• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.10 no.2
• /
• pp.95-100
• /
• 2010

This paper proposes a new spatial regularization of Fisher linear discriminant analysis (LDA) to reduce the overfitting due to small size sample (SSS) problem in face recognition. Many regularized LDAs have been proposed to alleviate the overfitting by regularizing an estimate of the within-class scatter matrix. Spatial regularization methods have been suggested that make the discriminant vectors spatially smooth, leading to mitigation of the overfitting. As a generalized version of the spatially regularized LDA, the proposed regularized LDA utilizes the non-uniformity of spatial correlation structures in face images in adding a spatial smoothness constraint into an LDA framework. The region-dependent spatial regularization is advantageous for capturing the non-flat spatial correlation structure within face image as well as obtaining a spatially smooth projection of LDA. Experimental results on public face databases such as ORL and CMU PIE show that the proposed regularized LDA performs well especially when the number of training images per individual is quite small, compared with other regularized LDAs.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.8 no.4
• /
• pp.13-18
• /
• 2012

In this paper, we propose a noise estimation method for noise reduction. It is based on block and pixel-based noise estimation. We assume that an input image is contaminated by the additive white Gaussian noise. Thus, we use an adaptive Gaussian filter and estimate the amount of noise. It computes the standard deviation of each block and estimation is performed on pixel-based operation. The proposed algorithm divides an input image into blocks. This method calculates the standard deviation of each block and finds the minimum standard deviation block. The block in flat region shows well noise and filtering effects. Blocks which have similar standard deviation are selected as test blocks. These pixels are filtered by adaptive Gaussian filtering. Then, the amount of noise is calculated by the standard deviation of the differences between noisy and filtered blocks. Experimental results show that our proposed estimation method has better results than those by existing estimation methods.

• Proceedings of the Korean Society of Agricultural Engineers Conference
• /
• 2000.10a
• /
• pp.365-370
• /
• 2000

Sea dike construction for the tidal flat reclamation works in estuary and coast may change the characteristics of tidal motion and wave conditions in the region. In turn, a new hydraulic condition provides the impacts on sediment transport pattern and forms a new morphological environment. Also, morphological changes during the closure works of sea dike are closely related with a safy of sea dike. Therefore, the prediction of morphological changes is required secure the safe closure work and the economic design of sea dikes. To investigate morphological changes due to sea dike construction, hydrodynamic changes of tides and waves have to be evaluated, then sediment transport and sea bottom changes are computed. Mathematical modelling is required for representation of interrelation of tidal motion, wave and sediment transport. In this study, numerical model MORSYS is applied to compute the hydrodynamics and morphological changes around the closure gap for Saemankuem dike. This model allows a flexible integration of the module for waves, currents, sediment transport and bottom changes.

• International Journal of Control, Automation, and Systems
• /
• v.3 no.1
• /
• pp.87-99
• /
• 2005

We present in this paper the stabilization (tracking) with motion planning of the six independent configurations of a mini unmanned areal vehicle equipped with four streamlined rotors. Naturally, the yaw-dynamic can be stabilized without difficulties and independently of other motions. The remaining dynamics are linearly approximated around a small roll and pitch angles. It will be shown that the system presents a flat output that is likely to be useful in the motion generation problem. The tracking feedback controller is based on receding horizon point to point steering. The resulting controller involves the lift (collective) time derivative for what flatness and feedback linearization are used. Simulation tests are performed to progress in a region with approximatively ten-meter-buildings.

• Journal of the Korean Ceramic Society
• /
• v.30 no.12
• /
• pp.1029-1038
• /
• 1993

The microstructures of aluminas, included of dissolved CaO as $\alpha$-alumina seeded pseudo-boehmite hydrosol was gelled in plaster mold and doped of MgO as dipping of calcines(120$0^{\circ}C$-2h) into Mg-nitrate solution, were compared to the one of which additives are excluded during the gellation. It was formed the boundary layer of 300~350${\mu}{\textrm}{m}$ distance from surface to the inside, containing of approximately 500ppm CaO by dissolved Ca from plaster mold. As the MgO addition to the boundary layer with dissolved CaO, the microstructure of the layer was uniformed and inhibited the grian growth, compared to one of that additives be excluded specimen and of MgO doped-inside region. This result was considered as abnormal grain growth and effect of flat boundary formation be appeared by effects of dissolved CaO, were decreased by MgO co-doping.

• Proceedings of the IEEK Conference
• /
• 2000.07a
• /
• pp.482-485
• /
• 2000

A modified watershed transform is proposed which is context-free marker-controlled and minima imposition-free to reduce the over-segmentation and to speedup the transform. In contrast to the conventional methods in which a priori knowledge, such as flat zones, zones of homogeneous texture, and morphological distance, is required for marker extraction, context-free marker extraction is proposed by using the attention operator based on the GST (generalized symmetry transform). By using the context-free marker, the proposed watershed transform exploit marker-constrained labeling to speedup the computation and to reduce the over-segmentation by eliminating the unnecessary geodesic reconstruction such as the minima imposition and thereby eliminating the necessity of the post-processing of region merging. The simulation results show that the proposed method can extract context-free markers inside the objects from the complex background that includes multiple objects and efficiently reduces over-segmentation and computation time.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.56 no.11
• /
• pp.1930-1936
• /
• 2007

According to previously published paper the phase advance angle is adopted to the BLDC motor drive with high speed. The report proposed describes the optimum algorism that phase current is in phase with the initial flat region of back EMF. This report studies the need of more leading phase advance angle compared with in phase concept between phase current and back EMF. In case of high reactance this report proposes the more phase advance angle than in phase. The test results more rms value of phase current and output power due to more phase advance angle than in phase. It will be helped the high power operation of BLDC motor at high speed.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.3 no.1
• /
• pp.46-52
• /
• 1998

This paper describes a current-shaping method for the production of constant torque of SRM under the nonlinear magnetic saturation condition. A current detection technique in the inductance increasing region and an approximation technique for modeling of nonlinear inductance profile are adopted. In the proposed system, a single switching angle control and voltage control is used to shape the current waveform for the generation of flat torque at any given load condition. Finally the validity of the proposed method was verified using a constructed 3HP 6/4 SRM.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.9 no.1
• /
• pp.18-24
• /
• 1984

Calculation of error probabilities for a coherent phase-shilft keyed communication system operating in a transionospheric scintillation channel is accomplished by means of the Gauss-quadrature integration formula. The channel model used, patterned after Rino's work, is slowly flat fading wherein the envelope of the received signal is modeled as the envelope of correlated Gaussian quadrature random processes. The error probability for the scintillation channel is calculated using actual ionospheric scintillation data for transmission in the UHF region(30-300MHz).

• Advances in aircraft and spacecraft science
• /
• v.1 no.4
• /
• pp.443-454
• /
• 2014

An experimental study was conducted to investigate the effect of Reynolds number on compressible convex-corner flows, which correspond to an upper surface of a deflected flap of an aircraft wing. The flow is naturally developed along a flat plate with two different lengths, resulting in different incoming boundary layer thicknesses or Reynolds numbers. It is found that boundary layer Reynolds number, ranging from $8.04{\times}10^4$ to $1.63{\times}10^5$, has a minor influence on flow expansion and compression near the corner apex in the transonic flow regime, but not for the subsonic expansion flow. For shock-induced separated flow, higher peak pressure fluctuations are observed at smaller Reynolds number, corresponding to the excursion phenomena and the shorter region of shock-induced boundary layer separation. An explicit correlation of separation length with deflection angle is also presented.