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

      오늘 본 자료

      • 오늘 본 자료가 없습니다.
      더보기
      • 무료
      • 기관 내 무료
      • 유료
      • KCI등재

        가상대학에서 교수자와 학습자간 상호작용을 위한 지식기반형 문자-얼굴동영상 변환 시스템

        김형근,박철하,Kim, Hyoung-Geun,Park, Chul-Ha 한국정보처리학회 2008 정보처리학회논문지B Vol.15 No.3

        In this paper, knowledge based text to facial sequence image system for interaction of lecturer and learner in cyber universities is studied. The system is defined by the synthesis of facial sequence image which is synchronized the lip according to the text information based on grammatical characteristic of hangul. For the implementation of the system, the transformation method that the text information is transformed into the phoneme code, the deformation rules of mouse shape which can be changed according to the code of phonemes, and the synthesis method of facial sequence image by using deformation rules of mouse shape are proposed. In the proposed method, all syllables of hangul are represented 10 principal mouse shape and 78 compound mouse shape according to the pronunciation characteristics of the basic consonants and vowels, and the characteristics of the articulation rules, respectively. To synthesize the real time facial sequence image able to realize the PC, the 88 mouth shape stored data base are used without the synthesis of mouse shape in each frame. To verify the validity of the proposed method the various synthesis of facial sequence image transformed from the text information is accomplished, and the system that can be applied the PC is implemented using the proposed method. 본 논문에서는 가상대학에서 교수자와 학습자간 상호작용을 위한 지식기반형 문자-얼굴동영상 변환(TTFSI : Text to Facial Sequence Image) 시스템에 관해 연구하였다. TTFSI 시스템의 구현을 위해, 한글의 문법적 특징을 기반으로 가상강의에 사용된 자막정보에 립싱크된 얼굴 동영상 합성하기 위하여 자막정보를 음소코드로 변환하는 방법, 음소코드별 입모양의 변형규칙 작성법, 입모양 변형규칙에 의한 얼굴 동영상 합성법을 제안한다. 제안된 방법에서는 한글의 구조분석을 통해 기본 자모의 발음을 나타내는 10개의 대표 입모양과 조음결합에서 나타나는 78개의 혼합 입모양으로 모든 음절의 입모양을 표현하였다. 특히 PC환경에서의 실시간 영상을 합성하기 위해서 매 프레임마다 입모양을 합성하지 않고, DB에서 88개의 해당 입모양을 불러오는 방법을 사용하였다. 제안된 방법의 유용성을 확인하기 위하여 텍스트 정보에 따른 다양한 얼굴 동영상을 합성하였으며, PC환경에서 구현 가능한 TTFSI 시스템을 구축하였다.

      • 대한협회(大韓協會)의 정당론(政黨論)과 정치활동(政治活動)

        柳永烈 ( Yoo Young Nyol ),朴哲河 ( Park Chul Ha ) 숭실대학교 인문과학연구소 1995 인문학연구 Vol.25 No.-

        Rejecting armed registance of Ubyong(義兵), admitting Japan’s protective government for korea on 'the theory of Oriental peace’ and the recognization of the age in the perspective of the social evolution, Dae-Han Hyop Hoe(大韓協會) had insisted on the movement for restoration of state power, knowing Japan as a model of korean civilization, or the leader of oriental civilization. On the base of the facts like this, Dae-Han Hyop Hoe asserted the conctruction of nation of people and establishment of government of people based on the constitutional system. And it thought the morden political party as a central body of the government and state in those days. It was just regarded Dae-Han Hyop Hoe as such political party at that time. And Dae-Han Hyop Hoe had pursuited the seperation of political party, especially two-parties system; another political party was Il-jin-hoe(一進會). Dae-Han Hyop Hoe had regarded new intellectual class, politian of ‘Kaehwapa (開化派)’,landholder and neo-bourgeoigies as the social bases of itself. Dae-Han Hyop Hoe had made an effort to take the reigns of government in place of the cabinet of Lee wan yong(李完容) that was corrupt and inefficient and to lead Korea to the morden civilized state with party politics.

