Research Article  Open Access
Optical Coherence Tomography Noise Reduction Using Anisotropic Local Bivariate Gaussian Mixture Prior in 3D Complex Wavelet Domain
Abstract
In this paper, MMSE estimator is employed for noisefree 3D OCT data recovery in 3D complex wavelet domain. Since the proposed distribution for noisefree data plays a key role in the performance of MMSE estimator, a priori distribution for the pdf of noisefree 3D complex wavelet coefficients is proposed which is able to model the main statistical properties of wavelets. We model the coefficients with a mixture of two bivariate Gaussian pdfs with local parameters which are able to capture the heavytailed property and inter and intrascale dependencies of coefficients. In addition, based on the special structure of OCT images, we use an anisotropic windowing procedure for local parameters estimation that results in visual quality improvement. On this base, several OCT despeckling algorithms are obtained based on using Gaussian/twosided Rayleigh noise distribution and homomorphic/nonhomomorphic model. In order to evaluate the performance of the proposed algorithm, we use 156 selected ROIs from 650 × 512 × 128 OCT dataset in the presence of wet AMD pathology. Our simulations show that the best MMSE estimator using local bivariate mixture prior is for the nonhomomorphic model in the presence of Gaussian noise which results in an improvement of 7.8 ± 1.7 in CNR.
1. Introduction
Optical coherence tomography (OCT) is an optical signal acquisition and processing method that captures 3D images from within optical scattering media such as biological tissues [1–4]. For example, in ophthalmology, OCT is used to obtain detailed images from within the retina [4]. Similar to other optical tomographic techniques, OCT suffers from speckle noise that reduces the ability of image interpretation [5]. So, noise reduction is an essential part of OCT image processing systems. Until now, several techniques for OCT noise reduction have been reported [6–14]. Initial methods perform in complex domain [15], that is, before producing magnitude of OCT interference signal, while most introduced despeckling methods are applied after an OCT image is formed [6–14]. These methods, which usually suppose multiplicative noise for speckled data, also can be categorized into image domain and transform domain methods. As an example for image domain techniques, in [16] the rotating kernel transform (RKT) filters are applied on an image with a set of oriented kernels and keep the largest filter output for each pixel. Other image domain methods based on enhanced Lee filter [17], median filter [17], symmetric nearest neighbor filter [17], and adaptive Wiener filter [17], and Idivergence regularization [6] and PDEbased nonlinear diffusion methods [14] have been reported in the literature.
Transform domain techniques typically outperform the image domain techniques because incorporating speckle statistics in the despeckling process would be facilitated in sparse domains. Such techniques apply a sparse transform (such as wavelet and curvelet transforms) [7–12, 18] directly on data (viz., nonhomomorphic methods) or on logtransformed data (viz., homomorphic methods), and suppose that in the sparse domain noise is converted to additive white Gaussian noise (AWGN) [13] or other models which can be removed using an appropriate shrinkage function. For example, in [18], a spatially adaptive wavelet thresholding method is used for speckle suppression in logtransformed domain. Since actual signal in OCT images consists of horizontal edges arising from reflections at the layer boundaries, most of the edge information is in “lowpass”“highpass” (LH) subbands (and some of it in HH subbands). Therefore, an increased threshold in the vertical subbands using a constant multiplier () is chosen to decrease further noise with a minimal effect on the edge sharpness. Other transform domain methods based on hard thresholding in 3D curvelet domain [8], soft thresholding in discrete complex wavelet transform (DCWT) domain [9], and temporal and spatial waveletbased filtering [10] have been reported in other literatures.
In fact denoising is the problem of obtaining the noisefree data from noisy data observation, which may be solved in a deterministic or probabilistic framework. In the first case, each voxel is considered as an unknown deterministic variable, and nonBayesian techniques are employed to solve this problem. In the second case, the data is modeled as a random field, and Bayesian methods are used for the estimation of clean data from the noisy environment. Therefore, the proposed prior probability distributions for noisefree data and noise (i.e., proposed as speckle for OCT data) play a key role in the noise reduction problem.
1.1. Statistical Properties of NoiseFree Coefficients
Description of the statistical properties of natural signals can be facilitated in the wavelet domain [19] due to sparseness and decorrelation properties of wavelets [20]. The sparseness property states that the marginal pdf of wavelet coefficients in each subband has a large peak at zero and its tails fall to zero slower than the Gaussian pdf (leptokurtic). On this base, some longtailed pdfs such as generalized Gaussian distribution (GGD) [21, 22], stable distributions [23], Bessel K form densities [24, 25], and mixture pdfs [26–31] have been proposed. Although the decorrelation property of wavelets states that coefficients at the same positions in the adjacent scales are uncorrelated, it does not mean that they are independent. The interscale dependency of wavelet states that large/small values of wavelet coefficients tend to propagate across scales [32]. Some researchers have proposed hidden Markov models (HMMs) [33] and Markov random fields (MRFs) [34] to model the interscale dependency [35]. Recently, it has been shown that some nonGaussian bivariate joint pdfs for each coefficient and its parent, such as circular symmetric Laplacian pdf [36], bivariate Cauchy distribution [37], (multivariate) Gaussian scale mixture (GSM) model [27, 38, 39], and bivariate Laplacian mixture models [40] are able to capture this property easily and produce better denoising results with lower computational complexity.
The dependencies between wavelet coefficients are not restricted to the interscale dependency. There is another dependency between spatial adjacent coefficients in each subband, namely, intrascale dependency [42]. This dependency states that if a particular wavelet coefficient is large/small, then the spatial adjacent coefficients are likely to be large/small too. Usually this property is captured using local parameters for pdfs [37], and it has been shown that denoising algorithms using this property for statistical modeling of wavelets are able to improve the denoising results [43–45]. For example, Mihçak [43] employs local variance for Gaussian pdf to model intrascale dependency. In [44], a mixture of two Laplace pdf with local parameters is proposed for simultaneously capturing heavytailed nature and intrascale dependency. Reference [45], using local variance for proposed model in [36], improves the results for noise reduction application because this local pdf models both interscale and intrascale dependencies. In this paper, we extend the proposed pdf in [46] based on a mixture of bivariate Gaussian pdfs with local parameters for noisefree wavelet coefficients. Since the empirically observed distribution of wavelet coefficient pairs in adjacent scales have elliptical symmetry, we use different variances for marginal pdfs that lead to an elliptical symmetric bivariate pdf instead of circular symmetric pdf. Recently, it has been shown that using anisotropic window instead of square window can improve the denoising results [47]. Based on the special structure of OCT data, we choose an anisotropic windowing procedure for local parameters estimation that results in visual quality improvement.
