JP5080872B2 - Scoring system and scoring program - Google Patents

Description

  The present invention relates to a scoring system and a scoring program.

In educational activities of school children (may include students, students, etc.), problem papers such as tests and prints used as teaching materials at educational sites are distributed to children in classrooms, etc. After completing the so-called scoring work, the teacher makes a correct / incorrect decision with a red pen, etc., and sums the scores of the correct answers, or the teacher fills the score on another sheet, or the score is calculated by the computer After being stored as electronic data in a (personal computer) etc., it is returned to the children.
The teacher sums up the score entered manually or inputs the score data into the score summing software on the computer, and uses it for the grade evaluation of the children. While performing this scoring work, teachers make a cycle to grasp the learning situation of children, etc., find problems of their own guidance, etc., and use them for the next guidance.
On the other hand, for children, etc., they look at the graded answer sheet returned from the teacher, check the correctness of their answers, and conduct learning activities to review the wrong understanding and knowledge correctly.
This scoring and counting work is a part of the teacher's basic and important educational activities, but the work itself is complicated and requires a lot of labor. Various efforts have been made.

  As a technology related to these, for example, Patent Document 1 has an issue of summing up the results at the same time as the entry work even if the entry work such as scoring is not performed and the data is not entered again by key entry or the like. The storage device defines a handwritten entry field on the answer sheet as an input area on the tablet, and also stores format data that defines the input area to be aggregated so that the answer sheet can be identified. In the state, the CPU captures the information entered in the handwritten entry field as handwritten data inputted in the input area of the tablet and recognizes the character. If this input area is defined in the format data as an aggregation target, the CPU It is disclosed that the aggregation process is performed based on the character recognition result.

  In addition, for example, in Patent Document 2, when scoring an answer that uses both a selective test and a descriptive test, the answer can be performed quickly, and a more accurate scoring process can be performed. An object of the present invention is to provide a scoring system, a reading means for reading an answer sheet, a selective answer storage means for storing answers to a selective test, and a selective expression for scoring the answer data stored in the selective answer storage means Test scoring means, scoring result storage means for storing the scoring results scored by the selective test scoring means, primary judgment criterion storage means for storing judgment criteria for narrowing down the scoring subjects of the descriptive test, and scoring results The scoring target for the descriptive test is determined from the scoring result of the selective test stored in the storage means and the judgment criteria stored in the primary judgment standard storage means, and the scoring target is stored in the scoring result storage means Answer scoring processing system comprising a primary determining means for storing is disclosed.

  Patent Document 3 aims to make it easy for anyone to automatically score answer sheets using a digital copying machine, and to effectively use memory to minimize cost increase. The image on the answer sheet is read by the image reading means, the image information is stored in the image storage means, the problem information extraction means extracts the image information of the problem from the image information and stores it in the problem information storage means, and the answer information extraction The means extracts the image information of the answer, stores it in the answer information storage means, compares the stored image information of the answer with the correct image information held by the correct answer information holding means by the scoring means, and the image information of the scoring result Then, the image information of the scoring results and the image information of questions and answers stored in the respective storage means are individually or arbitrarily combined by the drawing means. Draw Te, it is disclosed that is output by the image formed on the recording paper thereby image output unit.

  Also, in Patent Document 4, anyone can easily score an answer sheet using a digital copying machine, and be able to know immediately when a person forgets to score. For this purpose, the image of the answer sheet is read by the image reading means, the image information is stored in the image storage means, the answer recognition means recognizes the answer from the image information, and the scoring means scores the recognized answer Processing, the scoring result is stored in the scoring result storage means, and the scoring result output means forms an image on the recording paper together with the image of the answer sheet stored in the image storage means by the image output means, and outputs it. The discrimination information stored in the discrimination information storage means by the error presence / absence discrimination means is compared with the scoring results stored in the scoring result storage means to determine whether there is an error in the scoring results. And another, be notified to the user has been disclosed by the determination result notification means the rating result.

Further, Patent Document 5 makes it possible to save labor for scoring processing for educational materials, and does not require a dedicated component device for scoring processing, and also provides versatility for educational materials. A database means for storing and storing electronic data about educational materials, and a reading means for obtaining image data from educational materials filled with answers and correct / incorrect judgments, with the objective of ensuring sufficient security, Difference extracting means for comparing the electronic data and the image data to extract a difference, correct / wrong judgment recognizing means for recognizing the entry contents of the right / wrong judgment from the difference extraction result, and the educational material based on the recognition result It is disclosed that the teaching material processing apparatus is configured to include scoring and summing means for scoring and summarizing scoring for correctness / incorrectness entered in.
Japanese Patent Laid-Open No. 11-031046 JP 2004-029107 A JP 08-007076 A Japanese Patent Laid-Open No. 08-016085 JP 2006-235781 A

However, it is not necessarily preferable to require dedicated components such as a scoring table, a mark sheet reader, and a scoring pen in scoring processing for educational materials. This is because the dedicated component device can cause a complicated configuration of the entire system, an increase in cost, and the like. Moreover, if a dedicated component device is required, the educational materials that can be handled are limited, and the versatility of the educational materials may be limited.
On the other hand, in recent years, educational institutions have been equipped with personal computers, copiers or multifunction machines (also called multi-function copiers, which have functions such as scanners, printers, copiers, and fax machines). It is generally used.
In addition to scoring, in order to provide a higher-quality education, it is required to perform analysis by associating the answerer with the scoring results.
However, you can use a copier or multifunction device to relate the answerers to the scoring results, but you can use red pens, etc., on the answer sheet that you fill out directly on the multicolored question paper, such as elementary school test materials. In some cases, it was difficult to deal with the case where a judgment symbol such as XX was entered.
In addition, it is possible to respond to multi-colored printing problem papers with a determination symbol written with a red pen, etc., but when the determination symbol overlaps the image, multiple selection questions are answered or not answered Was difficult to deal with.

  Therefore, the present invention makes it possible to save labor in scoring a question sheet on which an answer is written by an answerer, and does not require a dedicated component device for the scoring process. It is an object to provide a scoring system and a scoring program that can be attached.

The gist of the present invention for achieving the object lies in the inventions of the following items.
[1] Image receiving means for receiving an image of the question sheet in which an answerer enters an answer for each question on a question sheet on which a question is printed in advance, and a grader enters a determination symbol regarding correctness in the answer for each question;
Corresponding to the image of the problem paper received by the image receiving means, original image receiving means for receiving an original image not filled in;
Extraction means for extracting the determination symbol based on the image received by the image receiving means and the original image received by the original image receiving means;
Shape recognition means for recognizing the shape of the determination symbol extracted by the extraction means;
Position calculating means for calculating the position of the determination symbol extracted by the extracting means;
Score calculation means for calculating a score based on the shape recognized by the shape recognition means and the position calculated by the position calculation means;
An answerer specifying means for specifying an answerer in the image received by the image receiving means;
An answerer information storage means for storing the answerer specified by the answerer specifying means and the score calculated by the score calculation means in association with each other;
In the case where the determination symbol to be recognized is related to a selection problem, the shape recognition means is configured such that the feature amount of the pixel surrounding the determination symbol or the feature amount of the pixel surrounding the selection question answer area is a predetermined condition. If you do not recognize the shape,
The scoring system characterized in that the scoring means calculates a score based on the position calculated by the position calculating means.
[2] Image receiving means for receiving an image of the question sheet in which an answerer enters an answer for each question on a question sheet on which a question is printed in advance, and a grader enters a determination symbol regarding correctness in the answer for each question;
Corresponding to the image of the problem paper received by the image receiving means, original image receiving means for receiving an original image not filled in;
Extraction means for extracting the determination symbol based on the image received by the image receiving means and the original image received by the original image receiving means;
Shape recognition means for recognizing the shape of the determination symbol extracted by the extraction means;
Position calculating means for calculating the position of the determination symbol extracted by the extracting means;
Score calculation means for calculating a score based on the shape recognized by the shape recognition means and the position calculated by the position calculation means;
An answerer specifying means for specifying an answerer in the image received by the image receiving means;
An answerer information storage means for storing the answerer specified by the answerer specifying means and the score calculated by the score calculation means in association with each other;
The extracting means extracts the answer based on the image received by the image receiving means and the original image received by the original image receiving means,
In the case where the determination symbol to be recognized is related to a selection problem, the shape recognition means is configured such that the feature amount of the pixel surrounding the determination symbol or the feature amount of the pixel surrounding the selection question answer area is a predetermined condition. If you do not recognize the shape,
The position calculating means calculates the position of the answer extracted by the extracting means,
The scoring system, wherein the scoring unit calculates a score based on the position of the answer calculated by the position calculating unit.

