JP2007017467A - Educational material processing device, educational material processing method, and educational material processing program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To accurately identify and specify an educational material, without being imposed of large load, when attaining labor saving, in grading tabulation processing regarding the educational material. <P>SOLUTION: The educational material processing device comprises a first image reading means 31 for acquiring image data from an educational material; arithmetic/computing means 36, 37 for tabulating/marking the educational material; a first feature amount calculation means 38 for calculating an image feature amount of the image data; a database means 40 for correlating the result of the marking tabulation with the image feature amount and storing them; a printing means 46 for printing out the result of the marking tabulation; a second image reading means 41 for acquiring image data from the educational material to be printed out; a second feature amount calculation means 44 for calculating the image feature amount of the image data; and an operation information acquisition means 45 for extracting the result of making tabulation correlate with the calculated image feature amount from the database means 40 and making the printing means 46 print it out. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to a teaching material processing apparatus, a teaching material processing method, and a teaching material processing program for handling educational teaching materials used in an educational institution, and more particularly to a teaching material processing device, a teaching material processing method, and a teaching material processing program for scoring the educational teaching material. .

  In general, in educational institutions such as schools and cram schools, educational materials such as test answer sheets and practice question sheets are often used. In other words, it is widely practiced to use an educational material that has a question and its answer column, and to have students fill in the answer on the educational material, and the teacher grades the written answer. ing.

  For educational materials used in such educational institutions, labor saving in the scoring process is strongly required. In order to respond to this, labor savings in scoring and summarization can be achieved by, for example, answering papers that are classified according to the question, in which the student fills in the answers and adds the score to the answer by the teacher. Character recognition of score entry is performed, the total score for all questions and other information (for example, overall ranking and average score) for all questions are counted from the character recognition result, and the totaled result is printed on the answer sheet Thus, a system that improves the efficiency of the aggregation has been proposed (see, for example, Patent Document 1).

JP 2002-245207 A

By the way, in order to print out the result of the scoring process for the educational material on the educational material, it is necessary to identify and identify the educational material. This is because the scoring result must be printed out accurately on the educational material from which the result is obtained.
Identification and specification of educational materials can be performed by, for example, individually assigning identification information such as ID numbers to each of the educational materials and recognizing the identification information at the time of printout. Conceivable. However, it is impractical to assign individual identification information to each educational material, or to distribute the educational material with identification information to the students in correspondence with the identification information. There is a possibility that it will impose a heavy burden on its operation.
In this regard, for example, individual identification information is not given to each educational material, but information that a student enters on the educational material, specifically the name and attendance number of the student who is the answerer Alternatively, it may be possible to identify and identify educational materials by reading handwritten characters such as an examination number and recognizing the characters. However, the character recognition accuracy for handwritten characters is not always good, and erroneous recognition occurs, and as a result, identification identification errors may occur.

  Therefore, the present invention can accurately identify and identify educational teaching materials with good accuracy, even in the case of saving labor for scoring the educational teaching materials, and does not impose a large burden for that purpose. It is an object of the present invention to provide a teaching material processing apparatus, teaching material processing method, and teaching material processing program capable of accurately outputting the result of scoring and counting processing on the educational material from which the result is obtained.

  The present invention is an educational material processing apparatus devised to achieve the above object, and performs image reading on an educational material in which an answer is entered in an answer column and whether a correct / incorrect determination is entered in the answer column. A first image reading means for obtaining image data from a learning material; an extraction means for extracting entry contents of the correctness determination from image data obtained by the first image reading means; and the first image based on an extraction result by the extraction means. A calculation / calculation unit that performs scoring for correctness / incorrectness written in the educational material for the educational material from which the reading unit has read the image, and an image feature amount for the image data obtained by the first image reading unit. The first feature quantity calculation means to calculate, the scoring result of correctness determination by the calculation / calculation means, and the image feature quantity calculation result by the first feature quantity calculation means are associated with each other. Database means for storing, printing means for printing out the result of scoring by the calculation / calculation means on the educational material, and image reading for the educational material to be printed by the printing means Second image reading means for obtaining image data from the educational material, second feature value calculating means for calculating image feature values for the image data obtained by the second image reading means, and the second feature Computation information acquisition means for taking out the result of scoring the correctness / incorrectness corresponding to the image feature quantity from the database means and printing the print means on the print means using the calculation result of the image feature quantity by the quantity calculation means as a key. It is a feature.

  In addition, the present invention is a teaching material processing method devised to achieve the above-mentioned object, and performs image reading on an educational teaching material in which an answer is entered in an answer column and whether a correct / incorrect determination is entered for the answer. A first image reading step for obtaining image data from educational materials, an extraction step for extracting the contents of the correct / incorrect determination from the image data obtained in the first image reading step, and the extraction result based on the extraction result in the extraction step A calculation / calculation step for scoring and summarizing correctness / incorrectness written in the educational material for the educational material that has been image-read in the first image reading step, and an image of the image data obtained in the first image reading step A first feature value calculating step for calculating a feature value, a score totaling result of correctness determination in the calculating / calculating step, and a first feature value calculating step A database step for storing and storing image feature value calculation results in association with each other, a print step for printing out the score calculation results of correctness determination in the calculation / calculation step on the educational material, and a print step A second image reading step of obtaining image data from the educational teaching material by performing image reading on the educational teaching material to be printed out, and calculating an image feature amount of the image data obtained in the second image reading step The second feature value calculating step and the image feature value calculation result at the second feature value calculating step are used as keys to store the score totaling result of the correctness determination corresponding to the image feature value at the database step. And a calculation information acquisition step that is used for printing output in the printing step.

  Further, according to the present invention, there is provided a teaching material processing program devised to achieve the above object. The computer connected to the image reading device for reading an image and the printing device for print output is configured to input an answer in the answer column and First image reading means for obtaining image data as a result of image reading for the educational material for which the correctness determination for the answer has been entered, and the contents of the correctness determination entry from the image data obtained by the first image reading means. Extraction means for extracting, and calculation / calculation means for performing scoring of correct / incorrect judgment written in the educational material for the educational material that has been read by the first image reading means based on the extraction result by the extracting means; A first feature amount calculating means for calculating an image feature amount for the image data obtained by the first image reading means; Database means for storing and holding the score totaling result and the image feature value calculation result by the first feature value calculating means in association with each other, and printing the score totaling result of correctness determination by the calculation / calculation means to the printing device A second image reading unit that obtains image data as a result of image reading for an educational teaching material to be printed out by the printing apparatus, and image data obtained by the second image reading unit. Second feature amount calculation means for calculating an image feature amount, and the result of scoring the correctness / incorrectness corresponding to the image feature amount from the database means, using the calculation result of the image feature amount by the second feature amount calculation means as a key. It is made to function as a calculation information acquisition means taken out and used for printing output by the printing means.

  In the teaching material processing apparatus having the above-described configuration, the teaching material processing method having the above-described procedure, and the teaching material processing program having the above-described configuration, the content of correct / incorrect determination (for example, “◯” or “ X ”(graphic shape) is recognized, and the correctness / incorrectness scoring score entered in the educational material based on the recognition result (for example, total score calculation, total ranking, average score, etc.) Image feature values (for example, quantitative representation of pixel distribution features) for image data read from teaching materials are calculated, and the score totaling results and image feature value calculation results are stored in association with each other. Keep it. Then, when printing out the result of scoring, the image feature amount of the image data read from the educational teaching material to be printed out is calculated, and the corresponding correctness determination is performed using the image feature amount as a key. The result of scoring the number is taken out from the already stored memory. That is, identification and identification of the educational material is performed based on the image feature amount on the educational material. Accordingly, the scoring result of correct / incorrect determination is accurately printed out on the educational material from which the result is obtained. Moreover, since the educational material is identified and specified using the image feature amount as a key, it is not necessary to assign individual identification information to the educational material for the identification and identification, and handwriting that may cause misrecognition There is no need for character recognition.

  As described above, in the teaching material processing apparatus, teaching material processing method, and teaching material processing program of the present invention, the educational teaching material of the educational teaching material used in the educational institution can be saved even if the scoring and summarizing processing is attempted. The identification and identification can be performed accurately and satisfactorily, and the results of scoring and counting can be accurately output on the educational material from which the results are obtained without imposing a heavy burden on the identification and identification. .