1.2. Discrete Complex Wavelet Transform (DCWT)
The wavelet based image denoising consists of the following steps.(1)Signal transformation of the noisy observation.(2)Modification of the noisy wavelet coefficients based on some criteria.(3)Inverse signal transformation of modified coefficients.
As explained earlier, the second step depends on the type of estimator and for a minimum mean square error (MMSE) estimator, the proposed model for signal and noise (which we propose as a multiplicative model), the proposed pdf of noisefree wavelet coefficients (modeled, in this paper, as a mixture of bivariate Gaussian pdfs with local parameters), and the proposed pdf for noise (with which we test both Gaussian and twosided Rayleigh distributions) define the performance of the algorithm. However, for the first and last steps of waveletbased denoising algorithm, the type of transformation plays a key role. In this paper, we use DCWT [48] instead of ordinary discrete wavelet transform (DWT). Despite DWT being a sparse representation that outperforms many signal processing approaches, it does not lead to an optimum performance in all applications and suffers from several fundamental shortcomings (especially in highdimensional cases), which DCWT avoids them. These shortcomings are as follows. (1)In the neighborhood of an edge, the DWT produces both large and small wavelet coefficients. In contrast, the magnitudes of DCWT coefficients are more directly related to their adjacency to the edge. The main reason of this phenomenon is using bandpass filters that produce DWT coefficients which oscillate positively and negatively around the singularities, and this subject complicates waveletbased processing.(2)DWT is not shift invariant. It means that a small shift in the input signal of DWT makes the total energy of wavelet coefficients in subband completely differ. This shift greatly perturbs oscillation pattern around singularities of the DWT coefficient which complicates waveletdomain processing. (3)Since the DWT coefficients in each subband are produced via critical sampling after using nonideal lowpass and highpass filters, substantial aliasing would be produced. If the wavelet coefficients are not changed, the inverse DWT cancels this aliasing. Applying any processing method on wavelet coefficients (such as thresholding) disarranges this balance between the forward and inverse transforms which leads to artifacts in the reconstructed signal.(4)The directional selectivity of 2D DCWT has been explained in Appendix A. Similar to the 2D case, the standard 3D data transforms, which are separable multiplication of 1D tensors, do not provide useful representations with good energy compaction property for 3D data. For example, the multidimensional standard separable DWT mixes orientations and motions in its subbands and produces the checkerboard artifacts (Figure 1). In contrast, since the spectrum of the (approximately) analytic 1D wavelet is supported on only one side of the frequency axis, the spectrum of the DCWT in 3D domain is supported in only 1/27 of the 3D frequency plane. So, instead of 3D DWT, usually oriented transforms such as 3D DCWT are proposed for 3D data processing [41, 48–52]. Figure 1 shows a comparison between subbands of 3D DWT and 3D DCWT.
(a)
(b)
1.3. Organization of the Paper
In Section 2, we explain our proposed pdf for noisefree 3D DCWT coefficients, that is, a mixture of bivariate Gaussian distributions with local parameters. In Section 3, at first we obtain a local thresholding function supposing a priori distribution as a bivariate Gaussian pdf with local variance, and then in a Bayesian framework we produce our new shrinkage functions derived from the proposed pdf and using Gaussian/twosided Rayleigh noise distribution and homomorphic/nonhomomorphic model. In Section 4, we explain the proposed anisotropic window selection procedure for local parameter estimation based on special structure of OCT data. In Section 5, we use our model for waveletbased denoising of several 3D OCT data. We compare our methods visually and in terms of PSNR. Also in this section, we use the proposed method for nonspeckle noise reduction. Finally, in Section 6, we summarize this paper and suggest some future work.
2. Bivariate Gaussian Mixture Model with Local Parameters
One of the primary properties of the wavelet transform is compression. This property means that the marginal distributions of wavelet coefficients are highly kurtotic, and so longtailed distributions are suitable models for marginal pdf. A zeromean mixture model could have a large peak at zero and would be long tailed. For example, in [22, 26, 29, 31] a mixture of Gaussian distributions is proposed to model the heavytailed nature of wavelet coefficients. Figure 2 shows this model that consists of two zeromean Gaussian distributions with two different variances. The Gaussian pdf with low variance can model the large peak at zero and the Gaussian pdf with high variance can model tails of distribution. The secondary properties of the wavelet transform are clustering and persistence. The clustering property, that is called intrascale dependency, states that if a particular wavelet coefficient is large/small, then adjacent coefficients are very likely to also be large/small [36], and usually local pdfs are able to model this property. The persistence property, that is called the interscale dependency, states that large/small values of wavelet coefficients tend to propagate across scales [36]. As an example, Figure 3 illustrates the empirical joint parentchild histogram of wavelet coefficients computed from the 200, images from the Corel image database [42]. Usually this property can be modeled using proper bivariate pdfs.
2.1. Description of the Proposed Model
In this paper, we assume a pdf as a mixture of two bivariate Gaussian pdfs with local parameters in order to model the distribution of wavelet coefficients of images as follows: where ,,,, are the mixture model parameters. For each random bivariable, the second component is the parent of the first component; for example, represent, the parent of at the same spatial position as the th wavelet coefficient and at the next coarser scale.
Our proposed model in this paper, that is a mixture of bivariate Gaussian pdfs with local parameters, is mixture, bivariate and local. Therefore, it is able to simultaneously capture the heavytailed property and inter and intrascale dependencies.
After substitution of mixture model in the definition of , we can see that this pdf represents two uncorrelated random variables as follows:
Interestingly, the marginal pdf of for , is the mixture of two univariate Gaussian pdf with local parameters [44],
It is easy to see that , are not independent; that is,
See Appendix B for more explanation.
2.2. Local EM Algorithm
To characterize the parameters in (1), it is necessary to have the parameters ,, , , and . For this mixture model, we use an iterative numerical algorithm to estimate these parameters. The expectation maximization (EM) algorithm is most frequently used to estimate such parameters. Usually, the EM algorithm for mixture models employs all data in each subband to obtain the parameters. Using this global EM algorithm, equal parameters are obtained for all data in each subband. However, to model the intrascale dependency, we must incorporate the local statistics and need to have different parameters for each voxel in each subband. So, we introduce a local version of EM algorithm. This local EM algorithm is able to obtain separate parameters for each voxel by the implementation of EM algorithm in each window centered at . This iterative algorithm has two steps. Assuming that the observed data for , the step calculates the responsibility factors for each data as follows:
The step updates the parameters ,,,,and. is computed by where is the number of coefficients in the square window centered at .
