KR950020298A - Hangul Handwriting Online Character Recognition Device and Method - Google Patents

Hangul Handwriting Online Character Recognition Device and Method Download PDF

Info

Publication number
KR950020298A
KR950020298A KR1019930031606A KR930031606A KR950020298A KR 950020298 A KR950020298 A KR 950020298A KR 1019930031606 A KR1019930031606 A KR 1019930031606A KR 930031606 A KR930031606 A KR 930031606A KR 950020298 A KR950020298 A KR 950020298A
Authority
KR
South Korea
Prior art keywords
recognition
hangul
dictionary
neutral
representative points
Prior art date
Application number
KR1019930031606A
Other languages
Korean (ko)
Other versions
KR0126800B1 (en
Inventor
안병재
도정인
Original Assignee
김광호
삼성전자 주식회사
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 김광호, 삼성전자 주식회사 filed Critical 김광호
Priority to KR1019930031606A priority Critical patent/KR0126800B1/en
Publication of KR950020298A publication Critical patent/KR950020298A/en
Application granted granted Critical
Publication of KR0126800B1 publication Critical patent/KR0126800B1/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/10—Image acquisition

Abstract

본 발명은 한글 필기체 온라인 문자인식 방법에 관한 것으로, 특히 한글의 각 소자를 분리하여 필기하지 않고 연결하여 필기한 한글의 인식 및 필기자의 자소간 연결 필기습관에 적응가능하도록 하는 한글 필기체 온라인 인식 시스템 및 그 방법에 관한 것으로 사용자로부터 한글데이타를 입력받는 문자입력부; 문자입력부를 통하여 입력되는 데이타에서 잡음 및 불필요한 부분을 삭제하고 대표적인 점들만을 추출하는 전처리부; 글자를 이루는 초성, 중성 및 종성에 대한 각 자소들과 이들의 결합에 의하여 형성되는 연결자소에 대한 정보를 포함하는 인식사전부; 전처리부에서 처리된 대표점들을 인식사전부를 검색하여 자소간 연결된 글자를 인식처리하는 인식제어부를 포함한다.The present invention relates to a Hangul handwriting online character recognition method, and in particular, Hangul handwriting online recognition system that can be adapted to the recognition of the handwritten Hangul Hangul and connected between the phoneme of the handwriting without separating each element of the Hangul and writing; and A character input unit for receiving the Hangul data from the user relates to the method; A preprocessor for removing noise and unnecessary parts from data input through the character input unit and extracting only representative points; A recognition dictionary including information on each phoneme of the initial, neutral, and final characters forming a letter and a linking phoneme formed by a combination thereof; It includes a recognition control unit for recognizing the characters connected between the elements by searching the recognition dictionary for the representative points processed by the preprocessor.

Description

한글 필기체 온라인 문자인식 장치 및 방법Korean Cursive Online Character Recognition Apparatus and Method

본 내용은 요부공개 건이므로 전문내용을 수록하지 않았음Since this is an open matter, no full text was included.

Claims (9)

