• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.10
• /
• pp.4903-4929
• /
• 2018

In this study, a fully automatic pose and expression invariant 3D face alignment algorithm is proposed to handle frontal and profile face images which is based on a two pass course to fine alignment strategy. The first pass of the algorithm coarsely aligns the face images to an intrinsic coordinate system (ICS) through a single 3D rotation and the second pass aligns them at fine level using a minimum nose tip-scanner distance (MNSD) approach. For facial recognition, multi-view faces are synthesized to exploit real 3D information and test the efficacy of the proposed system. Due to optimal separating hyper plane (OSH), Support Vector Machine (SVM) is employed in multi-view face verification (FV) task. In addition, a multi stage unified classifier based face identification (FI) algorithm is employed which combines results from seven base classifiers, two parallel face recognition algorithms and an exponential rank combiner, all in a hierarchical manner. The performance figures of the proposed methodology are corroborated by extensive experiments performed on four benchmark datasets: GavabDB, Bosphorus, UMB-DB and FRGC v2.0. Results show mark improvement in alignment accuracy and recognition rates. Moreover, a computational complexity analysis has been carried out for the proposed algorithm which reveals its superiority in terms of computational efficiency as well.

• The korean journal of orthodontics
• /
• v.26 no.5 s.58
• /
• pp.547-556
• /
• 1996

The purpose of this study was to evaluate the skeletal, dental and soft tissue profile changes following the face mask therapy in growing skeletal class III malocclusion patients. The fifteen patients with the good results were selected among the patients who visited the Department of Orthodontics in Seoul National University Hospital. The mean age was 10.63(range 7.25-13.25) years and the mean treatment duration was 9.84(range 2.00-27.00) months. Lateral cephalograms were taken just before and after face mask application. After tracing the cephalograms, thirty five items(twety angular and fifteen linear) were measured. The differences before and after the face mask therapy were compared statistically by the paired t-test(p<0.05). The results were as follows : SNA and Co-A(effective maxillary length) increased significantly after using the face mask(p<0.001), which reflects the orthopedic changes of maxilla. SNB and Co-Gn(effective mandibular length) also showed an increase(p<0.01), which may be a result of the strong growth trends of the samples. FMA, SN-GoGn and Y-axis angle increased significantly(p<0.01), which means the backward and downward rotation of the mandible. This positional change seemed to have compensated an increase of effective mandibular length. There was no statistically significant difference in angulation of upper and lower incisors between pre-treatment and post-treatment(p>0.05). In soft tissue profile, the upper lip was positioned anteriorly(p<0.01) after treatment and approximated to the normal standards.

• Geomechanics and Engineering
• /
• v.21 no.2
• /
• pp.215-226
• /
• 2020

The magnitude and distribution of tunnel deformation were widely discussed topics in tunnel engineering. In this paper, a three-dimensional (3D) finite element program was used for the analysis of various horseshoe-shaped opening expressway tunnels under different geologies. Two rock material models - Mohr-Coulomb and Hoek-Brown were executed in the process of analyses; and the results show that the magnitude and distribution of tunnel deformation were close by these two models. The tunnel deformation behaviors were relevant to many factors such as cross-sections and geological conditions; but the geology was the major factor to the normalized longitudinal deformation profile (LDP). If the time-dependent factors were neglected, the maximum displacements were located at the distance of 3 to 4 tunnel diameters behind the excavation face. The ratios of displacement at the excavation face to the maximum displacement were around 1/3 to 1/2. In general, the weaker the rock mass, the larger the ratio. The displacements in front of the excavation face were decreased with the increasement of distance. At the distance of 1.0 to 1.5 tunnel diameter, the displacements were reduced to one-tenth of the maximum displacement.

• Research in Community and Public Health Nursing
• /
• v.23 no.3
• /
• pp.231-243
• /
• 2012

Purpose: The purpose of this study was to identify the relationships between health status including objective health status and subjective health perception and Health-Promoting Lifestyle Profile II in North Korean immigrants. Methods: During August 2011 to November 2011, a convenience sample of 96 subjects aged 19 to 65 years were recruited from two centers and one public health center in Gyeongnam. The subjects were interviewed face to face by trained people with a survey questionnaire. Results: Approximately 40% of North Korean immigrants rated their health status as 'poor', and the prevalence of health problems in them was 81.3%. The average level of health-promoting lifestyle profile II was $1.78{\pm}0.35$. Females with normal weight or overweight, and have stayed for over 1 year in South Korea were related to the lower score of health-promoting lifestyle profile II. Conclusion: Considering North Korean immigrants' health background and health behaviors, customized health care program focusing on musculoskeletal disorder and psychological problems are required, and at the same time health behavior change program to achieve lifetime wellness should be developed.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.23 no.60
• /
• pp.23-36
• /
• 2000