  The teaching material processing apparatus, teaching material processing method, and teaching material processing program according to the present invention will be described below with reference to the drawings.

[Description of overall system configuration]
First, a system configuration for realizing the teaching material processing apparatus will be described. FIG. 1 is a block diagram showing a specific system configuration example of a teaching material processing apparatus according to the present invention. As shown in the figure, the system described here is roughly divided into a scanner unit 1, a data processing unit 2, a printer unit 3, and a wired or wireless communication line (not shown) connecting them to each other. , Is composed of.

  The scanner unit 1 obtains image data from the educational material 4 by performing image reading on the educational material 4 to be processed using a known optical image reading technique. However, the scanner unit 1 has an ADF (Automatic Document Feeder) so that image data can be continuously read from a plurality of educational materials 4.

Here, the educational material to be processed will be briefly described. FIG. 2 is an explanatory diagram showing a specific example of educational materials. As shown in the figure, the educational material 4 has a question and its answer column 4a, and specifically corresponds to a test answer sheet, a practice question sheet, and the like used in an educational institution. However, the educational material 4 only needs to have at least the answer column 4a, and the question sentence is not necessarily described.
The educational material 4 includes an identification information field 4b for identifying and specifying the educational material 4 and an answerer information field 4c regarding an answer entry person in the answer field 4a. In the identification information column 4b, for example, a subject, a title, an applicable grade, etc. of the educational material 4 are described in advance. However, in addition to or in addition to these descriptions, code information for identifying the educational material 4 may be embedded. The embedding of the code information may be realized by using a known technique. As one specific example thereof, for example, a line screen or a dot screen as a gradation expression such as a so-called “iTone (registered trademark)”. It is conceivable to use a technique of embedding digital information in a halftone image by changing the form (position, shape, etc.) of the pixels constituting the image. On the other hand, in the answerer information column 4c, the class, attendance number, name, etc. of the answerer can be entered.
Further, the educational material 4 has an information output field 4d. In the information output column 4d, the total score for the answer entered in the answer column 4a and other information accompanying the total score, for example, information such as an average score in class units or grade units, an overall ranking, a deviation value, etc. are entered. Is to do.

  In FIG. 1, a data processing unit 2 uses data processing functions for image data obtained by the scanner unit 1 using functions as a computer device that realizes an information storage processing function, an image processing function, an arithmetic processing function, and the like. A scoring process based on the data processing result is performed. For this purpose, the data processing unit 2 includes an original information holding / accumulating unit 11, an image data analyzing unit 12, a teaching material determining unit 13, a distortion correcting unit 14, a comparison extracting unit 15, a predetermined color extracting unit 16, and a pixel. A group dividing unit 17, a shape recognizing unit 18, an entry position recognizing unit 19, an information calculating unit 20, a calculating unit 21, a first feature quantity calculating unit 22, an associating unit 23, a database unit 24, A second feature amount processing unit 25 and a calculation information acquisition unit 26 are provided.

The original information holding / accumulating unit 11 uses the electronic data of the educational material 4 to be processed, which is not filled in the answer column, as the electronic data of the original of the educational material 4 It is the one that holds and accumulates.
The electronic data of the educational material 4 can be of any data format as long as it can be stored and stored in the original information storage and storage unit 11. For example, it may be bitmap image data or application document data created by document creation software.
However, the electronic data of the educational material 4 includes the educational material in addition to the data (hereinafter referred to as “original image data”) that can specify the layout of the answer field 4a and the identification information field 4b in the educational material 4. It is assumed that information (hereinafter referred to as “original image information”) for specifying four attributes (subjects, titles, applicable grades, etc.) and a score for each answer column 4a in the educational material 4 is included. With this original image information, for each answer field 4a on the educational material 4 for education, it is specified how many points are assigned to the answer field 4a at which position. Scoring may be different for each answer field 4a or may be uniform.

  The image data analysis unit 12 performs an analysis process on the image data obtained by the scanner unit 1. Examples of the analysis processing include layout analysis, character / graphic separation, character recognition, code information recognition, graphic processing, color component recognition, etc., and any of these may be realized using known image processing techniques. Detailed description thereof is omitted.

  The teaching material discrimination unit 13 includes at least one of a title analysis unit and a code information analysis unit. As a result of the analysis process in the image data analysis unit 12, particularly, the title analysis or code by the title analysis unit for the identification information column 4b Based on the result of at least one of the code analysis by the information analysis unit, the educational teaching material 4 that is the basis of the image data obtained by the scanner unit 1 is identified and specified. At this time, in the teaching material discriminating unit 13, the original information holding and storing unit 11 is compared with the teaching material 4 for storing and storing electronic data, and if the corresponding electronic data is not held and stored in the original information holding and storing unit 11. In this case, it is determined that the teaching material is an identification specific error. That is, the teaching material determination unit 13 specifies electronic data to be compared with the image data obtained by the scanner unit 1 from the analysis result of the image data analysis unit 12.

  The distortion correction unit 14 corrects image distortion in the image data obtained by the scanner unit 1. Examples of image distortion correction include tilt correction and enlargement / reduction correction in the main scanning direction or sub-scanning direction. Further, the image data obtained by the scanner unit 1 and the electronic data in the original information storage / storage unit 11 to be compared are compared and collated, and the image distortion (inclination, scaling, etc.) is corrected. Good. Since any correction may be realized using a known image processing technique, detailed description thereof is omitted here.

  The comparison and extraction unit 15 is image data obtained by the scanner unit 1 based on the identification and identification result of the educational material 4 by the educational material determination unit 13, and after the image distortion correction processing by the distortion correction unit 14. Are compared with the electronic data in the original information holding and accumulating unit 11 to be compared, and the difference between them is extracted.

  The predetermined color extraction unit 16 further extracts a predetermined color component (for example, a red component) from the difference extracted by the comparison extraction unit 15 based on the result of the analysis processing in the image data analysis unit 12. Thus, the contents of the correct / incorrect determination entry are extracted. The reason for extracting the predetermined color component is that the correct / incorrect determination is generally entered in a predetermined color (for example, red).

The pixel group dividing unit 17 collects pixel data related to each other (for example, those at close positions) as a single pixel group with respect to the extraction result of the predetermined color extraction unit 16, and the extraction result is a plurality of pixels. By dividing into groups, a pixel group that will constitute one figure shape (“◯” or “×”) is obtained.
In addition, the pixel group dividing unit 17 performs discontinuity correction processing as will be described in detail later when dividing the pixel group. The interruption correction process is a process for connecting the extracted line segments and eliminating the interruption between the extracted line segments.

  The shape recognizing unit 18 performs shape recognition on the content of the correct / incorrect determination extracted by the predetermined color extracting unit 16 and divided by the pixel group dividing unit 17, and displays the content of the correct / incorrect determination. Recognize. Shape recognition may be performed, for example, by pattern matching with a graphic shape of “◯” or “×”. Alternatively, the feature amount of the 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, the area ratio of the target graphic occupying the circumscribed rectangle, and the like.

  The entry position recognizing unit 19 recognizes the entry position on the educational material 4 with respect to the entry contents of the correctness determination whose shape is recognized by the shape recognizing unit 18. The recognition of the entry position may be performed by, for example, coordinate analysis on the educational material 4.

  The information calculation unit 20 recognizes the result of the correct / incorrect determination entered by the shape recognition unit 18, the result of the correct / incorrect determination entry by the entry position recognition unit 19, and the education held and accumulated by the original information holding / accumulating unit 11. Based on the scoring information about each answer field 4a of the educational material 4 included in the electronic data of the educational material 4, the educational material 4 that the scanner unit 12 has read an image is assigned to the educational material 4. The entered correctness judgment is scored and totaled to calculate the total score.

  Based on the calculation result obtained by the information calculation unit 20, the calculation unit 21 relates to other information attached to the total score which is the calculation result, for example, information such as an average score in class units or grade units, an overall ranking, a deviation value, and the like. In order to obtain these, an operation is performed. It is assumed that what kind of information is calculated is determined in advance.