사용자로부터 한글데이타를 입력받는 문자입력부; 상기 문자입력부를 통하여 입력되는 데이타에서 잡음 및 불필요한 부분을 삭제하고 대표적인 점들만을 추출하는 전처리부; 글자를 이루는 초성, 중성 및 종성에 대한 각 자소들과 이들의 결합에 의하여 형성되는 연결자소에 대한 정보를 포함하는 인식사전부; 상기 전처리부에서 처리된 대표점들을 인식사전부를 검색하여 자소간 연결된 글자를 인식처리하는 인식제어부를 포함하는 것을 특징으로 하는 한글 온라인 문자인식 장치.Character input unit for receiving Hangul data from the user; A preprocessor which removes noise and unnecessary parts from the data input through the character input unit and extracts only representative points; A recognition dictionary including information on each phoneme of the initial, neutral, and final characters forming a letter and a linking phoneme formed by a combination thereof; Hangul online character recognition device comprising a recognition control unit for recognizing the characters connected between the phone to search the recognition dictionary for the representative points processed in the pre-processing unit. 제1항에 있어서, 상기 한글 필기체 온라인 문자인식 장치는 상기 전처리부에서 대표점들에 대응하는 자소들이 상기 인식사전부에서 검색되지 않는 경우 이를 새로이 사전에 등록시키는 인식사전 생성부를 더 포함하는 것을 특징으로 하는 한글 온라인 문자인식 장치.The method of claim 1, wherein the Hangul handwriting online character recognition device further comprises a recognition dictionary generation unit for newly registering the phoneme corresponding to the representative points in the pre-processing unit if it is not found in the recognition dictionary. Hangul online character recognition device. 제1항 또는 제2항에 있어서, 상기 문자입력부를 통하여 입력되는 한글데이타는 필기체 데이타인 것을 특징으로 하는 한글 온라인 문자인식 장치.The Hangul online character recognition device according to claim 1 or 2, wherein the Hangul data input through the character input unit is handwritten data. 제3항에 있어서, 상기 인식사전부는 초성, 중성, 종성 초중연결, 초중종연결 및 중종연결사전을 포함하는 것을 특징으로 하는 한글 온라인 문자인식 장치.The Hangul online character recognition device according to claim 3, wherein the recognition dictionary comprises a consonant, a neutral, a consonant super middle connection, a super medium connection and a medium connection dictionary. 제4항에 있어서, 상기 인식제어부는 상기 전처리부에서 처리된 대표점들로 이루어진 자소들에 대하여 상기 인식사전을 참조하여 초성, 중성, 초중종 연결인식을 수행하는 제1인식부; 상기 제1인식부에서의 초성인식을 제외한 나머지 획수에 대한 자소들에 대하여 상기 인식사전을 참조하여 중성, 종중연결인식을 수행하는 제2인식부; 및 상기 제2인식부에서의 중성인식 후의 나머지 획수에 대한 자소들에 대하여 상기 인식사전을 참조하여 종성인식을 수행하는 제3인식부를 포함하는 것을 특징으로 하는 한글 온라인 문자인식 장치.5. The apparatus of claim 4, wherein the recognition controller comprises: a first recognition unit configured to perform initial, neutral, and middle and middle kind connection recognition with reference to the recognition dictionary with respect to phonemes consisting of representative points processed by the preprocessor; A second recognition unit for performing neutral and seed connection recognition with reference to the recognition dictionary on the phonemes for the remaining strokes except for the initial recognition in the first recognition unit; And a third recognition unit performing final recognition with reference to the recognition dictionary with respect to the phonemes for the remaining strokes after the neutral recognition in the second recognition unit. 온라인 한글인식 방법에 있어서, 외부로부터 입력되는 한글 데이타에서 잡음 및 불필요한 부분을 삭제하고 대표적인 점들만을 추출하는 전처리단계; 상기 전처리단계에서 처리된 대표점들을 인식사전부를 검색하여 자소간 연결된 글자를 인식하는 인식단계를 포함하는 것을 특징으로 하는 한글 온라인 문자인식 방법.An online Hangul recognition method comprising: a preprocessing step of removing noise and unnecessary portions from Hangul data input from outside and extracting only representative points; Hangul online character recognition method comprising a recognition step of recognizing letters connected between the phoneme by searching the recognition dictionary for the representative points processed in the preprocessing step. 제6항에 있어서, 상기 한글 온라인 문자인식 방법은 상기 전처리단계에서 대표점들에 대응하는 자소들이 상기 인식사전에서 검색되지 않는 경우 이를 새로이 사전에 등록시키는 자소등록 단계를 더 포함하는 것을 특징으로 하는 한글 온라인 문자인식 방법.The method of claim 6, wherein the Hangul online character recognition method further comprises a phoneme registration step of newly registering the phonemes corresponding to the representative points in the preprocessing step if they are not searched in the recognition dictionary. Hangul online character recognition method. 제6항 또는 제7항에 있어서, 상기 입력되는 한글 데이타는 필기체로 쓰여진 것을 특징으로 하는 한글 온라인 문자인식 방법.The method of claim 6 or 7, wherein the input Hangul data is written in handwriting. 제8항에 있어서, 상기 인식단계는 상기 전처리단계에서 처리된 대표점들로 이루어진 자소들에 대하여 상기 인식사전을 참조하여 초성, 중성, 초중종 연결인식을 수행하는 제1인식단계; 상기 제1인식단계에서 이루어진 초성인식을 제외한 나머지 획수에 대한 자소들에 대하여 상기 인식사전을 참조하여 중성, 종중연결인식을 수행하는 제2인식단계; 및 상기 제2인식단계에서의 중성인식 후의 나머지 획수에 대한 자소들에 대하여 상기 인식사전을 참조하여 종성인식을 수행하는 제3인식단계를 포함하는 것을 특징으로 하는 한글 온라인 문자인식 방법.The method of claim 8, wherein the recognizing step comprises: a first recognizing step of performing initial, neutral, and middle-medium sized connection recognition with reference to the recognition dictionary on the phonemes consisting of representative points processed in the preprocessing step; A second recognition step of performing neutral and cluster connection recognition with reference to the recognition dictionary on the phonemes for the remaining strokes except for the initial recognition made in the first recognition step; And a third recognition step of performing final recognition with reference to the recognition dictionary on the phonemes for the remaining strokes after the neutral recognition in the second recognition step. ※ 참고사항 : 최초출원 내용에 의하여 공개하는 것임.※ Note: The disclosure is based on the initial application.
KR1019930031606A 1993-12-30 1993-12-30 Hand-written korean character, on-line recognizing apparatus and its method KR0126800B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1019930031606A KR0126800B1 (en) 1993-12-30 1993-12-30 Hand-written korean character, on-line recognizing apparatus and its method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1019930031606A KR0126800B1 (en) 1993-12-30 1993-12-30 Hand-written korean character, on-line recognizing apparatus and its method