The variances ,,,and are computed by [40]:
3. Denoising Using MMSE Estimator
In this section, the denoising of a 3D OCT data is considered. We assume that dominant noise in OCT data is speckle. In this case as a common model, we propose multiplicative model as follows: where is the index of voxel and is between 1 and number of voxels.
As explained in Introduction, reported transformbased OCT noise reduction methods in the literatures [7–12, 18] usually at first transform data into log domain, and suppose that noise in log domain is AWGN: where in this paper shows 3D DCWT operator. So, we can write where , , and are, respectively, the th noisefree 3D DCWT coefficients, noisy 3D DCWT coefficients, and noise in the 3D DCWT domain.
Recently, it has been reported [56–59] that nonhomomorphic techniques that do not use this nonlinear operation and apply wavelet transform directly on speckled data lead to unbiased estimation of the data and decrease the computational complexity. On this base after applying 3D DCWT (directly) on data, we would have
Again we can write where , , and are, respectively, the th noisefree 3D DCWT coefficients, noisy 3D DCWT coefficients, and noise in the 3D DCWT domain. Since speckle noise can be modeled as a unitmean random process independent of the noisefree data, we would have , and also it can be easily shown [58] that which means that and are zeromean uncorrelated random variables. If , , and show the parent coefficients of , , and , respectively, we can write
Based on the persistence property, we need to have a bivariate model based on parentchild pairs. So, we can propose the following bivariate model: where , , and are, respectively, the th parentchild pairs of noisefree 3D DCWT coefficients, noisy 3D DCWT coefficients, and additive noise in the 3D DCWT domain. In the literature, several models such as distribution, Rayleigh, Weibull, lognormal, and Nakagami distributions have been proposed [57, 58, 60–63] for speckle in image domain. In this paper, we test both AWGN and twosided Rayleigh model for noise in wavelet domain as follows: where shows the noise variance.
Now our goal is the estimation of from , where is a Gaussian or twosided Rayleigh according to some criteria.
If we employ the MMSE estimator for the estimation problem, we get the posterior mean as an optimal solution:
3.1. Denoising Based on Modeling NoiseFree Data by Bivariate Gaussian PDF with Local Variance
In order to solve (17), we must know the prior distribution of 3D DCWT coefficients, that is, . Defining , if we suppose that , are independent Gaussian pdf with variances and , the following bivariate Gaussian pdf with local variances can be proposed for the noisefree wavelet coefficients:
In this case, and are uncorrelated and independent, and therefore the MMSE estimator of , yields the shrinkage function corresponding to univariate Gaussian pdf, that is, Wiener filter [21] as follows:
And so we can write
Similarly, if we choose twosided Rayleigh pdf for noise distribution, the following estimator is obtained [44]: where
And so we can write
Suppose that the input noise variance is known. To implement (20) or (23), we must know the parameter of the prior (suppose that ). Mihçak et al. [43] showed that using local variance (instead of global variance) for Wiener filter leads to a substantial improvement in denoising results (using local variance allows incorporating the local statistics of image into the proposed prior). It has been shown in the literature that the correctness of estimation of variance is an impact factor for denoising [23, 27, 34, 42–46]. Thus, the proposed criteria for estimation of the variance, such as the involved data for estimation (e.g., in some approaches the coarser scales are used as a source of prior), the type of estimator, and the shape and size of the proposed window for the local estimation of the variance, play key roles in the performance of denoising procedure. For example, in [54] a recurrence equation using a local Gaussian pdf is used for estimation of or in [64] the variable size of the locally adaptive window is obtained using a regionbased approach. However, for each data point , a simple estimation of can be formed based on a local neighborhood . In simplest case, we can use a square window centered at and suppose that in this window the variance is approximately constant. Then, an empirical estimate for can be obtained as follows: where is the number of coefficients in and can be estimated by [4] = median{noisy wavelet coefficients in finest scale}/0.6745. In this estimation, we propose the coarser scale as a source of prior, but another estimate can be obtained using only spatial adjacent in the same scale. It has been shown [47] that the local features in the edges of images are not isotropic and so can be better modeled in a shapeadaptive window selection manner. We explain in this regard in Section 4 and try to improve the denoising results by using anisotropic window instead of square window for the estimation of local parameters (such as variance in (24)).
3.2. Denoising Based on Modeling NoiseFree Data by a Mixture of Bivariate Gaussian PDFs with Local Parameters
A nonlinear shrinkage function for waveletbased denoising, which is derived by assuming that the noisefree wavelet coefficients follow a bivariate Gaussian mixture model with local parameters given by (1), is introduced in this section. Substituting (1) in (17), we can write where
In fact, is the 2D convolution of the pdf of (defined in (15) or (16)) and (defined in (1)). Using (15) as proposed model for noise, both and are bivariate Gaussian pdfs. So, we obtain
For twosided Rayleigh noise (16), more computations are needed. After some simplifications, the final formula would be where
Using (19), we can obtain numerators of (25), and finally (25) for AWGN can be written as where
We call the new obtained bivariate local shrinkage function as BiGaussMixShrinkL. Figure 4 shows this shrinkage function with sample constant parameters.
Similarly, using (21), we can obtain numerators of (25), and finally (25) for twosided Rayleigh noise is obtained as where
We call this bivariate local shrinkage function as BiGaussRayMixShrinkL. Figure 5 shows this shrinkage function with sample constant parameters.
For implementation of our denoising algorithm, we must estimate the parameters for , and (that are for noisefree data) from noisy observation. For AWGN, the noisy observation would be a Gaussian mixture model with parameters , for . So, the following local EM algorithm is used to obtain the parameters.
Estep
Mstep where is the number of coefficients in the window centered at . As discussed in the literatures [40], for nonGaussian mixture models, which is a case for twosided Rayleigh noise, using (34)–(36) finally converge to the final results.
Our denoising algorithm is summarized in Algorithm 1.

