• 전자공학회논문지CI
• /
• 제40권2호
• /
• pp.1-8
• /
• 2003

본 논문에서는 컬러 영상에서 Dominant 컬러쌍 정보를 이용한 객체기반 영상검색 기법을 제안한다. 기존의 대부분 연구에서는 관심있는 객체를 포함한 영상 전체에 대해 특징값을 추출하여 유사 영상을 검색함으로써 배경으로 인해 검색 성능이 나빠지는 단점이 있었다. 본 논문에서는 관심있는 객체 정보만 질의로 사용하고 DB내의 영상들에 대해서도 객체가 존재할 수 있는 후보 영역을 추출한 후 유사도를 측정하는 방법을 제안한다. 제안하는 기법은 평탄 컬러 영역들이 이웃하고 있는 경계부분에서의 Dominant 컬러쌍 정보를 추출하여 특징값으로 사용하였으며, 유사도는 색상을 이용한 Color Correlogram 방법을 사용하였다. 제안하는 Dominant 컬러쌍 특징값은 이동, 회전, 그리고 크기변화에 강건한 특성을 갖는다. 질의 객체 영상에 대해서 DB내에 있는 각각의 영상에 대해 영상 전체를 비교하는 것이 아니라 객체가 존재하는 영역을 추출한 후 유사도를 측정함으로써, 배경 컬러에 의해 영상이 잘못 검출되는 오류가 줄고, 검색 성능이 향상됨을 실험을 통해 확인하였다.

• 한국통신학회논문지
• /
• 제22권5호
• /
• pp.889-898
• /
• 1997

Most general content-based image retrieval techniques use color and texture as retrieval indices. Spatial information is not used to color histogram and color pair based on color retrieval techniques. This paper proposes the selection of a set of representative in the duplicated color histogram, the analysis of spatial information of the selected colors and the image retrieval process based on the duplicated color histogram and spatial information. Two color historgrams for background and object are used in order to decide on color selection in the duplicated color histogram. Spatial information is obtained using a maximum entropy discretization. A retrieval process applies to duplicated color histogram and spatial to retrieve input images and relevant images. As the result of experiment of the image retrieval, improved color his togram and spatial information method hs increased the retrieval effectiveness more the color histogram method and color pair method.

• 한국염색가공학회지
• /
• 제17권2호
• /
• pp.19-25
• /
• 2005

A colour-difference formulae would be based on a colour appearance model, but, So far, most colour-difference formulae in common use are based on empirical fits to data. Therefore, of the many proposed, none are completely satisfactory but advances have been made in recent years. A new color-difference data set has been produced with the aims of making a comparison of the advanced CIE Lab formulae as well as confirming the effect of color-difference. 416 low lightness pairs that have only lightness-difference were produced for evaluation of CIE Lab-based formulae on lightness-difference from glossy polyester fabric. The standard color-difference pair was prepared and used. It was neutral grey sample pair that has only lightness difference. The standard pair was used to investigate lightness tolerances. And grey-scale method used to evaluate visual assessment. CIE Lab coordinates of the samples were measured using a X-Rite 8200 spectrophotometer. Visual assessments were carried out using Gretag Macbeth The Judge II Light Booth. A study of color tolerances at low lightness was carried out and get avaliable some results.

• KSBB Journal
• /
• 제25권5호
• /
• pp.459-465
• /
• 2010

A simple and efficient analytical method for the simultaneous determination of seven tar color additives was developed using ion pair high performance liquid chromatography. The conditions for HPLC analysis were as follows: column, ${\mu}$-Bondapak C18 (10 ${\mu}m$, 300 ${\times}$ 3.9 mm i.d.); gradient mobile phase, 0.025 mol/L ammonium acetate (containing 0.01 mol/L tetrabutylammonium bromide)-acetonitrile-methanol (65:25:10) as a mobile for fraction A and 0.025 mol/L ammonium acetate (containing 0.01 mol/L tetrabutylammonium bromide)-acetonitrilemethanol (40:50:10) as a mobile for fraction B; flow rate, 1.0 mL/ min; detection wavelength, 254/520/620 nm. We could attain to the detection limits as 0.01~0.05 ${\mu}$g/mL (254 nm) and 0.005~0.01 ${\mu}$g/mL (520 nm) for six red tar color additives, and 0.05 ${\mu}$g/mL (254 nm) and 0.002 ${\mu}$g/mL (620 nm) for Fast green FCF. This analytical method was applicable to determine the tar color additives contained in several commercial cold syrups.

• 한국염색가공학회지
• /
• 제18권2호
• /
• pp.15-23
• /
• 2006

A new fastness formula based on CIEDE2000 color-difference formula is developed by B. Rigg and his coworkers. It is very simple to calculate fastness grade for color change than ISO 105-A05 fastness formula based on CIELAB color-difference formula. Sample pair sets which cover a wide range color space were accumulated from NCS(Natural Color System) color book. For those sample pair sets, visual measurement experiment and instrument measurement experiment of fastness grade were carried out and each performance of ISO 105-A02 fastness formula and newly developed fastness formula was compared through degree of agreement for visual measurement result. Newly developed fastness formula indicated improved performance for measuring fastness grade but current ISO fastness formula for assessing change in color, ISO 105-A05, was confirmed that it's performance is inadequate to measure fastness grade. Then fastness formulae were examined more closely according to particular color spaces and the correlation of hue, lightness and chrom for measuring fastness grade was also considered in this study.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.49.2-49
• /
• 2001

In this paper, a skin-color model in the HSV space was developed. Based on it, face region can be separated from other parts in a image. Face can be detected by the methods of Template and eye-pair. This realized in our robot.

