JP2021168088A - Information processing apparatus and information processing program - Google Patents

Abstract

To provide an information processing apparatus and an information processing program for accurately recognizing ruled lines even when the ruled lines cannot be recognized on an image directly.SOLUTION: A ruled line recognition unit 20 executes processing to acquire an image of ruled lines partially hidden by Go (board game) stones arranged on a Go board 16 having the ruled lines, and to recognize the ruled lines including the portion hidden by the Go stones on an image by using an imaginary line passing through a center area of a Go stone defined in advance and ruled lines recognized from the image.SELECTED DRAWING: Figure 3

Description

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

Non-Patent Document 1 proposes a technique of recognizing the outer frame of a shogi board and recognizing squares by using the Canny method and the Hough transform.

Teppei Kurita, Makoto Miwa, Takashi Chikayama, "Automatic Phase Recognition Method Using Image Information for Shogi", IPSJ Symposium Proceedings (IPSJ Workshop Proceedings), Japan, November 9, 2007 , 207, p. 172-179

As an example, when acquiring an image during a game and recording a game record, it is necessary to recognize the ruled line, but if the ruled line is hidden by an object (for example, a stone or a piece) superimposed on the ruled line, , The ruled line may not be recognized accurately. Therefore, an object of the present invention is to provide an information processing apparatus and an information processing program capable of accurately recognizing a ruled line even in a situation where the ruled line cannot be directly recognized on an image.

In order to achieve the above object, the information processing apparatus according to the first aspect includes a processor, in which the second object is arranged on the first object having a ruled line, and the second object is used. An image in which at least a part of the ruled line is hidden is acquired, and the second object is displayed on the image by using a virtual line passing through a predetermined center range of the second object and a ruled line recognized from the image. The process of recognizing the ruled line including the portion hidden by the object is performed.

The information processing device according to the second aspect is the information processing device according to the first aspect, wherein the virtual line exists within a predetermined threshold distance with respect to a predetermined center range of the second object. It is a line connecting the central ranges of another second object.

The information processing device according to the third aspect is the information processing device according to the first aspect or the second aspect, and the processor detects the outermost ruled line by using the virtual line and the ruled line recognized from the image. , The outermost ruled line and the predetermined number of ruled lines of the first object are used to recognize the ruled line of the first object.

The information processing device according to the fourth aspect is the information processing device according to the first aspect or the second aspect, and the processor detects the outermost ruled line by using the virtual line and the ruled line recognized from the image. , The ruled line of the first object is recognized by detecting the intersections existing at equal intervals in the outermost ruled line.

The information processing apparatus according to the fifth aspect is the information processing apparatus according to the third aspect or the fourth aspect. When there is a deviation, the virtual line and the ruled line recognized from the image are used to recognize the ruled line including the portion hidden by the second object on the image, and the outermost ruled line is recognized. If the positions of the four corners do not deviate from the positions of the outermost ruled lines detected in the past, the ruled lines recognized in the past are applied.

The information processing device according to the sixth aspect is the information processing device according to any one of the first to fifth aspects, in which the processor has the second object arranged on the ruled line and at least one of the ruled lines. Acquires an image including a part where the part is hidden.

The information processing device according to the seventh aspect is the information processing device according to any one of the first to fifth aspects, and the processor has a ruled line on the image in which the second object is arranged between the ruled lines. Acquires an image containing at least a part of the hidden part.

The information processing device according to the eighth aspect is the information processing device according to any one of the first to seventh aspects, and the processor is an image in which the image is an image of the first object viewed from an arbitrary depression angle. In the case of, the process of correcting the image viewed from directly above is further performed.

The information processing program according to the ninth aspect acquires an image in which a second object is arranged on a first object having a ruled line on a computer and at least a part of the ruled line is hidden by the second object. Using a virtual line passing through a predetermined center range of the second object and a ruled line recognized from the image, the ruled line including a portion hidden by the second object on the image is drawn. Execute the recognition process.

According to the first aspect, there is an effect that it is possible to provide an information processing device capable of accurately recognizing a ruled line even in a situation where the ruled line cannot be directly recognized on an image.

According to the second aspect, it is possible to detect a ruled line hidden by the second object as a virtual line.

According to the third aspect, it is possible to recognize the outermost ruled line and other ruled lines in the outermost ruled line.

