JP2017092947A - Learning support program, learning support device, learning tool formation notebook, and learning tool formation method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To efficiency perform processing for forming a learning tool with an image which is written to a notebook and is imaged.SOLUTION: A learning support program images a notebook having a configuration such that a first surface of a first column having one or more rows and a second surface of a second column having a plurality of rows are adjacent at a spread mode, forms a learning tool, and allows a computer to be operated. The program allows the computer to execute an acquisition of an image including a plurality of reference marks at one or more corners on the first surface at four corners of a virtual rectangle shape formed by the first and second surfaces at the spread mode of the notebook and at one or more corners on the second surface, identification of the plurality of reference marks in the image, calculation of a coordinate indicating each of the plurality of reference marks, division of the image into one or more first regions on the first surface side corresponding to the first column having the one or more rows and a plurality of second regions on the second surface side corresponding to the second column having the plurality of rows on the basis of the coordinate of the reference marks, and storing of learning card information to a storage part alternately corresponding to image information of the one or more first regions and the image information of the plurality of second regions.SELECTED DRAWING: Figure 4

Description

  The present disclosure relates to a learning support program, a learning support device, a learning tool generation book, and a learning tool generation method.

Conventionally, memorization cards, flash cards, and the like have been created by various methods for the purpose of enhancing learning effects.
For example, in Patent Document 1, a paper on which a question and an answer are written (question / answer writing paper) is taken into a computer by a scanner, an image of the memorized card is edited on the computer, and the memorized card is printed out. A method of making paper is disclosed. Patent Document 1 also describes that memorized card information that is created using a computer can be used for learning by displaying the memorized card information on a computer screen without outputting it to a paper medium. .

Japanese Patent Laying-Open No. 2015-27782

  However, Patent Document 1 does not specifically disclose a procedure for generating memorized card information from an image captured by a scanner. For this reason, with the method described in Patent Document 1, it is difficult to efficiently generate memorized card information.

  In view of the above-described circumstances, at least some embodiments of the present invention provide a learning support program, a learning support device, and a learning support program that can efficiently perform processing for generating a learning tool from an image obtained by capturing the content written on a book. An object is to provide a learning tool generation book and a learning tool generation method.

(1) A learning support program according to at least some embodiments of the present invention includes:
A learning tool is generated from an image obtained by capturing an image of a book configured such that a first sheet having one or more first columns and a second sheet having a plurality of columns of second columns are adjacent to each other when facing apart. A learning support program for operating a computer
Of the four corners of the virtual rectangle formed by the first paper surface and the second paper surface when the page is spread, one or more corners on the first paper surface and one or more corners on the second paper surface Obtaining the image including a plurality of fiducial marks located;
Identifying the plurality of reference marks in the image and calculating coordinates indicating the position of each of the plurality of reference marks;
Based on the coordinates of each of the fiducial marks, the image is placed in one or more first regions on the first paper surface side corresponding to the one or more first columns, and in the second column of the plurality of rows. A plurality of second regions on the second paper surface side corresponding to each of the second regions;
A procedure in which the image information of the one or more first areas and the image information of the plurality of second areas are associated with each other and stored as learning card information in a storage unit;
Is configured to cause the computer to execute.

According to the configuration of (1) above, by causing the computer to execute the above-described procedure, it is possible to easily generate learning card information including a pair of the first column and the second column of the book. Further, since the image of the book is divided based on the positions of the plurality of reference marks, the correspondence between the first column and the second column on the book is not disturbed without being affected by the imaging conditions of the book. The book image can be divided. Moreover, in the configuration of (1) above, of the four corners of the virtual rectangle formed by the first paper surface and the second paper surface when the book is spread, one or more corners on the first paper surface and 1 on the second paper surface. Reference marks are located at the above corners. For this reason, a plurality of fiducial marks are arranged so as to straddle the first paper surface and the second paper surface of the book surface, while maintaining the correspondence between the first column and the second column on the book surface with high accuracy. Images can be divided.
Therefore, it is not necessary to impose strict restrictions on the imaging conditions of the book, and the learning tool can be generated efficiently. In addition, since there is no need to impose strict restrictions on the imaging conditions of the notebook, there is a prerequisite knowledge using a simple camera (for example, a camera with a built-in smartphone) without using special equipment such as a jig for fixing the camera. Since learning tools can be generated from images taken by ordinary people who do not, the range of users can be expanded.

(2) In some embodiments, in the configuration of (1) above,
The learning support program includes:
Calculate the number of corners within the specified angle range of the figure (candidate figure) in the image,
A procedure for identifying the graphic as the reference mark based on success or failure of at least one identification condition including that the calculated number of corners of the graphic matches the number of corners of the reference mark. Further configured to be executed.

The “specified angle range” in the present specification may be arbitrarily set within a range of 80 degrees or more and 100 degrees or less, or may be set within a range of 85 degrees or more and 95 degrees or less. In the exemplary embodiment, the “specified angle range” is based on the angle of the reference mark corner (for example, 90 degrees) as a reference for reasons of accuracy in forming the reference mark on the book surface (for example, the reference mark printing accuracy). Possible errors (or errors and margins), and distortions of the reference mark image that may occur within the assumed range of the imaging conditions of the book (for example, a shift in the angle of the corner of the reference mark image caused by the tilt of the camera with respect to the book) (For example, ± 10 degrees, preferably ± 5 degrees).
In one embodiment, there are a plurality of “specified angle ranges”. In this case, the number of corners is calculated separately for each specified angle range, and one of the identification conditions is that the number of corners of each specified angle range matches between the candidate graphic and the reference mark. The identification process may be performed.

According to the configuration of (2) above, the entire shape of the figure in the image (the figure that may be the reference mark) is not focused on the similarity to the shape of the reference mark, but the angle of the figure in the image Since the reference mark is identified based on the number of parts, the calculation time required for the identification process of the reference mark can be shortened.
In addition, even if a figure confusing with the reference mark exists on the first sheet or the second sheet, if the figure is drawn by hand, the number of corners included in the specified angle range may happen. It is unlikely to match the number of corners. For this reason, it is possible to reduce the possibility of erroneously recognizing a handwritten figure (including characters and brackets) as a reference mark. Therefore, it is possible to divide the book image while maintaining the correspondence between the first column and the second column on the book with high accuracy.

(3) In some embodiments, in the configuration of (2) above,
The reference mark includes an outer reference contour and an inner reference contour located inside the outer reference contour;
The at least one identification condition is:
The number of corners within the specified angle range of the outer contour of the figure matches the number of corners of the outer reference contour; and
The number of corners within the specified angle range of the inner contour of the figure includes matching the number of corners of the inner reference contour.

