• Journal of Broadcast Engineering
• /
• v.24 no.5
• /
• pp.703-712
• /
• 2019

Single image Super-Resolution (SISR) aims to generate a visually pleasing high-resolution image from its degraded low-resolution measurement. In recent years, deep learning - based super - resolution methods have been actively researched and have shown more reliable and high performance. A typical method is WaveletSRNet, which restores high-resolution images through wavelet coefficient learning based on feature maps of images. However, there are two disadvantages in WaveletSRNet. One is a big processing time due to the complexity of the algorithm. The other is not to utilize feature maps efficiently when extracting input image's features. To improve this problems, we propose an efficient single image super resolution method, named RDB-WaveletSRNet. The proposed method uses the residual dense block to effectively extract low-resolution feature maps to improve single image super-resolution performance. We also adjust appropriated growth rates to solve complex computational problems. In addition, wavelet packet decomposition is used to obtain the wavelet coefficients according to the possibility of large scale ratio. In the experimental result on various images, we have proven that the proposed method has faster processing time and better image quality than the conventional methods. Experimental results have shown that the proposed method has better image quality by increasing 0.1813dB of PSNR and 1.17 times faster than the conventional method.

• Journal of Korean Society for Geospatial Information Science
• /
• v.10 no.5 s.23
• /
• pp.45-51
• /
• 2002

The goal of image merging techniques are to enhance the resolution of low-resolution images using the detail information of the high-resolution images. Among the several image merging methods, wavelet-based image merging techniques have the advantages of efficient decorrelation of image bands and time-scale analysis. However, they have no regard for spatial information between the bands. In other words, multiresolution data merging methods merge the same information-the detail information of panchromatic image-with other band images, without considering specific characteristics. Therefore, a merged image contains much unnecessary information. In this paper, we discussed this 'mixing' effect and, proposed a method to classify the detail information of the panchromatic image according to the spatial and spectral characteristics, and to minimize distortion of the merged image.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2010.04a
• /
• pp.221-224
• /
• 2010

When the image registration methods which were generally used to the low medium resolution satellite images is applied to the high spatial resolution images, some matching errors or limitations might be occurred because of the local distortions in the images. This paper, therefore, proposed the automatic image-to-image registration of high resolution satellite images using local properties of control points to improve the registration result.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• pp.98-101
• /
• 2019

At present, deep convolutional neural networks have made a very important contribution in single-image super-resolution. Through the learning of the neural networks, the features of input images are transformed and combined to establish a nonlinear mapping of low-resolution images to high-resolution images. Some previous methods are difficult to train and take up a lot of memory. In this paper, we proposed a simple and compact deep recursive residual network learning the features for single image super resolution. Global residual learning and local residual learning are used to reduce the problems of training deep neural networks. And the recursive structure controls the number of parameters to save memory. Experimental results show that the proposed method improved image qualities that occur in previous methods.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.63-66
• /
• 2018

Recently, a convolutional neural network (CNN) models at single image super-resolution have been very successful. Residual learning improves training stability and network performance in CNN. In this paper, we compare four convolutional neural network models for super-resolution (SR) to learn nonlinear mapping from low-resolution (LR) input image to high-resolution (HR) target image. Four models include general CNN model, global residual learning CNN model, local residual learning CNN model, and the CNN model with global and local residual learning. Experiment results show that the results are greatly affected by how skip connections are connected at the basic CNN network, and network trained with only global residual learning generates highest performance among four models at objective and subjective evaluations.

