• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.08a
• /
• pp.337-340
• /
• 2000

조명 및 반사광의 성질에 의해 블러링이 발생하고 이런 영상을 인식하는 경우 정확한 에지 검출이 어렵게 된다. 이를 최적으로 검출하기 위해 일정하게 에지를 검출할 수 있는 가우시안 함수와 2차 미분 함수를 합성한 새로운 하이브리드 함수를 제안하고 실제 영상과 컨볼루션 한 후 함수의 $\sigma$값을 변화시키면서, Canny 알고리즘의 방향성 에지 검출 방법을 적용하여 에지를 검출하였다. 그 결과 Sobel, Robert, Canny 에지 검출방법보다 0.2~14㏈ 정도 안정적으로 에지가 검출되었다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.2 no.1
• /
• pp.53-62
• /
• 2001

In this paper, the hybrid function by local scale control is proposed to detect the optimal edges from blurred images. In the case of image capturing, some blurring is occurred by the characteristics of the illumination and the reflected light. During processing the blurred image, it is difficult to detect perfect edges. This algorithm proposed a new hybrid function which is merged Gaussian function and the second derivative of Gaussian function. And it detects the optimal edges applying directional edge detection by Canny algorithm as the scale factor of $\sigma$ in the given local mask has been changed after convolving the hybrid function for input image. In the result, the performance is confirmed that this algorithm is better than Sobel, Robert and Canny edge detector by analyzing the some test images. And the results is obtained 0.2 ㏈ ~ 14 ㏈ of PSNR than those conventional method.

• The Journal of the Korea Contents Association
• /
• v.3 no.3
• /
• pp.11-18
• /
• 2003

Error diffusion is a procedure for generating high quality bilevel images from continuous-tone images but blurs the edge information. To solve this problem, we propose the improved method appling edge enhanced weights based on local characteristic of the original images. We consider edge information as local characteristic. First, we produce edges by appling 3$\times$3 sobel operator to the original image. The edge is normalized from 0 to 1. Edge information weights are computed by using sinusoidal function and the normalized edge information. The edge enhanced weights are computed by using edge information weights multiplied input pixels. The proposed method is compared with conventional methods by measuring the edge correlation and quality of the recovered images from the halftoned images. The proposed method provides better quality than the conventional method due to the enhanced edge and represents efficiently the detail edge. Also, the proposed method is improved in edge representation than the conventional method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.7
• /
• pp.1680-1686
• /
• 2015

Edge detection is an essential preprocessing for most image processing application, and there are several existing detection methods such as Sobel, Roberts, Laplacian, LoG(Laplacian of Gaussian) operators, etc. Those existing edge detection methods have not given satisfactory results since they do not offer enough pixel brightness change in low light level environment. Therefore, in this study new algorithms using brightness transfer function in the preprocessing and for edge detection applying standard deviation and average-weighted local masks are proposed. In addition, the performance of proposed algorithms was evaluated in comparison with the existing edge detection methods such as Sobel, Roberts, Prewitt, Laplacian, LoG operators.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.787-789
• /
• 2017

Edge detection is used in many applications such as image analysis, pattern recognition and computer vision. Existing edge detection methods, there is such Sobel, Prewitt, Roberts, and LoG(Laplacian of Gaussian). In the conventional edge detection method, edge detection is insufficient because the change of the pixel brightness is small when the original image is in low illumination. Therefore, in this paper, we proposed a function to convert the pixel brightness of low illumination image to solve this problem. And it was compared by applying the conventional methods Sobel, Prewitt, Roberts, LoG(Laplacian of Gaussian) to determine the performance of the pixel brightness transform function.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.562-564
• /
• 2002

