• Journal of the Korea Convergence Society
• /
• v.11 no.3
• /
• pp.19-26
• /
• 2020

In this paper, we propose a method to analyze the loss region of the dictionary-based super resolution result learned for image quality improvement and to map the learning data according to the analyzed loss region. In the conventional learned dictionary-based method, a result different from the feature configuration of the input image may be generated according to the learning image, and an unintended artifact may occur. The proposed method estimate loss information of low resolution images by analyzing the reconstructed contents to reduce inconsistent feature composition and unintended artifacts in the example-based super resolution process. By mapping the training data according to the final interpolation feature map, which improves the noise and pixel imbalance of the estimated loss information using a Gaussian-based kernel, it generates super resolution with improved noise, artifacts, and staircase compared to the existing super resolution. For the evaluation, the results of the existing super resolution generation algorithms and the proposed method are compared with the high-definition image, which is 4% better in the PSNR (Peak Signal to Noise Ratio) and 3% in the SSIM (Structural SIMilarity Index).

• Journal of the Korea Convergence Society
• /
• v.11 no.12
• /
• pp.15-22
• /
• 2020

In this paper, we proposed a deep learning based super-resolution method that combines Channel Attention and Spatial Attention feature enhancement methods. It is important to restore high-frequency components, such as texture and features, that have large changes in surrounding pixels during super-resolution processing. We proposed a super-resolution method using feature enhancement that combines Channel Attention and Spatial Attention. The existing CNN (Convolutional Neural Network) based super-resolution method has difficulty in deep network learning and lacks emphasis on high frequency components, resulting in blurry contours and distortion. In order to solve the problem, we used an emphasis block that combines Channel Attention and Spatial Attention to which Skip Connection was applied, and a Residual Block. The emphasized feature map extracted by the method was extended through Sub-pixel Convolution to obtain the super resolution. As a result, about PSNR improved by 5%, SSIM improved by 3% compared with the conventional SRCNN, and by comparison with VDSR, about PSNR improved by 2% and SSIM improved by 1%.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.6
• /
• pp.774-784
• /
• 2021

The object detection and recognition process is a very important task in the field of computer vision, and related research is actively being conducted. However, in the actual object recognition process, the recognition accuracy is often degraded due to the resolution mismatch between the training image data and the test image data. To solve this problem, in this paper, we designed and developed an integrated object recognition and super-resolution framework by proposing an image super-resolution technique to improve object recognition accuracy. In detail, 11,231 license plate training images were built by ourselves through web-crawling and artificial-data-generation, and the image super-resolution artificial neural network was trained by defining an objective function to be robust to the image flip. To verify the performance of the proposed algorithm, we experimented with the trained image super-resolution and recognition on 1,999 test images, and it was confirmed that the proposed super-resolution technique has the effect of improving the accuracy of character recognition.

• Journal of the Institute of Convergence Signal Processing
• /
• v.22 no.4
• /
• pp.156-163
• /
• 2021

Attention mechanisms have been used in deep learning-based computer vision systems, including single image super-resolution (SISR) networks. However, existing SISR networks with attention mechanism focused on real image super-resolution, so it is hard to know whether they are available for CG or VR images. In this paper, we attempt to apply a recent attention module, called balanced attention mechanism (BAM) module, to 12 state-of-the-art SISR networks, and then check whether the BAM module can achieve performance improvement in CG or VR image super-resolution. In our experiments, it has been confirmed that the performance improvement in CG or VR image super-resolution is limited and depends on data characteristics, size, and network type.

• Journal of Electrochemical Science and Technology
• /
• v.6 no.4
• /
• pp.121-130
• /
• 2015

The micro emulsion method has been successfully used for preparing perovskite LaCoO₃ with uniform, fine-shaped nanoparticles showing high activity as electro catalysts in oxygen reduction reactions (ORRs). They are, therefore, promising candidates for the air-cathode in metal-air rechargeable batteries. Since the activity of a catalyst is highly dependent on its specific surface area, nanoparticles of the perovskite catalyst are desirable for catalyzing both oxygen reduction and evolution reactions. Herein, LaCoO₃ powder was also prepared by sol-gel method for comparison, with a broad particle distribution and high agglomeration. The electro catalytic properties of LaCoO₃ and LaCoO₃-carbon Super P mixture layers toward the ORR were studied comparatively using the rotating disk electrode technique in 0.1 M KOH electrolyte to elucidate the effect of carbon Super P. Koutecky-Levich theory was applied to acquire the overall electron transfer number (n) during the ORR, calculated to be ~3.74 for the LaCoO₃-Super P mixture, quite close to the theoretical value (4.0), and ~2.7 for carbon-free LaCoO₃. A synergistic effect toward the ORR is observed when carbon is present in the LaCoO₃ layer. Carbon is assumed to be more than an additive, enhancing the electronic conductivity of the oxide catalyst. It is suggested that ORRs, catalyzed by the LaCoO₃-Super P mixture, are dominated by a 2+2-electron transfer pathway to form the final, hydroxyl ion product.

