• 반도체디스플레이기술학회지
• /
• 제10권2호
• /
• pp.1-5
• /
• 2011

In recent years, worldwide production of solar wafers increased rapidly. Therefore, the solar wafer technology in the developed countries already has become an industry, and related industries such as solar wafer manufacturing equipment have developed rapidly. In this paper we propose the color classification method of the polycrystalline solar wafer that needed in manufacturing equipment. The solar wafer produced in the manufacturing process does not have a uniform color. Therefore, the solar wafer panels made with insensitive color uniformity will fall off the aesthetics. Gaussian mixture models (GMM) are among the most statistically mature methods for clustering and we use the Gaussian mixture models for the classification of the polycrystalline solar wafers. In addition, we compare the performance of the color feature vector from various color space for color classification. Experimental results show that the feature vector from YCbCr color space has the most efficient performance and the correct classification rate is 97.4%.

• 한국의류산업학회지
• /
• 제6권3호
• /
• pp.285-296
• /
• 2004

Fashion business must reflect the seasonable fashion trend because fashion has change always, and therefore fashion business has a big risk at the attribute. Careful consideration should be given to the selection of a particular color code to meet the purpose of marketing research in various color products. It must be designed to grasp systematically and comprehensively the current trend of colors. The most suitable color code for meeting this proposition would be one based on the designation by color ranges. The ISCC-NBS method of designating colors, published in 1955, was established by dividing the color solid into 267 color name blocks. The detailed classification like the ISCC-NBS system is very appropriate to serve the purpose of giving all color names according to color ranges. But it is somewhat too complicated to answer the purpose of surveying the trend of colors and of comparing and evaluating the ups and downs in the popularity of the range of each individual color. I have worked out the most convenient method of designating colors in accordance with the type of investigation needed. It is the classification which involves four classification system in itself, fundamental, gross, medium, and minute. The fundamental classification system classifies hues and neutrals into 16ranges. The gross classification system divides the above 16 ranges into 30. The medium classification divides the above 30 ranges into 103 in terms of tones. The minute classification divides the above 103 ranges into 207 in terms of specipic hues.

• KSTLE International Journal
• /
• 제1권1호
• /
• pp.34-42
• /
• 2000

A method and results of classification of four different metallic wear debris were presented by using their color features. The color image of wear debris was used far the initial data, and the color properties of the debris were specified by HSI color model. Particles were characterized by a set of statistical features derived from the distribution of HSI color model components. The initial feature set was optimized by a principal component analysis, and multidimensional scaling procedure was used fer the definition of a classification plane. It was found that five features, which include mean values of H and S, median S, skewness of distribution of S and I, allow to distinguish copper based alloys, red and dark iron oxides and steel particles. In this work, a method of probabilistic decision-making of class label assignment was proposed, which was based on the analysis of debris-coordinates distribution in the classification plane. The obtained results demonstrated a good availability for the automated wear particle analysis.

• 한국측량학회지
• /
• 제35권4호
• /
• pp.303-312
• /
• 2017

This paper indirectly created high density point cloud data using unmanned aerial vehicle image. Then, we tried to suggest new concept of classification technique where particular objects from point cloud data can be selectively classified. For this, we established the classification technique that can be used as search factor in classifying color information in point cloud data. Then, using suggested classification technique, we implemented object classification and analyzed classification accuracy by relative comparison with self-created proof resource. As a result, the possibility of point cloud data classification was observable using the image's information. Furthermore, it was possible to classify particular object's point cloud data in high classification accuracy.

• 대한원격탐사학회지
• /
• 제37권6_3호
• /
• pp.2011-2025
• /
• 2021

고해상도 위성영상 분류에서 다양한 색상을 가지는 건물들과 같이 동일한 클래스에 속하지만 색상 정보가 상이한 화소들이 클래스를 구성하는 경우에는 클래스를 대표하는 색상 정보를 결정하기가 어렵다. 본 논문에서는 클래스의 대표적인 색상 정보를 결정하는 문제를 해결하기 위해 HSV(Hue Saturation Value)의 색상 채널을 분할하고 객체 기반의 분류를 수행하는 방법을 제안한다. 이를 위해 RGB 컬러 공간의 입력 영상을 HSV 컬러 공간의 성분으로 변환한 후에 색상(Hue) 성분을 일정 간격의 서브채널로 분할한다. 각 색상 서브채널에 대해 최소거리기반의 영상 분류를 수행하고 분류 결과를 영상 분할 결과와 결합한다. 제안한 방법을 아리랑3A 위성영상에 적용한 결과 overall accuracy는 84.97%, kappa coefficient는 77.56%로 나타났고 상용 소프트웨어 대비 분류 정확도가 10% 이상 개선된 결과를 보였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.162.4-162
• /
• 2001

