WO2019049187A1 - Programme, dispositif de traitement d'informations et procédé de traitement d'informations - Google Patents

Programme, dispositif de traitement d'informations et procédé de traitement d'informations Download PDF

Info

Publication number
WO2019049187A1
WO2019049187A1 PCT/JP2017/031864 JP2017031864W WO2019049187A1 WO 2019049187 A1 WO2019049187 A1 WO 2019049187A1 JP 2017031864 W JP2017031864 W JP 2017031864W WO 2019049187 A1 WO2019049187 A1 WO 2019049187A1
Authority
WO
WIPO (PCT)
Prior art keywords
input
handwriting
character
range
height direction
Prior art date
Application number
PCT/JP2017/031864
Other languages
English (en)
Japanese (ja)
Inventor
平松　直人
悠吾 松田
Original Assignee
富士通株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 富士通株式会社 filed Critical 富士通株式会社
Priority to PCT/JP2017/031864 priority Critical patent/WO2019049187A1/fr
Publication of WO2019049187A1 publication Critical patent/WO2019049187A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition

Definitions

  • the present invention relates to a program, an information processing apparatus, and an information processing method.
  • an object of the present invention is to provide a technique capable of improving the discrimination accuracy of characters input by handwriting.
  • the computer receives handwriting input on the screen on which the input field is displayed, identifies the range in the height direction of the accepted handwriting input, and the identified range and the height direction of the input field Or a character according to the handwriting of another handwriting input received on the screen before reception of the handwriting input, and based on the range in the height direction of the character displayed in the input field, There is provided a program that executes a process for identifying characters according to the handwriting of the input handwriting input.
  • FIG. 1 is a diagram showing an example of a functional block diagram of an information processing apparatus according to an embodiment of the present invention. It is a flow chart which shows an example of processing of an information processor concerning an embodiment. It is a figure which shows an example of the display screen at the time of being input by handwriting. It is a figure which shows an example of input column data. It is a figure which shows an example of a display screen when a handwritten character is converted into character information. It is a figure which shows an example of a display screen at the time of one handwritten character being added. It is a figure explaining comparison of the height of a handwritten character. It is a figure which shows an example of the display screen at the time of being input by handwriting.
  • FIG. 1 is a diagram illustrating an example of a hardware configuration of the information processing apparatus 10 according to the embodiment.
  • the information processing apparatus 10 of FIG. 2 includes a drive unit 100, an auxiliary storage unit 102, a memory unit 103, a CPU 104, an interface unit 105, a display unit 106, an input unit 107 and the like mutually connected by a bus B.
  • An information processing program for realizing the processing in the information processing apparatus 10 is provided by the recording medium 101.
  • the recording medium 101 in which the information processing program is recorded is set in the drive apparatus 100, the information processing program is installed from the recording medium 101 to the auxiliary storage apparatus 102 via the drive apparatus 100.
  • the installation of the information processing program does not necessarily have to be performed from the recording medium 101, and may be downloaded from another computer via a network.
  • the auxiliary storage device 102 stores the installed information processing program and also stores necessary files and data.
  • the memory device 103 reads out the program from the auxiliary storage device 102 and stores it when there is an instruction to start the program.
  • the CPU 104 implements the function related to the information processing apparatus 10 in accordance with a program stored in the memory device 103.
  • the interface device 105 is used as an interface for connecting to a network.
  • the display device 106 displays a graphical user interface (GUI) according to a program.
  • the input device 107 includes a touch panel, a button, and the like, and is used to input various operation instructions.
  • the recording medium 101 a portable recording medium such as a CD-ROM, a DVD disk, or a USB memory may be mentioned.
  • a hard disk drive (HDD) or a flash memory may be mentioned.
  • the recording medium 101 and the auxiliary storage device 102 both correspond to computer readable recording media.
  • FIG. 2 is a diagram showing an example of a functional block diagram of the information processing apparatus 10 according to the embodiment.
  • the information processing apparatus 10 includes an input unit 11, an acquisition unit 12, a determination unit 13, and a display control unit 14. These units are realized by processing that one or more programs installed in the information processing device 10 cause the CPU 104 of the information processing device 10 to execute.
  • the input unit 11 receives input (handwriting input) of characters by handwriting operation with a finger from a user or a stylus pen on a screen on which a predetermined form is displayed.
  • the acquisition unit 12 specifies the input field input by handwriting based on the position input to the input unit 11 and the range of the input field for each input item in the form displayed on the screen. In addition, the acquisition unit 12 specifies the range in the height direction of the handwriting input input to the input unit 11 in the input field.
