• Journal of Information Processing Systems
• /
• 제10권4호
• /
• pp.589-601
• /
• 2014

The performance of edge detection often relies on its ability to correctly determine the dissimilarities of connected pixels. For grayscale images, the dissimilarity of two pixels is estimated by a scalar difference of their intensities and for color images, this is done by using the vector difference (color distance) of the three-color components. The Euclidean distance in the RGB color space typically measures a color distance. However, the RGB space is not suitable for edge detection since its color components do not coincide with the information human perception uses to separate objects from backgrounds. In this paper, we propose a novel method for color edge detection by taking advantage of the HSV color space and the Mahalanobis distance. The HSV space models colors in a manner similar to human perception. The Mahalanobis distance independently considers the hue, saturation, and lightness and gives them different degrees of contribution for the measurement of color distances. Therefore, our method is robust against the change of lightness as compared to previous approaches. Furthermore, we will introduce a noise-resistant technique for determining image gradients. Various experiments on simulated and real-world images show that our approach outperforms several existing methods, especially when the images vary in lightness or are corrupted by noise.

• 정보처리학회논문지B
• /
• 제9B권1호
• /
• pp.129-138
• /
• 2002

본 논문에서는 모션캡쳐를 위해 컬러 스테레오 카메라를 이용한 거리 측정 알고리즘을 제안하였다. 현실공간의 연기자 각 관절 부위에 컬러마커를 부탁시키고 이를 컬러 스테레오 카메라를 이용해 촬영한 후, 본 논문에서 제안한 컬러 매칭방법과 컬러 영역중심의 분석방법에 의해 카메라로부터 마커가지의 거리를 계산한다. 스테레오 영상에서 마커의 컬러영역을 추출하기 위해 국부지역내의 각 픽셀의 RGB(red, green, blue) 컬러 정보를 CIE(Commission Internationale de1'Eclairage) 컬러 공간으로 변환시켜 컬러의 파장을 계산하고, 국부지역의 우월 파장이 마커의 컬러파장과 일치하는지를 검색한다. 가상공간에서의 캐릭터의 움직임은 시간에 따른 마커의 위치 변화정보를 처리하는 프로그램에 의하여 제어된다.

• 천문학회보
• /
• 제45권1호
• /
• pp.64.2-64.2
• /
• 2020

We present the properties of galaxies in filaments around the Virgo cluster with respect to their vertical distance from the filament spine. Using the NASA-Sloan Atlas and group catalogs, we select galaxies that do not belong to groups in filaments. The filament member galaxies are then defined as those located within 3.5 scale length from the filament spine. The filaments are mainly (~86%) composed of low-mass dwarf galaxies of logh2M∗/M⊙ < 9 dominantly located on the blue cloud in color-magnitude diagrams. We observe that the g - r color and stellar mass of galaxies correlate with their vertical distance from the filament spine in which the color becomes red and stellar mass decreases with increasing vertical filament distance. The galaxies were divided into two subsamples in different stellar mass ranges, with lower-mass (logh2M∗/M⊙ ≤ 8) galaxies showing a clear negative g-r color gradient, whereas higher-mass (logh2M∗/M⊙ > 8) galaxies have a flat distribution against the vertical filament distance. We observe a negative EW(Hα) gradient for higher-mass galaxies, whereas lower-mass galaxies show no distinct variation in EW(Hα) against the vertical filament distance. In contrast, the NUV - r color distribution of higher-mass galaxies shows no strong dependence on the vertical filament distance, whereas the lower-mass galaxies show a distinct negative NUV - r color gradient. We do not witness clear gradients of HI fraction in either the higher- or lower-mass subsamples. We propose that the negative color and stellar mass gradients of galaxies can be explained by mass assembly from past galaxy mergers at different vertical filament distances. In addition, galaxy interactions might be responsible for the contrasting features of EW(Hα) and NUV - r color distributions between the higher- and lower-mass subsamples. The HI fraction distributions of the two subsamples suggest that ram-pressure stripping and gas accretion could be ignorable processes in the Virgo filaments.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.396-399
• /
• 2009

In this paper, we present a method to define a color similarity between color images using Octree-based quantization and similar color integration. The proposed method defines major colors from each image using Octree-based quantization. Two color palettes to consist of major colors are compared based on Euclidean distance and similar color bins between palettes are matched. Multiple matched color bins are integrated and major colors are adjusted. Color histogram based on the color palette is constructed for each image and the difference between two histograms is computed by the weighted Euclidean distance between the matched color bins in consideration of the frequency of each bin. As an experiment to validate the usefulness, we discriminated the same clothing from CCD camera images based on the proposed color similarity analysis. We retrieved the same clothing images with the success rate of 88 % using only color analysis without texture analysis.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2017년도 추계학술발표대회
• /
• pp.944-945
• /
• 2017

