• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.2
• /
• pp.71-76
• /
• 2015

In similarity join processing, a general technique employs a generation-verification framework, which includes two phases: the first phase generates a set of candidate pairs from a collection of records; and the second phase verifies each candidate pair by computing real similarity. In order to reduce the number of candidate pairs in the verification phase, the median of one record of each candidate pair is used as a filter in this paper to test whether the other record can has the proper number of overlapped tokens. We propose a similarity join algorithm with the median filter, and show that the proposed algorithm has better performance in execution time than recent algorithms without the filter through extensive experiments on real-world datasets.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.11C
• /
• pp.940-947
• /
• 2010

Motion Compensated Frame Interpolation(MCFI) has been used to reduce motion jerkiness for dynamic scenes and motion blurriness for LCD-panel display as post processing for high quality display. However, MCFI that directly uses the motion information often suffers from annoying artifacts such as blockiness, ghost effects, and deformed structures. So in this paper, we propose a novel edge-based adaptively weighted vector median filter as post-processing. At first, the proposed method generates an edge direction map through a sobel mask and a weighted maximum frequent filter. And then, outlier MVs are removed by average of angle difference and replaced by a median MV of $3{\times}3$ window. Finally, weighted vector median filter adjusts the weighting values based on edge direction derived from spatial coherence between the edge direction continuity and motion vector. The results show that the performance of PSNR and SSIM are higher up to 0.5 ~ 1 dB and 0.4 ~ 0.8 %, respectively.

• Geophysics and Geophysical Exploration
• /
• v.15 no.4
• /
• pp.199-208
• /
• 2012

High-amplitude swell noises (HASN) are very difficult to eliminate from the marine seismic data. In this paper, we applied F-X filter and median filter in order to suppress HASN. Test data have been acquired on the northern offshore of the South Shetland Islands in December, 2010. Parts of data have been contaminated by HASN caused by bad weather during the cruise. We applied F-X filter and median filter to test data with HASN. After F-X filtering, most of non-coherent noises and small-amplitude swell noises are eliminated effectively but HASN are still remained significantly. With median filter, HASN was suppressed better than F-X filter, however some of non-coherent noises are still remains. We applied a cascade of two filters and results show HASN and non-coherent noises are suppressed effectively. After the cascade of two filtering, it is possible to define reflection layers clearly on the velocity spectrum and to produce better stacked section with a good signal-to-noise ratio.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2078-2080
• /
• 2001

본 논문은 기존의 가중 메디안 필터에 음의 가중치를 갖는 recursive weighted median(RWM) 필터 구조를 소개하고자 한다. 이는 연산과정에 퍼지 클러스터를 적용하여 또 다른 구조의 RWM 필터를 제안하였다. 제안된 RWM 필터는 infinte impulse response(IIR) 선형 필터의 부류로 상사되는 것으로서 기존의 선형 IIR 필터와는 달리 강건한 대역 또는 고역통과 필터의 특성 뿐만 아니라 피드백 되어진 계수 값에 상관없이 항상 BIBO 시스템에서의 안정성과 잡음에 강건한 특성을 나타낸다. 특히 퍼지 클러스터를 적용하여 중앙값 주변의 값을 적절히 취함으로서 신뢰성과 보다 빠른 연산속도의 성능을 여러 다른 구조의 필터들과 성능 비교 실험을 통해 입증하였다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.6
• /
• pp.83-88
• /
• 2005

In this paper, detection based - adaptive windowed nonlinear filters(DB-AWNF) are proposed for removing one-side impulse noise in infrared image. They are composed of impulse detector and window-size-variable median filters. Impulse detector checks whether current pixel is impulse or not using range function and nonlinear location estimator. If impulse is detected, current pixel is filtered according to four kinds of local masks by use of median filter. If not. current pixel is delivered to output like identity filter. In qualitative view, the proposed could have removed heavy corrupted noise up to $20\%$ and reserved the details of image. In quantitative view, PSNR was measured. The proposed could have 13 - 31[dB] more improved performance than those of median($3{\times}3$) filter and 18 - 25[dB] more improved performance than those of median($5{\times}5$) filter.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.352-352
• /
• 2022