The first feature value calculation unit 22 calculates an image feature value for the image data obtained by the scanner unit 1. The image feature amount is a quantitative representation of the feature of the image, and specifically includes a histogram of the pixel distribution in the image, a representation of the pixel distribution in the image by run length, etc. It is done.
However, the first feature amount calculation unit 22 calculates an image feature amount based on the difference extraction result in the comparison extraction unit 15. Further, the image feature amount is not calculated for all the image data obtained by the scanner unit 1, that is, the entire area of the educational teaching material 4 to be read, but the image data obtained from a specific portion, specifically, Is configured to calculate the image feature amount for the image data obtained from the solver information column 4c of the educational material 4.

  The associating unit 23 associates the score totaling result by the information calculating unit 20 and the calculation result by the calculating unit 21 with the calculation result of the image feature value by the first feature value calculating unit 22. As a result, the score totaling result and calculation result obtained from the same educational material 4 are associated with the image feature value calculation result.

  The database unit 24 displays the score totaling result by the information calculation unit 20 and the calculation result by the calculation unit 21 and the calculation result of the image feature value by the first feature value calculation unit 22 while following the result of the association by the association unit 23. The data are stored and held in association with each other.

The second feature amount processing unit 25 reads an image using a known optical image reading technique on the educational material 4 to be printed by the printer unit 3 prior to the printing output. The image data is obtained from the educational material 4 and the image feature amount for the image data is calculated. It is assumed that the image feature amount calculated by the second feature amount processing unit 25 is the same type as the image feature amount calculated by the first feature amount calculation unit 22.
However, the second feature amount processing unit 25 does not necessarily need to read the image data from the educational material 4 and calculate the image feature amount for the image data for the entire region of the educational material 4, and at least the first It may be performed only for the specific part where the one feature quantity calculation unit 22 has calculated the image feature quantity, specifically, the solver information column 4 c of the educational material 4.

  The calculation information acquisition unit 26 uses an image feature value calculation result by the second feature value processing unit 25 as a key, and an image feature value (same as or substantially the same as the image feature value (calculation result by the second feature value processing unit 25)). The score totaling result of correctness determination corresponding to the calculation result by the first feature amount calculating unit 22, that is, the score totaling result by the information calculating unit 20 and the calculation result by the calculating unit 21 are taken out from the database unit 24 and are used as a printer. The unit 3 prints out.

  While following the instruction from the calculation information acquisition unit 26, the printer unit 3 displays the score totaling result by the information calculation unit 20 and the calculation result by the calculation unit 21 on the teaching material 4 for obtaining the score totaling result and the calculation result. Printing is performed using a known electrophotographic technique.

By the way, the printer unit 3 prints out the media taken out one by one from the paper feed tray. Therefore, before the printer unit 3 performs printout, the educational material 4 to be printed out, that is, the image read by the scanner unit 1 is read in the paper feed tray of the printer unit 3. It is assumed that the educational material 4 is set.
In this case, the educational material 4 after image reading is fed into a paper feed tray of the printer unit 3 through a conveyance path (not shown) connecting the scanner unit 1 and the printer unit 3. Can be considered. That is, a conveyance path for conveying the educational material 4 is provided between the scanner unit 1 and the printer unit 3, and the educational material 4 after image reading by the scanner unit 1 is automatically supplied to the printer unit 3. Be transported into the paper tray.
On the other hand, the educational material 4 need not be automatically conveyed. For example, the teaching material 4 may be manually transferred from the scanner unit 1 to the printer unit 3.
In either case of automatic conveyance or manual conveyance, the above-described teaching material 4 to be printed out is identified and specified between the paper feed tray of the printer unit 3 and the printer engine unit. It is assumed that reading means such as a CCD (Charge Coupled Device) sensor used by the second feature amount processing unit 25 to read an image is provided.

  Of the teaching material processing apparatus having the system configuration including the scanner unit 1, the data processing unit 2, and the printer unit 3 as described above, the units 11 to 26 constituting the data processing unit 2 are preliminarily programmed in a computer device, for example. It is conceivable that this is realized by installing and executing the predetermined program. However, in this case, the predetermined program for realizing each unit 11 to 26 is not installed in advance, but may be provided by being stored in a computer-readable storage medium, or wired or It may be distributed via wireless communication means. That is, the teaching material processing apparatus having the above-described configuration can also be realized by a teaching material processing program that causes a computer connected to the scanner unit (image reading device) 1 and the printer unit (printing device) 3 to function as a teaching material processing device. .

[Description of characteristic functional configuration of teaching material processing device]
Next, the characteristic functional configuration of the educational material processing apparatus (including the case realized by the educational material processing program) realized by the system configuration as described above will be described in more detail.

  FIG. 3 is a block diagram showing a functional configuration example of the teaching material processing apparatus according to the present invention. As shown in the figure, the teaching material processing apparatus includes a first image reading unit 31, an original information storage unit 32, a first original search unit 33, a first additional record data extraction unit 34, an accuracy determination extraction unit 35, Information calculation means 36, calculation means 37, first feature quantity calculation means 38, feature quantity / information association means 39, database means 40, second image reading means 41, and second original search means 42 The second additional data extraction unit 43, the second feature amount calculation unit 44, the calculation information acquisition unit 45, and the print unit 46 are provided.

  The first image reading means 31 is a function realized by the scanner unit 1 and performs image reading on the educational teaching material 4 in which the answer is entered in the answer column 4a and the correctness / incorrectness judgment is entered for the answer. This is for obtaining image data from the teaching material 4.

  The original information storage means 32 is a function realized by the original information storage / storage unit 11 and is used to store and store the original data of the educational material 4 as electronic data.

  The first original search unit 33 is a function realized by the image data analysis unit 12 and the teaching material determination unit 13 and specifies electronic data to be compared with the image data obtained by the first image reading unit 31. The specified electronic data is searched from the original information storage means 32.

  The first additional data extraction unit 34 is a function realized by the image data analysis unit 12, the distortion correction unit 14, and the comparison extraction unit 15, and converts the image data obtained by the first image reading unit 31 into the original information storage unit 32. Compared with the electronic data stored and accumulated by the first original searching means 33 and extracted from the original information storing means 32, the difference is extracted. By this difference extraction, the contents to be added by the students and teachers on the educational material 4 are extracted.

  The correctness / error determination extracting unit 35 is a function realized by the predetermined color extracting unit 16, the pixel group dividing unit 17, the shape recognizing unit 18, and the entry position recognizing unit 19, and is based on the difference extraction result in the first additional data extracting unit 34. Thus, the contents of the correct / incorrect determination entered on the educational material 4 are extracted and recognized.

  The information calculation means 36 is a function realized by the information calculation section 20, and scores and sums the correctness / incorrectness determinations written in the educational material 4 based on the extraction / recognition results by the correctness / error determination extraction means 35, and calculates the total score. Is to be calculated.

  The calculation unit 37 is a function realized by the calculation unit 21 and performs a calculation based on the calculation result by the information calculation unit 36 to obtain other information attached to the calculation result.

  The first feature quantity calculation unit 38 is a function realized by the first feature quantity calculation unit 22, and the image data obtained by the first image reading unit 31 is converted into a difference extraction result by the first additional data extraction unit 34. Based on this, the image feature amount of the image data is calculated. However, the first feature quantity calculation means 38 calculates the image feature quantity for the image data obtained from the answerer information column 4 c of the educational material 4.

  The feature quantity / information associating means 39 is a function realized by the associating unit 23. The feature quantity / information associating means 39 is a function of scoring and summarizing results by the information calculating means 36, a computing result by the computing means 37, and an image feature quantity by the first feature quantity calculating means 38. The calculation results are associated with each other.

  The database unit 40 is a function realized by the database unit 24, and follows the result of the score calculation by the information calculation unit 36 and the calculation result by the calculation unit 37, while following the result of the association by the feature amount / information association unit 39. The calculation result of the image feature amount by the one feature amount calculating means 38 is stored and held in a state of being associated with each other.

  The second image reading unit 41 is a function realized by the second feature amount processing unit 25, performs image reading on the educational material 4 to be printed out by the printer unit 3, and reads the educational material 4 from the educational material 4. This is for obtaining image data. Note that the second image reading means 41 does not need to read the image for the entire area of the educational material 4, and only needs to read the image of at least the answerer information column 4 c of the educational material 4. Good.

