• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권12호
• /
• 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.

• 전기전자학회논문지
• /
• 제11권4호
• /
• pp.219-226
• /
• 2007

본 논문은 HDR(High Dynamic Range) 영상을 기존의 JPEG 압축 방법을 이용하여 효율적으로 압축할 수 있는 방안을 제안한다. 입력 HDR 영상을 동적 영역 압축(Dynamic range compression)하여 통해 얻어지는 LDR(Low Dynamic Rage) 영상 및 HDR 영상과 LDR영상의 비율을 나타내는 비율 (Ratio) 영상으로 분리한다. LDR 영상은 하위 호환성을 유지하기 위해 기존의 JPEG 알고리듬을 이용하여 압축하며, 비율 영상은 각 블록별로 HVS(Human Visual System)이 인지하는 차이를 모델링 한 비용함수를 최소화 하도록 압축한다. 따라서 제안하는 알고리듬을 적용하면 동일한 조건에서 압축된 결과 영상에 왜곡이 적게 발생하게 되며, 컴퓨터 모의실험을 통해 그 유효성을 확인한다.

• Journal of Information Display
• /
• 제12권2호
• /
• 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.

• 한국도로학회논문집
• /
• 제13권1호
• /
• pp.1-11
• /
• 2011

본 연구는 교량 중에 장대교량을 대표하는 현수교에 대한 설계 시 고려요소인 중앙경간과 새그비의 변화에 따른 경관선호도를 파악하고 경관선호도와 이미지요인과의 관계, 설계요소와 이미지요인과의 관계를 SD법을 적용하여 교량의 이미지 특성을 파악함으로써 경관적 환경을 조성할 수 있는 방안을 제시하는데 연구의 목적이 있다. 교량경관에 대한 경관적 선호도를 분석한 결과 교량의 중앙경간의 길이가 길어질수록 선호하는 새그비의 범위는 줄어드는 것으로 보아 중앙경간이 길어질수록 낮은 새그비를 선호하며, 중앙경간이 길어질수록 경관선호도가 높아짐을 알 수 있었다. 경관선호도와 이미지요인에서는 경관선호도가 높은 새그비의 속성에는 "안정성" "조형성" "심미성"과 모두(+)상관관계에 있지만 "조형성"의 영향이 미비하였다. 설계요소와 이미지 요인과의 관계에서는 중앙경간과 새그비의 요인에는 "안정성"이라는 요인과 더 관계되어 있었으며, 새그비가 낮아질수록 중앙경간이 길어질수록 "안정성"이 높게 평가되었다. 이 결과, 경관적으로 선호하는 이미지의 특성 중 "조형성"의 이미지 특성이 미비한 것으로 나타나 "조형성"의 이미지특성의 부각을 위해 중앙경간과 새그비의 비례요소가 아닌 균형과 대칭의 요소의 변화를 주어 보완실험을 하였다. 그 결과 3주탑현수교와 새그의 좌우대칭이 다른 현수교가 "조형성"의 이미지 특성이 더 부각되는 결과를 볼 수 있었고, 추후에 현수교의 경관설계를 할 때 비례요소뿐만 아니라 균형과 대칭의 요소도 고려하여 설계 시 반영하여야 할 것이다.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 1998년도 춘계학술대회 논문집
• /
• 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.

• 한국멀티미디어학회논문지
• /
• 제21권2호
• /
• 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.

• 한국멀티미디어학회논문지
• /
• 제11권1호
• /
• pp.23-33
• /
• 2008

본 논문에서는 공간정보와 색상변화율을 이용한 영상검색방법을 제안한다. 제안된 방법은 공간정보를 추출하기 위하여 임계치 $\tau$에 의하여 영상으로부터 색상영역들을 추출한다. 이 과정에서 색상 영역의 수와 색상변화 횟수를 계산하며, 이 값들을 이용하여 색상변화율을 얻는다. 영상간의 유사도는 공간정보에 의해여 측정되며, 색상변화율은 유사한 색상변화율을 가진 이미지가 보다 높은 검색 순위가 갖도록 돕는다. 다양한 자연영상들을 이용한 실험을 통하여 제안된 방법이 색상정보를 이용한 다른 일반적인 방법들보다 뛰어난 성능을 보임을 확인하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅲ
• /
• 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
• /
• 제34권3호
• /
• 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
• /
• 제19권4호
• /
• 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.