一种改进灰狼优化算法研究及应用

针对灰狼算法易陷入局部最优、收敛精度不高、收敛速度慢等缺点,提出一种改进的灰狼算法.引入莱维飞行,扩大搜索范围,增强全局搜索能力,避免陷入局部最优;引入贪婪原理,提升种群优良性以提高算法收敛精度;引入自适应收敛因子,加快收敛速度;引入动态权重策略,制约全局搜索与局部搜索的相互影响.将改进算法与其他四种算法作对比,实验表明,改进算法在收敛速度与收敛精度上都有更好的性能.最后,应用于图像多阈值分割中,采用GWO-Otsu法可以克服传统Otsu法在多阈值分割时计算量大,实时性差的特点,不但能够取得最优解,且明显缩减计算时间.     

基于亮度均衡化的图像阈值分割技术在黄河冰凌监测中的应用

一种基于亮度均衡化的图像阈值分割算法被提出.该算法将冰凌图像亮度数据均衡化,以类间方差最大为标准,求得最佳阈值,并将冰凌图像转化为二值图像,通过冰凌像素统计,最终确定冰凌密度.该算法被应用于黄河河道冰凌图像密度的计算中,取得较好的效果.     

基于Huber正则化的红外与可见光图像融合

图像融合通常是指从多源信道采集同一目标图像,将互补的多焦点、多模态、多时相和/或多视点图像集成在一起,形成新图像的过程.在本文中,我们采用基于Huber正则化的红外与可见光图像的融合模型.该模型通过约束融合图像与红外图像相似的像素强度保持热辐射信息,以及约束融合图像与可见光图像相似的灰度梯度和像素强度保持图像的边缘和纹理等外观信息,同时能够改善图像灰度梯度相对较小区域的阶梯效应.为了最小化这种变分模型,我们结合增广拉格朗日方法(ALM)和量身定做有限点方法(TFPM)的思想设计数值算法,并给出了算法的收敛性分析.最后,我们将所提模型和算法与其他七种图像融合方法进行定性和定量的比较,分析了本文所提模型的特点和所提数值算法的有效性.     

Bi-level thresholding using PSO, Artificial Bee Colony and MRLDE embedded with Otsu method

Image segmentation is required to be studied in detail some particular features (areas of interest) of a digital image. It forms an important and exigent part of image processing and requires an exhaustive and robust search technique for its implementation. In the present work we have studied the working of MRLDE, a newly proposed variant of differential evolution combined with Otsu method, a well known image segmentation method for bi-level thresholding. The proposed variant, termed as Otsu+MRLDE, is tested on a set of 10 images and the results are compared with Otsu method and some other well known metaheuristics.     

一种改进的混沌序列产生方法

根据灰度图像的二维直方图的特点,在已有的二维Arnold混沌系统的基础上,结合Bernstein形式的Bézier曲线的生成算法,给出了一种基于生成Bézier曲线的de Casteljau算法构造伪随机序列的方法,实验结果表明生成的二维序列不仅具有伪随机性,而且还具有在近似圆盘中随机分布的性质,这使得该伪随机序列更适合对灰度图像的二维灰度直方图进行基于混沌优化的图像分割.在此基础上,给出了一种基于混沌优化的二维最大熵的灰度图像分割算法,该算法对于含噪图像取得了良好的分割效果.     

A multi-scale image reconstruction algorithm for electrical capacitance tomography

Electrical capacitance tomography (ECT) is considered as a promising process tomography (PT) technology, and its successful applications depend mainly on the precision and speed of the image reconstruction algorithms. In this paper, based on the wavelet multi-scale analysis method, an efficient image reconstruction algorithm is presented. The original inverse problem is decomposed into a sequence of inverse problems, which are solved successively from the largest scale to the smallest scale. At different scales, the inverse problem is solved by a generalized regularized total least squares (TLS) method, which is developed using a combinational minimax estimation method and an extended stabilizing functional, until the solution of the original inverse problem is found. The homotopy algorithm is employed to solve the objective functional. The proposed algorithm is tested by the noise-free capacitance data and the noise-contaminated capacitance data, and excellent numerical performances and satisfactory results are observed. In the cases considered in this paper, the reconstruction results show remarkable improvement in the accuracy. The spatial resolution of the reconstructed images by the proposed algorithm is enhanced and the artifacts in the reconstructed images can be eliminated effectively. As a result, a promising algorithm is introduced for ECT image reconstruction.     

