• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.715-717
• /
• 2004

This paper proposes a new reconstruction method of high-resolution facial image from a low-resolution facial image based on a recursive error back-projection of top-down machine learning. A face is represented by a linear combination of prototypes of shape and texture. With the shape and texture information about the pixels in a given low-resolution facial image, we can estimate optimal coefficients for a linear combination of prototypes of shape and those of texture by solving least square minimization. Then high-resolution facial image can be obtained by using the optimal coefficients for linear combination of the high-resolution prototypes, In addition to, a recursive error back-projection is applied to improve the accuracy of synthesized high-resolution facial image. The encouraging results of the proposed method show that our method can be used to improve the performance of the face recognition by applying our method to reconstruct high-resolution facial images from low-resolution one captured at a distance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.8
• /
• pp.3942-3961
• /
• 2019

Recently, the models of deep super-resolution networks can successfully learn the non-linear mapping from the low-resolution inputs to high-resolution outputs. However, for large scaling factors, this approach has difficulties in learning the relation of low-resolution to high-resolution images, which lead to the poor restoration. In this paper, we propose Stage Generative Adversarial Networks (Stage-GAN) with semantic maps for image super-resolution (SR) in large scaling factors. We decompose the task of image super-resolution into a novel semantic map based reconstruction and refinement process. In the initial stage, the semantic maps based on the given low-resolution images can be generated by Stage-0 GAN. In the next stage, the generated semantic maps from Stage-0 and corresponding low-resolution images can be used to yield high-resolution images by Stage-1 GAN. In order to remove the reconstruction artifacts and blurs for high-resolution images, Stage-2 GAN based post-processing module is proposed in the last stage, which can reconstruct high-resolution images with photo-realistic details. Extensive experiments and comparisons with other SR methods demonstrate that our proposed method can restore photo-realistic images with visual improvements. For scale factor ${\times}8$, our method performs favorably against other methods in terms of gradients similarity.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.2
• /
• pp.294-302
• /
• 2008

In this paper, we present a new image up-sampling method which registers low resolution images to the high resolution grid when Bayesian super-resolution image processing is performed. The proposed up-sampling method interpolates high-resolution pixels using high-frequency data lying in all the low resolution images, instead of up-sampling each low resolution image separately. The interpolation is based on B-spline non-uniform re-sampling, adjusted for the super-resolution image processing. The experimental results demonstrate the effects when different up-sampling methods generally used such as zero-padding or bilinear interpolation are applied to the super-resolution image reconstruction. Then, we show that the proposed hybird up-sampling method generates high-resolution images more accurately than conventional methods with quantitative and qualitative assess measures.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.115-118
• /
• 2004

Images with high resolution are desired and often required in many visual applications. When resolution can not be improved by replacing sensors, either because of cost or hardware physical limits, super resolution image reconstruction method is what can be resorted to. Super resolution image reconstruction method refers to image processing algorithms that produce high quality and high resolution images from a set of low quality and low resolution images. The method is proved to be useful in many practical cases where multiple frames of the same scene can be obtained, including satellite imaging, video surveillance, video enhancement and restoration, digital mosaicking, and medical imaging. The method can be either the frequency domain approach or the spatial domain approach. Much of the earlier works concentrated on the frequency domain formulation, but as more general degradation models were considered, later researches had been almost exclusively on spatial domain formulations. The method in spatial domains has three stages: i) motion estimate or image registration, ii) interpolation onto high resolution grid and iii) deblurring process. The super resolution grid construction in the second stage was discussed in this paper. We applied the Maximum A­Posteriori(MAP) reconstruction method that is one of the major methods in the super resolution grid construction. Based on this method, we reconstructed high resolution images from a set of low resolution images and compared the results with those from other known interpolation methods.

