• 한국멀티미디어학회논문지
• /
• 제24권2호
• /
• pp.178-185
• /
• 2021

Three-dimensional high-resolution magnetic resonance imaging (MRI) provides fine-level anatomical information for disease diagnosis. However, there is a limitation in obtaining high resolution due to the long scan time for wide spatial coverage. Therefore, in order to obtain a clear high-resolution(HR) image in a wide spatial coverage, a super-resolution technology that converts a low-resolution(LR) MRI image into a high-resolution is required. In this paper, we propose a super-resolution technique through filter learning based on information on the surrounding gradient information in 3D space from 3D MRI images. In the learning step, the gradient features of each voxel are computed through eigen-decomposition from 3D patch. Based on these features, we get the learned filters that minimize the difference of intensity between pairs of LR and HR images for similar features. In test step, the gradient feature of the patch is obtained for each voxel, and the filter is applied by selecting a filter corresponding to the feature closest to it. As a result of learning 100 T1 brain MRI images of HCP which is publicly opened, we showed that the performance improved by up to about 11% compared to the traditional interpolation method.

• Wind and Structures
• /
• 제19권3호
• /
• pp.249-270
• /
• 2014

Through comparing the mean wind profiles observed overland during the passages of four typhoons, and the gradient wind speeds calculated based on the sea level pressure data provided by a numerical model, the present paper discusses, (a) whether the gradient balance is a valid assumption to estimate the wind speed in the height range of 1250 m ~ 1750 m, which is defined as the upper-level mean wind speed, in a tropical cyclone over land, and (b) if the super-gradient feature is systematically observed below the height of 1500 m in the tropical cyclone wind field over land. It has been found that, (i) the gradient balance is a valid assumption to estimate the mean upper-level wind speed in tropical cyclones in the radial range from the radius to the maximum wind (RMW) to three times the RMW, (ii) the super-gradient flow dominates the wind field in the tropical cyclone boundary layer inside the RMW and is frequently observed in the radial range from the RMW to twice the RMW, (iii) the gradient wind speed calculated based on the post-landfall sea level pressure data underestimates the overall wind strength at an island site inside the RMW, and (iv) the unsynchronized decay of the pressure and wind fields in the tropical cyclone might be the reason for the underestimation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권5호
• /
• pp.1141-1162
• /
• 2024

Humidity is an important parameter in meteorology and is closely related to weather, human health, and the environment. Due to the limitations of the number of observation stations and other factors, humidity data are often not as good as expected, so high-resolution humidity fields are of great interest and have been the object of desire in the research field and industry. This study presents a novel super-resolution algorithm for humidity fields based on the Wasserstein generative adversarial network(WGAN) framework, with the objective of enhancing the resolution of low-resolution humidity field information. WGAN is a more stable generative adversarial networks(GANs) with Wasserstein metric, and to make the training more stable and simple, the gradient cropping is replaced with gradient penalty, and the network feature representation is improved by sub-pixel convolution, residual block combined with convolutional block attention module(CBAM) and other techniques. We evaluate the proposed algorithm using ERA5 relative humidity data with an hourly resolution of 0.25°×0.25°. Experimental results demonstrate that our approach outperforms not only conventional interpolation techniques, but also the super-resolution generative adversarial network(SRGAN) algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권4호
• /
• pp.2109-2123
• /
• 2017

This paper presents a super-resolution reconstruction method based on sparse representation for two-dimensional bar code images. Considering the features of two-dimensional bar code images, Kirsch and LBP (local binary pattern) operators are used to extract the edge gradient and texture features. Feature extraction is constituted based on these two features and additional two second-order derivatives. By joint dictionary learning of the low-resolution and high-resolution image patch pairs, the sparse representation of corresponding patches is the same. In addition, the global constraint is exerted on the initial estimation of high-resolution image which makes the reconstructed result closer to the real one. The experimental results demonstrate the effectiveness of the proposed algorithm for two-dimensional bar code images by comparing with other reconstruction algorithms.

• 대한기계학회논문집B
• /
• 제31권1호
• /
• pp.40-50
• /
• 2007

The present contribution describes the application of elliptic-blending second moment closure to predict the gas cooling process of turbulent super-critical carbon dioxide flow in a square cross-sectioned duct. The gas cooling process under super-critical state experiences a drastic change in thermodynamic and transport properties. Redistributive terms in the Reynolds stress and turbulent heat flux equations are modeled by an elliptic-blending second moment closure in order to represent strongly non-homogeneous effects produced by the presence of walls. The main feature of Durbin's elliptic relaxation second moment closure that accounts for the nonlocal character of pressure-velocity gradient correlation and the near-wall inhomogeneity guaranteed by the elliptic blending second moment closure.

• 한국생산제조학회지
• /
• 제7권6호
• /
• pp.49-56
• /
• 1998

Super precision working technique and machine tool have been continually developed thanks to advanced electronic field. To obtain good result. it is necessary to investigate surface in grinding with $mu extrm{m}$ level. There were quite many researches to satisfy these demands by using non-contact methods through the computer vision. In this study, the texture of working surface was analyzed. co-occurrence matrices was obtained from the surface roughness. Texture parameter was obtained using position operator composed of $ heta$, d according to variation of angle direction and distance. As a result, it was found that surface texture was more affected by direction($\theta$) than distance(d).