• 한국콘텐츠학회논문지
• /
• 제9권12호
• /
• pp.86-93
• /
• 2009

본 논문에서는 실영상(컴퓨터로 생성한 영상 또는 실제 촬영한 영상)을 직접 손으로 스케치한 것과 같이 터치감이 나는 영상으로 변환하는 기법을 제안한다. 즉 실영상을 공간 필터 등의 영상 처리 기법을 통하여 사람이 손으로 직접 그린 것과 같이 농담의 차이를 느낄 수 있는 인간 친화적인 영상으로 변환한다. 먼저 소벨 마스크를 사용하여 윤곽선을 검출하고, 검출된 부분 중 불필요한 선들을 제거하여 첫 번째 영상을 구한다. 그리고 이를 반전시켜, 유사한 방법으로 두 번째 영상을 구하여 두 영상 간의 차를 구하고 여기에 해칭 효과를 적용하여 스케치 효과를 표현한다. 이와 같이 일련의 처리로 기존의 연필 해칭 효과 방식과 스케치 효과 방식에 비해 선에 농담 차이를 주어 수용성 펜을 이용하여 그린 느낌을 주었다. 또한, 입력 영상의 음영 부분에 서로 다른 해칭 효과를 적용하여 스케치의 느낌을 보다 잘 표현할 수 있었다.

• 한국생활과학회지
• /
• 제17권3호
• /
• pp.501-509
• /
• 2008

This research intends to help local small fashion industry to outgrow its limitation, preserving and developing environment-friendly dyeing tradition in Jeju renowned for persimmon juice dyeing. The study, then, aims to develop eco-friendly golf-wear designs, with maximizing advantages of natural dyeing (with persimmon juice, indigo plant, gallnut, cochineal, turmeric, and loess) such as rot-proofness, bacteria-proofness, stench-proofness and block of ultraviolet rays. The results are as follows: first, natural fabrics such as muslin(cotton 100%), linen(linen 100%) and spandex(mixed cotton 98%, polyurethane 2%) were developed into eco-friendly ones colored with various natural dye sources. Second, four kinds of golf-wear design were developed to stand out golf wear's natural image, focused on classic, neo-minimal style. The characteristic details and design elements of sportswear were added to basic golf wear design. Therefore, it is hopeful that those designs of naturally dyed golf wear for women could be utilized for other various purposes in the future.

• 한국의류학회지
• /
• 제23권2호
• /
• pp.296-306
• /
• 1999

This study reflects the aim of analyzing the fashion design connection with ecology. Ecology has been linked to human life through its changing relations with environment. In order to recover eco-system ecology-nature oriented methodology and technology oriented approach will suffice. On the modern design field Green design Recycling and Green marketing resulted in increasing rates of environment-friendly production and an effort to deliver environment-friendly corporate image. Based on above research ecological image on fashion design during the year 1990 to 1995 represents the following conclusion. In the fashion design field natural image primitive image nature -harmonious image material-recyling image culture-recycling image are proposed. In the technology field clean image and high-tech image are proposed. In the marketing field happy image harmonious image serious image and realistic image are proposed.

• 패션비즈니스
• /
• 제17권4호
• /
• pp.75-89
• /
• 2013

In 2000s, the interest of ROHAS has been increased and the environmental problem has begun to be discussed as the environmental and global value, not the individual perspective. And the standard of value for eco-friendly awareness has been expanded to the economic category. The trend of eco-friendly fabric can be divided into 3 periods depending on the property. The period for natural fabric with visual effects(2002~2004) can be summarized as the creation of natural shape using the natural image, the interaction of cotton and the technology from the visual perspective. In the period of functional conjunction with eco-friendliness and technology(2005~2008), the eco-friendly awareness through the conjunction of technology and nature and the re-cycling, and the responsibility to the environment had been increased. In the period of sustainable development for nature and environment(2009~2011), it showed the conjunction with nature and the integration with technology and eco-friendly issues. Therefore, the characteristic of eco-friendly trend in fabric since 2000 can be said; firstly, the high-quality fabric has been developed with technological development for the functional progress. Secondly, the ethical creativity has been displayed with the development and utilization of eco-friendly recycling materials. Thirdly, the materials reflected with eco-friendly issues have emerged.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -2
• /
• pp.1161-1164
• /
• 2002

We propose a simple method that can recognize human emotion from monocular dance image sequences. The method only exploits the information within image sequences and does not require cumbersome attachments like sensors. This makes the method a simple, human-friendly one. Moreover, the method is more robust and efficient by taking into account the statistical property of image sequences based on PCA (Principal Component Analysis). The correct recognition rate in real-time is about 75% in a variety of experiments.