  According to the configuration of (3) above, the outer contour and the inner contour of the graphic existing in the image have corner portions within the specified angle range equal to the corner portions of the outer reference contour and the inner reference contour of the reference mark, respectively. By identifying the reference mark based on whether or not it has, it is possible to further reduce the possibility of erroneously recognizing a handwritten figure as a reference mark while suppressing an increase in calculation load.

(4) In some embodiments, in the configuration of (3) above,
The reference mark is a polygon in which the outer reference contour is rectangular and the inner reference contour has eight or more right-angled corners.

  According to the configuration of (4) above, by adopting a simple reference mark that combines a rectangular outer reference contour and a polygonal inner reference contour having eight or more right-angled corners, It is possible to reduce the possibility of erroneously recognizing a handwritten figure as a reference mark while improving the reference mark identification processing speed by paying attention to the number of right-angled corners.

(5) In some embodiments, in any one of the above configurations (1) to (4),
The learning support program includes:
Calculate the area surrounded by the contour of the figure in the image,
A procedure for identifying the figure as the reference mark based on the success or failure of at least one identification condition including the calculated size of the area or the ratio of the area occupied in the image being within a specified range. The computer is further configured to execute.

  According to the configuration of (5) above, by identifying the reference mark based on the size of the area surrounded by the outline of the graphic existing in the image or the ratio of the area in the image, the reference mark can be identified. The possibility of erroneously recognizing a handwritten figure as a reference mark can be reduced while improving the identification processing speed of the reference mark using the corners.

(6) In some embodiments, in any one of the above configurations (1) to (5),
The learning support program includes:
Identify the coordinates of a plurality of corners within a specified angle range in the contour of the figure in the image,
Based on the success or failure of at least one identification condition including whether or not the shape obtained by connecting the coordinates of the corners within each specified angle range matches the shape of the reference mark, The computer is further configured to further execute a procedure for identifying as a mark.

  According to the configuration of (6) above, the reference mark is based on whether or not the shape obtained by connecting the coordinates of a plurality of corners within the specified angle range of the graphic existing in the image matches that of the reference mark. Thus, the possibility of erroneously recognizing a handwritten figure as a reference mark can be reduced while improving the reference mark identification processing speed by using the corner portion within the specified angle range.

(7) In some embodiments, in any one of the configurations (1) to (6) above,
The reference mark is provided at each of the four corners of the virtual rectangle,
The learning support program is:
When all the four reference marks cannot be detected in the image, the computer is further configured to execute a procedure for generating a mark recognition error signal.

According to the configuration of (7) above, the mark recognition error signal when the four reference marks provided at the four corners of the virtual rectangle formed by the first paper surface and the second paper surface cannot be detected when the page is spread. Therefore, it is possible to avoid a situation where learning card information with low accuracy is generated while a handwritten figure in the image is mistaken as a reference mark.
Note that the mark recognition error signal may be displayed on the user interface and allow the user to confirm whether or not to continue the learning card information generation process.

(8) In some embodiments, in any one of the above configurations (1) to (7),
The learning program is configured to further cause the computer to execute a procedure for correcting the image based on the coordinates of each of the reference marks.

According to the configuration of (8) above, since the image is corrected based on the coordinates of the reference mark, the correspondence between the first column and the second column on the page is not affected by the imaging conditions of the page. Can be divided while maintaining high accuracy. Therefore, it is not necessary to impose strict restrictions on the imaging conditions of the book, and the learning tool can be generated efficiently.
Note that the image correction processing includes, for example, a trapezoid correction processing for correcting the image to be rectangular when the image is a trapezoid, and an inclination correction processing for correcting the inclination when the image is tilted. .

(9) In some embodiments, in any one of the above configurations (1) to (8),
The learning support program includes:
Displaying at least one image information of the first region as question content;
Displaying at least one image information of the second region corresponding to each of the at least one first region as a response content;
Is further configured to cause the computer to execute.

  According to the configuration of (9) above, the image information of the first area in the generated learning card information is displayed as the question contents, and the image information of the second area corresponding to the first area is displayed as the answer contents. Therefore, the learning effect can be improved by effectively using the learning tool.

(10) In some embodiments, in any one of the above configurations (1) to (9),
Calculating a first area surrounded by an outer contour of the figure in the image and a second area surrounded by an inner contour located inside the outer contour;
Causing the computer to further execute a procedure for identifying the graphic as the reference mark based on success or failure of at least one identification condition including that the calculated ratio between the first area and the second area is within a specified range. Configured as follows.

  According to the configuration of the above (10), the reference mark is identified based on the ratio of the first area surrounded by the outer contour of the graphic existing in the image and the second area surrounded by the inner contour. The possibility of erroneously recognizing a handwritten figure as a reference mark can be reduced while improving the reference mark identification processing speed by using the corner portion within the angle range.

(11) In some embodiments, in any one of the above configurations (1) to (10),
The learning support program includes:
A procedure for specifying which one of the reference marks in the image among a plurality of types of reference marks respectively corresponding to a plurality of division conditions of the image;
Dividing the image into the first area and the second area according to the division condition corresponding to the identified reference mark;
Is further configured to cause the computer to execute.

The correspondence between the first column and the second column varies depending on the needs of the learner. For example, when there are a plurality of answer items for the question described in the first column, if the plurality of answer items are entered separately in a plurality of second columns, the listability as a learning card is improved. In addition, when the amount of information of each question item and the corresponding answer item is small, it is desirable that the number of divisions of the first region and the second region is large in order to generate more learning card information from one book. It is. Conversely, when the amount of information of each question item and the corresponding answer item is large, the smaller the number of divisions of the first region and the second region, the better the usability.
In this regard, according to the configuration of (11) above, the image division condition can be set for each type of reference mark, so the correspondence between the first column and the second column is changed according to the needs of the learner. be able to.

(12) A learning support apparatus according to at least some embodiments of the present invention includes:
By the learning support program having the configuration of any of (1) to (11) above,
Of the four corners of the virtual rectangle formed by the first paper surface and the second paper surface when the page is spread, one or more corners on the first paper surface and one or more corners on the second paper surface Obtaining the image including a plurality of fiducial marks located;
Identifying the plurality of reference marks in the image and calculating coordinates indicating the position of each of the plurality of reference marks;
Based on the coordinates of each of the fiducial marks, the image is placed in one or more first regions on the first paper surface side corresponding to the one or more first columns, and in the second column of the plurality of rows. A plurality of second regions on the second paper surface side corresponding to each of the second regions;
A procedure in which the image information of the one or more first areas and the image information of the plurality of second areas are associated with each other and stored as learning card information in a storage unit;
The computer is configured to be executable.

