JP6489041B2 - Information processing apparatus and program - Google Patents

Description

  The present invention relates to an information processing apparatus and program capable of creating a hole filling problem using a marked character string as an answer from a document image including a plurality of markings superimposed on a plurality of character strings.

  Read the image of the manuscript with the character string that is the answer to the problem specified by handwritten marking, extract the marking image from the image data of the read manuscript, extract the character string at the marking position, and at the marking position A technique for creating a hole filling problem in which a character string is erased and an answer column is set in the erased portion of the character string is known (Patent Document 1, Abstract). Optical character recognition (OCR, Optical Character Recognition) is known as a technique for extracting a character string (Patent Document 2).

JP 2007-4523 A JP 11-328309 A

  In an information processing apparatus capable of creating a hole filling problem, it is desired that both the problem creator and the respondent are more user-friendly.

  In view of the circumstances as described above, an object of the present invention is information that can create a hole filling problem with a marked character string as an answer from a document image including a plurality of markings superimposed on a plurality of character strings. In the processing apparatus and the program, the convenience of the user is improved.

In order to achieve the above object, an information processing apparatus according to an aspect of the present invention provides:
A marking extracting unit for extracting the plurality of markings from a document image including a plurality of markings respectively superimposed on a plurality of character strings;
Among the plurality of character strings on which the markings are superimposed, the same character string identifying unit for identifying the same character string,
A code determination unit that assigns the same code to the same character string and assigns different codes to different character strings.

  According to this embodiment, the same code is assigned to the same character string, and different codes are assigned to different character strings. As a result, since different codes are assigned to a plurality of blanks in which the same character string is to be answered, there is no possibility that the respondent will misunderstand that different words should be answered.

Information processing device
A blank creation unit for creating a blank image to be superimposed on each of the plurality of character strings on which the markings are superimposed,
The image processing apparatus further includes an image combining unit that generates a combined image by combining the document image, the plurality of blank images, and a code image that is an image of the assigned code.

  According to this embodiment, a composite image is created by combining the document image, the blank image, and the code image. As a result, the problem creator does not have to manually assign the same code to a plurality of blanks to which the same character string should be answered, and there is no possibility of assigning an incorrect code.

Information processing device
A marking determination unit that determines the position and shape of each of the plurality of markings extracted by the marking extraction unit in the document image;
Based on the determined positions and shapes of the plurality of markings, further comprising a character string extraction unit that extracts the plurality of character strings on which the respective markings are superimposed,
The same character string identifying unit identifies the same character string among the plurality of character strings extracted by the character string extracting unit.

The same character string identification unit is
A character string identifying unit for identifying the plurality of character strings extracted by the character string extracting unit;
A character string comparison unit that identifies the same character string by comparing the plurality of character strings identified by the character string identification unit and identifying the same character string.

The character string identification unit
Extracting a plurality of characters from each of the plurality of character strings extracted by the character string extraction unit,
Identifying each of the extracted plurality of characters;
The plurality of character strings are identified by combining the plurality of characters included in the character string.

  The character string identifying unit identifies the plurality of character strings by optical character recognition.

  The same character string identification unit determines the similarity between the plurality of character strings extracted by the character string extraction unit, and when the similarity is equal to or greater than a threshold, the plurality of character strings are the same character string. It has a character string similarity determination unit for determination.

  According to this embodiment, the character actually included in the character string is not a problem, and it is only necessary to know that the character string is the same. Therefore, the processing amount is small as compared with optical character recognition, and a database required for optical character recognition. Is unnecessary.

In order to achieve the above object, a program according to an aspect of the present invention is provided.
Information processing device
A marking extracting unit for extracting the plurality of markings from a document image including a plurality of markings respectively superimposed on a plurality of character strings;
Among the plurality of character strings on which the markings are superimposed, the same character string identifying unit for identifying the same character string,
The same code is assigned to the same character string and functions as a code determination unit that assigns different codes to different character strings.

  According to the present invention, in an information processing apparatus and program capable of creating a hole-filling problem using a marked character string as an answer from a document image including a plurality of markings superimposed on a plurality of character strings, Convenience is improved.