• 제어로봇시스템학회논문지
• /
• 제11권5호
• /
• pp.398-405
• /
• 2005

The intelligent robots that will be needed in the near future are human-friendly robots that are able to coexist with humans and support humans effectively. To realize this, robots need to recognize their position and posture in known environment as well as unknown environment. Moreover, it is necessary for their localization to occur naturally. It is desirable for a robot to estimate of his position by solving uncertainty for mobile robot navigation, as one of the best important problems. In this paper, we describe a method for the localization of a mobile robot using image information of a moving object. This method combines the observed position from dead-reckoning sensors and the estimated position from the images captured by a fixed camera to localize a mobile robot. Using a priori known path of a moving object in the world coordinates and a perspective camera model, we derive the geometric constraint equations which represent the relation between image frame coordinates for a moving object and the estimated robot's position. Also, the control method is proposed to estimate position and direction between the walking human and the mobile robot, and the Kalman filter scheme is used for the estimation of the mobile robot localization. And its performance is verified by the computer simulation and the experiment.

• 정보교육학회논문지
• /
• 제21권5호
• /
• pp.527-535
• /
• 2017

본 연구는 인공지능에 대해 초등학생들이 최근 인식하고 있는 이미지를 분석하였다. 인공지능에 대한 인식과 관련된 이미지 형용사 23쌍을 추출하고 인식과 감성, 능력의 3가지 유형으로 구분하였다. 827명의 초등학생들을 대상으로 검사하여 이미지 요인을 편리성, 기술진보성, 인간친화성, 우려성의 4가지 요인으로 분류하였다. 검사결과 초등학생들은 인공지능이 똑똑하고 새로우며 복잡하지만 신나는 뚜렷한 이미지를 나타냈다. 변인별 비교에서 여학생, 코딩 경험 학생과 고학년이 인공지능에 대해 우려하는 이미지를 갖고 있었다. 반면 인공지능의 관심과 인식이 높은 학생이 인간 친화적이고, 편리하고, 기술 진보적이라는 이미지를 갖고 있었다.

• 디자인학연구
• /
• 제17권4호
• /
• pp.233-240
• /
• 2004

과학기술이 발달한 현대에 살고 있는 우리는 모두 ‘에너지’로 인해 편리한 생활을 영위하고 있다. 우리나라는 자원빈국으로 에너지원의 대부분을 해외에서 수입하고 있는 실정이며 계속되는 경제 성장과 국민 생활수준의 향상으로 에너지 소비는 더욱 증가하는 추세이다. 원자력은 우리나라처럼 에너지 부존자원이 빈약하고 에너지 수입 의존도가 높은 나라에서는 필수적인 에너지 자립형 대체에너지라고 한다. 하지만 원자력 발전이 위험 시설이라는 부정적인 인식과 방사능 처리 시설에 대한 불신 문제가 이슈화되면서 원자력 발전에 대한 대국민 교육, 홍보가 절실히 요구되고 있다. 이러한 문제를 환경 색채계획의 관점인 친인간, 친환경 색채계획을 목표로 접근하였으며 이를 통해 원자력에 대한 부정적 이미지를 최소화하고 친근하고 자연스러운 이미지를 부각시키며 대 국민 신뢰성 향상 및 청정 이미지 구축이 본 연구의 목표이다. 이를 위하여 일본의 원자력 발전소와 국내 발전소의 사례를 조사, 분석하고 발전소가 건설될 대상지를 방문하여 자연환경, 현황분석을 통하여 구체적인 색을 추출하였으며 지역 주민의 참여를 유도하고자 선물조사를 실시하여 색채계획에 반영하였다. 원자력 발전소의 환경 친화적 이미지구현을 통해 발전소의 안정성 및 친근한 발전소 이미지를 구축하며 원자력 발전에 대한 일반 국민들의 부정적인 인식을 계도하는데 적극적인 홍보 전략 및 수단으로 외관 환경색채계획을 시도하며 이를 통해 원전의 새로운 이미지 창출에 기여할 것으로 기대된다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 학술대회 논문집 전문대학교육위원
• /
• pp.175-180
• /
• 2006

In this paper, we develope a type of humanoid robot which can express its emotion against human actions. To interact with human, the developed robot has several abilities to express its emotion, which are verbal communication with human through voice/image recognition, motion tracking, and facial expression using fourteen Servo Motors. The proposed humanoid robot system consists of a control board designed with AVR90S8535 to control servor motors, a framework equipped with fourteen server motors and two CCD cameras, a personal computer to monitor its operations. The results of this research illustrate that our intelligent emotional humanoid robot is very intuitive and friendly so human can interact with the robot very easily.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.835-838
• /
• 2003

Computer vision and natural-language dialogue play an important role in friendly human-machine interfaces for service robots. In this paper we describe an integrated face detection and face recognition system for a welfare robot, which has also been combined with the robot's speech interface. Our approach to face detection is to combine neural network (NN) and genetic algorithm (GA): ANN serves as a face filter while GA is used to search the image efficiently. When the face is detected, embedded Hidden Markov Model (EMM) is used to determine its identity. A real-time system has been created by combining the face detection and recognition techniques. When motivated by the speaker's voice commands, it takes an image from the camera, finds the face inside the image and recognizes it. Experiments on an indoor environment with complex backgrounds showed that a recognition rate of more than 88% can be achieved.