• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.7
• /
• pp.939-944
• /
• 2007

Edge is a significant element to represent boundary information between objects in images. There are various edge detection methods, which are based on differential operation, such as Sobel, Prewitt, Roberts, Canny, Laplacian, and etc. However the conventional methods have drawbacks as follow : (i) insensitivity to edges with gentle curve intensity, (ii) detection of double edges for edges with one pixel width. For the detection of edges, not only development of the effective operators but also that of appropriate thresholding methods are necessary. But it is very complicate problem to find an appropriate threshold. In this paper, we propose an edge detection method based on the region separateness between objects to overcome the drawbacks of the conventional methods, and a thresholding method for the proposed edge detection method. We show the effectiveness of the proposed method through experimental results obtained by applying the proposed and the conventional methods to well-known test images.

• Proceedings of the KAIS Fall Conference
• /
• 2006.05a
• /
• pp.139-142
• /
• 2006

본 연구는 장면 이미지로부터 텍스트에 존재하는 문자-에지 특징을 이용하여 텍스트를 추출하는 방법을 제안한다. 캐니(Canny)에지 연산자를 이용하여 장면 이미지로부터 에지를 추출하고, 추출된 에지로부터 16종류의 에지-맵 생성한다. 생성된 에지 맵을 재구성하여 문자 특징을 갖는 8종류의 문자-에지 맵을 만단다. 텍스트는 배경과 잘 분리되는 특징이 있으므로 텍스트에 존재하는 '문자-에지 맵'의 특징을 이용하여 텍스트를 추출한다. 텍스트 영역에 대한 검증은 문자-에지 맵의 분포와 텍스트에 존재하는 글자간의 공백 특징으로 한다. 제안한 방법은 다양한 종류의 장면 이미지를 실험대상으로 하였고, 텍스트는 적어도 2글자 이상으로 구성된다는 제한조건과 너무 크거나 작은 텍스트는 텍스트 추출에서 제외하였다. 실험결과 텍스트 영역 추출률은 약 83%를 얻었다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.21 no.4
• /
• pp.209-215
• /
• 2020

In this paper, we propose an algorithm for segmenting weld bead images using edge enhancement and active contours. In the proposed method, high-frequency filtering and contrast improvement are performed for edge enhancement, and then, by applying the active contour method, only the weld bead region can be obtained. The proposed algorithm detects an edge through high-frequency filtering and reinforces the detected edge by using contrast enhancement. After the edge information is improved in this way, the weld bead area can be extracted by applying the active contour method. The proposed algorithm shows better performance than the existing methods for segmenting the weld bead in the image. For the objective reliability of the proposed algorithm, it was compared with the existing high pass filtering methods, and it was confirmed that the welding bead segmentation of the proposed method is excellent. The proposed method can be usefully used in evaluating the quality of the weld bead through an additional procedure for the segmented weld bead.

• Journal of Advanced Marine Engineering and Technology
• /
• v.24 no.2
• /
• pp.82-89
• /
• 2000

Edge detection is the first step and very important step in image analysis. In this paper, proposed edge detection operators based on informations of edge types and it is different from other classical edge detection operators such as gradient and surface fitting operators. The first, we defined characteristics of edge types such as localization, thinness, length. The second, we defined valid edge types and ideal edge pixel positions in $3\times3$window based on edge characteristics of edge types. And we proposed edge detection algorithm and twelve windows based on valid edge types. In specially, proposed algorithm was shown better performence of edge detection than other operators such as gradient operator and the LoG(Laplacian of Gaussian) operator of zero crossings.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.05c
• /
• pp.299-302
• /
• 2002

컴퓨터를 이용한 독순 연구는 Man Machine Interface, 지적부호화에 있어서의 송신측 기술, 청각 장애인의 독순 훈련 시스템 등 다방면에서 그 응용이 기대된다. 본 논문은, 움직임 정보는 입술의 에지영역에 집중하고 있음에 주목하여, 입술 에지영역의 Optical Flow 추정값을 독순정보로 이용하는 방법을 제안한다. 휘도값을 갖지 않는 에지에, 선형 가상 휘도값를 정해주어 Optical Flow를 추정하는 VGM을 도입해 특징 파라미터를 계산하고, 마할라노비스 평방거리(Mahalanobis's square distance)에 기초한 최대우도판별함수를 이용하여 단모음을 분석하는 알고리즘을 제안한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2008.11a
• /
• pp.127-130
• /
• 2008

