• Journal of KIISE:Software and Applications
• /
• v.36 no.11
• /
• pp.901-911
• /
• 2009

In this paper, we propose a construction technique of two-level composite gradient map to automatically track a face with large movement in successive frames. Our method is composed of three main steps. First, the gradient maps with two-level resolution are generated for fast convergence of active contour. Second, to recognize the variations of face between successive frames and remove the neighbor background, weighted composite gradient map is generated by combining the composite gradient map and difference mask of previous and current frames. Third, to prevent active contour from converging local minima, the energy slope is generated by using closing operation. In addition, the fast closing operation is proposed to accelerate the processing time of closing operation. For performance evaluation, we compare our method with previous active contour model-based face tracking methods using a visual inspection, robustness test and processing time. Experimental results show that our method can effectively track the face with large movement and robustly converge to the optimal position even in frames with complicated background.

• Journal of The Korean Astronomical Society
• /
• v.45 no.5
• /
• pp.117-125
• /
• 2012

We present $^{12}CO$ J = 2-1 line observations of G54.1+0.3, a composite supernova remnant with a mid-infrared (MIR) loop surrounding the central pulsar wind nebula (PWN). We map an area of $12^{\prime}{\times}9^{\prime}$ around the PWN and its associated MIR loop. We confirm two velocity components that have been proposed to be possibly interacting with the PWN/MIR-loop; the +53 km $s^{-1}$ cloud, which appears in contact with the eastern boundary of the PWN and the +23 km $s^{-1}$ cloud, which has CO emission coincident with the MIR loop. However, we have not found a direct evidence for the interaction in either of these clouds. Instead, we detected an 5'-long arc-like cloud at +15-+23 km $s^{-1}$ with a systematic velocity gradient of ~3 km $s^{-1}$ $arcmin^{-1}$ and broad-line emitting CO gas with widths (FWHM) of ${\leq}7km\;s^{-1}$ in the western interior of the supernova remnant. We discuss their association with the supernova remnant.

• Applied Biological Chemistry
• /
• v.32 no.2
• /
• pp.85-90
• /
• 1989

High resolution two-dimensional (2-D) electrophoresis with isoelectrofocusing in the first dimension and electrophoresis in sodium dodecyl sulfate in acrylamide gradient gels in the second dimension has been used to produce maps of proteins, extracted from rice seeds with 2% sodium dodecyl sulfate/5% 2-mercaptoethanol. Six rice cultivars-three Japonica types and three Tongil(high-yielding) types-at six maturities were studied. Composite map was constructed and more than 300 polypeptide spots were counted in the pH range of $5.2{\sim}8.3$ and molecular range of $20,000{\sim}100,000$. Vast differences were observed between varieties and between maturities in the maps.

• Steel and Composite Structures
• /
• v.47 no.6
• /
• pp.759-779
• /
• 2023

The paper proposes two hybrid metaheuristic optimization and artificial neural network (ANN) methods for the close prediction of the ultimate axial compressive capacity of concentrically loaded concrete filled double skin steel tube (CFDST) columns. Two metaheuristic optimization, namely genetic algorithm (GA) and particle swarm optimization (PSO), approaches enable the dynamic training architecture underlying an ANN model by optimizing the number and sizes of hidden layers as well as the weights and biases of the neurons, simultaneously. The former is termed as GA-ANN, and the latter as PSO-ANN. These techniques utilize the gradient-based optimization with Bayesian regularization that enhances the optimization process. The proposed GA-ANN and PSO-ANN methods construct the predictive ANNs from 125 available experimental datasets and present the superior performance over standard ANNs. Both the hybrid GA-ANN and PSO-ANN methods are encoded within a user-friendly graphical interface that can reliably map out the accurate ultimate axial compressive capacity of CFDST columns with various geometry and material parameters.