[ 3 ] The image storage means for storing the image received by the image receiving means in association with the answerer specified by the answerer specifying means, further comprising [1] or [2] Scoring system.

[ 4 ] A correction unit that displays an image stored in the image storage unit and corrects a score stored in the answerer information storage unit related to the image according to an operation of the operator. The scoring system according to [ 3 ], wherein

[5] A grader specifying means for specifying a grader is provided,
The said shape recognition means recognizes the shape of a judgment symbol according to the judgment symbol filled in for every grader, The [1], [2], [3] or [4] Scoring system.

[ 6 ] The scoring system according to [ 3 ], wherein when the problem paper is a plurality of sheets or double-sided printing, the image storage unit stores the plurality of or double-sided problem paper images in association with each other.

[ 7 ] The scoring system according to [1] or [2] , wherein the answerer information storage unit stores a score for each question calculated by the score calculation unit.

[8] above, wherein the weight is that the density or brightness, said the predetermined condition, characterized in that the concentration or the brightness of the determination symbol is equal to or larger than the value of performing a predetermined operation [1] or [2 ] The scoring system described in the above.

[ 9 ] The scoring system according to [ 1 ] or [ 2 ], wherein the characteristic amount is density or lightness, and the predetermined condition is a predetermined density or lightness or more .

[ 10 ] The feature amount is a color, and the predetermined condition is that a color of a pixel of the determination symbol is approximate to a color of a pixel around the determination symbol or the selection question answer area. The scoring system according to [ 1 ] or [ 2 ].

[ 11 ] The scoring system according to [ 1 ] or [ 2 ], wherein the feature amount is a color, and the predetermined condition is an approximation to a predetermined color.

[12] A computer having a storage device,
An image receiving means for receiving an image of the question sheet in which an answerer enters an answer for each question on a question sheet on which a question is printed in advance, and a grader enters a determination symbol regarding correctness in the answer for each question;
Corresponding to the image of the problem paper received by the image receiving means, original image receiving means for receiving an original image not filled in;
Extraction means for extracting the determination symbol based on the image received by the image receiving means and the original image received by the original image receiving means;
Shape recognition means for recognizing the shape of the determination symbol extracted by the extraction means;
Position calculating means for calculating the position of the determination symbol extracted by the extracting means;
Score calculation means for calculating a score based on the shape recognized by the shape recognition means and the position calculated by the position calculation means;
An answerer specifying means for specifying an answerer in the image received by the image receiving means;
An answerer specified by the answerer specifying means and a score calculated by the score calculating means in association with each other and functioning as an answerer information storage means for storing in the storage device;
In the case where the determination symbol to be recognized is related to a selection problem, the shape recognition means is configured such that the feature amount of the pixel surrounding the determination symbol or the feature amount of the pixel surrounding the selection question answer area is a predetermined condition. If you do not recognize the shape,
The scoring program, wherein the scoring unit calculates a score based on the position calculated by the position calculating unit.
[13] A computer having a storage device,
An image receiving means for receiving an image of the question sheet in which an answerer enters an answer for each question on a question sheet on which a question is printed in advance, and a grader enters a determination symbol regarding correctness in the answer for each question;
Corresponding to the image of the problem paper received by the image receiving means, original image receiving means for receiving an original image not filled in;
Extraction means for extracting the determination symbol based on the image received by the image receiving means and the original image received by the original image receiving means;
Shape recognition means for recognizing the shape of the determination symbol extracted by the extraction means;
Position calculating means for calculating the position of the determination symbol extracted by the extracting means;
Score calculation means for calculating a score based on the shape recognized by the shape recognition means and the position calculated by the position calculation means;
An answerer specifying means for specifying an answerer in the image received by the image receiving means;
The answerer specified by the answerer specifying means and the score calculated by the score calculating means are associated with each other and stored in the storage device to function as answerer information storage means,
The extracting means extracts the answer based on the image received by the image receiving means and the original image received by the original image receiving means,
In the case where the determination symbol to be recognized is related to a selection problem, the shape recognition means is configured such that the feature amount of the pixel surrounding the determination symbol or the feature amount of the pixel surrounding the selection question answer area is a predetermined condition. If you do not recognize the shape,
The position calculating means calculates the position of the answer extracted by the extracting means,
The scoring program, wherein the scoring unit calculates a score based on the position of the answer calculated by the position calculating unit.

In the scoring system according to claim 1, as compared with the case where this configuration is not provided, work efficiency is improved without degrading the quality of the scoring action of describing the judgment symbol of the teacher in the conventional educational activity. Can be achieved. For example, even if a color image or the like is used for the problem paper and the determination symbols for scoring overlap, scoring accuracy can be improved.
In the scoring system according to claim 2, the work efficiency is improved without degrading the quality of the scoring action of describing the judgment symbol of the teacher in the conventional educational activity, as compared with the case where this configuration is not provided. Can be achieved. It is possible to deal with exceptions when multiple answers are made to the selected question or when no answer is given.

In the scoring system according to the third aspect , in addition to the effects of the scoring system according to the first or second aspect , it is possible to view the past answer contents by the answerer. This makes it possible, for example, to check the cause of the calculation of arithmetic at the elementary school stage, not only by numerical data, but to go back to the previous description with the contents of the specific answer. Can be useful.

In the scoring system according to claim 4 , in addition to the effect of the scoring system according to claim 3 , even when this scoring system is used, a scoring error can be corrected and efficiency can be improved. Can do.

In the scoring system according to claim 5 , in addition to the effects of the scoring system according to claim 1, 2 , 3 or 4 , the scoring person can set in advance a score when entering a judgment symbol. It is possible to adapt to specific scenes of educational activities and improve the accuracy of recognition of correct / incorrect information.

In the scoring system according to claim 6 , in addition to the effect of the scoring system according to claim 3 , scoring processing by the scoring system is possible even when the problem paper is a plurality of sheets or double-sided printing. .

In the scoring system according to the seventh aspect , in addition to the effect of the scoring system according to the first or second aspect , the score for each problem is stored, so that detailed guidance is possible at the educational site.

In the scoring system according to the eighth to eleventh aspects , for example, a color image or the like is used for the problem paper, and the scoring accuracy can be improved even if the determination symbols for scoring overlap. It is possible to deal with exceptions when multiple answers are made to the selected question or when no answer is given.

In the scoring program according to claim 12 , the work efficiency can be improved without degrading the quality of the scoring action of describing the judgment symbol of the teacher in the conventional educational activity, as compared with the case where this configuration is not provided. Can be achieved. For example, even if a color image or the like is used for the problem paper and the determination symbols for scoring overlap, scoring accuracy can be improved.
In the scoring program according to claim 13, the work efficiency can be improved without degrading the quality of the scoring act of describing the judgment symbol of the teacher in the conventional educational activity, as compared with the case where this configuration is not provided. Can be achieved. It is possible to deal with exceptions when multiple answers are made to the selected question or when no answer is given.

