• Journal of Navigation and Port Research
• /
• v.32 no.5
• /
• pp.355-361
• /
• 2008

Stereo matching is one of the most active research areas in computer vision. In this paper, we propose a stereo matching scheme using genetic algorithm for object depth recognition. The proposed approach considers the matching environment as an optimization problem and finds the optimal solution by using an evolutionary strategy. Accordingly, genetic operators are adapted for the circumstances of stereo matching. An individual is a disparity set. Horizontal pixel line of image is considered as a chromosome. A cost function is composed of certain constraints which are commonly used in stereo matching. Since the cost function consists of intensity, similarity and disparity smoothness, the matching process is considered at the same time in each generation. The LoG(Laplacian of Gaussian) edge is extracted and used in the determination of the chromosome. We validate our approach with experimental results on stereo images.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.46 no.10
• /
• pp.798-805
• /
• 2018

This study introduces an adaptive design of experiment (DoE) approach for the hypersonic shock-tunnel testing. A series of experiments are conducted to model the pitch moment coefficient of a cone as the function of the angle of attack and the pitch rate. An algorithm to construct the trajectory of the test model from the images obtained by the high-speed camera is developed to effectively analyze multiple time series experimental data. An adaptive DoE procedure to determine the experimental point based on the analysis results of the past experiments using the algorithm is proposed.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.16 no.1
• /
• pp.1-9
• /
• 1996

Many signal-processing techniques have been found to be useful in ultrasonic and nondestructive evaluation. Among the most popular techniques are signal averaging, spatial compounding, matched filters and homomorphic processing. One of the significant new process is split-spectrum processing(SSP), which can be equally useful in signal-to-noise ratio(SNR) improvement and grain characterization in several specimens. The purpose of this paper is to explore the utility of SSP in ultrasonic NDE. A wide variety of engineering problems are reviewed, and suggestions for implementation of the technique are provided. SSP uses the frequency-dependent response of the interfering coherent noise produced by unresolvable scatters in the resolution range cell of a transducer. It is implemented by splitting the frequency spectrum of the received signal by using gaussian bandpass filter. The theoretical basis for the potential of SSP for grain characterization in SUS 304 material is discussed, and some experimental evidence for the feasibility of the approach is presented. Results of SNR enhancement in signals obtained from real four samples of SUS 304. The influence of various processing parameters on the performance of the processing technique is also discussed. The minimization algorithm, which provides an excellent SNR enhancement when used either in conjunction with other SSP algorithms like polarity-check or by itself, is also presented.

• Journal of Korea Multimedia Society
• /
• v.12 no.1
• /
• pp.16-25
• /
• 2009

In the car environment that the first priority is a safety problem, the large vocabulary isolated word recognition system with POI domain is required as the optimal HMI technique. For the telematics terminal with a highly limited processing time and memory capacity, it is impossible to process more than 100,000 words in the terminal by the general speech recognition methods. Therefore, we proposed phoneme recognizer using the phonetic GMM and also PDM Levenshtein distance with multi-layer architecture for the POI recognition of telematics terminal. By the proposed methods, we obtained high performance in the telematics terminal with low speed processing and small memory capacity. we obtained the recognition rate of maximum 94.8% in indoor environment and of maximum 92.4% in the car navigation environments.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39A no.3
• /
• pp.149-154
• /
• 2014

The cross-correntropy concept can be expressed with inner products of two different probability density functions constructed by Gaussian-kernel density estimation methods. Blind algorithms based on the maximization of the cross-correntropy (MCC) and a symbol set of randomly generated N samples yield superior learning performance, but have a huge computational complexity in the update process at the aim of weight adjustment based on the MCC. In this paper, a method of reducing the computational complexity of the MCC algorithm that calculates recursively the gradient of the cross-correntropy is proposed. The proposed method has only O(N) operations per iteration while the conventional MCC algorithms that calculate its gradients by a block processing method has $O(N^2)$. In the simulation results, the proposed method shows the same learning performance while reducing its heavy calculation burden significantly.