      • 가상대학을 위한 수강자 인증 시스템의 설계

        박철하,전노선 대불대학교 2002 大佛大學校大學院 硏究論文集 Vol.- No.1

        The rapid proliferation of cyber universities has demanded that a new method is required to verify a user as the old verification system based on the user's password has been proven ineffective. The focus of this paper; hence, is to present a way to verify a user based on the human body, which has been the hot issue in the computer industry. There are two face recognition modules for a cyber university. The first student registration module conducts the database based on the unique features of the users. The second student verification module calculations the similarity between the original features recorded at registration and the facial features captured on the spot through the camera. The method suggested in the paper has an average histogram distribution chart based on the calculation of the eye, nose and mouth which are the most conspicuous facial features. Then, it derives the unique facial features based on the difference of this figure and the main attributes of the histogram of the user. And, it conducts the verification work based on the calculation of the similarity of the unique features. The paper also presents a way to reduce an error with a combination of the password verification system and the face recognition system. This method has been proven effective in verifying the students who register on-line as the resolution is high.

      • 얼굴동영상의 표정 및 운동정보의 추출

        박철하,김형호 대불대학교 2001 論文集 Vol.7 No.1

        We have developed a computer vision system, including both facial feature extraction, that automatically discriminates among subtly different facial expressions. Expression classification is based on Facial Action Coding System(FACS) action units (AUs), and discrimination is performed using direct estimation. Upon extraction of the facial information, non-rigid facial expression is separated from the rigid head motion component, and the face images are automatically aligned and normalized using an affine transformation. A number of examples are shown.

      • 개선된 유전자 알고리즘에 의한 얼굴영역 검출

        박철하,김하석 대불대학교 1999 論文集 Vol.5 No.1

        Face detection in a complex background is an unsolved problem which has fundamental importance to face recognition, model based video coding, content based image retrieval, and human computer interaction. In this paper, we proposed a new approach that improves detection accuracy and convergent speed for ellipse shapes by the combination of genetic algorithm and subpixel accuracy(SA&GA). In the preprocessing steps the edge image is extracted and the edge image is compressed for the reduction of processing time. The proposed method is used changeable face template for the effective detection of face region and is accomplished the research process for the detection of several face. Varied experiments show the effectiveness of proposed method in the face detection from images with many people and complex background.

      • 표정 및 운동 정보를 이용한 얼굴영상의 합성

        박철하 대불대학교 2001 論文集 Vol.7 No.1

        New image coding system for facial images called Knowledge-based image coding is described, in which input image is analized and output image is synthesized using analysis results. Analysis and synthesis method of facial expressions are presented. Synthesis rules are determined on the basis of facial muscles and are also used in analysis process to produce a faithful reconstruction of the original image. A number of examples are shown.

      • SCOPUSKCI등재

        소백산지역의 수액채취수종의 분포 및 수행채취량

        조남석,김홍은,권기철,박철하 한국목재공학회 1998 목재공학 Vol.26 No.3

        Lately public interest in tree saps of maple and birch trees has been increased for sap drink as a natural medical beverage. To ensure tree sap drink for commercial production, species which are available in resources, their ecological regeneration characteristics in the natural forest stand, and tree sap resources should be investigated. Species for the collecting tree saps and their distribution were surveyed in the areas of Mt.Sobaek, Tanyang-gun, Chungcheongbuk-do. Mt.Sobaek area was selected to the proper place to survey as the feasible area for tapping tree saps for the natural beverage. Feasible tree species of this area are Betula costata, Betula schmidtii, Corpus controversa, Acer mono, and Acer pseudosieboldianum based on the estimated tree sap amounts. Average and maximum species diversities of surveyed area were 4.2 and 5.39, respectively. Its evenness 0.78 referred that there are actively progressing ecological regeneration among diverse tree species. Tree saps are mainly harvested at the areas of upper and lower Wonmanteo. In terms of species, the most high sap amounts were from birch sap, next Corpus controversa, the 3rd Acer mono. Many measures were suggested ecologically and technically, for commercial or practical production of tree sap drinks, though Mt.Sobaek area was evaluated as improper place because of geographical and transportational limitation.

      연관 검색어 추천

      이 검색어로 많이 본 자료

      활용도 높은 자료

      해외이동버튼