• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4326-4344
• /
• 2021

The SinGAN is one of generative adversarial networks that can be trained on a single nature image. It has poor ability to learn more global features from nature image, and losses much local detail information when it generates arbitrary size image sample. To solve the problem, a non-linear function is firstly proposed to control downsampling ratio that is ratio between the size of current image and the size of next downsampled image, to increase the ratio with increase of the number of downsampling. This makes the low-resolution images obtained by downsampling have higher proportion in all downsampled images. The low-resolution images usually contain much global information. Therefore, it can help the model to learn more global feature information from downsampled images. Secondly, the attention mechanism is introduced to the generative network to increase the weight of effective image information. This can make the network learn more local details. Besides, in order to make the output image more natural, the TVLoss function is introduced to the loss function of SinGAN, to reduce the difference between adjacent pixels and smear phenomenon for the output image. A large number of experimental results show that our proposed model has better performance than other methods in generating random samples with fixed size and arbitrary size, image harmonization and editing.

• Journal of IKEEE
• /
• v.11 no.4
• /
• pp.219-226
• /
• 2007

An efficient block based two-layer JPEG encoding algorithm is proposed to compress high dynamic range (HDR) images in this work. The proposed algorithm separates an input HDR image into a tone-mapped low dynamic range (LDR) image and a ratio image, which represents the quotients of the original HDR pixels divided by the tone-mapped LDR pixels. Then, the tone-mapped LDR image is compressed using the standard JPEG scheme to preserve backward compatibility and the ratio image is encoded to minimize a cost function that models the perception of each block with different quantization parameters in the human visual system (HVS). Simulation results show that the proposed algorithm provides better performance than the conventional method, which encodes the ratio image without any prior information of blocks.

• Journal of Information Display
• /
• v.12 no.2
• /
• pp.85-87
• /
• 2011

The contrast ratio is one of the most important performance parameters for display devices. The general method of measuring the contrast ratio is to determine the ratio of the full-screen white pattern to the full-screen black pattern, according to the Video Electronics Standards Association standard. Real TV images seldom have these images, however, and the conventional method does not reflect the true performance of the display in actual use. In this paper, a new contrast ratio measurement method that uses image patterns is proposed, to demonstrate that active matrix organic light-emitting diode TVs have a higher contrast than LED (LCD) TVs.

• International Journal of Highway Engineering
• /
• v.13 no.1
• /
• pp.1-11
• /
• 2011

This study is aimed at suggesting a plan for creating a landscape environment by grasping a landscape preference according to the change of middle span and sag ratio which is a consideration factor when designing the suspension bridge representing long-span bridges and image property of the bridge while applying SD method to a relation between landscape preference and image factor, and a connection of design element with image factor. An analysis on landscape preference about the bridge landscape showed from what the longer the length of middle span, the extent of sag ratio of preference decreased, the longer the middle span low sag ratio was preferred and the higher the landscape preference became. In landscape preference and image factor, the attribute of sag ratio with high landscape preference was all positively correlated with "stability", "plasticity", and "aesthetic" but an influence of "plasticity" was insignificant. In the relation between design element and image factor, the factor of middle span and sag ratio was more related to the factor of "stability" and the lower the sag ratio and the longer the middle span, the higher the "stability" was rated. This result showed the image property of "plasticity" was insignificant among the one of preference in landscape and to highlight the one of "plasticity" a complementary experiment was done with a change in balance and symmetry elements not in proportional element of middle span and sag ratio. The result showed the image property of "plasticity" was more highlighted in the suspension bridge of 3-tower and different bilateral symmetry at sag, and when designing the landscape of suspension bridge later on, the elements of balance and symmetry as well as the proportional element should be considered and reflected in the design.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 1998.06a
• /
• pp.521-525
• /
• 1998

In this paper, we propose a fast algorithm for fractal image coding to shorten long time to take on fractal image encoding. For its performance evaluation, the algorithm compares with other traditional fractal coding methods. In the traditional fractal image coding methods, an original image is contracted by a factor in order to make an image to be matched. Then, the whole area of the contracted image is searched in order to find contractive transformation point of the original image corresponding to the contacted image. It needs a lot of searching time on encoding and remains limitation in the improvement of compression ratio. However, the proposed algorithm not only considerably reduces encoding tin e by using scaling method and limited search area method but also improves compression ratio by using bit-plane. When comparing the proposed algorithm with Jacquin's method, the proposed algorithm provides much shorter encoding time and better compression ratio with a little degradation of the decoded image quality than Jacquin's method.

