• Journal of KIISE:Software and Applications
• /
• v.28 no.2
• /
• pp.192-200
• /
• 2001

본 논문은 조명 변화, 표정 변화, 부분적인 오클루전이 있는 얼굴 영상에 강인하고 적은 메모리양과 계산량을 갖는 효율적인 얼굴 인식 방법을 제안한다. SKKUface(Sungkyunkwan University face)라 명명한 이 방법은 먼저 훈련 영상에 PCA(principal component analysis)를 적용하여 차원을 줄일 때 구해지는 특징 벡터 공간에서 조명 변화, 얼굴 표정 변화 등에 해당되는 공간이 최대한 제외된 새로운 특징 벡터 공간을 생성한다. 이러한 특징 벡터 공간은 얼굴의 고유특징만을 주로 포함하는 벡터 공간이므로 이러한 벡터 공간에 Fisher linear discriminant를 적용하면 클래스간의 더욱 효과적인 분리가 이루어져 인식률을 획기적으로 향상시킨다. 또한, SKKUface 방법은 클래스간 분산(between-class covariance) 행렬과 클래스내 분산(within-class covariance) 행렬을 계산할 때 문제가 되는 메모리양과 계산 시간을 획기적으로 줄이는 방법을 제안하여 적용하였다. 제안된 SKKUface 방법의 얼굴 인식 성능을 평가하기 위하여 YALE, SKKU, ORL(Olivetti Research Laboratory) 얼굴 데이타베이스를 가지고 기존의 얼굴 인식 방법으로 널리 알려진 Eigenface 방법, Fisherface 방법과 함께 인식률을 비교 평가하였다. 실험 결과, 제안된 SKKUface 방법이 조명 변화, 부분적인 오클루전이 있는 얼굴 영상에 대해서 Eigenface 방법과 Fisherface 방법에 비해 인식률이 상당히 우수함을 알 수 있었다.

• Journal of Fashion Business
• /
• v.10 no.3
• /
• pp.44-53
• /
• 2006

The purposes of this study were to find out any significants among somatotypes and face types and importance of image making to successful students' life. The respondents were composed of 181 males and 160 females. It consists of total 29 items including the facial features, personality expression methods, characteristics of body shapes, image making, colors and neckline and their responses were measured with Likert 5-point scale. For data analysis, descriptive statistics, cross-tabulation analysis including $Χ^2$-test and frequency analysis were used. As the results, 47％ of male students and 28% of female students responded they were satisfied with their own facial types. 32% of male students and all female students were not satisfied with their own body shapes and fashion depends on accessories like hat, sunglasses, boots and necklace rather than dress itself. All male and female students were not satisfied with their body shapes and recognized the importance of image. They answered that they change image if someone advices their image and it suggests that information and intellectual needs of image making are required and approach to efficient methods of image making is needed.

• Korean Journal of Occupational Health Nursing
• /
• v.24 no.4
• /
• pp.259-269
• /
• 2015

Purpose: The study is to identify a correlation among hospital nurses' emotional labor, social support and organizational commitment and to analyze the effects on organizational commitment. Methods: The participants are 300 nurses working at two general hospitals located in Gyeonggi-do, who agreed to join the study. Data collection were done from July to September in 2014. The collected data are analyzed a descriptive statistic, t-test, ANOVA, $Scheff{\acute{e}}$ test, Pearson's correlation coefficient, and multiple regression and SPSS/WIN 15.0 Program was used in the process. Results: Organizational commitment was negatively correlated with emotional works but it was positively correlated with social support. The factors affecting organizational commitment were informational support and evaluative support which were sub-domain of social support as well as level of emotional expression which was a sub-domain of emotional works, their positions and level of education. Conclusion: To increase the level of an organizational commitment, a method of coping in difficult situations and information relating to private assessments is recommended. Also, the organization should prepare a plan that members can properly manage their emotions face-to-face with clients.

• Journal of Environmental Health Sciences
• /
• v.27 no.2
• /
• pp.30-36
• /
• 2001

This review begins with a brief expression of aerosol capture mechanism of fibrous filter(s) and performance of particulate removing respirators. The more complicated and detailed discussion is not included in this articles. Filtration efficiency and pressure drop are introduced as quality factor ( $q_{F}$) and the way in which filtration efficiency varies with particle size is discussed. Quality factors fro filters recently certified in USA were found to be very higher than those of filters made in Korea, China and USA filters certified with old certified standards. Electrically charged filters are widely used because they have high filtration efficiency and low pressure drop, but their efficiency decreases sharply at the condition occurring wet and oil mist. A discussion is given of respirator leakage through face seal and filter media with fit testing and total inward leakage testing. Since fit factor (FF) refers to the reciprocal of the fraction of the total air entering a respirator through face seal leakage , the degree of fitting performance for respirators is expected with FF. Because respirators made in Korea had generally lower FFs than respirators made in USA, it is necessary to develope respirators that fit properly for Koreans or establish regulations for fit testing.g.

