• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.7
• /
• pp.1680-1684
• /
• 2009

The priming task was used in order to provide an experimental evidence on whether the processing unit of Korean syllable is antibody or not. Four types of experimental conditions were made: antibody overlap condition (e.g., sumjil -> sungjik), rime overlap condition (e.g.,: hungchik -> sungjik), onset and coda overlap condition (e.g.,: saengjeok -> sungjik), and no overlap condition (e.g.,: chanmeol -> sungjik). In addition, we manipulated the letter type by type and type in order to investigate on whether different degrees of priming are there for the priming task. The result showed that only type showed significant inhibitory effects. This implicates that certain Korean word would be represented and processed by the antibody unit, and further studies are needed to know the whole pattern of Korean word recognition.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.12a
• /
• pp.295-298
• /
• 2001

본 논문에서는 CCD카메라로 입력 받은 다중 크기 및 활자체로 구성된 한글문서의 화상 데이터를 편집기에서 수정 가능한 문자로 변환시키는 시스템을 구현하였다. 먼저 Dynamic 이 진화 처리 과정을 거친 화상을 흑백 화소의 누적분포에 따라 문자단위로 분할한 후, 다양한 크기로 분할된 문자를 표준패턴 크기로 표준화 시켰다. 한글을 자소 간 공백 위치의 특징에 따라서 6가지 유형으로 분류한 후, 퍼지 이론을 접목시킨 원형 패턴 벡터 알고리즘을 사용해서 표준벡터와 입력된 글자의 특징벡터를 비교하여 문자로 인식하게 하였다. 각 6가지 유형에서 서로 다른 자소로 결합된 문자들을 30개 선정하여 여러 가지 활자체 및 크기에 적용해 본 결과, 모두 문서화가 가능함을 알 수 있었다.

• Korean Journal of Optics and Photonics
• /
• v.34 no.1
• /
• pp.13-21
• /
• 2023

We have investigated the acceptance angle and imaging performance of a curved artificial compound eye (ACE), depending on the sag height of the microlens array to maximize its sensitivity to light. When the h/r values increased from 0.22 to 0.37, the acceptance angle of the curved ACE was expanded from 28.70° to 49.02°, which is an enhancement by 70.8%. With the designed optical system, it was demonstrated that a microlens located at the 23rd position from the center of the main lens could still focus an incident beam tilted at 56.35°, so that the letter F was clearly observed.

• Annual Conference on Human and Language Technology
• /
• 1993.10a
• /
• pp.295-301
• /
• 1993

제약이 없이 자유롭게 쓴 오프라인 필기체 한글을 인식하는 문제는 응용분야에 따른 도메인의 정보를 이용함으로써 보다 쉽게 접근할 수 있다. 본 연구는 오프라인 필기체 한글 인식을 위한 한 도메인으로 우편봉투를 대상으로 하였을 때, 우편번호가 할당된 지명과 건물명을 대상으로 글자의 종류와 빈도수를 통계 분석하였다. 분석 결과 가능한 한글 조합 11,172자중 403자만이 쓰이고 있음을 알았다. 이러한 정보는 자소 분할이 어려운 오프라인 필기체 한글 인식에 있어, 문자 단위 정합을 사용했을 때 인식속도 및 인식률 향상에 기여 할 것으로 생각된다.

• Proceedings of the IEEK Conference
• /
• 2001.09a
• /
• pp.425-428
• /
• 2001

본 논문에서는 문서 위의 문자를 Off-Line방식으로 컴퓨터에 저장할 수 있도록 기하학적 패턴 벡터를 이용하여 한·영문자 및 글꼴을 인식하는 알고리즘을 제안하였다. 일반적으로 문서에서는 여러 가지 글꼴에 따라 글자의 형태가 다르므로 대표적인 한·영 세 가지 글꼴을 기하학적 패턴(Geometrical Pattern Vector)을 이용하여 크기와 이동에 인식하도록 하였다. 이진 입력 한영혼용 영상에서 잡음을 제거하고 수평·수직 투영 기법을 이용하여 한 문자를 분할하여 문자의 폭에 따라 기하학적 패턴을 추출한다. 추출한 패턴은 각 합계를 계산하여 기준 패턴 합계와 비교한 후 기준 패턴 문자와 글꼴을 인식하게 된다. 마지막으로 제안한 알고리즘의 성능을 평가하기 위해 크기, 이동 변형이 있는 대표적인 한·영 글꼴(신명조, 궁서, 고딕)체와 영어 Time New Roman체를 대상으로 모의 실험을 수행하였다. 제안한 알고리즘은 기존의 원형 패턴 알고리즘보다 문자인식률과 글꼴 그리고 영어의 대·소문자를 구별하는 우수함을 보였다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.4 no.3
• /
• pp.52-58
• /
• 1999

This paper proposed and algorithm for distinguishing Korean and English characters which can be applied to multi-size and multi-font images The proposed algorithm distinguishes them as the ratio height to width of each character, the number of connected component, existing or not of stroke image on the left-upper area and detection of bars in an input image. The process of detecting bar is a sequence of left, upper, right, and lower. The proposed method was experimented and proved good performance for the Myungjo font, the Sinmyungjo font, the Gothic font, and the Kungseo font of Hanguel word processor which is widely used for the writing of documents.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.6
• /
• pp.1652-1663
• /
• 1997