4. Shape Adaptive Windows Selection
It has been shown that using anisotropic and shape adaptive window for local parameter estimation can extremely improve the modeling and processing results. For example, in [47] a new image denoising is introduced that proposes an anisotropic window around each pixel of image and obtains the denoised pixel just by using the located data in the window. Comparing with the denoising methods that are based on proposing isotropic window around each pixel (e.g., [23, 27, 34, 42–46]), the proposed method in [47] is able to segment the image to rather smoothed regions before denoising due to anisotropic window selection that leads to improvement of denoising results. As explained before, the mixture model parameters in each subbands are estimated locally using an isotropic window around each voxel. In this section at first we explain the structure of macular OCT then we introduce 3D “linear polynomial approximationintersection confidence interval” (LPAICI) method for applying shape adaptive window selection around each voxel in 3D DCWT domain. So we will try the despeckling results in 3D DCWT domain by choosing an anisotropic window (instead of isotropic) for estimating the parameters of mixture model in each subband locally.
4.1. OCT Structure
To select the shapeadaptive window, we must take a look at the special structure of OCT data. In ophthalmology, the OCT data shows detailed images from within the retina. The automated analysis of OCT images can be used for the imageguided retinal therapy. Every year, many people become blind as a result of agerelated macular degeneration (AMD) due to affecting the central retina where our central vision is perceived. The most sightthreatening form of AMD is called exudative or wet AMD. Choroidal neovascularization (CNV) is a common symptom of the degenerative maculopathy wet AMD. A wealth of powerful new treatments for CNV, especially antiVEGF agents, have become available very recently to restore normal visual function. The risk of ocular adverse events, including the devastating intraocular infection, endophthalmitis, increases with repeated intravitreal treatment injections, and the effects of chronic treatment with antiVEGF agents on the retina are unknown. Ideally a more costeffective, patientspecific dosing strategy with the minimally necessary number of antiVEGF injections is required. With all the promise, these novel treatments will only reach their full potential when objective and early indices of treatment response are developed. Prior to the introduction of retinal OCT imaging, clinical assessment of whether the preservation or restoration of visual function is successful, which indeed is the ultimate goal of treatment, could only be obtained by measuring visual function. Unfortunately, visual function lags structural response and is cumbersome and noisy, and its reproducibility is limited. Twodimensional OCT imaging of the retina was introduced several years ago, and was rapidly adopted, among others, to qualitatively measure macular structure as an indicator of AMD treatment response and for guidance of retreatment in CNV recurrence. It is now becoming clear that these simplified structural measures though leading indicators of visual function are inadequate, as they are based on simplified interpretation of single transverse slices of the macula, some patients do not recover visual function even though their total macular thickness has become normally thin after treatment, and others paradoxically gain visual acuity while their macula is still thickened.
True 3D spectral OCT imaging, that became available in 2007 is fast (1.5 s per volume scan), allows full 3D retinal coverage at a much higher resolution and offers improved imaging of subtle differences in retinal structure. In the recent years [65, 66], 3D analysis of 3D OCT as an improved measure of subtle macular structure has been proposed motivated by various hypotheses as follows: A model of retinal response to initial antiVEGF treatment for CNV, based on quantitative 3D OCTderived measures, can predict the timing of retreatment.
On this base, developing analysis methods and approaches for 3D spectral OCT image analysis in the presence of wet AMD pathology (Symptomatic Exudate Associated Derangements or SEADs, also known as AMDrelated cysts, vessel leakages, etc.) and assessing their performance by comparison to expert analyses are of utmost interest. Another interesting subject is determining how well the quantitative SEAD and layerderived measures from 3D OCT predict the patientspecific outcome parameters in response to postinduction antiVEGF treatment in patients with CNV in order to predict the timing of retreatment.
Figure 6 shows several sample macular OCTs and detected SEADs by an expert as the region of interest (ROI). As we can see in this figure, the most important information of OCT data (about retina layers) is located in the center of OCT images.
4.2. 3D LPAICI for Data between the First and Last Layers
In [47], a new image denoising based on using an anisotropic window around each pixel of image is introduced. To select the anisotropic window, the linear directional filters that are obtained using local polynomial approximation (LPA) are employed. The indicates the direction of filter that is a member of countable set , where is the number of directions. A common choice for is that results in the set {0°, 45°, 90°, 135°, 180°, 225°, 270°, 315°}. For each , the length of proposed window is selected from the countable and increasing set . So, for the noisy observation , we would have the following estimate:
For each and , an appropriate value of called is estimated using the nonlinear intersection of confidence intervals (ICI) rule. is the largest from the provided that the estimated data using does not have noticeable difference with the estimated data with smaller ’s. For this reason, the following confidence intervals are defined: where is the smoothing parameter and shows the variance of and is obtained as follows: where shows the power spectral density function and is the Fourier transform of , and for a white random process, (40) is simplified to
According to the ICI rule, is defined using the following formula:
The largest that leads to a nonempty value is called , and finally is obtained using .
Figure 7 shows an example of mentioned anisotropic window selection for a SEAD.
Since applying LPAICI in each subband is a time consuming process, a fast version of the mentioned algorithm can be based on only applying LPAICI to lowpass subbands using with an offset of 15° that results in the set {15°, 45°, 75°, 105°, 135°, 165°, 195°, 225°, 255°, 285°, 315°, 345°} in a 2D case. Since, in this case, each subband is extracting the information concentrated in a specific direction corresponding to {15° (195°), 45° (225°), 75° (255°), 105° (285°), 135° (315°), 165° (345°)}, the extracted that results from applying LPAICI to corresponding lowpass subband is used for obtaining the local parameters of th pixel. For example, suppose that DCWT is used for 3 scales and we want to calculate the local parameters of coarsest scale for the oriented real subband around 45° (225°). For this reason, and are extracted from the results of applying LPAICI on the LL subband of real part (or imaginary part) of DCWT. Then, if we are in the th scale, only pixel in direction of 45° and pixel in direction of 225° are used to extract the local parameters of th pixel in this subband (Figure 8).
A similar manner can be proposed in 3D case [67]. However, instead of using 2D direction , we use 3D direction . As shown in Figure 9, in 2D case we use a circular sector for each direction while for 3D case a conical body is produced for direction , and the sphere is covered (partly) using these cones. Similar to 2D case , is defined and for each the best called is obtained using ICI rule.
(a)
(b)
Note that in order to incorporate the anisotropic window selection for each DCWT coefficient in our OCT denoising algorithm explained in Algorithm 1, instead of using a square window for parameter estimation, an anisotropic window is obtained for each coefficient using the explained LPAICI method in this section, and only available data in this window are used for estimating and ,,), and .
