Information processing device and program

Abstract

To provide scanned image check and correction functions so as to lighten the work load of learning supporters.SOLUTION: An information processing device stores student identification information for identifying a student in association with the shade level target value of entry items having been entered to an entry sheet by the student. The information processing device also acquires the image data of an image derived by scanning the entry sheet. The information processing device identifies student identification information corresponding to the image data and extracts a target value from a storage unit on the basis of the identified student identification information. The information processing device also sets the current value of shade levels of entry items on the basis of the image data. Meanwhile, the information processing device determines, for each student, whether or not there is abnormality in the shade levels of the image, on the basis of the target value and the current value.SELECTED DRAWING: Figure 11

Description

[Technical Field]

[0001] The present invention relates to a technique for reducing the workload of a learning support worker. [Background technology]

[0002] Digital marking systems that automatically mark academic achievement tests, etc. have been known for some time. Patent Document 1 discloses a system that scans answer sheets on which answers have been written and improves the efficiency of the marking method based on the read data. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2007-322748 Summary of the Invention [Problem to be solved by the invention]

[0004] To use the digital scoring system, users must scan their answer sheets at the exam venue and then send the scanned image as data to the test provider for registration. When registering, the test provider manually checks whether the scanned image meets specifications, and if it does not, requests the user to rescan. In other words, if the specifications are not met, rework is required, which places a heavy workload on users and learning support staff such as test providers when dealing with large volumes of answer sheets.

[0005] The present invention has been made to solve, for example, the above-mentioned problems, and aims to provide an information processing device that reduces the workload of learning support staff by providing functions for checking and correcting scanned images. [Means for solving the problem]

[0006] In one aspect of the present invention, an information processing device includes a memory unit that stores student identification information for identifying a student and a target value of shading intensity of an entry item filled in by the student on a form, in association with each other; an image data acquisition unit that acquires image data of an image obtained by scanning the form; a student identification information identification unit that identifies the student identification information corresponding to the image data; a target value extraction unit that extracts the target value from the memory unit based on the identified student identification information; a current value setting unit that sets a current value of shading intensity of the entry item based on the image data; and an abnormality determination unit that determines whether or not there is an abnormality in the shading of the image for each student based on the target value and the current value. The entry form has a plurality of entry items, and is equipped with an area detection unit that detects all entry areas that are areas of the entry items from the image data, and the current value setting unit calculates an average value of the shading intensity of the entire entry area based on the shading intensity of each entry area, and sets the average value as the current value. According to this aspect, the information processing device can determine whether or not there is an abnormality in the shading of the scanned image for each student, based on the target value of the shading intensity for each student. In addition, according to this aspect, the information processing device can determine whether there are any abnormalities in the shading of the scanned image based on the target value of shading intensity for each student and the current value of shading intensity derived from multiple writing areas.

[0007] In one aspect of the information processing device, the information processing device further includes an alert output unit that outputs an alert when the abnormality determination unit determines that there is an abnormality in the shading of the image. According to this aspect, the alert allows the user to check the status and settings of the scanner if the same abnormality is found in multiple images, or to confirm that the student is not a different person if there is an abnormality in only one image.

[0008] In one aspect of the information processing device, when the abnormality determination unit determines that the image has an abnormality in shading, the information processing device includes a shading correction unit that corrects the shading of the image based on image data of the image with the abnormality in shading and target values ​​and current values ​​corresponding to the image data. According to this aspect, the information processing device performs optimal shading correction on the scanned image based on the target values ​​for each student, thereby ensuring the shading obtained by a normal scan.

[0011] In one aspect of the information processing device, the image data has a two-dimensional code including the student identification information, and the student identification information identification unit identifies the student identification information by reading the two-dimensional code included in the image data. According to this aspect, the information processing device can easily identify the student identification information corresponding to each image data.

[0012] In one aspect of the above information processing device, the information processing device is communicably connected to a scoring device that automatically scores, the entry form is an answer sheet on which the student writes their answers to questions, and the information processing device includes an image data transmission unit that transmits image data of the image whose shading has been corrected by the shading correction unit to the scoring device. According to this aspect, the information processing device can transmit image data of images with no shading problems to the scoring device, allowing the scoring device to be used efficiently without rework.

