• 한국멀티미디어학회논문지
• /
• 제18권10호
• /
• pp.1197-1204
• /
• 2015

Smoke detection plays an important role for the early detection of fire. In this paper, we suggest a newly developed method that generated LBPV(Local Binary Pattern Variance)s as special feature vectors from RGB contrast images can be applied to detect smoke using SVM(Support Vector Machine). The proposed method rearranges mean value of the block from each R, G, B channel and its intensity of the mean value. Additionally, it generates RGB contrast image which indicates each RGB channel’s contrast via smoke’s achromatic color. Uniform LBPV, Rotation-Invariance LBPV, Rotation-Invariance Uniform LBPV are applied to RGB Contrast images so that it could generate feature vector from the form of LBP. It helps to distinguish between smoke and non smoke area through SVM. Experimental results show that true positive detection rate is similar but false positive detection rate has been improved, although the proposed method reduced numbers of feature vector in half comparing with the existing method with LBP and LBPV.

• 한국정보디스플레이학회:학술대회논문집
• /
• 한국정보디스플레이학회 2007년도 7th International Meeting on Information Display 제7권2호
• /
• pp.1661-1663
• /
• 2007

The contrast of display is one of the important specifications. Even if the contrast indicates luminance range which is a capability of the display and is greater in lower luminance or higher luminance, we consider that the greater contrast gets not the better performance. It is not the same value in human visual system. In practice, it is difficult to achieve the full dynamic range seen by human beings using electronic equipment. Therefore, we consider ambient condition and human perception to calculate perceptual contrast using the CIECAM02. In this paper, we propose perceptual contrast that is calculated using the brightness of CIECAM02.

• 대한전기학회논문지:전기물성ㆍ응용부문C
• /
• 제51권11호
• /
• pp.536-540
• /
• 2002

This paper proposes a method to drive an AC plasma display panel(PDP) with a significantly improved contrast ratio. In the proposed method, during the first sub-field of one frame, all PDP cells are reset by the ramp waveform, and during the other sub-field, only the cells turned on in the previous sub-field are reset. No light is emitted during the reset period of every sub-field except the first sub-field. For a 10-bit picture, the luminance of the dark level for the proposed method is 10 times lower than that for the conventional method, in which the ramp waveform for the reset is used in every sub-field. Accordingly, the contrast ratio for the proposed method is 10 times higher than that for the conventional method. For the 10-bit picture, the measured contrast ratio was about 3080:1 for the proposed method and about 285:1 with the conventional method, a result the contrast ratio has been increased in 10.8 times. This result shows that the proposed method can realize an image with high contrast ratio.

• 복식문화연구
• /
• 제16권6호
• /
• pp.992-1007
• /
• 2008

This study was meant to offer the data for predicting the product plan answering the diverse demands for consumers based on the results of analyzing the image and formative property by transforming the stripe patterns. The concrete study way is composed of the collected stimulus centering on the interval of the stripe pattern and value contrast coloration. Consequently 192 stimuli, changed by the pattern direction and pattern interval, clothing style, and contrast coloration, are selected. The experimental materials made for this study are a set of stimuli and response scale. The statistics way used in analysis was factor analysis, ANOVA, dispersion analysis, multiple classification analysis. The results of this study were summed as following. Firstly, In the value contrast, a pair of 27 adjectives were made of attractiveness, activeness, gracefulness, visibility, and tenderness dimension. Secondly, the direction of the pattern, interval, clothing style, and contrast coloration were respectively transformed according to value contrast.

• 한국통신학회논문지
• /
• 제38A권11호
• /
• pp.928-937
• /
• 2013

본 논문은 특이값 분해와 영상 피라미드를 이용한 새로운 대비 개선 방법을 제안한다. 제안된 방법은 다음과 같이 네 단계로 진행 된다. 먼저 전역 명암대비와 지역적 디테일을 향상시키기 위해 영상 피라미드를 이용하여 영상을 기저영상과 세부영상들로 분해한다. 전역 명암대비 향상은 특이값 분해를 이용하여 영상 전체의 명암대비를 향상시키고, 지역적 디테일 향상은 가중치를 이용하여 개선시킨다. 영상 합성은 영상의 컬러 일관성을 유지하기 위해 컬러와 명암성분들을 결합한다. 실험 결과를 통해 제안된 방법은 기존의 방법들보다 영상의 세부 정보를 강화하면서 전체적인 명암대비 개선을 보인다.