  • the determination unit 13 determines whether the character input to the input unit 11 is upper case or lower case, or a hyphen according to the input field specified by the acquisition unit 12 and the range in the height direction of the handwriting input. Determine the type of whether it is an underscore or an underscore.
  • the determination unit 13 performs character recognition of the handwriting of the handwritten character input to the input unit 11 using the information of the type, and generates character information (text information) that is a result of the character recognition.
  • the display control unit 14 displays the handwriting of the handwritten character input by the input unit 11. Then, when the character information for the handwritten character is generated by the determination unit 13, the display of the handwriting of the handwritten character is erased, and the character information is acquired by the acquiring unit 12 using predetermined font data. Display in the area of the input field.
  • FIG. 3 is a flowchart showing an example of processing of the information processing apparatus 10 according to the embodiment.
  • step S1 the display control unit 14 displays a predetermined form on the screen.
  • the input unit 11 receives, from the user, an input (an example of a “second handwritten input”) of one or more handwritten characters (hereinafter referred to as a “handwritten character”) on the screen of the form.
  • an input an example of a “second handwritten input” of one or more handwritten characters (hereinafter referred to as a “handwritten character”) on the screen of the form.
  • the handwritten character may be a single character or a character string composed of a plurality of characters.
  • the display control unit 14 displays the input handwritten character at the position input on the screen of the form (step S3).
  • FIG. 4 is a diagram showing an example of a display screen when handwriting input is performed.
  • the handwriting 511 input by handwriting is displayed in the input field 501 for inputting the address.
  • the acquiring unit 12 determines an input field on the form on which the handwritten character is input according to the position on the form on which the handwritten character is input (step S4).
  • the actual paper size is compared with the method of inputting characters by handwriting in the area for handwriting input, which is different from the area where the input field is displayed.
  • the handwriting input can be performed on the form by the same simple operation as writing on the form as handwriting.
  • the determination unit 13 recognizes the handwritten character and acquires character information (step S5).
  • the character information includes information as to whether the character is alphanumeric, kanji, or kana, and full-width or half-width information.
  • the determination unit 13 stores the character information and the area of the handwritten character in the input field data 151 (step S6).
  • FIG. 5 is a view showing an example of the input field data 151.
  • items, the height of the lower side, the height of the upper side, the character information, and the handwriting area are stored in association with the input field ID.
  • the input field ID is identification information of the input field in the form.
  • the item is an item of information input in the input field.
  • the height of the lower side and the height of the upper side are values of vertical coordinates on the screen of the lower side and the upper side of the input field, respectively.
  • the coordinate in the vertical direction may be, for example, a unit of length such as cm, or may be a unit of pixel.
  • the handwriting region is a region of handwriting entered in the input field.
  • the determination unit 13 may store, as a handwritten area, a coordinate group representing an area such as a line included in the handwritten character. Alternatively, coordinates of a central position of a rectangle or the like circumscribing each character included in the handwritten character and the length of each side may be stored. In addition, a rectangle and a square shall be included in "rectangle etc.” Alternatively, if the input field into which the handwritten character is input is an input field for horizontal writing, the average value or the median value of the upper side of the rectangle etc. circumscribing each character included in the handwritten character, and the average value of the lower side or The median may be stored.
  • the display control unit 14 erases the display of the handwritten character from the screen, and it is determined that the handwritten character is input using predetermined font data as character information that is a recognition result of the handwritten character. It is displayed on the input field (step S7).
  • FIG. 6 is a view showing an example of a display screen when handwritten characters are converted into character information.
  • characters 512 of “Kanagawa Prefecture”, which are results of character recognition of characters input by handwriting, are displayed in the input field 501 for inputting an address, using predetermined font data.
  • the input unit 11 receives an input of one handwritten character (an example of “first handwritten input”) from the user in the input field on the form screen (step S8).
  • one character is also referred to as "one character to be processed”.
  • FIG. 7 is a diagram showing an example of a display screen when one handwritten character is added.