5. Experimental Results
In this section, we apply the proposed despeckling algorithm to OCT image noise reduction. For this reason, we use 20 threedimensional OCT datasets in the presence of wet AMD pathology (SEAD) and use mean signaltonoise ratio (MSNR) and contrasttonoise ratio (CNR) as two quality measurements for OCT data. To calculate these measurements, we must define the region of interest (ROI). In this paper, we propose this region within the SEAD as illustrated in Figure 10. The base MSNR and CNR are defined as follows: where shows the mean of ROI and indicates the standard deviation of a large region outside the ROI (noise ROI in Figure 10).
Table 1 shows the results of MSNR and CNR for proposed ROIs in OCT data using our algorithm. As discussed in Section 3, various shrinkage functions can be obtained using our algorithm based on applying log transformation before applying 3D DCWT (we use homomorphic prefix for this method and nonhomomorphic when we do not use log transformation) and proposing AWGN or twosided Rayleigh pdf for modeling noise in 3D DCWT domain (we name them BiGaussMixShrinkL and BiGaussRayMixShrinkL, resp.). Figures 11 and 12, respectively, show the results of applying nonhomomorphic and homomorphic methods for (a slice of) depicted OCT image in Figure 10. In this figure, also in Table 1, we compare the results of nonlocal version of methods to show the effect of using anisotropic window selection technique. In order to show the SNR improvements, CNR curves for 156 selected ROIs have been depicted in Figure 13. It is clear that nonhomomorphic BiGaussMixShrinkL method outperforms the others.

(a)
(b)
(c)
(d)
(a)
(b)
(c)
(d)
Another way for evaluating the effect of our despeckling algorithm is the investigation of the intralayer segmentation results. Figure 14 shows a comparison between the segmented layers of a Topcon 3D OCT1000 imaging system using proposed method in [53]. It is clear that the first layer is detected truly after despeckling.
(a)
(b)
(c)
6. Conclusion and Future Work
In this paper, we introduced a new noise reduction algorithm for 3D OCT data. We found new shrinkage functions employing a mixture of bivariate Gaussian for modeling wavelet coefficients in each subband of complex wavelets. The parameters of this mixture model are estimated locally using a shapeadaptive manner based on the special structure of OCT data. We also used this model for denoising of other kinds of noise. Experiments show that our model has better results than other methods visually and in terms of PSNR especially for the crowded images. In this paper, we suppose that the parameters of EM algorithm, in extracted windows are constant. It is possible to improve the EM algorithm, for example, by using recurrence equations. It is possible that we only propose the main section of data (between the first and last layers) containing retina layer information and apply our algorithm on the selected data to improve the speed and performance of denoising process.
Using 3D DCWT instead of other transforms such as 3D DWT is a main reason for improvement of the denoising results [30]. In [27], it has been shown that other kinds of oriented transforms such as steerable pyramid decomposition can produce better denoising results. However, for 3D case, 3D transforms that are applied on whole 3D data (not slice by slice) such as surfacelet [68] and 3D discrete curvelet [69] can be investigated.
Appendices
A. Directional Selectivity Property of 2D DCWT
Since DWT in 2D domain is produced using separable (rowcolumn) implementation, it has a poor directional selectivity. For example, the HH wavelet is the product of the highpass functions along the first and second dimensions. Because DWT uses real filters, the HH wavelet mixes +45° and −45° orientations that results in the checkerboard artifact because it fails to isolate these orientations. In contrast, since the spectrum of the (approximately) analytic 1D wavelet is supported on only one side of the frequency axis, the spectrum of the DCWT in 2D domain is supported in only one quadrant of the 2D frequency plane. Figure 15 illustrates a comparison between subbands of 2D DWT and 2D DCWT.
(a)
(b)
(c)
(d)
B. A Sample Bivariate Gaussian Mixture Model
Figure 16 shows the pdf of a bivariate Gaussian mixture model for sample parameters. We can see the marginal distribution produced from the model in this figure.
C. Other Kinds of Noise
In this appendix, we briefly explain the abilities of the proposed denoising algorithm in this paper for other kinds of noise.
C.1. Stationary Noise
We tested the shrinkage function BiGaussMixShrinkL for stationary noise and compared it with other methods such as ProbShrink [34], BiShrink [45], and BLSGSM [27] and found that our algorithm outperforms these techniques visually and in terms of peak signaltonoise ratio (PSNR) for various levels of noise. For example, our algorithm for crowded images preserves details of images while BiShrink [45] in some cases produces blurred images (e.g., compare the area around the corresponding arrows in Figure 17). In addition, in [40] using other bivariate mixture models such as bivariate Laplacian was examined. We compared the results of using our model with method in [40], and our simulations show that our algorithm is faster and outperforms the reported shrinkage functions in [40] for some images. For example, for a 8bit grayscale Barbara image, an improvement of 0.6 dB is obtained for noise level of 30, and BiGaussMixShrinkL is two times faster.
(a)
(b)
C.2. Nonstationary Noise
This section presents nonstationary noise reduction examples in complex wavelet domain. Although the stationary noise model is able to simplify the implementation of denoising algorithms, the statistical properties of the noise are not always accurately described with this assumption. For example, in some applications, the noise statistics are spatially varying and the noise power varies between pixels or samples. In these cases, the nonstationary noise assumption is more reasonable and can improve the denoising results. For example, we contaminate three grayscale images, namely, Lena, Boat, and Barbara using signaldependent Gaussian noise with variance that is defined as a linear function of the pixel intensities as [54]:
Since the variance of each noise component is spatially varying with the corresponding content of signal, the nonstationary processes are able to model the statistical properties of this noise. A comparison between the denoised image using soft thresholding, proposed method in [54], and the denoised image using a mixture of two bivariate Gaussian pdfs with local parameters (BiGaussMixShrinkL) for different noise levels can be seen in Table 2. In this table, the highest PSNR value is bolded. We can see from the table that our proposed algorithm has the better results compared to others especially for the Barbara image (which contains details) in the highlevel noise.