• Proceedings of the KSRS Conference
• /
• v.1
• /
• pp.413-416
• /
• 2006

As even small features can be classified as high resolution imagery, urban remote sensing is regarded as one of the important application fields in time of wide use of the commercialized high resolution satellite imageries. In this study, we have analyzed the variogram properties of high resolution imagery, which was obtained in urban area through the simple modeling and applied to the real image. Based on the grasped variogram characteristics, we have tried to decomposed two high-resolution imagery such as IKONOS and QuickBird reducing window size until the unique variogram that urban feature has come out and then been indexed. Modeling results will be used as the fundamental data for variographic analysis in urban area using high resolution imagery later on. Index map also can be used for determining urban complexity or land-use classification, because the index is influenced by the feature size.

• Korean Journal of Remote Sensing
• /
• v.40 no.1
• /
• pp.103-114
• /
• 2024

The escalating demands for high-resolution satellite imagery necessitate the dissemination of geospatial data with superior accuracy.Achieving precise positioning is imperative for mitigating geometric distortions inherent in high-resolution satellite imagery. However, maintaining sub-pixel level accuracy poses significant challenges within the current technological landscape. This research introduces an approach wherein upsampling is employed on both the satellite image and ground control points (GCPs) chip, facilitating the establishment of a high-resolution satellite image precision sensor orientation. The ensuing analysis entails a comprehensive comparison of matching performance. To evaluate the proposed methodology, the Compact Advanced Satellite 500-1 (CAS500-1), boasting a resolution of 0.5 m, serves as the high-resolution satellite image. Correspondingly, GCP chips with resolutions of 0.25 m and 0.5 m are utilized for the South Korean and North Korean regions, respectively. Results from the experiment reveal that concurrent upsampling of satellite imagery and GCP chips enhances matching performance by up to 50% in comparison to the original resolution. Furthermore, the position error only improved with 2x upsampling. However,with 3x upsampling, the position error tended to increase. This study affirms that meticulous upsampling of high-resolution satellite imagery and GCP chips can yield sub-pixel-level positioning accuracy, thereby advancing the state-of-the-art in the field.

• 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.

• Proceedings of the KSRS Conference
• /
• 2007.10a
• /
• pp.219-222
• /
• 2007

Today, use of high resolution satellite image with at least 1m resolution is expanding into many more areas including forest, river way, city, seashore and so forth for disaster prevention. Interest in this medium is increasing among the general public due to the roll-out to the private sector as Google earth, Virtual Earth and so forth. However, pre-processing process that revises the geometrical distortion that result at the time of photographing is required in order to use high resolution satellite image. The purpose of this research is to search the most accurate GCP(Ground Control Point) information acquisition method that is used for the revision of high resolution satellite image's geometrical distortion through automated processing. Through this, it is possible to contribute to increasing the level of accuracy at the time of high resolution satellite image revision and to secure promptness.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.254-257
• /
• 2009

In this paper, we propose a learning-based super-resolution algorithm. In the proposed algorithm, a multi-resolution wavelet approach is adopted to perform the synthesis of local high-frequency features. To obtain a high-resolution image, wavelet coefficients of two dominant LH- and HL-bands are estimated based on wavelet frames. In order to prepare more efficient training sets, the proposed algorithm utilizes the LH-band and transposed HL-band. The training sets are then used for the estimation of wavelet coefficients for both LH- and HL-bands. Using the estimated high frequency bands, a high resolution image is reconstructed via the wavelet transform. Experimental results demonstrate that the proposed scheme can synthesize high-quality images.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.648-650
• /
• 2003

Efficient multi-resolution image fusion aims to take advantage of the high spectral resolution of Landsat TM images and high spatial resolution of SPOT panchromatic images simultaneously. This paper presents a multi-resolution data fusion scheme, based on multirate image representation. Motivated by analytical results obtained from high-resolution multispectral image data analysis: the energy packing the spectral features are distributed in the lower frequency bands, and the spatial features, edges, are distributed in the higher frequency bands. This allows to spatially enhancing the multispectral images, by adding the high-resolution spatial features to them, by a multirate filtering procedure. The proposed method is compared with some conventional methods. Results show it preserves more spectral features with less spatial distortion.