• Journal of Digital Contents Society
• /
• v.19 no.6
• /
• pp.1197-1205
• /
• 2018

In this paper, we perform Single Image Super Resolution(SISR) for acquired images of EOTS or IRST from naval combat system. In order to conduct super resolution, we use Generative Adversarial Networks(GANs), which consists of a generative model to create a super-resolution image from the given low-resolution image and a discriminative model to determine whether the generated super-resolution image is qualified as a high-resolution image by adjusting various learning parameters. The learning parameters consist of a crop size of input image, the depth of sub-pixel layer, and the types of training images. Regarding evaluation method, we apply not only general image quality metrics, but feature descriptor methods. As a result, a larger crop size, a deeper sub-pixel layer, and high-resolution training images yield good performance.

• Journal of Arbitration Studies
• /
• v.25 no.3
• /
• pp.155-184
• /
• 2015

This paper addresses the question of what kinds of dispute resolution choices can effectively handle complex intellectual property disputes, given the rising importance of IP, the increasing frequency and complexity of IP disputes, and the lack of research on dispute resolution strategies. For this analysis, the study adopted the analytic hierarchy process approach, which covers complex, multi-criteria decision problems, to quantify the expert's judgments on IP dispute resolution choice. Its results show that the effectiveness of resolution methods differs, depending on the type of IP dispute classified into seven issues, which are (i) requirement for validity of IP right, (ii) range and duration of IP right, (iii) transfer of IP right, (iv) licensing, (v) use of IP right, (vi) declaration of IP infringement, and (vii) estimation of damage. The disputes over IPR ownership and IP infringement remain challenging issues in due to strong requirement of the cross-border enforcement. Alternative dispute resolution (ADR), especially arbitration, is determined to be a more effective method to deal with international IP disputes, but various advanced types of ADR techniques should be further developed to deal with the increasing complexity of IP disputes.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2328-2344
• /
• 2022

2D human pose estimation still faces difficulty in low-resolution images. Most existing top-down approaches scale up the target human bonding box images to the large size and insert the scaled image into the network. Due to up-sampling, artifacts occur in the low-resolution target images, and the degraded images adversely affect the accurate estimation of the joint positions. To address this issue, we propose a multi-resolution input feature fusion network for human pose estimation. Specifically, the bounding box image of the target human is rescaled to multiple input images of various sizes, and the features extracted from the multiple images are fused in the network. Moreover, we introduce a guiding channel which induces the multi-resolution input features to alternatively affect the network according to the resolution of the target image. We conduct experiments on MS COCO dataset which is a representative dataset for 2D human pose estimation, where our method achieves superior performance compared to the strong baseline HRNet and the previous state-of-the-art methods.

• Korean Journal of Remote Sensing
• /
• v.39 no.4
• /
• pp.395-407
• /
• 2023

Super-resolution (SR) has great significance in image processing because it enables downstream vision tasks with high spatial resolution. Recently, SR studies have adopted deep learning networks and achieved remarkable SR performance compared to conventional example-based methods. Deep-learning-based SR models generally require low-resolution (LR) images and the corresponding high-resolution (HR) images as training dataset. Due to the difficulties in obtaining real-world LR-HR datasets, most SR models have used only HR images and generated LR images with predefined degradation such as bicubic downsampling. However, SR models trained on simple image degradation do not reflect the properties of the images and often result in deteriorated SR qualities when applied to real-world images. In this study, we propose an image degradation model for HR satellite images based on the modulation transfer function (MTF) of an imaging sensor. Because the proposed method determines the image degradation based on the sensor properties, it is more suitable for training SR models on remote sensing images. Experimental results on HR satellite image datasets demonstrated the effectiveness of applying MTF-based filters to construct a more realistic LR-HR training dataset.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.17 no.2
• /
• pp.53-58
• /
• 2013

Purpose: To optimize correction method for SPECT/CT, image quality consisting of resolution and contrast was evaluated using three radioisotopes ($^{99m}Tc$, $^{201}Tl$ and $^{131}I$) and three different correction methods; attenuation correction (AC), scatter correction (SC) and both attenuation and scatter correction (ACSC). Materials and Methods: Images were acquired with a SPECT/CT scanner and a conventional CT protocol with an OESM reconstruction algorithm (2 iterations and 10 subsets). For resolution measurement, fixed radioactivity (2.22 kBq) was infused into a spatial resolution phantom and full width at half maximum (FWHM) was measured using a vendor-provided software. For contrast evaluation, radioactive source with a ratio of 1:8 to background was filled in a Flanged Jaszczak phantom and percent contrast (%) were calculated. All the parameters for image quality were compared with non-correction (NC) method. Results: As compared with NC, image resolution of all three isotopes were significantly improved by AC and ACSC, not by SC. In particular, ACSC showed better resolution than AC alone for $^{99m}Tc$ and $^{201}Tl$. Image contrast of all three radioisotopes in a sphere with the largest diameter were enhanced by all correction methods. ACSC showed the highest contrast in all three radioisotopes, which was the most accurate in $^{99m}Tc$ (85.9%). Conclusion: Image quality of SPECT/CT was improved in all the radioisotopes by CT-based attenuation correction methods, except SC alone. SC failed to improve resolution in any radioisotopes, but it was effective in contrast enhancement. ACSC would be the best correction method as it improved resolution in radioisotopes with low energy levels and contrast in radioisotope with low energy levels. However, in radioisotope with high energy level, AC would be better than ACSC for resolution improvement.