  • the input field 501 for entering an address displays a handwriting 513 in which the upper case “K” or the lower case “K” character is handwritten after the character 512 of “Kanagawa Prefecture”. There is.
  • the determination unit 13 is an input field data It is determined whether the area etc. of the other handwritten character in the said input column is memorize
  • the information of the other handwritten character in the said input column is memorize
  • the determination part 13 determines with "addition", when the position by which the handwriting input was carried out is an area
  • the determination unit 13 determines that the “correction” is made. Then, character information obtained by replacing the one character with the result of character recognition of the handwritten character is displayed on the screen, and the character information is stored in the item of character information of the input field data 151.
  • the determination unit 13 determines that the position input by handwriting is the position of the character information of the first one character displayed in the input field, and the position of the character information of the second one character next to the first character. If it is substantially in the middle, it is determined that "insertion" is made. And while displaying on the screen the character information which inserted the result of character recognition of the character inputted by handwriting between the first character and the second character, the character information is displayed in the input field data 151. Store in the item of text information.
  • determination unit 13 sets the area of the character information displayed using the predetermined font data at the position of the input box. Based on the score of the type indicating whether one character to be processed is upper case or lower case, hyphen or underscore (step S10).
  • the determination unit 13 determines that the difference between the height of the upper side of the character information and the height of the upper side of the one character to be processed is equal to or less than the first threshold, and the height of the lower side of the character information and the processing object If the difference from the height of the lower side of one character is equal to or less than the second threshold, a score indicating upper case likeness for one character to be processed may be calculated high.
  • the determination unit 13 when the difference between the height of the lower side of the character information to be compared and the height of the lower side of one character to be processed is equal to or less than a predetermined threshold, the determination unit 13 underscores the one character to be processed A score indicating likelihood may be calculated high, and if the difference is not equal to or less than a predetermined threshold, a score indicating hyphen likeness for one character to be processed may be calculated high.
  • the determination unit 13 determines that, for example, the difference between the middle of the height of the lower side of the comparison target to the upper side and the middle of the height of the lower side of the processing target character to the upper side is a predetermined threshold or less In this case, a score indicating the hyphen likeness to one character to be processed may be calculated high, and a score indicating the likelihood of underscore to one character to be processed may be calculated high when the difference is not equal to or less than a predetermined threshold.
  • the score which shows whether it is a hyphen or an underscore is the height of the lower side of the comparison object at the time of calculating the score which shows whether it is an upper case or a lower case mentioned later, respectively, Since the same calculation can be made using the middle of the height of the upper side, the description will be omitted.
  • the determination unit 13 determines that the difference between the height of the upper side of the character information and the height of the upper side of the one character to be processed is not less than the first threshold, and the height of the lower side of the character information and 1 If the difference with the height of the lower side of the character is equal to or less than the second threshold, a score indicating lower-case resemblance to one character to be processed may be calculated higher.
  • the difference between the top side and the height of 513 is relatively small. Therefore, a score indicating capitalization to the handwriting 513 is calculated high.
  • the determination unit 13 refers to the input field data 151 and calculates the score of the type of one character to be processed based on the handwritten area of the other handwritten character in the input field (step S11).
  • the determination unit 13 determines that the difference between the height of the upper side of the handwriting area stored in the input field data 151 and the height of the upper side of one character to be processed is equal to or less than a third threshold.
  • a score indicating capitality for one character to be processed may be calculated high.
  • the determination unit 13 determines that the difference between the height of the upper side of the handwriting area and the height of the upper side of one character to be processed is not less than the third threshold, and the height of the lower side of the handwriting area and 1 If the difference between the height of the lower side of the character and the height of the lower side of the character is equal to or less than the fourth threshold, a score indicating lower-case resemblance to one character to be processed may be calculated higher.
