Classifications

• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
  • G06V10/00—Arrangements for image or video recognition or understanding
  • G06V10/98—Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns
  • G06V10/987—Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns with the intervention of an operator

Definitions

• the present invention relates to a document processing method, a recording medium on which a document processing program is recorded, and a document processing device.
• the present invention is particularly applicable to the field of information equipment used in offices and the like, and a document processing method, a recording medium storing a document processing program, and a document processing apparatus capable of easily correcting a recognized character.
• BACKGROUND ART In general, in a character processing device, it is technically important to cut out written characters and to detect positions (lines and character positions) in a document. Then, when a correction character was written on a printed document with a black pencil or the like to correct the document, it was necessary to cut out the written character or the like from the document.
• FIG. 13 shows a configuration diagram of a conventional document processing apparatus.
• This document processing device includes a document file 101, a printout device 102, a photoelectric conversion device 105, an electronic data storage device 106, a print position detecting device 107, and a character extracting device 108. , Recognition means 109, associating means 110, and document processing means 111.
• FIG. 14 is an explanatory diagram relating to conventional document processing.
• the contents of the document file 101 are output by the printout means 102 using color ink, and a printout 103 is obtained.
• the recognized document 1 14 a is printed with color ink, and the mark 1 1 4 b indicating the character position and the mark 1 1 4 c indicating the line position are both printed in black. Have been.
• This fix Correction symbol and character 1 1 4 d are entered in the correct input 1 1 4.
• the correction document 111 with the correction symbol written in the printout 103 is obtained by photoelectric conversion means 115 which does not sense the color ink. Stored in 6.
• the type position detecting means 107 based on the result 115 of the photoelectric conversion, a type character is entered from a mark 115 b indicating a character position and a mark 115 c indicating a line position. The position on the electronic data that exists.
• the character extracting means 108 detects the written correction symbol and the character 115d based on the same photoelectric conversion result 115, finds the position on the electronic data, and recognizes the character. This is recognized by 109.
• the associating means 110 based on the result of the type position detecting means 107 and the result of the character segmenting means 108, it is possible to determine on which line and which character the entered character is to be corrected.
• the associating and document correcting means 1 1 1 1 corrects the electronic file 101.
• the present invention provides a document processing method in which a printout is output as dot characters or gray color instead of color ink, and the gray color is erased from this document to extract only written characters.
• Another object of the present invention is to provide a recording medium and a device in which a document processing program is recorded.
• the present invention cuts out the entered characters and the like from a document in which the characters for correction are entered, and determines which type of the character or the like is entered on the document, thereby erroneously recognizing the type.
• the purpose is to modify the document that has been submitted. Since the present invention enables correction processing using gray-colored sentences, it is possible to input a document using a general image reader, fax, scanner, or the like. Another object of the present invention is to enable output by a monochrome printer. It is another object of the present invention to eliminate the need for line and character position marks and to eliminate the need for special document output processing during printout.
• FIG. 1 is a configuration diagram of a document processing apparatus according to the present invention.
• FIG. 2 is a flowchart of a document processing method according to the present invention.
• C is an explanatory diagram relating to document processing.
• FIG. 4 is an explanatory diagram of print character position detection.
• FIG. 5 is an explanatory diagram of recognition of a correction symbol.
• FIG. 6 is an explanatory diagram of the contraction processing.
• FIG. 7 is an explanatory diagram of an edge image.
• FIG. 8 is an explanatory diagram regarding various processes for correction.
• FIG. 9 is a flowchart of various processes for correction.
• FIG. 10 is an explanatory diagram of word processing.
• FIG. 11 is an explanatory diagram of the combining process.
• FIG. 12 is an explanatory diagram of the separation process.
• FIG. 13 is a configuration diagram of a conventional document processing apparatus.
• FIG. 14 is an explanatory diagram related to the conventional document processing.
• BEST MODE FOR CARRYING OUT THE INVENTION According to a first solution means of the present invention, an output step of outputting a document reading recognition result as a dot character or a gray color image; and Provided is a document processing method and a recording medium on which a document processing program is provided, comprising: a correction recognition step of recognizing a correction symbol; and a correction step of correcting a recognition result according to the correction symbol recognized by the correction recognition step.
• a document file storage unit for storing a document reading recognition result, an output unit for outputting a document file stored in the document file storage unit as a dot character or a gray color image,
• Correction recognition means for recognizing a correction symbol written in the document output by the output means, and correcting the document file stored in the document file storage unit in accordance with the correction symbol recognized by the correction recognition means.
• a document processing device provided with a correction unit.
• BEST MODE FOR CARRYING OUT THE INVENTION FIG. 1 shows a configuration diagram of a document processing apparatus according to the present invention.
• FIG. 2 shows a flowchart of the document processing method according to the present invention.
• Fig. 3 shows an explanatory diagram related to document processing.