  The second original search unit 42 is a function realized by the second feature amount processing unit 25, specifies electronic data to be compared with the image data obtained by the second image reading unit 41, and specifies the specified electronic Data is searched from the original information storage means 32.

  The second additional data extraction means 43 is a function realized by the second feature amount processing unit 25, and is electronic data that the original information storage means 32 holds and stores the image data obtained by the second image reading means 41. The second original searching means 42 searches for the difference from the original information storing means 32 that is searched and extracted. By this difference extraction, the content added by the student to the answerer information column 4c of the educational material 4 is extracted.

  The second feature quantity calculating unit 44 is a function realized by the second feature quantity processing unit 25 and calculates the image feature quantity of the image data obtained by the second image reading unit 41. . At this time, the second feature amount calculation unit 44 calculates an image feature amount based on the difference extraction result in the second additional record data extraction unit 43. Therefore, the second feature quantity calculation unit 44 also calculates the image feature quantity of the image data obtained from the answerer information column 4c of the educational material 4 as in the first feature quantity calculation unit 38. .

  The calculation information acquisition unit 45 is a function realized by the calculation information acquisition unit 26, and uses the image feature amount calculation result by the second feature amount calculation unit 44 as a key, and the image feature amount (by the second feature amount calculation unit 44). The score summation result of the correctness / incorrectness determination corresponding to the image feature quantity (calculation result by the first feature quantity calculation means 38) that is the same as or substantially the same as the calculation result) is taken out from the data stored and held by the database means 40, It is to be printed out.

  The printing unit 46 is a function realized by the printer unit 3, and the scoring tabulation result of the correctness determination taken out from the database unit 40 by the arithmetic information acquisition unit 45, that is, the scoring tabulation result by the information calculating unit 36 and the arithmetic unit 37. The result is printed out on the educational material 4 from which the score totaling result and the calculation result are obtained.

[Description of processing operation overview]
Next, an example of processing operation in the teaching material processing apparatus (including the case where the teaching material processing program is also realized) configured as described above, that is, the procedure of the teaching material processing method according to the present invention will be described. FIG. 4 is an explanatory diagram showing an outline of a basic processing operation example in the teaching material processing apparatus according to the present invention.

  When using the teaching material processing apparatus, first, students and others fill in the name and the like in the answerer information column 4c and the answer in the answer column 4a, and the answer entered in each answer column 4a by the teacher etc. With respect to the educational teaching material 4 in which a correct / incorrect graphic such as “◯” or “×” is entered, the scanner unit 1 reads an image to obtain image data from the educational teaching material 4 (step 101, hereinafter) Step is abbreviated as “S”). At this time, by using ADF, for example, a plurality of educational teaching materials 4 to be processed collectively in one group such as the same class, the images are collectively read, and each educational teaching material 4 is continuously read. Image data can be obtained.

  The image data obtained by reading the image by the scanner unit 1 is sent to the data processing unit 2 and temporarily held in a memory or the like used as a work area of the data processing unit 2. In addition, the teaching material 4 after image reading is all fed into the paper feed tray of the printer unit 3 by an automatic conveyance path or by a person such as a teacher. At this time, it is desirable that the educational material 4 is set in the paper feed tray in the order of image reading by the scanner unit 1.

Thereafter, the data processing unit 2 sequentially performs an automatic scoring process and a totaling calculation process, which will be described in detail later, on the respective image data obtained from each educational material 4 (S102).
On the other hand, the data processing unit 2 sequentially performs feature amount calculation processing, which will be described in detail later, on each image data obtained from each educational material 4. Then, the calculation result of the image feature amount obtained by the feature amount calculation processing and the scoring count result and the calculation result obtained by the automatic scoring processing and the summing calculation processing are stored in a state of being associated with each other for each educational material 4. Hold it (S103).

  After the automatic scoring process, the totaling calculation process, and the feature amount calculation process in the data processing unit 2 are completed, the printer unit 3 sequentially applies to each educational material 4 set in the paper feed tray. Then, the calculation result in the automatic scoring process and the calculation result in the total calculation process are printed out (S104). In this print output process, the feature amount calculation process is performed for each educational material 4 to be printed by the printer unit 3, and the calculation result of the image feature amount obtained by the feature amount calculation process is used as a key. Thus, a search is made for the score totaling result and the calculation result to be printed out. By such a print output process, the processing results of the automatic scoring process and the total calculation process are added to the information output column 4d on the educational material 4 from which the calculation result and the calculation result are obtained and output. .

  Next, the automatic scoring process, the totaling calculation process, the feature amount calculation process, and the print output process in the above processing operation example will be described in more detail.

[Explanation of automatic scoring and totaling processing]
The automatic scoring process and the total calculation process are performed in the following procedure.
First, in the data processing unit 2, in the automatic scoring process, the image data analysis unit 12 performs an analysis process on the image data obtained from a certain educational material 4, and the material determination is performed based on the result of the analysis process. The unit 13 identifies and specifies the educational material 4. This identification and specification may be performed through title analysis such as “science”, “5 years”, “1. change in weather and temperature” or code analysis of code information embedded in the identification information column 4b. Through this identification and specification, the teaching material determination unit 13 can specify electronic data to be compared with the image data obtained by the scanner unit 1. When the teaching material discriminating unit 13 specifies the electronic data, the original information holding and accumulating unit 11 takes out the corresponding electronic data from the holding and accumulating according to the identification result, and receives it from the comparison and extraction unit 15. hand over.
That is, for the image data obtained by the function as the first image reading means 31, the function as the first original search means 33 identifies and specifies the electronic data to be compared, and the identified and specified electronic data is used as the original information. The search is made from the storage means 32.
This identification and specification may be performed sequentially for each of the plurality of educational materials 4 from which images have been read. However, the educational materials 4 that are generally processed in one group are all the same. Therefore, it is sufficient to perform only the educational material 4 that is processed first during the processing.

  For image data obtained from one educational material 4 for education, the distortion correction unit 14 corrects the image distortion in the image data. This correction of image distortion is performed to correct image distortion that may occur when the scanner unit 1 reads an image, and is used to improve accuracy such as comparison with subsequent electronic data and difference extraction. Is.

The comparison / extraction unit 15 compares the electronic data received from the original information holding / accumulating unit 11 with the image data obtained by the scanner unit 1 and corrected for image distortion by the distortion correction unit 14. Then, the difference is extracted. Further, for the difference extraction result by the comparison extraction unit 15, the predetermined color extraction unit 16 uses the difference extraction result for the predetermined color component in order to extract the contents of the correct / incorrect determination entry in each answer column 4a. Specifically, for example, a red component is extracted. The extraction of the predetermined color component can be performed by paying attention to the color component data constituting the pixel data, for example, when the difference extraction result is composed of pixel data.
That is, for the image data obtained by the first image reading means 31, when the first original search means 33 identifies and specifies the electronic data to be compared, the function as the first additional data extraction means 34 compares the data. Then, the difference is extracted, and the function as the correct / incorrect determination extracting means 35 extracts the contents of the correct / incorrect determination entry.

  By the way, in general, there are a plurality of answer fields 4 a on the educational material 4, and entry of correct / incorrect determination is also performed at a plurality of locations on the educational material 4. Therefore, in order to recognize the contents of the correct / incorrect determination, it is necessary to handle a plurality of items separately.

  Therefore, the pixel group dividing unit 17 performs pixel group division on the extraction result in the predetermined color extracting unit 16. The pixel group division may be performed by collectively handling pixel groups at close positions. That is, it is determined that pixels located at a position closer than a preset distance constitute one graphic shape, and labeling, which is a general image processing technique, is performed on a continuous pixel group located at the adjacent position. Processing is performed to enable discrimination from other groups of continuous pixels. By using the result of such labeling processing, it is possible to handle consecutive pixel groups that will form one graphic shape (“◯” or “×”) as one group after pixel group division. become.

