• 대한전자공학회논문지SP
• /
• 제41권1호
• /
• pp.21-28
• /
• 2004

내용기반 영상검색 분야에서 색, 질감, 모양 등과 같은 영상의 시각적인 내용을 표현하기 위하여 수치화한 특징들이 많이 제안되었다. 이런 특징들은 모두 독립적이라고 가정하기 때문에 한 특징 벡터를 추출할 때는 다른 특징들과의 상관성을 전혀 고려하지 않는다. 이 논문에서는 색과 질감 사이의 관계를 고려하여 새로운 CCE(channel color energy) 특징을 제안한다. 자연 영상을 대상으로 한 실험결과를 분석한 결과 제안하는 방법이 정규 가중거리 비교 방법과 SCFT(sequential chromatic Fourier transform) 기반 색 질감 방법에 비해 우수한 성능을 보이는 것을 확인할 수 있었다.

• 정보처리학회논문지B
• /
• 제10B권6호
• /
• pp.629-638
• /
• 2003

본 논문에서는 인간시각에 대한 워터마크의 무감지성을 향상하고 워터마크를 제거하고자 하는 공격에 강인한 워터마킹 방법을 제안한다. 제안하는 방법은 워터마크를 삽입할 대상의 DCT 블록에 대한 인간의 시각적인 특성을 고려하여 워터마크의 삽입 여부와 블록에 삽입될 워터마크의 위치와 강도를 적응적으로 결정한다. 워터마크될 블록을 선택하기 위하여 사용되는 특징은 텍스쳐, 휘도, 대비이다. 본 논문은 제안된 방법의 성능을 평가하기 위하여 절단, 영상강화, 저주파 필터링, PEG 압축의 영상처리 공격에 대한 실험결과를 보인다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권1호
• /
• pp.436-450
• /
• 2017

Recently, the method based on fractional order partial differential equation has been used in image processing. Usually, the optional order of fractional differentiation is determined by a lot of experiments. In this paper, a denoising model is proposed based on adaptive fractional order anisotropic diffusion. In the proposed model, the complexity of the local image texture is reflected by the local variance, and the order of the fractional differentiation is determined adaptively. In the process of the adaptive fractional order model, the discrete Fourier transform is applied to compute the fractional order difference as well as the dynamic evolution process. Experimental results show that the peak signal-to-noise ratio (PSNR) and structural similarity index measurement (SSIM) of the proposed image denoising algorithm is better than that of other some algorithms. The proposed algorithm not only can keep the detailed image information and edge information, but also obtain a good visual effect.

• 대한전자공학회논문지SP
• /
• 제46권5호
• /
• pp.111-119
• /
• 2009

본 논문에서는 영상의 영역별 특성을 고려한 영상의 보간 방법을 제안한다. 먼저 입력 영상은 에지 영역과 평탄한 저주파 영역으로 나뉜다. 그리고 에지 영역은 다시 방향성이 존재하는 에지 영역과 텍스처와 같이 에지의 방향성이 존재하지 않는 복잡한 고주파 영역으로 구분된다. 평탄한 저주파 영역에서는 쌍선형보간법 (Bilinear Interpolation), 방향성이 없는 복잡한 고주파 영역은 3차 컨벌루션 보간법 (Cubic Convolution Interpolation), 방향성이 있는 에지 영역은 NEDI (New Edge directed Interpolation)를 각각 적용한다. 다양한 영상에 대한 실험결과 제안한 방법이 기존이 방법보다 주관적 화질이 뛰어나고 우수한 성능을 발휘하는 것을 확인하였다.

• 한국산업정보학회논문지
• /
• 제7권4호
• /
• pp.9-16
• /
• 2002

멀티미디어 정보검색 중 내용기반 영상검색은 색상, 질감, 형태 등의 영상 내용 특징들을 이용하여 검색하는 방법으로, 색상과 질감 특징이 영상 검색 시스템에서 일반적으로 널리 사용되고 있다. 그러나 이 시스템은 영상의 형태가 서로 다른 경우 서로 다른 내용을 나타내므로 유사 영상검색에서 오류를 수반할 수 있다. 그러므로 영상의 특징을 나타내는 형태의 사용은 효과적인 내용기반 영상검색에서 중요하다. 그래서 본 논문에서는 영상의 윤곽선에 의한 전역 특징 필터링 처리 후에 형태정보의 히스토그램에 의한 성능이 더 우수한 형태 유사도 영상 검색 시스템을 개발한다.

• Journal of Nutrition and Health
• /
• 제32권8호
• /
• pp.967-973
• /
• 1999

The purpose of this study was to analyze sensory evaluation, to assess visual serving size and plate waste estimates of daily menu, and the identify customer expectation, perception and satisfaction. Questionnaires of sensory evaluation, serving size and were waste were developed and hand-delivered to 2,520 people. A total of 2,255 questionnaires were usable: a 89.5% response rate. Customer satisfaction questionnaires were handed out to 700 customers: (100 each at seven operations). A total of 551 were returned completed (78.7%). The data was analyzed using the SAS package program for Descriptive Analysis, t-test and ANOVA. The result of sensory evaluation showed that 'taste' was 3.20, 'freshness' 3.17, 'temperature' 3.25, 'texture' 3.15, 'appearance' 3.12, 'overall evaluation' 3.21, so these were little higher than 「normal」, that is 3.0. There was positive correlation among 'taste', 'freshness', 'temperature', 'texture', 'appearance' and 'overall evaluation'(p<.001). Serving size score was 2.97 and plate waste was 4.87, thus plate waste percentage was about 22-33%. As the result of customer expectation, perception and satisfaction of menu quality, characteristics. Customer satisfaction was defined as the difference expectation and perception and customer perceptions in theis survey were lower than expectation, thus this result implied customers dissatisfied in all menu quality characteristics. IPA analysis showed that 'diversity of menu selection' and 'menu price' was included in A area 'Focus here'.

