RISS 학술연구정보서비스

검색
다국어 입력

http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.

변환된 중국어를 복사하여 사용하시면 됩니다.

예시)
  • 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
  • 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
닫기
    인기검색어 순위 펼치기

    RISS 인기검색어

      검색결과 좁혀 보기

      선택해제
      • 좁혀본 항목 보기순서

        • 원문유무
        • 원문제공처
          펼치기
        • 등재정보
        • 학술지명
          펼치기
        • 주제분류
        • 발행연도
          펼치기
        • 작성언어
        • 저자
          펼치기

      오늘 본 자료

      • 오늘 본 자료가 없습니다.
      더보기
      • 무료
      • 기관 내 무료
      • 유료
      • 세선화를 위한 4 근접 연결값에 의한 알고리즘

        원남식,남인길 대구대학교 산업기술연구소 1994 産業技術硏究 Vol.13 No.-

        Feature extraction generated by thinning algorithms, are often used to represent objects in a binary digital image for shape analysis and classification. Many thinning algorithms have been proposed to date. They differ from each other because of the many definitions of digital skeletons and the failure to utilize available analytical tools in their design and performance evaluations. In this paper, New algorithm for the thinning is proposed. The key principle of the algorithm is to process object pixel by the 4 Neighbors Connectivity Value.

      • 8-이웃 연결값에 의한 병렬세선화 알고리즘

        원남식,손윤구,Won, Nam-Sik,Son, Yoon-Koo 한국정보처리학회 1995 정보처리논문지 Vol.2 No.5

        세선화 알고리즘은 문자 인식에서 인식율을 높이기 위한 매우 중요한 과정이 된다. 본 연구는 다양한 문자 인식에 적용 가능한 8-이웃 연결값을 이용한 병렬세선화 알고 리즘을 제안한다. 제안된 알고리즘의 특징은 병렬성 구현이 용이하며, 세선화된 결과 는 완전 8연결이 되고, 수치 정보로 표현된다. 특히 곡선 선분의 골격이 정확하게 표 현되므로 영문, 일어 등 곡선이 많은 문자에 더욱 적합함을 보인다. 성능 평가는 기준 골격선과 유사도 측정 방법에 의해 수행되었다. A thinning algorithm is a very important procedure in order to increase recognition rate in the character recognition. This paper is the study of a parallel thinning algorithm available for the recognition of various characters, and it proposes the parallel thinning algorithm using the 8-neighbors connectivity value. Characteristics of the proposed algorithm are easiness of implementation of parallelism, the result of thinning is perfectly-8 connectivity and represented by numeric information. The proposed algorithm is very suitable for characters having many curve segments such as English, Japanese etc. Performance evaluation was performed by the measure of similarity to reference skeleton.

      • 불 전파 방식에 의한 특징 추출 알고리즘

        원남식,남인길 대구대학교 산업기술연구소 1994 産業技術硏究 Vol.13 No.-

        During these days, many algorithms for data compression by thinning have been devised and applied to great variety of patterns for different purposes. This wide range of applications shows the usefulness of reducing patterns to thin-line representations, which can be attributed to the need to process a reduced amount of data as well as to the fact that shape analysis can be more easily made on line-like patterns. In this paper, New algorithm for the Feature Extraction by Fire Front's Propagation is proposed. The key principle of this algorithm for the thinning pre-process is to realize parallelism on the Fire Front's Propagation.

