基于自适应过完备稀疏表示的红外图像滤波方法

针对传统滤波算法在滤除红外图像噪声时会损失部分有用信息的问题,提出一种基于自适应过完备稀疏表示的红外图像滤波方法。该方法采用K-SVD算法以待滤波的红外图像为样本训练出自适应过完备原子库;采用正交匹配跟踪算法将红外图像信号在该过完备原子库上稀疏分解为稀疏成分和其他成分,稀疏成分对应红外图像中的有用信息,其他成分对应红外图像中的噪声,由稀疏成分重建图像,从而达到消除噪声的目的。实验结果表明:该方法相比传统方法具有更好的滤波效果,重建图像质量较高。     

超分辨率图像重建引起的噪声放大与滤波

总结了图像序列相位关系对超分辨率图像重建效果的影响规律,对超分辨率图像重建引起的高斯噪声和散粒噪声的放大予以研究.通过叠加不同方差的高斯噪声的图像序列重建实验,得到结论维纳滤波可以有效地滤除放大后的高斯噪声,但是超分辨率图像重建后散粒噪声放大成为"波纹"形状的噪声,传统的中值滤波法不能有效地滤除放大后的"波纹"形状噪声...     

一种改进权重的非局部均值滤波算法

传统非局部均值滤波算法采用指数型加权核函数,容易导致图像细节平滑过度,并且权值分配容易受到噪声的影响。针对这一问题,提出一种改进权重的非局部均值滤波算法,设计一种新的加权核函数替代原本的指数型核函数,改善权值的分配。实验结果表明,改进算法降噪效果优于传统非局部均值滤波算法,在滤除噪声的同时更好地保护了图像的边缘与细节,并且噪声强度越大,改进算法的优势越明显。     

EMCCD图像自适应模糊中值滤波算法研究

针对电子倍增CCD（EMCCD）图像噪声密度随着增益的变化而变化,提出了一种基于噪声点检测的自适应模糊中值滤波算法。该算法由模糊滤波模块和自适应模块两部分组成。首先,该算法对滤波窗口内的中心点进行噪声检测;然后对检测为噪声的像素点引入双阈值,并根据引入的阈值和滤波窗口内的中值建立噪声点的模糊隶属函数,根据模糊隶属函数对噪声点进行滤波处理后输出;最后采用自适应模块调整待处理图像的像素。仿真及实验结果表明,新算法不仅能够有效地将图像中的噪声去除,而且很好地保护了图像中的细节和边缘,PSNR比传统的自适应中值滤波算法平均提高了15 dB以上;该算法在低噪声密度情况下性能明显好于其他中值滤波器,在高噪声密度情况下性能也比较稳定。     

基于图像中值灰度相似度函数加权曲率滤波算法

曲率滤波算法通过构造滤波算子快速优化变分模型,但全变分曲率滤波及高斯曲率滤波易致去噪过平滑且椒盐噪声去除较差.提出了基于图像中值灰度相似度函数加权曲率滤波算法,其中,中值灰度相似度函数方差取决于小波变换最高频子带系数,能较好防止图像过平滑,且提高椒盐噪声去除能力;因此,采用中值灰度相似度函数分别对局部高斯曲率与局部全变分曲率投影算子加权,并分别迭代局部加权高斯曲率投影算子与局部加权全变分曲率投影算子,直至输出图像梯度总能量满足停止条件.实验表明,基于图像中值灰度相似度函数加权全变分曲率滤波与加权高斯曲率滤波比传统全变分曲率滤波和高斯曲率滤波去噪效果更好.     

