• 디지털융복합연구
• /
• 제10권7호
• /
• pp.207-212
• /
• 2012

본 연구는 정치인들의 용모가 미디어 수용자인 유권자의 정서와 투표에 미치는 영향을 살펴본 실험 연구이다. 그동안 자세, 제스추어, 메이컵 등과 같은 비언어적 단서들에 관한 연구는 다수 진행되어 왔으나, 정치 후보의 얼굴에 표현되어지는 안경착용이 유권자에 미치는 영향에 관한 연구는 찾아보기 어렵다. 따라서 본 연구에서는 지방선거 TV연설에 노출된 대학생 피험자들을 대상으로 정치 후보의 안경 착용이 미디어 수용자에게 미치는 영향을 실험을 통해 살펴보았다. 연구결과 TV연설에서 정치 후보자의 안경 착용은 유권자의 친근감과 신뢰감에는 영향을 미치지 못하였으나, 유권자의 호감도와 지지도에는 정적인 영향을 미치는 것으로 나타났다.

• 한국패션뷰티학회지
• /
• 제3권2호
• /
• pp.39-46
• /
• 2005

Art-Make-up has resulted in occupying one of the central areas of this culture. Art Make-up is currently undergoing various changes. The viewpoint of modern make-up is the infiniteness of emotion such as the subjectively individualized expressions and aesthetic values breaking with conventional thought. The most significant change is the idea of the 'grotesque'. The purpose of this research is to re-clarify the development of the diversity, professionalism and artistic feature through the study of Art make-up based on the 'grotesque' style. This also strives to focus attention at observing the deep and mysterious workings of the human inner world. In order to explain the features of 'grotesque' Art make-up, six images below are presented. Firstly, Inharmonious images. Secondly, disgusting inhuman images. Thirdly, mechanical images. Fourthly, distorted and exaggerated images. Fifthly, diabolic and horrific images. And, lastly, playful images. These six images thoroughly demonstrate the 'grotesque' features. The fact at we can see the 'grotesque' features in Art make-up explains the enormous growth of Art make-up and the unlimited range of expression in this field. It also implies that the choice of material and theme is not restricted to universal artistic criteria. In closing, it is necessary that Art make-up is thought of not as actual art but more as a tool for its subjects. As a result, this research will provide valuable information for studies in the future.

• 한국실내디자인학회:학술대회논문집
• /
• 한국실내디자인학회 2005년도 춘계학술발표대회 논문집
• /
• pp.271-272
• /
• 2005

As regards of designing, I chose a simple wall design of repeating pattern of vertical windows, rather than making the building as a glamourous obzet. This kind of approach was intended to pursue strong image of construction company, interchanging and communicating with its confused surrounding. Therefore, I boldly removed parts that I considered needless from the facade, and used simple and easy words clearly implying the organization. Lobby is the face of the building, but since the space is deep and narrow and the reality of lease should be considered, there was limit to give original image to the lobby. Instead, high ceiling is the biggest feature of this space. Doorae Engineering-Construction Corp. is young and energetic company. I wanted to highlight the young and energetic image of the company by crossing tore oblique piece of boards. This doesn't just has a simple function as ceiling, but also work as a major subject in the space. In addition of this powerful space of oblique lines, indirect lighting is used to emphasize the character of territory, continuity and deepness of the space. Character of territory that divides main and supplementary function and main and supplementary moving line is expressed by flow of dimension, and continuity and deepness of space is emphasized by indirect lighting flowing linearly through the crack between the ceiling and the wall.

• 한국정보통신학회논문지
• /
• 제16권5호
• /
• pp.932-938
• /
• 2012

얼굴 표정은 상호간 의사소통에 있어 중요한 의미를 갖는 것으로, 인간이 사용하는 다양한 언어보다도 수많은 인간 내면의 감정을 표현할 수 있는 유일한 수단이다. 본 논문에서는 쉽고 자연스러운 얼굴 표정 생성을 위한 근육 모델 기반 3D 얼굴 표정 생성 시스템을 제안한다. 3D 얼굴 모델의 표정 생성을 위하여 Waters의 근육 모델을 기반으로 자연스러운 얼굴 표정 생성에 필요한 근육을 추가하여 사용하고, 표정 생성의 핵심적 요소인 눈썹, 눈, 코, 입, 볼 등의 특징요소들을 중심으로 얼굴 근육과 근육벡터를 이용하여 해부학적으로 서로 연결된 얼굴 근육 움직임의 그룹화를 통해 얼굴 표정 변화의 기본 단위인 AU를 단순화하고 재구성함으로써 쉽고 자연스러운 얼굴 표정을 생성할 수 있도록 하였다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2003년도 춘계학술발표논문집 (상)
• /
• pp.599-602
• /
• 2003

본 논문에서는 스테레오 영상의 정합을 통한 얼굴의 굴곡 특징과 좌표 정보로서 정지 영상에서 생기는 제약 조건의 약화와 굴곡 특징을 이용하여 보다 강건한 얼굴 특징 추출 알고리즘을 제안한다. 얼굴 인식 기술은 정지 영상을 통한 얼굴 영역의 특징들로 얼굴을 구별하고, 얼굴을 검색하기 위하여 다양한 특징을 추출하는데 정지 영상에서는 추출할 수 없는 좌표 정보를 이용한 눈, 코, 입의 정보들과 굴곡 정보를 이용함으로서 얼굴 인식의 효율성을 높이는데 있다. 제안된 알고리즘의 단계는 색상으로부터의 얼굴 영역 검출 단계 얼굴 특징의 추출을 위한 전처리 단계, 눈, 코, 입에 대한 특징 정보로서 사람의 판별 유무와 찾아진 얼굴 영역에 눈 템플릿을 적용하고, 눈 사이의 거리와 기울어짐 코와 입에 대한 거리 정보들로서 스테레오 영상의 굴곡 특징 정보를 추출하는 단계로 이루어져 있다. 또한, 기존의 특징 정보뿐만 아니라 스테레오 영상의 정합을 통한 굴곡 특징 정보를 사용 각각 영상의 종류에 대해서 100%, 93%, 76%의 인식률을 얻었으며 평균 90%로서 정지 영상과의 비교를 통해 8%의 인식률의 향상으로 본 연구의 유효성을 입증하였다.

