• 제목/요약/키워드: Color image scale

검색결과 317건 처리시간 0.027초

컬러 불변 특징과 광역 특징을 갖는 확장 SURF(Speeded Up Robust Features) 알고리즘 (Extended SURF Algorithm with Color Invariant Feature and Global Feature)

  • 윤현섭;한영준;한헌수
    • 대한전자공학회논문지SP
    • /
    • 제46권6호
    • /
    • pp.58-67
    • /
    • 2009
  • 대응점 정합은 컴퓨터 비전에서 중요한 작업 중에 하나지만 스케일, 조명, 시점이 변한 환경에서 대응점을 찾는 과정은 매우 어렵다. 대응점 정합 알고리즘인 SURF(Speeded Up Robust Features) 기법은 SIFT(Scale Invariant Feature Transform) 기법에 비해 정합 속도가 매우 빠르고 비슷한 정합 성능을 보여 널리 사용되고 있다. 하지만 SURF 기법은 흑백 영상과 지역 공간정보를 사용하기 때문에 유사한 패턴이 존재하는 영상에서 대응점의 정합 성능이 매우 떨어진다. 이런 문제점을 해결하기 위해 본 논문에서는 강인한 컬러 특징 정보와 광역적 특징 정보를 이용하는 확장 SURF 알고리즘을 제안한다. 제안하는 알고리즘은 비슷한 패턴이 존재하더라도 색상정보과 광역 공간 정보를 추가로 사용되기 때문에 대응점 매칭 성능을 크게 향상시킨다. 본 논문에서는 제안하는 방법의 우수성을 조명과 시점이 변화하고 유사한 패턴들을 갖는 영상들에 적용하여 기존의 방법들과 비교 실험함으로서 입증하였다.

동적 원추 세포 응답을 이용한 높은 동적 폭을 갖는 영상 색상 보정 방법 (Color Correction Method for High Dynamic Range Image Using Dynamic Cone Response Function)

  • 최호형;윤병주
    • 전자공학회논문지
    • /
    • 제49권9호
    • /
    • pp.104-112
    • /
    • 2012
  • 최근 들어, 실제 환경 영상과 디스플레이 영상간의 인지적 불일치를 위해, 인간 시각 시스템을 흉내 낸 높은 동적 범위를 갖는 영상 촬영 기술이 LCD/LED 디스플레이 장치에 사용되고 있다. 그러나 HDR 영상에는 섬광 한계뿐만 아니라 국부 영상 대비 등의 문제가 있다. 이러한 문제를 해결하기 위해 중심/주변 레티넥스, 다중 스케일 영상 레티넥스, 톤 매핑 방법, iCAM06 등 여러 가지 색상 보정 방법들이 제안되었다. 그러나 기존의 방법들에서는 결과 영상내의 전반적으로 특정 색상 두드러짐 현상이 발생한다. 따라서 본 논문에서는 동적 원추 세포 응답을 이용한 영상 보정 방법을 제안한다. 제안하는 방법은 톤 매핑과 동적 원추 세포 응답으로 구성된다. 색도 성분과 비색도 성분의 선형적인 보간을 이용하여 톤 매핑을 수행하고, 톤 매핑의 결과 영상에서 동적 원추 세포 응답 함수를 이용하여 원추세포 응답을 획득한다. 획득된 원추세포 응답을 이용하여 색상 보정을 수행한다. 이는 인간 눈의 동적 응답을 예측함과 동시에 보정된 영상이 실제 환경과 최대한 일치하도록 한다. 실험 결과에서 제안한 방법이 기존의 방법에 비해 색상 보정 효과가 우수함을 보인다.

퍼지 논리를 이용한 컬러 영상 필터 (Color Image Filter Using Fuzzy Logic)

  • 고창룡;구경완;김광백
    • 한국컴퓨터정보학회논문지
    • /
    • 제16권12호
    • /
    • pp.43-48
    • /
    • 2011
  • 현재 영상 정보 개선을 위한 다양한 영상 필터링 알고리즘들이 제시되고 있으며, 그 중에서 기존의 퍼지 논리를 이용한 필터링 알고리즘은 다른 기존의 필터링 방식에서 잡음이 제거된 후에 블러링 효과와 잡음 제거율이 반비례하는 단점을 개선하기 위해서 퍼지 논리를 적용하였다. 그러나 기존의 퍼지 필터 방법은 그레이 영상의 단색 정보만을 잡음의 판단 기준으로 하였기 때문에 칼라 영상에서는 비효율적이다. 따라서 본 논문에서는 기존의 퍼지 논리를 이용한 필터링 알고리즘의 문제점을 개선하는 동시에 컬러 영상에 적용할 수 있는 퍼지 필터 알고리즘을 제안한다. 제시된 퍼지 필터 알고리즘은 영상의 RGB 컬러 정보를 각각의 R, G, B 채널 영상으로 분리하고, 각 채널 영상에 서 마스크가 위치한 기준 픽셀의 잡음 가능성 정도를 퍼지 논리에 적용하여 판단한다. 잡음 정도에 따라서 출력 영상의 화소값을 평균값 또는 중간값으로 결정한다. 제안된 방법을 잡음이 존재하는 칼라 영상에 적용한 결과, 단색 정보를 기준으로 처리하는 기존의 필터 방법에 비해서 효과적인 것을 확인하였다.