基于混合滤波算法的数字图像去噪方法研究

双边滤波已广泛应用于数字图像处理领域,但在图像的高梯度区域,双边滤波会产生阶梯效应。双边滤波是局部模式滤波的一种特殊形式,提出了基于高斯滤波和双边滤波的混合图像去噪方法。利用高斯滤波器对噪声图像进行滤波,得到参考图像,将参考图像和噪声图像作为范围核函数的输入双边滤波器。参考图像提供图像的低频信息,噪声图像提供图像的高频信息。与传统双边滤波法比较,混合去噪方法能够有效地克服阶梯效应,滤波后的图像更平滑,纹理特征更接近原始图像,可获得更高的峰值信噪比。     

一种抑制混合噪声的组合滤波算法

为了滤除图像中存在的混合噪声,提出了一种基于中值和均值的组合滤波算法。算法分两步进行,第一步采用改进的中值滤波算法过滤图像中的椒盐噪声;第二步将滤除椒盐噪声的图像采用均值滤波算法进行平滑,滤除高斯噪声。计算机仿真实验表明,组合滤波算法对于图像中的椒盐噪声和高斯噪声具有较好的滤除效果和细节保护作用,性能明显优于传统滤波算法。     

基于PSO和改进神经网络的图像滤波方法的研究

提出了一种基于改进BP神经网络和粒子群优化算法（PSO）的图像滤波方法。该方法利用对数最小均方误差函数（LNLS）代替BP神经网络传统的最小均方误差函数（LMS）,用来减小图像噪声对神经网络精度的影响;并将改进后的BP神经网络利用PSO算法优化,从而避免神经网络陷入局部极小值点,进一步提高神经网络滤波能力。实验结果表明,与传统滤波方法相比,该方法不仅能有效地滤除图像中的高斯噪声而且能很好地保护图像细节。     

少数投影最大熵图像重建的数值模拟

提出了一种新的少数投影层析图像重建算法,通过数值模拟,考察了该算法对不同场分布函数的重建效果以及抗噪声性能,结果表明,该算法具有较高的重建精度和良好的抗噪场性能。     

基于改进Canny算子的图像边缘检测方法

针对传统Canny边缘检测算法采用高斯滤波处理图像不能有效消除椒盐噪声的问题,提出改进Canny算子用于检测图像边缘.首先利用双滤波设计-融合自适应模糊中值滤波和双边滤波去除图像椒盐噪声,降低图像噪声同时保证图像边缘.然后在研究过程中遇到边缘检测人工阈值选取自适应不足的问题,采用最大类间方差(Otsu)算法计算得到高低...     

Efficient implementation of all-digital interpolation

B-splines are commonly used for continuous representation of discrete time signals. This kind of representation proves to be very useful in applications such as image interpolation, rotation and edge detection. In all these applications, the first step is to compute the B-spline coefficients of the signal, and this involves the use of an IIR noncausal filter called the direct B-spline filter. The signal reconstruction is achieved using the indirect B-spline filter, which in many applications operates at a higher rate. We introduce a simplified implementation of the signal reconstruction part that will significantly reduce the overall complexity. We also show that the direct B-spline filter can safely be replaced with a short FIR filter, without compromising the performance of the traditional method. Numerous examples show both visually and numerically that the differences between this method and the traditional one are indeed very small. Finally, we report the performance of these newly proposed methods in other image processing applications such as edge detection and least squares approximation.     

A coupled variational model for image denoising using a duality strategy and split Bregman

To reduce the staircase effect, high-order diffusion equations are used with high computational cost. Recently, a two-step method with two energy functions has been introduced to alleviate the staircase effect successfully. In the two-step method, firstly, the normal vector of noisy image is smoothed, and then the image is reconstructed from the smoothed normal field. In this paper, we propose a new image restoration model with only one energy function. When the alternating direction method is used, the estimation of the vector field and the reconstruction of the image are interlaced, which makes the new vector field can utilize sufficiently the information of the restored image, thus the constructed vector field is more accurate than that generated by the two-step method. To speed up the computation, the dual approach and split Bregman are employed in our numerical algorithm. The experimental results show that the new model is more effective to filter out the Gaussian noise than the state-of-the-art models.     