• Journal of the Korea Computer Graphics Society
• /
• v.25 no.3
• /
• pp.105-113
• /
• 2019

Physically-based fluid simulation takes a lot of time for high resolution. To solve this problem, there are studies that make up the limitation of low resolution fluid simulation by using deep running. Among them, Super-resolution, which converts low-resolution simulation data to high resolution is under way. However, traditional techniques require to the entire space where there are no density data, so there are problems that are inefficient in terms of the full simulation speed and that cannot be computed with the lack of GPU memory as input resolution increases. In this paper, we propose a new method that divides and classifies 2D smoke simulation data into the space using the quad tree, one of the spatial partitioning methods, and performs Super-resolution only required space. This technique accelerates the simulation speed by computing only necessary space. It also processes the divided input data, which can solve GPU memory problems.

• 제어로봇시스템학회:학술대회논문집
• /
• 1987.10b
• /
• pp.442-445
• /
• 1987

In this paper, a new ARMA spectrum estimation algorithm based on Circular Lattice filter is presented. Since APMA model is used in signal modeling, high-resolution spectrum can be obtained. And the computational burden is reduced by using Circular Lattice filter. By modifying the input estimation part of other proposed methods, we can get high-resolution spectrum with less computation and less memory compared with other Lattice methods. Some computer simulations are performed.

• Mass Spectrometry Letters
• /
• v.3 no.3
• /
• pp.63-67
• /
• 2012

The need of heavy and unconventional crude oil as an energy source is increasing day by day, so does the importance of petroleomics: the pursuit of detailed knowledge of heavy crude oil. Crude oil needs techniques with ultra-high resolving capabilities to resolve its complex characteristics. Therefore, ultra-high resolution mass spectrometry represented by Fourier transform ion cyclotron resonance mass spectrometry (FT-ICR MS) has been successfully applied to the study of heavy and unconventional crude oils. The analysis of crude oil with high resolution mass spectrometry (FT-ICR MS) has pushed analysis to the limits of instrumental and methodological capabilities. Each high-resolution mass spectrum of crude oil may routinely contain over 50,000 peaks. To visualize and effectively study the large amount of data sets is not trivial. Therefore, data processing and visualization methods such as Kendrick mass defect and van Krevelen analyses and statistical analyses have played an important role. In this regard, it will not be an overstatement to say that the success of FT-ICR MS to the study of crude oil has been critically dependent on data processing methods. Therefore, this review offers introduction to peotroleomic data interpretation methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.5
• /
• pp.2539-2554
• /
• 2017

Regression-based image super resolution (SR) methods have shown great advantage in time consumption while maintaining similar or improved quality performance compared to other learning-based methods. In this paper, we propose a novel single image SR method based on hierarchical regression to further improve the quality performance. As an improvement to other regression-based methods, we introduce a hierarchical scheme into the process of learning multiple regressors. First, training samples are grouped into different clusters according to their geometry similarity, which generates the structure layer. Then in each cluster, a compact dictionary can be learned by Sparse Coding (SC) method and the training samples can be further grouped by dictionary atoms to form the detail layer. Last, a series of projection matrixes, which anchored to dictionary atoms, can be learned by linear regression. Experiment results show that hierarchical scheme can lead to regression that is more precise. Our method achieves superior high quality results compared with several state-of-the-art methods.

• Journal of Arbitration Studies
• /
• v.18 no.3
• /
• pp.91-116
• /
• 2008

E-Commerce constitutes an important part of all commercial activities. Online Alternative Dispute Resolution(Online ADR) or Online Dispute Resolution(ODR) is a new method of dispute, resolution which, is provided online. Most Online ADR services are alternatives to litigation. In this respect, they are the online transposition of the methods developed in the ADR movement such as negotiation, mediation and arbitration. But there are also online courts which are really normal courts in which the contesting parties communicate essentially online. This paper deals with the current operation of Online ADR and the ways to, activate it. They include (1) die establishment of legal stability regarding Online ADR, (2) the enhancement of system security in providing Online ADR services, (3) the introduction of Online ADR service platform for providing the various services through single window on a national, or global basis, and (4) the introduction of Online ADR online monitoring system for systematic dispute resolution services.