• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.6
• /
• pp.783-788
• /
• 2004

Many reported methods assume that the faces in an image or an image sequence have been identified and localization. Face detection from image is a challenging task because of the variability in scale, location, orientation and pose. The difficulties in visual detection and recognition are caused by the variations in viewpoint, viewing distance, illumination. In this paper, we present an efficient linear discriminant for multi-view face detection and face location. We define the training data by using the Fisher`s linear discriminant in an efficient learning method. Face detection is very difficult because it is influenced by the poses of the human face and changes in illumination. This idea can solve the multi-view and scale face detection problems. In this paper, we extract the face using the Fisher`s linear discriminant that has hierarchical models invariant size and background. The purpose of this paper is to classify face and non-face for efficient Fisher`s linear discriminant.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.6
• /
• pp.31-40
• /
• 2003

Most face recognition systems are based on 2D images and applied in many applications. However, it is difficult to recognize a face when the pose varies severely. Therefore, head pose estimation is an inevitable procedure to improve recognition rate when a face is not frontal. In this paper, we propose a novel head pose estimation algorithm for 3D face recognition. Given the 3D range image of an unknown face as an input, we automatically extract facial feature points based on the face curvature. We propose an Error Compensated Singular Value Decomposition (EC-SVD) method based on the extracted facial feature points. We obtain the initial rotation angle based on the SVD method, and perform a refinement procedure to compensate for remained errors. The proposed algorithm is performed by exploiting the extracted facial features in the normaized 3D face space. In addition, we propose a 3D nearest neighbor classifier in order to select face candidates for 3D face recognition. From simulation results, we proved the efficiency and validity of the proposed algorithm.

• Journal of Korea Multimedia Society
• /
• v.8 no.5
• /
• pp.633-640
• /
• 2005

In this paper, we propose an adaptive face region extraction algorithm based on skin color information. It consists oi the extraction of face candidate region and projection step. In the step of face candidate region extraction, we extract the pixels which are regarded as the candidate skin color pixels by using the given range. Then, the ratio between the total pixels and the extracted pixels is calculated. According to the ratio, we adaptively decide the range of the skin color and extract face candidate region. In the projection step, we project the extracted face candidate region into vertical direction to estimate the width of the face. Then the redundant parts are efficiently removed by using the estimated face width. And the extracted face width information is used at the horizontal projection step to extract the height of the face. From the experiment results for the various images, the proposed algorithm shows more accurate results than the conventional algorithm.

• Journal of the Korean Geotechnical Society
• /
• v.18 no.5
• /
• pp.221-228
• /
• 2002

The stability of a tunnel face is one of the most important factors in tunnel excavation. Especially, if a tunnel is located under groundwater level, groundwater may flow into the tunnel face and seepage forces acting on the tunnel face due to groundwater flow may affect seriously the stability of the tunnel face. Therefore, the seepage pressure at the tunnel face should be considered fir the proper design and safe construction of a tunnel. In this paper, the effect of tunnel advance rate on the seepage forces acting on the tunnel face was studied. The finite element program to analyze the groundwater flow around a tunnel with the consideration of tunnel advance rate was developed. Using the program, the parametric study for the effect of the tunnel advance rate and hydraulic characteristics of the ground on the seepage forces acting on the tunnel face was made. From this study, it was concluded that the tunnel advance rate must betaken into consideration as an additional parameter to assess the seepage forces at the tunnel face and a rational design methodology fer the assessment of support pressures required for maintaining the stability of the tunnel face was suggested for undetwater tunnels.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.26 no.1
• /
• pp.128-132
• /
• 2012

In this paper, we performed a quantitative analysis of face color according to the health status of four constitution types. 205 Korean male in age from 65 to 80 were participated in this study and 85 subjects were finally selected for the analysis. Imaging process techniques were employed to extract feature variables associated with face color from a frontal facial image. Using the extracted feature variables, the correlations between face color and health status, face color and health status in each constitution type, and face color and four constitution types in heath status group were investigated. As the result, it was observed that the face color of healthy group contained more red component and less blue component than unhealthy group. For each constitution type, the face parts showing a significant difference according to health status were different. This is the first work which reports the correlation between the face color and health status of four constitution types with a objective method, and the numerical data for the face color according to the health status of four constitution types will be an objective standard to diagnose a patient's health status.