Selective diffusion involving reaction for binarization of bleed-through document images

Binarization has always been a challenging problem in document image processing because of various types of degradation. In this paper, we present a nonlinear reaction–diffusion model for binarization of bleed-through document images, which is the Perona–Malik equation involving diffusion coefficient based on structure tensor along with a nonlinear reaction term. The Perona–Malik diffusion is utilized to selectively smooth document images with bleed-through removal. Meanwhile, the nonlinear reaction term takes the responsibility for the desired binarization. In order to solve our model numerically, we develop a parallel–series splitting algorithm by combining finite differencing with two kinds of splitting methods in the literature. Our algorithm is tested on seven publicly available datasets (DIBCO 2009 to 2014 and 2016). The experimental results show that our method averagely outperforms six relevant models for the nineteen document images with bleed-through in the DIBCO series datasets.     

Noisy image segmentation based on nonlinear diffusion equation model

This paper addresses the segmentation problem in noisy image based on nonlinear diffusion equation model and proposes a new adaptive segmentation model based on gray-level image segmentation model. This model also can be extended to the vector value image segmentation. By virtue of the prior information of regions and boundary of image, a framework is established to construct different segmentation models using different probability density functions. A segmentation model exploiting Gauss probability density function is given in this paper. An efficient and unconditional stable algorithm based on locally one-dimensional (LOD) scheme is developed and it is used to segment the gray image and the vector values image. Comparing with existing classical models, the proposed approach gives the best performance.     

Intelligent Initialization and Adaptive Thresholding for Iterative Matrix Completion: Some Statistical and Algorithmic Theory for Adaptive-Impute

Over the past decade, various matrix completion algorithms have been developed. Thresholded singular value decomposition (SVD) is a popular technique in implementing many of them. A sizable number of studies have shown its theoretical and empirical excellence, but choosing the right threshold level still remains as a key empirical difficulty. This article proposes a novel matrix completion algorithm which iterates thresholded SVD with theoretically justified and data-dependent values of thresholding parameters. The estimate of the proposed algorithm enjoys the minimax error rate and shows outstanding empirical performances. The thresholding scheme that we use can be viewed as a solution to a nonconvex optimization problem, understanding of whose theoretical convergence guarantee is known to be limited. We investigate this problem by introducing a simpler algorithm, generalized- softImpute, analyzing its convergence behavior, and connecting it to the proposed algorithm.     

Two-Phase Image Segmentation by Nonconvex Nonsmooth Models with Convergent Alternating Minimization Algorithms

Two-phase image segmentation is a fundamental task to partition an image into foreground and background. In this paper, two types of nonconvex and nonsmooth regularization models are proposed for basic two-phase segmentation. They extend the convex regularization on the characteristic function on the image domain to the nonconvex case, which are able to better obtain piecewise constant regions with neat boundaries. By analyzing the proposed non-Lipschitz model, we combine the proximal alternating minimization framework with support shrinkage and linearization strategies to design our algorithm. This leads to two alternating strongly convex subproblems which can be easily solved. Similarly, we present an algorithm without support shrinkage operation for the nonconvex Lipschitz case. Using the Kurdyka-Łojasiewicz property of the objective function, we prove that the limit point of the generated sequence is a critical point of the original nonconvex nonsmooth problem. Numerical experiments and comparisons illustrate the effectiveness of our method in two-phase image segmentation.     

基于Gabor小波的纹理图像分类(英文)

For a texture image, by recognizining the class of every pixel of the image, it can be partitioned into disjoint regions of uniform texture. This paper proposed a texture image classification algorithm based on Gabor wavelet. In this algorithm, characteristic of every image is obtained through every pixel and its neighborhood of this image. And this algorithm can achieve the information transform between different sizes of neighborhood.Experiments on standard Brodatz texture image dataset show that our proposed algorithm can achieve good classification rates.     