[0013] In another aspect of the present invention, a program executed by an information processing device having a computer includes: a storage unit that stores student identification information for identifying a student and a target value of shading intensity of an entry item filled in by the student on an entry form, in association with each other; an image data acquisition unit that acquires image data of an image obtained by scanning the entry form; a student identification information identification unit that identifies the student identification information corresponding to the image data; a target value extraction unit that extracts the target value from the storage unit based on the identified student identification information; a current value setting unit that sets a current value of shading intensity of the entry item based on the image data; and an abnormality determination unit that determines, for each student, whether or not there is an abnormality in the shading of the image based on the target value and the current value. the form has a plurality of entry items, and an area detection unit detects all entry areas, which are areas of the entry items, from the image data; and causing the computer to function as The current value setting unit calculates an average value of the shading intensity of the entire writing area based on the shading intensity of each writing area, and sets the average value as the current value. By installing and executing this program on a computer, an information processing device according to the present invention can be configured. [Effects of the Invention]

[0014] According to the information processing device of the present invention, by providing a function for checking and correcting scanned images, the workload of the learning assistant can be reduced. [Brief explanation of the drawings]

[0015] [Figure 1] 1 shows the configuration of a check system to which an information processing device of the present invention is applied. [Figure 2] This is an example of an answer sheet. [Figure 3] FIG. 2 is a block diagram showing the hardware configuration of a check server. [Figure 4] FIG. 2 is a block diagram showing the functional configuration of a check server. [Figure 5] 10 is an example of a shading correction function. [Figure 6] The answer box area is shown before and after correction. [Figure 7] 10 is an example of a first result display screen. [Figure 8] 10 is an example of a second result display screen. [Figure 9] FIG. 2 is a block diagram showing the hardware configuration of the terminal device. [Figure 10] 10 is a flowchart of a target value registration process. [Figure 11] 10 is a flowchart of a check process. DETAILED DESCRIPTION OF THE INVENTION

[0016] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. <Embodiment> [Overall configuration] 1 shows the configuration of a check system to which the information processing device of the present invention is applied. The check system 100 is a system that checks the specifications and shading of scanned images of answer sheets read using a scanner or the like, and corrects the shading of the scanned images for each student if necessary. The check system 100 is configured so that a check server 10 and a terminal device 20 can communicate with each other via a network 5 such as the Internet.

[0017] The check server 10 is an information processing device that processes, stores, and transmits / receives various types of information, and is, for example, a server device, a personal computer, or a general-purpose tablet PC.

[0018] The terminal device 20 is used by a user and is, for example, an information processing device such as a personal computer. Specifically, the terminal device 20 is electrically connected to a scanner (optical device) 1 via a wired or wireless connection, and receives an image obtained by scanning a predetermined paper sheet (hereinafter also referred to as a "scanned image") from the scanner 1. The terminal device 20 then transmits the scanned image to the check server 10 as image data, and receives corrected image data from the check server 10. In this embodiment, the predetermined paper sheet is an answer sheet on which answers to an academic ability test or the like are written, and the answer sheet has multiple answer columns. The terminal device 20 may also have a built-in scanner function.

[0019] [Answer sheet] An example of an answer sheet is shown in Figure 2. As shown in Figure 2, the answer sheet 60 is a sheet on which students write answers to an academic ability test, and has multiple answer columns 61 where students write their answers for each question, and a two-dimensional code 62 containing information on the student ID that identifies the student who wrote the answer.

[0020] [Server Configuration] 3 is a block diagram showing the hardware configuration of the check server 10. The check server 10 includes a communication unit 11, a control unit 12, a storage unit 13, a recording medium 14, a display unit 15, an input unit 16, and a reading unit 17. These components and a gray-scale intensity database (hereinafter, "database" will be abbreviated as "DB") 51 are interconnected via a bus 19.

[0021] The check server 10 may be executed by a single computer, may be distributed and executed by a plurality of computers, or may be distributed and executed by virtual machines.

[0022] The communication unit 11 is a communication unit for communicating with the terminal device 20 through the network 5. Specifically, the communication unit 11 receives a scanned image from the terminal device 20 as image data, and transmits a corrected scanned image to the terminal device 20 as image data.

[0023] The control unit 12 includes a processing unit such as a CPU (Central Processing Unit), MPU (Micro-Processing Unit), GPU (Graphics Processing Unit), etc., and performs various information processing, control processing, etc. related to the check server 10 by reading and executing programs stored in the storage unit 13. The programs can be deployed so that they are executed on a single computer, located at one site, or distributed across multiple sites and on multiple computers interconnected by a communication network. Although FIG. 3 illustrates the control unit 12 as a single processor, it may also be a multi-processor.