(13) A learning tool generation book according to at least some embodiments of the present invention includes:
A first page having a first column of one or more rows;
A second page having a plurality of rows of second columns;
A learning tool generation book comprising:
When the learning tool generation book is spread, the first paper surface and the second paper surface are adjacent to each other, and the first paper surface among the four corners of the virtual rectangle formed by the first paper surface and the second paper surface. A plurality of fiducial marks located at one or more corners on the top and one or more corners on the second paper surface;
The learning support program having the configuration of any of (1) to (11) above is provided.
A procedure for acquiring an image of the learning tool generation book including the plurality of reference marks;
Identifying the plurality of reference marks in the image and calculating coordinates indicating the position of each of the plurality of reference marks;
Based on the coordinates of each of the fiducial marks, the image is placed in one or more first regions on the first paper surface side corresponding to the one or more first columns, and in the second column of the plurality of rows. A plurality of second regions on the second paper surface side corresponding to each of the second regions;
A procedure in which the image information of the one or more first areas and the image information of the plurality of second areas are associated with each other and stored as learning card information in a storage unit;
Is configured to generate a learning tool by causing a computer to execute.

  According to the configuration of (11) or (12) above, as described above with respect to (1) above, it is possible to easily generate learning card information consisting of a pair of the first column and second column of the book, Therefore, it is not necessary to impose strict restrictions on the imaging conditions, and learning tools can be generated efficiently.

(14) A learning tool generation method according to at least some embodiments of the present invention includes:
Learning that generates a learning tool from an image of a book that is configured such that a first page having one or more columns of the first column and a second page having a plurality of columns of the second column are adjacent to each other when facing apart. A tool generation method,
Of the four corners of the virtual rectangle formed by the first paper surface and the second paper surface when the page is spread, one or more corners on the first paper surface and one or more corners on the second paper surface Capturing the image including a plurality of fiducial marks located;
Identifying the plurality of reference marks in the image and calculating coordinates indicating the position of each of the plurality of reference marks;
Based on the coordinates of each of the fiducial marks, the image is placed in one or more first regions on the first paper surface side corresponding to the one or more first columns, and in the second column of the plurality of rows. Dividing into a plurality of second regions on the second paper surface side corresponding respectively;
Storing the image information of the one or more first areas and the image information of the plurality of second areas as learning card information in association with each other;
Is provided.

  According to the method of (14), it is possible to easily generate learning card information composed of a pair of the first column and the second column of the book. Further, since the image of the book is divided based on the positions of the plurality of reference marks, the correspondence between the first column and the second column on the book is not disturbed without being affected by the imaging conditions of the book. The book image can be divided. Moreover, in the method of (14), the correspondence between the first column and the second column on the page is based on the coordinates of a plurality of reference marks arranged so as to straddle the first page and the second page of the page. Can be divided while maintaining high accuracy. Therefore, it is not necessary to impose strict restrictions on the imaging conditions of the book, and the learning tool can be generated efficiently.

  According to at least some embodiments of the present invention, it is possible to easily generate learning card information consisting of pairs of the first and second fields of a book and to impose strict restrictions on the imaging conditions of the book. And learning tools can be generated efficiently.

It is a block diagram which shows the structure of the learning assistance apparatus which concerns on one Embodiment. It is a figure which shows the structural example of the book for learning tool production | generation. 3A to 3J are diagrams showing examples of the configuration of the reference marks. It is a flowchart which shows the procedure of the image processing by a processor. FIGS. 5A to 5F are diagrams schematically illustrating the states of the image processing by the processor. FIG. 6A is a diagram illustrating a configuration example of a learning tool generation book according to an embodiment, and FIG. 6B is a diagram illustrating a reference mark used for the book of FIG. 6A. FIG. 7A is a diagram illustrating a configuration example of a learning tool generation book according to an embodiment, and FIG. 7B is a diagram illustrating a reference mark used for the book of FIG. 7A. FIG. 8 is a diagram illustrating a configuration example of a learning tool generation book according to an embodiment. FIG. 9 is a flowchart showing a procedure for properly using a plurality of image division conditions using a plurality of types of reference marks.

  Hereinafter, some embodiments of the present invention will be described with reference to the accompanying drawings. However, the dimensions, materials, shapes, relative arrangements, etc. of the components described in the embodiments or shown in the drawings are not intended to limit the scope of the present invention, but are merely illustrative examples. Absent.

FIG. 1 is a block diagram illustrating a configuration of a learning support apparatus according to an embodiment.
As shown in FIG. 1, in some embodiments, the learning support device 1 includes a computer 10 that executes various procedures for generating learning card information used for a learning tool by a learning support program. The computer 10 may be a mobile terminal such as a smartphone or a tablet.

  In some embodiments, the computer 10 includes a processor 12, a camera 14, a memory 16, a display 18, and an input unit 20.

The processor 12 is configured to read the learning support program from the memory 16 and execute a procedure described later with reference to FIG. That is, the processor 12 acquires the image data captured by the camera 14 from the memory 16 according to the learning support program, processes it, and generates learning card information. The processor 12 also has a function of controlling various devices including the camera 14, the display 18, and the input unit 20. The display 18 and the input unit 20 constitute a graphical user interface (GUI), and are used for exchanging information between the user of the learning support apparatus 1 and the computer 10.
In the exemplary embodiment shown in FIG. 1, the camera 14 is built in the computer 10. However, in other embodiments, the camera is provided outside the computer 10. In this case, the image data acquired by the camera may be taken into the memory 16 of the computer 10 via an I / O interface or a network line.

FIG. 2 is a diagram illustrating a configuration example of a book (a learning tool generation book) that is an object to be imaged by the camera 14.
As shown in FIG. 2, the form (learning tool generation form) 100 includes a first sheet 110 having a first column 112 having one or more columns and a second sheet 120 having a second column 122 having a plurality of columns. Prepare.
In the exemplary embodiment shown in FIG. 2, a plurality of columns of the first column 112 are provided in correspondence with the plurality of columns of the second column 122 (the number of columns in the first column 112 and the second column 122). The number of columns in the match.) In the example shown in FIG. 2, the first column 112 and the second column 122 are provided in 12 columns, respectively, but the number of columns in the first column 112 and the second column 122 can be arbitrarily set.

