• Journal of Korea Society of Digital Industry and Information Management
• /
• v.16 no.3
• /
• pp.49-58
• /
• 2020

Image interpolation, a technology that converts low resolution images into high resolution images, has been widely used in various image processing fields such as CCTV, web-cam, and medical imaging. This technique is based on the fact that the statistical distributions of the white Gaussian noise and the difference between the interpolated image and the original image is similar to each other. The proposed algorithm is composed of three steps. In first, the interpolated image is derived by random image interpolation. In second, we derive weighting functions that are used to apply non-local mean filtering. In the final step, the prediction error is corrected by performing non-local mean filtering by applying the selected weighting function. It can be considered as a post-processing algorithm to further reduce the prediction error after applying an arbitrary image interpolation algorithm. Simulation results show that the proposed method yields reasonable performance.

• Journal of the Korean Mathematical Society
• /
• v.38 no.3
• /
• pp.657-667
• /
• 2001

We propose a statistical interpolation approximate solution for a nonlinear stochastic integral equation of a stock price process. The proposed method has the order O(h$^2$) of local error under the weaker conditions of $\mu$ and $\sigma$ than those of Milstein' scheme.

• Proceedings of the KIEE Conference
• /
• 1997.07b
• /
• pp.414-417
• /
• 1997

We propose a decentralized $H_{\infty}$ state estimation method in the multisensor state estimation problem. The proposed method bounds the maximum energy gain from unknown external disturbances to the estimation errors in the suboptimal case. And we formulate the decentralized state estimation method in the general case of different global and local models using alternative gain equation of the $H_{\infty}$ state estimator which can calculate global state estimates from the the linear combination of local state estimates. In addition, the proposed update equation between global and local Riccati solutions can reduce unnecessary calculation burden efficiently.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.24 no.9
• /
• pp.1148-1156
• /
• 2000

The QUICK scheme for convection terms is modified for unstructured finite volume method by using linear reconstruction technique and validated through the computation of two well defined laminar flows. It uses two upstream grid points and one downstream grid point in approximating the convection terms. The most upstream grid point is generated by considering both the direction of flow and local grid line. Its value is calculated from surrounding grid points by using a linear construction method. Numerical error by the modified QUICK scheme is shown to decrease about 2.5 times faster than first order upwind scheme as grid size decreases. Computations are also carried out to see effects of the skewness and irregularity of grid on numerical solution. All numerical solutions show that the modified QUICK scheme is insensitive to both the skewness and irregularity of grid in terms of the accuracy of solution.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.9
• /
• pp.4429-4447
• /
• 2018

Local binary descriptors are well-suited for many real-time and/or large-scale computer vision applications, while their low computational complexity is usually accompanied by the limitation of performance. In this paper, we propose a new optimization framework, RLDB (Robust-LDB), to improve a typical region-based binary descriptor LDB (local difference binary) and maintain its computational simplicity. RLDB extends the multi-feature strategy of LDB and applies a more complete region-comparing configuration. A cascade bit selection method is utilized to select the more representative patterns from massive comparison pairs and an online learning strategy further optimizes descriptor for each specific patch separately. They both incorporate LDP (linear discriminant projections) principle to jointly guarantee the robustness and distinctiveness of the features from various scales. Experimental results demonstrate that this integrated learning framework significantly enhances LDB. The improved descriptor achieves a performance comparable to floating-point descriptors on many benchmarks and retains a high computing speed similar to most binary descriptors, which better satisfies the demands of applications.

• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.1
• /
• pp.1162-1170
• /
• 2001

This paper proposes a practical gain-scheduling control law considering robust stability and performance of Linear Parameter Varying(LPV) systems in the presence of nonlinearities and uncertainties. The proposed method introduces LMI-based pole placement synthesis and also associates with a recently developed fuzzy control system based on Takagei-Sugenos fuzzy model. The sufficient conditions for robust controller design of linearized local dynamics and robust stabilization of fuzzy control systems are reduced to a finite set of Linear Matrix inequalities(LMIs) and solved by using co-evolutionary algorithms. The proposed method is applied to the longitudinal acceleration control of high performance aircraft with linear and nonlinear simulations.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.34C no.5
• /
• pp.43-54
• /
• 1997