Hereinafter, a preferred embodiment of the present invention will be described with reference to the drawings.
FIG. 1 is a conceptual module configuration diagram of an embodiment of the present invention.
The module generally refers to a component such as software or hardware that can be logically separated. Therefore, the module in the present embodiment indicates not only a module in a program but also a module in a hardware configuration. Therefore, the present embodiment also serves as an explanation of a program, a system, and a method. In addition, the modules correspond almost one-to-one with the functions. However, in mounting, one module may be composed of one program, or a plurality of modules may be composed of one program. A plurality of programs may be used. The plurality of modules may be executed by one computer, or one module may be executed by a plurality of computers in a distributed or parallel environment. In the following, “connection” includes not only physical connection but also logical connection (data exchange, instruction, etc.).
The system includes a configuration in which a plurality of computers, hardware, devices, and the like are connected by communication means such as a network, and also includes a case where the system is realized by a single computer, hardware, devices, and the like.
Hereinafter, a description will be given mainly by exemplifying a teacher as a grader and a child (may be a student, student, etc.) as an answerer.

  In this embodiment, an answer sheet used for a test is graded at an educational institution such as an elementary school. As shown in FIG. 1, an image input module 103, an original image acquisition module 104, an answer image / question Information DB 105, determination symbol extraction module 106, determination symbol recognition module 107, determination symbol position calculation module 108, score calculation module 109, answerer identification module 110, score information storage module 111, score result confirmation / correction module 112, answer image DB 113 The student / score information DB 114 is provided.

As shown in FIG. 1, the image input module 103 is connected to the answer image DB 113, the answerer identification module 110, the determination symbol extraction module 106, and the original image acquisition module 104, and forms the original 101 or correct / incorrect Checked answer sheet 102. Are read as color (at least red can be identified) image data. The original 101 is a question sheet on which a question is printed in advance, and an answer has not yet been entered. The correct / incorrect Checked Answer 102 is filled with answers by the students, etc., and the teacher uses a red pen etc. to answer each question with a correct / incorrect judgment symbol (correct answer: ○, error: ×, intermediate between correct: △) This is a written answer (question sheet). The image data of the original 101 is transferred to the original image acquisition module 104, and the image data of the correct / incorrect Checked answer 102 is transferred to the answer image DB 113, the answerer specifying module 110, and the determination symbol extracting module 106.
The image input module 103 may accept image data from an external device via a communication line, for example, in addition to a function as a scanner that accepts the original 101 or the paper 102 of the correct / incorrect checked answer as image data. Image data may be received from a storage device such as an image database.

  As shown in FIG. 1, the original image acquisition module 104 is connected to an image input module 103, a determination symbol extraction module 106, and an answer image / question information DB 105, and correct / incorrect Checked answer 102 input by the image input module 103. Corresponding to the above, the original 101 is acquired. That is, the original 101 is acquired in correspondence with the correct / incorrect Checked answer 102.

  As shown in FIG. 1, the answer image / question information DB 105 is connected to the original image acquisition module 104 and the score calculation module 109, and stores image data of the original 101 acquired by the original image acquisition module 104. Information regarding the problem paper is also stored and accessed from the score calculation module 109. Information regarding the problem paper will be described later with reference to FIG.

As illustrated in FIG. 1, the determination symbol extraction module 106 is connected to the image input module 103, the original image acquisition module 104, the determination symbol recognition module 107, and the determination symbol position calculation module 108, and is input by the image input module 103. The determination symbol is extracted based on the obtained image and the original image acquired by the original image acquisition module 104. That is, the difference between the image data of the original 101 and the image data of the correct / incorrect Checked answer 102 is taken. Specifically, a difference image is obtained by performing an EOR (exclusive OR) operation of both image data. The difference image here includes an answer entered by a child or the like and a determination symbol entered by a teacher. Since the answer written by the child or the like is written with a black pencil and the determination symbol written by the teacher is written with a red pen, only the pixels written in red need be extracted from the difference image. The extraction result (red pixel in the difference image) is passed to the determination symbol recognition module 107 and the determination symbol position calculation module 108.
Alternatively, only pixels written in black (answers entered by children or the like) may be extracted from the difference image. The extraction result (black pixel in the difference image) is passed to the determination symbol position calculation module 108.

As shown in FIG. 1, the determination symbol recognition module 107 is connected to the determination symbol extraction module 106 and the score calculation module 109, and recognizes the shape of the determination symbol from the image extracted by the determination symbol extraction module 106. That is, it is recognized whether the determination symbol is “◯”, “×”, or “Δ”. The recognition result is passed to the score calculation module 109. Further, the determination symbol recognition module 107 may identify a teacher who is a grader, and recognize the shape of the determination symbol according to the determination symbol to be entered for each teacher. That is, depending on the teacher, to indicate an error, a check symbol such as “L” is used instead of “X” or a diagonal line such as “/” is used. The meaning (correct answer, error, intermediate) is stored for each teacher, and can be used for recognition of the determination symbol.
In addition, the determination symbol recognition module 107 recognizes the shape if the determination symbol to be recognized is for a selection question, and if the feature amount of pixels around the determination symbol or the selection question answer area is a predetermined condition. May not be performed.

As shown in FIG. 1, the determination symbol position calculation module 108 is connected to the determination symbol extraction module 106 and the score calculation module 109, and calculates the position of the determination symbol from the image extracted by the determination symbol extraction module 106. That is, the position (coordinate value) where the determination symbol is located in the image data of the correct / incorrect Checked answer 102 is calculated. The calculation result is passed to the score calculation module 109.
The determination symbol position calculation module 108 may calculate the position of the answer from the image from which the answer is extracted by the determination symbol extraction module 106. Then, the calculation result is passed to the score calculation module 109.

As shown in FIG. 1, the score calculation module 109 is connected to the determination symbol recognition module 107, the determination symbol position calculation module 108, the answer image / question information DB 105, and the score information storage module 111. Based on the recognition result, the position calculation result by the determination symbol position calculation module 108, and the score for each question stored in the answer image / question information DB 105, the score of the correct / wrong checked answer 102 is calculated. To do.
When the determination symbol recognition module 107 does not recognize the shape, the score calculation module 109 calculates a score based on the position of the determination symbol calculated by the determination symbol position calculation module 108. Also good.
Further, the score calculation module 109 may calculate the score based on the position of the answer calculated by the determination symbol position calculation module 108.

  As shown in FIG. 1, the answerer identification module 110 is connected to the image input module 103 and the score information storage module 111, and identifies a child who is an answerer in the image data input by the image input module 103. . Here, you may make it recognize the character in the name column in the correct / incorrect Checked answer 102. Further, the correct / incorrect Checked answers 102 may be input in the order of attendance numbers, and the children and the like may be specified in the input order.

  As shown in FIG. 1, the score information storage module 111 is connected to the answerer identification module 110, the score calculation module 109, and the student / score information DB 114, and calculates scores with the students identified by the answerer identification module 110. The score calculated by the module 109 is associated and stored in the student / score information DB 114. The score information storage module 111 may calculate a score for each problem.

  As shown in FIG. 1, the answer image DB 113 is connected to the image input module 103 and the score result confirmation / correction module 112, and stores image data input by the image input module 103. Further, it may be stored in association with the child specified by the answerer specifying module 110. Further, when a plurality of question papers are printed on both sides or on both sides, the answer image DB 113 may store the plurality of or both sides of the question paper images in association with each other. That is, in the case of problem papers composed of a plurality of pages, they are associated with each other in the order of pages, and scoring is performed in order for each page.

