• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.790-792
• /
• 2004

본 논문에서는 컬러 영상에서 얼굴 구성요소 융합을 이용하여 얼굴 영역을 검출하는 방법을 제시한다. 먼저 광범위한 조명 환경과 인종을 포괄하는 피부색의 범위를 이용해 피부 영역을 검출하고. 영역 그룹화로 후보 얼굴 영역을 찾는다. 색 정보를 이용해 얼굴 구성요소(눈, 입)를 검출한 후, 검출된 구성요소와 구성요소 간의 관계를 융합하여 주어진 영상에서 얼굴 영역을 검출한다. 본 논문이 제안하는 구성요소 융합 방법은 구성요소 간의 관계에 대한 불확실성을 고려하고 있어, 구성요소간의 최적의 조합으로 얼굴의 크기와 포즈, 조명의 변화가 어느 정도 허용된 얼굴 검출이 가능하다.

• Journal of Broadcast Engineering
• /
• v.2 no.2
• /
• pp.156-169
• /
• 1997

This paper proposes an image segmentation technique using watershed algorithm followed by region merging method. A gradient image is obtained by applying multiscale gradient algorithm to the image simplified by morphological filters. Since the watershed algorithm produces the oversegmented image. it is necessary to merge small segmented regions as wel]' as region having similar characteristics. For region merging. we utilize the merging criteria based on both the mean value of the pixels of each region and the edge intensities between regions obtained by the contour following process. Experimental results show that the proposed method produces meaningful image segmentation results.

• Journal of Wellness
• /
• v.14 no.2
• /
• pp.207-223
• /
• 2019

The purpose This study aimed at proposing class module elements for creativity and convergence and class models for creativity and convergence by integrating content elements by physical activity field(health, challenge, competition, ) for physical education and STEAM. For this, literature review, focus group interview(FGI) and discussions with experts were conducted, and the following study results have been drawn up: First, concerning the class module elements for creativity and convergence, total 11 class module elements in the health field were suggested including detecting risks by posture analysis and analyzing and designing amount of physical activity. Second, total 7 module elements in the challenge field were deduced such as anticipation of obstacles to target achievement and modeling of effective exercise. There were 17 convergence elements in the competition field including game record analysis and creation of game data storage application. Third, total 9 creativity and convergence module elements in the field include modeling of technology improvement for motion and symbolization for motion records. In addition, class modules related to convergence with engineering in the health field, convergence with technology in the challenge field, convergence with art in the competition field and convergence with art and mathematical symbols were proposed.

• Journal of the Korea Convergence Society
• /
• v.9 no.7
• /
• pp.205-211
• /
• 2018

The purpose of this study is to propose a strategy to educate the core contents of various major fields in practical and convergent ways in universities in order to prepare for the 4th industrial revolution era. First, convergence field is established in the university curriculum in addition to the existing major and the liberal arts field. Second, convergence courses are created in connection with job ability, which are major curriculum but only for students in other departments. Third, convergence courses are organized in the form of module curriculum, which is a small-sized and independent curriculum consisting of 4 courses. D University, one of the local private universities in Korea, has provided such convergence module education since 2016, and satisfactory results have been obtained in the course enrollment rate and the course evaluation, etc. By combining these convergence modules in various ways, it is possible to easily create customized majors required and designed by local companies at low cost.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.11a
• /
• pp.707-710
• /
• 2002

본 논문은 오디오와 비디오 정보의 융합을 통한 멀티 모달 음성 인식 시스템을 제안한다. 음성 특징 정보와 영상 정보 특징의 융합을 통하여 잡음이 많은 환경에서 효율적으로 사람의 음성을 인식하는 시스템을 제안한다. 음성 특징 정보는 멜 필터 캡스트럼 계수(Mel Frequency Cepstrum Coefficients: MFCC)를 사용하며, 영상 특징 정보는 주성분 분석을 통해 얻어진 특징 벡터를 사용한다. 또한, 영상 정보 자체의 인식률 향상을 위해 피부 색깔 모델과 얼굴의 형태 정보를 이용하여 얼굴 영역을 찾은 후 강력한 입술 영역 추출 방법을 통해 입술 영역을 검출한다. 음성-영상 융합은 변형된 시간 지연 신경 회로망을 사용하여 초기 융합을 통해 이루어진다. 실험을 통해 음성과 영상의 정보 융합이 음성 정보만을 사용한 것 보다 대략 5%-20%의 성능 향상을 보여주고 있다.