• This document processing device includes a document file storage unit 1, an output unit 2, a photoelectric conversion unit 5, an electronic data storage unit 6, a character position detection unit 7, a correction recognition unit 8, a character recognition unit 9, a correspondence unit 10, a correction unit.
• Means 11 are provided.
• the photoelectric conversion unit 5 reads a document to be recognized and converts it into electronic data.
• the electronic data storage means 6 stores the electronic data read by the photoelectric conversion means 5.
• the character recognition means 9 recognizes the stored document.
• the document file storage means 1 reads a document and stores the recognition result.
• the output unit 2 outputs a printout 3 of the document file stored in the document file storage unit 1 as dot characters or a gray color image (S101). The operator modifies the printout 3 on the printout 3.
• the corrected input document 14 is image-input by the photoelectric conversion means 5, converted into electronic data, and stored in the electronic data storage means 6 (S105).
• the character position detecting means 7 detects the position of the character in which the correction symbol has been written in the document output by the output means 2 (S107).
• the character position detecting means 7 detects the line and the character position from the digitized document image, noting that the printed characters are printed in a dot. Details will be described later.
• the correction recognizing means 8 recognizes the correction symbols and characters entered in the correction input document 14 (S111).
• the correct character to be corrected can be recognized by, for example, the character recognition means 9 or the like.
• the associating means 10 associates the position of the character detected by the character position detecting means 7 with the correction symbol recognized by the correction recognizing means 8 and specifies a correction target character.
• the correction means 11 corrects the corresponding character by a correction process corresponding to the correction symbol according to the association of the association means 10 (S115).
• Correction means 1 1 The document file stored in the document file storage means 1 is corrected according to the correction symbol recognized by the means 8.
• the hatched instruction indicates, for example, a symbol that replaces the corresponding type with the character written thereon.
• the process of correcting “filled” into “physical” is performed on the document file storage means 1.
• the character recognition unit 9 or the correction recognition unit 8 recognizes “rea” as a correct character to be corrected.
• the correction unit 11 can also perform, for example, word recognition processing, combination processing, and division processing to correct the document file. This point will be described later.
• the output means 2 reads the corrected document file from the document file storage means 1 and outputs a correction result 16 (S117). At this time, it is OK to output and confirm not only on the printout but also on the display.
• Fig. 4 is an explanatory diagram of printout character position detection.
• the character position detecting means 7 detects the position of the character by multiplying the number of pixels in each of the horizontal direction and the vertical direction in the edge image of the input document. Specifically, for example, first create a contour image, emphasize it, detect the row position by counting the number of black pixels in the horizontal direction on this contour image, and then vertically in each row.
• the character position is detected by counting the number of black pixels.
• a description will be given of the position detection of the character printed as “this paper” on the first line and “printing device” on the second line by the character position detecting means 7.
• a character image 41 in which a correction symbol has been entered is input.
• the contour of each pixel is detected based on this character image, and a contour image 42 is obtained.
• the pixels are added or added in the horizontal direction to obtain a horizontal peripheral distribution 43.
• the position of the row can be detected from the horizontal distribution.
• the detected outline pixels 44 are cut out, and the pixels are added or added in the vertical direction to obtain the vertical peripheral distribution 45.
• Fig. 5 is an explanatory diagram of recognition of the correction symbol.
• the correction recognizing means 8 obtains the connected components of the pixels from the corrected input document 14 in the extraction of the corrected symbols (detection of the entered characters), and is determined in advance based on the obtained number of pixels of the connected components.
• the correction recognition means 8 includes, for example, a contraction process of setting a black pixel adjacent to a white pixel as an edge and removing the edge from the original image.
• a description will be given of the correction symbol written in the “package” of the character printed out “of the collecting device”.
• a character image 51 in which a correction symbol has been entered is input.
• each pixel is converted into a contracted image 52 in which contraction processing is performed.
• FIG. 6 shows an explanatory diagram of the contraction processing.
• FIG. 7 is an explanatory diagram of an edge image.
• the edge image of each pixel extracted from the input image 61 is the edge image 71 in FIG. That is, an edge is a black pixel adjacent to a white pixel. Note that a double or triple edge may be extracted.
• a first contracted image 62 is obtained.
• the second contracted image 63 is obtained by obtaining the edge image of the first contracted image 62 and removing the edge image. This shrinking process is performed an appropriate number of times to erase the dot character, thereby obtaining a corrected symbol extracted image 53 from which the corrected symbol has been extracted.
• a connected component which is a portion where black pixels are connected is obtained, and the number of black pixels of each connected component is obtained.
• a correction symbol can be extracted by leaving a connected component in which the number of black pixels is equal to or larger than a predetermined threshold value.
• the correction recognition means 8 By extracting the correction symbol and recognizing what correction symbol is to be used to issue a correction instruction, a correction symbol recognition result 54 can be obtained.