  As shown in FIG. 1, the score result confirmation / correction module 112 is connected to the answer image DB 113 and the student / score information DB 114, and displays image data of the correct / incorrect Checked answer 102 stored in the answer image DB 113. The score displayed on the apparatus and stored in the student / score information DB 114 related to the image data is corrected according to the operation of the operator. In other words, the recognition of the determination symbol by the determination symbol recognition module 107 may cause erroneous recognition, and the erroneous recognition is corrected.

  As shown in FIG. 1, the student / score information DB 114 is connected to the score result confirmation / correction module 112 and the score information storage module 111, and stores the score calculated by the score information storage module 111. Further, the score corrected by the score result confirmation / correction module 112 is stored. Moreover, the score to memorize | store may be a score for every problem as well as a total score.

A configuration example of the entire system when realizing the present embodiment will be described with reference to FIG.
A typical system configuration for realizing the present embodiment includes a scanner 201, a scoring server 202, a client 203, a scoring result storage server 204, and these are connected by a network (communication path) 205. They can communicate with each other.
The scanner 201 has an image input module 103, and the scoring server 202 has an original image acquisition module 104, a determination symbol extraction module 106, a determination symbol recognition module 107, a determination symbol position calculation module 108, a score calculation module 109, and an answerer identification module 110. The score information storage module 111, the client 203 has the score result confirmation / correction module 112, and the score result storage server 204 has the answer image / question information DB 105, the answer image DB 113, and the student / score information DB 114. ing.

The scanner 201 inputs the original 101 or the erratic checked answer 102 and transmits the image data to the scoring server 202 or the scoring result storage server 204.
The scoring server 202 performs the scoring process based on the image data received from the scanner 201. The result is transmitted to the scoring result storage server 204.
The client 203 confirms and corrects the scoring result (score etc.) stored in the scoring result storage server 204 in accordance with the operation of the operator.

  Which server has which module is arbitrary, for example, the scanner 201 may have all the modules shown in FIG. 1, or a plurality of scoring servers 202 share each module. May be.

The original sheet 101 of the problem paper will be described using a specific example shown in FIG.
The original 101 shown in FIG. 3 is an example of a science question sheet for fifth graders in elementary school, and the answer has not yet been entered by a child or the like. Specifically, this includes paper tests and practice question sheets used in educational institutions.
The original 101 includes an identification information field 301 in which the title of the question paper is written, an answerer information field 302 in which the class, attendance number, name, etc. of the child who is the answerer are written, and after the scoring is completed A score column 303 in which the score of the student or the like is entered by the teacher who is a grader, a problem description area 304 in which a question sentence is described, and a selection question (problem to select one from a plurality of options) In this case, there is an option area 305 and an answer description column 306 for answering as a sentence.
The selection area 305 includes, for example, a selection of a color photograph 305A as in a science problem, and a selection column 305B, which is a column for entering a symbol representing the selection, is included in each color photograph 305A as an option. is there.

  The identification information column 301 of the original 101 is preliminarily described with information for identifying and specifying the original 101, for example, a subject, an applied grade, a title, etc. of the original 101. However, in addition to these descriptions, or separately from these descriptions, code information for identifying the original 101 may be embedded. The embedding of the code information may be realized using a publicly known technique. As one specific example thereof, for example, a line screen or a dot screen as a gradation expression such as what is called “iTone (registered trademark)”. It is also possible to use a technique of embedding digital information in a halftone image by changing the form (position, shape, etc.) of the pixels constituting the.

An example of the missing line segment interpolation process performed by the determination symbol recognition module 107 will be described using the flowchart shown in FIG. 4 and the specific example shown in FIG.
In addition to the original 101 described with reference to FIG. 3, an answer written by a child or the like and a determination symbol written by a teacher are added to the correct / incorrect Checked answer 102. These additional notes are handwritten.
Since the determination symbol written by the teacher is handwritten, for example, as shown in FIG. 5, the determination symbol (◯) 501 indicating the correct answer may also be separated like an end point 503 and an end point 504. In general, it cannot be recognized as “◯”. Therefore, a missing line segment interpolation process as shown in the flowchart of FIG. 4 is performed.

In step S402, the determination symbol recognition module 107 thins the red pen image. This thinning process uses an existing method. For example, the red pen pixel that is the target pixel may be narrowed and continued until it becomes one pixel evenly from the four directions.
In step S404, end point processing is performed on the thinned image (determination symbol image). For example, as shown in FIG. 5, the end points 503 and 504 of the determination symbol (◯) 501 are extracted. This end point processing uses an existing method. For example, a point where there is no connected pixel may be used as an end point other than proceeding along a thinned image having one pixel and returning.
In step S406, it is determined whether or not the connection process has been completed for all end points extracted in step S404. If it has been completed (Y in step S406), it ends (step S420). If not completed (N in step S406), the process proceeds to step S408.
In step S408, one end point (unprocessed end point 1) for which the missing line segment interpolation processing has not been completed is selected.

In step S410, one end point (unprocessed end point 2) near the unprocessed end point 1 selected in step S408 is selected. In this case, the end point closest to the unprocessed end point 1 is selected, but other methods, for example, an end point on the extension of the line segment connected to the unprocessed end point 1 may be selected.
In step S412, it is determined whether or not the unprocessed endpoint 1 selected in step S408 and the unprocessed endpoint 2 selected in step S410 are corresponding endpoints. If it is the corresponding end point (Yes in step S412), the process proceeds to step S414. If it is not the corresponding end point (No in step S412), the process proceeds to step S418. Whether or not it is a corresponding end point is determined based on, for example, whether or not the distance between the end points is within a threshold value.
In step S414, the unprocessed endpoint 1 selected in step S408 and the unprocessed endpoint 2 selected in step S410 are connected to each other.
In step S416, the unprocessed endpoint 1 and the unprocessed endpoint 2 are processed. The process returns to step S406.
In step S418, the unprocessed end point 1 is processed. The process returns to step S406.

  For example, when the graphic shown in FIG. 5 is extracted by this missing line segment interpolation processing, even if the end point 504 and the end point 505 exist within a predetermined distance with respect to the end point 503, the nearest neighbor among them is present. The end point 504 is connected to the end point 503, and the discontinuity portion in the figure “◯” is corrected.

  An overall processing example according to the present embodiment will be described with reference to the flowchart shown in FIG. The thin solid line in the flowchart indicates the flow of the original 101 sheet or image data, the thick solid line indicates the correct or incorrect checked answer sheet 102 or image data flow, the double line indicates the processed image data flow, The dotted line shows the flow of data.

In step S601, the image input module 103 inputs the image data of the original 101 or the correct / incorrect check answer 102. Next, the image data of the original 101 is transferred to the processes of steps S602 and S604, and the image data of the right / wrong checked answer 102 is transferred to the process of step S604.
In step S <b> 602, the original image acquisition module 104 specifies the image data of the original 101 corresponding to the image data of the correct / incorrect Checked answer 102. Here, the positions of the identification information column 301, the answerer information column 302, the score column 303, the question description region 304, the option region 305, and the answer description column 306 are determined from the image data of the original 101 according to the operation of the operator. specify. Furthermore, the score (score) of each question is also specified here. Further, the position of the identification information column 301 or the like may be extracted by analyzing the image data of the original 101 without depending on the operation of the operator. Image data analysis includes layout analysis, character / graphic separation, character recognition, code information recognition, graphic processing, color component recognition, and the like. Next, the image data of the original 101 and the processing result (the position of the answerer information field 302, the position of the selection field 305B of the option area 305, the score of each question, etc.) are passed to step S603.
In step S603, the image data of the original 101 input in step S601 and the processing result in step S602 are stored. Next, the image data of the original 101 is transferred to step S604, the score and answer position information of the processing result of step S602 are transferred to step S610, and the attendance number position information (position information of the answerer information column 302) is transferred to step S611. hand over.