  • FIG. 8 is a diagram for explaining comparison of the heights of handwritten characters.
  • the upper side 551 of the area of the handwriting 511 input by handwriting in FIG. 4 and the upper case letter “ ⁇ ” or the lower case letter “ ⁇ ” are handwritten.
  • the difference 553 with the upper side 552 of the handwriting 513 is relatively large, and the lower edge 554 of the area of the handwriting 511 input by handwriting in FIG. 4 and the handwriting 513 by which the upper case letter “ ⁇ ⁇ ⁇ ” or the lower case letter “ ⁇ ” are handwritten input
  • the difference with the lower side 555 is relatively small. Therefore, the determination unit 13 calculates a score indicating the likelihood of a small letter with respect to the handwriting 513 to be high.
  • the determination unit 13 determines that, for example, the difference between the height of the lower side of the handwriting area and the height of the lower side of one character to be processed is equal to or less than a fourth threshold and from the lower side to the upper side of one character to be processed
  • a score indicating lower-case resemblance to one character to be processed may be calculated relatively high.
  • the lower side 554 of the area of the handwriting 511 input by handwriting in FIG. 4 and the upper case “ ⁇ ” or lower case “ ⁇ ” characters are handwritten
  • the difference from the lower side 555 of the handwriting 513 is relatively small.
  • the vertical width 556 of the handwriting 513 is about half of the vertical width 557 of the handwriting area. Therefore, the determination unit 13 further calculates a score indicating lower-case likeness with respect to the handwriting 513.
  • the determination unit 13 calculates the score of the type of one character to be processed based on the height of the lower side and the height of the upper side of the input field (step S12).
  • the determination unit 13 determines that the difference between the height of the upper side of the input field and the height of the upper side of one character to be processed is equal to or less than the fifth threshold, and the height of the lower side of the input field and the process If the difference from the height of the lower side of the target one character is equal to or less than the sixth threshold value, a score indicating upper-case resemblance to one character to be processed may be calculated high.
  • the determination unit 13 determines that the difference between the height of the upper side of the input field and the height of the upper side of the one character to be processed is not less than the fifth threshold, and the height of the lower side of the input field and the process target When the difference with the height of the lower side of one character is less than or equal to the sixth threshold value, a score indicating lower-case resemblance to one character to be processed may be calculated higher.
  • FIG. 9 is a view showing an example of a display screen when handwriting input is performed.
  • a handwriting 602 input by handwriting is displayed in the input field 601 for inputting the mail address.
  • the determination unit 13 calculates the score indicating the small letter likeness to the handwriting 602 highly.
  • the determination unit 13 determines the height of the lower side and the upper side of the input box, the height of the lower side of the other input box, the height of the upper side, and the range of the handwritten characters input to the input box.
  • the score of the type of one character to be processed is calculated based on the and the range of the handwritten character input in the other input field (step S13).
  • the determination unit 13 determines that the vertical width of the area of the handwritten character in the other input column is shorter than that of the input column, and the vertical width of the character of the processing target is larger than the vertical width of one character to be processed.
  • the score indicating lower-case likeness for may be calculated higher.
  • the determination unit 13 determines whether one of the processing target characters is alphanumeric, kanji, or kana type by character recognition, and among handwritten characters in other input fields, a handwritten character whose type matches You may use the area of
  • the vertical width 702 of the postal code input column 700 is shorter than the vertical width 701 of the input column 601 for inputting the mail address.
  • the vertical width 704 of the handwritten character area in the input column 700 is larger than the vertical width 703 of the handwritten character area in the input column 601. Therefore, the determination unit 13 calculates the score indicating the small letter likeness to the handwriting 602 highly.
  • the determination unit 13 determines, based on the calculated score, the type of upper case or lower case, hyphen, or underscore for one character to be processed (step S14). , End the process.
  • a form printed on paper and displayed on a screen may be considered to enable handwriting input on the screen in the same manner as writing on paper.
  • the height or the like of the one character can not be compared with the height or the like of the other characters.
  • Each functional unit of the information processing apparatus 10 may be realized by, for example, cloud computing configured by one or more computers.
  • the acquisition unit 12 is an example of a “first identification unit”.
  • the determination unit 13 is an example of a “second identification unit”.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Character Discrimination (AREA)

