• Journal of Broadcast Engineering
• /
• v.5 no.1
• /
• pp.31-40
• /
• 2000

In this paper, we propose an edge histogram to efficiently represent the edge distribution in the image for MPEG-7. To this end, we adopt global, semi-global, and local edge histogram bins. Also, we extract the edge information from the image in terms of image blocks rather than pixels, which reduces the extraction complexity and is also applicable to the block-based compression standards such as MPEG-1, and 2. Experimental results show that the proposed method yields better retrieval accuracy and feature extraction speed comparing to other non-homogeneous texture descriptors of MPEG-7 including the wavelet-based descriptor and local edge-based descriptor.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.413-414
• /
• 2024

영상 인식을 위한 학습 데이터 구성 단계에서 에지는 물체의 크기, 방향 등의 정보를 포함하고 있어 영상의 특징으로 사용한다. 본 논문에서는 얼굴 인식을 위하여 소벨 마스크를 사용하여 원영상과 압축영상 그리고 에지영상간의 학습에 따른 인식 정도를 파악하고자 한다. 실험결과, 원영상 그대로 인식하는 것보다 에지 영상에 의한 학습 속도에 차이가 있음을 알 수 있었다.

• The Korean Journal of Applied Statistics
• /
• v.13 no.2
• /
• pp.515-523
• /
• 2000

In this paper we detect edges using stutistical methods of the change-point problem. For this, we perform the hypothesis testing for differences in gray levels to see whether any $n\timesn$ subimage contains edge segments. The proposed method based on the twosample Kolmogorov-Smirnov test is introduced and the likelihood ratio test and the \VolfeSchechtman test for change-point problem arc also applied for edge detection. \Ve perform the experimental study to assess the performance of these methods in both noisy and uncontaminated sample noises.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.10a
• /
• pp.479-482
• /
• 2003

Edge, detected from image processing includes variety of information about original image's location and shape etc. So a lot of researches for detecting those edges have been continuing even now. And with the recent progress of wavelet theory which is presented as a new technique of signal processing fields, wavelet transform is being applied to many fields which analyzes singularities of image. For this reason, this paper detected original image's edge from the information such as local maximum, direction, and location of the wavelet transform data by using wavelet function which is independent of width of line.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.11a
• /
• pp.191-194
• /
• 1997

본 논문에서는 2D-DCT 변환된 동영상 프레임 사이의 오차 블록들의 활성 레벨(atcivity level)과 에지의 특성을 분류하여 동영상의 적응적인 양자화를 제안한다. 각 블록에서는 활성 레벨이 각기 다르고, 같은 활성 레벨이라 할지라도 에지의 특성도 각기 다르게 나타난다. 적응적인 양자화를 위해서, 2D-DCT 변환된 영상 오차의 각 블록의 활성레벨 뿐만 아니라 AC 계수들의 분포에 따른 에지 특성을 분류하면, 블록의 활성 레벨만을 일률적으로 적용한 Sorting 방법의 경우보다 향상된 영상을 복원할 수 있다. 블록의 활성 레벨은 AC energy에 의해서 측정하고, 에지 특성은 AC 계수들의 분포에 의해 결정하게 된다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.8C
• /
• pp.801-809
• /
• 2005

This paper proposes a new algorithm for improving the performance of the spatial filter which is the most important part of deinterlacing methods. The conventional edge-based algorithms are not satisfactory in deciding the exact edge direction which controls the performance of the interpolation. The proposed algorithm much increases the performance of the intrafield interpolation by finding exact edge directions based on the binary image. Edge directions are decided using 15 by 3 local window to find not only more accurate but also many low-angle edge directions. The proposed interpolation method upgrades the visual quality of the image by alleviating the misleading edge directions. Simulation results for various images show that the proposed method provides better performance than the existing methods do.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.770-772
• /
• 2013

Edges on the images are widely used in preprocessing in various areas including recognition and detection of the object. As generally known edge detection methods, there is a method using mask and these methods are Sobel, Prewitt, Roberts, Laplacian operator and etc. Implementation of these existing edge detection methods is simple. However, when processing the impulse noise added images, the properties of edge detection is not sufficient. Accordingly, in order to compensate for the weakness of existing edge detection methods and to detect strong edges on the images which were damaged by impulse noise, the edge detection algorithm using transformed mask was proposed in this paper.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.136-138
• /
• 2022

Edge detection includes information such as the shape, position, size, and material of an object with respect to an image, and is a very important factor in analyzing the characteristics of the image. Existing edge detection methods include Sobel edge detection filter, Roberts edge detection filter, Prewitt edge detection filter, and LoG (Lapacian of Gaussian) using secondary differentials. However, these methods have a disadvantage in that the edge detection results are somewhat insufficient because a fixed weight mask is applied to the entire image area. Therefore, in this paper, we propose an edge detection algorithm that increases edge detection characteristics by considering the center pixel in the mask. In addition, in order to confirm the proposed edge detection performance, it was compared through simulation result images.

• Proceedings of the KIEE Conference
• /
• 2007.10a
• /
• pp.413-414
• /
• 2007

본 논문은 칼라 필터 배열(color filter array : CFA) 영상에서 채널 간 상관관계를 이용한 새로운 에지 방향 컬러 보간 방법을 제시하였다. 고정 채널 간 컬러 차 가정에 따라 휘도와 색차간의 차가 큰 경우 에지 영역이라 판단한다. 에지 방향 판별을 정확히 하기 위해 수평, 수직 방향으로 컬러 차 영상을 구하고, 구한 영상에서 변화량을 계산하여 에지 방향 판별 기준으로 사용한다. 에지 판별 기준을 사용하여, 에지 방향에 따라 컬러 보간을 수행한다. 평탄 영역은 이웃 화소와의 유사성에 따라 가중치를 다르게 줘서, 이웃 화소의 가중치 합으로 구한다 실험 결과는 제안하는 알고리즘이 기존 알고리즘 보다 우수함을 보여준다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.802-804
• /
• 2014

Edge detection of image for performing the road lane recognition is an essential preprocessing. Various studies are being performed in order to detect such edge and there are conventional edge detection methods such as Sobel, Prewitt and Roberts. Such methods regardless of pixel distribution are processed by applying the same weighted value to the entire pixels and show a somewhat insufficient edge detection results. Therefore, this paper has proposed an algorithm that detects the edge using the suitable weighted value for the road lane recognition considering the pixel distribution shape of the image.