The processing from step S604 to step S609 is performed by the determination symbol extraction module 106, the determination symbol recognition module 107, and the determination symbol position calculation module 108.
In step S604, the position distortion is corrected for the image data of the original 101 and the image data of the correct / incorrect Checked answer 102. Examples of image distortion correction include tilt correction and enlargement / reduction correction in the main scanning direction or sub-scanning direction. The correction of image distortion is to reduce the difference in step S605 as much as possible, that is, to make it possible to extract only the answer entry of a child or the like and the judgment symbol of the teacher. Next, the image data of the original 101 is transferred to step S605, and the image data of the right / wrong checked answer 102 is transferred to steps S605 and S613.
In step S605, the original 101 after the image distortion correction processing in step S604 is compared with the correct / incorrect Checked answer 102, and a difference between them is extracted. That is, here, the question sentence in the question description area 304 or the like is deleted, and image data in which only the answer entry of the child or the like and the teacher's determination symbol remain is generated. Next, the difference image data is transferred to step S606 and step S611.
In step S606, pixels of a predetermined color (that is, red of the red pen) are extracted. That is, here, image data in which only the teacher's determination symbol remains is generated. Next, the processed image is transferred to step S607.

In step S607, a missing line segment interpolation process is performed on the image data in which only the teacher's determination symbol remains. That is, the processing described with reference to FIGS. 4 and 5 is performed. Next, the processing result image data is passed to step S608.
In step S608, the determination symbol that has been in contact with step S607 is separated. For example, since the answer columns are close to each other, there may be a case where a determination symbol written by the teacher is in contact with each other. This process is performed so as to identify a portion with two line segments and separate them so that the image is closer to the determination symbol. However, the present invention is not limited to this, and an existing technique may be used. . Next, the processed image is passed to step S609.
In step S609, the shape of the determination symbol is recognized to recognize the entry contents of the correctness determination. The shape recognition may be performed, for example, by pattern matching with a graphic shape of “◯”, “Δ”, or “×”. That is, the determination symbol recognition module 107 recognizes the contents of the determination symbol as “correct answer (◯)”, “intermediate (Δ)”, or “incorrect answer (×)”. Alternatively, the feature amount of a determination symbol that is a recognition target figure may be calculated, and the shape may be recognized from the feature amount. Examples of the feature amount include the number of holes and the area ratio of the target graphic occupying the circumscribed rectangle. The determination symbol position calculation module 108 recognizes the entry position on the correct / incorrect Checked answer 102 for the determination symbol whose shape is recognized by the determination symbol recognition module 107. The recognition of the entry position may be performed, for example, by coordinate analysis on the correct / incorrect Checked answer 102. Next, the determination symbol position and shape recognition results are passed to step S610.

In step S610, the score calculation module 109 determines whether the correct / incorrect Checked answer 102 is based on the scoring and answer position information that is the processing result in step S603, the position of the determination symbol that is the processing result in step S609, and the shape recognition result. The score for each of the questions (total of “○” and “△” points) is calculated. Next, the calculated score is passed to step S612.
In step S611, the answerer identification module 110 identifies the child who is the answerer based on the position information of the attendance number that is the processing result in step S603 and the difference image data that is the processing result in step S605. That is, the answerer information in the correct / incorrect Checked answer 102 is extracted through character recognition processing for the image in the difference image data at the attendance number position. As a result, it is possible to specify the class, attendance number, name, etc. of the answer entry person who entered the answer in one correct / incorrect Checked answer 102. Next, the answerer information as the processing result is passed to step S612.
In step S612, the scoring of the judgment symbols entered in the right / wrong checked answer 102 is performed. Then, the answerer and the score are related to all of the correct / incorrect Checked answers 102 in the class. Next, the counting result is passed to step S614.

In step S613, the answer image DB 113 stores the image data of the correct / wrong checked answer 102 in which the positional distortion is corrected in step S604. Then, it is associated with the database stored in step S614.
In step S614, the student / score information DB 114 stores the aggregation result, which is the processing result in step S612, in association with the image data of the correct / wrong checked answer 102 stored in step S613.
In step S615, the scoring result confirmation / correction module 112 displays to the operator the scoring result stored in association with the image data of the correct / wrong checked answer 102 in step S614, and allows the operator to confirm the scoring result. Correction is performed according to the correction instruction of the person in charge.
In step S616, the final score and the like are managed, the average score in the class is calculated, and subsequent grade management is performed.

In step S606, black pixels may be extracted as the predetermined color. That is, image data in which only the answers of children and the like remain may be generated.
In that case, in step S610, a score may be calculated based on the position of the answer calculated by the determination symbol position calculation module 108.

A more detailed configuration example of the present embodiment will be described with reference to FIG. The module configuration shown in FIG. 7 is a more detailed version of the determination symbol extraction module 106, the determination symbol recognition module 107, the determination symbol position calculation module 108, and the score calculation module 109 shown in FIG. 1, or functions described below. It consists of modules to be implemented.
The positional distortion correction module 701 is a module that performs the process of step S604 described with reference to FIG.
The difference extraction module 702 is a module that performs the process of step S605 described with reference to FIG.
The predetermined color pixel extraction module 703 is a module that performs the process of step S606 described with reference to FIG.
The missing line segment interpolation module 704 is a module that performs the process of step S607 described in FIG.
The error processing module 705 is a module that performs scoring processing for a selection question, particularly exception processing specific to the selection question, and mainly performs processing in cooperation with the determination method determination module 708 and the selection question correctness determination module 709. Do. Details will be described below.
The additional write position acquisition module 706 is equivalent to the determination symbol position calculation module 108, and is a module that performs the position acquisition process of step S609 described with reference to FIG.
The postscript corresponding question specifying module 707 is a module that performs the process of step S603 described with reference to FIG.
The determination method determination module 708 is a module that changes the determination method according to whether or not there is a selection problem. That is, a determination method suitable for the scoring process for the selection problem is determined. Details will be described below.
The selection question correct / incorrect determination module 709 is a module that calculates correctness, that is, a score, when scoring the selected question. Details will be described below.
The shape recognition module 710 is equivalent to the determination symbol recognition module 107, and is a module that performs the shape recognition processing in step S609 described with reference to FIG.
The scoring module 711 is a module that performs the process of step S610 described in FIG.
The aggregation module 712 is a module that performs the process of step S612 described with reference to FIG.

The answer column position area information table 800 necessary for the scoring process will be described with reference to FIG. The answer column position area information table 800 is stored in the answer image / question information DB 105 and relates to the answer position information stored in step S603 described with reference to FIG.
The answer column position area information table 800 has a table structure including a question number column 801, an answer column information column 802, a scoring column 803, a selected question correspondence flag column 804, and a correct answer column information column 805.
The question number column 801 is a column that stores the number of the question of the correct / wrong checked answer 102.
The answer column information column 802 is a column that stores coordinates indicating the position where the answer column is provided in the correct / incorrect Checked answer 102. The X coordinate column 8021 that stores the X coordinate of the upper left corner stores the Y coordinate. A Y coordinate field 8022, a height field 8023 for storing the height of the answer field, and a width field 8024 for storing the width of the answer field are provided.
The score column 803 is a column for storing the score of the question.
The selection question correspondence flag column 804 is a column for storing a code indicating whether or not the question is a selection question. If it is a selection problem, “ON” is entered, and if it is not a selection problem, “OFF” is entered.
The correct answer column information column 805 is a column that stores coordinates indicating the position of the column in which the question is a selection question and the correct answer is entered, and an X coordinate column 8051 that stores the X coordinate of the upper left corner of the correct answer column. Y coordinate column 8052 for storing coordinates, height column 8053 for storing the height of correct column, and width column 8054 for storing the width of correct column. If the question is not a selection question, the coordinate value is not stored and NULL (null) is entered.

