• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.11 no.8
• /
• pp.1414-1419
• /
• 2000

In this paper, we propose a resolution enhancement method for estimating direction-of-arrival (DOA) of narrowband incoherent signals incident on a general array. The resolution of DOA algorithm is dependent on the aperture size of antenna array. But it is very impractical to increase the physical size of antenna array in real environment. Therefore we propose the method that increases the aperture size by virtually expanding the sensor spacing of original antenna array and then construct the steering matrix of the virtual array using the proper transformation matrix. Superior resolution capabilities achieved with this method are shown by simulation results in comparison with the standard MUSIC for incoherent signals incident on a uniform circular array.

• Proceedings of the IEEK Conference
• /
• 2002.06d
• /
• pp.397-400
• /
• 2002

This paper has been studied speech enhancement method in noisy environment. By mean of that we prefer human auditory mechanism which is perfect system and applied wavelet transform. Multi-resolution of wavelet transform make possible multiband spectrum analysis like human ears. This method was verified very effective way in noisy speech enhancement.

• Journal of Broadcast Engineering
• /
• v.19 no.1
• /
• pp.118-121
• /
• 2014

Image interpolation is a method of determining the value of new pixel coordinate in the process of image scaling. Recently, image contents are likely to be a large-capacity, interpolation algorithm is required to generate fast enhanced result image. In this paper, fast multiple mixed image interpolation for image resolution enhancement is proposed. The proposed method estimates expected 12 shortfalls from four sub-images of a input image, and generates the result image that is interpolated in the combination of the expected shortfalls with the input image. The experimental results demonstrate that PSNR increases maximum value of 1.9dB, SSIM increases maximum value of 0.052, and the subjective quality is superior to any other compared methods. Moreover, it is known by algorithm running time comparison that the proposed method has been at least three times faster than the compared conventional methods. The proposed method can be useful for application on image resolution enhancement.

• 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%.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.218-220
• /
• 2021

본 논문에서는 CAR(content adaptive resampler)로 축소된 저해상도 이미지를 직접 다른 모델에 여러가지 방식으로 훈련을 시켜 성능을 개선시키고자 하였다. 본 논문에서는 단일 영상 super resolution 에 관하여 여러 기술이 존재하는 상황에 더 나은 기술을 테스트하려 하고 그를 위해 과거의 모델들에 대한 이해가 필요하여 이를 구현하였다. 현재 가장 뛰어난 성능을 보이고 있는 모델 중의 하나인 CAR 에서 복원 전 이미지를 사용하여 훈련을 시키면 더 나은 성능의 모델을 만들 수 있을 것이라고 가정하고 다양한 훈련을 통해 성능을 개선시키고자 하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.5
• /
• pp.1814-1828
• /
• 2021

Low-light image enhancement is a key technique to overcome the quality degradation of photos taken under scotopic vision illumination conditions. The degradation includes low brightness, low contrast, and outstanding noise, which would seriously affect the vision of the human eye recognition ability and subsequent image processing. In this paper, we propose an approach based on deep learning and Retinex theory to enhance the low-light image, which includes image decomposition, illumination prediction, image reconstruction, and image optimization. The first three parts can reconstruct the enhanced image that suffers from low-resolution. To reduce the noise of the enhanced image and improve the image quality, a super-resolution algorithm based on the Laplacian pyramid network is introduced to optimize the image. The Laplacian pyramid network can improve the resolution of the enhanced image through multiple feature extraction and deconvolution operations. Furthermore, a combination loss function is explored in the network training stage to improve the efficiency of the algorithm. Extensive experiments and comprehensive evaluations demonstrate the strength of the proposed method, the result is closer to the real-world scene in lightness, color, and details. Besides, experiments also demonstrate that the proposed method with the single low-light image can achieve the same effect as multi-exposure image fusion algorithm and no ghost is introduced.

• Proceedings of the Korean Vacuum Society Conference
• /
• 1996.02a
• /
• pp.154-154
• /
• 1996

• Journal of Arbitration Studies
• /
• v.29 no.3
• /
• pp.121-140
• /
• 2019

First, the purpose of this research is to review the Online Dispute Resolution (ODR) regulations in Korea to resolve disputes which can arise in international e-commerce in the near future. Second, this research tries to look for alternative solutions to dispute resolutions according to these regulations. Third, this research pursues to enhance the effectiveness of business deals by providing efficient and satisfactory dispute resolution methods for e-commerce business. Furthermore, this study evaluates the definition of global e-commerce by comparing Online Dispute Resolution (ODR) with Alternative Dispute Resolution (ADR). Through analyzing the domestic ODR system and ADR system, this research could boost the employment of settlements in small-sized disputes through easy and convenient consumer access to both ODR and ADR procedures. The enhancement of the competitiveness of Korean companies in the global market is estimated to take place as a result. This research is estimated to provide benefits to our businesses both domestically and internationally by using ODR regulations and ADR methods. Moreover, this research is anticipated to verify usefulness in terms of consumer protection by advancing consumers' access to dispute solution authorities locally and abroad.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.10
• /
• pp.118-128
• /
• 2015

Compressive sensing (CS) has to face with two challenges of computational complexity reconstruction and low coding efficiency. As a solution, this paper presents a novel spatially scalable Kronecker two layer compressive sensing framework which facilitates reconstruction up to three spatial resolutions as well as much improved CS coding performance. We propose a dual-resolution sensing matrix based on the quincunx sampling grid which is applied to the base layer. This sensing matrix can provide a fast-preview of low resolution image at encoder side which is utilized for predictive coding. The enhancement layer is encoded as the residual measurement between the acquired measurement and predicted measurement data. The low resolution reconstruction is obtained from the base layer only while the high resolution image is jointly reconstructed using both two layers. Experimental results validate that the proposed scheme outperforms both conventional single layer and previous multi-resolution schemes especially at high bitrate like 2.0 bpp by 5.75dB and 5.05dB PSNR gain on average, respectively.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.6
• /
• pp.71-77
• /
• 2011

In this paper, we propose a learning based super resolution algorithm using local block for image enhancement of vehicle license plate. Local block is defined as the minimum measure of block size containing the associative information in the image. Proposed method essentially generates appropriate local block sets suitable for various imaging conditions. In particular, local block training set is first constructed as ordered pair between high resolution local block and low resolution local block. We then generate low resolution local block training set of various size and blur conditions for matching to all possible blur condition of vehicle license plates. Finally, we perform association and merging of information to reconstruct into enhanced form of image from training local block sets. Representative experiments demonstrate the effectiveness of the proposed algorithm.