Restoration of images based on subspace optimization accelerating augmented Lagrangian approach

We propose a new fast algorithm for solving a TV-based image restoration problem. Our approach is based on merging subspace optimization methods into an augmented Lagrangian method. The proposed algorithm can be seen as a variant of the ALM (Augmented Lagrangian Method), and the convergence properties are analyzed from a DRS (Douglas-Rachford splitting) viewpoint. Experiments on a set of image restoration benchmark problems show that the proposed algorithm is a strong contender for the current state of the art methods.     

Optimizing multi-item multi-period inventory control system with discounted cash flow and inflation: Two calibrated meta-heuristic algorithms

A mixed binary integer mathematical programming model is developed in this paper for ordering items in multi-item multi-period inventory control systems, in which unit and incremental quantity discounts as well as interest and inflation factors are considered. Although the demand rates are assumed deterministic, they may vary in different periods. The situation considered for the problem at hand is similar to a seasonal inventory control model in which orders and sales happen in a given season. To make the model more realistic, three types of constraints including storage space, budget, and order quantity are simultaneously considered. The goal is to find optimal order quantities of the products so that the net present value of total system cost over a finite planning horizon is minimized. Since the model is NP-hard, a genetic algorithm (GA) is presented to solve the proposed mathematical problem. Further, since no benchmarks can be found in the literature to assess the performance of the proposed algorithm, a branch and bound and a simulated annealing (SA) algorithm are employed to solve the problem as well. In addition, to make the algorithms more effective, the Taguchi method is utilized to tune different parameters of GA and SA algorithms. At the end, some numerical examples are generated to analyze and to statistically and graphically compare the performances of the proposed solving algorithms.     

An efficient self-adaptive model for chaotic image encryption algorithm

In this paper, an efficient self-adaptive model for chaotic image encryption algorithm is proposed. With the help of the classical structure of permutation-diffusion and double simple two-dimensional chaotic systems, an efficient and fast encryption algorithm is designed. However, different from most of the existing methods which are found insecure upon chosen-plaintext or known-plaintext attack in the process of permutation or diffusion, the keystream generated in both operations of our method is dependent on the plain-image. Therefore, different plain-images will have different keystreams in both processes even just only a bit is changed in the plain-image. This design can solve the problem of fixed chaotic sequence produced by the same initial conditions but for different images. Moreover, the operation speed is high because complex mathematical methods, such as Runge–Kutta method, of solving the high-dimensional partial differential equations are avoided. Numerical experiments show that the proposed self-adaptive method can well resist against chosen-plaintext and known-plaintext attacks, and has high security and efficiency.     

Discontinuous Legendre wavelet element method for elliptic partial differential equations

By incorporating the Legendre multiwavelet into the discontinuous Galerkin (DG) method, this paper presents a novel approach for solving Poisson’s equation with Dirichlet boundary, which is known as the discontinuous Legendre multiwavelet element (DLWE) method, derive an adaptive algorithm for the method, and estimate the approximating error of its numerical fluxes. One striking advantage of our method is that the differential operator, boundary conditions and numerical fluxes involved in the elementwise computation can be done with lower time cost. Numerical experiments demonstrate the validity of this method. Furthermore, this paper generalizes the DLWE method to the general elliptic equations defined on a bounded domain and describes the possibilities of constructing optimal adaptive algorithm. The proposed method and its generalizations are also applicable to some other kinds of partial differential equations.     

A variational formulation for physical noised image segmentation

Image segmentation is a hot topic in image science. In this paper we present a new variational segmentation model based on the theory of Mumford-Shah model. The aim of our model is to divide noised image, according to a certain criterion, into homogeneous and smooth regions that should correspond to structural units in the scene or objects of interest. The proposed region-based model uses total variation as a regularization term, and different fidelity term can be used for image segmentation in the cases of physical noise, such as Gaussian, Poisson and multiplicative speckle noise. Our model consists of five weighted terms, two of them are responsible for image denoising based on fidelity term and total variation term, the others assure that the three conditions of adherence to the data, smoothing, and discontinuity detection are met at once. We also develop a primal-dual hybrid gradient algorithm for our model. Numerical results on various synthetic and real images are provided to compare our method with others,these results show that our proposed model and algorithms are effective.     