[0024] The storage unit 13 includes memory elements such as RAM (Random Access Memory) and ROM (Read Only Memory), and stores programs, data, etc. required for the control unit 12 to execute processing. The storage unit 13 also temporarily stores data, etc. required for the control unit 12 to execute arithmetic processing.

[0025] The recording medium 14 is a non-volatile, non-temporary recording medium such as a disk-shaped recording medium or semiconductor memory, and is configured to be detachable from the check server 10. The recording medium 14 records various programs executed by the control unit 12. When the check server 10 executes the target value registration process, check process, or shade correction process described below, the programs recorded on the recording medium 14 are loaded into the memory unit 13 and executed by the control unit 12.

[0026] The display unit 15 is a liquid crystal display, an organic EL (electroluminescence) display, or the like, and displays various information according to instructions from the control unit 12. The input unit 16 is an input device such as a mouse, keyboard, touch panel, or button, and outputs received operation information to the control unit 12. The reading unit 17 recognizes two-dimensional codes using a built-in camera or the like, and reads information. Specifically, the reading unit 17 recognizes the two-dimensional code 62 on the answer sheet and reads the student ID information included in the two-dimensional code 62.

[0027] The shading intensity DB51 stores information related to the target value of shading intensity for each student (hereinafter, the "target value of shading intensity" will also be simply referred to as the "target value") in association with the student ID. Here, shading intensity refers to the degree of intensity of a color; the lower the shading intensity, the darker the color; and the higher the shading intensity, the lighter the color. Since each student's writing pressure and style are different, the shading intensity will also be different for each student. Specifically, the shading intensity uses the maximum and minimum brightness values ​​in the answer column. The target value is calculated for each student based on a scanned image of the answer sheet filled out by each student, as will be described in detail below.

[0028] The storage format of each DB described above is an example, and other storage formats are possible as long as the relationships between the data are maintained. Each DB is realized by a recording medium such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive). In this embodiment, the storage unit 13 and the various DBs may be configured as an integrated storage device, or may be separate storage devices. The various DBs may also be external storage devices connected to the check server 10, and the configuration thereof may be set arbitrarily.

[0029] 4 is a block diagram showing the functional configuration of the check server 10. Functionally, the check server 10 includes a shading intensity DB 51, a target value registration unit 31, an image data acquisition unit 32, a student ID identification unit 33, a specification check unit 34, a target value extraction unit 35, an area detection unit 36, a current value setting unit 37, an abnormality determination unit 38, an alert output unit 39, a shading correction unit 40, a result output unit 41, and an image data transmission unit 42.

[0030] The target value registration unit 31, image data acquisition unit 32, student ID identification unit 33, specification check unit 34, target value extraction unit 35, area detection unit 36, current value setting unit 37, abnormality judgment unit 38, alert output unit 39, shading correction unit 40, result output unit 41 and image data transmission unit 42 are realized by the control unit 12 executing a program.

[0031] The target value registration unit 31 registers the target value of the shading intensity for each student in the shading intensity DB 51. The target value registration unit 31 first obtains registration image data, which is a scanned image of each student's answer sheet, from the terminal device 20. The registered image data is image data that has been checked in advance for specifications and shading and is found to be problem-free. The target value registration unit 31 then identifies the student ID by reading the information in the two-dimensional code 62 on the answer sheet based on the registered image data. The target value registration unit 31 also detects the area of ​​each answer column (hereinafter also referred to as "answer column area") from the registered image data. Details of the method for detecting the answer column area from image data will be explained in the area detection unit 36.

[0032] The target value registration unit 31 acquires the shading intensity of each answer column area and calculates the average value of the shading intensity of the entire answer column area. Specifically, if the answer sheet has 10 answer columns, the target value registration unit 31 detects 10 answer column areas from the registered image data. Then, the target value registration unit 31 acquires the minimum and maximum luminance values ​​of each stroke entered in one answer column area and calculates the average value of the minimum and maximum luminance values ​​of the entire stroke. The average values ​​of the minimum and maximum luminance values ​​of the entire stroke calculated in this way are set as the minimum and maximum luminance of one answer column area. In this way, the target value registration unit 31 acquires the minimum and maximum luminance values ​​of each answer column area. The minimum and maximum luminance values ​​of each answer column area are, in other words, the shading intensity of each answer column area.

