• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.54 no.9
• /
• pp.577-579
• /
• 2005

In this study, the automatic tracking algorithm tracing a human face is proposed by using YCbCr color coordinated information and its thermal properties expressed in terms of thermal indexes in an infra-red image. The facial candidates are separately estimated in CbCr color and infra-red domain, respectively with applying the morphological image processing operations and the geometrical shape measures for fitting the elliptical features of a human face. The identification of a true face is accomplished by logical 'AND' operation between the refined image in CbCr color and infra-red domain.

• Journal of the Korean Society for Precision Engineering
• /
• v.20 no.3
• /
• pp.210-220
• /
• 2003

This work presents a method of point to surface assignment fur 3D metrology of solder pastes on PCB. A bounding box enclosing the solder paste tightly on all sides is introduced to avoid incorrect assignment. The shape of bounding box fur solder paste brick is variable according to geometry of measured points. The surface geometry of bounding box is obtained by using five peaks selected in the histogram of normalized gradient vectors. By using the bounding box enclosing the solder pastes, the task of point-to-surface assignment has been successfully conducted, then geometrical features are obtained through the task of surface fitting.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.18 no.1
• /
• pp.223-231
• /
• 1994

When manufacturing mold dies, an operation sheet is required for each part of the mold dies. The consistent estimation of standard operation time in the operation sheet is difficult, because the estimation is mainly based on subjective judgement. In order to resolve it, concept of feature is introduced in this study. For CAD/CAPP integration, feature technology is being implemented to represent geometrical and technological information of part drawings. A feature database has already been designed, and then used to generate data for process and operation planning modules. Related to this former research, standard operation time is calculated using the feature information and tables used in a real factory.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.08a
• /
• pp.209-212
• /
• 2000

본 논문에서는 칼라 CCD 카메라로부터 입력된 얼굴 영상에서 칼라 정보와 눈, 코, 입 등의 얼굴 영역 특징자 및 턱선의 선형적 특징을 이용한 얼굴 인식 알고리즘을 제안하였다. 제안한 알고리즘에서는 인간의 시각 체계와 비교적 유사한 HSI좌표계 상에서 피부색에 대한 색상 정보와 명암값 정보를 함께 이용함으로써 얼굴영역 추출의 효율을 높였고, 적응적인 추출이 가능하도록 하였다. 또한 추출된 얼굴 영역에서 얼굴 인식율 개선을 위해 눈, 코, 입 등의 구조적 위치 정보와 턱선의 선형적인 특징값을 이용하여 얼굴 인식율을 개선하였다. 제안한 알고리즘에서는 기존의 명암 정보를 이용하는 방법과는 달리 색상 정보와 명암 정보를 함께 이용함으로써 정확한 얼굴 영역의 검출이 가능하였으며 인식 방법에 있어서 구조적 특징자 외에 턱선의 선형적인 관계값을 이용함으로써 인식 효율을 개선하였다.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.08a
• /
• pp.293-296
• /
• 2000

본 논문에서는 얼굴의 구조적 특성과 누적 히스토그램을 이용하여 다양한 정보를 포함하고 있는 얼굴의 6가지 표정을 인식하는 알고리즘을 기술하였다. 표정 인식을 위해 특징점 추출 전처리 과정으로 입력 영상으로부터 에지 추출, 이진화, 잡음 제거, 모폴로지 기법을 이용한 팽창, 레이블링 순으로 적용한다. 본 논문은 레이블 영역의 크기를 이용해 1차 특징점 영역을 추출하고 가로방향의 누적 히스토그램 값과 대칭성의 구조적인 관계를 이용하여 2차 특징점 추출 과정을 거쳐 정확하게 눈과 입을 찾아낸다. 또한 표정 변화를 정량적으로 측정하기 위해 추출된 특징점들의 눈과 입의 크기, 미간 사이의 거리 그리고 눈에서 입까지의 거리 정보를 이용하여 표정을 인식한다. 1, 2차 특징점 추출 과정을 거치므로 추출률이 매우 높고 특징점들의 표정에 따른 변화 거리를 이용하므로 표정 인식률이 높다. 본 논문은 안경 착용 영상과 같이 복잡한 얼굴 영상에서도 표정 인식이 가능하다.

