• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2003.06a
• /
• pp.14-17
• /
• 2003

웨이블릿 변환 영역에서 잡음제거 방법 중 Visushrink 추정에 사용되는 경계값은 측정 데이터 수와 잡음편차에 비례하는 것으로 알려져 있으나 잡음편차가 알려지지 않은 경우 Donoho는 웨이블릿 변환 영역의 최고대역에서 잡음편차 추정 방법을 제시하였다. 본 논문에서는 분산이 데이터 수에 반비례함을 이용하여 threshold 기법을 이용하여 잡음제거 시 계산량을 감소를 목적으로 차 신호를 이용하여 측정데이터 수를 줄인 후 영상신호의 가우시안 잡음을 soft threshold 기법을 적용하고 이 기법의 실용성을 밝혔다.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.08a
• /
• pp.281-284
• /
• 2000

이 논문은 웨이브릿 변환 영역의 백색 가우시안 잡음이 부가된 영상에서 최고 대역에서는 Donoho가 제시한 Visushrink 방법으로 잡음을 제거하고 최저대역을 제외한 나머지 대역들은 Monotonic 변환을 이용한 각 대역의 잡음편차를 추정하고 이를 VisuShrink 경계값에 적용하여 Soft-Threshold 기법으로 영상잡음을 제거하는 방법을 제안하였다. 실험 결과 이 논문에서 제시된 혼합방법에 의한 잡음 제거는 Donoho가 제시한 VisuShrink 방법보다 1㏈ 정도의 잡음제거 개선 효과가 있었다.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.08a
• /
• pp.21-24
• /
• 2000

Fractional Brownian motion(fBm)은 long-term persistence 특성을 가진 자연 현상, 1/f 잡음, 깊이가 낮은 해저에서의 배경음향잡음 등을 모델링하는데 많이 사용된다. 이 fBm은 nonstationary 유색잡음이다. 이러한 유색잡음 환경 하에서 신호를 검출하기 위한 한 방법은 Fredholm 적분방정식의 해를 구하는 것이다. 이 방정식을 이산화 하면 잡음의 공분산 행렬의 역행렬이 포함되어 계산량이 많다 본 논문에서는 fBm 잡음의 공분산 행렬을 웨이브렛 변환하여 얻어지는 행렬, 즉 fBm의 멀티스케일 성분들의 공분산행렬은 밴드화된 블록들로 근사화할 수 있다는 성질을 이용하여 적은 계산량으로 신호를 검출하는 알고리즘을 제안한다.

• The Korean Journal of Applied Statistics
• /
• v.24 no.5
• /
• pp.905-914
• /
• 2011

In the field of image processing, the removal noise contamination from the original image is essential. However, due to various reasons, the occurrence of the noise is practically impossible to prevent completely. Thus, the reduction of the noise contained in images remains important. In this study, we estimate the level of noise variance based on the measurement of the relative strength of the noise, and we propose a noise reduction algorithm that uses a sigma filter. As a result, the proposed statistical noise reduction methodology provides significantly improved results over the usual sigma filtering regardless of the level of the noise variance.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.6
• /
• pp.94-99
• /
• 1997

This paper describes a technique of probabilistic spectral subtraction which uses the knowledge of both noise and speech so as to reduce automatic speech recognition errors in noisy environments. Spectral subtraction method estimates a noise prototype in non-speech intervals and the spectrum of clean speech is obtained from the spectrum of noisy speech by subtracting this noise prototype. Thus noise can not be suppressed effectively using a single noise prototype in case the characteristics of the noise prototype are different from those of the noise contained in input noisy speech. To modify such a drawback, multiple noise prototypes are used in probabilistic subtraction method. In this paper, the probabilistic characteristics of noise and the knowledge of speech which is embedded in hidden Markov models trained in clean environments are used to suppress noise. Futhermore, dynamic feature parameters are considered as well as static feature parameters for effective noise suppression. The proposed method reduced error rates in the recognition of 50 Korean words. The recognition rate was 86.25% with the probabilistic subtraction, 72.75% without any noise suppression method and 80.25% with spectral subtraction at SNR(Signal-to-Noise Ratio) 10 dB.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2005.11a
• /
• pp.264-267
• /
• 2005

본 논문에서는 매 프레임 단위로 노이즈를 추정하는 방법을 적용하는 전처리 기법을 이용하여 적응 지각필터의 연산량을 개선하는 알고리즘을 제안한다. 제안된 전처리 잡음 주정 알고리즘은 잡음에 열화 된 대역으로부터 잡음을 추정하여 적응 지각필터에 적용함으로써 연산량 개선과 동시에 오디오 신호의 음질을 개선하는 알고리즘이다. 이는 처리되는 신호 구간에 따라 잡음에 열화 된 대역으로부터 잡음을 추정함으로써 초기 추정 잡음에 보다 가까운 추정 잡음을 얻을 수 있다. 결과적으로 적응 지각필터의 연산량을 효과적으로 줄일 수 있다. 성능 평가를 위하여 지각필터의 적용 결과와 제안한 알고리즘의 적용 결과로 얻어진 개선 신호의 SSNR, NMR의 비교와 적응 지각필터 적용 횟수, 동작 시간 등을 이용하여 성능의 개선을 확인하다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.10a
• /
• pp.379-382
• /
• 2008

In order to reduce the noise quantity in a conversation under the noisy environment, it is necessary for the signal processing system to process adaptively according to the noise quantity in order to enhance the performance. There fore this paper presents a recognition method for noise quantity by linear predictive coefficient using a three layered neural network, which is trained using three kinds of speech that is degraded by various background noises. In the experiment, the average values of the recognition results were 97.6% or more for various noises using Aurora2 database.

• Journal of the Institute of Convergence Signal Processing
• /
• v.20 no.3
• /
• pp.165-170
• /
• 2019

Recently, modern society has come up with the importance of video processing as various imaging systems have developed. However, deterioration occurs in the process of transmitting, processing, and storing video data for various reasons. Deterioration will damage the original image, and the typical noise is Salt and Pepper noise. There are A-TMF, CWMF, and linear interpolation as the means to eliminate Salt and Pepper noise. However, these methods show somewhat poor noise abatement performance in high-density noise areas. Therefore, this paper proposes an algorithm to eliminate noise using modified linear interpolation. To prove the validity of the proposed algorithm, PSNR, Profile was used to compare it with existing methods.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.3
• /
• pp.48-55
• /
• 2001

A novel method to reduce additive non-stationary noise is proposed. The method requires neither the information about noise nor the estimate of the noise statistics from any pause regions. The enhancement is performed on a band-by-band basis for each time frame. Based on both the decision on whether a particular band in a frame is speech or noise dominant and the masking property of the human auditory system, an appropriate amount of noise is reduced using spectral subtraction. The proposed method was tested on various noisy conditions (car noise, Fl6 noise, white Gaussian noise, pink noise, tank noise and babble noise) and on the basis of comparing segmental SNR with spectral subtraction method and visually inspecting the enhanced spectrograms and listening to the enhanced speech, the method was able to effectively reduce various noise while minimizing distortion to speech.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.793-796
• /
• 2017

Image signal can be damaged by a variety of noises during the signal processing, and multiple studies have been conducted to restore these signals. The representative noises to be added in the image are salt and pepper noise, additive white Gaussian noise(AWGN), and the composite noise which two noises are combined. Therefore, the algorithms were proposed to process with quadratic spline interpolation and median filter in case of salt and pepper noise with the central pixel of the local mask, and to process with weight filter by pixel changes in case of AWGN, upon noise determination to restore the damaged image in the composite noise environment, in this article.