An example of the determination symbol extraction result and the recognition result (misrecognition) in the case of a selection problem will be described with reference to FIG.
As for the selection problem, each option consists of a color photograph 305A and a selection field 305B, as in the option area 305 shown in FIG. For example, in a science issue, the question “Choose the state of summer change”, and as an option, color photo 305A such as “Who is active” or “Hibernate” is displayed. Some have a selection field 305B at the lower right corner.
If the entry of the determination symbol by the color photograph and the red pen overlaps, it is difficult to extract the determination symbol, and as a result, the determination symbol is erroneously recognized.
For example, as shown in FIG. 9 (1A), the determination symbol by the red pen is “◯”, but the image from which the determination symbol is extracted becomes an irregular figure as shown in FIG. 9 (1B). The recognition result by the module 107 is “Δ”. Similarly, as shown in FIG. 9 (2A), FIG. 9 (3A), and FIG. 9 (4A), when the red pen and the color photograph overlap, the extraction of the determination symbol is the original round. In many cases, it is recognized as “Δ” or “x” without being shaped.

With reference to the flowchart shown in FIG. 10, a processing example (processing example for a selection problem) of the selection problem correctness determination module 709 for solving the problem described with reference to FIG. 9 will be mainly described.
In step S1001, the coordinates of the correct answer column of the selected question are stored in the correct answer column information column 805 of the answer column position area information table 800. For this purpose, in step S602 described with reference to FIG. 6, the operator selects the correct answer field coordinates (selection field 305B) of the selected question to obtain the correct answer field coordinate values.
In step S1002, “ON” indicating a selection question is stored in the selection question response flag column 804 of the answer column position area information table 800. For this purpose, a selection problem is designated in accordance with the operation by the operator in step S602 described with reference to FIG.
In step S1003, the determination symbol recognition module 107 determines that the determination symbol to be recognized is for a selection question (that is, the selection question corresponding flag column 804 of the answer column position area information table 800 is “ON”). If the feature amount of the pixel around the determination symbol or the answer column is a predetermined condition (that is, the option is a color image), the shape is not recognized. That is, only the position of the determination symbol by the determination symbol position calculation module 108 is extracted.
Here, with reference to FIG. 14, when the feature amount is a density, a process for extracting the density of pixels around the answer column will be described. When the selection field 1401B of the option 1401 is specified as a correct answer field by the selection question corresponding flag field 804 and the correct answer field information field 805 of the answer field position area information table 800, a survey area that is a constant width area around the selection field 1401B The density of 1402 pixels is examined. If there are more than a certain area of pixels with a red pen density or more in the survey area 1402, it is determined that there is a color image near the determination symbol.

In step S1004, the score calculation module 109 determines whether there is an entry in the correct answer column. If there is an entry in the correct answer column, the process proceeds to step S1005, and if there is no entry, the process proceeds to step S1006. That is, the score calculation module 109 determines the meaning of the determination symbol based on the position calculated by the determination symbol position calculation module 108.
In step S1005, it is determined that the determination symbol is “◯”, and the score calculation module 109 calculates the score.
In step S1006, it is determined that the determination symbol is “x”, and the score calculation module 109 sets the score to 0.

Furthermore, an incorrect scoring process may be performed for the selection problem. This will be specifically described with reference to FIGS. 11, 12, and 13.
FIG. 11 shows a case in which a child or the like answers a plurality of answer columns (selection column 1101B, selection column 1104B) in spite of the problem of selecting one. In that case, the teacher may attach each determination symbol to each answer column (“×” in the selection column 1101B and “◯” in the selection column 1104B). In this case, in this selection problem, although it is 0 points, a score is given.
FIG. 12 is an example in which a child or the like did not answer the selection question. In this case, the teacher may enter “x” in the correct answer column. Also in this case, a score is given when the processing shown in FIG. 10 is performed.
In FIG. 13, the teacher enters a determination symbol “◯” (selection field 1302 </ b> B) for the selected question, and also enters a determination symbol (“◯”) for other problems in the vicinity thereof, and the determination is made. This is an example in which the symbols are in contact with each other. In this case, if a determination symbol for an answer to a question other than the selection question (“◯” positioned below in FIG. 13) is preferentially extracted, it is determined that there is no determination symbol for the selection question. In some cases, a score may not be given in spite of being “◯”.

In order to handle such a case, the determination symbol extraction module 106 extracts not only the determination symbol but also the answer based on the original 101 and the correct / incorrect check answer 102, and the determination symbol recognition module 107 The determination symbol position calculation module 108 does not perform shape recognition if, for example, the density of pixels around the determination symbol is equal to or higher than the concentration of the determination symbol. Then, the position of the answer of the extracted selection question is calculated, and the score calculation module 109 calculates the score based on the calculated position of the answer. In other words, when it is a selection problem and it is expected that recognition of the judgment symbol is very difficult (when there is a color image around it), it is not the judgment symbol that the teacher entered with the red pen, but the child's etc. You may make it judge correctness by the position of an answer. Or you may make it judge correctness by the position of the determination symbol, without recognizing the shape of the determination symbol.
That is, if the determination symbol to be recognized is for a selection problem, if the feature amount of the pixel around the determination symbol or the feature amount of the pixel around the answer area of the selection question is a predetermined condition, the shape Without recognition, the correctness is judged by the position of the answer written by the child or the judgment symbol. The feature amount here is a density or brightness, and the predetermined condition is a value equal to or higher than a value obtained by performing a predetermined calculation (for example, a calculation by multiplying a predetermined value) on the density or brightness of the determination symbol. Alternatively, the feature amount here is density or brightness, and the predetermined condition is that the density or brightness of the determination symbol is greater than or equal to a predetermined value. Alternatively, the feature amount here is a color, and the predetermined condition is that the color of the pixel of the determination symbol and the color of the pixels around the determination symbol or the selection question answer area are approximate. Alternatively, the feature amount here is a color, and the predetermined condition is that it approximates a predetermined color.

An example of processing for a selection problem will be described using the flowcharts shown in FIGS. The flowchart shown in FIG. 15 is a case where information in the answer column position area information table 800 is used, and the flowchart shown in FIG. 16 is a case where the determination symbol recognition module 107 is used.
First, the processing shown in FIG. 15 will be described.
In step S1502, the determination symbol in the correct / incorrect Checked answer 102 or the position where the answer is additionally written is acquired.
In step S1504, the corresponding question is specified from the position acquired in step S1502 using the answer column information column 802 in the answer column position area information table 800.

  In step S1506, a determination method for a determination symbol is determined. That is, it is determined whether or not the question identified in step S1504 is a selection problem. If it is not a selection problem, the process proceeds to step S1508, and if it is a selection problem, the process proceeds to step S1510. Further, not only whether or not it is a selection problem, for example, it may be further determined whether or not there is a region having a density equal to or higher than the density of the determination symbol around the position where the determination symbol is written. If there is a selection problem and there is an area of the determination symbol density or more around the position where the determination symbol is entered, the process may proceed to step S1510, and otherwise, the process may proceed to step S1508.

In step S1508, the determination symbol recognition module 107 recognizes the shape of the determination symbol.
In step S1510, correctness / incorrectness determination processing for a selection problem is performed. That is, using the correct answer column information column 805 of the answer column position area information table 800, correct / incorrect is determined only by the position of the determination symbol. Alternatively, using the correct answer column information column 805 of the answer column position area information table 800, whether the answer is correct is determined.
In step S1512, a score is determined using the scoring column 803 of the answer column position area information table 800 and the processing result in step S1508 or step S1510.
In step S1514, the score determined in step S1512 is used to perform aggregation and the like for use in results management.

