• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제15권2호
• /
• pp.121-125
• /
• 2015

In this paper, we propose a method that extracts features from character patterns using the fractal dimension of chaos theory. The input character pattern image is converted into time-series data. Then, using the modified Henon system suggested in this paper, it determines the last features of the character pattern image after calculating the box-counting dimension, natural measure, information bit, and information (fractal) dimension. Finally, character pattern recognition is performed by statistically finding each information bit that shows the minimum difference compared with a normalized character pattern database.

• 사상체질의학회지
• /
• 제27권4호
• /
• pp.396-403
• /
• 2015

Objectives The purpose of this study was to analyze the characteristics of each Soyang constitutional Exterior and Interior disease's favorable-unfavorable pattern using the Temperament and Character Inventory(TCI) in a Korean adult clinical sample.Methods A total of 32 subjects(age 20-49) completed the Korean version of the TCI. A Sasang Constitutional Medicine specialist determined each subject's Sasang constitutional type based on the Questionnaire for Sasang Constitution Diagnosis(QSCC∥) and comprehensive constitutional assessment. The participants consisting of 15 favorable pattern, 17 unfavorable pattern.Results Among the four temperament dimensions, the favorable pattern showed significantly higher scores than the unfavorable pattern in Novelty Seeking(NS) and Reward Dependence(RD). Among the three character dimensions, the unfavorable pattern showed significantly higher score than the favorable pattern subjects in Self-Directedness(SD).Conclusions Differences in temperament and character were discovered across the Soyang Constitutional disease's Exterior and Interior disease's favorable-unfavorable pattern.

• 한국컴퓨터산업학회논문지
• /
• 제2권3호
• /
• pp.285-296
• /
• 2001

본 논문에서는 초등학교 학생이나 외국인을 위해 한글을 익히는 교육용 시스템을 개발하고자 한다. 모델이 될 수 있는 표준 문자 패턴을 선정하고 이의 특징을 추출하여 데이터베이스화한다. 이를 위해 환경에 불변인 전처리과정의 수행과 특징 추출 그리고 유사도 함수를 정의한다. 최종적으로 초등학생이나 외국인이 쓴 문자에 대해 표준 문자 패턴과의 유사도를 계산하여 필기체 문자의 미적 평가를 행한다. 본 시스템은 특정 서체에 대해서도 표준 문자 패턴을 선정하여 서체 익히기까지 행할 수 있도록 확정이 가능한 시스템이며 실험에 의해 본 논문의 유용성을 입증하고자 한다.

• 한국통신학회:학술대회논문집
• /
• 한국통신학회 1985년도 추계학술발표회 논문집
• /
• pp.109-112
• /
• 1985

This paper proposes a algorithm of phonemes extraction in korean character pattern recognition. The phonemes are classified into the patterns which are separable and connected with each other. The former is extracted by means of pattern matching in consideration of topological structure of ponemes and direction of stroke sequentially. The latter is extracted by means of index and window algorithm which are performed by a 3$\times$3 sequential local operation in the thinned character pattern.

• 한국통신학회논문지
• /
• 제17권9호
• /
• pp.1029-1039
• /
• 1992

본 논문은 한글인식 방법중 주파수 변환영역에서 행하는 필터링의 방법을 제시한 것이다. 한글 문자패턴을 2차원 변조처리하여 공간위치에 의존적인 한글자소의 위상문자적 특징을 주파수 영역으로 사상하였고, 이때 변조 주파수를 정규화함으로서 주파수 영역에서 문자의 크기를 정규화 한다. 또한 한글의 각 자소를 발생위치에 따라 분류하여 표준패턴으로 설정하고, 설정된 각 자소의 표준패턴을 자소필터로 사용하여 주파수 영역으로 사상된 문자패턴을 필터링하였다. 한글자소의 분별 파라미터로는 정규화된 상호상관함수와 필터링 결과로 부터 유도된 코히어런스 함수를 산출하여 분별기준을 설정하였으며, 그 결과로서 문자크기의 변화, 자소의 융착, 제한적인 자획의 유실이나 잡음의 혼입등의 요인이 발생하였음 경우에도 한글자소의 분별이 가능하였고 또한 표준패턴을 설정함에 따라 숫자, 영문자등의 분별에도 적용할 수 있었다.

