• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.11
• /
• pp.4502-4518
• /
• 2015

Fisher linear discriminant analysis (LDA) is one of the most popular projection techniques for feature extraction and has been widely applied in face recognition. However, it cannot be used when encountering the single sample per person problem (SSPP) because the intra-class variations cannot be evaluated. In this paper, we propose a novel method called local similarity based linear discriminant analysis (LS_LDA) to solve this problem. Motivated by the "divide-conquer" strategy, we first divide the face into local blocks, and classify each local block, and then integrate all the classification results to make final decision. To make LDA feasible for SSPP problem, we further divide each block into overlapped patches and assume that these patches are from the same class. To improve the robustness of LS_LDA to outliers, we further propose local similarity based median discriminant analysis (LS_MDA), which uses class median vector to estimate the class population mean in LDA modeling. Experimental results on three popular databases show that our methods not only generalize well SSPP problem but also have strong robustness to expression, illumination, occlusion and time variation.

• Journal of Digital Convergence
• /
• v.20 no.2
• /
• pp.289-297
• /
• 2022

The purpose of this study was to investigate the perception of dental students based on their experiences of online classes after taking non-face-to-face education courses for all the school semesters in 2020. For the research method, an online survey was conducted on A survey was conducted on 161 dental students enrolled in A University. The analytical method was conducted through frequency analysis, correlation analysis, and multiple regression analysis. The survey analysis findings showed that the satisfaction of dental students' about the non-face-to-face education course was above 4.2, and the detailed items were in the order of the appropriateness of the attendance processing method, satisfaction with recorded video lectures, and the assessment method of the course grade. In the case of the factors that affect the satisfaction of non-face-to-face education courses, the learning system and assessment method were statistically significant. The online class type that is most preferred by the students is recorded video lectures, and the highest number of participants chose 21~30 minutes as the appropriate time for the class content. It is considered that the application of the online system will continue to be used together with face-to-face education courses in the education site and various university-level efforts like systematic support are required to achieve effective learning achievements. This study only investigated the non-face-to-face education operation conditions of A University, so it cannot be generalized to all universities, but it can be used as basic data to provide education curriculum design and supportive measures for the compatibility of face-to-face and non-face-to-face courses.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.2098-2114
• /
• 2021

Light intensity variation is one of the key factors which affect the accuracy of vehicle face re-identification, so in order to improve the robustness of vehicle face features to light intensity variation, a Nonnegative Matrix Factorization model with the constraint of image acquisition time difference is proposed. First, the original features vectors of all pairs of positive samples which are used for training are placed in two original feature matrices respectively, where the same columns of the two matrices represent the same vehicle; Then, the new features obtained after decomposition are divided into stable and variable features proportionally, where the constraints of intra-class similarity and inter-class difference are imposed on the stable feature, and the constraint of image acquisition time difference is imposed on the variable feature; At last, vehicle face matching is achieved through calculating the cosine distance of stable features. Experimental results show that the average False Reject Rate and the average False Accept Rate of the proposed algorithm can be reduced to 0.14 and 0.11 respectively on five different datasets, and even sometimes under the large difference of light intensities, the vehicle face image can be still recognized accurately, which verifies that the extracted features have good robustness to light variation.

• International Journal of Contents
• /
• v.10 no.2
• /
• pp.18-27
• /
• 2014

This study examines underlying factors that influence undergraduate students' willingness to enhance communication with their instructor by comparing the frequency of e-mail and face-to-face interaction between students and instructors. Data was collected through a survey of 322 undergraduate journalism students at a large Midwestern university. The findings showed that the more passive students were in expressing their opinion during the class, the less likely they were to send e-mails to their instructor (Coef. = -0.180, p < .01) or to communicate with their instructor face-to-face (Coef. = -0.262, p < .01). The findings also showed that the more students described their personality as "shy," the less likely they were to e-mail their instructor (Coef. = -0.157, p < .05) or communicate with their instructor face-to-face (Coef. = -0.210, p < .01). It is noteworthy that the degrees of both passivity and shyness had a more negative effect on the probability of face-to-face interaction than they did on email interaction. In summary, email usage follows similar broader patterns of social interaction, rather than introducing a different trend in communication. This finding implies that the importance of e-mail should not be exaggerated as a communication tool for reticent students.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.8 no.3
• /
• pp.137-143
• /
• 2013

This paper describes an implementation of face detection technology for a real-time application on the Android platform. Java class of Face-Detection for detection of human face is provided by the Android API. However, this function is not suitable to apply for the real-time applications due to inadequate detection speed and accuracy. In this paper, the AdaBoost based classification method which utilizes Local Binary Pattern (LBP) histogram is employed for face detection. The face detection module has been developed by C/C++ language for high-speed image processing, and this module is included to the Android platform using the Java Native Interface (JNI). The experiments were carried out in the Java-based environment and JNI-based environment. The experimental results have shown that the performance of JNI-based is faster than Java-based method and our system is well enough to apply for real-time applications.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.7
• /
• pp.2667-2682
• /
• 2015

