• Journal of Korea Multimedia Society
• /
• v.10 no.12
• /
• pp.1591-1600
• /
• 2007

Camera position information from 2D face image is very important for that make the virtual 3D face model synchronize to the real face at view point, and it is also very important for any other uses such as: human computer interface (face mouth), automatic camera control etc. We present an algorithm to detect human face region and mouth, based on special color features of face and mouth in $YC_bC_r$ color space. The algorithm constructs a mouth feature image based on $C_b\;and\;C_r$ values, and use pattern method to detect the mouth position. And then we use the geometrical relationship between mouth position information and face side boundary information to determine the camera position. Experimental results demonstrate the validity of the proposed algorithm and the Correct Determination Rate is accredited for applying it into practice.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.9
• /
• pp.2341-2350
• /
• 2012

Face detection is the first step of vision-based driver fatigue detection method. Traditional face detection methods have problems of high false-detection rates and long detection times. A space-time restrained Adaboost method is presented in this paper that resolves these problems. Firstly, the possible position of a driver's face in a video frame is measured relative to the previous frame. Secondly, a space-time restriction strategy is designed to restrain the detection window and scale of the Adaboost method to reduce time consumption and false-detection of face detection. Finally, a face knowledge restriction strategy is designed to confirm that the faces detected by this Adaboost method. Experiments compare the methods and confirm that a driver's face can be detected rapidly and precisely.

• Journal of Korea Multimedia Society
• /
• v.20 no.5
• /
• pp.758-768
• /
• 2017

In this paper, we present a novel method to extract face representation based on multi-resolution spatial pyramid. In our method, a face is subdivided into increasingly finer sub-regions (local regions) and represented at multiple levels of histogram representations. To cope with misaligned problem, patch-based local descriptor extraction has been also developed in a novel way. To preserve multiple levels of detail in local characteristics and also encode holistic spatial configuration, histograms from all levels of spatial pyramid are integrated by using dimensionality reduction and feature combination, leading to our spatial-pyramid face feature representation. We incorporate our proposed face features into general face recognition pipeline and achieve state-of-the-art results on challenging face recognition problems.

• International journal of advanced smart convergence
• /
• v.11 no.3
• /
• pp.64-71
• /
• 2022

Various types of attendance management systems are being introduced in a remote working environment and research on using face recognition is in progress. To ensure accurate worker's attendance, a face recognition-based attendance management system must analyze every frame of video, but face recognition is a heavy task, the number of the task should be minimized without affecting accuracy. In this paper, we proposed a search model using time interval variation to minimize the number of face recognition task of recorded videos for attendance management system. The proposed model performs face recognition by changing the interval of the frame identification time when there is no change in the attendance status for a certain period. When a change in the face recognition status occurs, it moves in the reverse direction and performs frame checks to more accurate attendance time checking. The implementation of proposed model performed at least 4.5 times faster than all frame identification and showed at least 97% accuracy.

• Journal of Engineering Education Research
• /
• v.25 no.2
• /
• pp.22-31
• /
• 2022

This study was conducted to investigate the effect of learning style and lecture attitude on academic achievement in non-face-to-face lectures. Among students attending H University in the first semester of 2020. 1,880 students voluntarily participated in the survey. The questionnaire consists of 33 questions, and actual GPA was used to determine academic achievement. In this study, ANOVA and regression were utilized to find out the factors affecting academic achievement. The results are as follows. First, in the correlation between learning style types, the higher the avoidant learning style, the lower the independent, cooperative, and competitive types. Second, the higher the independent learning type, the higher the positive lecture attitude and GPA, and the higher the type of cooperative learning, the higher the negative lecture attitude. Third, the positive attitudes of 4th graders were higher than that of 1st graders. Fourth, there was no difference in learning style between colleges. Fifth, independent/competitive learning styles and non-face-to-face lecture attitudes had a significant effect on academic achievement in non-face-to-face lectures. In conclusion, in order to narrow the academic gap, instructors must identify the type of learning style. And it is necessary to consider students' preferences for non-face-to-face lectures.

• Journal of Advanced Navigation Technology
• /
• v.24 no.5
• /
• pp.430-437
• /
• 2020

The proposed model implements a model that improves the face prediction rate and recognition rate through learning with an artificial neural network using face detection, landmark and face recognition algorithms. After landmarking in the face images of a specific person, the proposed model use the previously learned Caffe model to extract face detection and embedding vector 128D. The learning is learned by building machine learning algorithms such as support vector machine (SVM) and deep neural network (DNN). Face recognition is tested with a face image different from the learned figure using the learned model. As a result of the experiment, the result of learning with DNN rather than SVM showed better prediction rate and recognition rate. However, when the hidden layer of DNN is increased, the prediction rate increases but the recognition rate decreases. This is judged as overfitting caused by a small number of objects to be recognized. As a result of learning by adding a clear face image to the proposed model, it is confirmed that the result of high prediction rate and recognition rate can be obtained. This research will be able to obtain better recognition and prediction rates through effective deep learning establishment by utilizing more face image data.