  In addition, the pixel group dividing unit 17 performs an interruption correction process on the extraction result of the predetermined color extracting unit 16 in addition to the pixel group division using the labeling process, preferably before the image group dividing process. The correct or incorrect graphic entry such as “○” or “×” on the educational material 4 is performed by overlapping the question sentence, the frame for identifying each answer field 4a, the contents of answer entered in each answer field 4a, etc. In many cases, the extraction result of the predetermined color component by the predetermined color extraction unit 16 may be a result of removing the overlapped portion, that is, a discontinuity portion in a figure such as “◯” or “×”. Because it is expensive.

  Here, the discontinuity correction process performed by the pixel group dividing unit 17 will be described in detail.

FIG. 5 is an explanatory diagram illustrating an example of the interruption correction process.
In the interruption correction process, as shown in FIG. 5A, for the extraction result of the predetermined color component by the predetermined color extraction unit 16, that is, the extraction result that should be a graphic such as “◯” or “×”, Thinning processing is executed (S201), and end point extraction processing is further executed (S202). As a result, when there is an interrupted portion in the graphic such as “◯” or “×”, the end points at the interrupted portion are extracted. Note that the thinning process and the end point extraction process performed at this time may be performed using a known technique, and thus detailed description thereof is omitted here.
When the end points are extracted, the following processing is executed for all the extracted end points (S203). That is, first, an unprocessed end point is selected (S204), and within the predetermined distance set in advance from the selected end point (hereinafter referred to as “first end point”) and closest to the end point. A certain unprocessed end point (hereinafter referred to as “second end point”) is further selected (S205). If there is a second end point (S206), the first end point and the second end point are connected to each other (S207), and both the first end point and the second end point are processed (S208). On the other hand, if the second end point does not exist (S206), the end point is not processed and the first end point is processed (S209). Such processing is performed for all end points until there are no unprocessed end points (S203 to S209).
Thereby, for example, when the figure shown in FIG. 5B is extracted, even if the end points B and C exist within a predetermined distance from the end point A, the nearest end point B is within that range. It is connected to the end point A, and the discontinuity portion in the graphic “◯” is corrected.

FIG. 6 is an explanatory diagram illustrating another example of the interruption correction process.
In another example of the interruption correction process, in addition to the extraction result of the predetermined color component by the predetermined color extraction unit 16, image data after the image distortion correction by the distortion correction unit 14 is also used to improve the accuracy of the interruption correction process. ing. That is, in another example of the interruption correction process, as shown in FIG. 6A, the binarization process is performed on the image data after the image distortion correction by the distortion correction unit 14 (S301). However, if binarization processing is performed at the time of difference extraction by the comparison extraction unit 15 or extraction of a predetermined color component by the predetermined color extraction unit 16, the image data after the binarization processing may be used. .
Further, the thinning process is executed for the extraction result of the predetermined color component by the predetermined color extraction unit 16 (S302), and the end point extraction process is further executed (S303). When the end points are extracted, the following processing is executed for all the extracted end points (S304).
First, one unprocessed end point is selected (S305), and an unprocessed end point that is within a predetermined distance from the selected first end point and is closest is the second end point. (S306). If there is a second end point (S307), it is determined whether or not there is a pixel group that connects the first end point and the second end point in the image data after binarization processing (S308). . That is, it is determined whether or not there is an overlapping portion of the images that causes the interruption. As a result, if there is an overlapping portion, the first end point and the second end point are connected to each other (S309), and both the first end point and the second end point are processed (S310). On the other hand, if there is no overlapping portion, the process returns to the above-described step (S306), and an end point that is within a predetermined distance from the first end point and is closest to the next end point is selected as the second end point. . At this time, if there is no end point to be selected, the connection between the end points is not performed, and the first end point is processed (S311). Such processing is performed for all end points until there are no unprocessed end points (S304 to S311).
Thereby, for example, when the figure shown in FIG. 6B is extracted, if the end points B and C exist within a predetermined distance from the end point A, the nearest end point C is selected. However, since there is no pixel group connecting the end points A and C in the binarized image data, the end points A and C are not connected. Then, an end point B that is the next closest to the end point C is selected. Since there is a pixel group in the binarized image data between the end point B and the end point A, the end point B is the end point. A will be connected. That is, the discontinuity portion in the graphic “O” is corrected without erroneously connecting “O” and “X”.

After the pixel group division processing and the discontinuity correction processing by the pixel group division unit 17 as described above, the shape recognition unit 18 recognizes the shape of the entered content of the correct / incorrect determination, that is, pattern matching with the graphic shape of “◯” or “×” To confirm whether the contents of the correct / incorrect determination entry are “correct” or “incorrect”. Since the pattern matching performed at this time may be realized using a known technique, the description thereof is omitted here.
Alternatively, the feature amount of the recognition target figure may be calculated and the shape may be recognized from the feature amount. For example, known features such as the number of holes and the area ratio of the target figure occupying the circumscribed rectangle may be used as the feature amount, and the description thereof is omitted here.

  Then, when the shape recognition unit 18 performs shape recognition for the entry contents of the correct / incorrect determination, the entry position recognition unit 19 subsequently recognizes the entry position on the educational material 4 for the input contents of the correct / incorrect determination.

Here, the recognition process of the correct / incorrect determination entry position by the entry position recognition unit 19 will be described in detail. FIG. 7 is a flowchart illustrating an example of a recognition processing procedure for a correct / incorrect determination entry position.
In the recognition processing of the correct / incorrect determination position, since a plurality of correct / incorrect determinations are entered on the educational material 4, first, the count number K for the correct / incorrect determination is set to "1" (S401). Thus, until the count number K exceeds the number of correct / incorrect determinations that can exist on the educational material 4, that is, the number of answer columns 4a (S402), correct / incorrect determination detected in a predetermined scanning order (“◯ ”Or“ x ”graphic), the position is recognized in order from the first.
For example, the position recognition may be performed by calculating circumscribing rectangle information of a graphic of “◯” or “x” (S403) and further calculating the center coordinates of the circumscribing rectangle (S404). Specifically, a circumscribed rectangle is extracted from a figure (continuous pixel group) to be recognized, and the xy coordinates of a predetermined point (for example, the upper left vertex) of the circumscribed rectangle, and the width (W) of the circumscribed rectangle. And the height (h) is calculated. Then, from these calculation results, the center x coordinate = x + w / 2 and the center y coordinate = y + h / 2 are calculated, and the calculation result is set as the recognition result of the position of the continuous pixel group, that is, the correct / incorrect determination entry position.
Such processing is repeated until all the correct / incorrect determinations existing on the educational material 4 are recognized while incrementing the count number K (S405) (S402 to S405).

  After the entry position recognition unit 19 recognizes the correct / incorrect determination entry position in this way, the information calculation unit 20 performs scoring for correct / incorrect determination. At this time, the information calculation unit 20 performs the scoring calculation by recognizing the result of the correct / incorrect determination input by the shape recognition unit 18, the result of the correct / incorrect determination input position by the input position recognition unit 19, and the original information holding / accumulating storage unit. 11 is based on the scoring information about each answer field 4a of the educational material 4 included in the electronic data of the educational material 4 stored and accumulated.

However, although entry of correct / incorrect judgment is generally performed corresponding to each answer field 4a on the educational material 4, since it is handwritten by a teacher or the like, the entry position for each answer field 4a is not necessarily uniquely determined. I don't mean.
On the other hand, it is necessary to clarify the correspondence between each answer column 4a and the entry position of the correct / incorrect determination when scoring the correct / incorrect determination. The scoring of correct / incorrect determination is performed based on the correct / incorrect determination corresponding to each answer field 4a and the results of the correct / incorrect determination (whether it is correct or incorrect) and the score for each answer field 4a. Because.

  From this, the information calculation unit 20 performs scoring for correct / incorrect determination in the following procedure. That is, the information calculation unit 20 obtains an overlapping area between the circumscribed rectangle of the correct / incorrect determination graphic such as “◯” or “x” and the area to be the answer column 4a on the educational material 4 and calculates the area (the area relative to the circumscribed rectangle). The correct / incorrect determination figure having the largest ratio) and the answer column 4a are associated with each other, and the correct / incorrect determination figure is set as the correct / incorrect determination result entered for the answer column 4a. However, when the ratio of the overlapping area to the circumscribed rectangle is less than the predetermined threshold, it is determined that the determination regarding the association is impossible because the overlapping portion is small. After the association, if the correct / incorrect graphic is “◯”, the score specified from the corresponding score information for the answer column 4a is added, and the correct / incorrect graphic is “×”. If there is, the score addition is not performed for the answer column 4a corresponding to the answer column 4a, and such scoring is performed for all the answer columns 4a on the teaching material 4 for education.