• Journal of Korea Multimedia Society
• /
• v.21 no.2
• /
• pp.108-116
• /
• 2018

In this paper, we propose an image enhancement method based on Multi-Scale Retinex theory that designs Unsharp Masking Filter (UMF) and emphasizes the contrast ratio adaptively. Unsharp Masking (UM) technique emphasizes image sharpness and improves contrast ratio by adding high frequency component to the original image. The high frequency component is obtained by differentiating between original image and low frequency image. In this paper, we present how to design an UMF kernel and to adaptively apply it to increase the contrast ratio according to multi-scale retinex theory which resembles human visual system. Experimental results show that the proposed method has better quantitative performance indexes such as PSNR, ambe & SSIM and better qualitative feature like halo artifact suppression.

• Journal of Korea Multimedia Society
• /
• v.11 no.1
• /
• pp.23-33
• /
• 2008

In this paper, we propose a image retrieval algorithm using spatial information and color changing ratio. The proposed method extracts color regions from images by threshold $\tau$ to extract spatial information. During this process, we count extracted color regions and color changing, and these values are used to obtain color changing ratio. Image similarity between images is measured by extracted spatial information. Additively, color changing ratio makes images that has similar color changing ratio to be more higher retrieval rank. In our experiment using various natural images, we demonstrate a proposed method shows better performance than other common retrieval methods using color informations.

• Proceedings of the IEEK Conference
• /
• 2003.07d
• /
• pp.1515-1518
• /
• 2003

This paper suggests the condensed two-stage retrieval method for fast image retrieval in the content-based image retrieval system, and proves the validity of the performance. The condensed two-stage retrieval method reduces the overall response time remarkably while it maintains relevance with the conventional exhaustive search method. It is explained by properties of the Cauchy-Schwartz inequality. In experimental result, it turns out that there is an optimal value of condensation ratio which minimizes the overall response time. We analyze the optimal condensation ratio by modeling a similarity computation time mathematically.

• ETRI Journal
• /
• v.34 no.3
• /
• pp.470-473
• /
• 2012

In this letter, the constant driving power reduction ratio has been achieved for column drivers regardless of the input image by incorporating a new static power reduction scheme into the previous dynamic power reduction method. The measured power reduction ratio is around 50% for a 120 Hz liquid crystal display panel in such cases of still input video and fallback.

• Journal of Magnetics
• /
• v.19 no.4
• /
• pp.365-371
• /
• 2014

The aim of this study was to evaluate the utility of 3-D images by comparing and analyzing reconstructed 3-D images from fast spin echo images of MRI cholangiopancreatography (MRCP) images using maximum intensity projection (MIP) with the subtraction images derived from dynamic tests of magnetic resonance mammography. The study targeted 20 patients histologically diagnosed with pancreaticobiliary duct disease and 20 patients showing pancreaticobiliary duct diseases, where dynamic breast MR (magnetic resonance) images, fast spin echo imaged of pancreaticobiliary duct, and 3-D reconstitution images using a 1.5T MR scanner and 3.0T MR scanner were taken. As a result of the study, the signal-to-noise ratio in the subtracted breast image before and after administering the contrast agent and in the reconstructed 3-D breast image showed a high ratio in the reconstructed image of lesional tissue, relevant tissue, and fat tissue. However, no statistically meaningful differences were found in the contrast-to-noise ratio of the two images. In the case of the MRCP image, no differences were found in the ratios of the fast spin echo image and reconstructed 3-D image.