• Smart Media Journal
• /
• v.13 no.7
• /
• pp.27-35
• /
• 2024

Since COVID-19, the education industry has shifted many of its activities to non-face-to-face channels, and many programs are still being conducted in non-face-to-face channels during the endemic. This study aims to analyze the quality factors affecting user satisfaction of synchronous and asynchronous channels operated non-face-to-face and compare the differences between the two channels. For this purpose, we analyzed the reviews of graduate students of the same content in the synchronous and asynchronous channels at H University in Seoul, Korea. The non-face-to-face learning quality factors derived through topic modeling are educational system quality, content quality, instructor quality, and expectation confirmation, and their effects on user satisfaction were empirically analyzed through survey responses related to these quality factors. The results showed that all of the quality factors had a significant positive effect on satisfaction, and there were significant differences in satisfaction factors between the two channels. This study is significant in that it suggests that improving the content itself for synchronous channels and improving the convenience of the program operation system for asynchronous channels is effective in improving user satisfaction.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.8
• /
• pp.279-290
• /
• 2021

As the university's academic management was not carried out smoothly due to COVID-19, and most of them were conducted as non-face-to-face classes, students' dropout is steadily increasing. In this study focus group interviews were conducted to analyze physics students and professors' recognition of the COVID-19 non-face-to-face class environment. Based on the results, the implications of non-face-to-face classes for physics education were presented. Physics students described their feelings about un-tact teaching as 'the class in which the body is comfortable but the mind is uncomfortable', 'a person who is smarter than me seems to explain a book, reading it' and 'a short clip lecture which may be comfortable but cause losses to me', while the professors also described them as 'a fully transformed class system' and 'a online class putting much burden on me'. Regarding school dropout, students said that the concerns about dropout during non-face-to-face classes were deepened about transfer or transfer. The professors said that the department atmosphere had lost vitality due to the increase in non-face-to-face classes and academic dropouts, and had a lot of worries because of the recruitment rate and external university evaluation. The implications of the COVID-19 non-face-to-face class situation for physics education suggest that it is required to strengthen the interaction between professors and students, finding ways to enhance the sense of reality to supplement laboratory classes and giving opportunities to professors to share their pedagogical contents knowledge in physics.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.21 no.2
• /
• pp.9-16
• /
• 2013

The comparisons of performance characteristics between the super-mirror face grinding machine using variable air pressure developed in this laboratory to grind precisely the sliding face of a surface hardened workpiece with thermal spray and the conventional one are investigated by measuring the surface roughness and hardness for a SCM440. To process variously workpiece according to shape, size and materials, the rotating and contacting forces of the developed grinding machine can be changed by air pressure. The surface roughness of processed workpiece can be also attained to state of mirror face by grinding precisely the sliding face with changing the rotating speed of diamond wheel. It is possible to be attached to the various machine tools because the super-mirror face grinding machine using variable air pressure is a small size. The grinding efficiency is elevated because it can be worked by two or more grinding machines attached to concurrently a machine tool for the large workpiece. In this study, results show that the cusp height of the super-mirror face grinding machine for the particle size of 100 and $1500No./mm^2$ is lower than that of the conventional one because the vibration is reduced by rotating very fast the diamond wheel with a pressed air and it can be processed by rotating the diamond wheel with a constantly varied air pressure perpendicular to workpiece surface, and that the workpiece in the super-mirror face grinding machine for the particle size of $3000No./mm^2$ can be processed to state of mirror face that is rarely seen by the cusp height. It is also found that the surface hardness of both the conventional and the super-mirror face grinding machines are increased as the particle size of diamond wheel is reduced, and the surface hardness of the super-mirror face grinding machine is HRC 1.1 ~ 1.8 higher than that of the conventional one.

• Information Systems Review
• /
• v.23 no.4
• /
• pp.87-102
• /
• 2021

Smart cities are attracting attention as a new economic growth engine based on new technologies and means to solve side effects of urbanization such as a surge in energy consumption, deepening environmental pollution, and an increase in crime rates. In particular, as demand for non-face-to-face services increases due to COVID-19, the role of smart cities that can provide various online and offline non-face-to-face services is becoming more important. Therefore, this study defined smart city non-face-to-face services based on literature research on the concept and underlying technology of smart city, and analyzed consumer utility for each service using Conjoint analysis. In particular, differences in user preferences between Sejong City and Busan City, which are currently designated as national smart city pilot cities in Korea, were compared and analyzed, and based on the derived results, measures to improve the competitiveness of smart city services were suggested.