• Journal of Korea Society of Industrial Information Systems
• /
• v.26 no.1
• /
• pp.67-82
• /
• 2021

Both universities and professors are eagerly seeking effective communication method for e-learning under the COVID-19 pandemic. In order to achieve this goal, it is necessary to understand the differences in requirements according to the characteristics of students. In this study, the relationship between the demographic characteristics of learners and important/preferred types and methods of communication in terms of learning or expression of opinion was analyzed through chi-square tests. The results showed that communication importances/preferences vary significantly based on learner's characteristics.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.10 no.4
• /
• pp.237-249
• /
• 2014

The technological advances within the Internet industry have led to a revolution in terms of how people communicate with each other. For example, users are no longer limited to using face to face interactions to connect and communicate with their peers but can use email, instant messaging and more. A recent trend that researchers are observing is the adaption of SNS. SNS such as facebook and myspace has been a dominant global trend and has grown dramatically in the past 5 years. The purpose of this study was to test SNS usage motivations influencing the user satisfaction. The research model was developed based on literature review. SNS usage motivations consist of five factors: expression, relationship formation, social exchange, information seeking, trend. 189 questionnaires were used for the main part of regression analysis. The analysis results revealed that relationship formation, social exchange and information seeking were very significant factors influencing the user satisfaction. Especially, social exchange was the most significant factor. We can prospect that importance of user satisfaction on SNS usage motivations is more and more increasing in the future.

• Archives of Craniofacial Surgery
• /
• v.25 no.1
• /
• pp.1-10
• /
• 2024

The facial nerve stimulates the muscles of facial expression and the parasympathetic nerves of the face. Consequently, facial nerve paralysis can lead to facial asymmetry, deformation, and functional impairment. Facial nerve palsy is most commonly idiopathic, as with Bell palsy, but it can also result from a tumor or trauma. In this article, we discuss traumatic facial nerve injury. To identify the cause of the injury, it is important to first determine its location. The location and extent of the damage inform the treatment method, with options including primary repair, nerve graft, cross-face nerve graft, nerve crossover, and muscle transfer. Intracranial proximal facial nerve injuries present a challenge to surgical approaches due to the complexity of the temporal bone. Surgical intervention in these cases requires a collaborative approach between neurosurgery and otolaryngology, and nerve repair or grafting is difficult. This article describes the treatment of peripheral facial nerve injury. Primary repair generally offers the best prognosis. If primary repair is not feasible within 6 months of injury, nerve grafting should be attempted, and if more than 12 months have elapsed, functional muscle transfer should be performed. If the affected nerve cannot be utilized at that time, the contralateral facial nerve, ipsilateral masseter nerve, or hypoglossal nerve can serve as the donor nerve. Other accompanying symptoms, such as lagophthalmos or midface ptosis, must also be considered for the successful treatment of facial nerve injury.

• Journal of the Korea Convergence Society
• /
• v.11 no.10
• /
• pp.207-212
• /
• 2020

This study analyzes the Soju(Korean alcohol) advertisement image, which is relatively easy to interpret subjectively, among sexual appeal advertisements that stimulate consumers' curiosity, where the image is verified through AOI (area of interest) 3 areas (face, body, product), and eye-tracking, one of the psychophysiological indicators. The result of the analysis reveals that visual attention, the interest in the advertising model, was higher in the face than in the body shape. Contrary to the prediction that men would be more interested in body shape than women, both men and women showed higher interest in the face than a body. Besides, it was derived that recognition and recollection of the product were not significant. This study is significant in terms of examining the pattern of visual attention such as the gaze point and gaze time of male and female consumers on sexual appeal advertisements. In further, the study looks forward to bringing a positive influence to the soju advertisement image by presenting the expression method that the soju advertisement image should pursue as well as the appropriate marketing direction.

• The Korean Journal of Applied Statistics
• /
• v.31 no.5
• /
• pp.539-554
• /
• 2018

Effective interaction between user and device is considered an important ability of IoT devices. For some applications, it is necessary to recognize human facial expressions in real time and make accurate judgments in order to respond to situations correctly. Therefore, many researches on facial image analysis have been preceded in order to construct a more accurate and faster recognition system. In this study, we constructed an automatic recognition system for facial expressions through two steps - a facial recognition step and a classification step. We compared various models with different sets of data with pixel information, landmark coordinates, Euclidean distances among landmark points, and arctangent angles. We found a fast and efficient prediction model with only 30 principal components of face landmark information. We applied several prediction models, that included linear discriminant analysis (LDA), random forests, support vector machine (SVM), and bagging; consequently, an SVM model gives the best result. The LDA model gives the second best prediction accuracy but it can fit and predict data faster than SVM and other methods. Finally, we compared our method to Microsoft Azure Emotion API and Convolution Neural Network (CNN). Our method gives a very competitive result.

• The KIPS Transactions:PartB
• /
• v.12B no.5 s.101
• /
• pp.577-586
• /
• 2005

Many algorithms have been proposed for (ace recognition that is one of the most successful applications in image processing, pattern recognition and computer vision fields. Research for what kind of attribute of face that make harder or easier recognizing the target is going on recently. In flus paper, we propose method to improve recognition performance using relevance of face data and applied algorithms, because recognition performance of each algorithm according to facial attribute(illumination and expression) is change. In the experiment, we use n-tuple classifier, PCA and Gabor wavelet as recognition algorithm. And we propose three vectorization methods. First of all, we estimate the fitnesses of three recognition algorithms about each cluster after clustering the test data using k-means algorithm then we compose new clusters by integrating clusters that select same algorithm. We estimate similarity about a new cluster of test data and then we recognize the target using the nearest cluster. As a result, we can observe that the recognition performance has improved than the performance by a single algorithm without clustering.