• ETRI Journal
• /
• 제33권4호
• /
• pp.600-610
• /
• 2011

This paper presents a novel approach to face detection by localizing faces as the goal-specific saliencies in a scene, using the framework of selective visual attention of a human with a particular goal in mind. The proposed approach aims at achieving human-like robustness as well as efficiency in face detection under large scene variations. The key is to establish how the specific knowledge relevant to the goal interacts with the bottom-up process of external visual stimuli for saliency detection. We propose a direct incorporation of the goal-related knowledge into the specification and/or modification of the internal process of a general bottom-up saliency detection framework. More specifically, prior knowledge of the human face, such as its size, skin color, and shape, is directly set to the window size and color signature for computing the center of difference, as well as to modify the importance weight, as a means of transforming into a goal-specific saliency detection. The experimental evaluation shows that the proposed method reaches a detection rate of 93.4% with a false positive rate of 7.1%, indicating the robustness against a wide variation of scale and rotation.

• 사상체질의학회지
• /
• 제26권4호
• /
• pp.350-364
• /
• 2014

Objectives This study was aimed to find the significant features of face form according to the Taeeumin and Soyangin by analyzing the three-dimensional face information data. Also, making standard face of the Taeeumin and Soyangin was an object of this study. Methods We collected three-dimensional face data of patients aged between 20~45 years old diagnosed by a specialist of Sasang constitutional medicine. The data were collected using a 3D scanner, Morpheus 3D(Morpheus Corporation, KOREA). Extracting a face feature point total of 64, was set to 332 pieces(height, angle, ratio, etc.) of each variable between feature points. ANOVA test were used to compare the characteristics of subjects according to the Taeeumin and Soyangin. Results When not to consider gender, the Taeeumin and Soyangin were different from the 18 items(3 items in the ear, 9 items in the eye, 1 item in the nose, 1 item in the mouth, 4 items in the jaw). When to consider gender, the Taeeumin and Soyangin men were different from the 6 items(1 item in the ear, 2 items in the nose, 3 items in the face). And the Taeeumin and Soyangin women were different from 17 items(1 item in the ear, 10 items in the eye, 2 items in the nose, 1 item in the mouth, 3 items in the face). Conclusions These results show Taeeumin's face(both men and women) width of the right and left is larger than the length of the top and bottom. Compared to men of Soyangin, men of Taeeumin has greater wings of the nose. Compared to women of Soyangin, women of Taeeumin has longer length of the eye. Soyangin's face(both men and women) length of the top and bottom is larger than the width of the right and left. Compared to men of Taeeumin, men of Soyangin has smaller wings of the nose. Compared to women of Taeeumin, women of Soyangin has more stereoscopic facial features at the top and bottom of the lateral face. Also, by accumulating three-dimensional face data, this study modeled the standard facial features by Taeeumin and Soyangin. These results may be helpful in the development of Sasang constitutional diagnostics utilizing the characteristics of the facial form at later.

• 대한수학회지
• /
• 제45권4호
• /
• pp.1007-1025
• /
• 2008

We will describe a way to construct Ford domains of cusped hyperbolic 3-manifolds on maximal cusp diagrams and compute fundamental groups using face pairing maps as generators and Cannon-Floyd-Parry's edge cycles as relations. We also describe explicitly a cutting and pasting alteration to reduce the number of faces on the bottom region of Ford domains. We expect that our analysis of Ford domains will be useful on other future research.

• International journal of advanced smart convergence
• /
• 제9권4호
• /
• pp.192-197
• /
• 2020

In this study, we try to find ways to recognize face recognition more stably and to improve the effectiveness and reliability of face recognition. In order to improve the face recognition rate, a lot of data must be used, but that does not necessarily mean that the recognition rate is improved. Another criterion for improving the recognition rate can be seen that the top/bottom of the recognition rate is determined depending on how accurately or precisely the degree of classification of the data to be used is made. There are various methods for classification analysis, but in this study, classification analysis is performed using a support vector machine (SVM). In this study, feature information is extracted using a normalized image with rotation information, and then projected onto the eigenspace to investigate the relationship between the feature values through the classification analysis of SVM. Verification through classification analysis can improve the effectiveness and reliability of various recognition fields such as object recognition as well as face recognition, and will be of great help in improving recognition rates.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
• /
• pp.2307-2310
• /
• 2003

In this paper, a method for face recognition based on the wavelet packet decomposition is proposed. In the proposed method, the input image is decomposed by the 2-level wavelet packet transformation and then the face areas are defined by the Integral Projection technique applied to each of the 1-level subband images, HL and LH. After the defined face areas are divided into three areas, called top, bottom, and border, the mean and the variance of the three areas of the approximation image are computed, and the variance of the single predetermined face area for the rest of 15 detail images, from which the feature vectors of statistical measure are extracted. In this paper we use the wavelet packet decomposition, a generalization of the classical wavelet decomposition, to obtain its richer signal analysis features such as discontinuity in higher derivatives, self-similarity, etc. And we have shown that even with very simple statistical features such as mean values and variance we can make an excellent basis for face classification, if an appropriate probability distance is used.

• Steel and Composite Structures
• /
• 제21권5호
• /
• pp.1145-1156
• /
• 2016

To study the effects of foam core density and face-sheet thickness on the mechanical properties and failure modes of aluminum foam sandwich (AFS) beam, especially when the aluminum foam core is made in aluminum alloy and the face sheet thickness is less than 1.5 mm, three-point bending tests were investigated experimentally by using WDW-50E electronic universal tensile testing machine. Load-displacement curves were recorded to understand the mechanical response and photographs were taken to capture the deformation process of the composite structures. Results demonstrated that when foam core was combined with face-sheet thickness of 0.8 mm, its carrying capacity improved with the increase of core density. But when the thickness of face-sheet increased from 0.8 mm to 1.2 mm, result was opposite. For AFS with the same core density, their carrying capacity increased with the face-sheet thickness, but failure modes of thin face-sheet AFS were completely different from the thick face-sheet AFS. There were three failure modes in the present research: yield damage of both core and bottom face-sheet (Failure mode I), yield damage of foam core (Failure mode II), debonding between the adhesive interface (Failure mode III).