Due to the wide application of face recognition (FR) in information security, surveillance, access control and others, it has received significantly increased attention from both the academic and industrial communities during the past several decades. However, partial face occlusion is one of the most challenging problems in face recognition issue. In this paper, a novel method based on linear regression-based classification (LRC) algorithm is proposed to address this problem. After all images are downsampled and divided into several blocks, we exploit the evaluator of each block to determine the clear blocks of the test face image by using linear regression technique. Then, the remained uncontaminated blocks are utilized to partial occluded face recognition issue. Furthermore, an improved Distance-based Evidence Fusion approach is proposed to decide in favor of the class with average value of corresponding minimum distance. Since this occlusion removing process uses a simple linear regression approach, the completely computational cost approximately equals to LRC and much lower than sparse representation-based classification (SRC) and extended-SRC (eSRC). Based on the experimental results on both AR face database and extended Yale B face database, it demonstrates the effectiveness of the proposed method on issue of partial occluded face recognition and the performance is satisfactory. Through the comparison with the conventional methods (eigenface+NN, fisherfaces+NN) and the state-of-the-art methods (LRC, SRC and eSRC), the proposed method shows better performance and robustness.

• Restorative Dentistry and Endodontics
• /
• v.42 no.1
• /
• pp.48-53
• /
• 2017

Objectives: The aim of this study was to investigate the ability of the fluorescence-aided caries excavation (FACE) device to detect residual caries by comparing conventional methods in vivo. Materials and Methods: A total of 301 females and 202 males with carious teeth participated in this study. The cavity preparations were done by grade 4 (Group 1, 154 teeth), grade 5 (Group 2, 176 teeth), and postgraduate (Group 3, 173 teeth) students. After caries excavation using a handpiece and hand instruments, the presence of residual caries was evaluated by 2 investigators who were previously calibrated for visual-tactile assessment with and without magnifying glasses and trained in the use of a FACE device. The tooth number, cavity type, and presence or absence of residual caries were recorded. The data were analyzed using the Chi-square test, the Fisher's Exact test, or the McNemar test as appropriate. Kappa statistics was used for calibration. In all tests, the level of significance was set at p = 0.05. Results: Almost half of the cavities prepared were Class II (Class I, 20.9%; Class II, 48.9%; Class III, 20.1%; Class IV, 3.4%; Class V, 6.8%). Higher numbers of cavities left with caries were observed in Groups 1 and 2 than in Group 3 for all examination methods. Significant differences were found between visual inspection with or without magnifying glasses and inspection with a FACE device for all groups (p < 0.001). More residual caries were detected through inspection with a FACE device (46.5%) than through either visual inspection (31.8%) or inspection with a magnifying glass (37.6%). Conclusions: Within the limitations of this study, the FACE device may be an effective method for the detection of residual caries.

• Journal of Industrial Technology
• /
• v.28 no.B
• /
• pp.143-148
• /
• 2008

A real-time face detection is to find human faces robustly under the cluttered background free from the effect of occlusion by other objects or various lightening conditions. We propose a face detection system for real-time applications using wavelet decomposition method based on Gabor features. Firstly, skin candidate regions are extracted from the given image by skin color filtering and projection method. Then Gabor-feature based template matching is performed to choose face cadidate from the skin candidate regions. The chosen face candidate region is transformed into 2-level wavelet decomposition images, from which feature vectors are extracted for classification. Based on the extracted feature vectors, the face candidate region is finally classified into either face or nonface class by the Levenberg-Marguardt back-propagation neural network.

• Journal of Korean society of Dental Hygiene
• /
• v.21 no.6
• /
• pp.805-812
• /
• 2021

Objectives: To investigate the perceived quality of classes, academic emotions, and learning achievement levels associated with the non-face-to-face classes of health science students, and to analyze the factors related to class satisfaction. Methods: Using a questionnaire, 238 health science students were surveyed regarding the quality of classes, academic emotions, and learning achievement levels. Factors related to calss satisfaction were analyzed using stepwise multiple regression. Results: Lecture types that the students were most satisfied with were 'video lectures using PPT' and 'recorded lectures provided by LMS', while 'real-time video lectures' were scored the lowest (p=0.005). Factors affecting non-face-to-face class satisfaction were perceived achievement (β=0.425, p<0.001), learning content (β=0.265, p<0.001), learning emotion (β=0.171, p<0.001), and learning environment (β=0.137, p=0.012). The adjusted explanatory power for this model was 63.9%. Conclusions: To increase the satisfaction of health science students with non-face-to-face classes, it is necessary to prepare an institutional foundation and to develop an educational program that can increase perceived achievement.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.28 no.4
• /
• pp.643-648
• /
• 2001

Class III malocclusion usually becomes manifested at a very early age, most typically evidenced clinically by the appearance of either an edge-to-edge incisor relationship or an anterior crossbite. Anterior crossbite, by it-self, retards growth of maxilla, and accelerates growth of mandible. So, treatment should be started as early as the patient cooperates, removing any factors or forces that inhibit growth and development in the same physiologic maxillary displacement direction. The facial mask is effective in most developing Class III patients, because the appliance system affects virtually all areas contributing to a Class III malocclusion. Thus, the facial mask can be applied to most developing Class If cases regardless of the specific etiology. In these cases, the results were followed. Anterior crossbite was corrected by anterior movement of maxilla and downward backward rotation of mandible and simultaneously, lower facial height was increased. So, it can be concluded that the facial mask is effective in treating growing patients with a deficient maxilla.