본 논문에서는 아날로그 TV에서 사용되는 인터레이스 영상을 디지털 디바이스에서 보다 우수하게 출력하기 위해 새로운 디인터레이싱 알고리듬을 제안 한다. 기존의 에지 기반의 라인 평균 방법의 경우 제한된 방향의 화소단위 상관도를 이용하기 때문에 잡음과 계조도 변화에 취약하였다. 또한 공간적 방향 벡터를 사용한 DOI방법은 영상 내 수평 에지가 강한 영역을 보간하는데 우수하지만 좌우 넓은 검색 영역으로 인한 잡음에 취약한 단점이 있었다. ED4D는 에지기반 라인 평균 방법과 공간적 방향 벡터를 적절히 사용하여 규칙적 에지 특성을 갖는 영역에 대한 에지 방향의 정확도를 높였다. 하지만, 참조 방향 및 화소 보간의 판별 기준이 $3{\times}2$ 윈도우로 고정되어 있기 때문에 초기 방향성 판단 기준과 수평 방향 에지 검출에 있어 정밀도가 떨어지는 문제점을 안고 있다. 제안하는 방법은 기존에 사용하던 $3{\times}2$ 윈도우에 $5{\times}2$ 윈도우를 추가적으로 적용하여 초기 방향성 판단 기준을 더 섬세하게 하였으며, 변형된 공간적 방향 벡터를 사용하여 넓은 검색영역으로 인한 잡음의 간섭을 줄였다. 실험결과를 통하여 제안한 방법이 기존의 방법에 비해 주관적 화질뿐만 아니라 객관적인 성능도 우수함을 알 수 있다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.3
• /
• pp.718-723
• /
• 2013

In general, the boundary portion of the background and objects are the rapidly changing point and an important elements to analyze characteristics of image. Using these boundary parts, information about the position or shape of an object in the image are detected, and many studies have been continued in order to detect it. Existing methods are that implementation of algorithm is comparatively simple and its processing speed is fast, but edge detection characteristics is insufficient because weighted values are applied to all the pixels equally. Therefore, in this paper, we proposed an algorithm using region segmentation of the mask in order to adaptive edge detection according to image, and the results processed by proposed algorithm indicated superior edge detection characteristics in edge area.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.6A
• /
• pp.568-574
• /
• 2002

The main issue of noise reduction of image is how to preserve edge and reduce noise. Usually, The Wiener falter is used for this purpose. But the conventional Wiener filter cannot remove noise well in both edge and smooth region due to the single size estimation window. In addition, it ignores the correlation between pixels. In this paper, we propose a new noise reduction algorithm, in which adaptive estimation window is used according to property of smooth region and edge region. In order to make edge more clear, directional Gaussian mask and directional estimation window combines to the Wiener filter according to direction of edge. From the simulation results, it can be seen that the proposed algorithm showed improves performance in both PSNR arid subjective evaluation

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.4C
• /
• pp.223-229
• /
• 2005

In this paper, we proposed an extended edge-based line averaging method for deinterlacing with restricted search range. Conversion from interlaced signal to non-interlaced signal is one of important issues. Conventional deinterlacing algorithms usually utilize edge-based line average algorithm(ELA) within pixel-by-pixel approach. However, it is very sensitive to noise and variation of intensity. To reduce the sensitivity, the proposed method adopts a block-by-block approach and provides reliable direction of edge. Simulation results show that it provides a better performance than other pixel-by-pixel ELA-based methods.

• Journal of Sensor Science and Technology
• /
• v.8 no.2
• /
• pp.124-132
• /
• 1999

In this paper, we propose interband vector quantization of remotely sensed satellite image using edge region compensation. This method classifies each pixel vector considering spectral reflection characteristics of satellite image data. For each class, we perform classified intraband VQ and classified interband VQ to remove intraband and interband redundancies, respectively. In edge region case, edge region is compensated using class information of neighboring blocks and gray value of quantized reference band. Then we perform classified interband VQ to remove interband, redundancy using compensated class information, effectively. Experiments on remotely sensed satellite image show that coding efficiency of the proposed method is better than that of the conventional method.