• 한국멀티미디어학회논문지
• /
• 제19권10호
• /
• pp.1782-1791
• /
• 2016

Various color spaces such as RGB, HSV, log-chromaticity have been used in the field of person re-identification. However, not enough studies have been done to find suitable color space for the re-identification. This paper reviews color invariance of color spaces by diagonal model and explores the suitability of each color space in the application of person re-identification. It also proposes a method for person re-identification based on a histogram refinement technique and some fusion strategies of color spaces. Two public datasets (ALOI and ImageLab) were used for the suitability test on color space and the ImageLab dataset was used for evaluating the feasibility of the proposed method for person re-identification. Experimental results show that RGB and HSV are more suitable for the re-identification problem than other color spaces such as normalized RGB and log-chromaticity. The cumulative recognition rates up to the third rank under RGB and HSV were 79.3% and 83.6% respectively. Furthermore, the fusion strategy using max score showed performance improvement of 16% or more. These results show that the proposed method is more effective than some other methods that use single color space in person re-identification.

• 한국가구학회지
• /
• 제28권4호
• /
• pp.294-304
• /
• 2017

The purpose of this study is to analyse and derive the color characteristics of childhood children's learning spaces and furniture for improving the color design of those and to present the direction of design and to build up the DB. The study covers products from domestic and overseas infant furniture manufacturers and 11 preschool learning rooms. The study method uses the collected furniture and spatial images to derive a palette of colors and compare color characteristics. The analysis results show that, the domestic infant furniture tend to use a variety of colors with pale tone or use consistent hard wood furniture according to the requirements of adult taste and marketability. Also, it attempts to create a very negative color scheme, but it looks like disorganized, and there is not much color design integrated with the architecture. Thus, color designs ensure that the ordering elements of the color scheme are clearly recognized by applying preferred color tones of childhood, like vivid and bright tone with high chroma and middle or hight Brightness value. Lastly, it should establish guidelines for specific palettes and color scheme, which can be utilized in the design of childhood children's learning spaces and furniture.

• 한국멀티미디어학회논문지
• /
• 제11권5호
• /
• pp.610-622
• /
• 2008

이동 객체의 검출은 다양한 영상 감시 응용에 필수적인 중요한 기술이다. 그런데 이동 객체 검출 결과로 얻어진 전경 영상에는 그림자에 의한 색상 변화가 전경 영역으로써 함께 검출되는 경우가 쉽게 발생하며, 이러한 문제를 해결하기 위하여 이동 객체 검출은 흔히 그림자 제거와 함께 수행된다. 대부분의 그림자 제거 방법은 조명 변화발생시 색상의 조도 성분만 변화하며 색도 성분은 유지된다는 가정에 기반하여 색도 성분을 분리하여 표현하는 다양한 색상 공간을 통해 그림자 제거를 수행한다. 본 논문에서는 색도 성분을 분리하는 색상 공간 가운데 그림자 제거에 가장 적합한 색상 공간을 선택하고자 다양한 색상 공간 (YCbCr, HSI, 정규화된 rgb, Yxy, Lab, c1c2c3)을 비교하였다. 과거 그림자 제거에 있어서 다양한 색상 공간의 성능을 비교한 몇몇 연구가 있었으나, 기존 연구들은 각 논문에서 제안한 특정 그림자 제거 방법에 다양한 색상 공간을 적용하거나 임의의 임계값을 이용하여 각 색상 공간의 성능을 비교하였기 때문에, 각 색상 공간에서 조명 변화 발생에 따른 색상 왜곡을 정확히 측정하기 어려운 문제가 있었다. 본 논문에서는 이러한 기존 연구의 문제점을 피하고 각 색상 공간을 정확하게 비교하기 위하여 1) 서로 다른 조명 조건에 노출된 동일한 색상을 갖는 면의 경계에서 색도 성분의 기울기 값을 측정함으로서 조명 변화 발생 시 색도 성분의 변화 정도를 비교하였으며, 2) RoC 곡선을 통하여 임계치 설정의 문제를 피하면서 배경 제거 정확도를 비교하였다. 실험을 통하여 YCbCr 색상 공간과 정규화된 rgb 색상 공간이 비교대상으로 선택된 여러 색상 공간 가운데 가장 좋은 성능을 보이는 것을 확인하였다.

• 한국디자인학회:학술대회논문집
• /
• 한국디자인학회 2002년도 봄 학술발표회 논문집
• /
• pp.136-137
• /
• 2002

• 대한건축학회논문집:계획계
• /
• 제35권1호
• /
• pp.99-106
• /
• 2019

This study aims to recommend the proper Color rendering index (CRI), the Correlated Color Temperature (CCT), and illuminance levels of Light-Emitting Diode (LED) lighting based on the analysis of the criteria of the current CRI, the CCT, and illuminance levels in merchandising spaces with LED lighting conditions. It would be a basic material to apply in line with user preference for LED merchandising lighting. To this end, it examines relevant literature review on the experiments designed to test whether lighting characteristics affect brightness perception, color appearance, and pleasantness. Highly saturated colors appear brighter than low saturated colors. Two lighting applications - grocery and clothing shop - were created in elaborating the effect of LED lighting characteristics of CRI on color appearance and the CCT and illuminance on pleasantness. The findings show that the criteria of CIE Ra<80 are appropriate to provide better color appearance of illuminated products in terms of LED lighting that can enhance color saturation, particularly for the red color. Furthermore, 2700 K and less than 500 lux for grocery, 4000 K and more than 500 lux for clothing shop are found to be the proper the CCT and illuminance levels respectively to bring better preference under LED lighting.

