改进的contourlet变换域隐马尔可夫树模型

Contourlet域隐马尔科夫树(C_HMT)模型不但可以描述尺度间的相关性,而且可以对方向子带间contourlet系数的相关性做出统计描述,是一种比小波域HMT模型更为有效的系数相关性描述方法.本文提出了一种改进的contourlet变换域HMT模型,节点的状态不只依赖于其父节点的状态,而且兼顾到其父节点相邻节点的状态.这种模型可以进一步捕捉尺度间contourlet变换系数更为丰富的相关性,从而能够更准确和有效的刻画contourlet变换系数的非高斯性和持续性.将该模型应用于图像的去噪,并与另外几种典型的去噪算法作定性比较,验证了本文提出的改进的C_HMT模型在图像去噪性能方面有一定的优越性.     

非高斯双变量模型contourlet图像去噪

Contourlet变换是继小波变换之后的又一新变换.由于contourlet变换的多尺度和多方向特性,能有效地捕获到自然图像中的轮廓,并对其进行稀疏表示.详细分析了图像contourlet系数的统计特性,并利用非高斯双变量分布对系数层间相关性进行建模.最后,将此分布应用于图像去噪,就PSNR、NMSE和视觉质量这三方面的评价指标与contourlet HMT和小波阈值法进行了比较.实验结果表明：算法能获得较好的结果,尤其是对于含有丰富纹理的图像.     

Image watermarking using DNST-PHFMs magnitude domain vector AGGM-HMT

Invisibility, robustness and payload are three indispensable and contradictory properties for any image watermarking systems. Therefore, in this paper a novel statistical image watermark decoder based on robust discrete nonseparable Shearlet transform (DNST)-polar harmonic Fourier moments (PHFMs) magnitude and effective vector anisotropic generalized Gaussian mixtures (AGGM)-hidden Markov tree (HMT). We begin with a detailed study on the robustness and statistical characteristics of local DNST- PHFMs magnitudes of natural images. This study reveals the excellent robustness, highly non-Gaussian marginal statistics and strong dependencies of local DNST-PHFMs magnitudes. We also find that conditioned on their generalized neighborhoods, the local DNST-PHFMs magnitudes can be approximately modeled as anisotropic generalized Gaussian variables. Based on these findings, we model local DNST-PHFMs magnitudes using a vector AGGM-HMT that can capture all interscale, interdirection, and interlocation dependencies. Meanwhile, model parameters can be estimated effectively by using localization clues guided expectation–maximization (LCGEM) approach. Finally, we develop a new statistical image watermark decoder using the vector AGGM-HMT and maximum likelihood (ML) decision rule. Extensive experimental results show the superiority of the proposed watermark decoder over several state-of-the-art statistical watermarking methods and some approaches based on convolutional neural networks.     

Hidden Markov Bayesian texture segmentation using complex wavelet transform

The authors propose a multiscale Bayesian texture segmentation algorithm that is based on a complex wavelet domain hidden Markov tree (HMT) model and a hybrid label tree (HLT) model. The HMT model is used to characterise the statistics of the magnitudes of complex wavelet coefficients. The HLT model is used to fuse the interscale and intrascale context information. In the HLT, the interscale information is fused according to the label transition probability directly resolved by an EM algorithm. The intrascale context information is also fused so as to smooth out the variations in the homogeneous regions. In addition, the statistical model at pixel-level resolution is formulated by a Gaussian mixture model (GMM) in the complex wavelet domain at scale 1, which can improve the accuracy of the pixel-level model. The experimental results on several texture images are used to evaluate the algorithm.     

