bottom". In order to recognize such a table, if a corner point is found from either the left or right side, the table should be confirmed at that point. If no corner point is found, the process proceeds to step S504.

In step S504, it is determined whether or not there is an "end point in which the ruled line extends outward" for at least one of the left and right end points included in the horizontal ruled line to be processed.

The "left and right end points included in the horizontal ruled line to be processed" are intersections on the same vertical ruled line as the left end point acquired in the flowchart of FIG. 4 or intersections on the same vertical ruled line as the right end point. , Means the intersection included in the horizontal ruled line to be processed. Further, whether or not the ruled line extends outward is determined based on the "direction in which the ruled line extends" at the end point. Specifically, when the ruled line extends to the left with respect to the left end point, it is determined that the ruled line extends to the outside. Similarly, with respect to the right end point, when the ruled line extends to the right, it is determined that the ruled line extends outward.

When it is determined that there is an "end point where the ruled line extends outward" (step S504: YES), the process is shifted to step S505, and the area scanned so far (horizontal direction acquired by the process of FIG. 4). The area formed by the ruled line and the horizontal ruled line determined to be YES in S504) is determined and stored as a table area.

For example, in the example of FIG. 11, since the ruled line extends from the intersection c1103 toward the outside (left side), the scan of the table is stopped here, and the area 11101 (the area indicated by the dotted line) is determined as the table area.

If it is determined that there is no "end point where the ruled line extends outward" (step S504: NO), it is determined that the ruled line to be processed is not the horizontal ruled line that is the opposite side of the table. Move the processing target to the horizontal ruled line.

If the horizontal ruled lines that are the opposite sides of the table are not found even after executing the processes of S502 to S504 for all the horizontal ruled lines, it is determined that the table area does not exist, and the processing of this flowchart is terminated (). S507). For example, when the right end point and the left end point acquired in the flowchart of FIG. 4 are erroneous detections due to noise, such processing is performed.

In step S506, the flag indicating the detection status of the left end point is set to No, and the process proceeds to step S401 in FIG. Regarding the processing after S402 after the processing of step S506 is executed, only the horizontal ruled line candidates for which the processing of S502 to S504 has not been executed may be the processing target.

By the above processing, the table area can be extracted from the form image for which the table extraction request is received in S301.

In particular, as shown in FIG. 7, for a table in which two rectangles are combined (a table in which a detailed table in which individual items are described and a subtotal table in which the total amount is described are in contact with each other), the detailed table and the subtotal table are also displayed. It can be recognized as a separate table. As a result, it becomes possible to recognize the data included in the table with high accuracy in the recognition process.

Next, the process of step S307 will be described.

Step S307 is a process of extracting the cell area included in the table area extracted in step S306. The details of the cell area extraction process will be described below with reference to the flowchart of FIG.

In the flowchart of FIG. 13, the processes from steps S130 to S1314 are sequentially executed for the horizontal ruled line candidates (in this embodiment, they are sequentially executed from top to bottom) (S1301), and S1304 to S1306. Is sequentially executed for the intersections on the horizontal ruled lines (in this embodiment, it is sequentially executed from left to right).

In step S1302, the flag indicating the detection status of the intersection (left end point) at the upper left of the cell is set to NO. That is, it is in a state indicating that the intersection on the upper left has not been detected yet.

In step S1034, it is determined whether the flag indicating the detection status of the upper left intersection is YES, that is, whether the upper left intersection has been detected.

If it has been detected (step S1304: YES), the process proceeds to step S1308.

If it has not been detected (step S1304: NO), the process proceeds to step S1305.

In step S1305, it is determined whether the intersection to be processed is the left end point (the intersection at the upper left of the cell). Specifically, the determination of whether or not the intersection is at the upper left of the cell is made when the direction of the ruled line extending from the intersection includes "" right "and" bottom "" (if the right and bottom are included, it extends to the left or above. Even if there is a ruled line, it is determined to be the leftmost point), and the intersection is determined to be the intersection at the upper left of the cell. For example, in the example of FIG. 12, it is determined that the intersection c1201 is the left end point.

When it is determined that the intersection to be processed is the left end point (step S1305: YES), the process proceeds to step S1306.

When it is determined that the intersection to be processed is not the left end point (step S1305: NO), the reason is shifted to step S1307, and the processing is shifted to the next intersection (one right intersection).

