• Proceedings of the IEEK Conference
• /
• 2001.09a
• /
• pp.565-568
• /
• 2001

이 논문에서는 미디언 필터의 선형 조합을 통해 임의의 주파수 특성을 갖는 필터 구조와 그 설계 방법을 제안한다. Linear-phase FIR 저대역통과 필터의 홀수번째 필터 계수의 부호를 바꾸면 FIR 고대역 통과 필터를 얻을 수 있는데, 이것은 필터 계수의 부호가 모두 양수인 두 개의 부분 필터의 차와 같은 모양을 가진다. 이 과정을 일반화하여 비선형 필터에 적용하면 LCWM(linear combination of median filter)필터는 가중 미디언 부필터(sub-filter)의 선형 조합으로 구성된다. 이는 선형 대수학에서 어떤 공간상의 임의의 벡터가 그 공간의 기저 (basls) 벡터들의 선형 조합으로 표현된다는 사실과 유사하다. 따라서 부필터의 필터 계수를 기저 벡터로이용하여 얻어지는 기저 행렬과 필터의 주파수 특성을 조절하는 계수 벡터를 구함으로써 LCWM 필터를 설계할 수 있다. 제안된 필터 설계 방법을 이용하면 특정 주파수 특성을 가지는 FIR 필터와 유사한 특성을 갖는 비선형 필터 구조를 만들 수 있다. LCWM 필터는 고대역 통과, 저대역 통과, BP(band-pass), BS(band-stop)의 임의의 주파수 특성을 가지는 필터로 설계될 수 있음이 실험을 통해 확인되었다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.3
• /
• pp.471-478
• /
• 2007

The SA fillers encompass a large class of filters based on order statistics as veil as linear FIR filters. Using SA later structure, it is possible to design linear and non-linear filters under a unified framework. In this paper SA filters are applied to an image smoothing problem for mixed noise. Original image is contaminated by Gaussian and impulsive noise. Optimal SA filters are designed and applied to contaminated image. The experimental result shows that SA filters outperform linear FIR and ordering-based nonlinear filters.

• 전자공학회논문지 IE
• /
• v.49 no.1
• /
• pp.24-29
• /
• 2012

In this paper, we propose a progressive filter for impulse noise reduction. The proposed method uses non-linear filter and linear filter progressively. Non-linear filter reduces abrupt noise pattern. Also, linear filter adjusts filtering direction according to an edge in the image which is filtered by non-linear filter. Thus, our proposed method not only preserves edge, but also reduces noise in uniform region. Experimental results show that our proposed method has better quality than those by existing non-linear and linear progressive filtering methods.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.1
• /
• pp.71-76
• /
• 2023

This paper studied a method of attenuating nonlinear noise using a Wiener filter of a neural network structure in an acoustic noise attenuator. This system improves nonlinear noise attenuation performance with a deep learning algorithm using a neural network Wiener filter instead of using a conventional adaptive filter. A voice is estimated from a single input voice signal containing nonlinear noise using a 128-neuron, 8-neuron hidden layer and an error back propagation algorithm. In this study, a simulation program using the Keras library was written and a simulation was performed to verify the attenuation performance for nonlinear noise. As a result of the simulation, it can be seen that the noise attenuation performance of this system is significantly improved when the FNN filter is used instead of the Wiener filter even when nonlinear noise is included. This is because the complex structure of the FNN filter expresses any type of nonlinear characteristics well.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.5
• /
• pp.549-554
• /
• 2012

In this paper, we consider the optimal fuzzy filter of nonlinear discrete-time with estimation error variance constraint. First, the Takagi and Sugeno(T-S) fuzzy model is employed to approximate the nonlinear system. Next, the error state is mean square bounded, and the steady state variance of the estimation error of each state is not more than the individual predefined value. It is shown that, the addressed problem can be carried out by solving linear matrix inequality(LMI) and some algebraic quadratic matrix inequalities. Finally, some examples are provided to illustrate the design procedure and expected performance through simulations.

• Journal of the Institute of Convergence Signal Processing
• /
• v.14 no.1
• /
• pp.6-12
• /
• 2013

Mammography is the most common technique for the early detection of breast cancer. To diagnose correctly and treat of breast cancer efficiently, many image enhancement methods have been developed. This paper presents a nonlinear image enhancement method for the enhancement of digital mammogram. The proposed method is composed of a nonlinear function for brightness improvement and a nonlinear filter for contrast enhancement. The nonlinear function improves the brightness of dark area and extends the dynamic range of bright area, and the nonlinear filter efficiently enhances the specific regions and objects of the mammogram. The final enhanced image was obtained by combining the processed image with the nonlinear function and the filtered image with the nonlinear filter. The proposed nonlinear image enhancement method was confirmed the enhanced performance comparing with other existing methods.