• 디지털산업정보학회논문지
• /
• 제10권4호
• /
• pp.151-160
• /
• 2014

In this paper, a comparison of superpixel characteristics based on SLIC(simple linear iterative clustering) for several color feature spaces is presented. Computer vision applications have come to rely increasingly on superpixels in recent years. Superpixel algorithms group pixels into perceptually meaningful atomic regions, which can be used to replace the rigid structure of the pixel grid. A superpixel is consist of pixels with similar features such as luminance, color, textures etc. Thus superpixels are more efficient than pixels in case of large scale image processing. Generally superpixel characteristics are described by uniformity, boundary precision and recall, compactness. However previous methods only generate superpixels a special color space but lack researches on superpixel characteristics. Therefore we present superpixel characteristics based on SLIC as known popular. In this paper, Lab, Luv, LCH, HSV, YIQ and RGB color feature spaces are used. Uniformity, compactness, boundary precision and recall are measured for comparing characteristics of superpixel. For computer simulation, Berkeley image database(BSD300) is used and Lab color space is superior to the others by the experimental results.

• International Journal of Computer Science & Network Security
• /
• 제23권5호
• /
• pp.33-40
• /
• 2023

The mainstay of current image recovery frameworks is Content-Based Image Retrieval (CBIR). The most distinctive retrieval method involves the submission of an image query, after which the system extracts visual characteristics such as shape, color, and texture from the images. Most of the techniques use RGB color space to extract and classify images as it is the default color space of the images when those techniques fail to change the color space of the images. To determine the most effective color space for retrieving images, this research discusses the transformation of RGB to different color spaces, feature extraction, and usage of Convolutional Neural Networks for retrieval.

• 한국인쇄학회지
• /
• 제18권1호
• /
• pp.103-112
• /
• 2000

The color space transformation to link device-dependent color spaces and device-independent color spaces is essential for device characterization and cross-media color reproduction. There are various color conversion methods such as regression, 3D interpolation with LUT(look-up table), and neural network. In the color transformation with these methods, the conversion accuracy is essentially based on the sample data to be exploited for device characterization. In conventional method, color samples are uniformly selected in device-dependent space such as CMY and RGB. However, distribution of these color samples is very non-uniform in device-independent color space such as CIEL*a*b*. Accordingly, the conversion error in device-independent color space is irregular according to the distribution of the samples. In this paper, a color sampling method based on equi-visual perception is proposed to obtain approximate uniform color samples in CIEL*a*b* space. In order to evaluate transformation accuracy of proposed method, color space transformations are simulated using regression, 3D interpolation with LUT and neural network techniques, respectively.

• 한국통신학회논문지
• /
• 제32권5C호
• /
• pp.513-519
• /
• 2007

칼라 코렐로그램은 칼라 히스토그램처럼 픽셀의 칼라 정보만을 고려하지 않고 영상의 픽셀의 공간 정보까지 고려하기 때문에 콘텐츠 기반 영상 검색(CBIR)에서 널리 사용되어 왔다. 칼라 코렐로그램은 하나의 칼라 형태를 사용한다. 그래서 칼라 코렐로그램은 영상 검색 시 같은 영상이라도 크기가 다를 경우 다른 영상으로 인식하는 등 영상의 특징을 구별해내는데 강건하지 않다. 본 논문에서는 RGB와 HSV의 두 가지 칼라 형태를 사용하여 코렐로그램을 함으로써 기존의 알고리즘보다 영상의 특징을 더 잘 구별해내는 알고리즘을 제안하였다. 이 제안된 알고리즘은 대규모 영상 데이터베이스에서 테스트하였고 그 결과 하나의 칼라 형태를 사용한 코렐로그램 알고리즘과 비교하여 검색된 영상의 평균 순위가 5.63 낮아져 제안한 알고리즘이 더 나은 검색 성능을 나타낸다는 것을 보여준다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 학술대회 논문집 정보 및 제어부문
• /
• pp.186-188
• /
• 2005

Hand region detection in images is an important process in many computer vision applications. It is a process that usually starts at a pixel-level, and that involves a pre-process of color space transformation followed by a classification process. A color space transformation is assumed to increase separability between skin classes for hands and non-skin classes for other parts, to increase similarity among different skin tones, and to bring a robust performance under varying illumination conditions, without any sound reasonings. In this work, we examine if the color space transformation does bring those benefits to the problem of hand region detection on a dataset of images with different hand postures, backgrounds, people, and illuminations. Results indicate that best of the color space is the normalized RGB.