In [54], it has been shown that the proposed algorithm based on the signaldependent Gaussian noise can also be effective for the reduction of Poisson noise. On this base, we use our algorithm for noise reduction of images corrupted by Poisson noise generated using corresponding voxel intensities. For this reason, we use the software provided on http://willett.ece.wisc.edu/software.html to compare our method with Fast TI Haar algorithm [55]. The PSNR of grayscale images Lena, Boat, Barbara, Confocal Microscopy Phantom, Bowl, and Shepp Logan Phantom can be seen in Table 3. We can see that our algorithm outperforms the Fast TI Haar algorithm. Figure 18 illustrates a comparison between the denoised images produced from two algorithms. It is clear that our algorithm has better results especially for the crowded images. In fact, the Fast TI Haar algorithm has reasonable performance for soft images such as Confocal Microscopy Phantom, but since this algorithm blurs the produced images, for images with details such as Barbara, highfrequency features will be removed and we lose the important information.

(a)
(b)
(c)
(d)
(e)
(f)
(g)
(h)
References
 D. Huang, E. A. Swanson, C. P. Lin et al., “Optical coherence tomography,” Science, vol. 254, no. 5035, pp. 1178–1181, 1991. View at: Google Scholar
 J. M. Schmitt, “Optical coherence tomography (OCT): a review,” IEEE Journal on Selected Topics in Quantum Electronics, vol. 5, no. 4, pp. 1205–1215, 1999. View at: Publisher Site  Google Scholar
 M. A. Choma, M. V. Sarunic, C. Yang, and J. A. Izatt, “Sensitivity advantage of swept source and Fourier domain optical coherence tomography,” Optics Express, vol. 11, no. 18, pp. 2183–2189, 2003. View at: Google Scholar
 M. E. J. van Velthoven, D. J. Faber, F. D. Verbraak, T. G. van Leeuwen, and M. D. de Smet, “Recent developments in optical coherence tomography for imaging the retina,” Progress in Retinal and Eye Research, vol. 26, no. 1, pp. 57–77, 2007. View at: Publisher Site  Google Scholar
 J. M. Schmitt, S. H. Xiang, and K. M. Yung, “Speckle in optical coherence tomography,” Journal of Biomedical Optics, vol. 4, no. 1, pp. 95–105, 1999. View at: Google Scholar
 D. L. Marks, T. S. Ralston, and S. A. Boppart, “Speckle reduction by Idivergence regularization in optical coherence tomography,” Journal of the Optical Society of America A, vol. 22, no. 11, pp. 2366–2371, 2005. View at: Publisher Site  Google Scholar
 Z. Jian, Z. Yu, L. Yu, B. Rao, Z. Chen, and B. J. Tromberg, “Speckle attenuation in optical coherence tomography by curvelet shrinkage,” Optics Letters, vol. 34, no. 10, pp. 1516–1518, 2009. View at: Publisher Site  Google Scholar
 Z. Jian, L. Yu, B. Rao, B. J. Tromberg, and Z. Chen, “Threedimensional speckle suppression in optical coherence tomography based on the curvelet transform,” Optics Express, vol. 18, no. 2, pp. 1024–1032, 2010. View at: Publisher Site  Google Scholar
 S. Chitchian, M. A. Fiddy, and N. M. Fried, “Denoising during optical coherence tomography of the prostate nerves via wavelet shrinkage using dualtree complex wavelet transform,” Journal of Biomedical Optics, vol. 14, no. 1, Article ID 014031, 2009. View at: Publisher Site  Google Scholar
 V. Zlokolica, Lj. Jovanov, A. Pizurica, and W. Philips, “Waveletbased denoising for OCT images, Interaction between image processing, optics and photonics,” in Symposium on Optical Science and Technology, Proceedings of SPIE, August 2007. View at: Google Scholar
 V. Gupta, C. C. Chan, C.L. Poh, T. H. Chow, T. C. Meng, and N. B. Koon, “Computerized automation of wavelet based denoising method to reduce speckle noise in OCT images,” in Proceedings of the 5th International Conference on Information Technology and Applications in Biomedicine, pp. 120–123, May 2008. View at: Publisher Site  Google Scholar
 P. Puvanathasan and K. Bizheva, “Speckle noise reduction algorithm for optical coherence tomography based on interval type II fuzzy set,” Optics Express, vol. 15, no. 24, pp. 15747–15758, 2007. View at: Publisher Site  Google Scholar
 A. Pižurica, L. Jovanov, B. Huysmans et al., “Multiresolution denoising for optical coherence tomography: a review and evaluation,” Current Medical Imaging Reviews, vol. 4, no. 4, pp. 270–284, 2008. View at: Publisher Site  Google Scholar
 H. M. Salinas and D. C. Fernández, “Comparison of PDEbased nonlinear diffusion approaches for image enhancement and denoising in optical coherence tomography,” IEEE Transactions on Medical Imaging, vol. 26, no. 6, pp. 761–771, 2007. View at: Publisher Site  Google Scholar
 K. M. Yung, S. L. Lee, and J. M. Schmilt, “Phasedomain processing of optical coherence tomography images,” Journal of Biomedical Optics, vol. 4, no. 1, pp. 125–136, 1999. View at: Google Scholar
 J. Rogowska and M. E. Brezinski, “Evaluation of the adaptive speckle suppression filter for coronary optical coherence tomography imaging,” IEEE Transactions on Medical Imaging, vol. 19, no. 12, pp. 1261–1266, 2000. View at: Google Scholar
 A. Ozcan, A. Bilenca, A. E. Desjardins, B. E. Bouma, and G. J. Tearney, “Speckle reduction in optical coherence tomography images using digital filtering,” Journal of the Optical Society of America A, vol. 24, no. 7, pp. 1901–1910, 2007. View at: Publisher Site  Google Scholar
 D. C. Adler, T. H. Ko, and J. G. Fujimoto, “Speckle reduction in optical coherence tomography images by use of a spatially adaptive wavelet filter,” Optics Letters, vol. 29, no. 24, pp. 2878–2880, 2004. View at: Publisher Site  Google Scholar