According to the fourth aspect, it is possible to recognize the outermost ruled line and other ruled lines in the outermost ruled line.

According to the fifth aspect, for each image, the imaginary line and the ruled line recognized from the image are used to recognize the ruled line including the portion hidden by the second object on the image. Compared with the case, the processing load for recognizing the ruled line can be reduced.

According to the sixth aspect, even when the second object is arranged on the ruled line and the ruled line is hidden, the ruled line can be recognized.

According to the seventh aspect, even when the second object is arranged between the ruled lines and the ruled lines are hidden on the image, the ruled lines can be recognized.

According to the eighth aspect, even an image of the first target portion taken from an arbitrary depression angle can be converted into an image viewed from directly above.

According to the ninth aspect, there is an effect that it is possible to provide an information processing program capable of accurately recognizing a ruled line even in a situation where the ruled line cannot be directly recognized on an image.

It is a figure which shows the schematic structure of the ruled line recognition apparatus which concerns on this embodiment. It is a block diagram which shows the main part structure of the electric system of the information processing apparatus in the ruled line recognition apparatus which concerns on this embodiment. It is a functional block diagram which shows the functional structure of the information processing apparatus which concerns on this embodiment. It is a figure which shows the conventional method of specifying a ruled line / intersection by specifying the outermost ruled line by using the binarization method or the like. It is a figure which shows an example of the straight line detection, the outermost ruled line detection, and the ruled line detection of a go board. It is a figure which shows an example of the ruled line recognition method of a go board photographed from an oblique direction. It is a figure which shows an example of the detection of a virtual line. It is a flowchart which shows an example of the flow of the process which recognizes the ruled line of a go board at the time of generating a game record in the information processing apparatus which concerns on this embodiment. It is a flowchart which shows the modification of the flow of the process which recognizes the ruled line of a go board at the time of generating a game record in the information processing apparatus which concerns on this embodiment. It is a figure for demonstrating an example which applies the technique of specifying a geometric progression line or a geometric progression line to a form recognition technique.

Hereinafter, an example of the embodiment of the present invention will be described in detail with reference to the drawings. FIG. 1 is a diagram showing a schematic configuration of a ruled line recognition device according to the present embodiment.

As an example, the ruled line recognition device 10 according to the present embodiment will explain an example of recognizing the ruled line of the go board 16 as the first object and generating a game record.

In the ruled line recognition device 10, the information processing device 14 acquires an image taken by the photographing unit 12 that shoots the go board 16, and the information processing device 14 performs a process of recognizing the ruled line of the go board 16 from the image. Although the information processing device 14 is shown as a notebook-type personal computer in FIG. 1, the information processing device 14 is not limited to this, and for example, a mobile terminal such as a smartphone equipped with a camera may be applied. Further, the camera of the smartphone may be applied to the photographing unit 12.

Subsequently, the configuration of a main part of the electrical system of the information processing device 14 according to the present embodiment will be described. FIG. 2 is a block diagram showing a main configuration of an electrical system of the information processing device 14 in the ruled line recognition device 10 according to the present embodiment.

As shown in FIG. 2, the information processing device 14 according to the present embodiment has a CPU (Central Processing Unit) 14A, a ROM (Read Only Memory) 14B, a RAM (Random Access Memory) 14C, and an HDD (hard disk drive) 14D. , A keyboard 14E, a display 14F, and a communication line I / F (interface) unit 14G. The CPU 14A controls the overall operation of the information processing device 14. Various control programs, various parameters, and the like are stored in advance in the ROM 14B. The RAM 14C is used as a work area or the like when executing various programs by the CPU 14A. The HDD 14D stores various data, application programs, and the like. The keyboard 14E is used to input various information. The display 14F is used to display various kinds of information. The communication line I / F unit 14G is connectable to a communication line such as a network, and transmits / receives various data to / from other devices connected to the communication line. Each part of the above information processing apparatus 14 is electrically connected to each other by the system bus 14H. In the information processing apparatus 14 according to the present embodiment, the HDD 14D is applied as a storage unit, but the present invention is not limited to this, and another non-volatile storage unit such as a flash memory may be applied.