      • 한글 인식을 위한 병렬세선화 알고리즘

        원남식 경일대학교 산업기술연구소 1995 産業技術硏究所 論文集 Vol.5 No.-

        세선화 알고리즘은 문자 인식에서 인식율을 높이기 위한 매우 중요한 과정이 된다. 본 연구는 한글 인식에 적용 가능한 병렬세선화 알고리즘에 관한 연구로서, 각 화소들 간의 연결성을 나타내는 연결값(Connectivity Value)을 이용하여 세선화 함으로써 인식 문자의 골격(Skeleton)을 보다 원형에 가까운 형태로 얻을 수 있는 세선화 알고리즘을 제안한다. 제안된 알고지즘의 특징은 병렬성 구현이 용이하며, 세선화된 결과는 완전히 1화소 두께가 되고(완전 8연결), 수치 정보로 표현된다. 특히 곡선 선분의 골격이 정확하게 표현되므로 영문, 일어 등 곡선이 많은 문자에도 적합함을 보인다. 제안된 알고리즘의 성능 평가는 기준 골격선과의 유사도 측정 방법에 의해 수행되었다. A thinning algorithm is a very important procedure in order to increase recognition rate in the character recognition. This paper is the study of a parallel thinning algorithm available for the Korean Chaeacter recognition, and it proposes the thinning algorithm which can extract the skeleton of the recognized character almost similar to the original pattern by using the connectivity value representing connectivity of each pixel. Characteristics of the proposed algorithm are easiness of implementation of parallelism, the result of thinning is one pixel width(perfectly-8 connectivity) and represented by numeric information. Especially since the proposed algorithm represents the skeleton of curve segment more exactly. we shows it very suitable for characters having many curve segments such as English. Japanese etc. Performance evaluation of the proposed algorithm was performed by the measure of similarity to reference skeleton.

      • WPTA 세선화 알고리즘에서 침식현상 고찰

        원남식 경일대학교 산업기술연구소 1999 産業技術硏究所 論文集 Vol.6 No.-

        The thinning algorithms have a very important role in order to increase the recognition rate in character recognition. This paper considered about the erosion phenomenon which appears in the thinning algorithms WPTA4N and WPTA8N. The experimental results show that WPTA thinning algorithms can be applied in the application of both a straight line segment and a curved line segment.

      • 임계 획 밀도를 이용한 한영 구분 알고리즘

        元南植 慶一大學校 1996 論文集 Vol.13 No.2

        It is an important factor to distinguish the kind of the character for increasing recognition rate before the character recognition in the multi-font and multi-character document recognition system. All the letters have a various unique characteristic in the each composition. In this paper, we are used the stroke density as the mothod to distinguish the letter, and it has been adopted only Korean and English character. Input data is processed by the normalization to adopt multi-font document. Proposed method has been proved by the results of experiment the fact that the distinction probability for the Korean and English is more than 90% and almost no overhead for the execution time.

      • 컴퓨터 바둑에서 정적인 돌의 세기판단과 형세판단의 구현

        徐診澤,朴鉉秀,元南植 慶一大學校 1998 論文集 Vol.15 No.1

        In computer go game, the evaluating of stone power and the territory evaluating are the most important basis. In this paper, we evaluate statically the stone power on the basis of the eye information. And we decide the owner of eyes by using the evaluated stone power and evaluate the territory of a match with the decided information.

      • Token Passsing에 의한 세선화 Algorithem에 관한 연구 Ⅱ

        元南植 慶一大學校 1987 論文集 Vol.3 No.1

        A thinning algorithm by token passing represented in this Paper has more improved contents than a study I of a thinning algorithm. As using a thinning algorithm by token passing, processing speed can be more increased any other thinning algorithm. Also it's very suitable algorithm for the recognition of the Korean character that is composed almost stroke feature because this algorithm has very excellent lineation characteristic.

      • Node 분석에 의한 한글 인식 Algorithm에 관한 연구(Ⅱ)

        元南植 慶一大學校 1985 論文集 Vol.1 No.1

        In this paper, a new algorithm for recognizing Korean Character is proposed as follows. ·Syntactic method for recognizing Korean Character ·Node generation Algorithm ·Diagonal Searching method fro first Consonent searching ·Error node detection and regeneration method ·Pattern matching technique

      • Multi-Drop Communication 방식에 관한 고찰

        元南植 慶北工業專門大學 1981 論文集 Vol.18 No.-

        Now, the requirements of the data communication has been increased more and more. To design communication system, it is more important point that we must consider to select adequate communication methode. Generaly, we can consider two methode for data communication that is, point to point and multi-drop methode. In this paper, as for comparison of point to point and multi-drop methode, that's advantage and disadvantage, communication protocal, data format, reliability, and error recover, etc, we can select the best methode to build up communication system. This paper is based of the seoul Traffic control System.

      연관 검색어 추천

      이 검색어로 많이 본 자료

      활용도 높은 자료

      해외이동버튼