1 is a block diagram illustrating a hardware configuration of an image forming apparatus according to a first embodiment. 2 is a block diagram illustrating a functional configuration of the image forming apparatus. FIG. 3 is a flowchart illustrating an operation of the image forming apparatus. It is a figure for demonstrating operation | movement of an image forming apparatus. FIG. 6 is a block diagram illustrating a functional configuration of an image forming apparatus according to a second embodiment. 3 is a flowchart illustrating an operation of the image forming apparatus.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings.

(1. First embodiment)
(1-1. Hardware Configuration of Image Forming Apparatus)
FIG. 1 is a block diagram showing a hardware configuration of an image forming apparatus according to the first embodiment of the present invention.

  An information processing apparatus according to each embodiment of the present invention is an image forming apparatus (for example, MFP, Multifunction Peripheral), and is hereinafter referred to as an MFP.

  The MFP 1 includes a control unit 11. The control unit 11 includes a CPU (Central Processing Unit), a RAM (Random Access Memory), a ROM (Read Only Memory), a dedicated hardware circuit, and the like, and controls overall operation of the MFP 1. A computer program that causes the MFP 1 to function as each functional unit (described later) is stored in a non-transitory storage medium such as a ROM.

  The control unit 11 is connected to an image reading unit 12, an image processing unit 14, an image memory 15, an image forming unit 16, an operation unit 17, a storage unit 18, a network communication unit 13, and the like. The control unit 11 performs operation control of each of the above connected units and transmission / reception of signals or data to / from each unit.

  The control unit 11 operates for each function such as a scanner function, a print function, and a copy function function in accordance with a job execution instruction input from the user through the operation unit 17 or a personal computer (not shown) connected via a network. Controls the drive and processing of the mechanisms necessary to perform the control.

  The image reading unit 12 reads an image from a document.

  The image processing unit 14 performs image processing on the image data of the image read by the image reading unit 12 as necessary. For example, the image processing unit 14 performs image processing such as shading correction in order to improve the quality after the image read by the image reading unit 12 is formed.

  The image memory 15 has an area for temporarily storing document image data obtained by reading by the image reading unit 12 and temporarily storing data to be printed by the image forming unit 16.

  The image forming unit 16 forms an image of the image data read by the image reading unit 12.

  The operation unit 17 includes a touch panel unit and operation key units that receive instructions from the user regarding various operations and processes that can be executed by the MFP 1. The touch panel unit includes a display unit 17a such as an LCD (Liquid Crystal Display) provided with a touch panel.

  The network communication unit 13 is an interface for connecting to a network.

  The storage unit 18 is a large-capacity storage device such as an HDD (Hard Disk Drive) that stores a document image read by the image reading unit 12.

(1-2. Functional Configuration of Image Forming Apparatus)
FIG. 2 is a block diagram illustrating a functional configuration of the image forming apparatus.

  By executing the information processing program, the MFP 1 serves as a marking extraction unit 101, a marking determination unit 102, a character string extraction unit 103, an identical character string identification unit 110, a code determination unit 104, a blank creation unit 105, and an image composition unit 106. Function.

  The marking extraction unit 101 extracts a plurality of markings respectively superimposed on a plurality of character strings from the document image read by the image reading unit 12.

  The marking determination unit 102 determines the position and shape of each of the plurality of markings extracted by the marking extraction unit 101 in the document image.

  The character string extraction unit 103 extracts a plurality of character strings on which the respective markings are superimposed based on the positions and shapes of the plurality of markings determined by the marking determination unit 102.

  The same character string identification unit 110 includes a character string identification unit 111, an OCR database 112, and a character string comparison unit 113, and identifies the same character string among a plurality of character strings on which markings are superimposed. To do.

  The code determination unit 104 assigns the same code to the same character string identified by the character string comparison unit 113 and assigns different codes to different character strings.

  The blank creation unit 105 creates blank images that are respectively superimposed on a plurality of character strings on which markings are superimposed.