• 한국염색가공학회지
• /
• 제18권5호
• /
• pp.80-87
• /
• 2006

A new fastness formula based on the CIEDE2000 color-difference formula was developed by B. Rigg and his coworkers. It is much simpler to calculate the staining fastness grade than the ISO 105-A04 fastness formula based on the CIELAB color-difference formula. Sample pair sets, which cover a wide color space range were accumulated from the NCS(Natural Color System) color book. for those sample pair sets, a visual measurement experiment and an instrumental measurement experiment of fastness grade were carried out. Each performance of the ISO 105-A43 fastness formula and newly developed fastness formula was compared through degree of agreement for visual measurement results. The newly developed fastness formula indicated improved performance for measuring fastness grade as it was confirmed that the performance of the current ISO fastness formula ISO 105-A04 for assessing staining, was inadequate for measuring fastness grade. Then the fastness formulae were examined more closely according to the particular color spaces and the correlation of hue, lightness and chroma for measuring staining fastness grade was also considered to recommend more improved fastness formula. By modifying the weighting functions of CIEDE2000, which is a basis of new fastness formula developed by B. Rigg, a modified fastness formula is proposed in this study.

• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 2002년도 춘계학술대회 논문집
• /
• pp.261-265
• /
• 2002

The unique colors of paper, that is, blue, green, red, and yellow were used in the estimation of color from the subjective feeling. The monochrome with unique color or the unique color surrounded with the background color was presented. Subject gazed the monochrome or the unique color, which was called target color. The target and background color were the complementary color each other. The various ratios of the area of gazed color and background were taken. Subject answered the level of subjective feeling consisted of pair of adjective items for unique color presented. With the use of the subjective feeling fer the target color presented, the estimation of the unique color was carried out due to Fuzzy theory and neural networks. The results of color difference between unique color presented and the estimated color gave very small value for the case without background, while the results of the case with background color depended on the ratio of area of presented color and background color till the ration of 2:1, The relation showed the Kirschman's law. The color difference saturated in the increase of area of background with the ratio more than 2:1.

• 감성과학
• /
• 제5권2호
• /
• pp.73-78
• /
• 2002

The unique colors of paper, that is, blue, green, red, and yellow were used in the estimation of color from the subjective feeling. The monochrome with unique color or the unique color surrounded with the background color was presented. subject gazed the monochrome or the unique color, which was tailed target rotor. The target and background color were the complementary color each other. The various ratios of the area of gazed color and background were taken. Subject answered the level of subjective feeling consisted of pair of adjective items for unique color presented. With the use of the subjective feeling for the target color presented, the estimation of the unique color was cai\ulcornerlied out due to Fuzzy theory and neural networks. The results of color difference between unique color presented and the estimated color gave very small value for the case without background, while the results of the case with background color depended on the ratio of area of presented color and background color till the ration of 2:1, The relation showed the Kirschman's law, The color difference saturated In the increase of area of background with the ratio more than 2:1.

• 한국정보처리학회논문지
• /
• 제7권9호
• /
• pp.3037-3047
• /
• 2000

본 논문에서는 커러영상처리로 차량 후면에 위치하고 붉은색을 띄는 미등과 브레이크등을 이용하여 저속주행환경에서 근거리 전방차량을 추적하는 방법에 대해 설명한다. HSV 컬러모델로 변환된 컬러영상에서 미등과 브레이크등의 컬러특징을 이용하여 후보영역을 분할한 후, 미등과 브레이크등 패턴의 기하학적 특징과 위치적 특징을 이용하여 한 쌍의 미등 혹은 브레이크등을 탐지한다. 탐지된 등의 위치를 이용하여 전방차량의 위치를 측정하고 연속적으로 추적한다. 또한, 등 영역내의 HSV 컬러요소 변화를 측정하여 전방차량의 브레이크 사용여부를 판단한다. 도심지의 도로영상을 이용한 실험에서 성공적으로 근거리 전방차량을 추적할 수 있었으며, 주간보다 야간에서 효과적으로 적용될 수 있었다. 또한 본 알고리즘이 구현된 컬러비전시스템을 무인자동차 KAV-III(Korea Autonomous Vehicle-III)에 탑재하여 야간에 자동으로 전방차량을 15km/h의 속도로 따라갈 수 있는 결과를 얻었다. 이 방법은 도심지에서 가다서다를 반복하는 저속주행환경에서 차량 스스로 운전하여 운전자의 부담을 줄일 수 있는 LSA(Low Speed Automation)시스템 개발에 적용될 수 있을 것이다.