• Journal of Information Processing Systems
• /
• 제18권4호
• /
• 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.

• 디자인학연구
• /
• 제19권1호
• /
• pp.79-88
• /
• 2006

사람의 얼굴은 정체성의 시각적 상징이다. 사람마다 각기 다른 얼굴 모습은 타인과 구별할 수 있도록 하는 중요한 역할을 하면서 개인의 정체성과 직결된다. 역사적으로 볼 때 얼굴에 대한 시대적 인식의 변화와 함께 표현매체와 커뮤니케이션매체가 다양해지고 발전함에 따라 얼굴을 표현하는 것에도 많은 변화가 있었다. 그러나 지금처럼 얼굴에 대한 사람들의 관심과 주목이 컸던 적이 없었다. 기술적으로는 컴퓨터그래픽스의 등장으로 얼굴표현의 새로운 전기를 맞이하게 되었다. 특히 시각 이미지들이 디지털형태로 제작, 저장, 전송할 수 있게 되어 시간적, 공간적제약이 없어지면서 시각이미지정보는 커뮤니케이션에서 그 비중이 전보다 더 커지고 있다. 그 중에서 디지털로 만들어진 얼굴 이미지는 그 활용도가 점차 확대되고 있다. 이에 따라 컴퓨터그래픽스를 이용한 얼굴의 3d (3-dimensional) 표현은 수년전부터 얼굴 각 부분의 형태와 텍스추어 맵 등 각 요소들을 필요할 때 마치 퍼즐 조각처럼 조립해서 전문적인 기술이 없이도 손쉽게 표현할 수 있게 되었다. 본 연구에서는 3d 얼굴표현의 제작단계별 내용을 연구하고 그 결과를 바탕으로 케이스 스터디에서 시각화함으로써 3d 전문가가 아닌 일반 시각디자이너들이 3d 형태의 얼굴을 효과적으로 표현하는 방법을 연구한다.

• 한국의류산업학회지
• /
• 제15권5호
• /
• pp.682-693
• /
• 2013

Camouflage is evaluated by scientific principle in the fields of biology, military science, and art. It has a strong influence on contemporary fashion and means exposure with concealment. This study analyzed the visual characteristics of camouflage patterns in fashion design through documentaries and fashion photos. The fashion design results areas follow. The simple blending of a disruptive motif indicated an inaccurate repetition of a disruptive motif, the discontinuous or continuous connection of disruptive motif, the irregular repetition of a disruptive animal silhouette, the collage of a different disruptive motif, the craft of a disruptive motif and the intensive color match of a disruptive motif. It represented the maximization of complication, fantastic and fanciness. The overlap of a disruptive motif showed the overlap of disruptive print patterns with transparency and an overlap of different fabrics with a disruptive pattern. It represented spatial relationships of three dimensions as well as the maximization of visual illusion and the reinforcement of attractiveness. The blurring of a disruptive motif showed the pointage of disruptive motif, the pointage of image, value gradation, the whole blurring of a disruptive pattern cluster and stained appearance. It represented the obscurity of motif form, the uncertainty of object and double meaning. The trompe l'oeil of a partial background object showed the realistic and the painterly imitation of color and texture for partial objects through a close-up. It represented amazement and pleasure by illusion, scarcity and the decoration of surface and synecdochical remind. In conclusion, camouflage in fashion was weakened and modified from a classical military context by a unique expression of various motifs.

• 한국조경학회지
• /
• 제13권2호
• /
• pp.37-70
• /
• 1985

The purpose of this study is to present objective basic data for environmental design by the quantitative analysis of visual quality emboded in physical environment. For this, as for the front garden of high schools, the spatial image was measured by the S.D. Scale Method, Factor Analysis was proceeded by the principal component analysis and the visual preference was investigated by the Paired Comparision Method. The scale values of plain and unpleasant road surface and external appearance of buildings, which are related to emotions of simpleness fell from straightness and stability, were found to be high. But, except for the road surface of Kyunggi High School, scale values of variables explaining the variation of the quality of materials, level of floor and rythm were generally low. For all green spaces, scale values of variables explaining the degree of pleasantness was found to be generally high. And, those explaining tidiness and characteristics of green spaces were not in the same tendency. But, the green spaces of Youngdong High school can be considered to the space with plenty of visual absorption uniqueness were high. As for the correlation between variables, variables for green spaces(12 and 26) and those for overall view of front garden( 1 and 4) revealed high positive correlation. Also, "order - disorder" and "convenient- incovenient" included in road surface variable can be regarded to have the same meaning since the correlation coefficient between them is very high, 0.7045. Image variables including road surface, external appearance of buildings, green spaces and overall view of front garden showed 91.21~61.08% of total variance. Thus, the remains can be considered to be the error valiance or specific variance. In Fctor I, II and III, main components explaining the road surface image of front gardens are order, hardness, texture, color, gradient and rythm. As for the external appearance of b wilding, variables of color, hardness, stability, peculiality and shape revealed high values of factor load. For all variables, communality was drastically high and ellen values and common variance were found to be very high in Factor I. As for the front gardens, variables explaining volume and peculiarity were found to be the main components of Factor I. In Factor II and III, variables of factor load were tidiness, pleasantness.