Image denoising review: From classical to state-of-the-art approaches

Optimal bilateral filter and Convolutional Neural Network based denoising method of medical image measurements

Least squares support vector machine (LS-SVM)-based chiller fault diagnosis using fault indicative features

This paper proposes a statistically optimum adaptive wavelet packet (WP) thresholding function for image denoising based on the generalized Gaussian distribution. It applies computationally efficient multilevel WP decomposition to noisy images to obtain the best tree or optimal wavelet basis, utilizing Shannon entropy. It selects an adaptive threshold value which is level and subband dependent based on analyzing the statistical parameters of subband coefficients. In the utilized thresholding function, which is based on a maximum a posteriori estimate, the modified version of dominant coefficients was estimated by optimal linear interpolation between each coefficient and the mean value of the corresponding subband. Experimental results, on several test images under different noise intensity conditions, show that the proposed algorithm, called OLI-Shrink, yields better peak signal noise ratio and superior visual image quality—measured by universal image quality index—compared to standard denoising methods, especially in the presence of high noise intensity. It also outperforms some of the best state-of-the-art wavelet-based denoising techniques.

Efficient Image Denoising Method Based on a New Adaptive Wavelet Packet Thresholding Function

Landslides are recognized as one of the most important natural hazards in many areas throughout the world. Producing landslide susceptibility maps have received particular attention from a wide range of scientists. The main objective of this study was to produce landslide susceptibility maps using hybrid wavelet packet-statistical models (WP-SM). In the first step, landslide susceptibility maps were produced using single artificial neural network (ANN), support vector machine (SVM), maximum entropy (MaxEnt), and generalized linear model (GLM). In the next step, the input maps were preprocessed using different mother wavelets in different levels. Then, the hybrid models were developed using the wavelet-based preprocessed maps. Results showed that the wavelet packet transform can be effectively used to produce precise landslide susceptibility maps. It was shown that wavelet packet transform significantly enhanced the ability of the single statistical models. The kappa coefficients were increased from 0.829 to 0.941, 0.846 to 0.978, 0.744 to 0.829, and 0.735 to 0.817 in hybrid ANN, SVM, MaxEnt, and GLM, respectively. The best wavelet transform was performed using bior1.5 with a three-level decomposition. It was also recognized that MaxEnt and GLM produced approximately poor results. However, SVM performed better than the other three models both in single and hybrid forms. ANN also outperformed MaxEnt and GLM models. Spatial distribution of the susceptible area is consistent with the observed landslide distribution pattern particularly in maps obtained from the hybrid models. The produced maps showed that the general pattern of susceptible area intensively followed the pattern of roads and sensitive geological formations.

Development of hybrid wavelet packet-statistical models (WP-SM) for landslide susceptibility mapping

Image denoising is an important image processing task, both as itself, and as a preprocessing in image processing pipeline. The least squares support vector machine (LS-SVM) has shown to exhibit excellent classification performance in many applications. Based on undecimated discrete wavelet transform, a new wavelet-based image denoising using LS-SVM is proposed in this paper. Firstly, the noisy image is decomposed into different subbands of frequency and orientation responses using the undecimated discrete wavelet transform. Secondly, the feature vector for a pixel in a noisy image is formed by the spatial regularity in wavelet domain, and the LS-SVM model is obtained by training. Then the wavelet coefficients are divided into two classes (noisy coefficients and noise-free ones) by LS-SVM training model. Finally, all noisy wavelet coefficients are relatively well denoised by shrink method, in which the adaptive threshold is utilized. Extensive experimental results demonstrate that our method can obtain better performances in terms of both subjective and objective evaluations than those state-of-the-art denoising techniques. Especially, the proposed method can preserve edges very well while removing noise.

A New Wavelet-based image denoising using undecimated discrete wavelet transform and least squares support vector machine

Image denoising using SVM classification in nonsubsampled contourlet transform domain

Image denoising using bilateral filter and Gaussian scale mixtures in shiftable complex directional pyramid domain

Edge structure preserving image denoising using OAGSM/NC statistical model

Edge-preserving image denoising has become a very intensive research topic. In this paper, we propose a new image denoising scheme using support vector machine (SVM) classification in shiftable complex directional pyramid (PDTDFB) domain. Firstly, the noisy image is decomposed into different subbands of frequency and orientation responses using a PDTDFB transform. Secondly, the feature vector for a pixel in a noisy image is formed by the spatial regularity in PDTDFB domain, and the least squares support vector machine (LS-SVM) model is obtained by training. Then the PDTDFB detail coefficients are divided into two classes (edge-related coefficients and noise-related ones) by LS-SVM training model. Finally, the detail subbands of PDTDFB coefficients are denoised by using the different parameters to control the multiscale and multidirectional anisotropic diffusion. Extensive experimental results demonstrate that our method can obtain better performances in terms of both subjective and objective evaluations than those state-of-the-art denoising techniques. Especially, the proposed method can preserve edges very well while removing noise.

Zhong-Kai Fu

Papers

A New Wavelet-based image denoising using undecimated discrete wavelet transform and least squares support vector machine

Image denoising using SVM classification in nonsubsampled contourlet transform domain

Image denoising using bilateral filter and Gaussian scale mixtures in shiftable complex directional pyramid domain

Edge structure preserving image denoising using OAGSM/NC statistical model

A new image denoising scheme using support vector machine classification in shiftable complex directional pyramid domain