Next, the process shown in FIG. 16 will be described.
In step S1602, the determination symbol in the correct / incorrect Checked answer 102 or the position where the answer is additionally written is acquired.
In step S1604, the corresponding question is specified from the position acquired in step S1602 using the answer column information column 802 in the answer column position area information table 800.
In step S1606, the determination symbol recognition module 107 recognizes the determination symbol.
In step S1608, the reliability of the recognition result obtained in step S1606 is determined. That is, when the reliability is high, the process proceeds to step S1614, and when the reliability is low, the process proceeds to step S1610. Here, the reliability represents the degree of confidence in the recognition result when the determination symbol recognition module 107 recognizes the determination symbol. By comparing the reliability with a threshold value, the level of reliability is determined.
In step S1610, it is a case where the reliability of the recognition result is low, and whether or not the question to which the determination symbol is attached is a selection question is determined using the selection question response flag column 804 of the answer column position area information table 800. to decide. That is, if it is a selection problem, the process proceeds to step S1612, and if it is not a selection problem, the process proceeds to step S1614.
In step S1612, correctness determination processing for a selection problem is performed. That is, using the correct answer column information column 805 of the answer column position area information table 800, correct / incorrect is determined only by the position of the determination symbol. Alternatively, using the correct answer column information column 805 of the answer column position area information table 800, whether the answer is correct is determined.
In step S1614, a score is determined using the scoring column 803 of the answer column position area information table 800 and the processing result in step S1606 or step S1612.
In step S1616, the score determined in step S1614 is used for aggregation and the like, which is useful for results management.

In the above-described embodiment, the correct / incorrect Checked answer 102 has been mainly described in the case of color printing. However, even in the case of single-color printing, a correct / incorrect determination symbol such as ○ × Δ is extracted and the determination symbol is used. The correctness of the answer for each question can be determined.
Moreover, the correct / incorrect Checked answer 102 in which answers are entered by a plurality of children or the like may be continuously input as images, and the score for each child or the like may be calculated and recorded.

  A hardware configuration example of the present embodiment will be described with reference to FIG. The configuration shown in FIG. 17 is configured by, for example, a personal computer (PC), and shows a hardware configuration example including a data reading unit 1717 such as a scanner and a data output unit 1718 such as a printer.

  The CPU (Central Processing Unit) 1701 includes the various modules described in the above-described embodiment, that is, the determination symbol extraction module 106 and the determination symbol recognition module 107 illustrated in FIG. 1, and the error processing module 705 illustrated in FIG. The control unit executes processing according to a computer program in which the execution sequence of each module such as the determination method determination module 708 is described.

  A ROM (Read Only Memory) 1702 stores programs used by the CPU 1701, calculation parameters, and the like. A RAM (Random Access Memory) 1703 stores programs used in the execution of the CPU 1701, parameters that change as appropriate in the execution, and the like. These are connected to each other by a host bus 1704 including a CPU bus.

  The host bus 1704 is connected to an external bus 1706 such as a PCI (Peripheral Component Interconnect / Interface) bus via a bridge 1705.

  A keyboard 1708 and a pointing device 1709 such as a mouse are input devices operated by an operator. The display 1710 includes a liquid crystal display device or a CRT (Cathode Ray Tube), and displays various types of information as text and image information.

  An HDD (Hard Disk Drive) 1711 has a built-in hard disk, drives the hard disk, and records or reproduces a program executed by the CPU 1701 and information. The hard disk stores the original 101, the correct / incorrect Checked answer 102, the answer column position area information table 800, and the like. Further, various computer programs such as various other data processing programs are stored.

  The drive 1712 reads out data or a program recorded on a removable recording medium 1713 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, and the data or program is read out as an interface 1707 and an external bus 1706. , The bridge 1705, and the RAM 1703 connected via the host bus 1704. The removable recording medium 1713 can also be used as a data recording area similar to the hard disk.

  The connection port 1714 is a port for connecting the external connection device 1715 and has a connection unit such as USB or IEEE1394. The connection port 1714 is connected to the CPU 1701 and the like via an interface 1707, an external bus 1706, a bridge 1705, a host bus 1704, and the like. A communication unit 1716 is connected to the network and executes data communication processing with the outside. The data reading unit 1717 is a scanner, for example, and executes document reading processing. The data output unit 1718 is a printer, for example, and executes document data output processing.

  Note that the hardware configuration shown in FIG. 17 shows one configuration example, and the present embodiment is not limited to the configuration shown in FIG. 17, and is a configuration capable of executing the modules described in the present embodiment. If it is. For example, some modules may be configured with dedicated hardware (for example, Application Specific Integrated Circuit (ASIC), etc.), and some modules are in an external system and connected via a communication line In addition, a plurality of systems shown in FIG. 17 may be connected to each other via communication lines so as to cooperate with each other. Further, it may be incorporated in a copying machine, a fax machine, a scanner, a printer, a multifunction machine, or the like.

The program described above may be provided by being stored in a recording medium, or the program may be provided by communication means. In that case, for example, the above-described program may be regarded as an invention of a “computer-readable recording medium recording the program”.
The “computer-readable recording medium on which a program is recorded” refers to a computer-readable recording medium on which a program is recorded, which is used for program installation, execution, program distribution, and the like.
The recording medium is, for example, a digital versatile disc (DVD), which is a standard established by the DVD Forum, such as “DVD-R, DVD-RW, DVD-RAM,” and DVD + RW. Standards such as “DVD + R, DVD + RW, etc.”, compact discs (CDs), read-only memory (CD-ROM), CD recordable (CD-R), CD rewritable (CD-RW), etc. MO), flexible disk (FD), magnetic tape, hard disk, read only memory (ROM), electrically erasable and rewritable read only memory (EEPROM), flash memory, random access memory (RAM), etc. It is.
The program or a part of the program may be recorded on the recording medium and stored or distributed. Also, by communication, for example, a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a wired network used for the Internet, an intranet, an extranet, etc., or wireless communication It may be transmitted using a transmission medium such as a network or a combination of these, or may be carried on a carrier wave.
Furthermore, the above program may be a part of another program, or may be recorded on a recording medium together with a separate program. Moreover, it may be divided and recorded on a plurality of recording media. Further, it may be recorded in any manner as long as it can be restored, such as compression or encryption.

It is a conceptual module block diagram about the structural example of this Embodiment. It is explanatory drawing which shows the structural example of the whole system in the case of implement | achieving this Embodiment. It is explanatory drawing which shows a specific example of a problem paper. It is a flowchart which shows an example of a missing line segment interpolation process. It is explanatory drawing which shows the specific example of a missing line segment interpolation process. It is a notional flowchart about the example of processing by this embodiment. It is a module block diagram about the more detailed structural example of this Embodiment. It is explanatory drawing which shows the example of a data structure of answer column position area information. It is explanatory drawing which shows the example of the extraction result of a determination symbol. It is a flowchart which shows an example of the process with respect to a selection problem. It is explanatory drawing which shows the example which filled in the determination symbol with respect to the selection problem. It is explanatory drawing which shows the example which filled in the determination symbol with respect to the selection problem. It is explanatory drawing which shows the example which filled in the determination symbol with respect to the selection problem. It is explanatory drawing which shows the example of the surrounding area of the selection column of a selection question. It is a flowchart which shows an example of the process with respect to a selection problem. It is a flowchart which shows an example of the process with respect to a selection problem. It is a block diagram which shows the hardware structural example of the computer which implement | achieves this Embodiment.

