• Journal of Information Processing Systems
• /
• v.13 no.5
• /
• pp.1183-1202
• /
• 2017

Image restoration has been carried out by texture synthesis mostly for large regions and inpainting algorithms for small cracks in images. In this paper, we propose a new approach that allows for the simultaneous fill-in of different structures and textures by processing in a wavelet domain. A combination of structure inpainting and patch-based texture synthesis is carried out, which is known as patch-based inpainting, for filling and updating the target region. The wavelet transform is used for its very good multiresolution capabilities. The proposed algorithm uses the wavelet domain subbands to resolve the structure and texture components in smooth approximation and high frequency structural details. The subbands are processed separately by the prioritized patch-based inpainting with isophote energy driven texture synthesis at the core. The algorithm automatically estimates the wavelet coefficients of the target regions of various subbands using optimized patches from the surrounding DWT coefficients. The suggested performance improvement drastically improves execution speed over the existing algorithm. The proposed patch optimization strategy improves the quality of the fill. The fill-in is done with higher priority to structures and isophotes arriving at target boundaries. The effectiveness of the algorithm is demonstrated with natural and textured images with varying textural complexions.

• Journal of IKEEE
• /
• v.21 no.1
• /
• pp.46-65
• /
• 2017

This paper proposes a fast patch-based de-blurring algorithm including kernel estimation based on the angle between the edge and the blur direction. For de-blurring, image patches from the most informative edges in the blurry image are used to estimate a kernel with low computational cost. Moreover, the kernels of each patch are estimated based on the correlation between the edge direction and the blur direction. This makes the final kernel more reliable and creates an accurate latent image from the blurry image. The combination of directionally oriented kernel estimation and patch-based de-blurring is faster and more accurate than existing state-of-the art methods. Experimental results using various test images show that the proposed method achieves its objectives: speed and accuracy.

• Journal of KIISE:Software and Applications
• /
• v.37 no.4
• /
• pp.264-272
• /
• 2010

Example-based super resolution is a method to restore a high resolution image from low resolution images through training and retrieval of image patches. It is not only good in its performance but also available for a single frame low-resolution image. However, its time complexity is very high because it requires lots of comparisons to retrieve image patches in restoration process. In order to improve the restoration speed, an efficient patch retrieval algorithm is essential. In this paper, we applied various high-dimensional feature retrieval methods, available for the patch retrieval, to a practical example-based super resolution system and compared their speed. As well, we propose to apply the multi-phase candidate reduction approach to the patch retrieval process, which was successfully applied in character recognition fields but not used for the super resolution. In the experiments, LSH was the fastest among conventional methods. The multi-phase candidate reduction method, proposed in this paper, was even faster than LSH: For $1024{\times}1024$ images, it was 3.12 times faster than LSH.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.3
• /
• pp.154-161
• /
• 2015

A novel multiframe super-resolution (SR) algorithm is presented to overcome the limitation of existing single-image SR algorithms using motion information from adjacent frames in a video. The proposed SR algorithm consists of three steps: i) definition of a local region using interframe motion vectors, ii) multiscale patch generation and adaptive selection of multiple optimum patches, and iii) combination of optimum patches for super-resolution. The proposed algorithm increases the accuracy of patch selection using motion information and multiscale patches. Experimental results show that the proposed algorithm performs better than existing patch-based SR algorithms in the sense of both subjective and objective measures including the peak signal-to-noise ratio (PSNR) and structural similarity measure (SSIM).

• Current Optics and Photonics
• /
• v.8 no.3
• /
• pp.215-224
• /
• 2024

In medium- and long-range optical imaging systems, atmospheric turbulence causes blurring and distortion of images, resulting in loss of image information. An image-restoration method based on an adaptive feature-fusion multi-input-multi-output (MIMO) dense U-shaped network (Unet) is proposed, to restore a single image degraded by atmospheric turbulence. The network's model is based on the MIMO-Unet framework and incorporates patch-embedding shallow-convolution modules. These modules help in extracting shallow features of images and facilitate the processing of the multi-input dense encoding modules that follow. The combination of these modules improves the model's ability to analyze and extract features effectively. An asymmetric feature-fusion module is utilized to combine encoded features at varying scales, facilitating the feature reconstruction of the subsequent multi-output decoding modules for restoration of turbulence-degraded images. Based on experimental results, the adaptive feature-fusion MIMO dense U-shaped network outperforms traditional restoration methods, CMFNet network models, and standard MIMO-Unet network models, in terms of image-quality restoration. It effectively minimizes geometric deformation and blurring of images.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.3
• /
• pp.177-185
• /
• 2022