The objective of this paper is to present a controller-design method that can guarantee the global stability for nonlinear systems described by takagi-sugeno fuzzy models, and to apply the method to a typical nonlinear control problem. The presented method gives us a compensated fuzzy controller through the following major steps: First, if each local linear model of a given takagi-sugeno fuzzy system does not have the same input matrix, the method expands the system into the one with a method finds a takagi-sugeno fuzzy controller guaranteeing the global stability of the closed loop via solving relevant linear matrix inequalities. Compared to the conventional PDC (paralled distributed compensation) technique, the presented method has an advantage that trial-and-errors to check the global stability are not necessary. An illustrative simulation on the control of inverted pendulum is performed to demonstrate the applicability of the presented method, and its results show that a controller satisfying the global stability and robustness can be obtained by the method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.7
• /
• pp.3172-3193
• /
• 2018

Recently, several studies have shown that linear representation based approaches are very effective and efficient for image classification. One of these linear-representation-based approaches is the Collaborative representation (CR) method. The existing algorithms based on CR have two major problems that degrade their classification performance. First problem arises due to the limited number of available training samples. The large variations, caused by illumintion and expression changes, among query and training samples leads to poor classification performance. Second problem occurs when an image is partially noised (contiguous occlusion), as some part of the given image become corrupt the classification performance also degrades. We aim to extend the collaborative representation framework under limited training samples face recognition problem. Our proposed solution will generate virtual samples and intra-class variations from training data to model the variations effectively between query and training samples. For robust classification, the image patches have been utilized to compute representation to address partial occlusion as it leads to more accurate classification results. The proposed method computes representation based on local regions in the images as opposed to CR, which computes representation based on global solution involving entire images. Furthermore, the proposed solution also integrates the locality structure into CR, using Euclidian distance between the query and training samples. Intuitively, if the query sample can be represented by selecting its nearest neighbours, lie on a same linear subspace then the resulting representation will be more discriminate and accurately classify the query sample. Hence our proposed framework model the limited sample face recognition problem into sufficient training samples problem using virtual samples and intra-class variations, generated from training samples that will result in improved classification accuracy as evident from experimental results. Moreover, it compute representation based on local image patches for robust classification and is expected to greatly increase the classification performance for face recognition task.

• International Journal of Contents
• /
• v.7 no.4
• /
• pp.1-5
• /
• 2011

Physics based fluid animation schemes need large computation cost due to tremendous degree of freedom. Many researchers tried to reduce the cost for solving the large linear system that is involved in grid-based schemes. GPU based algorithms and advanced numerical analysis methods are used to efficiently solve the system. Other groups studied local operation methods such as SPH (Smoothed Particle Hydrodynamics) and LBM (Lattice Boltzmann Method) for enhancing the efficiency. Our method investigates this efficiency problem thoroughly, and suggests novel paradigm in fluid animation field. Rather than physics based simulation, we propose a robust boundary handling technique for procedural fluid animation. Our method can be applied to arbitrary shaped objects and potential fields. Since only local operations are involved in our method, parallel computing can be easily implemented.

• Ocean Science Journal
• /
• v.41 no.2
• /
• pp.97-104
• /
• 2006

A useful radiance-converting method was developed to convert the Landsat-7 ETM+thermal-infrared (TIR) band's radiance ($L_{{\lambda},L7/ETM+}$) to that of Landsat-5 TM TIR ($L_{{\lambda},L5/TM+})$ as: $L_{{\lambda},L5/TM}=0.9699{\times}L_{{\lambda},L7/ETM+}+0.1074\;(R^2=1)$. In addition, based on the radiance-converting equation and the linear relation between digital number (DN) and at-satellite radiance, a DN-converting equation can be established to convert DN value of the TIR band between Landsat-5 and Landsat-7. Via this method, it is easy to integrate Landsat-5 and Landsat-7 TIR data to retrieve the sea surface temperature (SST) in coastal waters on the basis of local empirical algorithms in which the radiance or DN of Lansat-5 and 7 TIR band is usually the only input independent variable. The method was employed in a local empirical algorithm in Daya Bay, China, to detect the thermal pollution of cooling water discharge from the Daya Bay nuclear power station (DNPS). This work demonstrates that radiance conversion is an effective approach to integration of Landsat-5 and Landsat-7 data in the process of a SST retrieval which is based on local empirical algorithms.