Color image edge detection is an important operation in many image processing areas. This paper presents a new method for edge detection based on the Bhattacharyya distance that can handle arbitrary boundaries by exploring several edge patterns. Experiments show promising results compared to some existing methods.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.632-635
• /
• 2003

This paper describes a system fur tracking multiple faces in an input video sequence using facial convex hull based facial segmentation and robust hausdorff distance. The algorithm adapts skin color reference map in YCbCr color space and hair color reference map in RGB color space for classifying face region. Then, we obtain an initial face model with preprocessing and convex hull. For tracking, this algorithm computes displacement of the point set between frames using a robust hausdorff distance and the best possible displacement is selected. Finally, the initial face model is updated using the displacement. We provide an example to illustrate the proposed tracking algorithm, which efficiently tracks rotating and zooming faces as well as existing multiple faces in video sequences obtained from CCD camera.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제3권1호
• /
• pp.87-92
• /
• 2003

This paper describes a system for tracking multiple faces in an input video sequence using facial convex hull based facial segmentation and robust hausdorff distance. The algorithm adapts skin color reference map in YCbCr color space and hair color reference map in RGB color space for classifying face region. Then, we obtain an initial face model with preprocessing and convex hull. For tracking, this algorithm computes displacement of the point set between frames using a robust hausdorff distance and the best possible displacement is selected. Finally, the initial face model is updated using the displacement. We provide an example to illustrate the proposed tracking algorithm, which efficiently tracks rotating and zooming faces as well as existing multiple faces in video sequences obtained from CCD camera.

• 전자공학회논문지
• /
• 제52권12호
• /
• pp.174-182
• /
• 2015

본 연구에서는 저가형 컬러센서를 이용하여 원거리 인식이 가능한 소형 RGB 센서를 개발하였다. 이 센서의 수광부에는 원거리 인식을 위해 카메라 렌즈를 사용하였으며, 고출력 백색 LED와 반사경이 장착된 렌즈를 조명부에 사용하여 조명의 강도를 높였다. RGB 색상 인식 알고리즘은 학습과정과 실시간 인식과정으로 구성되어 있다. 학습과정에서는 기준색으로 도색된 시편을 이용하여 RGB 색상에 대한 정규화된 기준 데이터를 취득하고, 인식과정에서는 마할라노비스 거리를 이용하여 3색을 분류한다. 개발한 RGB 색상 인식 센서를 부품 분류 시제품에 적용하여 성능을 검증하였다.

• 대한전자공학회논문지SP
• /
• 제49권3호
• /
• pp.67-73
• /
• 2012

지역적인 영상의 색변환이란 영상에서 특정 색을 포함하는 영역을 추정하고 이를 원하는 색으로 변환시키는 것이다. 기존방법에서는 색차만을 이용해서 바꾸고자 하는 색을 포함하는 영역을 추정하고 이를 변환하였다. 따라서 변환되는 색 주변에서 원하지 않는 색결점(color artifact)이 나타나게 되었다. 제안한 방법에서는 이러한 색결점을 줄이기 위해 컬러 카테고리 맵과 수정된 color influence map을 결합한 지역적인 색변환 방법을 제안하였다. 컬러 카테고리 맵은 모든 색을 사람의 인지를 기반으로 11가지의 컬러 카테고리로 나눈 것으로서, 컬러 정보만을 이용해서 먼저 바꾸고자하는 색을 포함한 입력 영상의 지역 영역을 대략적으로 추정한다. 다음으로, 수정된 color influence map을 이용하여 인접한 영역의 색을 고려한 색변환 정도를 계산한다. 기존의 방법처럼 단순히 동일한 가중치를 주는 색차보다는 밝기와 색도에 서로 다른 가중치를 주어 수정된 color influence map을 계산하였다. 마지막으로 각각의 컬러 카테고리 맵과 수정된 color influence map에 가중치를 결합하여 지역적인 영상의 색변환을 수행하였다. 실험을 통해 제안한 방법과 기존의 색변환 방법의 결과 영상을 비교해 보았으며, 제안한 방법에서 색결점이 적게 나타나는 것을 확인할 수 있다.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2001년도 가을 학술발표논문집 Vol.28 No.2 (2)
• /
• pp.40-42
• /
• 2001

Most people have to deal with color and color problems occasionally. There are many strange things about color and color vision that most people do not notice. Even though color seems intuitive and simple it is not. In this paper, we modeled the color using fuzzy set theory. The proposed fuzzy color model is based on the Munsell color space. We defined several fuzzy color terminologies, and proposed a extended center of gravity defuzzification mthod for fuzzy color set. Finally, three distance measures between fuzzy colors were also formulated.