• Journal of the Optical Society of Korea
• /
• v.20 no.2
• /
• pp.239-244
• /
• 2016

Mugshot face images, routinely collected by police, usually contain both frontal and profile views. Existing automated face recognition methods exploited mugshot databases by enlarging the gallery with synthetic multi-view face images generated from the mugshot face images. This paper, instead, proposes to match the query arbitrary view face image directly to the enrolled frontal and profile face images. During matching, the 3D face shape model reconstructed from the mugshot face images is used to establish corresponding semantic parts between query and gallery face images, based on which comparison is done. The final recognition result is obtained by fusing the matching results with frontal and profile face images. Compared with previous methods, the proposed method better utilizes mugshot databases without using synthetic face images that may have artifacts. Its effectiveness has been demonstrated on the Color FERET and CMU PIE databases.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.11
• /
• pp.5546-5559
• /
• 2019

Facial action units (AUs) have recently drawn increased attention because they can be used to recognize facial expressions. A variety of methods have been designed for frontal-view AU detection, but few have been able to handle multi-view face images. In this paper we propose a method for multi-view facial AU detection using a fused multilayer, multi-task, and multi-label deep learning network. The network can complete two tasks: AU detection and facial view detection. AU detection is a multi-label problem and facial view detection is a single-label problem. A residual network and multilayer fusion are applied to obtain more representative features. Our method is effective and performs well. The F1 score on FERA 2017 is 13.1% higher than the baseline. The facial view recognition accuracy is 0.991. This shows that our multi-task, multi-label model could achieve good performance on the two tasks.

• Journal of Korean Neurosurgical Society
• /
• v.43 no.4
• /
• pp.198-200
• /
• 2008

Giant cavernous malformations (GCMs) occur very rarely and little has been reported about their clinical characteristics. The authors present a case of a 20-year-old woman with a GCM. She was referred due to two episodes of generalized seizure. Computed tomography and magnetic resonance image demonstrated a heterogeneous multi-cystic lesion of $7\times5\times5$ cm size in the left frontal lobe and basal ganglia, and enhancing vascular structure abutting medial portion of the mass. These fingings suggested a diagnosis of GCM accompanying venous angioma. After left frontal craniotomy, transcortical approach was done. Total removal was accomplished and the postoperative course was uneventful. GCMs do not seem differ clinically, surgically or histopathologically from small cavernous angiomas, but imaging appearance of GCMs may be variable. The clinical, radiological feature and management of GCMs are described based on pertinent literature review.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.50 no.12
• /
• pp.889-898
• /
• 2022

In this paper, parallel computing method on the three-dimensional electromagnetic field is proposed. The present electromagnetic scattering analysis is conducted based on the time-harmonic vector wave equation and the finite element method. The edge-based element and 2^nd -order absorbing boundary condition are used. Parallelization of the elemental numerical integration and the matrix assemblage is accomplished by allocating the partitioned finite element subdomain for each processor. The graph partitioning library, METIS, is employed for the subdomain generation. The large sparse matrix computation is conducted by MUMPS, which is the parallel computing library based on the multi-frontal method. The accuracy of the present program is validated by the comparison against the Mie-series analytical solution and the results by ANSYS HFSS. In addition, the scalability is verified by measuring the speed-up in terms of the number of processors used. The present electromagnetic scattering analysis is performed for a perfect electric conductor sphere, isotropic/anisotropic dielectric sphere, and the missile configuration. The algorithm of the present program will be applied to the finite element and tearing method, aiming for the further extended parallel computing performance.

• Proceedings of the KWS Conference
• /
• 2003.11a
• /
• pp.156-158
• /
• 2003

An implicit finite element implementation for Leblond's transformation plasticity constitutive equations, which are widely used in welded steel structure is proposed in the framework of parallel computing. The implementation is based upon the multiplicative decomposition of deformation gradient and hyper elastic formulation. We examine the efficiency of parallel computation for the finite element analysis of a welded structure using domain-wise multi-frontal solver.