This paper proposes a distinction algorithm of Korean and English characters which can be applied to multi-font from the results of thinning. The proposed algorithm distinguishes Korean and English characters as the number of connected components. If it can not distinguish those characters with the number of connected component, it distinguishes them as the vowel included in Korean characters. In experimental results, the distinction rate is about 99.82% for the 21,150 characters of three widely used fonts.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.8 no.4
• /
• pp.1-13
• /
• 2009

VMS(Variable Message Sign) which makes the traffic flow smooth by providing traffic information to road users in real-time has been being installed or operated on the road as part of the detailed ITS system. However, some problems were found as a result of survey on express way currently. In the part of the phase operation, the message interpretation time wasn't defined so that the phase operation was difficult. In the part of the information service, not considering characteristic of the VMS section caused the confusion to drivers. In the part of the message exposure, font, alignment, conversion and composition of the information were not consistent and use of superfluous words and inconsistent use of word having the same meaning brought about the problem on information communication This study established the detailed exposure method based on instructions relative to VMS operation. The method established by defining the number of appropriate phase and setting required function of each individual VMS installation location. The method is as follow. the font type is the GULIM, the message conversion method is simple conversion method, the alignment method is centering alignment method and the color is defined according to each situation. In this study, the preference survey was performed to review the validity of the proposed improvement through the common driver. The results were similar with the pre-study except for the font type. This study established the detailed exposure method based on instructions relative to VMS operation. The method established by defining the number of appropriate phase and setting required function of individual VMS installation location. For the evaluation of status and improvement, preference survey of ordinary drivers and statistics analysis was carried.

• Journal of Korean Ophthalmic Optics Society
• /
• v.19 no.2
• /
• pp.217-224
• /
• 2014

Purpose: This study was conducted to compare and analyze the accommodative system (accommodative response and accommodative lag) according to the material and font size of near visual media that we often encounter in daily life. Methods: Forty adult men and women aged 20 to 30 who not had specific ocular diseases and refractive surgery experience were examined to measure and compare the accommodative response according to the material of near visual media (print paper, newspaper, magazine, the I-Phone, LCD monitor) and font size (6, 8, 10, 12) by using both eyes open-view auto-refractometer. Results: The accommodative stimulus was $2.28{\pm}0.11D$ and the accommodative response was $1.66{\pm}0.30D$. The accommodative lag namely the difference between accommodative stimulus and accommodative response was $0.62{\pm}0.28D$. The accommodative response according to material of visual media using LCD monitor was $1.35{\pm}0.26D$ (p=0.00) and using the I-Phone was $1.55{\pm}0.25D$ (p=0.04). Both of them were statistically significant lower. The accommodative lag using LCD monitor was $0.93{\pm}0.24D$ (p=0.00) and using the I-Phone was $0.73{\pm}0.25D$ (p=0.04) and they were statistically significant higher. The accommodative response and accommodative lag according to font size were not statistically significant (p>0.05). Conclusions: During near working, the accommodative system was more affected by material than font size of visual media. Especially, visual media of non-luminous material (print paper, newspaper, magazine) are considered fewer burdens on eyes than luminous material (I-Phone, LCD monitor) in terms of accommodative system.

• Information and Communications Magazine
• /
• v.9 no.11
• /
• pp.34-36
• /
• 1992

여러 개의 문자(혹은 여러 개의 자소로 구성된 한개의 문자)를 인식할때에는 문자(혹은 자소) 상호간에 영향을 미쳐서 오인식이 발생할 가능성이 높다. 개개의 숫자인식에 기초한 숫자열 인식이나, 개개의 자소인식을 바탕으로한 필기체 한글인식이 그 좋은 보기일 것이다. 예를 들어 단순한 한글 '그'를 Neocognitron으로 인식한다고 생각해 보자, 조합 가능한 글자를 모두 기억시키려면 방대한 규모의 회로가 필요하므로 현실적으로 불가능하다. 따라서 기본 자소(자음 14개, 모음 10개)를 인식하도록 학습시키고 이를 바탕으로 한글을 인식하는 것이 효율적이다. 이때, 회로의 각 세포가 보는 receptive field가 유한하여 '?'의 끝 세로부분 'I'가 '?'에 영향을 미쳐서 '?'로 인식된다 즉, 자소간의 섭동에 의해 '그'가 '고'로 인식되는 것이다. 이와같은 예는 '니'가 '넉'으로, '41'이 '4H'로 인식되는 등 매우 많지만 그 해결에 대한 연구는 거의 없다. 이 논문에서는 필기체 한글 자소를 인식하는 Necognitron외에 자소간의 섭동현상을 제거하기 위한 high-level constraint 회로를 Lotka-Volterra동역학에 기초하여 설계하였다. 이로써 off-line필기체 한글인식을 보다 효과적으로 할 수 있음을 컴퓨터 시뮬레이션으로 보인다.