Further, the paper 100 is bound by the binding unit 102, and when the paper 100 is closed, the first paper surface 110 and the second paper surface 120 face each other, and as shown in FIG. The first paper surface 110 and the second paper surface 120 are configured to be adjacent to each other. The binding unit 102 may have a configuration of yarn binding that binds a plurality of sheets with a thread, a configuration of wireless binding that fixes a plurality of sheets with glue alone, or a configuration of ring binding that binds sheets with a ring. In the exemplary embodiment shown in FIG. 2, the binding portion 102 has a plurality of holes 104 formed in each of the first paper surface 110 and the second paper surface 120, and has a ring-binding configuration in which a ring is passed through the hole 104. Have.
If the binding portion 102 of the ring binding method is configured so that the first paper surface 110 and the second paper surface 120 are adjacent to each other when the book surface 100 is spread, the paper surface on which the contents of the question are described by folding the book surface 100 with the binding portion 102. A paper surface (the other of the first paper surface 110 or the second paper surface 120) on which the contents of the answer are written is located on the back side of the first paper surface 110 or the second paper surface 120, and the notebook 100 itself is memorized as a note. It can also be used.

  As shown in FIG. 2, in some embodiments, the book surface 100 is located on the first paper surface 110 among the four corners of the virtual rectangle 140 formed by the first paper surface 110 and the second paper surface 120 when the book surface 100 is spread. And a plurality of reference marks 130 located at one or more corners on the second paper surface 120. In the exemplary embodiment shown in FIG. 2, four reference marks 130 are provided at the four corners of the virtual rectangle 140, respectively.

Here, the shape of the reference mark 130 will be described with reference to FIG. 3A to 3J are diagrams showing examples of the configuration of the reference mark 130, respectively.
As shown in FIGS. 3A to 3J, in some embodiments, the reference mark 130 has a plurality of corners 132 (132a, 132b). 3A to 3J show an example in which the angle of each corner 132 is 90 degrees.

In some embodiments, each fiducial mark 130 includes an outer reference contour 134 and an inner reference contour 136 located inside the outer reference contour 134. The outer reference contour 134 and the inner reference contour 136 each form a polygon closed by a plurality of broken lines.
The inner reference contour 136 may be an (8 + 2n) square having (8 + 2n) (where n is an integer equal to or greater than 0) right-angled corners 132b. In the exemplary embodiment shown in FIGS. 3 (a)-(j), the outer reference contour 134 is a rectangle with four right angle corners 132a and the inner reference contour 136 is eight right angle corners 132b. Is an octagon.

In the exemplary embodiment shown in FIGS. 3 (a) to 3 (d), the reference mark 130 includes a square outer reference contour 134 and a T-shaped inner reference contour 136 located inside the outer reference contour 134. And having. As shown in FIGS. 3A to 3D, the direction of the T-shape of the inner reference contour 136 is not particularly limited.
In the exemplary embodiment shown in FIGS. 3 (e) to 3 (h), the reference mark 130 includes a square outer reference contour 134 and a U-shaped inner reference contour located inside the outer reference contour 134. 136. As shown in FIGS. 3A to 3D, the direction of the U-shape of the inner reference contour 136 is not particularly limited.
In the exemplary embodiment shown in FIGS. 3 (i) and 3 (j), the fiducial mark 130 includes a square outer reference contour 134 and a Z-shaped inner reference contour 136 located inside the outer reference contour 134. And having. As shown in FIGS. 3 (i) and 3 (j), the Z-shaped orientation of the inner reference contour 136 is not particularly limited.

  As shown in FIGS. 3A to 3J, the region 135 surrounded by the outer reference contour 134 and the inner reference contour 136 may be a solid (solid) region of one or more colors. Good. On the other hand, the region 137 surrounded by the inner reference contour 136 may be a region where no ink exists, as shown in FIGS. 3 (a) to 3 (j).

  Next, an image processing procedure by the processor 12 based on the learning support program will be described with reference to FIGS. 4 and 5.

FIG. 4 is a flowchart showing a procedure of image processing by the processor 12. FIGS. 5A to 5F are diagrams schematically showing the state of each stage of image processing by the processor 12.
5A to 5F illustrate a case where it is determined whether or not the candidate graphic 200 in the image is the reference mark 130 shown in FIG.

  As shown in FIG. 4, the processor 12 reads the image data in the spread state of the book surface 100 from the memory 16 (step S2). The image data of the book surface 100 may be captured by the camera 14 of the computer 10. Note that, as an imaging condition of the book surface 100, a restriction that the reference mark 130 on the book surface 100 is within a predetermined area may be imposed. In this case, it is preferable to set a sufficiently wide area in which the reference mark 130 should be stored so that the imaging condition is not excessively limited.

Subsequently, a region to be subjected to image processing is cut out from the image data of the book 100 (step S4).
At this time, an area including all of the figures appearing at the four corners of the virtual rectangle 140 formed by the first paper surface 110 and the second paper surface 120 (a graphic that may be the reference mark 130) is cut out from the image data. This region (target image region) is the target of image processing. For example, the range of the target image region to be cut out from the image data may be set so as to include the region set as the imaging condition (the region where the reference mark 130 should fit).

Next, an image of a graphic (graphic that may be the reference mark 130) included in the target image region or an image including the graphic is cut out to obtain an image including the candidate graphic 200 of the reference mark 130 (step S6). Here, the image clipping range from the target image area may be set based on an instruction input via the input unit 20, or when the area is set as an imaging condition, You may set to the range which includes at least one part of the said area | region. Then, each of the images of the candidate graphic 200 obtained in step S6 is converted into a gray scale, and further binarized (step S8).
FIG. 5A shows a state in which the candidate graphic 200 is converted into a gray scale, and FIG. 5B shows a state in which the candidate graphic 200 is binarized after being converted into a gray scale.
In the exemplary embodiment shown in FIG. 4, in step S <b> 6, an image including the candidate graphic 200 is cut out from the target image area, and this is set as a target for subsequent image processing. However, in another embodiment, the image cropping process in step S6 may not be performed, and the process after step S8 may be performed with the entire target image area set in step 2 as “an image including the candidate graphic 200”.

Subsequently, the contour of the binarized candidate graphic 200 is extracted, and this contour is approximated to a straight line (step S10). In this way, the linear outlines 234 and 236 of the candidate graphic 200 are obtained. If the contours 234 and 236 are linearly approximated in this way, the corner portion 232 can be specified with high accuracy without being affected by noise.
FIG. 5C shows a state where the contour of the binarized candidate graphic 200 is approximated by a straight line. In the exemplary embodiment shown in the figure, an outer contour 234 and an inner contour 236 of the candidate graphic 200 are shown.