A probabilistic model of burr formation in face milling of gray cast iron is proposed. During a face milling operation, an irregular pattern of the edge profile consisting of burrs and edge breakouts is observed at the end of cut. Based on the metal cutting theory, we derive a probabilistic model. The operational bayesian modeling approach is adopted to include the relevant theory in the model.

• Proceedings of the KIEE Conference
• /
• 1988.07a
• /
• pp.679-682
• /
• 1988

From the viewpoint of general recognition system, B-spline is introduced for the approximation and recognition of human profile contours. Profile contour is approximated to the cublic B-spline curve by least square fitting so that B-Spline nodes nearly correspond with the curvature extrema of the contour. This method is designed for the spline to be good features in recognition, and also showed good approximation compared with the variants of B-spline appraximation.

• Proceedings of the KIEE Conference
• /
• 1988.07a
• /
• pp.683-686
• /
• 1988

In the recognition of similar patterns like profile contours of human faces, feature measure plays important role. We extracted effective and general feature by B-spline approximation. The nodes and vertices of the approximated curve are normalized and used as features. Since the features have both local property of curvature extrema and global property by B-spline approximation, they are superior to those of curvature extrema of the profile contour. For the image data of six sets of 56 persons, some of which are ill-made, averaged accuracy rate of 97.6 % is obtained in recognizing combinational 333 test samples.

• Journal of Information Display
• /
• v.8 no.3
• /
• pp.29-33
• /
• 2007

The temporal dark image sticking phenomena are examined and compared for the two different electrode structures such as the face-to-face and coplanar sustain electrode structure. To compare the temporal dark image sticking phenomena for both structures, the differences in the infrared emission profile, luminance, and perceived luminance of the image sticking cells and the non image sticking cells were measured. It is observed that the temporal dark image sticking is mitigated for the face-to-face structure. The mitigation of the temporal dark image sticking for the face-to-face structure is due to the slight increase in the panel temperature induced by the ITO-less electrode structure.

• Journal of the Semiconductor & Display Technology
• /
• v.15 no.2
• /
• pp.61-65
• /
• 2016

Facial feature detection is a fundamental function in the field of computer vision such as security, bio-metrics, 3D modeling, and face recognition. There are many algorithms for the function, active shape model is one of the most popular local texture models. This paper addresses issues related to face detection, and implements an efficient extraction algorithm for extracting the facial feature points to use on iOS platform. In this paper, we extend the original ASM algorithm to improve its performance by four modifications. First, to detect a face and to initialize the shape model, we apply a face detection API provided from iOS CoreImage framework. Second, we construct a weighted local structure model for landmarks to utilize the edge points of the face contour. Third, we build a modified model definition and fitting more landmarks than the classical ASM. And last, we extend and build two-dimensional profile model for detecting faces within input images. The proposed algorithm is evaluated on experimental test set containing over 500 face images, and found to successfully extract facial feature points, clearly outperforming the original ASM.

• Geomechanics and Engineering
• /
• v.30 no.4
• /
• pp.363-372
• /
• 2022

One of the most frequent issues in tunnel excavation is the collapse of rock blocks and the dropping of rock fragments from the tunnel face. The tunnel face can be reinforced using a number of techniques. One of the most popular and affordable solutions is the use of face longitudinal dowels, which has benefits including high strength, flexibility, and ease of cutting. In order to examine the reinforced face, this work shows the longitudinal deformation profile and ground response curve for a tunnel face. This approach is based on assumptions made during the analysis phase of problem solving. By knowing the tunnel face response and dowel behavior, the interaction of two elements can be solved. The rock element equation derived from the rock bolt method is combined with the dowel differential equation to solve the reinforced ground response curve (GRC). With a straightforward and accurate analytical equation, the new differential equation produces the reinforced displacement of the tunnel face at each stage of excavation. With simple equations and a less involved computational process, this approach offers quick and accurate solutions. The FLAC3D simulation has been compared with the suggested analytical approach. A logical error is apparent from the discrepancies between the two solutions. Each component of the equation's effect has also been described.