http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
유태웅 한국컴퓨터산업학회 2001 컴퓨터産業敎育學會論文誌 Vol.2 No.11
실시간 자막 탐지는 비디오 인덱싱, 텍스트의 이해, 자동 자막 탐지시스템 등 수많은 응용 분야에서 요구된다. 본 논문은 I 프레임을 기반으로 MPEG 압축 동영상에서 자막을 탐지하는 알고리즘을 제안한다. 제안한 알고리즘은 자막 텍스춰 정보와 색체 정보를 사용하여 배경 영상으로부터 자막을 정확히 분리한다. 기존 알고리즘들은 압축 동영상으로부터 텍스트 영역을 추출하기 전에 압축을 먼저 해제하는데 제안한 알고리즘은 DCT 압축 도메인에서 직접 자막 텍스트 영역을 탐지한다. For the applications like video indexing, text understanding, and automatic captions localization system, real-time localization of captions is an essential task. This paper presents a algorithm for localization of captions in MPEG compression images based on I frame. In this algorithm, caption text regions are segmented from background images using their distinguishing texture characteristics and chrominance information. Unlike previously published algorithms which fully decompress the video sequence before extracting the text regions, this algorithm locates candidate caption text region directly in the DCT compressed domain.
아미노실란화 몬모릴로나이트가 도입된 애폭시 나노복합재료의 제조 및 특성분석
유태웅,김승수,조을룡,이재락,조창기 한국생체재료학회 2011 생체재료학회지 Vol.15 No.2
The effects of montmorillonite (MMT) incorporated with aminoalkyl silan to the properties of epoxy resin were studied. Aminosilanized MMT was prepared by the reaction between sodium montmorillonite (Na+-MMT) and 3-aminopropyl triethoxysilane (APS). The MMT particles were characterized with the analysis of X-ray diffraction (XRD), electron spectroscopy for chemical analysis (ESCA), Fourier transform infrared spectroscopy (FT-IR). The mixture of epoxy prepolymer and MMT suspended in acetone was polymerized to prepare nanocomposites. The glass transition temperature (Tg) and mechanical properties of epoxy nanocomposites incorporated with aminosilanized MMT were enhanced, compared to those of a control epoxy resin. However, the physical values were not significantly increased.
유태웅,오일석 全北大學校 1995 論文集 Vol.40 No.-
This paper proposes a method for extracting the face regions and features from frontal color images. At first, we extract face region from the face images, and then extract eye and mouth features in that region. Face regions are extracted using symmetry of face from HSI color image that consists of hue and saturation components insensitive to intensity. We also use hue range for skin color. In extracted face region, we automatically determine location of eyes and mouth using physical relation of eyes and mouth and characteristics of gray-level distribution.
유기실란처리 실리카를 이용한 에폭시 나노복합소재의 제조 및 분석
유태웅,우지선,지종훈,이병민,김승수 한국생체재료학회 2012 생체재료학회지 Vol.16 No.1
The effects of organo-silanized fumed silica to the thermal and mechanical properties of epoxy resin were studied. The organo-silanized fumed silica was prepared by the reaction of 3-aminopropyl triethoxysilane (APS) and 3-glycidoxypropyl trimethoxisilane (GPS). The organo-silanized fumed silica were characterized with electron spectroscopy for chemical analysis (ESCA), Fourier transform infrared spectroscopy (FT-IR), and scanning electron microscopy (SEM), etc. The mixture of epoxy prepolymer and organo-silanized fumed silica suspended in methanol was polymerized to prepare nanocomposites. The glass transition temperature (Tg) and mechanical properties of epoxy nanocomposites with the organo-silanized fumed silica were enhanced, compared to those of a control epoxy resin.
가시성을 표시한 사과 검출 데이터셋과 적응형 히트맵 회귀를 이용한 딥러닝 검출
유태웅,서다솜,김민우,이슬기,오일석 (사)한국스마트미디어학회 2023 스마트미디어저널 Vol.12 No.10
In the fruit harvesting field, interest in automatic robot harvesting is increasing due to various seasonality and rising harvesting costs. Accurate apple detection is a difficult problem in complex orchard environments with changes in light, vibrations caused by wind, and occlusion of leaves and branches. In this paper, we introduce a dataset and an adaptive heatmap regression model that are advantageous for robot automatic apple harvesting. The apple dataset was labeled with not only the apple location but also the visibility. We propose a method to detect the center point of an apple using an adaptive heatmap regression model that adjusts the Gaussian shape according to visibility. The experimental results showed that the performance of the proposed method was applicable to apple harvesting robots, with MAP@K of 0.9809 and 0.9801 when K=5 and K=10, respectively.
박용성,유태웅 群山大學校 1996 論文集 Vol.23 No.-
Finding human faces automatically in a scene is a difficult yet significant problem. This paper proposes a method for detecting face regions from a complex background, and describes the experimental results. We perform face location based on the observation that human faces are characterized by their color information and texture features as follows. Firstly we construct a face chromatic histogram in hue and saturation chromatic space. Secondly we use the chromatic histogram to detect skin pixels from the input image. Thirdly a face texture model is constructed by calculating inertia, inverse difference and correlation of facial images. Finally the locations of the face region are determined by face texture features.
PSDE 시스템의 효율적인 내부 구조 : PSDE:PELIHAN Syntax-Directed Editor
유태웅,박용성 群山大學校 1994 論文集 Vol.21 No.-
We are currently developing a version of the PSDE for PELIHAN (Programming Educational Language In HANgul). The PSDE system is an interactive programming environment with integrated facilities to create, edit, execute, and debug programs. Both editing and execution are guided by the syntactic structure of the programming language. The grammar of the programming language is embodied in a collection of templates predefined for all but the simplest statement types. This editor provides the language-based interaction environment that an user can simply programming. This paper presents an efficient internal organization in PSDE system that is one of the syntax-directed editor. Moreover, this system produces intermediate code for fast execution.