Nonparametric regression sinogram smoothing using a roughness-penalized Poisson likelihood objective function

We develop and investigate an approach to tomographic image reconstruction in which nonparametric regression using a roughness-penalized Poisson likelihood objective function is used to smooth each projection independently prior to reconstruction by unapodized filtered backprojection (FBP). As an added generalization, the roughness penalty is expressed in terms of a monotonic transform, known as the link function, of the projections. The approach is compared to shift-invariant projection filtering through the use of a Hanning window as well as to a related nonparametric regression approach that makes use of an objective function based on weighted least squares (WLS) rather than the Poisson likelihood. The approach is found to lead to improvements in resolution-noise tradeoffs over the Hanning filter as well as over the WLS approach. We also investigate the resolution and noise effects of three different link functions: the identity, square root, and logarithm links. The choice of link function is found to influence the resolution uniformity and isotropy properties of the reconstructed images. In particular, in the case of an idealized imaging system with intrinsically uniform and isotropic resolution, the choice of a square root link function yields the desirable outcome of essentially uniform and isotropic resolution in reconstructed images, with noise performance still superior to that of the Hanning filter as well as that of the WLS approach.     

High spectral quality pansharpening approach based on MTF-matched filter banks

Pansharpening consists in merging a low-resolution multispectral image (MS) with a high spatial resolution panchromatic image (PAN) to produce a high resolution pansharpened MS image. It consists in enhancing spatially the low-resolution MS image by injecting the missing details provided by the high-resolution PAN image. In this paper, we propose a novel pansharpening approach based on decomposition/reconstruction processing using low-pass and high-pass filter banks. On the one hand, the low-pass approximation (taking into account the imaging system modulation transfer function MTF) of the pansharpened MS image is assumed to be equal to the original MS image in order to preserve the spectral quality. On the other hand, the high-pass filter allowing us to extract the high-frequency PAN details is designed as complementary filter to the low-pass one in order to provide perfect reconstruction in the ideal case. Quantitative assessment performed on reduced and full-resolution images are used to validate the proposed technique and compare it to state-of-art. Experimental results using Pléaides and GeoEye-1 data show that our proposed fusion schema outperforms the pre-existing methods visually as well as quantitatively.     

Fast magnetic resonance imaging with simultaneously oscillating and rotating fiell gradients

We present an approach to magnetic resonance imaging employing a magnetic field gradient that rotates 180 degrees in the image plane while the gradient magnitude oscillates rapidly during the rotation. A single free induction decay recorded during this rotation contains all the information needed to reconstruct a two-dimensional image. In effect, each sinusoidal oscillation of the gradient provides information corresponding to one projection in more conventional Fourier-projection approaches. Since the data acquisition can be achieved in a period less than T2, the method offers the potential of great speed, which is limited only by the gradient modulation frequency. An explicit image reconstruction formula is derived that gives, when evaluated, a reconstruction of the magnetization equal to the true magnetization convolved with a space-invariant point spread function. This point spread function is derived and characterizes the resolving power and sidelobe response of the technique. Moreover, we derive a similar reconstruction formula which is valid when known inhomogeneities in the static field H0 and T2 are present. Finally, we show how the general approach can be extended to three dimensions.     

Elitist Reconstruction Genetic Algorithm Based on Markov Random Field for Magnetic Resonance Image Segmentation

In this paper,elitist reconstruction genetic algorithm(ERGA) based on Markov random field(MRF) is introduced for image segmentation.In this algorithm,a population of possible solutions is maintained at every generation,and for each solution a fitness value is calculated according to a fitness function,which is constructed based on the MRF potential function according to Metropolis function and Bayesian framework.After the improved selection,crossover and mutation,an elitist individual is restructured based on the strategy of restructuring elitist.This procedure is processed to select the location that denotes the largest MRF potential function value in the same location of all individuals.The algorithm is stopped when the change of fitness functions between two sequent generations is less than a specified value.Experiments show that the performance of the hybrid algorithm is better than that of some traditional algorithms.     