 S. G. Mallat, A Wavelet Tour of Signal Processing, Academic Press, San Diego, Calif, USA, 1998.
 B. Vidakovic, Statistical Modeling by Wavelets, John Wiley & Sons, New York, NY, USA, 1999.
 E. P. Simoncelli and E. H. Adelson, “Noise removal via Bayesian wavelet coring,” in Proceedings of the IEEE International Conference on Image Processing, pp. 379–382, Lausanne, Switzerland, September 1996. View at: Google Scholar
 E. P. Simoncelli, “Bayesian denoising of visual images in the wavelet domain,” in Bayesian Inference in Wavelet Based Models, P. Muller and B. Vidakovic, Eds., pp. 291–308, Springer, New York, NY, USA, 1999. View at: Google Scholar
 A. Achim, A. Bezerianos, and P. Tsakalides, “Novel Bayesian multiscale method for speckle removal in medical ultrasound images,” IEEE Transactions on Medical Imaging, vol. 20, no. 8, pp. 772–783, 2001. View at: Publisher Site  Google Scholar
 J. M. Fadili and L. Boubchir, “Analytical form for a Bayesian wavelet estimator of images using the Bessel K form densities,” IEEE Transactions on Image Processing, vol. 14, no. 2, pp. 231–240, 2005. View at: Publisher Site  Google Scholar
 P. A. Khazron and I. W. Selesnick, “Bayesian estimation of bessel K form random vectors in AWGN,” IEEE Signal Processing Letters, vol. 15, pp. 261–264, 2008. View at: Publisher Site  Google Scholar
 M. S. Crouse, R. D. Nowak, and R. G. Baraniuk, “Waveletbased statistical signal processing using hidden Markov models,” IEEE Transactions on Signal Processing, vol. 46, no. 4, pp. 886–902, 1998. View at: Publisher Site  Google Scholar
 J. Portilla, V. Strela, M. J. Wainwright, and E. P. Simoncelli, “Image denoising using scale mixtures of Gaussians in the wavelet domain,” IEEE Transactions on Image Processing, vol. 12, no. 11, pp. 1338–1351, 2003. View at: Publisher Site  Google Scholar
 H. Rabbani and S. Gazor, “Image denoising employing local mixture models in sparse domains,” IET Image Processing, vol. 4, no. 5, pp. 413–428, 2010. View at: Publisher Site  Google Scholar
 A. Elmzoughi, A. BenazzaBenyahia, and J.C. Pesquet, “An interscale multivariate statistical model for map multicomponent image denoising in the wavelet transform domain,” in Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '05), pp. II45–II48, March 2005. View at: Publisher Site  Google Scholar
 H. Rabbani and M. Vafadust, “Image/video denoising based on a mixture of Laplace distributions with local parameters in multidimensional complex wavelet domain,” Signal Processing, vol. 88, no. 1, pp. 158–173, 2008. View at: Publisher Site  Google Scholar
 H. A. Chipman, E. D. Kolaczyk, and R. E. McCulloch, “Adaptive Bayesian wavelet shrinkage,” Journal of the American Statistical Association, vol. 92, no. 440, pp. 1413–1421, 1997. View at: Google Scholar
 M. J. Borran and R. D. Nowak, “Waveletbased denoising using hidden Markov models,” in Proceedings of the IEEE Interntional Conference on Acoustics, Speech, and Signal Processing, pp. 3925–3928, May 2001. View at: Google Scholar
 J. K. Romberg, H. Choi, and R. G. Baraniuk, “Bayesian treestructured image modeling using waveletdomain hidden Markov models,” IEEE Transactions on Image Processing, vol. 10, no. 7, pp. 1056–1068, 2001. View at: Publisher Site  Google Scholar
 A. Pižurica, W. Philips, I. Lemahieu, and M. Acheroy, “A joint inter and intrascale statistical model for Bayesian wavelet based image denoising,” IEEE Transactions on Image Processing, vol. 11, no. 5, pp. 545–557, 2002. View at: Publisher Site  Google Scholar
 A. A. Bharath and J. Ng, “A steerable complex wavelet construction and its application to image denoising,” IEEE Transactions on Image Processing, vol. 14, no. 7, pp. 948–959, 2005. View at: Publisher Site  Google Scholar
 L. Şendur and I. W. Selesnick, “Bivariate shrinkage functions for waveletbased denoising exploiting interscale dependency,” IEEE Transactions on Signal Processing, vol. 50, no. 11, pp. 2744–2756, 2002. View at: Publisher Site  Google Scholar
 H. Rabbani, M. Vafadust, S. Gazor, and I. Selesnick, “Image denoising employing a bivariate cauchy distribution with local variance in complex wavelet domain,” in Proceedings of the 12th IEEE Digital Signal Processing Workshop and 4th IEEE Signal Processing Education Workshop, pp. 203–208, Grand Teton National Park, Wy, USA, September 2006. View at: Publisher Site  Google Scholar
 J. Portilla, “Full blind denoising through noise covariance estimation using gaussian scale mixtures in the wavelet domain,” in Proceedings of the International Conference on Image Processing (ICIP '04), pp. 1217–1220, October 2004. View at: Google Scholar
 S. Lyu and E. P. Simoncelli, “Modeling multiscale subbands of photographic images with fields of Gaussian scale mixtures,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 31, no. 4, pp. 693–706, 2009. View at: Publisher Site  Google Scholar
 H. Rabbani, R. Nezafat, and S. Gazor, “Waveletdomain medical image denoising using bivariate laplacian mixture model,” IEEE Transactions on Biomedical Engineering, vol. 56, no. 12, pp. 2826–2837, 2009. View at: Publisher Site  Google Scholar
 I. Selesnick and K. Li, “Video denoising using 2d and 3d dualtree complex wavelet transforms,” in Wavelet Applications in Signal and Image Processing, vol. 5207 of Proceedings of SPIE, August 2003. View at: Google Scholar
 Z. Cai, T. H. Cheng, C. Lu, and K. R. Subramanian, “Efficient waveletbased image denoising algorithm,” Electronics Letters, vol. 37, no. 11, pp. 683–685, 2001. View at: Publisher Site  Google Scholar
 M. K. Mihçak, I. Kozintsev, K. Ramchandran, and P. Moulin, “Lowcomplexity image denoising based on statistical modeling of wavelet coefficients,” IEEE Signal Processing Letters, vol. 6, no. 12, pp. 300–303, 1999. View at: Publisher Site  Google Scholar
 H. Rabbani, M. Vafadust, P. Abolmaesumi, and S. Gazor, “Speckle noise reduction of medical ultrasound images in complex wavelet domain using mixture priors,” IEEE Transactions on Biomedical Engineering, vol. 55, no. 9, pp. 2152–2160, 2008. View at: Google Scholar
