• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1992년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 19-21 Oct. 1992
• /
• pp.892-895
• /
• 1992

This paper presents a methodology for automatic feature extraction used in a vision system of FMC (flexible Manufacturing Cell). To implement a robot vision system, it is important to make a feature database for object recognition, location, and orientation. For industrial applications, it is necessary to extract feature information from CAD database since the detail information about an object is described in CAD data. Generally, CAD description is three dimensional information but single image data from camera is two dimensional information. Because of this dimensiional difference, many problems arise. Our primary concern in this study is to convert three dimensional data into two dimensional data and to extract some features from them and store them into the feature database. Secondary concern is to construct feature selecting system that can be used for part recognition in a given set of objects.

• Journal of Computational Design and Engineering
• /
• 제3권2호
• /
• pp.102-111
• /
• 2016

In this paper, we study the problem of computing smooth feature curves from CAD type point clouds models. The proposed method reconstructs feature curves from the intersections of developable strip pairs which approximate the regions along both sides of the features. The generation of developable surfaces is based on a linear approximation of the given point cloud through a variational shape approximation approach. A line segment sequencing algorithm is proposed for collecting feature line segments into different feature sequences as well as sequential groups of data points. A developable surface approximation procedure is employed to refine incident approximation planes of data points into developable strips. Some experimental results are included to demonstrate the performance of the proposed method.

• 전기학회논문지
• /
• 제58권10호
• /
• pp.2041-2046
• /
• 2009

In this paper, we propose the feature points extraction method of hand region using vision. To do this, first, we find the HCbCr color model by using HSI and YCbCr color model. Second, we extract the hand region by using the HCbCr color model and the fuzzy color filter. Third, we extract the exact hand region by applying labeling algorithm to extracted hand region. Fourth, after finding the center of gravity of extracted hand region, we obtain the first feature points by using Canny edge, chain code, and DP method. And then, we obtain the feature points of hand region by applying the convex hull method to the extracted first feature points. Finally, we demonstrate the effectiveness and feasibility of the proposed method through some experiments.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 학술대회 논문집 정보 및 제어부문
• /
• pp.6-8
• /
• 2005

Study that uses geometrical information in computer vision is lively. Problem that should be preceded is matching problem before studying. Feature point should be extracted for well matching. There are a lot of methods that extract feature point from former days are studied. Because problem does not exist algorithm that is applied for all images, it is a hot water. Specially, it is not easy to find feature point in endoscope image. The big problem can not decide easily a point that is predicted feature point as can know even if see endoscope image as eyes. Also, accuracy of matching problem can be decided after number of feature points is enough and also distributed on whole image. In this paper studied algorithm that can apply to endoscope image. SIFT method displayed excellent performance when compared with alternative way (Affine invariant point detector etc.) in general image but SIFT parameter that used in general image can't apply to endoscope image. The gual of this paper is abstraction of feature point on endoscope image that controlled by contrast threshold and curvature threshold among the parameters for applying SIFT method on endoscope image. Studied about method that feature points can have good distribution and control number of feature point than traditional alternative way by controlling the parameters on experiment result.

• 한국컴퓨터정보학회논문지
• /
• 제16권8호
• /
• pp.95-101
• /
• 2011

본 논문에서는 픽셀 연결성 추적을 이용한 의사 특징점 제거에 관하여 연구하였다. 특징점을 추출하는 방법에는 교차수를 이용한 방법이 있다. 그러나 교차수를 이용한 방법에서는 의사 특징점이 많이 추출된다. 교차수를 이용한 방법에서 잘못 추출된 특징점들을 제거하기 위하여 단점과 분기점 주위에 있는 8개 픽셀을 추적하여 조건을 만족하는 경우 실제 특징점으로 추출하고 조건을 만족하지 않는 경우 의사 특징점이므로 제거하였다. 성능 평가를 위하여 교차수를 이용한 방법과 픽셀 연결성 추적을 이용하여 추출된 실제 특징점을 비교하였으며, 실험결과 픽셀 연결성 추적을 이용하여 궁상문형, 와상문형, 제상문형에 대하여 의사특징점이 각각 47%, 40%, 30% 제거되었음을 알 수 있었다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.98.4-98
• /
• 2002

$\textbullet$ Feature Detection $\textbullet$ Extracting Feature information $\textbullet$ Feature Map $\textbullet$ Feature Map Building $\textbullet$ Experimental Results

