• 한국통신학회논문지
• /
• 제16권3호
• /
• pp.232-247
• /
• 1991

본 논문에서는 한자인식을 위한 전단계로서 인쇄체 한자를 대상으로 한자의 특성과 구조적 정보를 이용한 새로운 분류 알고리즘을 제안하였다. 한자는 자종이 많고 구조가 복잡하여 인식은 물론이고 분류하는 데에도 많은 어려움이 따른다. 이러한 문제점을 해결하기 위해, 본 연구에서는 한자패턴을 형식분류한 후 분류된 패턴에서 공통으로 존재하는 부분패턴을 추출하는 실험을 행하였다. 먼저 입력한 문자 패턴에 대해 전처리를 행한 후, 방향 세그먼트를 추출하여 4방향화면상에서 레이블링을 하고, 문자패턴의 부분패턴 존재 영역에 기초한 구조적 정보를 이용하여 12가지 형식으로 분류한 다음 그 부분패턴을 추출하였다. 중, 고교 교육용한자 1800자에 대해서 실험을 행한 결과 93.07%의 형식분류율을 얻었고, KS C5601표준 삼보 LBP 한자 폰트 4,888자에 대해서는 90.12%의 형식분류율을 얻었으며, 분류된 데이타로 부터 부분패턴을 추출하여 인식에의 적용가능성을 보였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 하계종합학술대회논문집
• /
• pp.913-916
• /
• 1998

In this paper, to provide the robustness of character recognition, we propose a recognition method using the dilated boundary curve feature which has the invariance characteristics for the shift, scale, and rotation changes of character pattern. And its some characteristics and effectieness are evaluated through the experiments for both the english alphabets and the numeral digits. The feature vector is represented by the fourier descriptor for a boundary curve of the dilated character pattern which is generated by the circular mask dilation method, and is used for a nearest neighbort classifier(NNC) or a nearest neighbor mean classifier(NNMC). These the processing time and the recognition rate, and take also the robustness of recognition for both some internal noise and partial corruption of an image pattern.

• 디자인학연구
• /
• 제14권3호
• /
• pp.135-144
• /
• 2001

우리의 전통문화 유산에서 새롭게 디자인 모티브를 발굴하고 시각적으로 상징화하는 연구는 과거의 것과 현대의 것을 융합시키므로써 형태와 미학의 조화 속에 새로운 한국적 디자인을 창조하는 일이며, 미래의 가치를 찾는 작업이고, 새로운 전통 문화를 만드는 일이라고 할 수 있다. 본 연구는 우리 전통상징문양과 12지신 캐릭터에서 디자인 모티브를 발굴하고, 전통과 현대의 이미지를 접목하여 참신하고 세련된 감각과 흥미를 유발할 수 있는 캐릭터에 대한 표현연구를 통해 독특한 한국적 캐릭터를 개발하여 이를 현대 디자인에 다양하고 실질적인 활용방안을 제시하고자 했다. 이는 전통상징문양의 시각적인 효과와 캐릭터 개발만이 아닌, 우리만의 고유한 문화요소로 정체성과 독창성을 표현하여 외래문화 속에서 우리의 한국적 아이덴티티(Identity)를 찾고 한국적 디자인으로 미래의 세계시장에서 새로운 국가경쟁력을 갖기 위함이 그 목적이다.

• 한국의류산업학회지
• /
• 제19권5호
• /
• pp.635-645
• /
• 2017

The industry of character toys is increasing and new characters are constantly being developed. However, the development of 2D cover patterns for toys is time-consuming due to frequent pattern modifications made through trial and error. Studies are now underway to obtain 2D clothing patterns from 3D body data, however, little research has been done on 2D pattern of character toys. This study suggests efficient guidelines to develop 2D cover patterns with a reasonable accuracy and processing time. Two 3D models of a dog and rabbit were used to develop 2D cover patterns. Independent variables of this study are set as 3 levels of triangle area (small, medium, and large) that influence the efficacy of 3D and 2D pattern development. The determination of the appropriate triangular area was based on the area and shape change of the 2D pattern. A medium or large triangle area was shown to be suitable for a character dog with a smooth curved surface. However, the appropriate triangle area was small if the characteristics of the curved surface are complicated as in the case of rabbit. The head of a dog (a double-curved surface) and the curved forepaw of a rabbit (a triangular area) should be small when the characteristics of the curved surface (such as the hind leg of a rabbit having a large convex surface and a small surface area) are complicated. Grouping by 3D surface characteristics could be a suitable guideline for the triangle area selection.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1987년도 전기.전자공학 학술대회 논문집(II)
• /
• pp.936-940
• /
• 1987

This paper describes the recognition boundary of Hangeul character to interpret variance factor in accordance with various combination. When the recognition algorithm based on comparing the MSE value with the one of the standard pattern in $16{\times}16$ images is performed, we come to a conclusion that we have towe must make a decision MSE value above 34 in order to achive theve recognition rate larger than 90%. Also we understand that varing component coordinates method based on statistical process of each character pattern is preferred.