• 동의생리병리학회지
• /
• 제29권3호
• /
• pp.218-222
• /
• 2015

Facial diagnosis based on quantitative facial features has been studied in many Korean medicine fields, especially in Sasang constitutional medicine. By the rapid growing of 3D measuring technology, generic and cheap 3D sensors, such as Microsoft Kinect, is popular in many research fields. In this study, the possibility of using Kinect in facial diagnosis is examined. We introduce the development of facial feature extraction system and verify its accuracy and repeatability of measurement. Furthermore, we compare Sasang constitution diagnosis results between DSLR-based system and the developed Kinect-based system. A Sasang constitution diagnosis algorithm applied in the experiment was previously developed by a huge database containing 2D facial images acquired by DSLR cameras. Interrater reliability analysis result shows almost perfect agreement (Kappa = 0.818) between the two systems. This means that Kinect can be utilized to the diagnosis algorithm, even though it was originally derived from 2D facial image data. We conclude that Kinect can be successfully applicable to practical facial diagnosis.

• 인터넷정보학회논문지
• /
• 제16권5호
• /
• pp.87-92
• /
• 2015

Numerous IT organizations and companies around the world aspire to improve the efficiency and general standard of their software development. The IT organizations want to seize the opportunities and take advantages of new development processes and methodologies. These advantages include higher customers' satisfaction and better software quality among many. In order to achieve them, different agile software methodologies such as scrum, Feature driven development, eXtremeProgramming (XP), Dynamic system development method, Kanban and others have been frequently adopted by IT organizations across the world. Several studies have shown that agile software development methods are effective in a lot of settings. This study, in which 40 agile practitioners from Malaysia participated, additionally confirms the effectiveness of agile development methods. Furthermore, this paper presents some of the critical barriers not well-known by IT-organizations. The results of this analysis can be used to guide IT organization from the obstacles they may face while adopting agile in their environments.

• 한국정보통신학회논문지
• /
• 제12권7호
• /
• pp.1291-1300
• /
• 2008

본 논문에서는 패턴인식의 정확성을 향상시키기 위한 지능시스템을 제안한다. 제안한 지능시스템은 신경회로망의 무감독학습 방법인 SOPM(Self Organizing Feature Map), LVQ(Learning Vector Quantization), 그리고 퍼지이론의 FCM(Fuzzy C-means)을 이용하여 구성한다. 제안한 지능시스템의 유용성은 실험을 통해 확인한다. 실험은 Fisher의 Iris 데이터 분류, Cambridge 대학의 Olivetti 연구실(ORL; Olivetti Research Laboratory)에서 제공하는 얼굴 데이터베이스를 이용한 얼굴 영상 데이터 분류, 그리고 근전도(EMG, Electromyogram) 데이터를 분류하는 것이다. 제안한 지능시스템은 일반적인 LVQ와 비교한다. 실험을 통해 제안한 지능시스템이 일반적인 LVQ보다 패턴 인식의 정확성이 더 우수함을 알 수가 있었다.

• 한국컴퓨터정보학회논문지
• /
• 제23권11호
• /
• pp.51-57
• /
• 2018

In this paper, we studied about the extraction of the parameter and implementation of speechreading system to recognize the Korean 8 vowel. Face features are detected by amplifying, reducing the image value and making a comparison between the image value which is represented for various value in various color space. The eyes position, the nose position, the inner boundary of lip, the outer boundary of upper lip and the outer line of the tooth is found to the feature and using the analysis the area of inner lip, the hight and width of inner lip, the outer line length of the tooth rate about a inner mouth area and the distance between the nose and outer boundary of upper lip are used for the parameter. 2400 data are gathered and analyzed. Based on this analysis, the neural net is constructed and the recognition experiments are performed. In the experiment, 5 normal persons were sampled. The observational error between samples was corrected using normalization method. The experiment show very encouraging result about the usefulness of the parameter.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권12호
• /
• pp.4476-4491
• /
• 2021

Video service providers tend to face user network problems in the process of transmitting video streams. They strive to provide user with superior video quality in a limited bitrate environment. It is necessary to accurately determine the target bitrate range of the video under different quality requirements. Recently, several schemes have been proposed to meet this requirement. However, they do not take the impact of visual influence into account. In this paper, we propose a new multi-category model to accurately predict the target bitrate range with target visual quality by machine learning. Firstly, a dataset is constructed to generate multi-category models by machine learning. The quality score ladders and the corresponding bitrate-interval categories are defined in the dataset. Secondly, several types of spatial-temporal features related to VMAF evaluation metrics and visual factors are extracted and processed statistically for classification. Finally, bitrate prediction models trained on the dataset by RandomForest classifier can be used to accurately predict the target bitrate of the input videos with target video quality. The classification prediction accuracy of the model reaches 0.705 and the encoded video which is compressed by the bitrate predicted by the model can achieve the target perceptual quality.