The area to be the answer field 4a on the educational material 4 is specified by the answer field position area information included in the electronic data of the educational material 4 as the score information for each answer field 4a or in the same manner as the score information. Shall be. FIG. 8 is an explanatory diagram showing a specific example of answer column position area information. The answer column position area information includes the number of the question existing on the educational material 4, the score for the answer of the question, and a predetermined point (for example, the upper left vertex) of the area treated as the answer column 4a for entering the answer of the question Information, and the width (W) and height (h) of the circumscribed rectangle, which are stored in advance in the original information storage / storage unit 11 in a table format associating them with each other as shown in the figure. It is what has been accumulated.
The following method may be used for scoring the correctness determination in the information calculation unit 28. The circumscribed rectangle center coordinates of the calculated correct / incorrect determination figure (“○” or “×”) are compared with the answer field position area information, and a predetermined point (for example, the upper left vertex) of the area described in the answer field position area information When the circumscribing rectangle center coordinates of the correct / incorrect determination figure are included in the rectangular area indicated by the xy coordinates and the width (W) and height (h) of the circumscribing rectangle, they are associated with each other.

Here, the score calculation for correct / incorrect determination by the information calculation unit 20 will be described in more detail. FIG. 9 is a flowchart illustrating an example of a processing procedure for scoring the correct / incorrect determination.
Since the plurality of correct / incorrect determinations are entered on the educational material 4 when scoring the correct / incorrect determination, first, the count number K for the correct / incorrect determination is set to “1” (S501). Thus, until the count number K exceeds the number of correct / incorrect determinations that can exist on the educational material 4, that is, the number of answer columns 4a (S502), correct / incorrect determination (“◯”) detected in a predetermined scanning order. ”Or“ x ”graphic), the processing for scoring is performed in order from the first.
That is, the area of the circumscribed rectangle of the Kth “◯” or “x” figure is calculated, and this is set to “L” (S503). Further, the count number P for the number of answer columns 4a (= number of questions) is set to “1” (S504), and if the count number P is less than or equal to the number of questions existing on the educational material 4 (S505). The answer field position area information about the answer field 4a is taken out. Then, an overlapping area between the Kth circumscribed rectangle and the Pth region is calculated, and the calculation result is “S (P)” (S506). Further, a ratio between the overlapping area S (P) and the circumscribed rectangular area L is calculated, and this is set as “R (P)” (S507). Such processing is repeated until the count value P is incremented (S508) and is completed for all answer field position area information (S505 to S508).
Thereafter, the maximum value of the ratio R (P) is obtained and is set to “Max” (S509), and the value of the count number P that maximizes the overlapping area S (P) is obtained, and this is designated as “Pmax”. (S510). If the maximum value Max is less than the predetermined threshold Th (S511), it is impossible to associate the correct / incorrect determination graphic with the answer column 4a, and the question number corresponding to the correct / incorrect determination graphic is unknown. Judgment is made (S512). On the other hand, if the value of the maximum value Max is equal to or greater than the predetermined threshold Th (S511), then it is determined whether the Kth correct / incorrect determination graphic is “◯” or “×” ( S513). As a result, if it is “◯”, the score for the answer to the question of the count number Pmax is added in the “scoring result by question” described later (S514). On the other hand, if “x”, the score is not added to the answer to the question of the count number Pmax, and “0 points” is set (S515).
Then, such a process is repeated until all the correct / incorrect determinations on the educational material 4 are completed (S502 to S515) while incrementing the value of the count number K (S516).

  FIG. 10 is an explanatory diagram showing a specific example of the problem-specific scoring results. The scoring result for each question is information consisting of the number of the question on the educational material 4, the correctness / incorrectness determination for the answer of the question, each score based on the correctness / incorrectness determination, and the total score. In addition, these are output from the information calculation unit 20 for each educational material 4 in a table format that associates them with each other.

Through such a series of automatic scoring processes, the information calculation unit 20 can score and correct the correctness / incorrectness determination entered in the educational material 4 and obtain the total score.
That is, the function as the information calculation means 36 scores the correct / incorrect determination and calculates the total score.

After the automatic scoring process as described above, a totaling calculation process is subsequently performed. That is, in the data processing unit 2, the calculation unit 21 uses, for example, an average score in each class unit or grade unit, an overall ranking, Calculations on information such as deviation values are performed. It is assumed that what item (information) the calculation unit 21 performs calculation is set in advance. Note that the arithmetic processing itself performed by the arithmetic unit 21 may be performed using a known technique, and thus detailed description thereof is omitted here.
That is, the function as the calculation means 37 performs a calculation for obtaining other information attached to the calculation result based on the calculation result by the information calculation means 36.

[Description of feature value calculation processing]
Next, a feature amount calculation process that is performed separately or in parallel with the automatic scoring process and the totaling calculation process described above will be described.
In the feature amount calculation processing, the data processing unit 2 uses the image data obtained by the first feature amount calculation unit 22 in the scanner unit 1 based on the difference extraction result by the comparison extraction unit 15 obtained in the above-described automatic scoring process. Among them, the image feature amount is calculated for the part obtained from the solver information column 4c. That is, since the function as the first feature amount calculating unit 38 calculates the image feature amount of the image data obtained by the first image reading unit 31 based on the difference extraction result in the first additional record data extracting unit 34. is there.

The calculation of the image feature amount can be performed as described below.
For example, projection histograms on the vertical and horizontal axes are collected for the part of the answerer information column 4c of the image data to be processed. As a result, a histogram of the pixel distribution in the answerer information column 4c is obtained.
The answerer information column 4 c is filled with handwritten characters of the answerer (student), but the contents of the entry differ depending on the educational material 4. Therefore, the pixel distribution in the answerer information column 4c is also characteristic for each educational material 4. From this, the histogram of the pixel distribution in the answerer information column 4c is appropriate for handling as an image feature amount because it expresses the characteristic of the pixel distribution quantitatively.
In this case, the image data to be processed is after the image distortion is corrected by the distortion correction unit 14, and it is desirable that the image data be further binarized. This is because binarization can facilitate the processing for making a histogram and improve accuracy.
The image feature amount is not necessarily limited to the histogram of the pixel distribution in the answerer information column 4c. For example, the image feature amount is suitable for handling as an image feature amount, such as the pixel distribution represented by run length. Any other known technique may be used as long as it is a proper one.

In this way, when the first feature value calculation unit 22 calculates the image feature value obtained from each educational material 4, the calculation result of the image feature value, the score totaling result and the calculation by the information calculation unit 20 are thereafter calculated. The association unit 23 associates the calculation results obtained by the unit 21 with each other. At this time, the results obtained from the same educational material 4 are associated with each other. When the associating unit 23 performs associating, the database unit 24 stores and holds the state in which the results are associated with each other.
In other words, the function as the feature quantity / information association unit 39 is configured so that the scoring result by the information calculation unit 36 and the calculation result by the calculation unit 37 and the calculation result of the image feature quantity by the first feature quantity calculation unit 38 are mutually connected. In addition to the association, the function as the database means 40 stores and holds the scoring and calculation results and the calculation results and the image feature amount calculation results in association with each other.

  Through the above-described feature amount calculation processing, for each educational material 4 whose image has been read by the scanner unit 1, the score totaling result and the calculation result of the contents entered for correct / incorrect determination are displayed in the answerer information column 4c. It is associated with the image feature amount and stored in the database unit 24.

[Description of print output processing]
In the print output process, the calculation result in the automatic scoring process and the calculation result in the total calculation process described above are printed out on the educational teaching material 4 from which the calculation result and the calculation result are obtained.
At this time, the printed output on the educational material 4 includes the relationship between the calculation result in the automatic scoring process and the calculation result in the totaling calculation process (hereinafter simply referred to as “printed output content”) and each educational material 4. Is maintained correctly, that is, it is necessary to appropriately print out the printed output content on each educational material 4.
Therefore, in the print output process, first, for the educational material 4 to be printed, the second feature value processing unit 25 identifies and specifies the educational material 4.