인터플로라 세계월드컵대회의 웨딩부케 색채이미지 분석 (Analysis of Color Image Wedding Bouquet in the Interflora World Cup Competition)

  • 여화선;김신원;박시현
    • 화훼연구
    • /
    • 제18권4호
    • /
    • pp.308-314
    • /
    • 2010
  • 화훼디자인 분야에 있어서 색채의 중요성이 부각된 것은 오래 되었지만 전문적인 교육과 표준화 작업은 미흡한 실정이며, 화훼디자인 분야에서 큰 비중을 차지하고 있는 웨딩부케도 이러한 문제점을 직시하고 있다. 이에 본 연구는 인터플로라 세계월드컵대회의 출품작 중 웨딩부케의 색채이미지 분석을 통해 화훼디자인의 기초자료로 활용하고자 연구를 수행하였다. 분석 결과, 명도와 채도가 높은 색채를 선호하였고, 난색과 한색의 고른 분포가 나타났다. 반면 파란색(Blue)의 사용은 없는 것으로 결과가 도출되어, 화색(花色) 중 파란색(Blue)을 띠는 식물의 희소성을 보여주는 결과라고 판단되었다. 색채 배색의 분석 결과 대륙별로 차이점을 보이고 있었다. 유럽의 웨딩부케는 한가지 색에 치중하지 않고 다양한 색채 배색이 나타난 반면, 아시아의 웨딩부케는 빨간색(Red)계열이 나타났다. 본 연구에서 살펴본 결과 웨딩부케의 색채이미지스케일은 12개의 대표이미지 중 8개의 이미지에 분포하였고, '맑은, 우아한, 점잖은, 모던한'의 4개의 이미지에는 나타나지 않았다.

영상 분석장치를 이용한 골 흑화도의 정량적 평가에 관한 연구 (A QUANTITATIVE STUDY OF BONE DENSITY ON RADIOGRAM BY USING IMAGE ANALYZER)

  • 최원재;김재덕
    • 치과방사선
    • /
    • 제25권2호
    • /
    • pp.521-533
    • /
    • 1995
  • This study was performed to develop and evaluate the method to detect Quantitatively the serial changes in the size of artificial lesion in the spongious bone by automatic color image analyzer. 15 intraoral radiograms taken before and after endodontic treatment of 5 cases were used for contour line analysis. 30 intraoral radiograms taken by geometrically standardized apparatus before and after serially the formation of artificial lesions of 0.80, 1.20, 1.75, 2.00mm in diameter at the periapical area and interdental area of spongious bone were used. The analysis of image according to the variance of lesion size by 0.25, 0.35, 0.55, and 0.85mm serially was performed by the histogram and the color enhancement with subtraction. The images inputted by CCDcamera were digitized and analyzed by NEXUS QUBE program with NEC PC-9801 computer. The obtained results were as follows: 1. There was no reliability in the analysis of lesions by contour line 2 .. The mean difference of the grey scale at each pixel was 1 step between reference image and the corrected images. 3. In the analysis by histogram of the artificial lesion in spongeous bone, the change over 0.55mm in the mesiodistal size was detectable by the change of the numbers of pixel showing the change in grey scale. 4. In the analysis by histogram of the artificial lesion in spongeous bone, the change over 0.25mm in the buccolingual size was detectable by the change in grey scale. 5. By color enbancement with- subtraction, each lesion was able to be isolated and the change in it's mesiodistal size was detectable visually , but not in it's buccolingual size.

  • PDF

광공진 현상을 이용한 입체 영상센서 및 신호처리 기법 (Optical Resonance-based Three Dimensional Sensing Device and its Signal Processing)