In step S1306, the flag indicating the detection status of the left end point is set to YES. Then, the process shifts to the next intersection (one right intersection) (S1307). In the example of FIG. 12, the processing target is shifted to the intersection c1202.

In step S1308, it is determined whether the intersection to be processed is the right end point (the intersection at the upper right of the cell). Specifically, the determination of whether or not the intersection is at the upper right of the cell is made when the direction of the ruled line extending from the intersection includes "" left "and" bottom "" (if the left and bottom are included, it extends to the right or above. Even if there is a ruled line, it is determined to be the rightmost point), and the intersection is determined to be the intersection at the upper right of the cell. In the example of FIG. 12, it is determined that the intersection c1202 is the right end point.

When it is determined that the intersection to be processed is the right end point (step S1308: YES), the process proceeds to step S1309, and the processes of S131 to S1311 are sequentially executed for the horizontal ruled line candidates.

When it is determined that the intersection to be processed is not the right end point (step S1308: NO), the process is shifted to step S1307, and the process is shifted to the next intersection (one right intersection). Step S1308: YES If it is determined, the processing of steps S131 to S1311 is executed for the horizontal ruled line candidate located one below the horizontal ruled line candidate to be processed. The horizontal ruled line candidates here are the intersection on the same vertical ruled line as the left end point detected in S1305 and the same vertical ruled line as the right end point detected in S1308 among the straight lines that are horizontal ruled lines. Indicates a line segment specified by the intersection of.

In step S1310, it is determined whether the horizontal ruled line candidate to be processed is shared with other confirmed cells.

If it is determined that they are shared (step S1310: YES), the process proceeds to step S1313.

If it is determined that the data is not shared (step S1310: NO), the process proceeds to step S1311.

In step S1311, it is determined whether or not the inward ruled line extends from the left and right end points of the horizontal ruled line candidate to be processed. The inward-facing ruled line is a ruled line that extends to the right if it is the left end point, and is a ruled line that extends to the left if it is the right end point. It is sufficient that the ruled lines extending inward are included, and even if the ruled lines extending in other directions are included, this process is determined to be YES. For example, in the example of FIG. 12, since there is a ruled line extending to the right at the intersection c1204 which is the left end point and a ruled line extending to the left at the intersection 1203 which is the right end point, YES is determined in step S1311.

When it is determined that the inward ruled line extends from the left and right end points (step S1311: YES), the process proceeds to step S1313.

When it is determined that the inward ruled line does not extend from the left and right end points (step S1311: NO), the process proceeds to step S1312, and the process proceeds to the next (one lower) horizontal ruled line candidate. ..

In step S1313, it is formed by a line segment formed by the left end point detected in S1305 and the right end point detected in S1308, and a line segment determined to be YES in S1310 or a line segment determined to be YES in S1311. The cell to be used is fixed as a cell area.

Then, in step S1314, the detection flag at the left end point is set to NO, and the process is returned to S1303.
The above is the process of detecting the cell area.
In this embodiment, when the table area and the cell area are detected and specified, the horizontal (horizontal) ruled lines are used as a reference, but the processing is executed based on the vertical (vertical) ruled lines. Is also good.

The present invention can be implemented as, for example, a system, an apparatus, a method, a program, a recording medium, or the like. Specifically, it may be applied to a system composed of a plurality of devices, or may be applied to a device composed of one device.

Further, the program in the present invention is a program in which a computer can execute the processing methods of the flowcharts shown in FIGS. 3 to 5, and the storage medium of the present invention uses the processing methods of FIGS. 3 to 5 and 13. A program that can be executed by a computer is stored. The program in the present invention may be a program for each processing method of each device of FIGS. 3 to 5 and 13.

As described above, a recording medium on which a program that realizes the functions of the above-described embodiment is recorded is supplied to the system or device, and the computer (or CPU or MPU) of the system or device stores the program in the recording medium. Needless to say, the object of the present invention can be achieved by reading and executing.

In this case, the program itself read from the recording medium realizes the novel function of the present invention, and the recording medium on which the program is recorded constitutes the present invention.

Recording media for supplying programs include, for example, flexible disks, hard disks, optical disks, magneto-optical disks, CD-ROMs, CD-Rs, DVD-ROMs, magnetic tapes, non-volatile memory cards, ROMs, EEPROMs, and silicon. A disk or the like can be used.

Further, by executing the program read by the computer, not only the function of the above-described embodiment is realized, but also the OS (operating system) or the like running on the computer is actually operated based on the instruction of the program. Needless to say, there are cases where a part or all of the processing is performed and the processing realizes the functions of the above-described embodiment.