  Specifically, the function as the second image reading unit 41 reads an image of the educational teaching material 4 to be printed, and obtains image data from the answerer information column 4 c of the educational teaching material 4. obtain.

  After the image reading by the second image reading means 41, the function as the second original searching means 42 identifies and specifies the electronic data to be compared with the image data obtained by the image reading, and identifies and specifies it. The electronic data is searched from the original information storage means 32. The identification specification and search at this time may be performed by a method similar to that in the original identification specification and search in the automatic scoring process described above.

After the identification and identification of the educational teaching material 4 and its search, the function as the second additional record data extraction means 43 is followed by the electronic data on the original as the search result and the image reading by the second image reading means 41. Is compared with the image data obtained in step (1), and the difference between them is extracted. By this difference extraction, the content to be added to the answerer information column 4c of the educational material 4 is extracted.
Then, after the difference extraction for the answerer information column 4c, the function as the second feature amount calculation means 44 is based on the difference extraction result, and the image feature amount for the image data obtained by the second image reading means 41. Is calculated. The calculation of the image feature amount at this time may be performed by a method similar to the case of the image feature amount calculation by the first feature amount calculation means 38 in the automatic scoring process described above.

  After a series of processing by the second feature amount processing unit 25 such as identification and identification of the educational material 4, extraction of the difference from the original and calculation of the image feature amount based on the difference extraction result, calculation is then performed. The information acquisition unit 26 extracts the print output content from the database unit 24 based on the processing result by the second feature amount processing unit 25. In other words, in the calculation information acquisition unit 26, the function as the calculation information acquisition unit 45 uses the calculation result of the image feature quantity in the second feature quantity calculation unit 44 as a key and the calculation result by the second feature quantity calculation unit 44. Print output contents (calculation result in the automatic scoring process and calculation result in the total calculation process) corresponding to the image feature quantity (calculation result by the first feature quantity calculation means 38) that is the same as or almost the same as a certain image feature quantity are stored in the database. A search is made from among the data stored and held by the means 40. If there is a print output content corresponding to the same image feature amount, the printer unit 3 is caused to print out the print output content. On the other hand, if there is no print output content corresponding to the same image feature amount, there is a high possibility that appropriate print output cannot be performed. Therefore, the print output process is interrupted, and an alarm output to that effect is performed.

  Printing on the educational material 4 by the printer unit 3 may be performed using a known electrophotographic technique. In other words, when the printer unit 3 receives the print output content taken out from the database unit 24 by the calculation information acquisition unit 26, the printer unit 3 can decompose the print output content, and the printer unit 3 can output the print output content. The data format is converted and printed on the educational material 4. The print output at this time is performed only on a specific area on the educational material 4, specifically on the information output field 4 d. Therefore, the printer unit 3 needs to recognize the position of the information output column 4d when performing the decomposing. The position recognition of this information output column 4d can be performed based on the identification specification of the educational material 4 by the second feature quantity processing unit 25 and the electronic data in the original information holding / accumulating unit 11 corresponding to the identification specification result. It is conceivable to individually perform various kinds of educational materials 4. However, the position recognition may be omitted if the information output fields 4d in all kinds of educational materials 4 are all set to be the same.

Through the processing in the printer unit 3 as described above, the calculation result in the automatic scoring process and the calculation result in the total calculation process are the information output fields on the educational material 4 from which the calculation result and the calculation result are obtained. It is printed out in 4d.
The print output process in the printer unit 3 is not necessarily performed for both the calculation result in the automatic scoring process and the calculation result in the totaling calculation process, and may be performed at least for the calculation result in the automatic scoring process. This is because the calculation result in the total calculation process is information accompanying the calculation result in the automatic scoring process.

  As described above, in the teaching material processing apparatus, the teaching material processing method, and the teaching material processing program according to the present embodiment, the content of correct / incorrect determination (for example, “◯” or “ After recognizing the “x” graphic shape) and performing the totaling of the correctness / incorrect judgment entered in the educational material 4 based on the recognition result, the totaling result (for example, total score, overall ranking, average score, etc.) ) Is printed out on the educational material 4 from which the image data is read. Therefore, in the case of the educational teaching material 4 in which the correctness / incorrectness determination is entered, since the image data for the educational teaching material 4 is read, the entered correctness / incorrectness determination is automatically performed, and as a result, the educational teaching material 4 is scored. Processing is labor-saving. In addition, since the scoring result is printed out on the educational material 4, the answering person can easily recognize the scoring result by referring to the educational material 4 after scoring. .

  Further, when the score totaling result is printed out, the image feature amount of the image data read from the educational material 4 to be printed out is calculated, and the corresponding correctness determination is performed using the image feature amount as a key. The scoring result is taken out from the already held memory. That is, identification and identification of the educational material 4 is performed based on the image feature amount on the educational material 4. Therefore, the scoring result of correct / incorrect determination is accurately printed on the educational material 4 from which the result is obtained. Moreover, since the educational teaching material 4 is identified and specified using the image feature amount as a key, it is not necessary to assign individual identification information to the educational teaching material 4 for the identification and specification, and erroneous recognition occurs. There is no need for character recognition of handwritten characters to be obtained.

  That is, according to the teaching material processing apparatus, the teaching material processing method, and the teaching material processing program according to the present embodiment, the educational teaching material can be used for the educational teaching material 4 used in the educational institution even if the scoring process is reduced. 4 can be identified and specified accurately and accurately, and the result of the scoring process can be accurately output on the educational material 4 from which the result is obtained without imposing a heavy burden. It becomes like this. Therefore, it becomes very convenient when used in an educational institution, and a highly reliable scoring process can be performed smoothly.

  In particular, as described in the present embodiment, the calculation of the image feature quantity that is the basis for identification and identification of the educational material 4 is not performed directly on the image reading result, but the difference extraction result from the original electronic data In this case, the original image portion, that is, the image portion common to each educational material 4 is excluded, and differs depending on each educational material 4 such as handwritten characters of the answerer (student). Since the image feature amount is calculated for the image portion, the characteristic of each educational material 4 is surely reflected in the calculation result, and as a result, the educational material 4 with high accuracy and reliability is identified. Identification can be realized.

  Further, as described in the present embodiment, the image feature amount is not calculated for the entire area of the educational material 4, but only for the part of the answerer information column 4 c included in the educational material 4. By calculating, it is possible to keep the processing accuracy required for the identification and identification of the educational material 4 high while maintaining the processing load as low as possible. As a result, it is possible to speed up the processing.

  In addition, although this embodiment demonstrated the suitable Example of this invention, this invention is not limited to the content.

For example, in the present embodiment, when recognizing the contents of correct / incorrect determination or calculating the image feature amount, image data obtained by image reading is compared with electronic data (original image data) about the original. As an example. This is because the comparison object is the original image data, so that it can be expected to improve accuracy such as extraction of entry contents for correct / incorrect determination. However, the comparison is not necessarily performed in comparison with the original image data. For example, image data obtained from a plurality of educational materials 4 by image reading are compared with each other, and a matching point (that is, a problem sentence) between the comparison results is obtained. Etc.) and differences (that is, additional portions such as answers and correct / incorrect judgments) are extracted, and it is conceivable to perform based on the differences. In this way, if image data obtained from a plurality of educational materials 4 are compared with each other, it is not necessary to store and store the original image data, so that simplification of the apparatus configuration can be expected.
Further, in the present embodiment, when calculating the image feature amount, the image data obtained by reading the image is compared with the electronic data (original image data) of the original, and the image obtained as a result of the difference extraction is used. An image feature amount may be calculated from image data obtained by image reading. Also, the image data obtained by reading the image or the image of the difference extraction result is divided into a plurality of areas, the feature amount is calculated for each of the plurality of regions, and the plurality of feature amounts are associated with the score totaling result and the calculation result. The data may be stored in the database, or the score totaling result and the calculation result may be searched from the database using a plurality of feature amounts.

