• The Journal of the Acoustical Society of Korea
• /
• v.19 no.6
• /
• pp.53-61
• /
• 2000

In the speech recognition under the noisy environments, reducing the mismatch introduced between training and testing environments is an important issue. Spectral subtraction is widely used technique because of its simplicity and relatively good performance in noisy environments. In this paper, we introduce histogram method as a reliable noise estimation approach for spectral subtraction. This method has advantages over the conventional noise estimation methods in that it does not need to detect non-speech intervals and it can estimate the noise spectra even in time-varying noise environments. Even though spectral subtraction is performed using a reliable average noise spectrum by the histogram method, considerable amount of residual noise remains due to the variations of instantaneous noise spectrum about mean. To overcome this limitation, we propose a new over-estimation technique based on distribution characteristics of histogram used for noise estimation. Since the proposed technique decides the degree of over-estimation adaptively according to the measured noise distribution, it has advantages to be few the influence of the SNR variation on the noise levels. According to speaker-independent isolated word recognition experiments in car noise environment under various SNR conditions, the proposed histogram-based over-estimation technique outperforms the conventional over-estimation technique.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.5
• /
• pp.281-286
• /
• 2013

In this paper, we propose a noise estimation method using edge detection. It is a filter-based noise estimation method. Edge detection is to exclude structures and details which have an effect on the noise estimation. To detect edge, we use a modified rational filter which is robust to details of images. The proposed noise estimation method is more efficiently applied to noise estimation in various types of images and has better results than those of conventional filter-based noise estimation methods.

• Structural Engineering and Mechanics
• /
• v.47 no.3
• /
• pp.361-381
• /
• 2013

A Bayesian probabilistic method is proposed for online estimation of the process noise and measurement noise parameters for Kalman filter. Kalman filter is a well-known recursive algorithm for state estimation of dynamical systems. In this algorithm, it is required to prescribe the covariance matrices of the process noise and measurement noise. However, inappropriate choice of these covariance matrices substantially deteriorates the performance of the Kalman filter. In this paper, a probabilistic method is proposed for online estimation of the noise parameters which govern the noise covariance matrices. The proposed Bayesian method not only estimates the optimal noise parameters but also quantifies the associated estimation uncertainty in an online manner. By utilizing the estimated noise parameters, reliable state estimation can be accomplished. Moreover, the proposed method does not assume any stationarity condition of the process noise and/or measurement noise. By removing the stationarity constraint, the proposed method enhances the applicability of the state estimation algorithm for nonstationary circumstances generally encountered in practice. To illustrate the efficacy and efficiency of the proposed method, examples using a fifty-story building with different stationarity scenarios of the process noise and measurement noise are presented.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.8 no.4
• /
• pp.13-18
• /
• 2012

In this paper, we propose a noise estimation method for noise reduction. It is based on block and pixel-based noise estimation. We assume that an input image is contaminated by the additive white Gaussian noise. Thus, we use an adaptive Gaussian filter and estimate the amount of noise. It computes the standard deviation of each block and estimation is performed on pixel-based operation. The proposed algorithm divides an input image into blocks. This method calculates the standard deviation of each block and finds the minimum standard deviation block. The block in flat region shows well noise and filtering effects. Blocks which have similar standard deviation are selected as test blocks. These pixels are filtered by adaptive Gaussian filtering. Then, the amount of noise is calculated by the standard deviation of the differences between noisy and filtered blocks. Experimental results show that our proposed estimation method has better results than those by existing estimation methods.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2003.05a
• /
• pp.202-207
• /
• 2003

The purpose of this study was to investigate the effect of background noise on loudness magnitude estimation of Heavy-weight impact noise. Relationship between loudness magnitude estimation and estimation methods about floor impact noise had appeared low in apartment which receive much effect of background noise. Then, to need new estimation method abut effect of background noise. Masking effects by background noise is increased steadily, there is a continuous transition between an audible impact noise and one that is totally masked. Result 1 hat analyze interrelationship of phychoacoustical data and values through Zwicker Parameters, to Investigate that an estimation experiment about Annoyance need.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.1
• /
• pp.381-394
• /
• 2016

The several noise level estimation algorithms that have been developed for use in image processing and computer graphics generally exhibit good performance. However, there are certain special types of noisy images that such algorithms are not suitable for. It is particularly still a challenge to use the algorithms to estimate the noise levels of complex textured photographic images because of the inhomogeneity of the original scenes. Similarly, it is difficult to apply most conventional noise level estimation algorithms to images rendered by the Monte Carlo (MC) method owing to the spatial variation of the noise in such images. This paper proposes a novel noise level estimation method based on histogram modification, and which can be used for more accurate estimation of the noise levels in both complex textured images and MC-rendered images. The proposed method has good performance, is simple to implement, and can be efficiently used in various image-based and graphic applications ranging from smartphone camera noise removal to game background rendition.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.574-576
• /
• 2004

Since variance of noise is important parameter for a noise filter to reduce noise in image and the performance of noise filter is dependent on estimated variance. In this paper, we apply additive noise variance estimation method to estimate variance of speckle noise of synthetic aperture radar (SAR) imagery. Generally, speckle noise is in multiplicative model, logarithmic transformation is then used to transform multiplicative model into additive model. Here, speckle noise is generally modeled as Gamma distribution function with different looks. The additive noise variance estimation is processed in log domain. The synthesis image and real image of SAR are implemented to test and confirm results and show that more accurate estimation can be achieved.

• Journal of Communications and Networks
• /
• v.14 no.3
• /
• pp.237-242
• /
• 2012

One of the major problems for accurate channel estimation in power line communication systems is impulsive noise. Traditional channel estimation algorithms are based on the assumption of Gaussian noise, or the need to locate the positions of impulsive noise. The algorithms may lose optimality when impulsive noise exists in the channel, or if the location estimation of impulsive noise is inaccurate. In the present paper, an effective channel estimation algorithm based on a robust cost function is proposed to mitigate impulsive noise. The proposed method can provide a closed-form solution, and the application of robust estimation theory enables the proposed method to be free from localization of impulsive noise and thus can guarantee that the proposed method has better performance. Simulations verified the proposed algorithm.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.4
• /
• pp.207-212
• /
• 2015

We propose a noise estimation method using edge detection in moving pictures. Edge detection is to exclude structures and details which have an effect on the noise estimation. To detect edge, we use Sobel and morphological closing operators which are robust to details of images. The proposed noise estimation method is more efficiently applied to noise estimation in various types of moving images and has better results than those of existing noise estimation methods. Also, proposed algorithm can be efficiently applied to image and video applications.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.7
• /
• pp.178-187
• /
• 1999

In order to identify a transfer function model with noise, penalty function method has been widely used. In this method, estimation process for possible model parameters from low to higher order proceeds the model identification process. In this study, based on linear estimation method, a new approach unifying the estimation and the identification of ARMAX model is proposed. For the parameter estimation of a transfer function model with noise, linear estimation method by noise separation is suggested instead of nonlinear estimation method. The feasibility of the proposed model identification and estimation method is verified through simulations, namely by applying the method to time series model. In the case of time series model with noise, the proposed method successfully identifies the transfer function model with noise without going through model parameter identification process in advance. A new algorithm effectively achieving model identification and parameter estimation in unified frame has been proposed. This approach is different from the conventional method used for identification of ARMAX model which needs separate parameter estimation and model identification processes. The consistency and the accuracy of the proposed method has been verified through simulations.