[0033] The target value registration unit 31 calculates the average value of the minimum and maximum brightness values ​​of the entire answer box area based on the minimum and maximum brightness values ​​of the 10 answer box areas. The average value of the minimum and maximum brightness values ​​of the entire answer box area calculated in this way is set as the average value of the shading intensity of the entire answer box area. Note that if the student does not know the answer and does not write anything in one answer box, the target value registration unit 31 invalidates the shading intensity of that answer box and calculates the average value of the shading intensity of the entire answer box area from the nine answer box areas (hereinafter, the "average value of shading intensity" will also be simply referred to as the "average value").

[0034] The target value registration unit 31 calculates the average value of the entire answer column area for each student based on the image data of the answer sheet on which each student has written their answers.The target value registration unit 31 then associates the average value of the entire answer column area with the student ID and registers it as a target value in the shading intensity DB 51.In other words, the shading intensity DB 51 stores the target value of shading intensity for each student.

[0035] The image data acquisition unit 32 acquires image data of the scanned image from the terminal device 20 that scanned the answer sheet at the exam venue of the academic ability test, etc. Unlike the registered image data, the specifications and shading of the image data in this case have not been checked.

[0036] The student ID identification unit 33 identifies the student ID by reading the information of the two-dimensional code 62 on the answer sheet based on each image data.

[0037] The specification check unit 34 checks whether there are any problems with the specifications of each image data. Specifically, specifications are requirements that must be met for automatic grading, such as the image data resolution, color, storage format, and image size. The requirements are not limited to these, and can be set arbitrarily, such as the image data's inclination. The specification check unit 34 checks whether the image data's resolution, color, storage format, and image size match the pre-set requirements. If they do not match, the specification check unit 34 temporarily stores the image data with the specifications problem as a result of the specification check, the student ID of the image data, and the mismatched requirements in the storage unit 13.

[0038] In this embodiment, the registered image data is checked in advance for specifications and shading to ensure that there are no problems, but the specification check at this time may be performed by the specification check unit 34 .

[0039] Based on the student ID identified for each image data, the target value extraction unit 35 extracts the target value from the shading intensity DB 51. In other words, the target value extraction unit 35 extracts the target value of the student who filled out the answer sheet corresponding to the image data.

[0040] The area detection unit 36 ​​uses a machine-learned detector to detect the answer column area of ​​each answer column 61 from each image data. Examples of machine learning techniques include deep learning such as R-CNN (Regions with CNN features).

[0041] The current value setting unit 37 sets the current value of the shading intensity of the answer column of the answer sheet corresponding to each image data (hereinafter, the "current value of shading intensity" will also be simply referred to as the "current value"). Specifically, the current value setting unit 37 first obtains the shading intensity of each answer column area. Then, based on the shading intensity of each answer column area, the current value setting unit 37 calculates the average value of the shading intensity of the entire answer column area. The method of calculating the average value is the same as the method of calculating the target value of shading intensity described above, so for convenience, the explanation will be omitted. The current value setting unit 37 sets the average value as the current value of the answer column.

[0042] The abnormality determination unit 38 determines whether or not there is an abnormality in the shading of the scanned image displayed by each image data, based on the target value and the current value. In other words, it determines whether or not there is an abnormality in the shading of the scanned image for each student corresponding to each image data. For example, the abnormality determination unit 38 may compare the target value with the current value and determine that there is an abnormality if there is a deviation of more than a predetermined range, or may determine that there is an abnormality if the current value exceeds a threshold value that is preset based on the target value. The method of determining an abnormality based on the target value and the current value can be set arbitrarily.

[0043] The alert output unit 39 outputs an alert to the terminal device 20 when the abnormality determination unit 38 determines that an abnormality exists. The alert output method can be set arbitrarily, such as highlighting a scanned image determined to have an abnormality or highlighting a student ID corresponding to a scanned image determined to have an abnormality. In the check process described below, the alert output unit 39 outputs an alert each time the abnormality determination unit 38 determines that an abnormality exists, but the present invention is not limited to this, and an alert may be output all at once after abnormality determination has been completed for all image data.

[0044] By outputting an alert before correcting the shading of a scanned image, the user can check the status and settings of Scanner 1 if the same abnormality is found in multiple scanned images, or can confirm that the student is not a different person if the abnormality is found in only one scanned image.