  Further, in the present embodiment, a case where a difference extraction result of a predetermined color component, specifically, for example, a red component, for example, is recognized as an entry content of correctness determination is taken as an example. This is because it is generally considered that the entry of correctness / incorrectness determination is performed in red, and by making the difference for the predetermined color component the correctness / incorrectness determination entry content, the recognition process is facilitated, and that This is to improve the reliability of the recognition accuracy. However, the additional portion extraction from the educational material 4 represented by the extraction of the correct / incorrect determination is not necessarily limited to the predetermined color component, particularly the red component, and may be performed using other known methods. It doesn't matter.

In addition, the distortion correction process, the break correction process, and the like described in the present embodiment are performed to improve recognition accuracy, but are not necessarily essential.
Further, when the answer column 4a and the entry position of the correct / incorrect determination are associated with each other in the scoring of the correct / incorrect determination, the overlapping area between the circumscribed rectangle of the correct / incorrect determination graphic as described in the present embodiment and the area of the answer column 4a. For example, it is conceivable that the association is performed based on the distance between the respective center coordinates, or the association is simply performed based on whether or not there is an overlapping portion.

  As described above, the present invention can be modified as appropriate without departing from the scope of the description of the present embodiment.

It is a block diagram which shows the specific system configuration example of the teaching material processing apparatus which concerns on this invention. It is explanatory drawing which shows a specific example of the educational material. It is a block diagram which shows the function schematic structural example of the teaching material processing apparatus which concerns on this invention. It is explanatory drawing which shows the outline | summary of the basic processing operation example in the teaching material processing apparatus which concerns on this invention. It is explanatory drawing which shows an example of a discontinuation correction process. It is explanatory drawing which shows the other example of a discontinuation correction process. It is a flowchart which shows an example of the recognition processing procedure of a correct / incorrect determination entry position. It is explanatory drawing which shows a specific example of answer column position area information. It is a flowchart which shows an example of the process sequence of scoring total of a correct / incorrect determination. It is explanatory drawing which shows one specific example of the scoring result according to a problem.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 1 ... Scanner part, 2 ... Data processing part, 3 ... Printer part, 4 ... Educational teaching material, 4a ... Answer column, 4b ... Identification information column, 4c ... Answerer information column, 4d ... Information output column, 11 ... Original information Retention and accumulation unit, 12 ... Image data analysis unit, 13 ... Teaching material discrimination unit, 14 ... Distortion correction unit, 15 ... Comparison extraction unit, 16 ... Predetermined color extraction unit, 17 ... Pixel group division unit, 18 ... Shape recognition unit, 19 ... Entry position recognition unit, 20... Information calculation unit, 21... Calculation unit, 22... First feature amount calculation unit, 23 ... Association unit, 24 ... Database unit, 25 ... Second feature amount processing unit, 26. Acquisition unit 31 ... first image reading unit 32 ... original information storage unit 33 ... first original search unit 34 ... first additional record data extraction unit 35 ... correction determination extraction unit 36 ... information calculation unit 37 ... Calculation means, 38... First feature quantity calculation means, 39... Feature quantity / information. Corresponding means, 40 ... database means, 41 ... second image reading means, 42 ... second original searching means, 43 ... second additional data extracting means, 44 ... second feature quantity calculating means, 45 ... calculation information obtaining means, 46. Printing means

Claims (6)

First image reading means for obtaining image data from the educational material by performing image reading on the educational material in which the answer is entered in the answer column and whether the answer is correct or incorrect is entered;
Extraction means for extracting the contents of the correct / incorrect determination from the image data obtained by the first image reading means;
A calculation / calculation unit that performs scoring for correctness / incorrectness written in the educational material for the educational material for which the first image reading unit has performed image reading based on the extraction result by the extraction unit;
First feature amount calculating means for calculating an image feature amount for image data obtained by the first image reading means;
Database means for storing and holding the score totaling result of correctness / incorrectness determination by the calculating / calculating means and the image feature value calculation result by the first feature value calculating means in association with each other;
Print means for printing out the score totaling result of correctness / incorrectness judgment by the calculation / calculation means on the educational material;
Second image reading means for obtaining image data from the educational material by performing image reading on the educational material to be printed by the printing means;
Second feature amount calculating means for calculating an image feature amount for the image data obtained by the second image reading means;
Calculation information acquisition means for taking out the result of scoring of the correctness / incorrectness corresponding to the image feature quantity from the database means and printing the print means on the print means using the image feature quantity calculation result by the second feature quantity calculation means as a key; A teaching material processing apparatus comprising: The first feature amount calculation unit divides the image data obtained by the first image reading unit into a plurality of regions, calculates a feature amount for each divided region, and calculates the plurality of feature amounts for each region and the calculation / Corresponding the scoring result of correctness determination by the computing means, and storing and holding in the database means,
The second feature amount calculation unit divides the image data obtained by the second image reading unit into a plurality of regions that are the same as the divided region, calculates a feature amount for each of the divided regions, and calculates a plurality of values calculated for each region. The teaching material processing apparatus according to claim 1, wherein the feature amount is used as a key to be extracted from the score totaling result of the correctness determination from the database unit. Original information storage means for storing and storing image data of the original teaching material;
A first additional data extraction means for comparing the image data obtained by the first image reading means with the image data held and accumulated by the original information accumulation means;
The image data obtained by the second image reading means is compared with the image data held and accumulated by the original information accumulation means, and a second additional data extraction means for extracting the difference is provided.
The first feature amount calculating unit and the second feature amount calculating unit calculate the image feature amount based on a difference extraction result in the first additional record data extraction unit and the second additional record data extraction unit, respectively. The teaching material processing apparatus according to claim 1 or 2, characterized in that The said 1st feature-value calculation means and the said 2nd feature-value calculation means calculate the image feature-value about the image data obtained from the answerer information column which the said teaching material has. The teaching material processing apparatus according to 1, 2, or 3. A first image reading step for obtaining image data from the educational material by performing image reading on the educational material in which the answer is entered in the answer column and whether the answer is correct or incorrect is entered;
An extraction step for extracting the content of the correctness determination from the image data obtained in the first image reading step;
A calculation / calculation step for performing scoring of correct / incorrect judgment written in the educational material for the educational material subjected to image reading in the first image reading step based on the extraction result in the extraction step;
A first feature amount calculating step for calculating an image feature amount for the image data obtained in the first image reading step;
A database step of storing and holding the score totaling result of correctness determination in the calculation / calculation step and the calculation result of the image feature amount in the first feature amount calculation step in association with each other;
A printing step for printing out the scoring result of the correctness determination in the calculation / calculation step on the educational material;
A second image reading step of obtaining an image data from the educational material by performing image reading on the educational material to be printed in the printing step;
A second feature amount calculating step for calculating an image feature amount for the image data obtained in the second image reading step;
Using the calculation result of the image feature amount in the second feature amount calculation step as a key, the score totaling result of the correctness determination corresponding to the image feature amount is taken out from the stored and held in the database step and printed in the print step A teaching material processing method comprising: an arithmetic information acquisition step for output. A computer connected to an image reading apparatus that performs image reading and a printing apparatus that performs print output,
First image reading means for obtaining image data as a result of image reading for an educational teaching material in which an answer is entered in an answer column and whether a correct / incorrect determination is entered for the answer;
Extraction means for extracting the contents of the correct / incorrect determination from the image data obtained by the first image reading means;
A calculation / calculation unit that performs scoring for correctness / incorrectness written in the educational material for the educational material for which the first image reading unit has performed image reading based on the extraction result by the extraction unit;
First feature amount calculating means for calculating an image feature amount for image data obtained by the first image reading means;
Database means for storing and holding the score totaling result of correctness / incorrectness determination by the calculating / calculating means and the image feature value calculation result by the first feature value calculating means in association with each other;
Printing means for causing the printing apparatus to print out the scoring result of the correctness / incorrectness determination by the calculation / calculation means;
Second image reading means for obtaining image data as a result of image reading with respect to educational teaching materials to be printed out in the printing apparatus;
Second feature amount calculating means for calculating an image feature amount for the image data obtained by the second image reading means;
Calculation information acquisition means for taking out the result of scoring the correctness / incorrectness corresponding to the image feature quantity from the database means and using the result of calculation of the image feature quantity by the second feature quantity calculation means as a key for printing output by the printing means A teaching material processing program characterized by functioning as

Images