• Proceedings of the KWS Conference
• /
• 2004.05a
• /
• pp.273-275
• /
• 2004

A parallel multi-frontal solver is developed for finite element analysis of an arc-welding process, which entails phase evolution, heat transfer, and deformations of structure. We verify the code via comparison to a commercial code,SYSWELD. Attention is focused on the implementation of the parallel solver using MPI library, on the speedup by parallel computation, and on the effectiveness of the solver in welding application

• Proceedings of the KWS Conference
• /
• 2002.05a
• /
• pp.161-163
• /
• 2002

An implicit finite element implementation for Leblond's transformation plasticity constitutive equations, which are widely used in welded steel structure is proposed in the framework of parallel computing. The implementation is based upon the updated Lagrangian formulation. We examine the efficiency of parallel compuatation for the finite element analysis of a welded structure using multi-frontal solver.

• Science of Emotion and Sensibility
• /
• v.16 no.4
• /
• pp.527-534
• /
• 2013

In this study, we analyzed spatial-frequency relationship related brain function for change of the time during attentional visual stimulus through the analysis of Coherence. With experimentation about ERP(Event Related Potential)data, it revealed that change of the phase synchronization between different scalp locations at ${\theta}$, ${\alpha}$ band. ERP between left and right frontal lobes, between the frontal and central lobes showed the phase synchronization at the P100, N200, ERP between the frontal and occipital lobes showed the phase synchronization at the P300 related information of visual stimulus. Compared to STFT using the window of a fixed length, CWT is able to multi-resolution analysis with the adjustment of parameters of mother wavelet. Thus, coherence results with CWT was found to be effective for analysis of time-varying spatial-frequency relationship in ERP. The phase synchronization for inattentional visual stimulus was not observed.

• Journal of Information Processing Systems
• /
• v.9 no.1
• /
• pp.173-188
• /
• 2013

In Facial Expression Recognition Systems (FERS), only particular regions of the face are utilized for discrimination. The areas of the eyes, eyebrows, nose, and mouth are the most important features in any FERS. Applying facial features descriptors such as the local binary pattern (LBP) on such areas results in an effective and efficient FERS. In this paper, we propose an automatic facial expression recognition system. Unlike other systems, it detects and extracts the informative and discriminant regions of the face (i.e., eyes, nose, and mouth areas) using Haar-feature based cascade classifiers and these region-based features are stored into separate image files as a preprocessing step. Then, LBP is applied to these image files for facial texture representation and a feature-vector per subject is obtained by concatenating the resulting LBP histograms of the decomposed region-based features. The one-vs.-rest SVM, which is a popular multi-classification method, is employed with the Radial Basis Function (RBF) for facial expression classification. Experimental results show that this approach yields good performance for both frontal and near-frontal facial images in terms of accuracy and time complexity. Cohn-Kanade and JAFFE, which are benchmark facial expression datasets, are used to evaluate this approach.

• Journal of Biomedical Engineering Research
• /
• v.29 no.1
• /
• pp.17-24
• /
• 2008

The aim of this paper is to report our preliminary results of investigating the spatial focalization of Zen-meditation EEG (electroencephalograph) in alpha band (8-13 Hz). For comparison, the study involved two groups of subjects, practitioners (experimental group) and non-practitioners (control group). To extract EEG alpha rhythm, wavelet analysis was applied to multi-channel EEG signals. Normalized alpha-power vectors were then constructed from spatial distribution of alpha powers, that were classified by Fuzzy C-means based algorithm to explore various brain spatial characteristics during meditation (or, at rest). Optimal number of clusters was determined by correlation coefficients of the membership-value vectors of each cluster center. Our results show that, in the experimental group, the incidence of frontal alpha activity varied in accordance with the meditation stage. The results demonstrated three different spatiotemporal modules consisting with three distinctive meditation stages normally recognized by meditation practitioners. The frontal alpha activity in two groups decreased in different ways. Particularly, monotonic decline was observed in the control group, and the experimental group showed increasing results. The phenomenon might imply various mechanisms employed by meditation and relaxation in modulating parietal alpha.