• ETRI Journal
• /
• 제41권6호
• /
• pp.797-810
• /
• 2019

Image saliency detection is the basis of perceptual image processing, which is significant to subsequent image processing methods. Most saliency detection methods can detect only a single object with a high-contrast background, but they have no effect on the extraction of a salient object from images with complex low-contrast backgrounds. With the prior knowledge, this paper proposes a method for detecting salient objects by combining the boundary contrast map and the geodesics-like maps. This method can highlight the foreground uniformly and extract the salient objects efficiently in images with low-contrast backgrounds. The classical receiver operating characteristics (ROC) curve, which compares the salient map with the ground truth map, does not reflect the human perception. An ROC curve with distance (distance receiver operating characteristic, DROC) is proposed in this paper, which takes the ROC curve closer to the human subjective perception. Experiments on three benchmark datasets and three low-contrast image datasets, with four evaluation methods including DROC, show that on comparing the eight state-of-the-art approaches, the proposed approach performs well.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2009년도 춘계학술대회
• /
• pp.419-421
• /
• 2009

얼음의 경우 주변의 압력, 습도 등의 환경에 따라서 결빙점이 달라지는데 얼음의 투명도를 측정함으로써 얼음의 결빙 과정을 유추할 수 있고 얼음의 밀도 등의 특징을 파악하는데 도움이 된다. 본 논문은 이미지 상에 포함되어 있는 얼음의 투명도를 측정하는 방법을 제시하고자 한다. 얼음이 포함된 이미지를 먼저 $CIEL^*a^*b^*$ 색 공간으로 변경한 후, $L^*$ 값의 평균과 RMS(Root Mean Square) Contrast를 조합해서 얼음의 투명도를 측정하는 지수를 만들었다. 얼음 이미지의 경우 Wever Contrast나 Michelson Contrast 등 기존의 컨트라스트 비교에 비해 훨씬 만족할만한 성능을 보여주었다.

• Journal of the Optical Society of Korea
• /
• 제17권1호
• /
• pp.86-90
• /
• 2013

Various methods have been proposed for enhancing the contrast of laser speckle contrast image (LSCI) in subcutaneous blood flow measurements. However, the LSCI still suffers from low image contrast due to tissue turbidity. Herein, a physicochemical tissue optical clearing (PCTOC) method was employed to enhance the contrast of LSCI. Ex vivo and in vivo experiments were performed with porcine skin samples and male ICR mice, respectively. The ex vivo LSCIs were obtained before and 90 min after the application of the PCTOC and in vivo LSCIs were obtained for 60 min after the application of the PCTOC. In order to obtain the skin recovery images, saline was applied for 30 min after the application of the PCTOC was completed. The visible appearance of the tubing under ex vivo samples and the in vivo vasculature gradually enhanced over time. The LSCI increased as a function of time after the application of the PCTOC in both ex vivo and in vivo experiments, and properly recovered to initial conditions after the application of saline in the in vivo experiment. The LSCI combined with the PCTOC was greatly enhanced even in deep vasculature. It is expected that similar results will be obtained in in vivo human studies.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권11호
• /
• pp.4043-4064
• /
• 2021

Night-time image quality evaluation is an urgent requirement in visual inspection. The lighting environment of night-time results in low brightness, low contrast, loss of detailed information, and colour dissonance of image, which remains a daunting task of delicately evaluating the image quality at night. A new blind quality assessment metric is presented for realistic night-time scenario through a comprehensive consideration of contrast, texture, and colour in this article. To be specific, image blocks' color-gray-difference (CGD) histogram that represents contrast features is computed at first. Next, texture features that are measured by the mean subtracted contrast normalized (MSCN)-weighted local binary pattern (LBP) histogram are calculated. Then statistical features in Lαβ colour space are detected. Finally, the quality prediction model is conducted by the support vector regression (SVR) based on extracted contrast, texture, and colour features. Experiments conducted on NNID, CCRIQ, LIVE-CH, and CID2013 databases indicate that the proposed metric is superior to the compared BIQA metrics.

• 핵의학기술
• /
• 제18권1호
• /
• pp.19-25
• /
• 2014

PET/MRI에서는 MRI의 진단적 가치를 높이기 위해 T1 조영제를 사용하고 있다. PET의 감쇠 보정을 위해 T1 시컨스 계열인 VIBE DIXON은 조영제에 직접적으로 영향을 미치지만, 실제 ${\mu}-map$과 감쇠 보정된 PET 영상에는 큰 변화가 없었다. 그러므로 PET/MRI 검사시 조영제 사용은 PET 데이터 얻기 전 후 언제든 사용할 수 있을 것이다.