A segmentation procedure of the pervious area of the aorta artery from CT images without contrast medium

In this paper, we develop an algorithm for the segmentation of the pervious lumen of the aorta artery in computed tomography (CT) images without contrast medium, a challenging task due to the closeness gray levels of the different zones to segment. The novel approach of the proposed procedure mainly resides in enhancing the resolution of the image by the application of the algorithm deduced from the mathematical theory of sampling Kantorovich operators. After the application of suitable digital image processing techniques, the pervious zone of the artery can be distinguished from the occluded one. Numerical tests have been performed using 233 CT images, and suitable numerical errors have been computed and introduced ex novo to evaluate the performance of the proposed method. The above procedure is completely automatic in all its parts after the initial region of interest (ROI) selection. The main advantages of this approach relies in the potential possibility of performing diagnosis concerning vascular pathologies even for patients with severe kidney diseases or allergic problems, for which CT images with contrast medium cannot be achieved.     

Contrast enhancement for image by WNN and GA combining PSNR with information entropy

A new contrast enhancement algorithm for image is proposed combining genetic algorithm (GA) with wavelet neural network (WNN). In-complete Beta transform (IBT) is used to obtain non-linear gray transform curve so as to enhance global contrast for an image. GA determines optimal gray transform parameters. In order to avoid the expensive time for traditional contrast enhancement algorithms, which search optimal gray transform parameters in the whole parameters space, based on gray distribution of an image, a classification criterion is proposed. Contrast type for original image is determined by the new criterion. Parameters space is, respectively, determined according to different contrast types, which greatly shrink parameters space. Thus searching direction of GA is guided by the new parameter space. Considering the drawback of traditional histogram equalization that it reduces the information and enlarges noise and background blur in the processed image, a synthetic objective function is used as fitness function of GA combining peak signal-noise-ratio (PSNR) and information entropy. In order to calculate IBT in the whole image, WNN is used to approximate the IBT. In order to enhance the local contrast for image, discrete stationary wavelet transform (DSWT) is used to enhance detail in an image. Having implemented DSWT to an image, detail is enhanced by a non-linear operator in three high frequency sub-bands. The coefficients in the low frequency sub-bands are set as zero. Final enhanced image is obtained by adding the global enhanced image with the local enhanced image. Experimental results show that the new algorithm is able to well enhance the global and local contrast for image while keeping the noise and background blur from being greatly enlarged.     

基于直方图初始化的有效的多区域Mumford-Shah图像分割方法（英文）

The Mumford-Shah energy functional is a successful image segmentation model. It is a non-convex variational problem and lacks of good initialization techniques so far. In this paper, motivated by the fact that image histogram is a combination of several Gaussian distributions, and their centers can be considered as approximations of cluster centers, we introduce a histogram-based initialization method to compute the cluster centers. With this technique, we then devise an effective multi-region Mumford-Shah image segmentation method, and adopt the recent proximal alternating minimization method to solve the minimization problem. Experiments indicate that our histogram initialization method is more robust than existing methods,and our segmentation method is very effective for both gray and color images.     

A Nonlinear Diffusion Equation-Based Model for Ultrasound Speckle Noise Removal

Ultrasound images are contaminated by speckle noise, which brings difficulties in further image analysis and clinical diagnosis. In this paper, we address this problem in the view of nonlinear diffusion equation theories. We develop a nonlinear diffusion equation-based model by taking into account not only the gradient information of the image, but also the information of the gray levels of the image. By utilizing the region indicator as the variable exponent, we can adaptively control the diffusion type which alternates between the Perona–Malik diffusion and the Charbonnier diffusion according to the image gray levels. Furthermore, we analyze the proposed model with respect to the theoretical and numerical properties. Experiments show that the proposed method achieves much better speckle suppression and edge preservation when compared with the traditional despeckling methods, especially in the low gray level and low-contrast regions.