• Bulletin of the Korean Chemical Society
• /
• v.3 no.1
• /
• pp.9-13
• /
• 1982

Sulfametrole, $C_9H_{10}N_4O_3S_2$, crystallizes in the monoclinic system, space group $P2_1/n$ , with a = 8.145(2), b = 16.505(4), c = 9.637(1)${\AA},{\beta}=103.72(1)^{\circ},D_m=1.52gcm^{-3}$,Z=4.Intensities for 3594(2143 observed) unique reflections were measured on a four-circle diffractometer with Mo $K{\alpha}$ radiation $({\lambda}=0.71069{\AA})$. The structure was solved by direct method and refined by full-matrix least squares to a final R of 0.070. The geometrical features of the thiadiazole ring indicate some ${pi}$-electron delocalization inside the ring. The least squares planes defined by the benzene and thiadiazole rings are nearly perpendicular to each other(dihedral angle; $93.9^{\circ}$ ). All the potential hydrogen-bond donor atoms in the molecule, N(1) and N(2), are included in the hydrogen bonding. The molecules through hydrogen bonding form three dimensional network.

• Journal of ILASS-Korea
• /
• v.24 no.2
• /
• pp.58-65
• /
• 2019

A 3D FEM (Finite Element Method) based Helmholtz solver has been commonly used to characterize fundamental acoustic behavior and investigate dynamic instability features in many combustion systems. In this approach, a geometrical simplification of the target system has been generally made in order to reduce computational time and cost because a real combustor and fuel nozzle have a very complicated flow passage. The feasibility of these simplifications is quantitatively investigated in a small aero gas turbine nozzle in term of acoustic characteristics. It is found that the simplification in a nozzle geometry during the 3D FEM analysis process has no great influence on the acoustic modeling results, while the calculation complexity can be improved for a similar modeling accuracy.

• Korean Institute of Interior Design Journal
• /
• no.28
• /
• pp.33-43
• /
• 2001

Mario Botta is one of the modern architects who established his own architectural world on the basis of the architectural spirit of Modernism. His works have been a good theme not only for those who study architecture but also for those who study the relationship between architecture and the surrounding environment and there have been many published papers and reports on his works. However, most of them stressed on the importance of the external appearance of architecture or on the relationship between architecture and the surrounding environment. There have been relatively few studies that have dealt intensively with interior space. The aim of this study is to find the characteristics of interior space in public buildings that were designed by Botta and to analyze them from the view design principles and design elements. For this purpose, the five most important public buildings were selected and the public space of the building like the central hall, the lobby, and the foyer were analyzed. Through this study, the followings are realized. A) Spatial features: $\circled1$ Refined and graceful interiors where the principle of symmetry was applied, $\circled2$ Centripetal interiors surrounded by thick walls, $\circled3$ Interior design lit by skylights above the central area, B) Formative features: $\circled1$ The shapes of the external and internal spaces are identical, $\circled2$ Simple geometrical shapes were applied in defining the shapes of internal spaces, $\circled3$ Skylights and light wells were combined and were utilized as form elements, $\circled4$ Architectural vocabularies of Corbusier such as stairs, round pillars, and bridges were developed and utilized, $\circled5$ Utilized the geometry that resembled his architecture as a form element to the furniture, C) material pattern features: $\circled1$ Plainly expressed the patterns of bricks that appear in the course of construction, $\circled2$ Made and used horizontal stripe patterns using stones of different colors.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.6C
• /
• pp.815-823
• /
• 2004

A hue-based attention operator and a combinational integral projection function(CIPF) are proposed to extract the normalized regions of face and facial features robustly against illumination variation. The face candidate regions are efficiently detected by using skin color filter, and the eyes are located accurately nil robustly against illumination variation by applying the proposed hue- and symmetry-based attention operator to the face candidate regions. And the faces are confirmed by verifying the eyes with the color-based eye variance filter. The proposed CIPF, which combines the weighted hue and intensity, is applied to detect the accurate vertical locations of the eyebrows and the mouth under illumination variations and the existence of mustache. The global face and its local feature regions are exactly located and normalized based on these accurate geometrical information. Experimental results on the AR face database［8］ show that the proposed eye detection method yields better detection rate by about 39.3% than the conventional gray GST-based method. As a result, the normalized facial features can be extracted robustly and consistently based on the exact eye location under illumination variations.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.6
• /
• pp.121-126
• /
• 2004

An efficient multi face detection technique is proposed based on hierarchical context-free attention operators in which multiple faces are efficiently detected from a noisy and complex background. A noise-tolerant generalized symmetry transform (NTSGT) is applied hierarchically, as a context free attention operator, to the input pyramidal image for the high speed global location of the regions of face candidates (ROFCs) with a single mask. For the face verification, local NTGST is applied within each ROFC to confirm the existence of the detailed facial features. First, by globally applying NTGST which introduces the average pyramid method and focusing to the input image with complex background, ROFCs with recognizable resolution are detected robustly. Morphological operations are applied only to the each detected ROFCs to emphasize the facial features like eyes and lips. Then, eyes are detected by locally appling NTGST to the ROFCs and only faces are detected by verifying the existence of the geometrical features of the faces relatively to the location of eyes. The experimental results show that the proposed method can efficiently detect multiple faces from a noisy or complex background with 93.5% detection rate.