• Journal of the Korea Convergence Society
• /
• v.10 no.3
• /
• pp.81-91
• /
• 2019

The purpose of this study was to specifically explore the dilemma posed by lifelong education for the disabled in Korea at the point of convergence. Research to achieve the research objectives consisted of areas that should be considered in developing and implementing support systems for lifelong education for the disabled. The outcome of the area consisted of five things: convergence dilemmas in fields, convergence dilemmas in institutions, convergence dilemmas in eligibility, convergence dilemmas in disability areas, and convergence dilemmas in national administration. And the five areas were considered by interlinked views and contexts. Based on the results of the study, the university's special education department (including vocational special education) was concluded and considered with emphasis on strengthening the role functions of the university's special education system for the support system for lifelong education for the disabled, including the preconditions for establishing the academic identity of lifelong education for the disabled. Through this ideal, it is worth suggesting that the academic identity of lifelong education for the disabled should be established as appropriate based on convergence between the categories of lifelong education and special education based on the practical nature and context of education for the Korean.

• Proceedings of the IEEK Conference
• /
• 2001.09a
• /
• pp.443-446
• /
• 2001

본 논문에서는 센서 융합과 배경 추정 기법을 이용하여 연속된 영상에서 물체 영역을 검출하는 기법을 제안하였다. IR/CCD각각의 카메라로부터 얻은 입력 영상을 정렬하고 융합하는 과정을 거친 후, 각 화소 단위의 배경 모델을 추정하고 시간이 지남에 따라 이를 갱신함으로써 물체 영역을 효과적으로 검출하는 기법을 제시하고 있다. 실험은 차량을 대상으로 하였고, 카메라가 움직이는 상황과 비교적 복잡한 환경에서도 좋은 결과를 얻을 수 있었다.

• Journal of Korean Philosophical Society
• /
• v.116
• /
• pp.111-132
• /
• 2010

While this paper will be of interest to Convergence of Knowledge and Border Thinking, one of my main concerns has been to open the world of mind. Because the convergence of knowledge and border thinking are closely related to the problems of mind. It should be clear from this procedure that the scope of this study is limited. It is not intended to be a definitive account of all problems of mind, bur rather a clear and thorough account of that segment of mind that pertains to an analysis of convergence of knowledge and border thinking. This claim, with their supporting arguments, will be discussed as follow; 1. What our knowledge has been for? 2. Knowledge and convergence of knowledge 3. How is the convergence of knowledge made up? 1) meeting at border 2) mind as a border 3) converging at mind.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.08a
• /
• pp.233-236
• /
• 2000

최근 수많은 인쇄된 문서들이 HTML과 같은 디지털 문서로 바뀌고 있으며 이를 자동으로 변환해 주는 문자인식 기술에 대한 관심이 증가하고 있다. 본 논문에서는 그림과 글자가 공존하는 문서에서 자동으로 문자영역을 추출해서 문자를 인식하는 방법을 제안한다. 우선 입력문서는 유사한 칼라로 이루어진 영역들로 나누어진 뒤 휴리스틱 룰에 의해 문자후보 영역과 비 문자 영역으로 나누어진다. 그 다음 이들 문자후보영역들은 문자인식기를 이용하여 문자 혹은 문자의 일부분으로 인식된다. 제안된 방법으로 여러 문서들에 대하여 실험한 결과를 보이며 그 성능을 평가한다.

• Journal of the Korean earth science society
• /
• v.41 no.6
• /
• pp.670-683
• /
• 2020

The purpose of this study was to develop a test tool for convergence problem solving skill. To this end, constructs of convergence problem solving skill were defined in three domains: convergence attributes, convergence thinking, and convergence literacy domains. Thirty-seven pilot items were developed on the basis of the sub-categories for each domain that was defined through intensive literature review; problem solving & convergent thinking and creative thinking for convergence thinking domain, individual and social propensity for the convergence attributes domain, and convergence literacy as convergence literacy domain. Through an exploratory factor analysis, 30 items in the constructs of the test tool were confirmed. A confirmatory factor analysis result showed that the five construct models well captured the covariance between all the items well. Finally a statistical result shows that the reliability of the items and constructs were well established (Cronbach's α value= .963). Thus, the test tool for convergence problem solving skill developed in this study was statistically reliable.