수위자료는 기초 수문자료의 하나로서 자료 수집시 이에 대한 품질관리가 반드시 필요하다. 이 과정에서 이상치 여부를 점검하여 이상치로 확인된 경우 소거하거나 수정하는 등의 처리를 해야 한다. 수위자료의 이상치 점검에는 다양한 방법이 있지만 아직 일반화된 방법은 없다. 이에 다양한 방법에 대한 적용가능성을 평가해 볼 필요가 있다. Hampel 필터는 신호처리 시 신호의 이상치를 찾아 보완하려고 개발된 필터이다. 시계열자료에서 이상치를 감지하는 고전적인 접근 방법은 이동평균과 이동표준편차를 이용하는 것이지만 고전적인 이동평균과 이동표준편차는 이상치의 영향을 받는다. 이에 따라 이상치의 추정이 어렵게 되는 경우가 있다. 이에 반하여 Hampel 필터는 이동평균 및 이동표준편차 대신 중앙값과 중앙값 절대편차(Median Absolute Deviation; MAD)를 이용함으로써 더 나은 결과를 얻을 수 있다. Hampel 필터는 신호처리용으로 개발되었기 때문에 부드러운 Sine 곡선에 적합할 것으로 보이며, 이미 하천수위 변화보다는 부드러운 변화를 보이는 저수지수위의 이상치를 점검하기 위해 사용되고 있다. 하지만 변화가 급격하고 첨두가 발생하는 하천의 수위에 대해서도 적용할 수 있는지에 대해서는 평가가 필요하다. 이에 본 연구에서는 신호처리에 사용되는 Hampel 필터를 이용하여 수위자료의 이상치 점검에 적용하고 과거 자료에 기록된 실제 이상치 자료와 비교하여 그 성능을 평가해 보았다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2016.07a
• /
• pp.289-291
• /
• 2016

본 논문에서는 VR의 발전과 함께 주목받고 있는 컴퓨터 비전 관련 기술들에 대하여 살펴보고, 가장 먼저 선행되어야 하는 이미지 필터링 알고리즘에 대하여 살펴 본다. 다양한 case에서의 여러 Image Filter를 구현, 성능을 비교 분석해 보고, 정확도를 향상 시킬 수 있는 방안에 대하여 연구한다.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.5
• /
• pp.231-241
• /
• 2013

In this paper, we propose an average approximation filter which can effectively remove the noises of the images. The noises include impulse noises, gaussian noises and mixed noises. The algorithm is as follows. First, as a step of noise detection, we find whether the difference between the pixel value and the average value is greater than the threshold value or not after getting the average value that removed the minimum and maximum values in the applied mask. If the pixel value is greater than the threshold value, the pixel value is processed as noise. If it is less than or equal to the threshold value, it is processed as non-noise. Next, as the noise reduction step, we output the approximate value in mask as the pixel value and the average value except the minimum and maximum values of the pixel including the noise. As the result of applying this average approximation filter to the mixed noise images, the approximation filter can reduce the noises effectively more than 0.4[dB] as compared with applying the median filter and the average filter, respectively.

• The Journal of the Acoustical Society of Korea
• /
• v.31 no.1
• /
• pp.29-38
• /
• 2012

This paper presents a transient noise reduction system in a speech signal. The proposed transient noise reduction system utilizes a median filter to reduce the transient noise. Since the median filter can distort speech during the noise reduction, a long-term prediction (LTP) filter is adopted as a pre-processor to minimize speech distortion. The speech information preserved by the LTP filter is re-synthesized after reducing the noise. This paper verifies the weakness of a linear prediction (LP) filter and the superiority of the LTP filter for preserving the speech component in transient noise presence environment. Applying the proposed system, the signal-to-noise ratio (SNR) of output is improved by 8dB in both speech and noise presence region, and PESQ score is increased by 1 point comparing with noisy input.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.1
• /
• pp.101-108
• /
• 2005

Adaptive constant false alarm rate(CFAR) algorithm is used for good detection probability as well as constant false alarm rate in clutter background. Especially, filtering technique adaptive to spatial variation is necessary for improving detection quality in non stationary clutter environment which has spatial correlation and large magnitude deviation. In this paper, we propose a two-dimensional block interpolation(TBI) adaptive CFAR algorithm that calculates the node estimate in the fred two dimensional region and subsequently determines the final estimate for each resolution cell by two-dimensional interpolation. The proposed method is efficient for filtering abnormal ejection by adopting distribution median in fixed region and also has advantage of reducing required memory space by using estimation method which gets final values after calculating the block node values. Through simulations, we show that the proposed method is superior to the traditional adaptive CFAR algorithms which are transversal or recursive in aspect of the detection performance and required memory space.