[0045] When the abnormality determination unit 38 determines that there is an abnormality, the shading correction unit 40 corrects the shading of the scanned image based on the image data of the scanned image and the target value and the current value corresponding to the image data. The target value is based on the normal pen pressure and writing style of each student, and the shading correction unit 40 corrects the shading so that the scanned image reproduces the normal entry state of each student regardless of the state and settings of the scanner 1.

[0046] Specifically, the shading correction unit 40 uses the target value and the current value to generate a shading correction function that converts the current value to the target value as shown in FIG. 5. FIG. 5 is an example of a shading correction function. As shown in the figure, the vertical axis of the shading correction function is the output luminance and the horizontal axis is the input luminance. The shading correction unit 40 determines each mapping point based on the minimum luminance value of the target value (hereinafter also referred to as "minimum luminance target value") and the minimum luminance value of the current value (hereinafter also referred to as "minimum luminance current value"), and the maximum luminance value of the target value (hereinafter also referred to as "maximum luminance target value") and the maximum luminance value of the current value (hereinafter also referred to as "maximum luminance current value"), thereby generating a shading correction function. The shading correction unit 40 corrects the shading of the scanned image so as to reproduce the normal entry state of the student by converting the current value to the target value using the generated shading correction function.

[0047] FIG. 6 shows the state before and after shading correction of a predetermined answer column area 65. For example, when it is determined that the shading of the scanned image is abnormal because the minimum luminance current value is lower than the threshold value, as shown in FIG. 6(a), the shading correction unit 40 corrects the scanned image so that the character string "Jito" entered in the answer column area 65a becomes darker. On the other hand, when it is determined that the shading of the scanned image is abnormal because the maximum luminance current value is higher than the threshold value, as shown in FIG. 6(b), the shading correction unit 40 corrects the scanned image so that the character string "Jito" entered in the answer column area 65b becomes lighter. In this way, the shading correction unit 40 corrects the shading of the scanned image not for readability, ease of recognition, etc., but to reproduce the normal entry state of the student.

[0048] The result output unit 41 outputs the specification check result by the specification check unit 34 and the shading check result by the abnormality determination unit 38 to the terminal device 20. The specification check result includes information about image data with a problem in the specifications, the student ID of the image data, and requirements that do not match the settings. The shading check result also includes information about image data of the scanned image determined to have an abnormality by the abnormality determination unit 38, image data of the scanned image whose shading has been corrected by the shading correction unit 40 (hereinafter also referred to as "corrected image data"), and the student ID of the image data.

[0049] Specifically, the result output unit 41 creates a result display screen displaying the specification check results and the shading check results, and transmits the result display screen to the terminal device 20. By displaying the result display screen received by the terminal device 20, the user can check image data for problems with specifications or shading for answer sheets scanned by the scanner 1. FIG. 7 is an example of a first result display screen displaying an abnormality determination result. As shown in FIG. 7, the first result display screen includes scanned images 70 of students' answer sheets and serial numbers for the scanned images 70. In the example of FIG. 7, the first result display screen displays scanned images 70a to 70h of eight students' answer sheets, each assigned serial numbers 1 to 8. Furthermore, the first result display screen highlights scanned image 70d determined to have an abnormality based on the shading check results, for example, by surrounding it with a red frame 75. This allows the user to check scanned image 70d with shading abnormalities by comparing it with other scanned images 70.

[0050] Figure 8 shows an example of the second result display screen that displays the anomaly determination result. When the highlighted scanned image 70d on the first result display screen is clicked, the second result display screen is displayed in a separate window, showing the scanned image 70d before and after the shading correction, as shown in Figure 8. This allows the user to compare the scanned image before and after the shading correction with the paper answer sheet.

[0051] In this embodiment, the first result display screen and the second result display screen are given as examples, but the present invention is not limited to this, and the configuration of the result display screen can be set arbitrarily, such as displaying the specification check results and the shading check results on one screen.

[0052] The image data transmission unit 42 transmits image data of a scanned image that has been determined to have no abnormality by the abnormality determination unit 38 to the terminal device 20. In addition, the image data transmission unit 42 transmits corrected image data of a scanned image that has been determined to have an abnormality by the abnormality determination unit 38 to the terminal device 20.