With the above configuration, the information processing apparatus 14 according to the present embodiment uses the CPU 14A to access the ROM 14B, the RAM 14C, and the HDD 14D, acquire various data via the keyboard 14E, and display various information on the display 14F. .. Further, the information processing device 14 executes control of transmission / reception of communication data via the communication line I / F unit 14G by the CPU 14A.

Here, the functional configuration realized by the CPU 14A of the information processing apparatus 14 executing the program stored in the ROM 14B will be described. FIG. 3 is a functional block diagram showing a functional configuration of the information processing apparatus 14 according to the present embodiment.

The information processing device 14 has the functions of an image acquisition unit 18, a ruled line recognition unit 20, and a drawing display processing unit 36.

The image acquisition unit 18 acquires an image obtained by photographing the go board 16 having the ruled line by the photographing unit 12 from the photographing unit 12.

The ruled line recognition unit 20 performs a process of recognizing the ruled line of the go board 16 from the image acquired by the image acquisition unit 18. Depending on the background, the contrast between the board and the background is clear, and the ruled line / intersection can be specified by specifying the outermost ruled line by the conventional method as shown in FIG. 4 using a binarization method or the like. .. However, as shown in the problem of FIG. 4, when the contrast between the board and the background is unclear due to the color of the background on which the board is placed, the outermost ruled line cannot be specified by the conventional method. As a result, it becomes impossible to identify the ruled lines and intersections. Therefore, in the present embodiment, the ruled line recognition unit 20 displays an image including a portion in which a go stone 17 as a second object is arranged on a go board 16 having a ruled line and at least a part of the ruled line is hidden by the go stone 17. Using the virtual line that passes through the predetermined central range of the go stone 17 and the ruled line recognized from the image, a process of recognizing the ruled line including the portion hidden by the go stone 17 on the image is performed. Further, when there is one second object (that is, one go stone), it is not necessary to detect a virtual line passing through a predetermined center range of the first object, and there are two second objects. In the case of the above (that is, two or more go stones), the virtual line may be detected. The ruled line recognition unit 20 may also perform a process of detecting the go stone 17 from the image acquired by the image acquisition unit 18.

As shown in FIG. 3, the ruled line recognition unit 20 functions as a straight line detection unit 22, an outermost ruled line detection unit 24, a keystone correction unit 28, a circular extraction unit 30, a virtual line detection unit 32, and a go board ruled line determination unit 34. Have.

The straight line detection unit 22 detects all straight lines included in the image acquired by the image acquisition unit 18. For example, using the Canny method and the Hough transform, all straight lines in the image are detected as shown in the upper part of FIG. That is, all the straight lines in the image are detected by performing the process of extracting the contour portion of the image using the Canny method and performing the process of detecting the straight lines by the Hough transform. Note that FIG. 5 shows an image taken from directly above the board 16.

The outermost ruled line detecting unit 24 detects the outermost ruled line among the ruled lines of the go board 16 from the detection result of the straight line detecting unit 22. For example, as shown in the middle part of FIG. 5, the outermost ruled line of the detected ruled line is detected. Specifically, since the straight line detection unit 22 recognizes various lines other than the ruled lines of the go board 16, it scans in the X-axis and Y-axis directions in order to identify the ruled lines from among them. Then, the intersections of the scanning lines and the detected lines are found, and the number of consecutive intersections is n at equal intervals (since the interval is a planting calculation method, n = the size of the input go board 16 and 7 at 7 roadbeds). ) If it exists, the line connecting the outermost intersections among the intersections arranged at equal intervals is specified as the outermost ruled line. Here, in the case of an image of the Go board taken from directly above, it is sufficient to specify whether or not there are n consecutive intersections at equal intervals, but when the Go board is taken from an arbitrary depression angle, there is a geometric progression. Using a sequence, it is specified whether or not there are n consecutive intersections at intervals that satisfy the conditions (see FIG. 6). The X-axis and the Y-axis are axes in the directions along the grid-shaped ruled lines of the board 16.

As shown in FIG. 1, the trapezoidal correction unit 28 performs keystone correction to correct the image taken from directly above because the board 16 is trapezoidal when the image is taken from diagonally above. In the present embodiment, by performing the keystone correction, the keystone of the grid 16 of the board 16 is corrected to a square shape. When the photographing unit 12 is photographing from directly above, the keystone correction unit 28 is omitted. Further, the keystone correction may be omitted.

