• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2011년도 추계학술대회
• /
• pp.918-920
• /
• 2011

본 논문에서는 이진화 결과 임펄스 노이즈 형태가 나타나는 영상에서 직선 성분을 검출할 때 사용되는 에지 패턴 분리 방법을 제안한다. 임펄스 노이즈가 발생하면 직선형태의 에지 패턴이 왜곡되어 복잡한 형태의 에지 형태가 된다. 왜곡된 상태에서 직선 검출 알고리즘을 적용하면 노이즈로 왜곡된 직선을 검출하지 못하기 때문에 전체 영상의 에지 성분을 방향성을 이용하여 분리하여야 한다. 본 논문에서는 4 방향에 대해서 에지 성분을 분리하였고, 분리한 각 영상에 대해서 겹쳐진 직선 패턴을 분리하여 직선을 검출하였다. 실험 결과는 제안하는 방법이 간단하면서도 정확하게 직선을 검출함을 보여준다.

• 한국통신학회논문지
• /
• 제32권2C호
• /
• pp.124-131
• /
• 2007

본 논문에서는 전송 에러로 인해 발생하는 영상의 손실을 정밀한 방향성 보간(FDI: Fine Directional Interpolation)을 이용하여 복원하는 기법을 제안한다. 제안된 알고리즘은 공간 방향 벡터(SDV: Spatial Direction Vector)를 도입한다. 공간 방향 벡터는 손실블럭 주위의 영상 데이터의 에지 정보를 추출하여 구한다. 이 후 손실된 영상 블록은 공간 방향 벡터를 이용하여 픽셀단위로 적응적으로 보간함으로써 복원된다. 이러한 방식은 평탄한 영역뿐만 아니라 에지를 포함한 복잡한 영역도 우수하게 복원할 수 있다. 실험결과 제안된 방식은 기존의 공간적 에러은닉 방법과 비교하여 성능이 우수하다는 것을 알 수 있다.

• Journal of information and communication convergence engineering
• /
• 제9권5호
• /
• pp.591-596
• /
• 2011

Image denoising is a key issue in all image processing researches. Generally, the quality of an image could be corrupted by a lot of noise due to the undesired conditions of image acquisition phase or during the transmission. Many approaches to image restoration are aimed at removing either Gaussian or impulse noise. Nevertheless, it is possible to find them operating on the same image, which is called mixed noise and it produces a hard damage. In this paper, we proposed noise type classification method and a mixed nonlinear filter for mixed noise suppression. The proposed filtering scheme applies a modified adaptive switching median filter to impulse noise suppression and an efficient nonlinear filer was carried out to remove Gaussian noise. The simulation results based on Matlab show that the proposed method can remove mixed Gaussian and impulse noise efficiently and it can preserve the integrity of edge and keep the detailed information.

• Journal of information and communication convergence engineering
• /
• 제10권1호
• /
• pp.45-52
• /
• 2012

Thedenoising of a natural image corrupted by Gaussian noise is a long established problem in signal or image processing. Today the research is focus on the wavelet domain, especially using the wavelet threshold method. In this paper, a waveletbased image denoising modified adaptive thresholding method is proposed. The proposed method computes thethreshold adaptively based on the scale level and adaptively estimates wavelet coefficients by using a modified thresholding function that considers the dependency between the parent coefficient and child coefficient and the soft thresholding function at different scales. Experimental results show that the proposed method provides high peak signal-to-noise ratio results and preserves the detailed information of the original image well, resulting in a superior quality image.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.480-485
• /
• 2005

Perspective dynamical systems arise in machine vision problems, in which only perspective observation is available. This paper considers the state estimation problem for a rigid body moving in three dimensional spaces using the image data obtained by a CCD camera or some other means. Because the motion of the rigid body and the observed data are generally corrupted by noises, it is necessary to seek a state estimation method to reduce the influence of the noises. In this paper, by means of computer simulations for a simple example, we examine the sensitivity to the noises of the nonlinear observer developed in the recent paper ([1] R. Abdursul, H. Inaba and B. Ghosh, Nonlinear observers for perspective time-invariant linear systems, Automatica, vol. 40, Issue 3, pp. 481-490, 2004) and the effectiveness of the Extended Kalman Filter.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2007년도 추계종합학술대회
• /
• pp.367-370
• /
• 2007

Both impluse noise and AWGN (additive white Gaussian noise) are easily corrupted into images, during signal transmission and acquisition. Thus, an algorithm for removing both noises is represented in this paper. An impulse noise detection step can effectively separate impulse noise with AWGN, then in the noise filtering step, by using several parameters, not only impulse noise but also AWGN can be reduced. The value of those parameters are automatically changeable when the standard deviation of AWGN, the impulse noise density, and the spatial distances between pixels are different. Results of computer simulations show that the proposed approach performs better than other conventional filters.

• Journal of information and communication convergence engineering
• /
• 제9권1호
• /
• pp.59-63
• /
• 2011

Conventional noise reduction filtering schemes realize limited improvements of the peak signal-to-noise ratio (PSNR) in the low-level noisy images. The flatness degree and the edge information are effectively used to estimate the noise volume. We propose a noise estimator for reducing noise in the AWGN (additive white gaussian noise) corrupted images using three intermediate image maps (FGM(flatness gray map), FIM(flatness index map), NEM(noise estimate map)). The proposed noise estimator is fed into the conventional noise reduction filters as a pre-processor. The performance of noise reduction is tested in the various AWGN corrupted images.

• 전자공학회논문지B
• /
• 제30B권5호
• /
• pp.103-108
• /
• 1993

An image can be largely corrupted by the ambient illuminant, so that the image enhancement to restory natural color without respect to the ambient illuminant is needed. It this paper, a new color image enhancement technique based on color constancy is proposed. To enhance the image quality, higher volues of contrast and saturation are preferred, but their excessive values make an image unnatural. Since the color constancy processing preserves only hue, while reducing the dynamic range of lightness and saturation,the technique is needed in order to compensate this phenomenon. The proposed method transforms and increases lightness and saturation simultaneously to avoid the complexity in the related transformation by analyzing the relationship between the RGB and modified IHS coordinate system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권8호
• /
• pp.3842-3855
• /
• 2018

A novel image completion method is proposed that uses the advantage of planar structural information to fill corrupted portions of an image. First, in estimating parameters of the projection plane, the image is divided into several planes, and their planar structural information is analyzed. Second, in calculating the a priori probability of patch and patch offset regularity, this information is converted into a constraint condition to guide the process of filling the hole. Experimental results show that the proposed algorithm is fast and effective, and ensures the structure continuity of the damaged region and smoothness of the texture.

• 한국정보통신학회논문지
• /
• 제11권7호
• /
• pp.1373-1379
• /
• 2007

본 논문에서는 임펄스 잡음검출과 필터링을 기반으로 하는 변형된 적응 스위칭 메디안 필터 알고리즘을 제안하였다. 임펄스 잡음검출 과정에서는 마스크 내의 화소값의 차에 의해 설정된 임계값을 사용하며, 이 때 잡음으로 판단된 화소들에 대하여 필터링 과정을 수행한다. 제안한 필터링 방법은 국부 잡음밀도에 상응하여 마스크 크기를 가변하며, 필터링을 반복 수행한다. 그리고 제안한 방법의 시뮬레이션을 위해, 다양한 밀도의 임펄스 잡음을 원영상에 중첩하여 테스트 영상으로 사용하였으며, 기존의 방법과 비교하였다. 또한 평가를 위한 기준으로 PSNR을 적용하였으며, 시뮬레이션 결과에서 제안한 알고리즘은 우수한 성능을 나타내었다.