 L. Şendur and I. W. Selesnick, “Bivariate shrinkage with local variance estimation,” IEEE Signal Processing Letters, vol. 9, no. 12, pp. 438–441, 2002. View at: Publisher Site  Google Scholar
 H. Rabbani, M. Vafadust, and S. Gazor, “Image denoising based on a mixture of bivariate gaussian distributions with local parameters in complex wavelet domain,” in Proceedings of the International Conference on Biomedical and Pharmaceutical Engineering, pp. 174–179, December 2006. View at: Publisher Site  Google Scholar
 V. Katkovnik, K. Egiazarian, and J. Astola, “Adaptive window size image denoising based on intersection of confidence intervals (ICI) rule,” Journal of Mathematical Imaging and Vision, vol. 16, no. 3, pp. 223–235, 2002. View at: Publisher Site  Google Scholar
 I. W. Selesnick, R. G. Baraniuk, and N. G. Kingsbury, “The dualtree complex wavelet transform,” IEEE Signal Processing Magazine, vol. 22, no. 6, pp. 123–151, 2005. View at: Publisher Site  Google Scholar
 B. Wang, Y. Wang, I. Selesnick, and A. Vetro, “Video coding using 3D dualtree wavelet transform,” Eurasip Journal on Image and Video Processing, vol. 2007, Article ID 42761, 15 pages, 2007. View at: Publisher Site  Google Scholar
 W. Jingwei, G. Xinbo, and Z. Juanjuan, “A video watermarking based on 3D complex wavelet,” in Proceedings of the 14th IEEE International Conference on Image Processing, pp. V493–V496, September 2007. View at: Publisher Site  Google Scholar
 J. Yang, Y. Wang, W. Xu, and Q. Dai, “Image and video denoising using adaptive dualtree discrete wavelet packets,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 19, no. 5, pp. 642–655, 2009. View at: Publisher Site  Google Scholar
 I. Bayram and I. W. Selesnick, “A dualtree rationaldilation complex wavelet transform,” IEEE Transactions on Signal Processing, vol. 59, no. 12, pp. 6251–6256, 2011. View at: Publisher Site  Google Scholar
 K. Lee, M. Niemeijer, M. K. Garvin, Y. H. Kwon, M. Sonka, and M. D. Abramoff, “Segmentation of the optic disc in 3D OCT scans of the optic nerve head,” IEEE Transactions on Medical Imaging, vol. 29, no. 1, pp. 159–168, 2010. View at: Publisher Site  Google Scholar
 W. Y. Lo and I. W. Selesnick, “Waveletdomain softthresholding for nonstationary noise,” in Proceedings of the IEEE International Conference on Image Processing, pp. 1441–1444, October 2006. View at: Publisher Site  Google Scholar
 R. M. Willett and R. D. Nowak, “Fast multiresolution photonlimited image reconstruction,” in Proceedings of the 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano (ISBI '04), vol. 2, pp. 1192–1195, April 2004. View at: Google Scholar
 A. Pižurica, W. Philips, I. Lemahieu, and M. Acheroy, “A versatile wavelet domain noise filtration technique for medical imaging,” IEEE Transactions on Medical Imaging, vol. 22, no. 3, pp. 323–331, 2003. View at: Publisher Site  Google Scholar
 S. Gupta, R. C. Chauhan, and S. C. Saxena, “Robust nonhomomorphic approach for speckle reduction in medical ultrasound images,” Medical and Biological Engineering and Computing, vol. 43, no. 2, pp. 189–195, 2005. View at: Publisher Site  Google Scholar
 S. Gupta, L. Kaur, R. C. Chauhan, and S. C. Saxena, “A versatile technique for visual enhancement of medical ultrasound images,” Digital Signal Processing, vol. 17, no. 3, pp. 542–560, 2007. View at: Publisher Site  Google Scholar
 S. Yan, J. Yuan, M. Liu, and C. Hou, “Speckle noise reduction of ultrasound images based on an undecimated wavelet packet transform domain nonhomomorphic filtering,” in Proceedings of the 2nd International Conference on Biomedical Engineering and Informatics, pp. 1–5, October 2009. View at: Publisher Site  Google Scholar
 R. F. Wagner, M. F. Insana, and D. G. Brown, “Statistical properties of radiofrequency and envelopedetected signals with applications to medical ultrasound,” Journal of the Optical Society of America A, vol. 4, no. 5, pp. 910–922, 1987. View at: Google Scholar
 P. M. Shankar, “Ultrasonic tissue characterization using a generalized Nakagami model,” IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, vol. 48, no. 6, pp. 1716–1720, 2001. View at: Publisher Site  Google Scholar
 P. M. Shankar, J. M. Reid, H. Ortega, C. W. Piccoli, and B. B. Goldberg, “Use of nonRayleigh statistics for the identification of tumors in ultrasonic Bscans of the breast,” IEEE Transactions on Medical Imaging, vol. 12, no. 4, pp. 687–692, 1993. View at: Publisher Site  Google Scholar
 P. M. Shankar, “A model for ultrasonic scattering from tissues based on the K distribution,” Physics in Medicine and Biology, vol. 40, no. 10, pp. 1633–1649, 1995. View at: Publisher Site  Google Scholar
 I. K. Eom and Y. S. Kim, “Waveletbased denoising with nearly arbitrarily shaped windows,” IEEE Signal Processing Letters, vol. 11, no. 12, pp. 937–940, 2004. View at: Publisher Site  Google Scholar
 W. Drexler and J. G. Fujimoto, “Stateoftheart retinal optical coherence tomography,” Progress in Retinal and Eye Research, vol. 27, no. 1, pp. 45–88, 2008. View at: Publisher Site  Google Scholar
 M. D. Abramoff, M. K. Garvin, and M. Sonka, “Retinal imaging and image analysis,” IEEE Reviews in Biomedical Engineering, vol. 3, pp. 169–208, 2010. View at: Publisher Site  Google Scholar
 C. Ercole, A. Foi, V. Katkovnik, and K. Egiazarian, “Spatiotemporal pointwise adaptive denoising of video: 3D nonparametric approach,” in Proceedings of the 1st International Workshop on Video Process and Quality Metrics for Consumer Electronics (VPQM '05), 2005. View at: Google Scholar
 Y. M. Lu and M. N. Do, “Multidimensional directional filter banks and surfacelets,” IEEE Transactions on Image Processing, vol. 16, no. 4, pp. 918–931, 2007. View at: Publisher Site  Google Scholar
 L. Ying, L. Demanet, and E. Candès, “3D discrete curvelet transform,” in Wavelets XI, vol. 5914 of Proceedings of SPIE, pp. 1–11, August 2005. View at: Publisher Site  Google Scholar
Copyright
Copyright © 2013 Hossein Rabbani et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.