  • 박용화;유장우;박창영;윤희선
    • 한국소음진동공학회:학술대회논문집
    • /
    • 한국소음진동공학회 2013년도 추계학술대회 논문집
    • /
    • pp.763-764
    • /
    • 2013
  • A three-dimensional image capturing device and its signal processing algorithm and apparatus are presented. Three dimensional information is one of emerging differentiators that provides consumers with more realistic and immersive experiences in user interface, game, 3D-virtual reality, and 3D display. It has the depth information of a scene together with conventional color image so that full-information of real life that human eyes experience can be captured, recorded and reproduced. 20 Mega-Hertz-switching high speed image shutter device for 3D image capturing and its application to system prototype are presented[1,2]. For 3D image capturing, the system utilizes Time-of-Flight (TOF) principle by means of 20MHz high-speed micro-optical image modulator, so called 'optical resonator'. The high speed image modulation is obtained using the electro-optic operation of the multi-layer stacked structure having diffractive mirrors and optical resonance cavity which maximizes the magnitude of optical modulation[3,4]. The optical resonator is specially designed and fabricated realizing low resistance-capacitance cell structures having small RC-time constant. The optical shutter is positioned in front of a standard high resolution CMOS image sensor and modulates the IR image reflected from the object to capture a depth image (Figure 1). Suggested novel optical resonator enables capturing of a full HD depth image with depth accuracy of mm-scale, which is the largest depth image resolution among the-state-of-the-arts, which have been limited up to VGA. The 3D camera prototype realizes color/depth concurrent sensing optical architecture to capture 14Mp color and full HD depth images, simultaneously (Figure 2,3). The resulting high definition color/depth image and its capturing device have crucial impact on 3D business eco-system in IT industry especially as 3D image sensing means in the fields of 3D camera, gesture recognition, user interface, and 3D display. This paper presents MEMS-based optical resonator design, fabrication, 3D camera system prototype and signal processing algorithms.

  • PDF

A Robust Face Detection Method Based on Skin Color and Edges

  • Ghimire, Deepak;Lee, Joonwhoan
    • Journal of Information Processing Systems
    • /
    • 제9권1호
    • /
    • pp.141-156
    • /
    • 2013
  • In this paper we propose a method to detect human faces in color images. Many existing systems use a window-based classifier that scans the entire image for the presence of the human face and such systems suffers from scale variation, pose variation, illumination changes, etc. Here, we propose a lighting insensitive face detection method based upon the edge and skin tone information of the input color image. First, image enhancement is performed, especially if the image is acquired from an unconstrained illumination condition. Next, skin segmentation in YCbCr and RGB space is conducted. The result of skin segmentation is refined using the skin tone percentage index method. The edges of the input image are combined with the skin tone image to separate all non-face regions from candidate faces. Candidate verification using primitive shape features of the face is applied to decide which of the candidate regions corresponds to a face. The advantage of the proposed method is that it can detect faces that are of different sizes, in different poses, and that are making different expressions under unconstrained illumination conditions.

고등학교 전정의 공간 Image와 시각적 선호도 조사에 관한 연구 (A Study on the Spatial Image and Visual Preference for Front Gardens of High School)

  • 진희성;서주환
    • 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.

  • PDF

야구 유니폼의 이미지 평가에 관한 연구 (A Study on Image Evaluation of Baseball Uniform)

  • 표유경;이명희
    • 복식
    • /
    • 제50권8호
    • /
    • pp.43-55
    • /
    • 2000
  • The objectives of this study were to investigate the differences of image evaluation of baseball uniform by uniform design and perceiver's gender. and to examine how baseball uniform preferences vary according to perceiver's gender. Stimuli consisted of 12 color photographs of a male model wearing a baseball uniforms which were manipulated according to the color of shorts and pants. A semantic differential scale of 23 items were used to evaluate the image of the stimuli. Subjects were 288 males and females. Five dimensions derived to account for the image of baseball uniform. These were manly, ability, activity, preference, and visibility. Wearing of red shirts had a positive effect on the evaluation of ability, activity, and visibility. Dark blue shirts had a positive effect on the evaluation of preference. Grey uniforms had negative effects on the evaluation of ability, activity, and visibility. Men liked white uniforms and vertical stripes uniforms of black and white more than dud women. Women talked dark blue shirts more than did men.

  • PDF

바디페인팅에 활용된 배색 이미지 연구 (The Characteristics of Practical Color Combination in Body Painting)

  • 이해미루;김성남
    • 패션비즈니스
    • /
    • 제19권1호
    • /
    • pp.77-94
    • /
    • 2015
  • Due to the inflammatory of body exposure it did not become popular to the Korean nation but the body painting as a body art is definitely required for it be become a new pure artwork. In this body painting color is the core factor for visual part and expression and coloring obtained from the color is very important in creating effective image. In Korea beauty industry the researches are limited to the study on coloring expression of general beauty makeup. Therefore, this research analyzes color images in recent body painting artworks by defining characteristics of colors and coloring applied by theme. For the research subjects, dominant and secondary colors were extracted from the artworks presented in preliminary and final rounds of year 2012 and 2013 World Body Painting Festival. For the selection of final coloring stimulation the most frequent coloring by theme was first chosen. Among them, 2 individual coloring bands were selected by theme among the high frequency colors. For the analysis of coloring image shown in body painting works total 8 coloring bands were created and they were compared and analyzed by indicating each divided coloring band on the coloring image scale by theme. In this research coloring image analysis was done after examining colors and coloring of artworks presented in World Body Painting Festival by theme. This research has its meaning that it provides information and guideline for coloring design work of body painting by analyzing coloring image used in color and coloring of body painting by theme.