The circular extraction unit 30 determines whether or not there is a circular object in the image acquired by the image acquisition unit 18, and if there is a circular object, performs circular extraction to detect the go stone 17. For example, in the Hough transform, a circle is extracted by scanning while changing the radius of the circle.

The virtual line detection unit 32 specifies the center coordinates as an example of the predetermined center range of the circular object extracted by the circular extraction unit 30, and the center coordinates of another circular object existing within the predetermined threshold distance. A virtual line is detected by connecting each other with a virtual line. In the present embodiment, if there is another circular object immediately next to the center of the circular object in the XY axis direction, the logic is used to connect the centers with a virtual line. More specifically, if an XY-axis line passing through the center of one go stone 17 is created on the image and it is determined that it has passed through the area of another circular object, the centers of the go stones 17 are virtualized. Perform the process of connecting with a line. For example, as shown by the dotted line in FIG. 7, a virtual line is detected.

The board ruled line determining unit 34 determines how many roadbeds the board 16 is, and determines the ruled lines of the squares in the outermost ruled line detected by the outermost ruled line detecting unit 24. For example, the user may be asked to input the number of ruled lines in advance in order to specify how many roads the board 16 is. Alternatively, the size may be automatically detected from the image and the number of ruled lines may be determined without having the user input the size of the board 16. Alternatively, a predetermined number of ruled lines may be determined for each application or service. As an example of the method of determining the ruled line of the go board 16, the outermost ruled line detection unit 24 detects the straight line detected by the straight line detection unit 22 and the virtual line detected by the virtual line detection unit 32. The ruled line of the grid may be determined by scanning the image in the XY axis direction in the ruled line and detecting the intersections existing at equal intervals or equal ratio intervals. When detecting the intersections existing at equal intervals, the intersections at intervals corresponding to the number of ruled lines input in advance by the user may be detected. Alternatively, as shown in the lower part of FIG. 5, each ruled line of the go board 16 is determined by equally dividing the inside of the outermost ruled line detected by the outermost ruled line detecting unit 24 by the number of ruled lines input in advance by the user. May be good. The latter example will be described below. When a circular object is extracted by the circular extraction unit 30, the outermost ruled line detection unit 24 uses the virtual line detected by the virtual line detection unit 32 and the straight line detected by the straight line detection unit 22. The outer ruled line is detected, and the go board ruled line determination unit 34 determines the ruled line of the go board 16. When the ruled line is specified, the area can be divided into equal parts based on the size of the board (for example, in the case of a 9-road board, it is divided into 9 equal parts based on the specified outermost ruled line), and the coordinates of the intersection can be specified (Fig.). 6-4, 5, 6).

Further, after determining the ruled line and specifying the intersection coordinates, a process of recognizing the color of the go stone is performed, and the drawing display processing unit 36 sets the image of the go board 16 and the go stone 17 obtained from the ruled line recognition result of the ruled line recognition unit 20. Is drawn and displayed on the display 14F.

Subsequently, a specific process performed by the information processing apparatus 14 according to the present embodiment configured as described above will be described. FIG. 8 is a flowchart showing an example of a flow of processing for recognizing the ruled lines of the go board 16 when generating a game record in the information processing device 14 according to the present embodiment. The process of FIG. 8 omits the process of detecting the go stone 17, and shows it as a process of extracting only the portion that recognizes the ruled line.

In step 100, the CPU 14A acquires an image of the board 16 and proceeds to step 102. That is, the image acquisition unit 18 acquires an image obtained by photographing the go board 16 having a ruled line from the photographing unit 12.

In step 102, the CPU 14A detects a straight line from the acquired image and proceeds to step 104. That is, the straight line detection unit 22 detects all the straight lines included in the acquired image. For example, by performing a process of extracting the contour portion of the image using the Canny method and performing a process of detecting straight lines by the Hough transform, all the straight lines in the image are detected as shown in the upper part of FIG. ..

In step 104, the CPU 14A detects a circular region from the acquired image and proceeds to step 106. That is, the circular extraction unit 30 determines whether or not there is a circular object in the image acquired by the image acquisition unit 18, and if there is a circular object, performs circular extraction to detect the go stone 17. For example, in the Hough transform, a circle is extracted by scanning while changing the radius of the circle.