[0053] In the above configuration, the image data acquisition unit 32, target value extraction unit 35, area detection unit 36, current value setting unit 37, abnormality determination unit 38, alert output unit 39, and shading correction unit 40 of the check server 10 are examples of the image data acquisition unit, target value extraction unit, area detection unit, current value setting unit, abnormality determination unit, alert output unit, and shading correction unit of the present invention, respectively. Also, the shading intensity DB 51 and student ID identification unit 33 are examples of the memory unit and student identification information identification unit of the present invention, respectively. The answer sheet and answer column are examples of the form and entry items of the present invention, respectively.

[0054] [Terminal device configuration] 9 is a block diagram showing the hardware configuration of terminal device 20. Terminal device 20 includes a communication unit 21, a control unit 22, a storage unit 23, a display unit 25, and an input unit 26. These components are interconnected via a bus 29.

[0055] The communication unit 21 is a communication unit for communicating with the check server 10 via the network 5. Specifically, the communication unit 21 transmits image data to the check server 10 and receives a result display screen and corrected image data from the check server 10. The communication unit 21 may also transmit the image data and corrected image data received from the check server 10 to a digital scoring system that performs automatic scoring processing.

[0056] The control unit 22 includes an arithmetic processing unit such as a CPU, an MPU, a GPU, etc., and reads and executes programs stored in the storage unit 23 to perform various information processing, control processing, etc. related to the terminal device 20. Note that although the control unit 22 is described as a single processor in Fig. 9, it may be a multiprocessor.

[0057] The storage unit 23 includes memory elements such as RAM and ROM, and stores programs, data, etc. required for the control unit 22 to execute processing. The storage unit 23 also temporarily stores data, etc. required for the control unit 22 to execute arithmetic processing.

[0058] The display unit 25 is a liquid crystal display, an organic EL display, or the like, and displays various information in accordance with instructions from the control unit 22. The input unit 26 is an input device, such as a mouse, keyboard, touch panel, or button, and outputs received operation information to the control unit 22. The input unit 26 may also be an interface for connecting to these devices. In this embodiment, the interface is an interface for connecting to the scanner 1 via a wired or wireless connection, and supplies the scanned image received from the scanner 1 to the control unit 22.

[0059] [Target value registration process] Next, we will explain the process of registering target values ​​of shading intensity for each student based on the registered image data. Figure 10 is a flowchart of the target value registration process. This process is realized by the check server 10 executing a program prepared in advance. In this embodiment, it is assumed that one student fills out one answer sheet.

[0060] A user uses the terminal device 20 to upload registered image data, which is a scanned image of each student's answer sheet, to the check server 10. As a result, the check server 10 acquires the registered image data from the terminal device 20 (step S101). Then, the check server 10 identifies the student ID by reading the information in the two-dimensional code on the answer sheet based on the registered image data corresponding to one answer sheet (step S102). In addition, the check server 10 uses a machine-learned detector to detect each answer column area from the registered image data (step S103).

[0061] The check server 10 acquires the shading intensity of each answer box area and calculates the average value of the shading intensity of the entire answer box area. The calculated average value is set as the target value (step S104). Then, the check server 10 associates the identified student ID with the set target value and registers it in the shading intensity DB 51 (step S105). When registration of the target value for one student based on the registered image data is completed, the check server 10 determines whether registration of target values ​​has been completed based on all registered image data (step S106). If it is determined that there is registered image data for which target values ​​have not yet been registered (step S105; No), the check server 10 returns to step S102 and performs processing based on the registered image data for which registration has not yet been completed. On the other hand, if it is determined that registration of target values ​​has been completed based on all registered image data (step S105; Yes), the check server 10 ends the target value registration process. As a result, the shading intensity target value for each student is stored in the shading intensity DB 51.

[0062] [Check process] Next, a check process will be described in which specifications and the shading of the scanned image are checked based on image data acquired from the terminal device 20, and the shading of the scanned image is corrected if an abnormality is found. Fig. 11 is a flowchart of the check process. This process is realized by the check server 10 executing a program prepared in advance.

[0063] A user uses the terminal device 20 to scan an answer sheet at an examination site for an academic ability test or the like, and uploads the image data of the scanned image to the check server 10. As a result, the check server 10 acquires the image data from the terminal device 20 (step S201). Then, the check server 10 identifies the student ID by reading the information of the two-dimensional code on the answer sheet based on the image data corresponding to one answer sheet (step S202).