基于小波域统计建模及显著性修正的SAR图像相干斑抑制

该文提出了一种基于小波域统计建模与小波系数显著性修正相结合的斑点噪声滤波方法。这种方法首先通过对数变换将乘性噪声模型转化为加性噪声模型,对对数变换后的图像进行小波变换并对小波域的高频子带系数用混合高斯模型与隐马尔可夫树模型进行建模,并采用EM算法来估计模型参数。在模型参数估计的基础上;利用贝叶斯最小均方误差准则来估计干净的小波系数。在此基础上引入基于显著性准则的小波系数修正,最后通过小波逆变换与指数变换获得抑制斑点噪声后的图像。用真实SAR图像实验表明,该文提出的方法能够有效地抑制斑点噪声,同时能够很好地保存边缘细节结构与强散射中心。     

基于四元数小波变换域统计模型的图像去噪

图像去噪是图像处理的基本问题,四元数小波变换是1种新的多尺度分析工具.图像经四元数小波变换后,其小波系数不仅在尺度间具有相关性,而且在尺度内也具有一定的相关性.首先利用层内及层间的相关性,用非高斯分布对四元数小波系数进行建模,然后给出分类准则,把小波系数分类为重要系数和不重要系数,再用非高斯分布模型对重要系数与其邻域系...     

Removal of Correlated Noise by Modeling the Signal of Interest in the Wavelet Domain

Images, captured with digital imaging devices, often contain noise. In literature, many algorithms exist for the removal of white uncorrelated noise, but they usually fail when applied to images with correlated noise. In this paper, we design a new denoising method for the removal of correlated noise, by modeling the significance of the noise-free wavelet coefficients in a local window using a new significance measure that defines the “signal of interest” and that is applicable to correlated noise. We combine the intrascale model with a hidden Markov tree model to capture the interscale dependencies between the wavelet coefficients. We propose a denoising method based on the combined model and a less redundant wavelet transform. We present results that show that the new method performs as well as the state-of-the-art wavelet-based methods, while having a lower computational complexity.      

基于贝叶斯估计的多分辨图像滤波方法

图像的小波系数具有很强的非高斯统计特性,可以建立推广的拉普拉斯先验分布,用贝叶斯估计对图像小波系数滤波来达到降噪目的.由于正交小波的正交性质能够保证白噪声干扰图像的小波系数所包含的噪声是白色的,基于正交小波变换的贝叶斯估计有较好的降噪性能.     

Multiscale image segmentation using wavelet-domain hidden Markovmodels

We introduce a new image texture segmentation algorithm, HMTseg, based on wavelets and the hidden Markov tree (HMT) model. The HMT is a tree-structured probabilistic graph that captures the statistical properties of the coefficients of the wavelet transform. Since the HMT is particularly well suited to images containing singularities (edges and ridges), it provides a good classifier for distinguishing between textures. Utilizing the inherent tree structure of the wavelet HMT and its fast training and likelihood computation algorithms, we perform texture classification at a range of different scales. We then fuse these multiscale classifications using a Bayesian probabilistic graph to obtain reliable final segmentations. Since HMTseg works on the wavelet transform of the image, it can directly segment wavelet-compressed images without the need for decompression into the space domain. We demonstrate the performance of HMTseg with synthetic, aerial photo, and document image segmentations.     

Noise reduction for magnetic resonance images via adaptive multiscale products thresholding

Edge-preserving denoising is of great interest in medical image processing. This paper presents a wavelet-based multiscale products thresholding scheme for noise suppression of magnetic resonance images. A Canny edge detector-like dyadic wavelet transform is employed. This results in the significant features in images evolving with high magnitude across wavelet scales, while noise decays rapidly. To exploit the wavelet interscale dependencies we multiply the adjacent wavelet subbands to enhance edge structures while weakening noise. In the multiscale products, edges can be effectively distinguished from noise. Thereafter, an adaptive threshold is calculated and imposed on the products, instead of on the wavelet coefficients, to identify important features. Experiments show that the proposed scheme better suppresses noise and preserves edges than other wavelet-thresholding denoising methods.     