• 대한전자공학회논문지
• /
• 제13권1호
• /
• pp.23-30
• /
• 1976

이 논문에서는 위상회전에 의한 오목구조의 짐출로서 필기체 한글을 인식하는 한 방법을 검토한다. 문자 Pattern를 오목구조적인 기본 Segment로 분해하여 집합으로 분류하고, 그들 집함에 대한 각 Segment의 폐상태와 위상특징을 logic으로 표현한다. 다음 그들 logic pattern의 위상회전으로서 오목구조의 topological성질과 위상특징을 검출하여 문자를 결정한다. 이 방법은 필기체의 변화와 문자의 대소, 경사 띤 위치 변위에 대한 식별의 유연성을 가지며, 인식율이 높다. In this paper, a method is proposed for the recognition of hand-written Hangeul. This is peiformed by extraction of the concave structural segments by phase rotation. Character patterns can be decomposed into the fundamental concave structural segments which are also categorized into segment sects, and the closure and phase features of each segment in set is represented by logics. By rotating the logic pattern, the topological and phase features of segment are extracted for the reliable recognition of the character. It is also evaluated that this method applies to a wide variety of shape, position and declination of the character.

• Journal of Ecology and Environment
• /
• 제31권4호
• /
• pp.255-260
• /
• 2008

A commonly held view in studies of character displacement is that character states of both species are shifted in areas of sympatry. This view has been confirmed in an overwhelming number of cases for ecological character displacement. Excluding species pairs in which one of the two interacting species is found only within the distribution of the other species and species displaying gynogenesis, the pattern of reproductive character displacement is asymmetrical in that the shift in character states between areas of symaptry and allopatry occurs in only one of the two interacting species. Hypotheses for the reasons behind this asymmetry in reproductive character displacement include (1) homogenization by gene flow, (2) other mechanisms of reproductive isolation, and (3) sufficient reproductive isolation being provided by one of the interacting species exhibiting a pattern of reproductive character displacement. Because reproductive isolation can be achieved by divergence at any point in a sequence of premating reproductive behaviors and postmating developments, it is necessary to understand the mechanisms of reproductive isolation of two interacting taxa in areas of sympatry and allopatry and to analyze the relative contributions of potential factors to reproductive isolation to disentangle hypotheses for the patterns of asymmetry.

• 한국통신학회논문지
• /
• 제11권2호
• /
• pp.85-92
• /
• 1986

한글 Wordprocessor, Workstation 및 Telematics용 I/O Device에서는 각종 크기의 문자나 도형들을 요구하고 있다. 본 논문에서는 내장된 문자 dot pattern을 축소 또는 확대시키기 위하여 지금까지 연구되어온 각종 방식의 알고리즘을 논한다. 또한 문자 dot pattern의 크기를 변환시키는 방법을 평가하기 위한 항목을 논하며 이항목에 따라서 종래의 방식을 주관적으로 평가한다.

• 한국정보처리학회논문지
• /
• 제7권3호
• /
• pp.1025-1031
• /
• 2000

Pre-existing pattern recognition techniques, in the case of character recognition, have limited on the application field. But CAI character learning system and writer's recognition system are very important parts. The application field of pre-existing system can be expanded in the content that the learning of characters and the recognition of writers in the proposed paper. In order to achieve these goals, the development contents are the following: Firstly, pre-processing method by understanding the image structure is proposed, secondly, recognition of characters are accomplished b the histogram distribution characteristics. Finally, similarity measure functions are defined from standard character pattern for matching of the input character pattern. Also the effectiveness of this system is demonstrated by experimenting the standard primitive image.

• 제어로봇시스템학회논문지
• /
• 제12권3호
• /
• pp.241-247
• /
• 2006

We propose a character recognition system to extract the component reference names from printed circuit boards (PCBs) automatically. The names are written in horizontal, vertical, reverse-horizontal and reverse-vertical directions. Also various symbols and figures are included in PCBs. To recognize the character and orientation effectively, we divide the recognizer into two stages: character classification stage and orientation classification stage. The character classification stage consists of two sub-recognizers and a verifier. The rotaion-invarint features of input pattern are then used to identify the character independent of orientation. Each recognizer is implemented as a neural network, and the weight values of verifier are obtained by genetic algorithm. In the orientation classification stage, the input pattern is compared with reference patterns to identify the orientation. Experimental results are presented to verify the usefulness of the proposed system.