• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 추계종합학술대회 논문집(4)
• /
• pp.5-8
• /
• 2000

In this paper, a technique to estimate the circular object's center and radius under noisy condition is described. The technique is based on Davies'Hough transform approach to circular object location but more robust to noise and faster to estimate the circle by using an area of cumulated points.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2007년도 춘계종합학술대회
• /
• pp.819-822
• /
• 2007

본 논문에서는 CHT(Circular Hough Transform)을 이용한 이동 로봇의 물체 추적 방식을 제안한다. 제안한 방식은 연산 속도를 높이기 위해 1차원 투영방법을 이용하여 움직이는 객체의 영역을 추출하고, CHT를 적용하여 원형의 물체를 검출한다. 제안한 방식의 유용성을 확인하기 위하여 CMOS 카메라를 장착한 ARM 프로세서 기반의 이동로봇을 설계하여 공 모양의 이동 물체 추적 실험을 수행한다.

• 한국멀티미디어학회논문지
• /
• 제17권4호
• /
• pp.413-419
• /
• 2014

In this paper, we develop an automatic coin calculation system by using digital image processing. Existing schemes have the problem that is not able to exclude non-circular shape from the calculation. We propose a method to detect only coins which have circular form by applying the circular Hough transform(CHT). However, the CHT has the drawback that detects multiple circles even for just one coin because of shadow noise, the patterns on coins, and non-circular edge detection. We propose a post processing algorithm to overcome these limitations. The proposed system was implemented and successfully calculated the coin amount in the case that non-circular objects are mixed with coins.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2013년도 추계학술대회
• /
• pp.90-93
• /
• 2013

This paper presents a multistage adaptive thresholding method and circular Hough transform for pupil detection. Multistage adaptive thresholding is a thresholding method that applies local image statistic within a neighborhood variable and the global thresholds. Therefore, the method can adopt the benefit of local thresholding and prevent an over segmentation at the same time because of the global image information. To detect a pupil, a circular Hough transform is applied to it in which the pupil pattern is considered as a circle shape. The experimental results show the reliability of our proposed method in detecting pupil properly.

• 반도체디스플레이기술학회지
• /
• 제16권3호
• /
• pp.8-13
• /
• 2017

In this paper, the measurement of the inner diameter dimension of the circular hole by using a machine vision system was studied. This paper was focused on the theory and key technologies of machine vision inspection technology for the improvement of measurement accuracy and speed of the micro circular holes. A new method was proposed and was verified through the experiments on Gray conversion, binarization, edge extraction and Hough transform in machine vision system processes. Firstly, the Hough transform was proposed in order to improve the speed increase and implementation ease, it demonstrated the superiority of Hough transform and improvement through a comparative experiment. Secondly, we propose a calibration method of the system in order to obtain exactly the inner diameter of the circular hole. Finally, we demonstrate the reliability of the entire system as a MATLAB-based implementation of the GUI program, measuring the inner diameter of the circular hole through the circular holes of different dimensions measuring experiment.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1991년도 추계학술대회 논문집 학회본부
• /
• pp.197-200
• /
• 1991

In this paper, a technique to reduce the computational effort of Hough Transform used to recognize digital circles is proposed. The technique, which is a version of the Hough Transform uses bisectors of circles cords to estimate the center of circles. This system which is implemented in this paper gets center, radius, thickness of circular fiducials regardless of input form. This system uses fuzzy set theory which deals with 'ambigousness', In order to recognize imprecise circular fiducial.

• 한국산학기술학회논문지
• /
• 제12권7호
• /
• pp.3184-3190
• /
• 2011

본 논문에서는 디지털 비디오 데이터에서 이동 경계선의 형태가 원형의 모양을 가지는 아이리스 라운드(Iris Round) 와이프를 효과적으로 검출하는 새로운 방법을 제안한다. 제안된 아이리스 라운드 검출 방법에서는 영상에 존재하는 원형의 이동 경계선을 개선된 허프 변환(Hough transform)을 이용하여 강건하게 추출하고, 이들의 진행 방향 및 형태를 효과적으로 분석하여 아이리스 라운드 와이프의 발생 유무를 판단한다. 본 논문의 실험 결과에서는 제안된 방법이 원형의 이동 경계선을 가지는 아이리스 라운드를 효과적으로 검출할 수 있다는 것을 다양한 비디오 데이터를 이용한 실험을 통하여 보인다.

• 한국멀티미디어학회논문지
• /
• 제16권12호
• /
• pp.1385-1392
• /
• 2013

최근 생체 정보를 이용한 다양한 방식의 인증 시스템에 대한 연구가 많이 이루어지고 있다. 본 연구에서는 홍체 인식을 위한 홍채 영역 검출을 위하여 임계값의 변경 없이 원둘레의 일부 정보를 이용하여 만들어진 원의 연립방정식을 이용하여 전안부 영상에서의 홍채 영역을 효과적으로 검출할 수 있는 새로운 알고리즘을 제안한다. 제안 알고리즘은 외곽정보를 통해 계산된 원의 중점 좌표가 가장 많이 누적된 영역을 검출될 원의 중점으로 인식하여 검출하게 된다. 이를 위하여 50명의 사람의 전안부 이미지에서 테스트를 통해 알고리즘을 circular hough transform, Daugman의 방법과 비교한 결과, 두 방법에 비하여 속도는 각각 5배, 75배가 향상되었으며, 제안한 방법의 중심위치 정확도는 95.36%로 circular hough transform 방법의 92.43%에 비하여 더 우수한 성능을 나타내었다. 본 연구는 홍채인식을 통한 신분 인증 시스템이나, 전안부 영상을 이용한 질병진단 시스템에서의 유용하게 활용이 될 것이라 예상된다.

• 제어로봇시스템학회논문지
• /
• 제15권1호
• /
• pp.54-60
• /
• 2009

In this paper, a precision landing approach is implemented based on real-time image processing. A full-scale landmark for automatic landing is used. canny edge detection method is applied to identify the outside quadrilateral while circular hough transform is used for the recognition of inside circle. Position information on the ground landmark is uplinked to the unmanned helicopter via ground control computer in real time so that the unmanned helicopter control the air vehicle for accurate landing approach. Ground test and a couple of flight tests for autonomous landing approach show that the image processing and automatic landing operation system have good performance for the landing approach phase at the altitude of $20m{\sim}1m$ above ground level.

• 한국컴퓨터정보학회논문지
• /
• 제23권2호
• /
• pp.27-34
• /
• 2018

In this paper, we propose a new method to read the hand of analog gauges to prepare for the smart factory. In addition, we suggest a new and improved method that can apply, in general, diverse analog gauges even if their scale types and ranges are various. Many companies are making great efforts to build smart factories that increase energy efficiency and automation. Managers use a variety of equipment and tools to manage the production process at the factory. In this kind of factory, analog gauges have been often used with many equipment and tools. Analog gauges are mostly circular in shape, and most papers use circular hough transform to find the center and radius of a circle. However, when the object to be found is not of the correct circle type, it takes a long time to recognize the circle using the circular hough transform, and the center and radius of the circle can not be calculated accurately. The proposed method was tested on various circular analog gauges. As a result, we confirmed that our method is outstanding.