This paper presents a fuzzy-based method for classification skin color object in a complex background under varying illumination Parameters of fuzzy rule base are generated using a genetic algorithm(GA). The color model is used in the YCbCr color space. We propose a unique fuzzy system in order to accommodate varying background color and illumination condition This fuzzy system approach to skin color classification is discussed along with an overview of YCbCr color space.

• 대한전자공학회논문지SP
• /
• 제48권4호
• /
• pp.86-97
• /
• 2011

본 논문에서는 칼라분류 및 방향성 에지정보의 클러스터링과 이들의 통합에 의한 새로운 도로영역 및 차선검출 알고리즘을 제안한다. 도로영역 및 차선을 하나의 인식대상 물체로 취급하고, 통계적 파라미터의 반복 최적화에 의한 칼라정보의 클러스터링을 수행해서 검출과 인식을 위한 초기정보로 사용한다. 다음으로, 칼라정보가 갖는 물체인식 의 한계를 개선하기 위해 에지정보를 검출하고, 관심영역(Region Of Interest for Lane Boundary(ROI-LB))의 추출과 ROI-LB 영역에서 방향성 에지정보의 검출과 클러스터링을 수행한다. 칼라분류 및 에지 클러스터링의 결과를 통합해, 이들 각각의 정보가 갖는 특징을 이용함으로서 도로환경에 적합한 도로영역 및 차선을 검출할 수 있도록 한다. 제안방법은 도로와 차선에 관한 파라미터릭 수학적 모델을 사용하지 않고 칼라 및 에지의 클러스터링 정보에 의한 non-parametric 방법으로 다양한 도로 환경에 유연한 대응이 가능한 장점을 갖는다. 본 제안방법의 유효성을 입증하기 위해 상이한 촬상조건 및 도로환경에서의 영상에 대한 실험결과를 제시한다.

• 한국윤활학회:학술대회논문집
• /
• 한국윤활학회 2000년도 제31회 춘계학술대회
• /
• pp.54-61
• /
• 2000

A method and results of classification of 4 types metallic wear debris were presented by using their color features. The color image of wear debris was used (or the initial data, and the color properties of the debris were specified by HSI color model. Particle was characterized by a set of statistical features derived from the distribution of HSI color model components. The initial feature set was optimized by a principal component analysis, and multidimensional scaling procedure was used for the definition of classification plane. It was found that five features, which include mean values of H and S, median S, skewness of distribution of S and I, allow to distinguish copper based alloys, red and dark iron oxides and steel particles. In this work, a method of probabilistic decision-making of class label assignment was proposed, which was based on the analysis of debris-coordinates distribution in the classification plane. The obtained results demonstrated a good availability for the automated wear particle analysis.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.42.1-42
• /
• 2001

This paper presents a fuzzy-based method for classification skin color object in a complex background under varying illumination. Parameters of fuzzy rule base are generated using a genetic algorithm(GA). The color model is used in the YCbCr color space. We propose a unique fuzzy system in order to accommodate varying background color and illumination condition. This fuzzy system approach to skin color classification is discussed along with an overview of YCbCr color space.

• 한국의류학회지
• /
• 제44권2호
• /
• pp.354-368
• /
• 2020

Accurate and versatile image data-sets are essential for fashion AI research and AI-based fashion businesses based on a systematic attribute classification system. This study constructs a color and texture attribute hierarchical classification system by collecting fashion item images and analyzing the metadata of fashion items described by consumers. Essential dimensions to explain color and texture attributes were extracted; in addition, attribute values for each dimension were constructed based on metadata and previous studies. This hierarchical classification system satisfies consistency, exclusiveness, inclusiveness, and flexibility. The image tagging to confirm the usefulness of the proposed classification system indicated that the contents of attributes of the same image differ depending on the annotator that require a clear standard for distinguishing differences between the properties. This classification system will improve the reliability of the training data for machine learning, by providing standardized criteria for tasks such as tagging and annotating of fashion items.