Further, after the program read from the recording medium is written in the memory provided in the function expansion board inserted in the computer or the function expansion unit connected to the computer, the function expansion board is based on the instruction of the program code. It goes without saying that there is a case where the CPU or the like provided in the function expansion unit performs a part or all of the actual processing, and the function of the above-described embodiment is realized by the processing.

Further, the present invention may be applied to a system composed of a plurality of devices or a device composed of one device. It goes without saying that the present invention can also be applied when it is achieved by supplying a program to a system or an apparatus. In this case, by reading the recording medium in which the program for achieving the present invention is stored into the system or the device, the system or the device can enjoy the effect of the present invention.

Further, by downloading and reading a program for achieving the present invention from a server, database, or the like on the network by a communication program, the system or device can enjoy the effect of the present invention. It should be noted that all the configurations in which each of the above-described embodiments and modifications thereof are combined are also included in the present invention.

101 Information processing device 102 Scanner 103 File server

Claims (9)

An acquisition method for acquiring an image including a table, and
A detection means for detecting a straight line that is a candidate for a ruled line in a table from the acquired image,
For each intersection of the detected ruled lines, a ruled line direction specifying means for specifying a direction in which the ruled line extends from the intersection, and a ruled line direction specifying means.
A table area specifying means for specifying a table area included in the image by using the direction in which the ruled line specified by the specifying means extends.
An information processing device characterized by being equipped with. The first aspect of claim 1, wherein the tablespace specifying means specifies a tablespace based on intersections forming four corners of a table, which are detected based on a direction in which a ruled line specified by the ruled line direction specifying means extends. The information processing device described. Among the intersections, the corner point specifying means for specifying the intersections forming the upper left and upper right corners of the table based on the direction in which the ruled line specified by the ruled line direction specifying means extends.
The opposite side specifying means for specifying the opposite side of the side formed from the corner points specified by the corner point specifying means, and the opposite side specifying means.
With
The tablespace specifying means is characterized in that a region including a side formed from a corner point specified by the corner point specifying means and a opposite side specified by the opposite side specifying means is specified as a table area. Item 2. The information processing apparatus according to item 1 or 2. Among the intersections, the corner point specifying means for specifying the intersections forming the lower left and lower right corners of the table based on the direction in which the ruled line specified by the ruled line direction specifying means extends.
The opposite side specifying means for specifying the opposite side of the side formed from the corner points specified by the corner point specifying means, and the opposite side specifying means.
With
The tablespace specifying means is characterized in that a region including a side formed from a corner point specified by the corner point specifying means and a opposite side specified by the opposite side specifying means is specified as a table area. Item 2. The information processing apparatus according to item 1 or 2. The opposite side specifying means is a side parallel to the side formed from the corner points specified by the corner point specifying means, and is characterized in that the side including the intersection forming the four corners of the table is specified as the opposite side. The information processing apparatus according to claim 3 or 4. The opposite side specifying means specifies a side parallel to the side formed from the corner points specified by the corner point specifying means and including an intersection having a ruled line extending outward as the opposite side. The information processing apparatus according to any one of claims 3 to 5, wherein the information processing apparatus is characterized. Any one of claims 1 to 6, further comprising a specific means for specifying a cell in the tablespace based on a direction in which a ruled line of an intersection included in the tablespace specified by the tablespace specifying means extends. The information processing device described in the section. The acquisition process of acquiring the image including the table by the acquisition means of the information processing device,
A detection step in which the detection means of the information processing device detects a straight line as a candidate for a ruled line in a table from the acquired image.
The ruled line direction specifying means of the information processing apparatus has a ruled line direction specifying step of specifying a direction in which a ruled line extends from the intersection of each of the detected ruled lines.
A tablespace specifying step in which the tablespace specifying means of the information processing apparatus specifies a table area included in the image by using the direction in which the ruled line specified by the specifying step extends.
An information processing method characterized by being provided with. Computer,
An acquisition method for acquiring an image including a table, and
A detection means for detecting a straight line that is a candidate for a ruled line in a table from the acquired image,
For each intersection of the detected ruled lines, a ruled line direction specifying means for specifying a direction in which the ruled line extends from the intersection, and a ruled line direction specifying means.
A program for functioning as a table area specifying means for specifying a table area included in the image by using the direction in which the ruled line specified by the specific means extends.

Images