In step 106, the CPU 14A determines whether or not there is a circular region. The determination determines whether or not the circular region has been extracted by the circular extraction unit 30, and if the determination is denied, the process proceeds to step 108, and if the determination is affirmative, the process proceeds to step 110.

In step 108, the CPU 14A detects the outermost ruled line that serves as the frame of the board 16 from the detected straight line, and proceeds to step 114. That is, as shown in the middle part of FIG. 5, the outermost ruled line detecting unit 24 detects the outermost ruled line among the ruled lines of the board 16 from the detection result of the straight line detecting unit 22.

On the other hand, in step 110, the CPU 14A detects the virtual line and proceeds to step 112. That is, the virtual line detection unit 32 specifies the center coordinates of the circular region extracted by the circular extraction unit 30, and within a predetermined threshold distance (for example, from the extracted circular region, up, down, left, and right in the rule line direction). By connecting the center coordinates of another circular object existing (within a predetermined distance in the direction of) with a virtual line, a virtual line as shown by the dotted line in FIG. 7 is detected.

In step 112, the CPU 14A detects the outermost ruled line using the detected straight line and virtual line, and proceeds to step 114. That is, the outermost ruled line detecting unit 24 detects the outermost ruled line among the ruled lines of the go board 16 by using the straight line detected by the straight line detecting unit 22 and the virtual line detected by the virtual line detecting unit 32. ..

In step 114, the CPU 14A performs keystone correction on the image in which the ruled line is detected, and proceeds to step 116. That is, as shown in FIG. 1, when the trapezoidal correction unit 28 is photographed from diagonally above, the keystone 16 is trapezoidal, so that the keystone correction is performed so that the image is captured from directly above. conduct. If the photographing unit 12 is photographing from directly above, the step 114 is omitted.

In step 116, the CPU 14A determines the ruled line of the board 16 and proceeds to step 118. That is, the Go board ruled line determination unit 34 determines each ruled line of the Go board 16 as shown in the lower part of FIG. 5 by equally dividing the inside of the outermost ruled line by the number of ruled lines input in advance by the user.

In step 118, the CPU 14A displays the drawing on the board and proceeds to step 120. That is, the drawing display processing unit 36 identifies the intersection coordinates from the ruled line recognition result of the ruled line recognition unit 20, draws the recognition result of the color of the go stone existing at the position of the intersection, and displays it on the display 14F. .. The image of the board 16 including the ruled lines may be displayed.

In step 120, the CPU 14A determines whether or not to end the process of recognizing the ruled line. The determination determines, for example, whether or not the operation instructing the end by the user is performed by the keyboard 14E or the like. If the determination is denied, the process returns to step 100 and the above-mentioned processing is repeated, and when the determination is affirmed, a series of processing is terminated.

Subsequently, a modified example of the processing performed by the information processing apparatus 14 according to the present embodiment will be described. FIG. 9 is a flowchart showing a modified example of the flow of processing for recognizing the ruled lines of the go board 16 when generating a game record in the information processing device 14 according to the present embodiment. The same processing as in FIG. 8 will be described with the same reference numerals.

In step 100, the CPU 14A acquires an image of the board 16 and proceeds to step 102. That is, the image acquisition unit 18 acquires an image obtained by photographing the go board 16 having a ruled line from the photographing unit 12.

In step 102, the CPU 14A detects a straight line from the acquired image and proceeds to step 103. That is, the straight line detection unit 22 detects all the straight lines included in the acquired image. For example, by performing a process of extracting the contour portion of the image using the Canny method and performing a process of detecting straight lines by the Hough transform, all the straight lines in the image are detected as shown in the upper part of FIG. ..

In step 103, the CPU 14A detects the outermost ruled line that serves as the frame of the board 16 from the detected straight line, and proceeds to step 105. That is, as shown in the middle part of FIG. 5, the outermost ruled line detecting unit 24 detects the outermost ruled line among the ruled lines of the board 16 from the detection result of the straight line detecting unit 22.

In step 105, the CPU 14A determines whether or not the four corner positions of the outermost ruled line have been detected. In this determination, step 117, which will be described later, has already been performed to determine whether or not the four corner positions are stored. If the determination is affirmed, the process proceeds to step 107, and if the determination is negative, the process proceeds to step 114.