Explanation of symbols

101 ... Original 102 ... Correct / Error Checked Answer 103 ... Image Input Module 104 ... Original Image Acquisition Module 105 ... Answer Image / Problem Information DB
DESCRIPTION OF SYMBOLS 106 ... Determination symbol extraction module 107 ... Determination symbol recognition module 108 ... Determination symbol position calculation module 109 ... Score calculation module 110 ... Solver identification module 111 ... Score information storage module 112 ... Score result confirmation / correction module 113 ... Answer image DB
114 ... Student / Results Information DB
DESCRIPTION OF SYMBOLS 201 ... Scanner 202 ... Scoring server 203 ... Client 204 ... Scoring result etc. storage server 205 ... Network (communication channel)
701 ... Position distortion correction module 702 ... Difference extraction module 703 ... Predetermined color pixel extraction module 704 ... Missing line segment interpolation module 705 ... Error processing module 706 ... Additional write position acquisition module 707 ... Additional write corresponding question identification module 708 ... Determination method determination module 709 ... Selected question correct / incorrect determination module 710 ... Shape recognition module 711 ... Scoring module 712 ... Totaling module 800 ... Answer column position area information table

Claims (13)

An image receiving means for receiving an image of the question sheet in which an answerer enters an answer for each question on a question sheet on which a question is printed in advance, and a grader enters a determination symbol regarding correctness in the answer for each question;
Corresponding to the image of the problem paper received by the image receiving means, original image receiving means for receiving an original image not filled in;
Extraction means for extracting the determination symbol based on the image received by the image receiving means and the original image received by the original image receiving means;
Shape recognition means for recognizing the shape of the determination symbol extracted by the extraction means;
Position calculating means for calculating the position of the determination symbol extracted by the extracting means;
Score calculation means for calculating a score based on the shape recognized by the shape recognition means and the position calculated by the position calculation means;
An answerer specifying means for specifying an answerer in the image received by the image receiving means;
An answerer information storage means for storing the answerer specified by the answerer specifying means and the score calculated by the score calculation means in association with each other;
In the case where the determination symbol to be recognized is related to a selection problem, the shape recognition means is configured such that the feature amount of the pixel surrounding the determination symbol or the feature amount of the pixel surrounding the selection question answer area is a predetermined condition. If you do not recognize the shape,
The scoring system characterized in that the scoring means calculates a score based on the position calculated by the position calculating means. An image receiving means for receiving an image of the question sheet in which an answerer enters an answer for each question on a question sheet on which a question is printed in advance, and a grader enters a determination symbol regarding correctness in the answer for each question;
Corresponding to the image of the problem paper received by the image receiving means, original image receiving means for receiving an original image not filled in;
Extraction means for extracting the determination symbol based on the image received by the image receiving means and the original image received by the original image receiving means;
Shape recognition means for recognizing the shape of the determination symbol extracted by the extraction means;
Position calculating means for calculating the position of the determination symbol extracted by the extracting means;
Score calculation means for calculating a score based on the shape recognized by the shape recognition means and the position calculated by the position calculation means;
An answerer specifying means for specifying an answerer in the image received by the image receiving means;
An answerer information storage means for storing the answerer specified by the answerer specifying means and the score calculated by the score calculation means in association with each other;
The extracting means extracts the answer based on the image received by the image receiving means and the original image received by the original image receiving means,
In the case where the determination symbol to be recognized is related to a selection problem, the shape recognition means is configured such that the feature amount of the pixel surrounding the determination symbol or the feature amount of the pixel surrounding the selection question answer area is a predetermined condition. If you do not recognize the shape,
The position calculating means calculates the position of the answer extracted by the extracting means,
The scoring system, wherein the scoring unit calculates a score based on the position of the answer calculated by the position calculating unit. The scoring system according to claim 1, further comprising: an image storage unit that stores an image received by the image receiving unit in association with an answerer specified by the answerer specifying unit. Correction means for displaying an image stored in the image storage means and correcting the score stored in the answerer information storage means related to the image in accordance with the operation of the operator. The scoring system according to claim 3. A grader specifying means for specifying a grader is provided,
The scoring system according to claim 1, 2, 3, or 4, wherein the shape recognizing unit recognizes the shape of the determination symbol in accordance with a determination symbol to be entered for each grader. 4. The scoring system according to claim 3, wherein when the problem paper is a plurality of sheets or double-sided printing, the image storage unit stores the plurality of or double-sided problem paper images in association with each other. The scoring system according to claim 1, wherein the answerer information storage unit stores a score for each question calculated by the score calculation unit. The scoring according to claim 1 or 2, wherein the feature amount is density or brightness, and the predetermined condition is a value obtained by performing a predetermined calculation on the density or brightness of the determination symbol. system. The scoring system according to claim 1, wherein the feature amount is density or brightness, and the predetermined condition is a predetermined density or brightness or higher. The feature amount is a color, and the predetermined condition is that a color of a pixel of the determination symbol is approximate to a color of a pixel around the determination symbol or the selection problem answering area. The scoring system according to claim 1 or 2. The scoring system according to claim 1, wherein the feature amount is a color, and the predetermined condition is an approximation to a predetermined color. A computer having a storage device;
An image receiving means for receiving an image of the question sheet in which an answerer enters an answer for each question on a question sheet on which a question is printed in advance, and a grader enters a determination symbol regarding correctness in the answer for each question;
Corresponding to the image of the problem paper received by the image receiving means, original image receiving means for receiving an original image not filled in;
Extraction means for extracting the determination symbol based on the image received by the image receiving means and the original image received by the original image receiving means;
Shape recognition means for recognizing the shape of the determination symbol extracted by the extraction means;
Position calculating means for calculating the position of the determination symbol extracted by the extracting means;
Score calculation means for calculating a score based on the shape recognized by the shape recognition means and the position calculated by the position calculation means;
An answerer specifying means for specifying an answerer in the image received by the image receiving means;
An answerer specified by the answerer specifying means and a score calculated by the score calculating means in association with each other and functioning as an answerer information storage means for storing in the storage device;
In the case where the determination symbol to be recognized is related to a selection problem, the shape recognition means is configured such that the feature amount of the pixel surrounding the determination symbol or the feature amount of the pixel surrounding the selection question answer area is a predetermined condition. If you do not recognize the shape,
The scoring program, wherein the scoring unit calculates a score based on the position calculated by the position calculating unit. A computer having a storage device;
An image receiving means for receiving an image of the question sheet in which an answerer enters an answer for each question on a question sheet on which a question is printed in advance, and a grader enters a determination symbol regarding correctness in the answer for each question;
Corresponding to the image of the problem paper received by the image receiving means, original image receiving means for receiving an original image not filled in;
Extraction means for extracting the determination symbol based on the image received by the image receiving means and the original image received by the original image receiving means;
Shape recognition means for recognizing the shape of the determination symbol extracted by the extraction means;
Position calculating means for calculating the position of the determination symbol extracted by the extracting means;
Score calculation means for calculating a score based on the shape recognized by the shape recognition means and the position calculated by the position calculation means;
An answerer specifying means for specifying an answerer in the image received by the image receiving means;
The answerer specified by the answerer specifying means and the score calculated by the score calculating means are associated with each other and stored in the storage device to function as answerer information storage means,
The extracting means extracts the answer based on the image received by the image receiving means and the original image received by the original image receiving means,
In the case where the determination symbol to be recognized is related to a selection problem, the shape recognition means is configured such that the feature amount of the pixel surrounding the determination symbol or the feature amount of the pixel surrounding the selection question answer area is a predetermined condition. If you do not recognize the shape,
The position calculating means calculates the position of the answer extracted by the extracting means,
The scoring program, wherein the scoring unit calculates a score based on the position of the answer calculated by the position calculating unit.

Images