  The image composition unit 106 creates a composite image by combining the document image read by the image reading unit 12, the blank image created by the blank creation unit 105, and the code image that is the code image assigned by the code determination unit 104. To do.

(1-3. Operation of Image Forming Apparatus)
FIG. 3 is a flowchart showing the operation of the image forming apparatus. FIG. 4 is a diagram for explaining the operation of the image forming apparatus.

  As a premise, a character string as text data is printed on an original (typically, paper). Alternatively, a character string image as image data is formed on the document (a document on which the character string is printed is copied). A plurality of partial character strings (jukugo, phrases, numerical values, etc.) of the entire character string are marked by hand using a fluorescent marker pen or the like by a problem creator as a user. The marked character string is a character string that becomes an answer in the hole filling problem.

  The image reading unit 12 optically scans the original and reads the original image (step S101, see FIG. 4). The “document image” is image data of a document document including a large number of character strings as a whole, and includes a plurality of markings (hatched portions shown in FIG. 4) superimposed on a plurality of character strings. The “character string” is a phrase (word, phrase, sentence, etc.), a numerical value, and the like, strictly speaking, an image thereof.

  The marking extraction unit 101 extracts a plurality of markings respectively superimposed on a plurality of character strings from the document image read by the image reading unit 12 (step S102). Specifically, the marking extraction unit 101 extracts a region having a specific shape and size (such as a strip-shaped rectangle having a specific width) that is different from the background (white or the like) in brightness and / or saturation and the like as a marking. .

  The marking determination unit 102 determines the position and shape in the document image of each of the plurality of markings extracted by the marking extraction unit 101 (step S103). Specifically, the marking determination unit 102 calculates the entire document image as the entire coordinate system and the marking position and shape as coordinates.

  The character string extraction unit 103 extracts a plurality of character strings on which the respective markings are superimposed based on the positions and shapes (coordinates) of the plurality of markings determined by the marking determination unit 102 (step S104). Specifically, the character string extraction unit 103 extracts a character string on which a marking defined by the position and shape (coordinates) determined by the marking determination unit 102 is superimposed by edge detection. Note that the character string extraction unit 103 does not extract one character and one character included in the character string, but extracts the entire character string on which one marking is superimposed as one character string.

  The character string identifying unit 111 identifies each of a plurality of character strings extracted by the character string extracting unit 103. Specifically, the character string identification unit 111 extracts a plurality of characters from each of the plurality of character strings extracted by the character string extraction unit 103. “Character” is one character per character included in the character string (may be one word per word depending on the language), and is strictly an image thereof. The character string identifying unit 111 refers to the OCR database 112 and identifies each of the extracted plurality of characters (step S105). Specifically, in the OCR database 112, character image patterns and character codes are associated and registered one by one. The character string identification unit 111 searches the OCR database 112 for an image pattern indicating the extracted character, and acquires a character code associated with the image pattern obtained by the search. The character string identifying unit 111 acquires character codes for all characters included in the character string. The character string identifying unit 111 identifies the character string by combining the character codes of all the characters included in the character string (step S106). The character string identifying unit 111 extracts characters from all the character strings on which the marking is superimposed, acquires the character codes indicated by the characters, combines the character codes, and identifies the character strings based on the combined character codes. .

  The character string comparison unit 113 identifies the same character string by comparing the character strings identified by the character string identification unit 111 and identifying the same character string (step S107). Specifically, the character string comparison unit 113 identifies the same character string by comparing the combined character codes with respect to all the character strings on which the marking is superimposed.

  The code determination unit 104 assigns the same code (numbers, characters, symbols, etc.) to the same character string identified by the character string comparison unit 113, and assigns different codes to different character strings (step S108).

  The blank creation unit 105 creates blank images that are respectively superimposed on a plurality of character strings on which markings are superimposed (see step S109, FIG. 4). Specifically, the blank creating unit 105 erases the character string extracted by the character string extraction unit 103 by edge detection (step S104) and the edge portion of the marking protruding from the character string ( Create a blank image of coordinates. The blank image may be a simple blank or may include a predetermined style (underline, rectangular frame, parentheses, etc.). In the example shown in FIG. 4, the blank image includes an underline.

