• Journal of Industrial Convergence
• /
• v.19 no.6
• /
• pp.123-129
• /
• 2021

This Study is to identify factors that affect the interaction between professors and university students and their satisfaction with non-face-to-face lectures. The subjects were 348 university student who attended from October 5 to October 23, 2020. The statistics program was SPSS win 22.o. Among the expected benefits of non-face-to-face classes, the temporal benefit was 3.69 points, the expected benefit of the learning effect was 3.46 points, and the technical familiarity was 3.47 points. Satisfaction with non-face-to-face classes was found to be 3.58 points. Factors affecting the satisfaction of lectures in non-face-to-face classes were expected benefits of learning effect, university satisfaction, technical familiarity, expected benefits over time, and the number of non-face-to-face classes desired for the next semester. Learning effect The higher the expected benefit, the higher the university satisfaction, the higher the technical familiarity, the higher the expected temporal benefit, the higher the number of non-face-to-face classes desired for the next semester, the higher the satisfaction with the non-face-to-face class lectures. Therefore, it was confirmed that the role of the instructor was important in the interaction between the instructor and university students in the non-face-to-face class and the satisfaction of the lecture.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.04a
• /
• pp.397-400
• /
• 2007

In this paper, we discuss the user-customized interaction for intelligent home environments. The interactive system is based upon the integrated techniques using both speech and face recognition. For essential modules, the speech recognition and synthesis were basically used for a virtual interaction between user and proposed system. In experiments, particularly, the real-time speech recognizer based on the HM-Net(Hidden Markov Network) was incorporated into the integrated system. Besides, the face identification was adopted to customize home environments for a specific user. In evaluation, the results showed that the proposed system was easy to use for intelligent home environments, even though the performance of the speech recognizer did not show a satisfactory results owing to the noisy environments.

• Journal of Institute of Control, Robotics and Systems
• /
• v.11 no.1
• /
• pp.50-57
• /
• 2005

We present a simple and effective method of face and facial feature detection under pose variation of user face in complex background for the human-robot interaction. Our approach is a flexible method that can be performed in both color and gray facial image and is also feasible for detecting facial features in quasi real-time. Based on the characteristics of the intensity of neighborhood area of facial features, new directional template for facial feature is defined. From applying this template to input facial image, novel edge-like blob map (EBM) with multiple intensity strengths is constructed. Regardless of color information of input image, using this map and conditions for facial characteristics, we show that the locations of face and its features - i.e., two eyes and a mouth-can be successfully estimated. Without the information of facial area boundary, final candidate face region is determined by both obtained locations of facial features and weighted correlation values with standard facial templates. Experimental results from many color images and well-known gray level face database images authorize the usefulness of proposed algorithm.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.171.4-171
• /
• 2001

This paper proposes a method of human- robot interaction (HRI) using face directional gesture. A single CCD color camera is used to input face region, and the robot recognizes the face directional gesture based on the facial feature´s positions. One can give a command such as stop, go, left and right turn to the robot using the face directional gesture. Since the robot also has the ultra sonic sensors, it can detect obstacles and determine a safe direction at the current position. By combining the user´s command with the sensed obstacle configuration, the robot selects the safe and efficient motion direction. From simulation results, we show that the robot with HRI is more reliable for the robot´s navigation.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.1
• /
• pp.300-308
• /
• 2021

The epidemic of COVID19 caused a big change in design collaboration, which has been conducting using face-to-face interaction. Designers actively used video conferencing and online document tools in situations where face-to-face meetings were difficult, and this gave them an opportunity to experience that non-face-to-face collaboration can be more effective in a specific design process. In this regard, this study attempted to find out which activities during the design process are more compelling in face-to-face collaboration or non-face-to-face collaboration. To do this, three user experience design projects conducted after the COVID19 epidemic were analyzed through a retrospective interview method. As a result, during four design stages, 'Discover, Define, Develop, Deliver', face-to-face collaboration is necessary for the areas that require creative problem solving through active interaction. In contrast, non-face-to-face collaboration is preferred and more effective when designers need their own space and proceed their design work. In addition, the aspects of design tools supporting non-face-to-face collaboration were also illustrated. Findings discovered through this study are expected to contribute to research on the design process later.

