KR960002072A - Contact Character Separation Method of English Recognition System - Google Patents

Contact Character Separation Method of English Recognition System Download PDF

Info

Publication number
KR960002072A
KR960002072A KR1019940012558A KR19940012558A KR960002072A KR 960002072 A KR960002072 A KR 960002072A KR 1019940012558 A KR1019940012558 A KR 1019940012558A KR 19940012558 A KR19940012558 A KR 19940012558A KR 960002072 A KR960002072 A KR 960002072A
Authority
KR
South Korea
Prior art keywords
character
contact
separating
contact character
separated
Prior art date
Application number
KR1019940012558A
Other languages
Korean (ko)
Inventor
이영태
Original Assignee
이헌조
엘지전자 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 이헌조, 엘지전자 주식회사 filed Critical 이헌조
Priority to KR1019940012558A priority Critical patent/KR960002072A/en
Publication of KR960002072A publication Critical patent/KR960002072A/en

Links

Landscapes

  • Character Input (AREA)

Abstract

본 발명은 영문인식시스템의 접촉문자 분리방법에 관한 것으로서, 종래에는 문자열에서 수직흑화소 수에 의하여 각 개별문자를 분리하고 각 개별문자의 폭과 공간(space)의 평균폭을 이용하여 물리적으로 인접문자를 융합하거나 절단하는 경우 이는 문자의 평균폭과 공간의 폭의 일정한 경우에는 가능하나 영문자의 폭은 각기 달라 분리하기가 힘들 뿐만아니라 접촉문자의 분리성능이 떨어지는 문제점이 있었다. 따라서 본 발명은 접촉유형을 판단하고 문자의 콘케이브(concave)정보를 이용하여 보다 정확한 분리를 행할 수 있도록 한다.The present invention relates to a method of separating contact characters of an English recognition system. In the related art, each individual character is separated by a vertical black pixel number from a character string and is physically adjacent using an average width of each individual character. In the case of fusion or truncation, this is possible in the case where the average width of the character and the width of the space are constant, but the width of the alphabet is difficult to separate, and the separation performance of the contact character is inferior. Therefore, the present invention allows to determine the contact type and to perform a more accurate separation using the concave information of the character.

Description

영문인식시스템의 접촉문자 분리방법Contact Character Separation Method of English Recognition System

본 내용은 요부공개 건이므로 전문내용을 수록하지 않았음As this is a public information case, the full text was not included.

제2도는 본 발명 영문인식시스템의 접촉문자 분리방법에 대한 흐름도,2 is a flow chart for a method of separating contact characters of the present invention English recognition system,

제3도는 제2도에서 접촉문자 분리를 수행하기 위한 시스템 구성도,3 is a system diagram for performing contact character separation in FIG.

제4도는 제2도에서 접촉문자 분리 흐름도.4 is a flow chart of contact character separation in FIG.

Claims (2)

스캐너로 부터 입력된 이진영상에 대하여 문자열을 분리하는 문자열 분리단계와, 상기 문자열 분리단계에서 분리된 문자열에 대해 수직방향의 누적 흑화소를 이용해 개별문자를 추출하는 개별문자 분리단계와, 상기 개별문자 분리단계에서 분리된 개별문자를 인식하는 인식단계와, 상기 인식 단계에서 실패(reject)한 문자는 접촉문자로 판단하여 콘케이브(concave) 영역을 찾아내는 콘케이브영역 추출단계와, 상기 콘케이브영역 추출 단계에서 구한 콘케이브의 위치에 따라 접촉문자를 유형별로 분류하는 접촉문자유형 분류단계와, 상기 접촉문자유형 분류단계에서 분류된 접촉문자를 각각 분리하고 그 분리된 접촉문자는 다시 인식단계로 되돌아가도록 하는 접촉문자 분리단계로 이루어짐을 특징으로 하는 영문인식시스템의 접촉문자 분리방법.A character string separating step of separating a character string from a binary image input from a scanner, an individual character separating step of extracting individual characters using a vertical black cumulative pixel with respect to the character string separated in the character string separating step, and the individual character Recognition step of recognizing individual characters separated in the separation step, Concave area extraction step of finding the concave area by determining the character rejected in the recognition step as a contact character, Extraction of the concave area The contact character type classification step of classifying the contact letters by type according to the position of the concave obtained in the step, and the contact letters classified in the contact letter type classification step, respectively, and the separated contact letters are returned to the recognition step again. Contact character separation method of the English recognition system, characterized in that consisting of the contact character separation step. 제1항에 있어서, 접촉문자유형 분류단계에서 분류된 유형은 상단접촉문자와 하단접촉문자 및 상하단접촉문자로 이루어져 있음을 특징으로 하는 영문인식시스템의 접촉문자 분류방법.The method of claim 1, wherein the type classified in the contact character type classification step comprises an upper contact character, a lower contact character, and an upper and lower contact character. ※ 참고사항 : 최초출원 내용에 의하여 공개하는 것임.※ Note: The disclosure is based on the initial application.
KR1019940012558A 1994-06-03 1994-06-03 Contact Character Separation Method of English Recognition System KR960002072A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1019940012558A KR960002072A (en) 1994-06-03 1994-06-03 Contact Character Separation Method of English Recognition System

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1019940012558A KR960002072A (en) 1994-06-03 1994-06-03 Contact Character Separation Method of English Recognition System

Publications (1)

Publication Number Publication Date
KR960002072A true KR960002072A (en) 1996-01-26

Family

ID=66686097

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1019940012558A KR960002072A (en) 1994-06-03 1994-06-03 Contact Character Separation Method of English Recognition System

Country Status (1)

Country Link
KR (1) KR960002072A (en)

Similar Documents

Publication Publication Date Title
Zhou et al. Bangla/English script identification based on analysis of connected component profiles
RU2259592C2 (en) Method for recognizing graphic objects using integrity principle
Lam et al. Reading newspaper text
Rodrigues et al. Cursive character recognition–a character segmentation method using projection profile-based technique
Vijay Kumar et al. Machine recognition of printed Kannada text
Bharathi et al. Segmentation of Telugu touching conjunct consonants using overlapping bounding boxes
KR960002072A (en) Contact Character Separation Method of English Recognition System
JPS60153574A (en) Character reading system
Nguyen et al. Enhanced character segmentation for format-free Japanese text recognition
Chiou et al. Recognition of Chinese business cards
Mashiyat et al. Bangla off-line handwritten character recognition using superimposed matrices
KR102064974B1 (en) Method for recogniting character based on blob and apparatus using the same
KR0186172B1 (en) Character recognition apparatus
Emmanuel et al. Automatic detection and recognition of Malayalam text from natural scene images
Kaur et al. Adverse conditions and techniques for cross-lingual text recognition
JPS60153575A (en) Character reading system
JPS6227887A (en) Character type separating system
KR100480024B1 (en) Collection Recognition Method Using Stroke Thickness Information
Bodduluri et al. A novel way of identifying telugu, tamil and english scripts by priority check using discerning features
KR950001553A (en) How to Separate Individual Characters in English Strings
KR970002740A (en) Contact Character Separation and Feature Extraction Method of Character Recognition Device
JP2000181989A (en) Character recognition device, method therefor and computer readable recording medium recording the method as program
KR960011775A (en) How to separate contact character of character recognition device
Johns et al. Typed Malayalam Character Recognition.
JP2978801B2 (en) Character input method for handwritten character recognition

Legal Events

Date Code Title Description
WITN Application deemed withdrawn, e.g. because no request for examination was filed or no examination fee was paid