• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.6
• /
• pp.109-120
• /
• 2004

The current paper presents an effective deblocking algorithm for block-based coded images using singularity detection in Mallat wavelet transform. In block-based coded images. The local maxima of the wavelet transform modulus detect all singularities, including blocking artifacts, from multiscale edges. Accordingly, the current study discriminates between blocking artifacts and edges by estimating the Lipschitz regularity of the local maxima and removing the wavelet transform modulus of blocking artifacts. Experimental results showed that the performance of the proposed algorithm was objectively and subjectively superior.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.711-714
• /
• 2015

A new technique for image restoration using Weighted cross-shaped median filter with edge-detection algorithm is proposed in this paper. It consists of simple hypothesis test for edge-detection, and makes use of the weighted cross-shape window. This method is applied to noise corrupted image and its results are compared with those of median filters. As for the experimental result, method of weighted cross-shape median filter is superior to other median filters.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.1006-1009
• /
• 2013

In this paper, a new technique for image enhancement using cross-shaped median filter with edge-detection algorithm is proposed. It consists of simple hypothesis test for edge-detection, and makes use of the cross-shaped window. This method is applied to noise corrupted image and its results are compared with those of median filters. As for the experimental result, method of cross-shaped median filter is superior to other median filters.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.10A
• /
• pp.1011-1020
• /
• 2002

The current paper presents an effective deblocking algorithm for block-based coded images using singularity detection in a wavelet transform. In block-based coded images, the local maxima of a wavelet transform modulus detect all singularities, including blocking artifacts, from multiscale edges. Accordingly, the current study discriminates between a blocking artifact and an edge by estimation the Lipschitz regularity of the local maxima and removing the wavelet transform modulus of a blocking artifact that has a negative Lipschitz regularity exponent. Experimental results showed that the performance of the proposed algorithm was objectively and subjectively superior.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.11a
• /
• pp.755-758
• /
• 2002

스테레오스코픽 영상은 스테레오스코픽 카메라를 이용하여 좌 영상(left image)과 우 영상(right image)을 동시에 획득하는 것으로 사람의 눈으로 보는 것과 같은 입체감을 얻을 수 있는 것을 특징으로 한다. 스테레오스코픽 영상에서 객체의 깊이값을 구하기 위해서는 영상의 정합점을 찾는 것이 중요한데, 본 논문에서는 일반화 대칭변환(generalized symmetry transform) 알고리즘을 적용하여 스테레오스코픽(stereoscopic) 영상의 정합점(correspond points)을 찾는 방법을 제안한다. 본 논문에서 제안하는 방법은 먼저 좌 영상과 우 영상에 대해 에지(edge), 코너 검출 방법을 통해 특징점(feature point)을 검출하고 각 특징점들을 중심으로 사각 영역을 설정하고 이 범위내의 에지들이 갖는 대칭도(symmetry magnitude)를 특징점의 위치에 누적 시킨다. 좌영상의 대칭도를 구한 결과를 우 영상의 에지들의 대칭도와 비교를 수행해 임계치(threshold) 이하의 값을 가진 점들을 정합 후보로 선택한다. 이 정합 후보들을 영역내의 반지름 단위의 대칭도 비교를 통해 더욱 세분화된 비교를 수행하고 만약 이와 같은 과정을 통해서도 정합점을 찾지 못한다면 정합 후보들에 대해 칼라 정합도를 측정하여 최종적으로 정합점을 검출한다. 제안한 알고리즘을 이용한다면 특징점만을 이용하여 검색을 수행했을 때보다 더욱 정확한 정합점을 구할 수 있다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.10a
• /
• pp.684-686
• /
• 2017

Currently, image processing is used in various fields including military, medical and industrial fields. Noise added to images undermine the quality of images. As such, the removal of noise is an essential step to process images such as through recognition of images, detection of edge and segmentation of images. Studies on removing noise from images are actively being undertaken. One of the leading noises that are added to images is the AWGN(additive white Gaussian noise). This paper suggests an algorithm that synthesizes a filter that uses edge detection and standard deviation to ease AWGN.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.10a
• /
• pp.956-958
• /
• 2016

Currently, image processing has been widely utilized and the noise may be occurred in the processes of image data transmission, processing, and storage. The studies have been actively conducted to eliminate the added noise in the image. The types of noise in the image are various depending on the causes and the forms, and additive white Gaussian noise(AWGN) is the representative one. The algorithm to apply and process the weighted value was suggested by the directions of the pixel in the local mask using edge detection to relieve the added AWGN in the image in this article.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.3
• /
• pp.109-114
• /
• 2021

GAN(Generative Adversarial Network) is an image generation model, which is composed of a generator network and a discriminator network, and generates an image similar to a real image. Since the image generated by the GAN should be similar to the actual image, a loss function is used to minimize the loss error of the generated image. However, there is a problem that the loss function of GAN degrades the quality of the image by making the learning to generate the image unstable. To solve this problem, this paper analyzes GAN-related studies and proposes an edge GAN(eGAN) using edge detection. As a result of the experiment, the eGAN model has improved performance over the existing GAN model.

• Journal of Broadcast Engineering
• /
• v.14 no.2
• /
• pp.253-264
• /
• 2009

This paper presents an algorithm, aims at practical applications, for the high speed processing and performance enhancement of lane detection base on vision processing system. As a preprocessing for high speed lane detection, the vanishing line estimation and the optimal extraction of region of interest for lane boundary (ROI-LB) can be processed to reduction of detection region in which high speed processing is enabled. Image feature information is extracted only in the ROI-LB. Road lane is extracted using a non-parametric model fitting and Hough transform within the ROI-LB. With simultaneous processing of noise reduction and edge enhancement using the Laplacian filter, the reliability of feature extraction can be increased for various road lane patterns. Since outliers of edge at each block can be removed with clustering of edge orientation for each block within the ROI-LB, the performance of lane detection can be greatly improved. The various real road experimental results are presented to evaluate the effectiveness of the proposed method.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2009.01a
• /
• pp.215-218
• /
• 2009

본 논문에서는 웨이블릿 변환 된 고주파 서브밴드들의 에지 정보를 이용하여 관심 객체 영역을 고속으로 자동 검출해주는 새로운 알고리즘을 제안하였다. 제안된 방법에서는 에지정보를 이용하여 블록단위의 4-방향 객체 윤곽 탐색 알고리즘(4-DOBS)을 수행하여 관심객체를 검출한다. 전체 이미지는 $64{\times}64$ 또는 $32{\times}32$ 크기의 코드 블록으로 먼저 나누어지고, 각 코드 블록 내에 에지들이 있는지 없는지에 따라 관심 코드블록 또는 배경이 된다. 4-방향은 바깥쪽에서 이미지의 중앙으로 탐색하여 접근하며, 피사계 심도가 낮은 이미지는 중앙으로 갈수록 에지가 발견된다는 특징을 이용한다. 기존 방법들의 문제점 이였던 복잡한 필터링 과정과 영역병합 문제로 인한 높은 계산도를 상당히 개선시킬 수 있었다. 또한 블록 단위의 처리로 인하여 실시간 처리를 요하는 응용에서도 적용 가능 하였다.