Next, the number of corners 232 (232a, 232b) in the contours 234, 236 that are linearly approximated in the candidate graphic 200 is calculated. In addition, the corner | angular part 232 can be specified as a location where each edge | side of the outlines 234 and 236 cross | intersects within a regulation angle range among the outlines 234 and 236. Here, the “specified angle range” refers to the accuracy of forming the reference mark 130 on the book surface 100 (for example, the printing accuracy of the reference mark 130) with the angle of the corner portion 132 (for example, 90 degrees) of the reference mark 130 as a reference. It is a range (for example, ± 10 degrees, preferably ± 5 degrees) in consideration of an error (or an error and a margin) that may occur for a reason. The “specified angle range” may be arbitrarily set within a range of 80 degrees to 100 degrees, for example, and may be set within a range of 85 degrees to 95 degrees.
5D shows a state where the four corners 232a in the outer contour 234 of the candidate graphic 200 are specified, and FIG. 5E shows the eight corners 236 in the inner contour 236 of the candidate graphic 200. The state which specified the corner | angular part 232b is shown.

Then, the success or failure of the first identification condition is determined as to whether the number of corners 232 (232a, 232b) in the contours 234, 236 matches the number of corners 132 (132a, 132b) of the reference mark 130 (step). S12).
In the example shown in FIG. 5D, the number of corner portions 232a (= 4) of the outer contour 234 of the candidate graphic 200 is equal to the corner of the outer reference contour 134 of the reference mark 130 shown in FIG. This matches the number of parts 132a (= 4). In the example shown in FIG. 5E, the number (= 8) of corners 232b of the inner contour 236 of the candidate graphic 200 is equal to the corner of the inner reference contour 136 of the reference mark 130 shown in FIG. This matches the number of parts 132b (= 8). Therefore, in the example shown in FIG. 5D and FIG. 5E, the candidate graphic 200 satisfies the first identification condition.

Subsequently, the size of the area S (S1, S2) surrounded by the contours 234, 236 of the candidate graphic 200 is calculated, and the size of the area S (S1, S2) or the target image cut out in step S4 Whether the ratio of the area S (S1, S2) occupying the entire region falls within the specified range is determined (step S14).
5D shows the area S1 surrounded by the outer contour 234 of the candidate graphic 200, and FIG. 5E shows the area S2 surrounded by the inner contour 236 of the candidate graphic 200. Yes.

Further, the coordinates of the corners 232 (232a, 232b) of the contours 234, 236 of the candidate graphic 200 are calculated, and the third is to determine whether the shape connecting the coordinates matches the shapes of the contours 134, 136 of the reference mark 130. The success or failure of the identification condition is determined (step S16).
Specifically, it is determined whether or not the shape connecting the corners 232a of the outer contour 234 of the candidate graphic 200 is the same shape (for example, a rectangle or a square) as the outer reference contour 134 of the reference mark 130. Also, whether or not the shape connecting the corners 232b of the inner contour 236 of the candidate graphic 200 is the same shape as the inner reference contour 136 of the reference mark 130 (for example, a shape having eight right-angled corners). judge.

Then, only when the first identification condition, the second identification condition, and the third identification condition are all satisfied (that is, when YES is determined in steps S12, S14, and S16), the candidate graphic 200 is used as a reference. It is identified as a mark 130 (step S17). Further, the coordinates of the corners 232 (232 a and 232 b) of the contours 234 and 236 of the candidate graphic 200 identified as the reference mark 130 are stored in the memory 16.
Thereafter, in step S18, it is determined whether or not all the reference marks 130 (for example, four) have been detected. If all the reference marks 130 have been detected (YES determination at step S18), the process of identifying the reference marks 130 is finished, and the process proceeds to the subsequent step S24.

  On the other hand, when any of the first identification condition, the second identification condition, and the third identification condition is not satisfied (that is, when any of Step S12, Step S14, or Step S16 is NO), the candidate graphic 200 Is determined not to be the reference mark 130, and the process proceeds to step S20.

In other embodiments, in addition to the above-described first to third identification conditions, as a fourth identification condition, the first area S ₁ surrounded by the outer contour 234 of the candidate graphic 200 and the candidate graphic 200 It may also be determined whether the ratio with the second area S ₂ surrounded by the inner contour 236 is within a specified range (for example, 0.1 ≦ S ₂ / S ₁ ≦ 1).
The success or failure of only one or more of the first identification condition, the second identification condition, the third identification condition, or the fourth identification condition without using all of the first to fourth identification conditions described above. Based on the above, it may be determined whether or not the candidate graphic 200 is the reference mark 130.

In step S20, it is determined whether there are other candidate graphics 200 remaining. If another candidate graphic 200 remains (YES determination in step S20), the mark identification steps in steps S12 to S16 are performed for the new candidate graphic 200.
On the other hand, if no other candidate graphic 200 remains (NO determination at step S20), the processor 12 generates an identification error signal for the reference mark 130 (step S22). The identification error signal may be sent to the display 18 to display a warning on the display 18 informing that the identification of the reference mark 130 has failed. Then, the user may be prompted to give an instruction via the input unit 20 as to whether or not to continue the learning card information generation process.

After all the reference marks 130 are detected normally, in step S24, the image (that is, the image in the target image area set in step S4) is corrected based on the coordinates of each reference mark 130.
Specifically, the coordinates of the corners 232 (232a, 232b) of the contours 234, 236 of the candidate graphic 200 (reference mark 130) stored in step S17 are read from the memory 16 to indicate the position of the reference mark 130. Representative coordinates (for example, the coordinates of the center point of the reference mark 130) are calculated. Then, based on the representative coordinates of each fiducial mark 130, the image in the target image area is corrected.
Note that the image correction processing includes, for example, a trapezoid correction processing for correcting the image to be rectangular when the image is a trapezoid, and an inclination correction processing for correcting the inclination when the image is tilted. .

Thereafter, in step S26, the image in the target image area is divided according to the number of columns in the first column 112 and the second column 122 based on the representative coordinates of each reference mark 130 (step S26). Specifically, one or more first regions 212 on the first paper surface 110 side corresponding to one or more first columns 112 of the book surface 100 and a second paper surface 120 corresponding to each of the second columns 122 of a plurality of rows. The image in the target image area is divided into a plurality of second areas 222 on the side. At this time, the first region 212 and the second region 222 are not included so that the binding portion 102 between the first paper surface 110 and the second paper surface 120 and the hole 104 formed in the first paper surface 110 and the second paper surface 120 are not included. May be set.
In the exemplary embodiment shown in FIG. 5F, a state in which an image is divided into a total of 12 columns of first regions 212 and a total of 12 columns of second regions 222 is shown.

In step S28, the image information of one or more first areas 212 and the image information of the plurality of second areas 222 are associated with each other and stored in the memory 16 as learning card information. Note that the “learning card information” here may be information including a pair of image information of the first area 212 and image information of the second area 222 in the same column as the first area 212.
In the case of the example shown in FIG. 5F, since 12 pairs of image information of the first area 212 and image information of the second area 222 are formed, 12 types of learning card information are generated in step S28. .