[0064] Next, the check server 10 checks whether there is a problem with the specifications of the image data (step S203). Specifically, the check server 10 checks whether the resolution, color, storage format, and image size of the image data match the pre-set requirements. If they do not match, the check server 10 temporarily stores the image data with the specification problem, the student ID of the image data, and the mismatched requirements as the specification check results in the storage unit 13.

[0065] The check server 10 also extracts a target value of shading intensity from the shading intensity DB 51 based on the identified student ID (step S204). The check server 10 uses a machine-learned detector to detect answer box areas from the image data (step S205). The check server 10 acquires the shading intensity of each detected answer box area and calculates the average value of the shading intensity of the entire answer box area. The check server 10 then sets the calculated average value as the current value of the shading intensity (step S206).

[0066] The check server 10 determines whether there is an abnormality in the shading of the scanned image displayed by the image data based on the extracted target value and the set current value (step S207). If it is determined that there is no abnormality in the shading (step S207; No), the check server 10 proceeds to the processing of step S210. On the other hand, if it is determined that there is an abnormality in the shading (step S207; Yes), an alert is output to the terminal device 20 (step S208). Then, the check server 10 corrects the shading of the scanned image determined to have an abnormality based on the image data of the scanned image determined to have an abnormality and the target value and current value corresponding to the image data (step S209). The shading correction unit 40 corrects the shading so that the scanned image reproduces each student's normal writing state, regardless of the state or settings of the scanner 1.

[0067] The check server 10 then determines whether the specification check and the shade check of the scanned image have been completed based on all the image data (step S210). If it is determined that there is image data for which the check has not yet been completed (step S210; No), the check server 10 returns to step S202 and performs processing based on the image data for which the check has not yet been completed. On the other hand, if it is determined that the check of all the image data has been completed (step S210; Yes), the check server 10 outputs the specification check result and the shade check result to the terminal device 20 (step S211). Then, the check server 10 transmits the image data of the scanned image determined to be normal to the terminal device 20. Furthermore, for the scanned image determined to be abnormal, the check server 10 transmits the corrected image data to the terminal device 20 (step S212). Specifically, the user downloads the image data from the check server 10 using the terminal device 20, and the image data and the corrected image data are transmitted from the check server 10 to the terminal device 20. This completes the check process.

[0068] The terminal device 20 may transmit the image data and corrected image data received from the check server 10 to a digital scoring system that performs automatic scoring processing. Since the check processing allows image data of scanned images that have no problems with shading to be transmitted to the digital scoring system, the digital scoring system can be used efficiently without rework.

[0069] The check system 100 of this embodiment performs optimal automatic shading correction on each student's scanned image when performing specification checks and shading checks, ensuring the shading obtained by normal scanning. This reduces the user's workload. It also makes it possible to efficiently obtain image data of scanned images that can be applied to a digital grading system.

[0070] <Modification> Next, modified examples will be described. The following modified examples can be applied to the embodiment in appropriate combinations.

[0071] (First Modification) In the above embodiment, the shading intensity DB 51 stores one target shading intensity value for each student, but the present invention is not limited to this. For example, multiple target values ​​may be stored for each type of content, such as for characters and non-character entries. A student's pen pressure and writing style may differ when writing characters and when writing graphs and other non-character entries. Therefore, this allows the check server 10 to use a target value according to the type of content, allowing for more appropriate shading correction of the scanned image.

[0072] (Second Modification) In the above embodiment, the target value registered in the shading intensity DB 51 by the target value registration process may be updated by the check server 10 by the check process. Specifically, the check server 10 sets a current value in the answer column by the check process and compares it with the target value to determine whether there is an abnormality in the shading of the scanned image. At this time, the check server 10 sets the current value corresponding to the scanned image determined to have no abnormality in shading as the new target value to be stored in the shading intensity DB 51. By updating the target value in this way, the check server 10 can use a target value that corresponds to the student's writing pressure and writing style, which change as the student grows, and can perform more appropriate shading correction of the scanned image.

[0073] (Third Modification) In the above embodiment, the check server 10 acquires the shading intensity of each answer box area detected from the image data and sets the average value of the entire answer box area as the current value. The check server 10 then determines whether there is an abnormality in the shading of the scanned image based on a target value extracted based on the student ID and a current value derived from multiple answer box areas. However, the present invention is not limited to this. The check server 10 may set the shading intensity of each answer box area to a current value and determine whether there is an abnormality in the shading of the scanned image for each answer box area based on the target value and the current value. This allows the check server 10 to determine which answer box area has an abnormality in shading, rather than the entire scanned image. In other words, it can determine whether there is an abnormality in shading not only in the entire scanned image but also in part of the scanned image. In this case, the check server 10 outputs an alert to the terminal device 20 even if there is an abnormality in shading in part of the scanned image. The check server 10 also outputs information about the answer box area with an abnormality in shading to the terminal device 20 as the shading check result.