• ETRI Journal
• /
• v.33 no.2
• /
• pp.251-258
• /
• 2011

Applying face alignment after face detection exerts a heavy influence on face recognition. Many researchers have recently investigated face alignment using databases collected from images taken at close distances and with low magnification. However, in the cases of home-service robots, captured images generally are of low resolution and low quality. Therefore, previous face alignment research, such as eye detection, is not appropriate for robot environments. The main purpose of this paper is to provide a new and effective approach in the alignment of small and blurred faces. We propose a face alignment method using the confidence value of Real-AdaBoost with a modified census transform feature. We also evaluate the face recognition system to compare the proposed face alignment module with those of other systems. Experimental results show that the proposed method has a high recognition rate, higher than face alignment methods using a manually-marked eye position.

• Human Ecology Research
• /
• v.62 no.2
• /
• pp.217-231
• /
• 2024

The aims of this study were to identify (a) the social network contact frequency of the elderly with children, relatives, and friends; (b) the impact of contact frequency (face-to-face/non-face-to-face) on life satisfaction of the elderly; and (c) the moderating effect of digital capabilities of the elderly on the relationship between social contact frequency and life satisfaction. Data were obtained from the National Survey of Older Koreans 2020. The sample comprised 6,119 adults aged 65+ who were in single or couple households. The principal findings were as follows. First, couple households, higher levels of education, and better health status increased life satisfaction of the elderly. Second, the higher the frequency of face-to-face contact with children and the higher the frequency of non-face-to-face contact with friends, the more positive the effect on life satisfaction of the elderly. Third, the interaction effect of the digital capabilities of the elderly differed according to children, relatives and friends. There was a significant and positive moderating effect on the relationship between life satisfaction and the frequency of face-to-face/non-face-to-face contact with children and the frequency of face-to-face contact with relatives. Conversely, there was a significant negative effect on the relationship between life satisfaction and the frequency of face-to-face/non-face-to-face contact with friends. By examining the impact of non-face-to-face contact on life satisfaction of the elderly in the era of digital transformation, the findings have significance in that they provide basic data to support policies and education programs aimed at improving the digital capabilities of the elderly.

• The KIPS Transactions:PartB
• /
• v.18B no.1
• /
• pp.21-28
• /
• 2011

A 3D face shape derived from 2D images may be useful in many applications, such as face recognition, face synthesis and human computer interaction. To do this, we develop a fast 3D Active Appearance Model (3D-AAM) method using depth estimation. The training images include specific 3D face poses which are extremely different from one another. The landmark's depth information of landmarks is estimated from the training image sequence by using the approximated Jacobian matrix. It is added at the test phase to deal with the 3D pose variations of the input face. Our experimental results show that the proposed method can efficiently fit the face shape, including the variations of facial expressions and 3D pose variations, better than the typical AAM, and can estimate accurate 3D face shape from images.

• Proceedings of the IEEK Conference
• /
• 2007.07a
• /
• pp.211-212
• /
• 2007

Pose-variation factors present a significant problem in 2D face recognition. To solve this problem, there are various approaches for a 3D face acquisition system which was able to generate multi-view images. However, this created another pose estimation problem in terms of normalizing the 3D face data. This paper presents a 3D head pose-normalization method using 2D and 3D interaction. The proposed method uses 2D information with the AAM(Active Appearance Model) and 3D information with a 3D normal vector. In order to verify the performance of the proposed method, we designed an experiment using 2.5D face recognition. Experimental results showed that the proposed method is robust against pose variation.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.2
• /
• pp.129-141
• /
• 2022

The purpose of this study is to reveal the variables that affect learning immersion, in real-time non-face-to-face classes. To this end, a survey was conducted from November 22, 2021 to December 5, 2021 for students with experience in zoom classes. Excluding incorrect questionnaire, 117 copies were analyzed using a structural equation model. The results show that 'interest' and 'interaction level' influenced 'learning immersion', and 'learning immersion' had a positive effect on 'learning outcome'. The contribution of this study is that it empirically analyzed variables affecting learning immersion in real-time non-face-to-face classes. In the follow-up study, it is necessary to verify variables that affect learning immersion in various platforms, including zoom.