A method of restoring the occluded area was proposed by referring to images taken with the same types of sensors on high-resolution optical satellite images through deep learning. For the natural continuity of the simulated image with the occlusion region and the surrounding image while maintaining the pixel distribution of the original image as much as possible in the patch segmentation image, CycleGAN (Cycle Generative Adversarial Network) method with ConvNeXt block applied was used to analyze three experimental regions. In addition, We compared the experimental results of a training patch size of 512*512 pixels and a 1024*1024 pixel size that was doubled. As a result of experimenting with three regions with different characteristics,the ConvNeXt CycleGAN methodology showed an improved R² value compared to the existing CycleGAN-applied image and histogram matching image. For the experiment by patch size used for training, an R² value of about 0.98 was generated for a patch of 1024*1024 pixels. Furthermore, As a result of comparing the pixel distribution for each image band, the simulation result trained with a large patch size showed a more similar histogram distribution to the original image. Therefore, by using ConvNeXt CycleGAN, which is more advanced than the image applied with the existing CycleGAN method and the histogram-matching image, it is possible to derive simulation results similar to the original image and perform a successful simulation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.6
• /
• pp.2748-2766
• /
• 2016

Compared with traditional patch-based sparse representation, recent studies have concluded that group-based sparse representation (GSR) can simultaneously enforce the intrinsic local sparsity and nonlocal self-similarity of images within a unified framework. This article investigates an accelerated split Bregman method (SBM) that is based on GSR which exploits image compressive sensing (CS). The computational efficiency of accelerated SBM for the measurement matrix of a partial Fourier matrix can be further improved by the introduction of a fast Fourier transform (FFT) to derive the enhanced algorithm. In addition, we provide convergence analysis for the proposed method. Experimental results demonstrate that accelerated SBM is potentially faster than some existing image CS reconstruction methods.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.6
• /
• pp.1303-1310
• /
• 2021

We propose an edge-preserving transmission estimation by comparing the patch-based dark channel and the pixel-based dark channel near the edge, in order to improve the quality of outdoor images deteriorated by conditions such as fog and smog. Moreover, we propose a refinement that applies the Guided Image Filtering (GIF), a kind of edge-preserving smoothing filtering methods, to edges using Laplacian operation for natural restoration of image objects and backgrounds, so that we can dehaze a single image and improve the visibility effectively. Experimental results carried out on various outdoor hazy images that show the proposed method has less computational complexity than the conventional methods, while reducing distortion such as halo effect, and showing excellent dehazing performance. In It can be confirmed that the proposed method can be applied to various fields including devices requiring real-time performance.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.5
• /
• pp.21-29
• /
• 2024

Reducing the radiation dose during CT scanning can lower the risk of radiation exposure, but not only does the image resolution significantly deteriorate, but the effectiveness of diagnosis is reduced due to the generation of noise. Therefore, noise removal from CT images is a very important and essential processing process in the image restoration. Until now, there are limitations in removing only the noise by separating the noise and the original signal in the image area. In this paper, we aim to effectively remove noise from CT images using the wavelet transform-based GAN model, that is, the WT-GAN model in the frequency domain. The GAN model used here generates images with noise removed through a U-Net structured generator and a PatchGAN structured discriminator. To evaluate the performance of the WT-GAN model proposed in this paper, experiments were conducted on CT images damaged by various noises, namely Gaussian noise, Poisson noise, and speckle noise. As a result of the performance experiment, the WT-GAN model is better than the traditional filter, that is, the BM3D filter, as well as the existing deep learning models, such as DnCNN, CDAE model, and U-Net GAN model, in qualitative and quantitative measures, that is, PSNR (Peak Signal-to-Noise Ratio) and SSIM (Structural Similarity Index Measure) showed excellent results.