• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.2 s.308
• /
• pp.12-18
• /
• 2006

This paper presents a method to extract a good high-resolution image from a low-resolution video in an automatic manner. Since a high-resolution image reconstruction method utilizing several low-resolution input images works better than a conventional interpolation method utilizing single low-resolution input image only if the input images are well registered onto a common high-resolution grid, low-resolution input images should be carefully chosen so that the registration errors can be carefully considered. In this paper, the statistics obtained from the motion-compensated low-resolution images are utilized to evaluate the feasibility of the input image candidates. Maximum motion-compensation error is estimated from the high-resolution image observation model. U the motion-compensation error of the input image candidate is greater than the estimated maximum motion-compensation error, the input image candidate is discarded. The number of good input image candidates and the statistics of the motion-compensation errors are used to choose final input images. The final input images chosen from the input image selection block are given to the following high-resolution image reconstruction block. It is expected that the proposed method is utilized to extract a good high-resolution image efficiently from a low-resolution video without any user intervention.

• Korean Journal of Remote Sensing
• /
• v.23 no.6
• /
• pp.547-552
• /
• 2007

This study presents an approach to reconstruct high-resolution imagery for multispectral imagery of low-resolution using panchromatic imagery of high-resolution. The proposed scheme reconstructs a high-resolution image which agrees with original spectral values. It uses a linear model of high-and low- resolution images and consists of two stages. The first one is to perform a global estimation of the least square error on the basis of a linear model of low-resolution image associated with high-resolution feature, and next local correction then makes the reconstructed image locally fit to the original spectral values. In this study, the new method was applied to KOMPSAT-1 EOC image of 6m and LANDSAT ETM+ of 30m, and an 1m RGB image was also generated from 4m IKONOS multispectral data. The results show its capability to reconstruct high-resolution imagery from multispectral data of low-resolution.

• 한국신재생에너지학회:학술대회논문집
• /
• 2009.06a
• /
• pp.455-457
• /
• 2009

The purposes of this study are to consider the influence of topography resolution on atmospheric flow simulation and to suggest a method of atmospheric flow simulation using a low-resolution DEM. Simulations using a low-resolution DEM has more critical error at near surface than simulations using high-resolution DEM because it is ignored the small curve topography of high-resolution DEM. Therefore when we convert the height differences between low-resolution DEM and high-resolution DEM into the topography roughness, we can be able to reduce the error on atmospheric flow simulations.

• Smart Media Journal
• /
• v.8 no.4
• /
• pp.64-71
• /
• 2019

The performance of an OMR (Optical Music Recognition) system is usually determined by the characterizing features of the input music score images. Low resolution is one of the main factors leading to degraded image quality. In this paper, we handle the low-resolution problem using the super-resolution technique. We propose the use of a deep neural network with instance normalization to improve the quality of music score images. We apply instance normalization which has proven to be beneficial in single image enhancement. It works better than batch normalization, which shows the effectiveness of shifting the mean and variance of deep features at the instance level. The proposed method provides an end-to-end mapping technique between the high and low-resolution images respectively. New images are then created, in which the resolution is four times higher than the resolution of the original images. Our model has been evaluated with the dataset "DeepScores" and shows that it outperforms other existing methods.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.781-784
• /
• 2017

Face recognition systems are characterized by low invasiveness of acquisition, and increasingly better reliability. Such systems may not be applied effectively, when the images are in low resolution (LR) as in the case that photos are taken from long distances, typically public surveillance. In theory, the high resolution (HR) image reconstructed from an LR face image, applying a super resolution (SR) method, can be used for face recognition. However, existing face SR algorithms may not give satisfactory results in face recognition. This article investigates the very low resolution face recognition problem and introduces a partial differential equation (PDE)-based SR method for a face recognition system of convolutional neural network (CNN).

• Journal of Korea Multimedia Society
• /
• v.18 no.9
• /
• pp.1039-1046
• /
• 2015

We propose a feature generation method for low-resolution face recognition. For this, we first generate new features from the input features (pixels) of a low-resolution face image by adding the higher-order terms. Then, we evaluate the separability of both of the original input features and new features by computing the discriminant distance of each feature. Finally, new data sample used for recognition consists of the features with high separability. The experimental results for the FERET, CMU-PIE and Yale B databases show that the proposed method gives good recognition performance for low-resolution face images compared with other method.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.1
• /
• pp.52.1-52.1
• /
• 2019

The Helioseismic and Magnetic Imager (HMI) is the instrument of Solar Dynamics Observatory (SDO) to study the magnetic field and oscillation at the solar surface. The HMI image is not enough to analyze very small magnetic features on solar surface since it has a spatial resolution of one arcsec. Super resolution is a technique that enhances the resolution of a low resolution image. In this study, we use a method for enhancing the solar image resolution using a Deep-learning model which generates a high resolution HMI image from a low resolution HMI image (4 by 4 binning). Deep learning networks try to find the hidden equation between low resolution image and high resolution image from given input and the corresponding output image. In this study, we trained a model based on a very deep residual channel attention networks (RCAN) with HMI images in 2014 and test it with HMI images in 2015. We find that the model achieves high quality results in view of both visual and measures: 31.40 peak signal-to-noise ratio(PSNR), Correlation Coefficient (0.96), Root mean square error (RMSE) is 0.004. This result is much better than the conventional bi-cubic interpolation. We will apply this model to full-resolution SDO/HMI and GST magnetograms.

• Korean Journal of Remote Sensing
• /
• v.27 no.6
• /
• pp.625-635
• /
• 2011

This paper investigates the effects of spatial autocorrelation structures in low resolution data on downscaling without ground measurements or secondary data, as well as the potential of geostatistical downscaling. An advanced geostatistical downscaling scheme applied in this paper consists of two analytical steps: the estimation of the point-support spatial autocorrelation structure by variogram deconvolution and the application of area-to-point kriging. Point kriging of block data without variogram deconvolution is also applied for a comparison purpose. Experiments using two low resolution thematic maps derived from remote sensing data showing very different spatial patterns are carried out to discuss the objectives. From the experiments, it is demonstrated that the advanced geostatistical downscaling scheme can generate the downscaling results that well preserve overall patterns of original low resolution data and also satisfy the coherence property, regardless of spatial patterns in input low resolution data. Point kriging of block data can produce the downscaling result compatible to that by area-to-point kriging when the spatial continuity in block data is strong. If heterogeneous local variations are dominant in input block data, the treatment of the low resolution data as point data cannot generate the reliable downscaling result, and this simplification should not be applied to donwscaling.

• 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.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.2
• /
• pp.70.4-70.4
• /
• 2019

Image super-resolution (SR) is a technique that enhances the resolution of a low resolution image. In this study, we use three SR models (RCAN, ProSRGAN and Bicubic) for enhancing solar SDO/HMI magnetograms using deep learning. Each model generates a high resolution HMI image from a low resolution HMI image (4 by 4 binning). The pixel resolution of HMI is about 0.504 arcsec. Deep learning networks try to find the hidden equation between low resolution image and high resolution image from given input and the corresponding output image. In this study, we trained three models with HMI images in 2014 and test them with HMI images in 2015. We find that the RCAN model achieves higher quality results than the other two methods in view of both visual aspects and metrics: 31.40 peak signal-to-noise ratio(PSNR), Correlation Coefficient (0.96), Root mean square error (RMSE) is 0.004. This result is also much better than the conventional bi-cubic interpolation. We apply this model to a full-resolution SDO/HMI image and compare the generated image with the corresponding Hinode NFI magnetogram. As a result, we get a very high correlation (0.92) between the generated SR magnetogram and the Hinode one.