Vonn distribution of relative phase for statistical image modeling in complex wavelet domain

With the assumptions of Gaussian as well as Gaussian scale mixture models for images in wavelet domain, marginal and joint distributions for phases of complex wavelet coefficients are studied in detail. From these hypotheses, we then derive a relative phase probability density function, which is called Vonn distribution, in complex wavelet domain. The maximum-likelihood method is proposed to estimate two Vonn distribution parameters. We demonstrate that the Vonn distribution fits well with behaviors of relative phases from various real images including texture images as well as standard images. The Vonn distribution is compared with other standard circular distributions including von Mises and wrapped Cauchy. The simulation results, in which images are decomposed by various complex wavelet transforms, show that the Vonn distribution is more accurate than other conventional distributions. Moreover, the Vonn model is applied to texture image retrieval application and improves retrieval accuracy.     

A new multiscale Bayesian algorithm for speckle reduction in medical ultrasound images

This paper introduces a new multiscale speckle reduction method based on the extraction of wavelet interscale dependencies to visually enhance the medical ultrasound images and improve clinical diagnosis. The logarithm of the image is first transformed to the oriented dual-tree complex wavelet domain. It is then shown that the adjacent subband coefficients of the log-transformed ultrasound image can be successfully modeled using the general form of bivariate isotropic stable distributions, while the speckle coefficients can be approximated using a zero-mean bivariate Gaussian model. Using these statistical models, we design a new discrete bivariate Bayesian estimator based on minimizing the mean square error (MSE). To assess the performance of the proposed method, four image quality metrics, namely signal-to-noise ratio, MSE, coefficient of correlation, and edge preservation index, were computed on 80 medical ultrasound images. Moreover, a visual evaluation was carried out by two medical experts. The numerical results indicated that the new method outperforms the standard spatial despeckling filters, homomorphic Wiener filter, and new multiscale speckle reduction methods based on generalized Gaussian and symmetric alpha-stable priors.     

Speckle Suppression in SAR Images Using the 2-D GARCH Model

A novel Bayesian-based speckle suppression method for Synthetic Aperture Radar ( SAR) images is presented that preserves the structural features and textural information of the scene. First, the logarithmic transform of the original image is analyzed into the multiscale wavelet domain. We show that the wavelet coefficients of SAR images have significantly non-Gaussian statistics that are best described by the 2-D GARCH model. By using the 2-D GARCH model on the wavelet coefficients, we are capable of taking into account important characteristics of wavelet coefficients, such as heavy tailed marginal distribution and the dependencies between the coefficients. Furthermore, we use a maximum a posteriori (MAP) estimator for estimating the clean image wavelet coefficients. Finally, we compare our proposed method with various speckle suppression methods applied on synthetic and actual SAR images and we verify the performance improvement in utilizing the new strategy.     

一种基于小波-Contourlet变换的图像去噪算法

提出了一种基于小波-Contourlet变换的图像去噪算法.实验证明,该算法相对于小波变换和Contourlet变换能更稀疏的表达图像,并利用此优越性进行图像去噪,可以达到更好的效果和更高的PSNR值.     

一种概率自适应图像去噪模型

从小波变换入手,提出了一种概率自适应去噪模型.该模型包括尺度层间模型和层内模型.去噪方法首先利用小波域层间模型,将小波系数分成两类:有意义系数和无意义系数;然后在层内概率模型下运用最大后验概率估计方法,从有意义系数中恢复出原始系数.我们还将这种模型引入复数小波变换域.实验结果及分析表明了该去噪模型的有效性.     

Image denoising using derotated complex wavelet coefficients

A method for removing additive Gaussian noise from digital images is described. It is based on statistical modeling of the coefficients of a redundant, oriented, complex multiscale transform. Two types of modeling are used to model the wavelet coefficients. Both are based on Gaussian scale mixture (GSM) modeling of neighborhoods of coefficients at adjacent locations and scales. Modeling of edge and ridge discontinuities is performed using wavelet coefficients derotated by twice the phase of the coefficient at the same location and the next coarser scale. Other areas are modeled using standard wavelet coefficients. An adaptive Bayesian model selection framework is used to determine the modeling applied to each neighborhood. The proposed algorithm succeeds in providing improved denoising performance at structural image features, reducing ringing artifacts and enhancing sharpness, while avoiding degradation in other areas. The method outperforms previously published methods visually and in standard tests.     