• correction symbols and characters have been described, but the present invention can also extract correction symbols for instructing various corrections. Therefore, the following describes the correction processing, word processing, combination processing, and division processing by the correction recognition means 8, the association means 10, the correction means 11, and the like.
• FIG. 8 shows an explanatory diagram of various processes for correction.
• FIG. 9 shows a flowchart of various processes for correction.
• the output means 4 outputs the recognition result (S207). Here, it is assumed that the recognition output 8 1 1 has been output. This output is output in dot character or gray color
• the operator instructs correction contents for characters and documents that have not been sufficiently recognized (S211).
• the instructions for the correction content are, for example, the first symbol 8 1 2 a, the second symbol 8 1 2 b, and the third symbol 8 1 2 c in the correction input 12 in which the symbol characters are entered. This is done with a correction symbol.
• the first symbol 8 1 2a, the second symbol 8 1 2b, and the third symbol 8 1 2c are symbols for instructing word processing, combining character patterns, and separating character patterns, respectively. It is.
• the correction recognition means 6 cuts out the written correction symbol (S213).
• the modified character is recognized as a modification process for modifying one character
• the above-described modification process is executed (S2115).
• the word processing for finding the most likely combination as a word from the combination of candidate characters in the character set corresponding to this symbol in the recognition candidate character Perform (S2 17).
• FIG. 10 is an explanatory diagram of the word processing.
• each character pattern is recognized, and the first recognition candidate character is output as a recognition result. If this is determined as a word, for example, by a combination of two letters, the combination of the first and second letters Among them, there are restrictions on what can be realized as words, so that false recognition is reduced.
• the first candidate is “mochi”
• the second candidate is “special”
• the third candidate is “samurai”
• the fourth candidate is “earning”.
• three characters are determined as recognition candidates as a result of recognizing the second character. That is, the first candidate is “fine”, the second candidate is “sign”, and the third candidate is “work”.
• the recognition results for each character the first candidates “Toku” and “Fine” were selected, respectively.
• word processing the user was instructed to recognize these two characters as words, so we consider combinations of each candidate for each character.
• the combination of the second candidate “Toku” and the second candidate “Sho” is the sum of the candidate priorities 4 (2 + 2), and the fourth candidate “Earn” and the third candidate “Work” It is determined that the combination with is the sum of the candidate priorities 7 (4 + 3). Therefore, as the word processing result, the first candidate “feature” and the second candidate “operation” are determined as recognition candidates in descending order of priority (ie, in order of decreasing sum of priorities).
• the “feature” power of the first candidate is recognized as a result of word processing. If it is recognized that the character pattern is to be combined, the corresponding character patterns are combined, and a combining process for recognizing one character is executed (S219).
• FIG. 11 shows an explanatory diagram of the combining process.
• FIG. 12 shows an explanatory diagram of the separation processing.
• the character pattern corresponding to the character indicated by the correction symbol is cut out as two character patterns and recognized again.
• the instruction to separate the “sum” of the recognition results was given, and as a result of the recognition again, “f” and “e” were recognized.
• the correction means 8 corrects the document file storage means 3 according to each process (S2 23), and outputs a correction result 8 13 (S2 25).
• the process returns to step S211 to repeat the processing.
• the processing ends.
• the gray color is not limited to a dot, and may be an outline font or a font formed with oblique lines as long as it is not solid black.
• the method of detecting the character position, detecting the position of the entered character, and recognizing the same effect is not limited to this as long as the same effect is obtained.
• the symbols used to modify the document are only examples, but the modified symbols are not limited to these.
• the character position detection method may be a method that detects lines by detecting continuous characters, a method of detecting lines and columns by detecting a space between lines and characters, and a method of detecting lines or columns.
• the character position may be detected.
• For input and output between processes, such as moving a document file, communication via the Internet or the like may be used.
• INDUSTRIAL APPLICABILITY According to the present invention, as described above, printouts are output as dot characters or gray color instead of color ink, and gray color is erased from this document to extract only the written characters. It is possible to provide a document processing method and a recording medium and a device in which the document processing program is recorded.
• the written characters and the like are cut out from the document in which the characters for correction are written, and the characters or the like are erroneously recognized by judging on which type the characters are written.
• the revised document can be modified.
• correction processing can be performed using gray-colored sentences, so that it is possible to input a document with a general image reader, fax, scanner, or the like, and output it with a monochrome printer. I do.

Landscapes

• Engineering & Computer Science (AREA)
• Quality & Reliability (AREA)
• Physics & Mathematics (AREA)
• General Physics & Mathematics (AREA)
• Multimedia (AREA)
• Theoretical Computer Science (AREA)
• Character Discrimination (AREA)
• Character Input (AREA)

Priority Applications (1)

Applications Claiming Priority (2)

Publications (1)

Family

ID=16857575

Family Applications (1)

Country Status (3)

Cited By (1)

Families Citing this family (7)

Citations (6)

Family Cites Families (8)

• 1999
  • 1999-08-11 JP JP22723199A patent/JP3954246B2/ja not_active Expired - Fee Related
• 2000
  • 2000-04-17 WO PCT/JP2000/002483 patent/WO2001013324A1/ja not_active Ceased
  • 2000-04-17 US US10/049,102 patent/US7142733B1/en not_active Expired - Fee Related

Patent Citations (6)

Also Published As

Similar Documents

Legal Events