  The image composition unit 106 reads the original image read by the image reading unit 12 (step S101), the blank image created by the blank creation unit 105 (step S109), and the image assigned by the code determination unit 104 (step S108). A synthesized image is created by synthesizing the encoded image (see step S110, FIG. 4). Specifically, the image composition unit 106 arranges a blank image whose shape and position are defined by coordinates in the coordinate system of the document image. Then, the image composition unit 106 arranges a code of a predetermined style (font, size, etc.) at a predetermined position (center, left end, etc.) of the blank image arranged in the document image, thereby synthesizing. Create an image. In the example shown in FIG. 4, the document image, the blank image including the underline, and the code image are combined.

  The image forming unit 16 forms (prints out) the composite image created by the image composition unit 106 on paper (step S111).

(2. Second Embodiment)
In the following description, the same configurations and operations as those of the first embodiment will not be described, and different points will be mainly described.

  In the first embodiment, the same character string identification unit 110 identifies a character string by optical character recognition (OCR) (step S105) (step S106), and identifies the same character string (step S107). On the other hand, in the second embodiment, the same character string identification unit identifies the same character string by a method different from optical character recognition (OCR).

(2-1. Functional Configuration of Image Forming Apparatus)
FIG. 5 is a block diagram illustrating a functional configuration of the image forming apparatus according to the second embodiment.

  By executing the information processing program, the MFP 2 performs a marking extraction unit 101, a marking determination unit 102, a character string extraction unit 103, a character string similarity determination unit 201, a code determination unit 104, a blank creation unit 105, and an image composition unit 106. Function as. The MFP 2 has a character string similarity determination unit 201 instead of the character string identification unit 111, the OCR database 112, and the character string comparison unit 113 as the same character string identification unit 110 of the first embodiment. Others are the same as those of the MFP 1 of the first embodiment.

  The character string similarity determination unit 201 determines the similarity between a plurality of character strings extracted by the character string extraction unit 103, and determines that the plurality of character strings are the same character string when the similarity is equal to or greater than a threshold value. To do.

(2-2. Operation of Image Forming Apparatus)
FIG. 6 is a flowchart showing the operation of the image forming apparatus.

  Steps S101 to S104 are the same as those in the first embodiment.

  After step S104, the character string similarity determination unit 201 determines the similarity between a plurality of character strings extracted by the character string extraction unit 103 (step S104). If the similarity is equal to or greater than a threshold, a plurality of character strings Are the same character strings (step S201). Specifically, the character string similarity determination unit 201 compares the image patterns (pixels) of the character strings, and determines that the character strings are the same character string when the overlapping degree of the image patterns is equal to or greater than a threshold value. This threshold value may be a value that can be determined to be the same character string even if the character configuration is the same but the font is different. For example, the threshold is 90% or the like, and the user may arbitrarily set the identification level.

  After step S201, steps S108 to S111 are the same as in the first embodiment.

(3. Modified examples)
In each embodiment, the image reading unit 12 reads a document image (step S101). Alternatively, the MFPs 1 and 2 may receive document images from an information processing apparatus (not shown) connected to the network via the network communication unit 13.

(4. Summary)
When creating a hole-filling problem using an original manuscript, a character string as an answer may appear many times in one sentence. In this case, if the character string that becomes the answer is displayed as a hint in the sentence, it is necessary to leave all the same character strings that become the answer blank. That is, there are a plurality of blanks in which the same character string should be answered. However, if different codes are assigned to a plurality of blanks in which the same character string is to be answered, the respondent may misunderstand that he / she should answer different words. In order to prevent this situation, it is troublesome for the problem creator to manually assign the same code to a plurality of blanks to which the same character string should be answered. In particular, when the total number of blanks is large or when there are a plurality of sets of the same character string, if the problem creator manually assigns a code, there is a possibility that an incorrect code is assigned.