• International journal of advanced smart convergence
• /
• v.12 no.3
• /
• pp.149-156
• /
• 2023

Joint research on software, electronic engineering, computer engineering, and financial engineering and the use of ICT knowledge through network formation play an important role in strengthening science and technology-based innovation capabilities and facilitating the development and production process of products using new technologies. For the purpose of this study, I would like to strategically propose ICT specialized education in the 4th industrial revolution. To this end, the ICT specialization model, ICT specialization strategy analysis, and ICT specialization operation and effect were explored to establish ICT specialization strategies centered on software, electronic engineering, computer engineering, and financial engineering in the era of super-intelligence, hyper-connected, and hyper-convergence. Secondly, a roadmap for detailed promotion tasks related to efficient ICT characterization based on core strategies, detailed promotion tasks, and programs was proposed, focusing on talent related to ICT characterization. Thirdly, we would like to propose a reorganization of the academic structure and organization related to ICT characterization. Finally, we would like to propose the establishment of a future-oriented education system related to ICT specialization based on the advanced education and research environment.

• Journal of Korea Multimedia Society
• /
• v.24 no.2
• /
• 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.

• Steel and Composite Structures
• /
• v.29 no.4
• /
• pp.493-508
• /
• 2018

Free vibration analysis of super-elliptical composite thin plates was investigated. Plate is formed by symmetrical quasi-isotropic laminates. Rayleigh-Ritz method was used for parametric analysis based on the governing differential equations of Classical Laminated Plate Theory (CLPT). Simply supported and clamped boundary conditions at the periphery of plates were considered. Parametric study was performed for the effect of different lamination type, aspect ratio, thickness and super-elliptical power on natural frequencies. Convergence study and validation of isotropic case were achieved. A number of design parameters like different dimensions, structure systems, panel sizes, panel thicknesses, lamination sequences, boundary conditions and loading conditions must be considered in the production of composite ships. The number of possible combinations practically may be so high that a parametric study should be carried out in order to determine the optimum design parameters rapidly during the preliminary design stage. The use of Rayleigh-Ritz method could make this parametric study possible. Thereby it might be decreasing the consumption of time, material and labor. Certain results for some different super-elliptical powers presented in tabulated form in Appendix for designers as well.

• Journal of the Korea Convergence Society
• /
• v.9 no.6
• /
• pp.45-52
• /
• 2018

In this paper, we propose a linear interpolation method based on patch information generated from a low - resolution image for generating a super resolution image in a single image. Using the regression model of the global space, which is a conventional super resolution generation method, results in poor quality in general because of lack of information to be referred to a specific region. In order to compensate for these results, we propose a method to extract meaningful information by dividing the region into patches in the process of super resolution image generation, analyze the constituents of the image matrix region extended for super resolution image generation, We propose a method of linear interpolation based on optimal patch information that is searched by correlating patch information based on the information gathered before the interpolation process. For the experiment, the original image was compared with the reconstructed image with PSNR and SSIM.

• Journal of the Korea Convergence Society
• /
• v.10 no.8
• /
• pp.277-282
• /
• 2019

This study was conducted to compare the lap time of high school boys' K-2 1000m final at the $99^{th}$ National Sports Festival with the lap time of the World Championship final held in 2018 and to find an optimal pacing strategy to enhance the performance. The high school boys' average final record was 242.89 seconds, and the top international's 199.58 seconds. There was 43 seconds difference in records and by lap-time it were 9, 12, 9, and 13 seconds behind every 250m. World Championship players used the Super Fast-Even Pacing-Even Pacing-Spurt strategy. The $1^{st}$ to $3^{rd}$ ranked high school boys used Slow-Fast-Super Slow-Super Fast strategy, and $4^{th}$ to $9^{th}$ ranked boys used Fast-Slow-Fast-Slow strategy. The high school boys need to modify their pacing strategies to achieve world-class performance.