Image denoising with anisotropic bivariate shrinkage

This paper presents a novel image denoising algorithm based on the modeling of wavelet coefficients with an anisotropic bivariate Laplacian distribution function. The anisotropic bivariate Laplacian model not only captures the child-parent dependency between wavelet coefficients, but also fits the anisotropic property of the variances of wavelet coefficients in different scales of natural images. With this statistical model, we derive a closed-form anisotropic bivariate shrinkage function in the framework of Bayesian denoising and a new image denoising approach with local marginal variance estimation based on this newly derived shrinkage function is proposed in the discrete wavelet transform (DWT) domain. The proposed anisotropic bivariate shrinkage approach is also extended to the dual-tree complex wavelet transform (DT-CWT) domain to further improve the performance of image denoising. To take full advantage of DT-CWT, a more accurate noise variance estimator is proposed and the way the anisotropic bivariate shrinkage function applied to the magnitudes of DT-CWT coefficients is presented. Experiments were carried out in both the DWT and the DT-CWT domain to validate the effectiveness of the proposed method. Using a representative set of standard test images corrupted by additive white Gaussian noise, the simulation results show that the proposed method provides promising results and is competitive with the best wavelet-based denoising results reported in the literature both in terms of peak signal-to-noise ratio (PSNR) and in visual quality.     

Color monogenic wavelet transform for multichannel image denoising

This paper proposes an effective color image denoising algorithm using the combination color monogenic wavelet transform (CMWT) with a trivariate shrinkage filter. The CMWT coefficients are one order of magnitude with three phases: two phases encode the local color information while the third contains geometric information relating to texture within the color image. In the CMWT domain, a trivariate Gaussian distribution is applied to capture statistical dependencies between the CMWT coefficients, and then a trivariate shrinkage filter is derived using a maximum a posteriori estimator. The performance of the proposed algorithm is experimentally verified using a variety of color test images with a range of noise levels in terms of PSNR and visual quality. The experimental results demonstrate that the proposed algorithm is equal to or better than current state-of-the-art algorithms in both visual and quantitative performance.     

Wavelet thresholding of multivalued images

In this paper, a denoising technique for multivalued images exploiting interband correlations is proposed. A redundant wavelet transform is applied and denoising is applied by thresholding wavelet coefficients. Specific functions of the wavelet coefficients are defined that exploit interscale and/or interband correlation of the signal. Three functions are studied: the square of the wavelet coefficients, products of coefficients at adjacent scales, and products of coefficients from different bands. For these functions, the signal and noise probability density functions (pdf) become more separated. The high signal correlation between bands is exploited by summing these products over all bands, in this way separating noise and signal pdfs even more. The noise pdf of the proposed quantities is derived analytically and from this, a wavelet threshold is derived. The technique is demonstrated to outperform single band wavelet thresholding on multispectral remote sensing images and on multimodal MRI images.     

Wavelet-based statistical signal processing using hidden Markovmodels

Wavelet-based statistical signal processing techniques such as denoising and detection typically model the wavelet coefficients as independent or jointly Gaussian. These models are unrealistic for many real-world signals. We develop a new framework for statistical signal processing based on wavelet-domain hidden Markov models (HMMs) that concisely models the statistical dependencies and non-Gaussian statistics encountered in real-world signals. Wavelet-domain HMMs are designed with the intrinsic properties of the wavelet transform in mind and provide powerful, yet tractable, probabilistic signal models. Efficient expectation maximization algorithms are developed for fitting the HMMs to observational signal data. The new framework is suitable for a wide range of applications, including signal estimation, detection, classification, prediction, and even synthesis. To demonstrate the utility of wavelet-domain HMMs, we develop novel algorithms for signal denoising, classification, and detection