• The Korean Journal of Applied Statistics
• /
• v.23 no.3
• /
• pp.595-607
• /
• 2010

This paper addresses the problem of reducing the speckle noise in SAR images by wavelet transformation, using a non-local means(NLM) filter originated for Gaussian noise removal. Log-transformed SAR image makes multiplicative speckle noise additive. Thus, non-local means filtering and wavelet thresholding are used to reduce the additive noise, followed by an exponential transformation. NLM filter is an image denoising method that replaces each pixel by a weighted average of all the similarly pixels in the image. But the NLM filter takes an acceptable amount of time to perform the process for all possible pairs of pixels. This paper, also proposes an alternative strategy that uses the t-test more efficiently to eliminate pixel pairs that are dissimilar. Extensive simulations showed that the proposed filter outperforms many existing filters terms of quantitative measures such as PSNR and DSSIM as well as qualitative judgments of image quality and the computational time required to restore images.

• Korean Journal of Materials Research
• /
• v.23 no.8
• /
• pp.447-452
• /
• 2013

Recently, products that a have 3-dimensional(3D) micro structure have been in wide use. To fabricate these 3D micro structures, several methods, such as stereo lithography, reflow process, and diffuser lithography, have been used. However, these methods are either very complicated, have limitations in terms of patterns dimensions or need expensive components. To overcome these limitations, we fabricated various 3D micro structures in one step using a pair of diffusers that diffract the incident beam of UV light at wide angles. In the experiment, we used positive photoresist to coat the Si substrate. A pair of diffusers(ground glass diffuser, opal glass diffuser) with Gaussian and Lambertian scattering was placed above the photomask in the passage of UV light in the photolithography equipment. The incident rays of UV light diffracted twice at wider angles while passing through the diffusers. After exposure, the photoresist was developed fabricating the desired 3D micro structure. These micro structures were analyzed using FE-SEM and 3D-profiler data. As a result, this dual diffuser lithography(DDL) technique enabled us to fabricate various microstructures with different dimensions by just changing the combination of diffusers, making this technology an efficient alternative to other complex techniques.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.4
• /
• pp.31-37
• /
• 2004

Wavelet transform is a useful tool for analysis and process of image. This showed good performance in image compression and noise reduction. Wavelet coefficients can be effectively modeled by hidden Markov tree(HMT) model. However, in application of HMT model to image interpolation, training procedure is needed. Moreover, the parameters obtained from training procedure do not match input image well. In this paper, the structure of HMT is used for image interpolation, and the parameters of HMT are obtained from statistical characteristics across wavelet subbands without training procedure. In the proposed method, wavelet coefficient is modeled as Gaussian mixture model(GMM). In GMM, state transition probabilities are determined from statistical transition characteristic of coefficient across subbands, and the variance of each state is estimated using the property of exponential decay of wavelet coefficient. In simulation, the proposed method shows improvement of performance compared with conventional bicubic method and the method using HMT model with training.

• Journal of the Korean Magnetics Society
• /
• v.13 no.2
• /
• pp.47-52
• /
• 2003

Ferromagnetic tunnel junctions were fabricated by dc magnetron sputtering and plasma oxidation process. The local transport properties of the ferromagnetic tunnel junctions were studied using contact-mode Atomic Force Microscopy (AFM) and the local current-voltage analysis. Tunnel junctions with the structure of sub./Ta/Cu/Ta/NiFe/Cu/Mn$\_$75/Ir$\_$25//Co$\_$70/Fe$\_$30//Al-oxide were prepared on thermally oxidized Si wafers. Al-oxide layers were formed with microwave excited plasma using radial line slot antenna (RLSA) for 5 and 7 sec. Kr gas was used as the inert gas mixed with $O_2$ gas for the plasma oxidization. No correlation between topography and current image was observed while they were measured simultaneously. The local current distribution was well identified with the distribution of local barrier height. Assuming the gaussian distribution of the local barrier height, the ferromagnetic tunnel junction with longer oxidation time was well fitted with the experimental results. As contrast, in the case of the shorter time oxidation junction, the current mainly flow through the low barrier height area for its insufficient oxygen. Such leakage current might result in the decrease of tunnel magnetoresistance (TMR) ratio.

• Journal of the Korea Convergence Society
• /
• v.8 no.10
• /
• pp.45-52
• /
• 2017

Drifter is an equipment for observing the characteristics of seawater in the ocean, and it can be used to predict effluent oil diffusion and to observe ocean currents. In this paper, we design models or the prediction of drifter trajectory using machine learning. We propose methods for estimating the trajectory of drifter using support vector regression, radial basis function network, Gaussian process, multilayer perceptron, and recurrent neural network. When the propose mothods were compared with the existing MOHID numerical model, performance was improve on three of the four cases. In particular, LSTM, the best performed method, showed the imporvement by 47.59% Future work will improve the accuracy by weighting using bagging and boosting.