본 논문에서는 자기상관함수의 국소적 특징을 사용하여 에지 특징을 추출한 후, 이를 이용해 유사이미지를 검색하는 방법을 제시한다. 자기상관함수의 국소적 특징을 이용하여 이미지를 검색할 경우 크기, 밝기, 색상등과 같은 이미지 요소가 서로 다를 경우에도 영향을 받지 않고 에지 특징정보를 추출해 낼 수 있다. 이는 얻어진 에지 특징을 이미지 크기와 고차 국소 자기상관함수의 변위에 의해 변하지 않도록 정규화를 하고, 동일 이미지에 대해 밝기가 조금 달라지면 검색효율이 떨어지는 점을 해결하기 위해 거리척도로서 방향여현거리(direction cosine distance)를 이용함으로써 가능하다. 이렇게 추출된 특징벡터를 자기조직화 맵에 의하여 클러스터링하고, 유사이미지 검색의 효율성을 비교해본 결과, 본 논문에서 제시한 방법을 사용하여 검색한 경우 재현율이 기존의 방법에 비해서 비교적 높은 수치를 나타냈다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.3
• /
• pp.748-753
• /
• 2004

Edge includes variety of information about image's location and shape etc. So a lot of researches for detecting those edges have been continuing even now and at the early stage of the research, edge detection operators searched neighborhood pixels and used relation among pixels. However, these methods do not have excellent performance in the image which exists noise and can not detect edges selectively. For this reason, in this paper we detected image's line-edge element from degraded image by AWGN (additive white gaussian noise) with wavelet function which is independent of line's width.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.545-548
• /
• 2005

H.264의 인트라 프레임 에러복원기법은 상하좌우 인접한 블록의 픽셀을 사용하여 거리의 가중치 평균값으로 손실된 블록을 복원한다. H.264의 인트라 프레임 에러복원기법으로 복원된 블록은 주변블록 픽셀들의 평균을 취하기 때문에 그로 인해 생기는 블러링 현상을 피할 수 없다. 이를 개선하기 위하여 주변블록의 에지정보를 이용하여 인터폴레이션하는 방법이 제안되었으나 에지성분이 다양하거나 에지성분이 없는 경우, 블록을 복원하는 데 있어서 기존 H.264의 복원기법보다 성능이 저하되는 문제점이 있다. 본 논문에서는 주변블록의 정보를 이용하여 손실된 블록의 인터폴레이션의 에지방향을 추정하고 방해함수를 통해서 임계치를 결정하여 적응적으로 에지방향의 인터폴레이션과 가중치평균 인터폴레이션을 선택하여 복원하는 방법을 제안한다. 에지방향의 인터폴레이션에서는 선택된 전체에지방향과 상하좌우 각각의 주변블록의 에지방향들간의 상호 관계를 고려함으로써 최종적으로 최적에지 방향을 선택하여 성능을 향상시킨다. 제안된 방법은 영상에 따라 H.264 에러복원기법보다 객관적인 화질이 $0.5dB\;{\sim}\;2dB$ PSNR 향상을 보였고 주관적인 화질개선의 결과를 보였다.

• Journal of Korea Multimedia Society
• /
• v.8 no.2
• /
• pp.174-180
• /
• 2005

Points of sharp variations in image are the most important components when we analyze the features of image. And they include a variety of information about image's shape and location etc. So a lot of researches for detecting edges have been continued. Edge detection operators which were used at the early stage of the research were to utilize relations among neighboring pixels. These methods detect edge at all boundaries, therefore they perform edge detection twice about curves below some width such as line-edge. In the meantime, wavelet transform which is presented as a new technique of signal processing field provides multiscale edge detection and is being applied widely in many fields that analyze edge-like characteristic. Therefore, in this paper we detected line-edge with new 2-D wavelet function which is independent of line's width.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.12
• /
• pp.2975-2980
• /
• 2015

Edge detection is one of image processing techniques applied for a variety of purposes in a number of areas and it is used as a necessary pretreatment process in most applications. Detect this edge has been conducted in various fields at domestic and international. In the conventional edge detection methods, there are Sobel, Prewitt, Roberts and LoG, etc using a fixed weights mask. Since conventional edge detection methods apply the images to the fixed weights mask, the edge detection characteristics appear somewhat insufficient. Therefore in this study, to complement this, preprocessing using gray-level transformation function and algorithm finding final edge using maximum and minimum value of estimated mask by local mask are proposed. And in order to assess the performance of proposed algorithm, it was compared with a conventional Sobel, Roberts, Prewitt and LoG edge detection methods.