# US 2017/0257520 A1 · Information processing apparatus > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2017/0257520 A1 - Document ID: US20170257520A1 - Status: Published application - Kind: A1 - Application number: 15/438,331 - Filed: 2017-02-21 - Published: 2017-09-07 - Earliest claimed: 2016-03-01 - Assignees: KYOCERA Document Solutions Inc. - Applicants: Kyocera Document Solutions Inc. - Inventors: TOMOHIRO MIURA - Web page: https://patentgrep.com/patent/US20170257520A1 ## CPC - H04N 1/393: Enlarging or reducing - H04N 1/00331: {with an apparatus performing optical character recognition (character recognition G06V30/10)} - H04N 1/38: Circuits or arrangements for blanking or otherwise eliminating unwanted parts of pictures (H04N1/387 takes precedence) - H04N 1/3876: {Recombination of partial images to recreate the original image} - H04N 1/4177: {encoding document change data, e.g. form drop out data} - H04N 2201/0094: Multifunctional device, i.e. a device capable of all of reading, reproducing, copying, facsimile transception, file transception - H04N 2201/3243: of type information, e.g. handwritten or text document - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract Provided is an information processing apparatus including: a marking extraction circuit that extracts, from a script image including a plurality of markings respectively superimposed on a plurality of character strings, the plurality of markings; a same-character-string identification circuit that identifies the same character string out of the plurality of character strings on which the markings are respectively superimposed; and a symbol determination circuit that allocates the same symbol to the same character string and allocates different symbols to different character strings. ## Claims ### Claim 1 An information processing apparatus, comprising: a marking extraction circuit that extracts, from a script image including a plurality of markings respectively superimposed on a plurality of character strings, the plurality of markings; a same-character-string identification circuit that identifies the same character string out of the plurality of character strings on which the markings are respectively superimposed; and a symbol determination circuit that allocates the same symbol to the same character string and allocates different symbols to different character strings. ### Claim 2 (depends on 1) The information processing apparatus according to claim 1, further comprising: a blank creation circuit that creates a plurality of blank images to be respectively superimposed on the plurality of character strings on which the markings are respectively superimposed; and an image synthesis circuit that creates a synthesis image by synthesizing the script image, the plurality of blank images, and a symbol image as an image of the allocated symbols. ### Claim 3 (depends on 1) The information processing apparatus according to claim 1, further comprising: a marking judgment circuit that judges a position and shape of each of the plurality of markings extracted by the marking extraction circuit, within the script image; and a character string extraction circuit that extracts the plurality of character strings on which the markings are respectively superimposed based on the judged position and shape of the plurality of markings, wherein the same-character-string identification circuit identifies the same character string out of the plurality of character strings extracted by the character string extraction circuit. ### Claim 4 (depends on 3) The information processing apparatus according to claim 3, wherein the same-character-string identification circuit extracts a plurality of characters from each of the plurality of character strings extracted by the character string extraction circuit, identifies each of the plurality of extracted characters, and identifies each of the plurality of character strings by combining the plurality of characters included in each of the character strings. ### Claim 5 (depends on 1) The information processing apparatus according to claim 1, wherein the same-character-string identification circuit identifies the plurality of character strings by optical character recognition. ### Claim 6 (depends on 3) The information processing apparatus according to claim 3, wherein the same-character-string identification circuit includes a character string similarity degree judgment circuit that judges a similarity degree among the plurality of character strings extracted by the character string extraction circuit and judges that the plurality of character strings are the same character string when the similarity degree is equal to or larger than a threshold value. ### Claim 7 An information processing apparatus, comprising: a marking extraction circuit that extracts, from a script image including a character string area including a character string on which a marking is superimposed and a character string on which a marking is not superimposed, the marking; and an image conversion circuit that creates an enlarged character string by enlarging the character string on which the marking is superimposed and creates a reduced character string by reducing the character string on which a marking is not superimposed. ### Claim 8 (depends on 7) The information processing apparatus according to claim 7, further comprising: a blank creation circuit that creates a blank image to be superimposed on the enlarged character string; and an image synthesis circuit that creates a synthesis image by synthesizing the reduced character string and the blank image. ### Claim 9 (depends on 7) The information processing apparatus according to claim 7, further comprising: a marking judgment circuit that judges a position and shape of the marking extracted by the marking extraction circuit, within the script image; a character string area judgment circuit that judges a position and size of the character string area within the script image; a row area judgment circuit that divides the character string area into one or more row areas and judges a position and size of each of the one or more row areas within the character string area; and a row area division circuit that judges, based on a position and size of the marking within the script image and a position and size of each of the one or more row areas within the character string area, a position and size of the marking within the row area to which the marking belongs, and divides the row area to which the marking belongs into the character string on which the marking is superimposed and the character string on which a marking is not superimposed, wherein the image conversion circuit creates the enlarged character string and the reduced character string by enlarging and reducing the character strings obtained by the division by the row area division circuit. ### Claim 10 (depends on 7) The information processing apparatus according to claim 7, further comprising a conversion ratio calculation circuit that calculates an enlargement ratio for creating the enlarged character string from the marking superimposed on the character string, or calculates a reduction ratio for creating the reduced character string from the character string on which a marking is not superimposed. ### Claim 11 (depends on 10) The information processing apparatus according to claim 10, wherein within a range where a length of the row area including the enlarged character string in a direction in which characters are arranged within the row area is equal to or smaller than that of the row area before enlargement and reduction, the conversion ratio calculation circuit calculates the enlargement ratio based on a specific reduction ratio such that the enlarged character string has a maximum size, or the reduction ratio based on a specific enlargement ratio such that the reduced character string has a maximum size. ### Claim 12 (depends on 10) The information processing apparatus according to claim 10, wherein within a range where a length of the character string area including the enlarged character string in a direction in which the one or more row areas are arranged is equal to or smaller than that of the character string area before enlargement and reduction, the conversion ratio calculation circuit calculates the enlargement ratio based on a specific reduction ratio such that the enlarged character string has a maximum size, or the reduction ratio based on a specific enlargement ratio such that the reduced character string has a maximum size. ### Claim 13 An information processing apparatus, comprising: a marking extraction circuit that extracts, from a script image including a marking superimposed on a character string, the marking; and a character string comparison circuit that extracts, from the script image, a character string on which a marking is not superimposed, the character string being the same as that on which a marking is superimposed. ### Claim 14 (depends on 13) The information processing apparatus according to claim 13, further comprising: a blank creation circuit that creates a plurality of blank images to be superimposed on each of the character string on which the marking is superimposed and the extracted character string; and an image synthesis circuit that creates a synthesis image by synthesizing the script image and the plurality of blank images. ### Claim 15 (depends on 13) The information processing apparatus according to claim 13, further comprising: a character extraction circuit that extracts a plurality of characters from the script image; and a character identification circuit that identifies the plurality of characters extracted by the character extraction circuit and identifies the character string on which a marking is superimposed out of the plurality of identified characters, wherein the character string comparison circuit extracts the character string on which a marking is not superimposed, the character string being the same as that identified by the character identification circuit and on which a marking is superimposed, from the plurality of characters identified by the character identification circuit. ### Claim 16 (depends on 15) The information processing apparatus according to claim 15, further comprising: a marking judgment circuit that judges a position and shape of the marking extracted by the marking extraction circuit, within the script image, wherein the character identification circuit identifies the character string on which a marking is superimposed based on the position and shape of the marking. ### Claim 17 (depends on 13) The information processing apparatus according to claim 13, wherein the character string comparison circuit allocates the same symbol to the character string on which a marking is superimposed and the same character string on which a marking is not superimposed.