• Ocean Systems Engineering
• /
• 제12권4호
• /
• pp.385-402
• /
• 2022

This paper deals with the study of hydrodynamic pressure in reservoir adjacent to the concrete gravity dam subjected to dynamic excitation. Widely famous finite element method is used to discretize the reservoir domain for modelling purpose. Pressure is considered as nodal variable following Eulerian approach. A suitable nonreflecting boundary condition is applied at truncated face of reservoir to make the infinite reservoir to finite one for saving the computational cost. Thorough studies have been done on generation of hydrodynamic pressure in reservoir with variation of different geometrical properties. Velocity profile and hydrodynamic pressure are observed due to harmonic excitation for variation of inclination angle of dam reservoir interface. Effect of bottom slope angle and inclined length of reservoir bottom on hydrodynamic pressure coefficient of reservoir are also observed. There is significant increase in hydrodynamic pressure and distinct changes in velocity profile of reservoir are noticeable for change in inclination angle of dam reservoir interface. Change of bottom slope and inclined length of reservoir bottom are also governing factor for variation of hydrodynamic pressure in reservoir subjected to dynamic excitation.

• 한국의류학회지
• /
• 제33권6호
• /
• pp.938-948
• /
• 2009

본 연구는 2003년에서 2004년에 실시된 제 5차 한국인 인체치수 조사사업을 통해 확보된 측정사진 중 성인여성 20, 30, 40, 50대 각 150명, 총 600명의 정면과 측면 얼굴사진을 대상으로 얼굴의 연령별 특성을 파악하는데 필요하다고 판단되는 62개의 측정항목과 보다 세부적인 얼굴형태의 분석에 활용될 수 있는 21개의 지수 및 계산항목 총 83개 항목을 본 연구자가 선정한 후 Size Kroea 사업 중 얼굴의 측정 프로그램으로 사용되었던 "Venus face2D"를 이용하여 2차원 간접 측정하였다. 간접 측정기간은 2006년 3월 1일부터 6월 30일까지였다. 연구의 결과는 다음과 같다. 성인여성의 주요 측정항목에 대한 평균 측정치는 얼굴길이 196mm, 상안 62.3mm, 중안 68.9mm, 하안 66.5mm이었고, 이마너비는 125.1mm, 눈살수평너비는 141.2mm, 옆광대점너비 150.8mm 턱아래점너비 124.4mm였다. 이를 바탕으로 우리나라 성인여성 얼굴의 세부항목에 대한 연령집단별 차이를 분석하였으며, 전체 성인여성의 평균 얼굴형과 더불어 각 연령집단별 평균 얼굴형을 제시하였다. 본 연구는 정량화된 수치와 비율을 이용하여 우리나라 성인여성 및 각 연령별 평균 얼굴형을 제시하고, 연령별 얼굴특성을 분석하였다는데 연구의 의의가 있다.

• 한국터널지하공간학회 논문집
• /
• 제18권5호
• /
• pp.499-509
• /
• 2016

최근들어 지하공간의 활용이 빈번해지면서 도심지 터널의 수요가 급증하고 있다. 토피가 얕고 연약한 지반에 시공되는 도심지 터널에서는 굴진면에서 다양한 형태의 굴진면 변위가 발생할 수 있으며 이로 인해 터널이 3차원 거동하여 종방향 하중전이의 영향이 클 수 있다. 굴진면에서는 분할 굴착, 토피, 지반의 불균질성 등에 의해 다양한 형태의 변위가 발생할 수 있고, 이에 따라 지반의 이완형태는 물론 주변지반으로 전이되는 하중의 분포 형태와 크기가 다양하게 나타날 수 있다. 따라서 본 연구에서는 터널 굴진면의 변위거동을 등변위, 상부 큰 변위, 하부 큰 변위로 이상화하여 모형시험을 수행하였으며, 이를 분석하여 굴진면의 변위와 터널 상부 지반의 종방향 하중 전이를 집중적으로 연구하였다. 연구 결과 굴진면의 변위형태에 따라 굴진면에 작용하는 토압은 물론 터널 종방향으로 전이되는 하중의 크기와 분포형태가 다르게 나타났다. 터널 종방향으로 전이되는 하중의 크기는 굴진면 변위가 등변위 형태일때에 가장 크고 하부 큰 변위 형태일때와 상부 큰 변위 형태일때의 순서로 작아졌다. 또한 토피고가 낮아지면 터널 종방향 하중전이가 굴진면 근접부에 집중되어 발생되지만 토피고가 일정값 이상으로 커지면 하중전이 영역이 넓어지는 것으로 나타났다.

• 한국공작기계학회논문집
• /
• 제15권3호
• /
• pp.32-38
• /
• 2006

During stereolithography processes, the shape errors such as curl distortion and distortion of side face are generated due to the shrinkage of liquid resins. In this study, the effects of dimension of part and structure of supports on the shape error are examined. Cubic specimens which have different thicknesses are manufactured and their deformations are measured with CMM. Thicker part generates smaller curl distortion of top face and larger of bottom face. Also thicker part generates larger distortion of side face until part thickness increases to about 20mm. Larger stiffness of supports which is obtained by shorter spacing of the supports and line type contact instead of point type contact generates smaller shape error of the part.