• Journal of Korea Multimedia Society
• /
• v.12 no.1
• /
• pp.26-30
• /
• 2009

We propose an adaptive Recursive Least Rank(RLR) L-filter which uses an L-estimator in order statistics and is based on rank estimate in robust statistics. The proposed RLR L-filter is a non-linear adaptive filter using non-linear adaptive algorithm and adapts itself to optimal filter in the sense of least dispersion measure of errors with non-homogeneous step size. Therefore the filter may be suitable for applications when the transmission channel is nonlinear channels such as Gaussian noise or impulsive noise, or when the signal is non-stationary such as image signal.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.26 no.3
• /
• pp.263-273
• /
• 2008

The precision of sensors' position is particularly important in the application of road extraction or digital map generation. In general, the various ranging solution systems such as GPS, Total Station, and Laser Ranger have been employed for the position of the sensor. Basically, the ranging solution system has problems that the signal may be blocked or degraded by various environmental circumstances and has low temporal resolution. To overcome those limitations a IMU/range integrated system could be introduced. In this paper, after pointing out the limitation of extended Kalman filter which has been used for workhorse in navigation and geodetic community, the two sampling based nonlinear filters which are sigma point Kalman filter using nonlinear transformation and carefully chosen sigma points and particle filter using the non-gaussian assumption are implemented and compared with extended Kalman filter in a simulation test. For the ranging solution system, the GPS and Total station was selected and the three levels of IMUs(IMU400C, HG1700, LN100) are chosen for the simulation. For all ranging solution system and IMUs the sampling based nonlinear filter yield improved position result and it is more noticeable that the superiority of nonlinear filter in low temporal resolution such as 5 sec. Therefore, it is recommended to apply non-linear filter to determine the sensor's position with low degree position sensors.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1998.11a
• /
• pp.398-402
• /
• 1998

본 논문에서는 유ㆍ무선 통신 채널을 통한 데이터 전송시 발생하는 비선형 왜곡을 적응 필터를 이용하여 보상하였다. 특히 통신채널에서는 심볼간 간섭(ISI)이 발생하는데 이러한 간섭을 비선형 필터를 이용하여 제거하였다. 비선형 채널을 모델링하는 방법에는 볼테라급수를 이용하는 방법과 쌍선형 방법이 있다. 쌍선형 방법은 볼테라 방법에 비하여 계산량이 적은 장점을 지니고 있다. 따라서 쌍선형 필터에 적응 알고리듬을 적용하여 신호의 왜곡을 보상하였다. 적응 알고리듬에는 LMS 계열과 LS 계열 알고리듬이 있으나 통신 채널에서는 알고리듬의 안정도가 중요하므로 LMS 계열 알고리듬을 적용하였다. 또한 적응 알고리듬은 입력 데이터의 상관성과 데이터 수에 의존하여 수렴속도와 안정도가 결정된다. 알고리듬의 수렴속도를 증가시키기 위하여 입력신호를 신호파형으로부터 다량의 데이터를 검출하는 방법을 적용하였다. 이러한 방법을 입증하기 위하여 입력신호는 2진 랜덤 가우시안 데이터를 이용하였고, 통신채널에서 채널간 간섭을 발생시켰으며 화이트 가우시안 잡음을 부가 시켰다. 이러한 신호를 수신한 수신기에 적응 등화기를 설계하여 대량의 데이터를 생성시키고, 적응 알고리듬을 적용하여 채널의 왜곡을 빠른 속도로 보상하였다.

• The Journal of the Acoustical Society of Korea
• /
• v.34 no.3
• /
• pp.177-183
• /
• 2015

This paper proposes a robust nonlinear acoustic echo canceller (NAEC) which is effective for modeling the nonlinearity of a speaker module and the long acoustic echo path within a speech communication environment. The proposed NAEC utilizes a sigmoid pre-processor for modeling the speaker nonlinearity and a partitioned block frequnecy-domain adaptive filter for identifying the acoustic echo path with small delay. Simulation results confirmed that the proposed algorithm achieves excellent performance with much lower computational complexity than the previous NAEC.