  According to the embodiment shown in FIG. 4, the learning card information including the pair of the first column 112 and the second column 122 of the book 100 can be easily obtained by causing the computer 10 to execute the above-described procedure (steps S <b> 2 to S <b> 28). Can be generated. Further, since the image of the book surface 100 is divided based on the positions of the plurality of reference marks 130, the first column 112 and the second column 122 on the book surface 100 are not affected by the imaging conditions of the book surface 100. It is possible to divide the image of the book face 100 without breaking the corresponding relationship. Moreover, among the four corners of the virtual rectangle 140 formed by the first paper surface 110 and the second paper surface 120 when the book surface 100 is spread, one or more corners on the first paper surface 110 and one or more corners on the second paper surface 120. Reference marks 130 are located at the corners. Therefore, the plurality of reference marks 130 are arranged so as to straddle the first paper surface 110 and the second paper surface 120 of the book surface 100, and the correspondence relationship between the first column 112 and the second column 122 on the book surface 100 is determined. The image of the book surface 100 can be divided while maintaining high accuracy. Therefore, it is not necessary to impose strict restrictions on the imaging conditions of the book surface 100, and the learning tool can be generated efficiently.

Further, since the reference mark 130 is identified based on the number of corners 232 (232a, 232b) of the graphic 200 in the image, the calculation time required for the identification process of the reference mark 130 can be shortened.
Moreover, even if the figure 200 confusing with the reference mark 130 exists on the first paper surface 110 or the second paper surface 120, the corner portion 232 included in the specified angle range if the graphic 200 is handwritten. It is unlikely that the number of coincides with the number of corners 132 of the reference mark 130. For this reason, the possibility of erroneously recognizing the handwritten figure 200 as the reference mark 130 can be reduced. Therefore, the image of the book 100 can be divided while maintaining the correspondence between the first column 112 and the second column 122 on the book 100 with high accuracy.

  In addition, the outer contour 234 and the inner contour 236 of the graphic 200 existing in the image are within the same specified angle range as the outer reference contour 134 of the reference mark 130 and the corner 132 (132a, 132b) of the inner reference contour 136, respectively. By identifying the reference mark 130 based on whether or not it has the corner portion 232 (232a, 232b), the possibility of erroneously recognizing the handwritten figure 200 as the reference mark 130 can be further reduced.

  In addition, by adopting a simple reference mark 130 that combines a rectangular outer reference contour 134 and a polygonal inner reference contour 136 having eight or more right-angled corners 132b, Focusing on the number of right-angled corners 232 (232a, 232b) to improve the identification processing speed of the reference mark 130, it is possible to reduce the possibility of erroneously recognizing the handwritten figure 200 as the reference mark 130.

  Further, the reference mark 130 is identified based on the size of the area S (S1, S2) surrounded by the outlines 234, 236 of the graphic 200 existing in the image or the ratio of the area S (S1, S2) in the image. As a result, the recognition processing speed of the reference mark 130 is improved by focusing on the corners 232 (232a, 232b) within the specified angle range, and the possibility that the handwritten figure 200 is erroneously recognized as the reference mark 130 is reduced. can do.

  Further, the reference mark is determined based on whether or not the shape obtained by connecting the coordinates of a plurality of corners 232 (232a, 232b) within the specified angle range of the graphic 200 existing in the image matches that of the reference mark 130. By identifying 130, it is possible to erroneously recognize the handwritten figure 200 as the reference mark 130 while improving the identification processing speed of the reference mark 130 by focusing on the corners 232 (232a, 232b) within the specified angle range. Can be reduced.

  Further, a mark recognition error signal is generated when the four reference marks 130 provided at the four corners of the virtual rectangle 140 formed by the first paper surface 110 and the second paper surface 120 cannot be detected when the book surface 100 is spread. Since it did in this way, the situation which produces | generates low-precision learning card information can be avoided, misrecognizing the handwritten figure 200 in an image as the reference | standard mark 130. FIG.

  Furthermore, since the image is corrected based on the coordinates of the reference mark 130, the correspondence between the first column 112 and the second column 122 on the book surface 100 is highly accurate without being affected by the imaging conditions of the book surface 100. It is possible to divide the image of the book 100 while maintaining the above. Therefore, it is not necessary to impose strict restrictions on the imaging conditions of the book surface 100, and the learning tool can be generated efficiently.

  The learning card information obtained by the above-described procedure is read from the memory 16 by the processor 12 and used as a learning tool. That is, the processor 12 displays the image information of the first area 212 on the display 18 as the question content, and responds to the operation signal via the input unit 20 and displays the image information of the second area 222 as the answer content. May be displayed. Thereby, the learning effect can be improved.

The processor 12 may store the correct answer rate for each learning card information in the memory 16. In this case, the processor 12 may display the learning card information with a low correct answer rate on the display 18 in preference to the learning card information with a high correct answer rate. Alternatively, the processor 12 may randomly read the learning card information stored in the memory 16 and display it on the display 18.
As described above, the learning effect can be further improved by appropriately selecting the learning card information displayed on the display 18 by the processor 12.

  The present invention is not limited to the above-described embodiments, and includes forms obtained by modifying the above-described embodiments and forms obtained by appropriately combining these forms.

  For example, in the above-described embodiment, it is mainly assumed that the learner generates learning card information from the character information written in the first column 112 and the second column 122 of the book 100, but in other embodiments. Information included in at least one of the first column 112 and the second column 122 may generate learning card information from image information (pictures, drawings, symbols, photographs, etc.). This will be described in detail with reference to FIGS. 6 (a) and 6 (b).

FIG. 6A is a diagram showing a configuration example of a learning tool generation book according to an embodiment, and FIG. 6B is a diagram showing a reference mark 130 used for the book of FIG. 6A.
As shown in FIG. 6A, the first column 112 includes image information indicating the appearance of the product, and the second column 122 includes character information related to the image information (for example, product name, product features). Product price, product color type, etc.). In other embodiments, a picture or photo of a historical person is included in the first column 112, and the second column 122 includes the person's name, feat, area of activity, or the time when the person lived. Information may be included. In another embodiment, a landmark picture or photo may be included in the first column 112 and the second column 122 may include information such as the name, location, etc. of the landmark. In yet another embodiment, photographs or pictures of animals and plants such as animals, fish and insects are included in the first column 112, and the second column 122 includes the name, classification, habitat, etc. of the organism or plant. May be included.
In the exemplary embodiment shown in FIGS. 6A and 6B, the reference mark 130 includes an outer reference contour 134 having eight corners 132a and an inner reference contour having ten corners 132b. 136. In FIG. 6B, only the representative corner portions 132a and 132b are denoted by reference numerals.

