• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.18 no.8
• /
• pp.98-103
• /
• 2019

A more accurate method of feature point extraction and matching for three-dimensional reconstruction using low-resolution images of crops is proposed herein. This method is important in basic computer vision. In addition to three-dimensional reconstruction from exact matching, map-making and camera location information such as simultaneous localization and mapping can be calculated. The results of this study suggest applicable methods for low-resolution images that produce accurate results. This is expected to contribute to a system that measures crop growth condition.

• Journal of Multimedia Information System
• /
• v.8 no.4
• /
• pp.203-210
• /
• 2021

Deep leaning convolutional neural networks (CNN) have successfully been applied to image super-resolution (SR). Despite their great performances, SR techniques tend to focus on a certain upscale factor when training a particular model. Algorithms for single model multi-scale networks can easily be constructed if images are upscaled prior to input, but sub-pixel convolution upsampling works differently for each scale factor. Recent SR methods employ multi-scale and multi-path learning as a solution. However, this causes unshared parameters and unbalanced parameter distribution across various scale factors. We present a multi-scale single-path upsample module as a solution by exploiting the advantages of sub-pixel convolution and interpolation algorithms. The proposed model employs sub-pixel convolution for the highest scale factor among the learning upscale factors, and then utilize 1-dimension interpolation, compressing the learned features on the channel axis to match the desired output image size. Experiments are performed for the single-path upsample module, and compared to the multi-path upsample module. Based on the experimental results, the proposed algorithm reduces the upsample module's parameters by 24% and presents slightly to better performance compared to the previous algorithm.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.372-375
• /
• 2003

The incidence of blindness resulting from diabetic retinopathy has significantly increased despite the intervention of insulin to control diabetes mellitus. Early signs are microaneurysms, exudates, intraretinal hemorrhages, cotton wool patches, microvascular abnormalities, and venous beading. Advanced stages include neovascularization, fibrous formations, preretinal and vitreous microhemorrhages, and retinal detachment. Microaneurysm count is important because it is an indicator of retinopathy progression. The purpose of this paper is to apply data mining to detect diabetic retinopathy patterns in routine fundus fluorescein angiography. Early symptoms are of principal interest and therefore the emphasis is on detecting microaneurysms rather than vessel tortuosity. The analysis does not involve image-recognition algorithms. Instead, mathematical filtering isolates microaneurysms, microhemorrhages, and exudates as objects of disconnected sets. A neural network is trained on their distribution to return fractal dimension. Hausdorff and box counting dimensions grade progression of the disease. The field is acquired on fluorescein angiography with resolution superior to color ophthalmoscopy, or on patterns produced by physical or mathematical simulations that model viscous fingering of water with additives percolated through porous media. A mathematical filter and neural network perform the screening process thereby eliminating the time consuming operation of determining fractal set dimension in every case.

• Journal of the Korean Institute of Navigation
• /
• v.16 no.3
• /
• pp.77-85
• /
• 1992

Camera arrangement for depth and image correspondence is very important to the computer vision. Two conventional comera arrangements for stereo computer vision are lateral model and axial motion model. In this paper, using the axial motion stereo camera model, the algorithm for camera focal length measurement and the surface smoothness with the radiance-irradiance is proposed fro 3-dimensional image correspondence on stereo computer vision. By adapting the above algorithm, camera focal length can be measured precisely and the resolution of 3-dimensional image correspondence has been improved comparing to that of the axial motion model without the radiance-irradiance relation.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2004.04a
• /
• pp.239-243
• /
• 2004

It does not exist almost that Most satellite image has both high spectral and spatial resolution. In order to apply the satellite image for to be actual, we need numerical and analytical technique development to improve the resolution. Specially in the function of solid illustration, we represent the solid image through the image generation to solid screen. The main function includes magnification, reduction, screen center movement, Panning, territory magnification. The method to process the image includes histogram and contrast modulation. Afterwards, we will develop the function includes 3-dimension cursor to control the elevation position and calculate the ground coordination automatically. There is the layer control includes the representation and the edition of 3D vector, extraction the Z value by On the Ground and digital elevation.

• Economic and Environmental Geology
• /
• v.33 no.1
• /
• pp.41-50
• /
• 2000

Geo-radar survey which has the advantage of high-resolution and relatively fast survey has been widely used for engineering and environmental problems. Three-dimensional effects have to be considered in the interpretation of geo-radar for high-resolution. However, there exists a trouble on the analysis of the three dimensional effects. To solve this problem an efficient three dimension numerical modeling algorithm is needed. Numerical radar modeling in three dimensional case requires large memory and long calculating time. In this paper, a finite difference method time domain solution to Maxwell's equations for simulating electromagnetic wave propagation in three dimensional media was developed to make economic algorithm which requires smaller memory and shorter calculating time. And in using boundary condition Liao absorption boundary. The numerical result of cross-hole radar survey for tunnel is compared with real data. The two results are well matched. To prove application to three dimensional analysis, the results with variation of tunnel's incident angle to survey cross-section and the result when the tunnel is parallel to the cross-section were examined. This algorithm is useful in various geo-radar survey and can give basic data to develop dat processing and inversion program.

• The Korean Journal of Nuclear Medicine
• /
• v.38 no.2
• /
• pp.205-208
• /
• 2004

The two major classes of magnetic resonance (MR) contrast agents are paramagnetic contrast agents, usually based on chelates of gadolinium generating T1 positive signal enhancement, and super-paramagnetic contrast agents that use mono- or polycrystalline iron oxide to generate strong T2 negative contrast in MR images. These paramagnetic or super-paramagnetic complexes are used to develop new contrast agents that can target the specific molecular marker of the cells or tan be activated to report on the physiological status or metabolic activity of biological systems. In molecular imaging science, MR imaging has emerged as a leading technique because it provides high-resolution three-dimension maps of the living subject. The future of molecular MR imaging is promising as advancements in hardware, contrast agents, and image acquisition methods coalesce to bring high resolution in vivo imaging to the biochemical sciences and to patient care.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.17 no.7 s.94
• /
• pp.1731-1739
• /
• 1993

An application of Scanning Tunneling Microscopy(STM) is investigated for the measurement of 3-dimensional profiles of the macro-machined patterns of which critical dimensions lie in the range of submicrometers. Special emphasis of this investigation is given to extending the measuring ranges of STM upto the order of several micrometers while maintaining superb nanometer measuring resolution. This is accomplished by correcting hysteresis effects of piezoelectric actuators by using non-linear compensation models. Detailed aspects of design and control of a prototype measurement system are described with some actual measuring examples in which fine It patterns can successfully be traced with a resolution of 1 nanometer over a surface range of $4{\times}2$ micrometers.

• Journal of Integrative Natural Science
• /
• v.4 no.4
• /
• pp.278-281
• /
• 2011

We discuss an application of 'restrictions on the entries of the maps in the minimal free resolution' and '$SC_r$-condition of modules', and give an alternative proof of the following result of Foxby: Let M be a finitely generated module of dimension over a Noetherian local ring (A,m). Suppose that $\hat{A}$ has no embedded primes. If A is not Gorenstein, then ${\mu}_i(m,A){\geq}2$ for all i ${\geq}$ dimA.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.17 no.1
• /
• pp.142-148
• /
• 2014

The mirror which is considered in designing a MFD is off-axis primary one and its dimension is wide 556mm height 345mm. The MFD(Mirror Fixation Device) load specification is generated for the high resolution mirror. The optical WFEs for unit loads are calculated from mirror sensitivity analysis and they are compared with allocated allowable optical WFE. The parasite load for the MFD is calculated from their comparison. The MFD compliant with the parasite load is designed.