• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• 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.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.10
• /
• pp.23-29
• /
• 2015

In this paper, we suggest a method of detecting defects by applying Hough transform and least squares on ceramic images obtained from non-destructive testing. In the ceramic images obtained from non-destructive testing, the background area, where the defect does not exist, commonly show gradual change of luminosity in vertical direction. In order to extract the background area which is going to be used in the detection of defects, Hough transform is performed to rotate the ceramic image in a way that the direction of overall luminosity change lies in the vertical direction as much as possible. Least squares are then applied on the rotated image to approximate the contrast value of the background area. The extracted background area is used for extracting defects from the ceramic images. In this paper we applied this method on ceramic images acquired from non-destructive testing. It was confirmed that extracted background area could be effectively applied for searching the section where the defect exists and detecting the defect.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.10a
• /
• pp.789-792
• /
• 2001

본 논문은 자동차의 번호판 인식 시스템의 한 부분인 번호판 추출과 자모 분리를 통한 문자 인식까지의 과정을 실험한 것이다. 본 논문은 gray-level에서 영상을 실험하였고, 번호판을 추출하기 위해서 morphology를 반복 적용하고 크기 보정을 통해 번호판을 추출하며, hough transform을 이용한 크기 재보정을 통해 최종적으로 번호판을 추출한다. 그리고, 문자 인식 단계에서는 먼저 hough transform을 사용하여 한글의 모음의 시작점을 얻고, 문자 특징을 이용하여 자음과 모음을 분리하여 모음을 인식한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.10a
• /
• pp.488-490
• /
• 2017

본 논문에서는 장폐색 영역을 추출하는 방법을 제안한다. 제안된 방법은 Canny Edge Detector을 이용하여 X-ray 영상에서 객체들의 에지를 추출한다. 검출된 객체 에지들에서 장폐색의 영역이 형태학적으로 수평적으로 평평하다는 특징을 이용하기 위해서 Hough transform을 적용하여 수평적으로 평평한 영역을 가진 객체들을 추출하고, 추출된 객체들을 장폐색 영역으로 검출한다. 제안된 추출 방법을 25개의 장폐색 X-ray 영상을 대상으로 실험한 결과, 제안된 방법에서는 19개 대장 장폐색 영상에서는 모두 추출되었으나 6개의 소장 장폐색 영상에서는 추출에 실패하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.05a
• /
• pp.338-341
• /
• 2013

눈동자 검출은 운전 부주의 검출, 졸음 검출, 시선 검출 등 다양한 상황 인지에 이용되고 있다. 이러한 상황 인지를 위해 본 논문에서는 원 허프 변환(Hough Circle Transform)을 이용한 눈동자 검출방법을 제안한다. 이것은 영상 내 원을 검출하는 방법으로 연산량이 많아 실시간 처리에 문제가 된다. 이러한 문제를 해결하기 위해 눈 검출 후 눈 영역의 크기를 일정한 눈 크기로 정규화 하고 눈의 양쪽 끝점간 거리에 따른 대략적인 눈동자의 반지름 값 범위를 추정한다. 그 추정된 반지름 값 범위 내에서 Hough Circle Transform을 수행하면 연산량의 축소가 가능하며 그 결과 초당 21frames 정도의 눈동자 검출이 가능하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.165-168
• /
• 2009

차선 검출을 위한 영상처리연구는 Hough Transform을 이용하는 방법과 주파수 변환 방법, 히스토그램을 이용하는 방법, 템플릿을 이용하는 방법등이 사용되고 있다. 차선 검출에 가장 많이 사용되는 Hough Transform은 연산 과정이 복잡하여 차량의 속도가 증가하면 실제 상황과 오차가 생길 확률이 높다. 이러한 문제를 해결하기 위해 영상을 분할하여 최소한의 영역을 처리하여 처리량을 줄였으며, 차선 이외의 선이 추출될 경우 그 선의 각도와 위치를 고려하여 연산에 방해되는 선을 삭제한다. 또한 고속으로 진행하는 차량의 경우, 점선으로 이루어져 선이 보이지 않는 부분에서는 차선의 인식이 불가능하여 위험한 상황을 초래한다. 따라서 최소한의 차선을 이용하여 차선을 연장하고, 여러 직선으로 곡선을 표현하여 차량 진행 방향을 예측할 수 있다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.11
• /
• pp.2094-2105
• /
• 1994

This paper contains a Hough transform based projection method derived from Radon transform for tracking dim unresolved(sub-pixel) moving targets that move along straight line parths across a time sequential image data. In contrast to several recently presented Hough transform methods using a compressed image referred to as the track map our proposed technique utilizing a set of projections taken along arbitrary orientations effectively increases the changes of target detection, and creates a robust track estimation environment by incorporating all the available knowledge obtained from the projections. Moreover, in order to quantitatively assess the estimation capability of the projection-based Hough transform algorithm, the analytical bounds on the Hough space parameter errors introduced by image space noise contamination are derived. The simulation yielded promising results of estimating the track parameters even under low signal to noise rations when our technique was tested against the time sequential sets of real infrared image data referred to as the HiCamps.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.1
• /
• pp.161-171
• /
• 2014

When the Hough transform is applied to identify an instance of a given model, the output is typically a histogram of votes cast by a set of image features into a parameter space. The next step is to threshold the histogram of counts to hypothesize a given match. The question is "What is a reasonable choice of the threshold?" In a standard implementation of the Hough transform, the threshold is selected heuristically, e.g., some fraction of the highest cell count. Setting the threshold too low can give rise to a false alarm of a given shape(Type I error). On the other hand, setting the threshold too high can result in mis-detection of a given shape(Type II error). In this paper, we derive two conditional probability functions of cell counts in the accumulator array of the generalized Hough transform(GHough), that can be used to select a scientific threshold at the peak detection stage of the Ghough.

• Korean Journal of Cognitive Science
• /
• v.4 no.1
• /
• pp.243-260
• /
• 1993

This paper presents an efficient method for estimationg and correcting the slant of off-line handwritten Hangul strings.In the proposed method,after extracting contours from input image.Hough tranform is applied to the contours to detect lines and estimate slants of the lines.When Hough trans form is applied to the contours,pixels which are not parts of the same stroke could be detected as a line.In order to exclude these lines from slant estimation process,detected lines which have the length less than threshold are eliminated.Experiments have been performed with address images which were extracted from live envelopes provided by Seoul Mail Center.Experimental results show that the proposed method is superior to the previous methods,which had been done with handwritten English strings.in estimation the slant of off-line handwritten Hangul strings.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.12
• /
• pp.3710-3717
• /
• 1999

For the development of unmanned autonomous vehicle, it is essential to detect obstacles, especially vehicles, in the forward direction of navigation. In order to reliably exclude regions that do not contain obstacles and save a considerable amount of computational effort, it is often necessary to confine computation only to ROI(region of interest)s. A ROI is usually chosen as the interior region of the lane. We propose a computationally simple and efficient method for the detection of lanes based on Hough transform and quadratic curve fitting. The proposed method first employs Hough transform to get approximate locations of lanes, and then applies quadratic curve fitting to the locations computed by Hough transform. We have experimented the proposed method on real outdoor road scene. Experimental results show that our method gives accurate detection of straight and curve lanes, and is computationally very efficient.