  In the above-described embodiment, it is assumed that one type of reference mark 130 is mainly used. However, a plurality of types of reference marks 130 may be used. The use of a plurality of types of reference marks 130 can meet various needs of learners. This will be described in detail below with reference to FIGS. 2 and 7 to 9.

FIG. 7A is a diagram illustrating a configuration example of a learning tool generation book according to an embodiment, and FIG. 7B is a diagram illustrating a reference mark 130 used for the book of FIG. 7A.
The book 100 shown in FIG. 7A has fewer columns in the first column 112 and the second column 122 than the example shown in FIG. For this reason, more information can be included in each of the first column 112 and the second column 122. In the exemplary embodiment shown in FIG. 7 (a), the first sheet 110 is provided with six columns of first columns 112, and the second sheet 120 is provided with six columns corresponding to the first columns 112, respectively. A second column 122 is provided. As shown in FIG. 7B, the reference mark 130 in the present embodiment has an L-shaped outer reference contour 134 having six corners 132a and a T-shape having eight corners 132b. Inner reference contour 136. In FIG. 7B, only the representative corners 132a and 132b are denoted by reference numerals.

FIG. 8 is a diagram illustrating a configuration example of a learning tool generation book according to an embodiment.
8 differs from the example shown in FIGS. 2 and 7A in that the number of columns in the first column 112 and the second column 122 is different. Specifically, a plurality of second columns 122 are associated with one first column 112. Therefore, a plurality of types of information corresponding to one first column 112 can be included in the second column 122 in a plurality of columns. In the exemplary embodiment shown in FIG. 8, the first page 110 is provided with two rows of first columns 112, and the second page 120 has three rows of second columns 112 for each first column 112. A total of six columns of second columns 122 are provided so that the columns 122 correspond. The reference mark 130 in the present embodiment is the same as that shown in FIG.

  FIG. 9 is a flowchart showing a procedure for properly using a plurality of image division conditions using a plurality of types of reference marks 130. Here, a learning tool generation method will be described in which a plurality of image division conditions are selectively used by utilizing the three types of reference marks 130 described with reference to FIGS. 2, 7A, and 8.

As shown in FIG. 9, in step S30, the processor 12 sets the reference mark 130 based on the success or failure of the first identification condition to the fourth identification condition according to the procedure (steps S2 to S18) described above with reference to FIG. To detect. The reference mark 130 here is one of the three types of reference marks 130 shown in FIGS. 2, 7A and 8. Here, the three types of reference marks 130 shown in FIGS. 2, 7A and 8 are referred to as a first reference mark 130A, a second reference mark 130B and a third reference mark 130C, respectively.
When executing step S30, the identification conditions (first identification condition to fourth identification condition) are individually set for each of the three types of reference marks 130 (130A to 130C) and stored in the memory 16 in advance. May be. For example, in the case of the first reference mark 130A, the first identification condition is that the outer reference contour 134 has four corners 132a and the inner reference contour 136 has eight corners 132b, whereas the second reference mark 130B has In this case, the first identification condition is six corners 132a of the outer reference contour 134 and eight corners 132b of the inner reference contour 136. In the case of the third reference mark 130C, the first identification condition is the outer reference contour 134. There are four corners 132a and eight inner reference contours 132b. Similarly, the other identification conditions (second identification condition to fourth identification condition) are individually set for each of the reference marks 130A to 130C. In this case, in order to execute step S30, the processor 12 reads the first identification condition to the fourth identification condition individually set for each of the reference marks 130A to 130C from the memory 16, and any one of the first identification conditions The candidate graphic 200 that satisfies the fourth identification condition may be detected as the reference mark 130.

Next, in steps S32 to S36, it is specified which of the first reference mark 130A to the third reference mark 130C is the detected reference mark 130. At this time, when the reference mark 130 is detected in step S30, the identification of the reference mark 130 is determined based on which of the reference marks 130 (130A to 130C) the identification condition (first identification condition to fourth identification condition) is satisfied. May be performed.
For example, if the first to fourth identification conditions for the first reference mark 130A are satisfied when the reference mark 130 is detected in step S30, the reference mark 130 is determined to be the first reference mark 130A. (YES determination of step S32). Similarly, if the first to fourth identification conditions for the second reference mark 130B are satisfied when the reference mark 130 is detected in step S30, it is determined that the reference mark 130 is the second reference mark 130B. (YES determination in step S34). Furthermore, if the first identification condition to the fourth identification condition for the third reference mark 130C are satisfied when the reference mark 130 is detected in step S30, it is determined that the reference mark 130 is the third reference mark 130C. (YES determination of step S36).
Thus, in steps S32 to S36, it is specified which of the first reference mark 130A to the third reference mark 130C is the detected reference mark 130. When it is determined that the detected reference mark 130 is not any of the first reference mark 130A to the third reference mark 130C (NO determination in step S36), the processor 12 generates a specific error signal of the reference mark 130. (Step S37).

  Thereafter, the process proceeds to step S38, and an image division condition corresponding to the identified reference mark 130 (130A to 130C) is determined. At this time, the processor 12 may determine the image division condition by reading the image division condition corresponding to each of the reference marks 130 </ b> A to 130 </ b> C from the memory 16.

  Subsequently, in step S40, an image is displayed in the first column 112 and the second column 122 of the number of columns specified by the image division condition based on the representative coordinates of the reference mark 130 (130A to 130C) according to the determined image division condition. Split. For example, when the first fiducial mark 130A is detected, the image is divided into 12 columns of the first column 112 and 12 columns of the second column 122 according to the image dividing condition corresponding to the first fiducial mark 130A. Similarly, when the second fiducial mark 130B is detected, the image is divided into six columns of the first column 112 and six columns of the second column 122 according to the image dividing condition corresponding to the second fiducial mark 130B. Further, when the third reference mark 130C is detected, the image is divided into two columns of the first column 112 and six columns of the second column 122 according to the image dividing condition corresponding to the third reference mark 130C.

  Finally, in step S42, the image information in the first area 212 and the image information in the second area 222 are associated with each other and stored in the memory 16 as learning card information.

In this way, if the learning card information is generated by using the plurality of kinds of reference marks 130 (130A to 130C) by the procedure described with reference to FIG. 9, the first column is adapted to the needs of the learner. It is possible to selectively use a plurality of types of books having different correspondences between 112 and the second column 122.
In the embodiment described above with reference to FIG. 9, the example using all of the first identification condition to the fourth identification condition has been described. However, according to the identification condition including one or more of the first identification condition to the fourth identification condition. The reference mark 130 (130A to 130C) may be specified.