The Use of Filtering Methods to Compensate for Constant Attenuation in Single-Photon Emission Computed Tomography

A back projection of filtered projection (BKFIL) reconstruction algorithm is presented that is applicable to single-photon emission computed tomography (ECT) in the presence of a constant attenuating medium such as the brain. The filters used in transmission computed tomography (TCT)-comprised of a ramp multiplied by window functions?are modified so that the single-photon ECT filter is a function of the constant attenuation coefficient. The filters give good reconstruction results with sufficient angular and lateral sampling. With continuous samples the BKFIL algorithm has a point spread function that is the Hankel transform of the window function. The resolution and statistical properties of the filters are demonstrated by various simulations which assume an ideal detector response. Statistical formulas for the reconstructed image show that the square of the percent-root-mean-square (percent-rms) uncertainty of the reconstruction is inversely proportional to the total measured counts. The results indicate that constant attenuation can be compensated for by using an attenuation-dependent filter that reconstructs the transverse section reliably. Computer time requirements are two times that of conventional TCT or positron ECT and there is no increase in memory requirements.     

Hardware Implementation of Enhancement Embedded Reduced Runtime Recovery Algorithm for Compressively Sensed Images

Compressed sensing is based on the principle that, through optimization, the sparsity of a signal can be exploited to recover it from fewer samples than required by the criterion. In compressed sensing, data is compressed and converted into fewer measurements and transmitted through wireless channel which is reconstructed at the receiver. Since very few samples are used for reconstruction, there are possibilities of degradation in quality of reconstruction. Unlike traditional methods, enhancement can now be done using the recent technique of compressed sensing by embedding image enhancement techniques like edge detection, histogram, filtering and their combinations with CS recovery procedure. This work proposes such a method by binding the image enhancement techniques along with the compressed sensing process. Filter of Gaussian filter (FGF), a combinational filter proposed in this study enables an increase in PSNR of 1 dB when compared to other filtering techniques besides using least number of measurements and maintaining minimum time consumption. The runtime difference with and without the FGF is ~?3 s, which is affordable even in hardware with minimum specifications. Real time experimentation of embedded enhancement CS was carried out in WINGZ board to prove the feasibility of enhanced recovery process with lower end hardware.     

基于线性迭代的DFT调制滤波器组的设计算法

该文研究了单原型的DFT调制滤波器组的设计方法。在该方法中,滤波器组的设计问题被归结为一个无约束的优化问题,其目标函数为滤波器组的传递失真、混叠失真和原型滤波器的阻带能量的加权和。结合线性化方法,原型滤波器通过迭代求解。在单步迭代中,原型滤波器的系数通过解析式求解得到。仿真表明,与传统的设计算法相比,本文方法设计所得的DFT调制滤波器组重构误差减小了约40dB,阻带衰减提高了约2dB。并且新算法的计算复杂度明显低于传统算法。     

基于双引导滤波的红外和可见光图像融合算法

图像融合是将多幅图像中有用或互补信息整合成一幅图像的过程。本文提出了一种基于引导滤波多尺度分解的红外和可见光图像融合算法。在传统的引导滤波图像融合算法的基础之上,利用双引导滤波器代替均值滤波器将源图像分解为小尺度纹理细节、大尺度边缘和基础图像;直接利用纹理细节及边缘层图像构建显著性映射图,用其代替额外的特征提取操作,可很好地突出源图像显著性信息的同时大大降低算法复杂度;利用显著性映射图、Sigmoid函数构造权重图,将源图像中具有视觉意义的信息注入到融合图像中;利用色彩模型转换融合方式,可更好保留图像的色彩信息。定性和定量实验结果证明,相比于传统的基于引导滤波的图像融合算法,本文算法的融合效果得到进一步提升。