  In contrast, according to each embodiment, the MFP 1 assigns the same code to the same character string, and assigns different codes to different character strings (step S108). As a result, since different codes are assigned to a plurality of blanks in which the same character string is to be answered, there is no possibility that the respondent will misunderstand that different words should be answered. In addition, there is no need for the problem creator to manually assign the same code to a plurality of blanks in which the same character string should be answered, and there is no possibility of assigning an incorrect code.

  In the second embodiment, the MFP 2 determines the similarity between a plurality of character strings, and determines that the plurality of character strings are the same character string when the similarity is equal to or greater than a threshold value (step S201). That is, the characters actually included in the character string are not a problem, and it is only necessary to know that the character strings are the same. The second embodiment has an advantage that the processing amount is smaller than that of the OCR of the first embodiment and a database is unnecessary.

  In addition, in each embodiment, although the process when the character string which has a some character was marked was demonstrated, also when the character string which consists of one character is marked, it processes according to FIG.3 and FIG.6. Is also possible. In this case, in step S106 shown in FIG. 3, the character string identifying unit 111 does not need to combine the character codes of all the characters included in the character string, and identifies the character by one character code on which the marking is superimposed. do it. In addition, in step S107 illustrated in FIG. 3, the character string identifying unit 111 may identify the same single character by comparing the character codes with respect to all the single characters on which the marking is superimposed.

1, 2, ... MFP
DESCRIPTION OF SYMBOLS 12 ... Image reading part 16 ... Image formation part 101 ... Marking extraction part 102 ... Marking determination part 103 ... Character string extraction part 104 ... Code | symbol determination part 105 ... Blank creation part 106 ... Image composition part 110 ... Same character string identification part 111 ... Character string identification unit 112 ... OCR database 113 ... Character string comparison unit 201 ... Character string similarity determination unit

Claims (8)

A marking extracting unit for extracting the plurality of markings from a document image including a plurality of markings respectively superimposed on a plurality of character strings;
Among the plurality of character strings on which the markings are superimposed, the same character string identifying unit for identifying the same character string,
An information processing apparatus comprising: a code determining unit that assigns the same code to the same character string and assigns different codes to different character strings. The information processing apparatus according to claim 1,
A blank creation unit for creating a blank image to be superimposed on each of the plurality of character strings on which the markings are superimposed,
An information processing apparatus further comprising: an image composition unit that creates a composite image by combining the document image, the plurality of blank images, and a code image that is an image of the assigned code. The information processing apparatus according to claim 1 or 2,
A marking determination unit that determines the position and shape of each of the plurality of markings extracted by the marking extraction unit in the document image;
Based on the determined positions and shapes of the plurality of markings, further comprising a character string extraction unit that extracts the plurality of character strings on which the respective markings are superimposed,
The information processing apparatus, wherein the same character string identification unit identifies the same character string among the plurality of character strings extracted by the character string extraction unit. The information processing apparatus according to claim 3,
The same character string identification unit is
A character string identifying unit for identifying the plurality of character strings extracted by the character string extracting unit;
An information processing apparatus comprising: a character string comparison unit that identifies the same character string by comparing the plurality of character strings identified by the character string identification unit to identify the same character string. The information processing apparatus according to claim 4,
The character string identification unit
Extracting a plurality of characters from each of the plurality of character strings extracted by the character string extraction unit,
Identifying each of the extracted plurality of characters;
An information processing apparatus that identifies the plurality of character strings by combining the plurality of characters included in the character string. An information processing apparatus according to claim 4 or 5,
The information processing apparatus, wherein the character string identification unit identifies the plurality of character strings by optical character recognition. The information processing apparatus according to claim 3,
The same character string identification unit determines the similarity between the plurality of character strings extracted by the character string extraction unit, and when the similarity is equal to or greater than a threshold, the plurality of character strings are the same character string. An information processing apparatus having a character string similarity determination unit for determining. Information processing device
A marking extracting unit for extracting the plurality of markings from a document image including a plurality of markings respectively superimposed on a plurality of character strings;
Among the plurality of character strings on which the markings are superimposed, the same character string identifying unit for identifying the same character string,
A program that functions as a code determination unit that assigns the same code to the same character string and assigns different codes to different character strings.

Images