In step 107, the CPU 14A determines whether or not the positions of the four corners of the outermost ruled line have moved. The determination determines whether or not the four-cornered position has moved with respect to the four-cornered position stored in step 117 described later. If the determination is affirmed, it is determined that the outermost ruled line may be hidden by the go stone 17 and may not be detected, and the process proceeds to step 109. If the determination is denied, the process proceeds to step 111. ..

In step 109, the CPU 14A detects a circular region from the acquired image and proceeds to step 110. That is, the circular extraction unit 30 determines whether or not there is a circular object in the image acquired by the image acquisition unit 18, and if there is a circular object, performs circular extraction to detect the go stone 17. For example, in the Hough transform, a circle is extracted by scanning while changing the radius of the circle.

In step 110, the CPU 14A detects the virtual line and proceeds to step 112. That is, the virtual line detection unit 32 specifies the center coordinates of the circular region extracted by the circular extraction unit 30, and connects the center coordinates of another circular object existing within a predetermined threshold distance with a virtual line. As a result, a virtual line as shown by the dotted line in FIG. 7 is detected.

In step 112, the CPU 14A detects the outermost ruled line using the detected straight line and virtual line, and proceeds to step 114. That is, the outermost ruled line detecting unit 24 detects the outermost ruled line among the ruled lines of the go board 16 by using the straight line detected by the straight line detecting unit 22 and the virtual line detected by the virtual line detecting unit 32. ..

In step 114, the CPU 14A performs keystone correction on the image in which the ruled line is detected, and proceeds to step 116. That is, as shown in FIG. 1, when the trapezoidal correction unit 28 is photographed from diagonally above, the keystone 16 is trapezoidal, so that the keystone correction is performed so that the image is captured from directly above. conduct. If the photographing unit 12 is photographing from directly above, the step 114 is omitted.

In step 116, the CPU 14A determines the ruled line of the board 16 and proceeds to step 117. That is, the Go board ruled line determination unit 34 determines each ruled line of the Go board 16 as shown in the lower part of FIG. 5 by equally dividing the inside of the outermost ruled line by the number of ruled lines input in advance by the user.

In step 117, the CPU 14A updates the positions of the four corners of the outermost ruled line and proceeds to step 118.

In step 118, the CPU 14A displays the drawing on the board and proceeds to step 120. That is, the drawing display processing unit 36 specifies the intersection coordinates from the ruled line recognition result of the ruled line recognition unit 20, and displays the recognition result of the go stones existing on the intersection. It should be noted that the process of drawing the image of the board 16 including the ruled lines and displaying it on the display 14F may be performed.

In step 120, the CPU 14A determines whether or not to end the process of recognizing the ruled line. The determination determines, for example, whether or not the operation instructing the end by the user is performed by the keyboard 14E or the like. If the determination is denied, the process returns to step 100 and the above-mentioned processing is repeated, and when the determination is affirmed, a series of processing is terminated.

On the other hand, in step 111, the CPU 14A applies the previously determined ruled line and proceeds to step 118, draws an image of the board 16 including the previously determined ruled line, and proceeds to step 120.

As described above, in the modified example, the processing load for recognizing the ruled line is reduced by storing the positions of the four corners of the outermost ruled line and using it for determining the ruled line of the go board 16.

In the above embodiment, an example of recognizing the ruled line of the go board 16 in which the go stone 17 is arranged on the ruled line has been described as an example, but the recognition of the ruled line is not limited to the go board 16. For example, with an image including a part where pieces and stones are arranged between ruled lines such as shogi where pieces are arranged between ruled lines and reversi where stones are arranged between ruled lines and at least a part of the ruled lines is hidden on the image. It may be applied to a form that recognizes the ruled lines of other board games, and is not limited to board games, but hidden lines and marks from images in which an object exists on some line or mark. A form that can recognize (for example, a traffic sign or line on the road hidden under the vehicle, taken from above with a plurality of vehicles of the second object lined up on the road, which is the first object. It may be applied to the technique for identifying the above.

Further, in the above embodiment, an example has been described in which the outermost ruled line is detected, keystone correction is performed, and then the processing is performed in the order in which the ruled line of the go board 16 is determined, but the processing order is not limited to this. For example, the outermost ruled line may be determined, the ruled line of the board 16 may be determined, and then the keystone correction may be performed at the end.