• Journal of Digital Convergence
• /
• v.19 no.11
• /
• pp.485-498
• /
• 2021

This study confirmed the perceptions of performing arts field workers and related experts under the theme of non-face-to-face performing arts. As a result of the analysis, first, respondents agreed with the practical need for non-face-to-face performing arts, but respondents in the field viewed the lack of "fieldability" and "communication with the audience" of non-face-to-face performances as a problem. Second, respondents who participated in non-face-to-face performance production had negative perceptions of realism, immersion, interaction with the audience, lack of enjoyment outside the performance, and difficulties in securing budgets, filming and editing, and actors' acting commitment. Third, regarding the government's non-face-to-face performing arts-related support policy, they complained that support was only given to specific organizations and a small number of people, and administrative difficulties in support. Through this study, it can be suggested that face-to-face and non-face-to-face performance arts should be treated in a complementary and balanced relationship in terms of government policy.

• Journal of Korean Home Economics Education Association
• /
• v.34 no.1
• /
• pp.151-165
• /
• 2022

The aim of this study is to examine the effectiveness of non-face-to-face classes conducted due to the COVID-19 crisis. In order to achieve this goal, a non-face-to-face class with flipped learning was applied in one subject of clothing major held at 'S' University in Cheongju, Korea. In addition, this study tried to analyze the differences between pre- and post-non-face-to-face classes in problem analysis ability, resource/information/technology literacy, convergent thinking ability as core competencies, and overall learning satisfaction. As a result, after participating in the non-face-to-face class in which the flipped learning was applied, the students recognized that their abilities improved in the three problem-solving competency sub-areas, and their overall learning satisfaction also increased. The effectiveness of non-face-to-face classes in the field of clothing and fashion has been mainly measured in fashion design and clothing construction courses. However, based on the results of this study, it can be suggested that non-face-to-face classes in a theory-oriented lecture-type class can be effective methods for improving students' core competencies such as problem-solving skills if teaching-learning methods such as flipped learning are applied. Therefore, the results of this study will be useful data for designing differentiated non-face-to-face class strategies in a theory-oriented lecture-type class to improve the core competencies of college students.

• Journal of Forest and Environmental Science
• /
• v.18 no.1
• /
• pp.15-30
• /
• 2001

The twenty-first century was entered and began to show the extent where revegetation of the face of slopes using the native woody plant was nationwide at last. Then, future revegetation of the face of slopes was considered on the basis of them in order to attempt the development of this direction, while the recognition for fundamental matter of the revegetation and revegetation of the regional inhabitant was arranged this time. The regional inhabitant sufficiently understood the necessity of the revegetation, and the method using the native woody plant had sufficiently been recognized, and the high evaluation was given in the method. In the other, the major inhabitant questioned it for introducing the exotic species. It was proposed that the utilization of native weeds should be advanced by the pursuit of many facets of the revegetation of the face of the slopes based on these in future in the place where the introduction of the native woody plant is difficult. And, the method for stretching the wire netting for the face of slopes indicated the necessity of the urgent review, because the artificial disaster might be caused. As a conclusion, the goal of the revegetation of the face of slopes confirmed that it was ecologically stable short-terminable face of slopes physically and connects it with the medium and long term for improvement and improvement of global environment, and it indicated the importance of the revegetation of the face of slopes.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.4
• /
• pp.897-904
• /
• 2005

Face Recognition has been an active research area because it is not difficult to acquire face image data and it is applicable in wide range area in real world. Due to the high dimensionality of a face image space, however, it is not easy to process the face images. In this paper, we propose a method to reduce the dimension of the facial data and extract the features from them. It will be solved using the method which extracts the features from holistic face images. The proposed algorithm consists of two parts. The first is the using of principal component analysis (PCA) to transform three dimensional color facial images to one dimensional gray facial images. The second is integrated linear discriminant analusis (PCA+LDA) to prevent the loss of informations in case of performing separated steps. Integrated LDA is integrated algorithm of PCA for reduction of dimension and LDA for discrimination of facial vectors. First, in case of transformation from color image to gray image, PCA(Principal Component Analysis) is performed to enhance the image contrast to raise the recognition rate. Second, integrated LDA(Linear Discriminant Analysis) combines the two steps, namely PCA for dimensionality reduction and LDA for discrimination. It makes possible to describe concise algorithm expression and to prevent the information loss in separate steps. To validate the proposed method, the algorithm is implemented and tested on well controlled face databases.

• Proceedings of the IEEK Conference
• /
• 2009.05a
• /
• pp.31-33
• /
• 2009

Face detection using AdaBoost algorithm is capable of processing images rapidly while having high detection rates. It seemed to be the fastest and the most robust and it is still today. Many improvements or extensions of this method have been proposed. However, previous approaches only deal with upright faces. They suffer from limited discriminant capability for rotated faces as these methods apply the same features for both upright and rotated faces. To solve this problem, it is necessary that we rotate input images or make independently trained detectors. However, this can be slow and can require a lot of training data, since each classifier requires the computation of many different image features. This paper proposes a robust algorithm for finding rotated faces within an image. It reduces the computational and sample complexity, by finding common features that can be shared across the classes. And it will be able to apply with multi-class object detection.