• 한국전기전자재료학회논문지
• /
• 제18권10호
• /
• pp.965-975
• /
• 2005

In the case of the fault in stator windings of a high voltage motor. it facilitates certain destructive characteristics in insulations. This will result in a decreased reliability in power supplies and will prevent the generation of electricity, which will result in huge economic losses. This study simulates motor windings using normal windings and four faulty windings for an actual fault in stator winding of a high voltage motor. The partial discharge signals produced in each faulty winding were measured using an 80 PF epoxy/mica coupler sensor. In order to quantified signal waves its a way of feature extraction for each faulty signal, the signal wave of winding was quantified to measure the degree of skewness shape and kurtosis, which are both types of statistical parameters, using a discrete wavelet transformation method for each faulty type. Wave types present different types lot each faulty type, and the skewness and kurtosis also present different quantified values. The result of feature extraction was used as a preprocessing stage to identify a certain fault in stater windings. It is evident that the type of faulty signals can be classified from the test results using faulty signals that were randomly selected from the signal, which was not applied in the training after the training and learning period, by applying it to a back-propagation algorithm due to the supervising and learning method in a neural network in order to classify the faulty type. This becomes an important basis for studying diagnosis methods using the classification of faulty signals with a feature extraction algorithm, which can diagnose the fault of stator windings in the future.

• 전자공학회논문지CI
• /
• 제39권3호
• /
• pp.32-43
• /
• 2002

본 논문에서는 신경망에 기반한 디지털 신호를 위한 패턴분류 시스템을 제안한다. 제안하는 시스템은 두 가지 신경망 모델로 구성된다. 첫 번째 부분은 특징 추출의 역할을 하는 웨이블릿 신경망이다. 이 부분을 위해 기존의 웨이블릿 신경망 모델들을 비교한 후, 특징 추출을 위한 새로운 웨이블릿 신경망 모델을 제안한다. 다른 부분은 패턴 분류를 위한 웨이블릿 신경망이다. 패턴 분류에 적용하기 위해 기존의 웨이블릿 신경망 구조를 수정하고 학습 방법을 제안한다. 패턴 분류 웨이블릿 신경망의 입력은 특징 추출 신경망의 은닉노드의 연결강도, 확장 및 이동 파라미터로 구성되었다. 또 출력은 특징 추출 신경망의 입력 신호가 속한 부류를 나타낸다. 제안한 시스템을 EEG 신호를 주파수에 따라서 분류하는 문제에 적용하였다.

• 한국콘텐츠학회논문지
• /
• 제12권9호
• /
• pp.9-15
• /
• 2012

기존의 이벤트 문장 추출에 관한 연구는 학습단계에서 3W 자질을 학습하지 않고, 추출단계에서 3W 자질의 존재여부에 따른 규칙만을 적용하여 이벤트 문장을 추출하였다. 본 논문에서는 온라인 동향 분석을 위해 학습단계에서 3W 자질을 추출하고 가중치를 계산하고, 추출단계에서 3W 자질을 반영하는 문장 가중치 기반 이벤트 문장 추출 방안을 제시한다. 실험결과, 자질필터링은 $TF{\times}IDF$ 가중치 기법을 사용한 상위 30% 자질만을 사용하는 것이 가장 우수한 결과를 보였다. 공공이슈 분야인 부동산 도메인에서 문장 가중치 기반 방법은 3W 자질 중 who와 when 자질이 가장 영향을 많이 미치는 것으로 나타났다. 아울러 다른 기계학습 방법과의 비교하여 공공이슈 분야인 부동산 도메인에서 문장 가중치 기반 이벤트 문장 추출 방법이 가장 좋은 성능을 보였다.

• 대한전자공학회논문지SP
• /
• 제40권3호
• /
• pp.203-216
• /
• 2003

In this paper a new feature extraction and target classification method is proposed for the recognition part of FLIR(Forwar Looking Infrared)-image-based ATR system. Proposed feature extraction method is "cluster(=set of classes)-based"version of previous fisherfaces method that is known by its robustness to illumination changes in face recognition. Expecially introduced class clustering and cluster-based projection method maximizes the performance of fisherfaces method. Proposed target image classification method is based on the mixture of experts model which consists of RBF-type experts and MLP-type gating networks. Mixture of experts model is well-suited with ATR system because it should recognizee various targets in complexed feature space by variously mixed conditions. In proposed classification method, one expert takes charge of one cluster and the separated structure with experts reduces the complexity of feature space and achieves more accurate local discrimination between classes. Proposed feature extraction and classification method showed distinguished performances in recognition test with customized. FLIR-vehicle-image database. Expecially robustness to pixelwise sensor noise and un-wanted intensity variations was verified by simulation.