Further, the method described in the present embodiment for scanning the image of the go board 16 in the X-axis and Y-axis directions and specifying the lines at equal intervals or equal ratio intervals is not limited to the go board 16, and is shown in FIG. It may be applied to the technique of recognizing a form as described above. Specifically, since the number of ruled lines in the XY direction and the ratio between ruled lines are determined for each type of form, the type of form may be determined by the ratio of the distance between the ruled lines. For example, even if the form is read from an arbitrary depression angle with a smartphone, etc., or the characters are difficult to recognize, the ruled line can be specified by scanning the form in the X-axis and Y-axis directions. , The type of form is specified by specifying the ratio of the distances between the specified ruled lines. For example, as shown in FIG. 10, when an image of a form taken from diagonally above is scanned in the X-axis direction, six vertical ruled line intervals are specified, and the ratio of the intervals is 1: 4: 7: 2. : It is assumed that it is 6. Based on the information, it is collated with the form type database, and it is specified that the form is a birth certificate.

Further, in the above embodiment, the CPU has been described as an example of a processor, but the processor refers to a processor in a broad sense, and is a general-purpose processor (for example, CPU) or a dedicated processor (for example, GPU: Graphics Processing Unit, etc.). ASIC: Application Specific Integrated Circuit, FPGA: Field Programmable Gate Array, programmable logic device, etc.).

Further, the operation of the processor in the above embodiment may be performed not only by one processor but also by a plurality of processors existing at physically separated positions in cooperation with each other. Further, the order of each operation of the processor is not limited to the order described in each of the above embodiments, and may be changed as appropriate.

Further, the process performed by the information processing apparatus 14 according to the above embodiment may be a process performed by software, a process performed by hardware, or a combination of both. Further, the processing performed by the information processing apparatus 14 may be stored as a program in a storage medium and distributed.

Further, the present invention is not limited to the above, and it goes without saying that the present invention can be variously modified and implemented within a range not deviating from the gist thereof.

10 Ruled line recognition device 12 Imaging unit 14 Information processing device 14A CPU
16 Go board 17 Go stone

Claims (9)

A processor is provided, and the processor is
An image in which a second object is arranged on a first object having a ruled line and at least a part of the ruled line is hidden by the second object is acquired.
Using a virtual line passing through a predetermined center range of the second object and a ruled line recognized from the image, the ruled line is recognized including a portion hidden by the second object on the image. An information processing device that performs processing. The virtual line is a line connecting the central ranges of another second object that exist within a predetermined threshold distance with respect to the predetermined center range of the second object. The information processing apparatus according to 1. The processor detects the outermost ruled line by using the virtual line and the ruled line recognized from the image, and uses the outermost ruled line and a predetermined number of ruled lines of the first object. The information processing device according to claim 1 or 2, which recognizes the ruled lines of the first object. The processor detects the outermost ruled line using the virtual line and the ruled line recognized from the image, and detects intersections existing at equal intervals in the outermost ruled line to detect the first object. The information processing device according to claim 1 or 2, which recognizes a ruled line. The processor
When the positions of the four corners of the outermost ruled line deviate from the positions of the outermost ruled line detected in the past, the virtual line and the ruled line recognized from the image are used to make the first ruled line on the image. 2 Recognize the ruled line including the part hidden by the object,
The information processing apparatus according to claim 3 or 4, wherein when the positions of the four corners of the outermost ruled line do not deviate from the positions of the outermost ruled line detected in the past, the ruled line recognized in the past is applied. The information processing device according to any one of claims 1 to 5, wherein the processor acquires an image including a portion in which the second object is arranged on a ruled line and at least a part of the ruled line is hidden. The information processing according to any one of claims 1 to 5, wherein the processor acquires an image including a portion in which the second object is arranged between the ruled lines and at least a part of the ruled lines is hidden on the image. Device. The information according to any one of claims 1 to 7, wherein when the image is an image of the first object viewed from an arbitrary depression angle, the processor further performs a process of correcting the image to be viewed from directly above. Processing equipment. On the computer
An image in which a second object is arranged on a first object having a ruled line and at least a part of the ruled line is hidden by the second object is acquired.
Using a virtual line passing through a predetermined center range of the second object and a ruled line recognized from the image, the ruled line is recognized including a portion hidden by the second object on the image. An information processing program for executing the processing to be performed.

Images