[0074] (Fourth Modification) In the above embodiment, it is determined whether there is an abnormality in the shading of the scanned image, and the shading of the scanned image that has an abnormality is corrected, but the present invention is not limited to this, and the shading of all scanned images may be corrected based on the target value and the current value so as to reproduce each student's normal writing state.

[0075] (Fifth Modification) In the above embodiment, the user uses the terminal device 20, but the present invention is not limited to this, and the user may use a terminal device 20x that has the functions of the check server 10. The terminal device 20x is, like the check server 10, for example, a personal computer.

[0076] In this case, the terminal device 20x also executes the target value registration process and check process that were previously performed by the check server 10, and can register target values ​​in the shading intensity DB 51, and perform specification checks and shading corrections based on image data. Furthermore, like the terminal device 20, the terminal device 20x may transmit the image data and corrected image data received from the check server 10 to a digital scoring system that performs automatic scoring. The terminal device 20x is an example of an information processing device of the present invention. Furthermore, the image data transmission unit 42x included in the terminal device 20x is the image data transmission unit of the present invention. [Explanation of symbols]

[0077] 5. Network 10 Check Server 20, 20x terminal equipment 31 Target value registration section 32 Image data acquisition unit 33 Student ID Identification Unit 34 Specification Check Department 35 Target value extraction section 36 Area detection unit 37 Current value setting section 38 Abnormality determination section 39 Alert output section 40 Shade correction section 41 Result output section 42 Image data transmission unit 100 Check System

Claims

1. a storage unit that stores student identification information for identifying a student and a target value of shading intensity of an entry item entered by the student on the entry form in association with each other; an image data acquisition unit that acquires image data of an image obtained by scanning the form; a student identification information identification unit that identifies student identification information corresponding to the image data; a target value extraction unit that extracts the target value from the storage unit based on the identified student identification information; a current value setting unit that sets a current value of the shading intensity of the entry item based on the image data; an abnormality determination unit that determines, for each student, whether or not there is an abnormality in the shading of the image based on the target value and the current value; the form has a plurality of entry items, and an area detection unit detects all entry areas, which are areas of the entry items, from the image data; Equipped with The current value setting unit calculates an average value of the shading intensity of the entire writing area based on the shading intensity of each writing area, and sets the average value as the current value.

2. The information processing apparatus according to claim 1 , further comprising an alert output unit that outputs an alert when the abnormality determination unit determines that there is an abnormality in the shading of the image.

3. 3. The information processing device according to claim 1, further comprising a shading correction unit that, when the abnormality determination unit determines that there is an abnormality in the shading of the image, corrects the shading of the image based on image data of the image having the abnormality in shading and target values ​​and current values ​​corresponding to the image data.

4. The image data has a two-dimensional code including the student identification information, The information processing device according to claim 1 , wherein the student identification information specifying unit specifies the student identification information by reading a two-dimensional code included in the image data.

5. It is communicably connected to a scoring device that automatically scores the games, The form is an answer sheet on which the student writes answers to questions, The information processing device according to claim 3 , further comprising an image data transmission unit that transmits image data of the image whose shading has been corrected by the shading correction unit to the scoring device.

6. A program executed by an information processing device having a computer, a storage unit that stores student identification information for identifying a student and a target value of shading intensity of an entry item entered by the student on the entry form in association with each other; an image data acquisition unit that acquires image data of an image obtained by scanning the form; a student identification information identification unit that identifies student identification information corresponding to the image data; a target value extraction unit that extracts the target value from the storage unit based on the specified student identification information; a current value setting unit that sets a current value of the shading intensity of the entry item based on the image data; an abnormality determination unit that determines, for each student, whether or not there is an abnormality in the shading of the image based on the target value and the current value; the form has a plurality of entry items, and an area detection unit detects all entry areas, which are areas of the entry items, from the image data; causing the computer to function as The current value setting unit calculates an average value of the shading intensity of the entire writing area based on the shading intensity of each writing area, and sets the average value as the current value.

Images