Publications (2)

Publication Number Publication Date
KR950020298A true KR950020298A (en) 1995-07-24
KR0126800B1 KR0126800B1 (en) 1998-04-02

Family

ID=19374546

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1019930031606A KR0126800B1 (en) 1993-12-30 1993-12-30 Hand-written korean character, on-line recognizing apparatus and its method

Country Status (1)

Country Link
KR (1) KR0126800B1 (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100754497B1 (en) * 1998-05-07 2007-09-03 뉘앙스 커뮤니케이션스 이스라엘, 리미티드 Handwritten and voice control of vehicle components
KR20030090381A (en) * 2002-05-23 2003-11-28 퍼셉컴(주) Letters recognition method and letters recognition apparatus
KR100957059B1 (en) * 2007-12-04 2010-05-13 한미아이티 주식회사 A method and system for processing character data written on a touch screen
CN106440704B (en) * 2016-11-20 2018-10-26 广西大学 A kind of field straw burning grain drying device

Also Published As

Publication number Publication date
KR0126800B1 (en) 1998-04-02

Similar Documents

Publication Publication Date Title
Alginahi A survey on Arabic character segmentation
Wshah et al. Statistical script independent word spotting in offline handwritten documents
Abdelaziz et al. A large vocabulary system for Arabic online handwriting recognition
JPH0684006A (en) Method of online handwritten character recognition
Mesleh et al. An optical character recognition
Manke et al. A connectionist recognizer for on-line cursive handwriting recognition
Maloo et al. Gujarati script recognition: a review
Sharma et al. Rearrangement of recognized strokes in online handwritten Gurmukhi words recognition
Fallah et al. Detecting features of human personality based on handwriting using learning algorithms
Belaïd et al. Human reading based strategies for off-line Arabic word recognition
KR950020298A (en) Hangul Handwriting Online Character Recognition Device and Method
Ma et al. A new database for online handwritten Mongolian word recognition
KR20090111202A (en) The Optical Character Recognition method and device by the numbers of horizon, vertical and slant lines which is the element of Hanguel
Saeed Automatic recognition of handwritten arabic text: A survey
Sudarsan et al. A novel approach for handwriting recognition in malayalam manuscripts using contour detection and convolutional neural nets
Khin et al. Myanmar character extraction from vehicle images using aspect ratio and bounding box
KR970059977A (en) Online Character Recognition Method and Online Character Recognition Device
Chamchong et al. A combined method of segmentation for connected handwritten on palm leaf manuscripts
CN111429921A (en) Voiceprint recognition method, system, mobile terminal and storage medium
KR950005533B1 (en) On-line character recognizing system
Annanurov et al. Feature selection for Khmer handwritten text recognition
Colaco et al. Design and implementation of Konkani text to speech generation system using OCR technique
Das et al. Pattern recognition approaches to japanese character recognition
Malik et al. Recognition of printed Devnagari characters with regular expression in finite state models
KR930023867A (en) Online Hangul Handwritten Character Recognition Method

Legal Events

Date Code Title Description
A201 Request for examination
E902 Notification of reason for refusal
E601 Decision to refuse application
J2X1 Appeal (before the patent court)

Free format text: APPEAL AGAINST DECISION TO DECLINE REFUSAL

E701 Decision to grant or registration of patent right
GRNT Written decision to grant
FPAY Annual fee payment

Payment date: 20070928

Year of fee payment: 11

LAPS Lapse due to unpaid annual fee