• Journal of Information Processing Systems
• /
• v.18 no.4
• /
• pp.575-586
• /
• 2022

Uneven light in real-world causes visual degradation for underexposed regions. For these regions, insufficient consideration during enhancement procedure will result in over-/under-exposure, loss of details and color distortion. Confronting such challenges, an unsupervised low-light image enhancement network is proposed in this paper based on the guidance of the unpaired low-/normal-light images. The key components in our network include super-resolution module (SRM), a GAN-based low-light image enhancement network (LLIEN), and denoising-scaling module (DSM). The SRM improves the resolution of the low-light input images before illumination enhancement. Such design philosophy improves the effectiveness of texture details preservation by operating in high-resolution space. Subsequently, local lightness attention module in LLIEN effectively distinguishes unevenly illuminated areas and puts emphasis on low-light areas, ensuring the spatial consistency of illumination for locally underexposed images. Then, multiple discriminators, i.e., global discriminator, local region discriminator, and color discriminator performs assessment from different perspectives to avoid over-/under-exposure and color distortion, which guides the network to generate images that in line with human aesthetic perception. Finally, the DSM performs noise removal and obtains high-quality enhanced images. Both qualitative and quantitative experiments demonstrate that our approach achieves favorable results, which indicates its superior capacity on illumination and texture details restoration.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.1
• /
• pp.72-79
• /
• 2007

In this paper, It propose a new restoration algorithm of high resolution, which is reconstructed to high resolution image using low resolution image informations. The proposed algorithm is constructed based on super resolution theory, it is consisted of progressive steps of the integration and construction. It reduced a lot of data-processing capacity and noise with integration through sub-pixel movement and wavelet basis through a higher resolution. As a result, it is shown that the main information is maintained and the error rate is improved. Using expansion fuzzy wavelet B-spline interpolation in stage of construction, it is confirmed that we can achieve smoothing image and good resolution without blur and block.

• Journal of radiological science and technology
• /
• v.40 no.3
• /
• pp.393-400
• /
• 2017

The purpose of this study is to suggest a method to reduce the dose by Analyzing the dose area product (DAP) and image quality according to the change of tube current using NEMA Phantom. The spatial resolution and low contrast resolution were used as evaluation criteria in addition to signal to noise ratio (SNR) and contrast to noise ratio (CNR), which are important image quality parameters of intervention. Tube voltage was fixed at 80 kVp and the amount of tube current was changed to 20, 30, 40, and 50 mAs, and the dose area product and image quality were compared and analyzed. As a result, the dose area product increased from $1066mGycm^2$ to $6160mGycm^2$ to 6 times as the condition increased, while the spatial resolution and low contrast resolution were higher than 20 mAs and 30 mAs, Spatial resolution and low contrast resolution were observed below the evaluation criteria. In addition, the SNR and CNR increased up to 30 mAs, slightly increased at 40 mAs, but not significantly different from the previous one, and decreased at 50 mAs. As a result, the exposure dose significantly increased due to overexposure of the test conditions and the image quality deteriorated in all areas of spatial resolution, low contrast resolution, SNR and CNR.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.2343-2346
• /
• 2003

The spatial resolution of multispectral images can be improved by merging them with higher resolution image data. A fundamental problem frequently occurred in existing fusion processes, is the distortion of spectral information. This paper presents a spatially adaptive image fusion algorithm which produces visually natural images and retains the quality of local spectral information as well. High frequency information of the high resolution image to be inserted to the resampled multispectral images is controlled by adaptive gains to incorporate the difference of local spectral characteristics between the high and the low resolution images into the fusion. Each gain is estimated to minimize the l$_2$-norm of the error between the original and the estimated pixel values defined in a spatially adaptive window of which the weight are proportional to the spectral correlation measurements of the corresponding regions. This method is applied to a set of co-registered Landsat7 ETM＋ panchromatic and multispectral image data.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.11a
• /
• pp.59-61
• /
• 2018

Highly compressed images typically not only have low resolution, but are also affected by compression artifacts. Performing image super-resolution (SR) directly on highly compressed image would simultaneously magnify the blocking artifacts. In this paper, a SR method based on deep learning is proposed. The method is an end-to-end trainable deep convolutional neural network which performs SR on compressed images so as to reduce compression artifacts and improve image resolution. The proposed network is divided into compression artifacts removal (CAR) part and SR reconstruction part, and the network is trained by three-step training method to optimize training procedure. Experiments on JPEG compressed images with quality factors of 10, 20, and 30 demonstrate the effectiveness of the proposed method on commonly used test images and image sets.