DESCRIPTION OF SYMBOLS 1 Learning support apparatus 10 Computer 12 Processor 14 Camera 16 Memory 18 Display 20 Input part 100 Book face 102 Binding part 104 Hole 110 1st paper surface 112 1st column 120 2nd paper surface 122 2nd column 130 Reference mark 132,132a, 132b (reference | standard) Outer reference contours 134, 136 (reference mark) contours 135, 137 Region 136 Inner reference contour 140 Virtual rectangle 200 Candidate graphic 212 First region 222 Second region 232, 232a, 232b (of candidate graphic) Corners 234, 236 (candidate graphic) contour 234 outer contour 236 inner contour

Claims (14)

A learning tool is generated from an image obtained by capturing an image of a book configured such that a first sheet having one or more first columns and a second sheet having a plurality of columns of second columns are adjacent to each other when facing apart. A learning support program for operating a computer
Of the four corners of the virtual rectangle formed by the first paper surface and the second paper surface when the page is spread, one or more corners on the first paper surface and one or more corners on the second paper surface Obtaining the image including a plurality of fiducial marks located;
Identifying the plurality of reference marks in the image and calculating coordinates indicating the position of each of the plurality of reference marks;
Based on the coordinates of each of the fiducial marks, the image is placed in one or more first regions on the first paper surface side corresponding to the one or more first columns, and in the second column of the plurality of rows. A plurality of second regions on the second paper surface side corresponding to each of the second regions;
A procedure in which the image information of the one or more first areas and the image information of the plurality of second areas are associated with each other and stored as learning card information in a storage unit;
A learning support program for causing the computer to execute. Calculate the number of corners within the specified angle range of the figure in the image,
A procedure for identifying the graphic as the reference mark based on success or failure of at least one identification condition including that the calculated number of corners of the graphic matches the number of corners of the reference mark. The learning support program according to claim 1, further configured to be executed. The reference mark includes an outer reference contour and an inner reference contour located inside the outer reference contour;
The at least one identification condition is:
The number of corners within the specified angle range of the outer contour of the figure matches the number of corners of the outer reference contour; and
The learning support program according to claim 2, wherein the number of corners in the prescribed angle range of the inner contour of the figure matches the number of corners of the inner reference contour.   4. The learning support program according to claim 3, wherein the reference mark is a polygon in which the outer reference contour is rectangular and the inner reference contour has eight or more right-angled corners. Calculate the area surrounded by the contour of the figure in the image,
A procedure for identifying the figure as the reference mark based on the success or failure of at least one identification condition including the calculated size of the area or the ratio of the area occupied in the image being within a specified range. The learning support program according to claim 1, further configured to be executed by the computer. Identify the coordinates of a plurality of corners within a specified angle range in the contour of the figure in the image,
Based on the success or failure of at least one identification condition including whether or not the shape obtained by connecting the coordinates of the corners within each specified angle range matches the shape of the reference mark, The learning support program according to any one of claims 1 to 5, wherein the computer is further configured to execute a procedure of identifying as a mark. The reference mark is provided at each of the four corners of the virtual rectangle,
7. The apparatus according to claim 1, wherein when the four reference marks cannot be detected in the image, a procedure for generating a mark recognition error signal is further executed by the computer. 8. Learning support program.   The learning support program according to any one of claims 1 to 7, wherein the computer is further configured to further execute a procedure for correcting the image based on the coordinates of each of the reference marks. Displaying at least one image information of the first region as question content;
Displaying at least one image information of the second region corresponding to each of the at least one first region as a response content;
The learning support program according to claim 1, further causing the computer to execute the following. Calculating a first area surrounded by an outer contour of the figure in the image and a second area surrounded by an inner contour located inside the outer contour;
Causing the computer to further execute a procedure for identifying the graphic as the reference mark based on success or failure of at least one identification condition including that the calculated ratio between the first area and the second area is within a specified range. The learning support program according to claim 1, configured as described above. A procedure for specifying which one of the reference marks in the image among a plurality of types of reference marks respectively corresponding to a plurality of division conditions of the image;
Dividing the image into the first area and the second area according to the division condition corresponding to the identified reference mark;
The learning support program according to claim 1, wherein the learning support program is further configured to cause the computer to execute. The learning support program according to any one of claims 1 to 11,
Of the four corners of the virtual rectangle formed by the first paper surface and the second paper surface when the page is spread, one or more corners on the first paper surface and one or more corners on the second paper surface Obtaining the image including a plurality of fiducial marks located;
Identifying the plurality of reference marks in the image and calculating coordinates indicating the position of each of the plurality of reference marks;
Based on the coordinates of each of the fiducial marks, the image is placed in one or more first regions on the first paper surface side corresponding to the one or more first columns, and in the second column of the plurality of rows. A plurality of second regions on the second paper surface side corresponding to each of the second regions;
A procedure in which the image information of the one or more first areas and the image information of the plurality of second areas are associated with each other and stored as learning card information in a storage unit;
A learning support apparatus comprising a computer configured to execute the above. A first page having a first column of one or more rows;
A second page having a plurality of rows of second columns;
A learning tool generation book comprising:
When the learning tool generation book is spread, the first paper surface and the second paper surface are adjacent to each other, and the first paper surface among the four corners of the virtual rectangle formed by the first paper surface and the second paper surface. A plurality of fiducial marks located at one or more corners on the top and one or more corners on the second paper surface;
The learning support program according to any one of claims 1 to 11,
A procedure for acquiring an image of the learning tool generation book including the plurality of reference marks;
Identifying the plurality of reference marks in the image and calculating coordinates indicating the position of each of the plurality of reference marks;
Based on the coordinates of each of the fiducial marks, the image is placed in one or more first regions on the first paper surface side corresponding to the one or more first columns, and in the second column of the plurality of rows. A plurality of second regions on the second paper surface side corresponding to each of the second regions;
A procedure in which the image information of the one or more first areas and the image information of the plurality of second areas are associated with each other and stored as learning card information in a storage unit;
A learning tool generation book configured to generate a learning tool by running a computer. Learning that generates a learning tool from an image of a book that is configured such that a first page having one or more columns of the first column and a second page having a plurality of columns of the second column are adjacent to each other when facing apart. A tool generation method,
Of the four corners of the virtual rectangle formed by the first paper surface and the second paper surface when the page is spread, one or more corners on the first paper surface and one or more corners on the second paper surface Capturing the image including a plurality of fiducial marks located;
Identifying the plurality of reference marks in the image and calculating coordinates indicating the position of each of the plurality of reference marks;
Based on the coordinates of each of the fiducial marks, the image is placed in one or more first regions on the first paper surface side corresponding to the one or more first columns, and in the second column of the plurality of rows. Dividing into a plurality of second regions on the second paper surface side corresponding respectively;
Storing the image information of the one or more first areas and the image information of the plurality of second areas as learning card information in association with each other;
A learning tool generation method comprising: