• Title/Summary/Keyword: 자소

Search Result 184, Processing Time 0.037 seconds

Detection of Intersection Points of Handwritten Hangul Strokes using Run-length (런 길이를 이용한 필기체 한글 자획의 교점 검출)

  • Jung, Min-Chul
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.7 no.5
    • /
    • pp.887-894
    • /
    • 2006
  • This paper proposes a new method that detects the intersection points of handwritten Hangul strokes using run-length. The method firstly finds the strokes' width of handwritten Hangul characters using both horizontal and vertical run-lengths, secondly extracts horizontal and vertical strokes of a character utilizing the strokes' width, and finally detects the intersection points of the strokes exploiting horizontal and vertical strokes. The analysis of both the horizontal and the vertical strokes doesn't use the strokes' angles but both the strokes' width and the changes of the run-lengths. The intersection points of the strokes become the candidated parts for phoneme segmentation, which is one of main techniques for off-line handwritten Hangul recognition. The segmented strokes represent the feature for handwritten Hangul recognition.

  • PDF

Chemical Composition of Perilla frutescens Britton var. Crispa Decaisne Cultivated in Different Areas of Korea -Part 1. Characteristics of Lipid and Fatty Acid Composition- (자소(紫蘇)의 산지별(産地別) 화학조성(化學組成) -제일보(弟一報) 지질(脂質)의 특성(特性) 및 지방산조성(脂肪酸組成)-)

  • Park, H.S.;Kim, J.G.;Cho, M.J.
    • Applied Biological Chemistry
    • /
    • v.24 no.4
    • /
    • pp.224-229
    • /
    • 1981
  • Perilla (Perilla frutescens Britton var. Crispa Decasne) cultivated in three geographical areas of Korea, Gwangju, Taegu and Jeju, was analyzed for carbohydrate, lipid, protein, inorganic components and fatty acid composition. Carbohydrate, lipid and protein content of perilla seed ranged from 40 (Taegu) to 44% (Jelu), from 28 (Jeju) to 34% (Taegu) and from 15 (Gwangju) to 16% (Jeju), respectively. The overage contents of potassium, silicate, calcium, phosphate, iron, zinc, magnesium and mangane in the perilla seed varied between $426{\sim}446$, $197{\sim}229$. $124{\sim}136$, $46{\sim}56$, $30{\sim}49$, $42{\sim}45$, $40{\sim}45$, and $30{\sim}36mg%$, respectively and those variations different cultivation areas were not significant except iron. Saponification number, iodine value and acid value of the perilla oil were between $194{\sim}198$, $196{\sim}200$ and $4{\sim}5$, respectively. Those variations among the cultivation areas were not significant. The composition of the perilla oil was observed to be composed of $92{\sim}95%$ of triglyceride, $1.2{\sim}1.3%$ of phospholipid, $1.7{\sim}1.9%$ of unsaponifiables, $0.7{\sim}0.9%$ of free fatty acid, and $1.1{\sim}1.4$ linolenic, linoleic and oleic acid as $55{\sim}56$, $16{\sim}18$ and $16{\sim}20%$ of total fatty acids, but in phospholipid, the content of saturated fatty acids, $12{\sim}24$ of total fatty acid, was higher than that in triglyceride, $8{\sim}19%$ of total fatty acids. The content of saturated fatty acids in sterylester $(14{\sim}19%)$ was higher than that in sterylglycoside ($6{\sim}7%$ of total fatty acids). The variation in fatty acid composition was not significant in the composition of total fatty acid but a significant difference was observed in the composition of phospholipid, in which the content of palmitate ranged from 11.8%(Taegu) to 24%(Gwangju) of total fatty acids. No significant variation was found in the fatty acid composition among the cultivation areas, while a significant difference was observed in phospholipid.

  • PDF

Study on the Neural Network for Handwritten Hangul Syllabic Character Recognition (수정된 Neocognitron을 사용한 필기체 한글인식)

  • 김은진;백종현
    • Korean Journal of Cognitive Science
    • /
    • v.3 no.1
    • /
    • pp.61-78
    • /
    • 1991
  • This paper descibes the study of application of a modified Neocognitron model with backward path for the recognition of Hangul(Korean) syllabic characters. In this original report, Fukushima demonstrated that Neocognitron can recognize hand written numerical characters of $19{\times}19$ size. This version accepts $61{\times}61$ images of handwritten Hangul syllabic characters or a part thereof with a mouse or with a scanner. It consists of an input layer and 3 pairs of Uc layers. The last Uc layer of this version, recognition layer, consists of 24 planes of $5{\times}5$ cells which tell us the identity of a grapheme receiving attention at one time and its relative position in the input layer respectively. It has been trained 10 simple vowel graphemes and 14 simple consonant graphemes and their spatial features. Some patterns which are not easily trained have been trained more extrensively. The trained nerwork which can classify indivisual graphemes with possible deformation, noise, size variance, transformation or retation wre then used to recongnize Korean syllabic characters using its selective attention mechanism for image segmentation task within a syllabic characters. On initial sample tests on input characters our model could recognize correctly up to 79%of the various test patterns of handwritten Korean syllabic charactes. The results of this study indeed show Neocognitron as a powerful model to reconginze deformed handwritten charavters with big size characters set via segmenting its input images as recognizable parts. The same approach may be applied to the recogition of chinese characters, which are much complex both in its structures and its graphemes. But processing time appears to be the bottleneck before it can be implemented. Special hardware such as neural chip appear to be an essestial prerquisite for the practical use of the model. Further work is required before enabling the model to recognize Korean syllabic characters consisting of complex vowels and complex consonants. Correct recognition of the neighboring area between two simple graphemes would become more critical for this task.

Grapheme-to-Phoneme Conversion Regularity Effects among Late Korean-English Bilinguals (후기 한국어-영어 이중언어화자의 자소-음소 변환 규칙에 따른 영어 규칙성 효과)

  • Kim, Dahee;Baik, Yeonji;Ryu, Jaehee;Nam, Kichun
    • Korean Journal of Cognitive Science
    • /
    • v.26 no.3
    • /
    • pp.323-355
    • /
    • 2015
  • This study examined grapheme-to-phoneme regularity effect among late Korean-English bilinguals by using whole word level task (lexical processing) and two meta-phonological tasks(sub-lexical processing): [1] English word naming task(whole word level), [2] rhyme judgement task(rhyme level), and [3] phoneme deletion task(phoneme level). Forty-three late Korean-English bilinguals participated in all three tasks. In these tasks, participants showed better performance in regular word conditions compared to irregular word conditions, demonstrating a clear English regularity effect. Post-hoc correlational analysis revealed strong correlation between word naming task and rhyme judgement task, which is different from the results reported with English monolinguals. The contradicting results might be due to the relevantly low English proficiency level among late Korean-English bilingual speakers. In conclusion, this study suggests that late Korean-English bilinguals make use of L2 grapheme-to-phoneme conversion (GPC) rule when reading L2 English words.

Studies on Tissue Culture of Perilla frutescens var. acuta(I) (자소(紫蘇)의 조직배양에 관한 연구(I))

  • Shin, Soon-Hee
    • Korean Journal of Pharmacognosy
    • /
    • v.16 no.4
    • /
    • pp.210-213
    • /
    • 1985
  • Callus was derived from the leaves of Perilla frutescens var. acuta which is commonly cultivated in Korea. It has been found that the light decreased the growth rate of the callus but rather increased the contents of essential oils. The addition of one ppm of 1-naphthyl acetic acid and 5ppm of kinetin in the medium caused the increased production of essential oils.

  • PDF

Recognition of Hangeul Character Using Grapheme Segmentation and Pixel Distribution (자소분할과 픽셀분포를 이용한 한글문자인식)

  • Cho, Young-Guk;Lee, Dong-Wook
    • Proceedings of the KIEE Conference
    • /
    • 2009.07a
    • /
    • pp.1919_1920
    • /
    • 2009
  • 한글 문자 인식에 관한 연구는 통계적 방법과 구조적 방법, 신경 회로망 등 다양한 방법론이 제시되어 왔다. 그러나 한글은 영문이나 숫자에 비해 방대한 문자수와 복잡한 구조로 인하여 인식에 많은 어려움을 가지고 있다. 따라서 본 논문에서는 한글을 가장 단순한 구조인 자음과 모음으로 분리한 뒤 각 개체의 픽셀 분포를 파악하고, 한글의 구조적 특징을 이용하여 자소의 행과 열에서의 peak값과 픽셀의 분포를 그룹으로 나누어 한글을 인식하는 방법을 제시한다.

  • PDF

Studies on Tissue Culture of Perilla Species (자소(紫蘇)의 조직배양에 관한 연구(II))

  • Shin, Soon-Hee
    • Korean Journal of Pharmacognosy
    • /
    • v.17 no.1
    • /
    • pp.7-11
    • /
    • 1986
  • The young leaf of Perilla species was cultured by two stage culture system using the medium containing mevalonic acid lactone. The growth rate and productivity of essential oil of callus were increased. The essential oil from intact plant and callus was also analysed. Sesquiterpene hydrocarbons and one sesquiterpene alcohol were identified in essential oils of callus.

  • PDF

Hangul Recognition Using The Path Following Algorithm (Path Following 에 의한 자모추출 한글인식 Algorithm)

  • Hwang, To-Chan;Kim, Sung-Shick
    • IE interfaces
    • /
    • v.3 no.2
    • /
    • pp.53-62
    • /
    • 1990
  • 본 연구는 컴퓨터에 의한 인쇄체 한글의 인식방법을 제안하고 있다. 일반적인 인식방법에서는 세선화과정 후의 이미지를 처리하고 있으나, 본 연구는 이 과정을 거치지 않고 원 이미지로부터 직업 패턴점들을 찾아내고, 이들을 이용하여 획을 결정하고 자모를 분리하였다. 문자 판별시에는 한글 의사 결정 나무(Decision-Tree)를 이용하여 자소를 분리하고 판별하였다. 본 연구는 자형에 관계없는 인식 방법을 제안 하였으므로 필기체 한글 인식에 기초를 제공하게 된다.

  • PDF

Genetic Algorithm for English Keyboard of Touch Screen Style (터치 스크린 유형 영문자판을 위한 유전자 알고리즘)

  • 강태원;김미숙;조용만;한수경
    • Proceedings of the Korean Information Science Society Conference
    • /
    • 2001.04b
    • /
    • pp.289-291
    • /
    • 2001
  • 터치스크린 상에 소프트웨어적으로 제공되는 자판은 대부분 크기가 작기 때문에 한 두 손가락만을 사용하여 글자를 입력한다. 그런데 이 자판은 양손을 모두 사용하는 경우를 전제로 하여 자소들을 배열한 것이다. 이 논문에서는 보다 빠르게 영문을 입력할 수 있는 영문자판 배열을 유전자 알고리즘을 이용하여 찾는 것에 대하여 연구한다. 실험결과 유전자 알고리즘을 이용하여 생성한 자판이 기존의 자판에 비하여 평균적으로 약 40% 정도 빠르게 글자를 입력할 수 있다.

  • PDF

Proposal for a New Korean Keyboard Layout (Q2. 5벌식 한글자만 배열 제안)

  • Lee, Yill-Byung
    • Annual Conference on Human and Language Technology
    • /
    • 1991.10a
    • /
    • pp.133-138
    • /
    • 1991
  • 새로운 한글 자판 배열이 제안되었다. 자판에서 키 선택을 위한 기본적인 원칙들과 유추되는 제안들이 간략하게 설명되었으며, 나아가 이들에 토대한 키 배열이 선택되었다. 가장 중요한 원칙은 한글에 대한 인지모형을 따라서 자음중에서 초성자와 종성자의 구분이 같은 키에서 Shift의 동작의 유무로 이루어지는 점이며, 따라서 2벌식과 3벌식의 중간 형태로 생각될 수 있으므로, 본 자판 배열은 2.5벌식으로 명명하였다. 구체적인 키들의 배열은 최근에 조사된 신빙성있는 현대 한글에 대한 자소 빈도수와 손가락에 대한 부하를 고려해서 결정되었다.

  • PDF