Abstract

Selon la présente invention, un ordinateur est amené à effectuer un processus pour : recevoir une entrée manuscrite sur un écran qui affiche un champ d'entrée ; identifier la dimension en hauteur de l'entrée manuscrite reçue ; et identifier un caractère correspondant aux traits de l'entrée manuscrite reçue, en fonction de la dimension identifiée et de la dimension en hauteur du champ d'entrée, ou de la dimension en hauteur d'un caractère qui a été affiché dans le champ d'entrée et qui correspond aux traits d'une autre entrée manuscrite, qui a été reçue sur l'écran avant de recevoir l'entrée manuscrite actuelle.
PCT/JP2017/031864 2017-09-05 2017-09-05 Programme, dispositif de traitement d'informations et procédé de traitement d'informations WO2019049187A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/JP2017/031864 WO2019049187A1 (fr) 2017-09-05 2017-09-05 Programme, dispositif de traitement d'informations et procédé de traitement d'informations

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2017/031864 WO2019049187A1 (fr) 2017-09-05 2017-09-05 Programme, dispositif de traitement d'informations et procédé de traitement d'informations

Publications (1)

Publication Number Publication Date
WO2019049187A1 true WO2019049187A1 (fr) 2019-03-14

Family

ID=65633676

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2017/031864 WO2019049187A1 (fr) 2017-09-05 2017-09-05 Programme, dispositif de traitement d'informations et procédé de traitement d'informations

Country Status (1)

Country Link
WO (1) WO2019049187A1 (fr)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS6132187A (ja) * 1984-07-19 1986-02-14 インタ−ナショナル　ビジネス　マシ−ンズ　コ−ポレ−ション 文字認識方式
JPH09231316A (ja) * 1996-02-28 1997-09-05 Casio Comput Co Ltd 手書き文字認識装置
JP2001188881A (ja) * 1999-12-28 2001-07-10 Fujitsu Ltd 文字認識装置
JP2001357356A (ja) * 2001-04-13 2001-12-26 Sharp Corp 手書き認識装置及び手書き認識方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS6132187A (ja) * 1984-07-19 1986-02-14 インタ−ナショナル　ビジネス　マシ−ンズ　コ−ポレ−ション 文字認識方式
JPH09231316A (ja) * 1996-02-28 1997-09-05 Casio Comput Co Ltd 手書き文字認識装置
JP2001188881A (ja) * 1999-12-28 2001-07-10 Fujitsu Ltd 文字認識装置
JP2001357356A (ja) * 2001-04-13 2001-12-26 Sharp Corp 手書き認識装置及び手書き認識方法

Similar Documents

Publication Publication Date Title
US10437466B2 (en) Formula inputting method and apparatus
EP3104305B1 (fr) Circuit et procédé pour reduire le stockage de traces écrites à la main
JP5604279B2 (ja) ジェスチャー認識装置、方法、プログラム、および該プログラムを格納したコンピュータ可読媒体
SE519014C2 (sv) Metod och anordning för igenkänning av ett handskrivet mönster
KR102075433B1 (ko) 필기 입력 장치 및 그 제어 방법
US9171218B2 (en) Image processing apparatus, image processing method, and computer readable medium that recognize overlapping elements in handwritten input
JP6000992B2 (ja) 文書ファイル生成装置及び文書ファイル生成方法
CN101964048A (zh) 一种字符识别方法及系统
KR20140089915A (ko) 필기 문자 조정 방법 및 장치
JP5694236B2 (ja) 文書検索装置、方法およびプログラム
WO2016170691A1 (fr) Programme de traitement d'entrées, dispositif de traitement d'entrées, procédé de traitement d'entrées, programme d'identification de caractères, dispositif d'identification de caractères, et procédé d'identification de caractères
CN104346320A (zh) 手写文档处理装置、手写文档处理方法和手写文档处理程序
JP6432179B2 (ja) 文書ファイル生成装置及び文書ファイル生成方法
US20180032244A1 (en) Input control device, input control method, character correction device, and character correction method
WO2019049187A1 (fr) Programme, dispositif de traitement d'informations et procédé de traitement d'informations
JP6373664B2 (ja) 電子機器、方法及びプログラム
WO2021220589A1 (fr) Procédé de modification de données d'encre, dispositif de traitement d'informations et programme
JP6325218B2 (ja) 文字認識結果検証装置及び文字読取システム
US20210303842A1 (en) Information processing device and non-transitory computer readable medium
JP2014154066A (ja) 文字認識システム、文字認識プログラム及び文字認識方法
JP2014078168A (ja) 文字認識装置及びプログラム
WO2016031016A1 (fr) Dispositif électronique, procédé et programme
JP6772629B2 (ja) 情報処理装置、文字入力プログラムおよび文字入力方法
JP6030915B2 (ja) 画像再配置方法、画像再配置システム、および画像再配置プログラム
JP2021152696A (ja) 情報処理装置及びプログラム

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17924111

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17924111

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: JP