• 복식
• /
• 제38권
• /
• pp.83-100
• /
• 1998

The purpose of this study is to figure out how stage costume of Peking Opera communicates what the character wants to inform to spectator. The stage costume means the clothing, shoes, headdress, accessory that the cast is worn for communicating personality of character. Stage costume not only reveals the character of new spirit who the director and the work is like to create, but also makes the style of play harmonizing with the atmosphere of the work. So, the stage costume in the play is a sort of symbol system that forms the depth of play. The stage costume of Peking Opera was formed on the basis of the Chinese traditional stage costume in the Qing period, however the style of stage costume was beautified the costume of Ming period and here contained the factors of successive costumes. But the stage costume of Peking Opera don't have the same rank system with real history costume and don't have demarcation according to period and history. Only it is that transformed and created the real history costume with Chinese fine view and made how they wear Chinese fine view and made how they wear the costume according to position, age, personality of character in the play. In the stage costume of Peking Opera, the color is cultural language that director can communicate to spectators and can inform spectator of sex, age, personality, position of the character. The color of the stage costume of Peking Opera reflects the principles of Yin and Yang and the five elements of the Chinese cosmogony. The pattern of decoration also makes the personality and characteristic of the character. The dragon pattern symbols the authority and majesty, so only the character of high position can use it. The pattern of tiger and leopard symbols bravery, so the military officer can use it. Civil officer decorates with the pattern of Japanese apricot, orchid, chrysanthmum, bamboo that symbols integrity and honor. The stage costume of Peking Opera communicates the identity of character with the special form of costume. Kanjien is a costume of the young priestess, Houyi is the Sunwukong'costume. Chayi is a costume of boatman. Lingzi, Sweixiu, Kaoqi is the props for the foramtive effect of stage costume, also they play an important part in expressing the emotion situation. In the result of study, we could know that the form, color, pattern of the stage costume and props of Peking Opera play important parts in communicating informations that let spectator can understand the play. So, the stage costume of Peking Opera is an‘picturizing costume’that the form, color, pattern of the stage costume is a sort of symbol system. It makes spectator feels actually the viewing Peking Opera.

• 한국통신학회논문지
• /
• 제16권2호
• /
• pp.180-195
• /
• 1991

본 논문은 한글 문자 패턴을 인식하기 위하여 쉐이프 패턴을 대상으로 한글의 구조적 정보를 이용한 새로운인식 방법에 대해서 연구하였다. 먼저, 입력된 데이타에 대하여 문자의 위치를 알기 위하여 문자 영역의 블럭화를 행하였고, 둘째로 한글의 무게 중심을 이용한 종모음의 유무를 결정하고, 횡모음과 짧은 기둥의 위치와 길이 조사 및 종정의 존재 여부를 조사하여 한글이 가지는 6가지의 기본 구조로 형식 분류를 하였으며, 마지막으로 분류된 형식에 따라 각각의 자소에 대해 유크리드 기리(Uclid distance)에 의한 탬플레이트 매칭(template matching)을 실행하여 인식을 행하였다. 본 연구는 실험을 통하여 총 2350자의 문자에 대하여 98.3%의 형식 분류율과 95.2%의 한글 인식율을 얻었다.

• 한국산학기술학회논문지
• /
• 제7권6호
• /
• pp.1167-1174
• /
• 2006

자연이미지로부터 텍스트 영역 추출은 자동차 번호판 인식 등과 같은 많은 응용프로그램에서 유용하다. 따라서 본 논문은 문자-에지 맵의 패턴 히스토그램을 이용한 텍스트 영역을 추출하는 방법을 제안한다. 16종류의 에지맵을 생성하고, 이것을 조합하여 문자 특징을 갖는 8종류 문자-에지 맵 특징을 추출한다. 문자-에지 맵의 특징을 이용하여 텍스트 후보 영역을 추출하고, 텍스트 후보 영역에 대한 검증은 문자-에지 맵의 패턴 히스토그램 및 텍스트 영역의 구조적 특징을 이용하였다. 실험결과 제안한 방법은 복잡한 배경, 다양한 글꼴, 다양한 텍스트 컬러로 구성된 자연이미지로부터 텍스트 영역을 효과적으로 추출하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.129-131
• /
• 2006

The performances of neural network systems mainly depend on the kind and the number of input patterns for its training. Hence, the kind of input patterns as well as its number is very important for the character recognition system using back-propagation network. The more input patters are used, the better the system recognizes various characters. However, training is not always successful as the number of input patters increases. Moreover, there exists a limit to consider many input patterns of the recognition system for cursive script characters. In this paper we present a new character recognition system using the back-propagation neural networks. By using an additional neural network, an input pattern generation method is provided for increasing the recognition ratio and a successful training. We firstly introduce the structure of the proposed system. Then, the character recognition system is investigated through some experiments.

• Journal of information and communication convergence engineering
• /
• 제1권1호
• /
• pp.53-57
• /
• 2003

Chaos theory is a study researching the irregular, unpredictable behavior of deterministic and non-linear dynamical system. The interpretation using Chaos makes us evaluate characteristic existing in status space of system by tine series, so that the extraction of Chaos characteristic understanding and those characteristics enables us to do high precision interpretation. Therefore, This paper propose the new method which is adopted in extracting character features and recognizing characters using the Chaos Theory. Firstly, it gets features of mesh feature, projection feature and cross distance feature from input character images. And their feature is converted into time series data. Then using the modified Henon system suggested in this paper, it gets last features of character image after calculating Box-counting dimension, Natural Measure, information bit and information dimension which are meant fractal dimension. Finally, character recognition is performed by statistically finding out the each information bit showing the minimum difference against the normalized pattern database. An experimental result shows 99% character classification rates for 2,350 Korean characters (Hangul) using proposed method in this paper.