Local fractal geometric features for image segmentation

In this article, features based on fractal geometry are used for segmentation of synthetic and natural scenes. Assuming a fractional Brownian motion model of image regions, we extract, at each pixel, small, one-variable “slices” in each of four directions from which we estimate two features: the fractal dimension and the intercept. While the fractal dimension has received most attention recently as a scale-invariant feature, we show that the intercept is related to the dimension and possesses even better discriminatory power for segmentation purposes when calculations are made on small, one variable windows. These parameters are studied as segmentation features on both composite images of synthetically generated fractional Brownian motion surfaces and on intensity images of natural scenes.     

A machine learning approach for brain image enhancement and segmentation

In brain MRI analysis, image segmentation is commonly used for measuring and visualizing the brain's anatomical structures, for surgical planning, etc. However, due to presence of noise and uncertainty between different tissues in the brain image, the segmentation of brain is a challenging task. This problem is rectified in this article using two stages. In the first stage an enhancement technique called contrast limited fuzzy adaptive histogram equalization (CLFAHE) which is a combination of CLAHE and fuzzy enhancement is used to improve the contrast of MRI Brain images. Contrast of the image is controlled using contrast intensification operator (Clip limit). The second stage deals with the segmentation of enhanced image. The enhanced brain images are segmented using new level‐set method which has the property of both local and global segmentation. Signed pressure force (SPF) function is also used here which stops the contours at weak and blurred edged efficiently.     

An overview of optical flow-based approaches for motion segmentation

The goal of motion segmentation is to segregate a visual scene into independently moving objects. It is an indispensable pre-processing step for various tasks in computer vision and has evolved as an active and flourishing research area in the last few decades. In the sequences captured using a monocular camera, motion segmentation is typically performed by analyzing apparent motion of pixels in the image plane, i.e. the optical flow. Optical flow is generally contemplated as an appropriate representation of image motion. Numerous techniques for reliable flow estimation and subsequent advancements in their framework have been proposed in the last couple of decades and are outlined briefly in this work. The paper attempts to give a summary of diverse optical flow-based approaches used for robust segmentation of static or dynamic scenes containing rigidly moving objects and discusses in brief the shortcomings associated with them.     

Improved quadtree image segmentation approach to region information

Images are full of information and most often, little information is desired for subsequent processing. Hence, region of interest has key importance in image processing. Quadtree image segmentation has been widely used in many image processing applications to locate the region of interest for further processing. There are also variable block-size image coding techniques to effectively reduce the number of transmitted parts. This paper presents quadtree partition technique as a pre-processing step in image processing to determine what part should be more heterogeneous than the others. It also introduces an idea to solve the problem of squared images. Finally, proposed approach is implemented and analysed. The simulation of the Matlab code of the quadtree is represented by all algorithms and the figures. Thus, achieved results are promising in the state of the art.     

Fast geometric transformations for image processing

The algorithms of affine, bilinear, projective, polynomial, and piecewise polynomial transformations of the raster image are suggested. Application of various iterative procedures allows us to reduce considerably the execution time of these transformations in comparison with the programs by the straightforward formulas application.     

Methods for automatic microarray image segmentation

This paper describes image processing methods for automatic spotted microarray image analysis. Automatic gridding is important to achieve constant data quality and is, therefore, especially interesting for large-scale experiments as well as for integration of microarray expression data from different sources. We propose a Markov random field (MRF) based approach to high-level grid segmentation, which is robust to common problems encountered with array images and does not require calibration. We also propose an active contour method for single-spot segmentation. Active contour models describe objects in images by properties of their boundaries. Both MRFs and active contour models have been used in various other computer vision applications. The traditional active contour model must be generalized for successful application to microarray spot segmentation. Our active contour model is employed for spot detection in the MRF score functions as well as for spot signal segmentation in quantitative array image analysis. An evaluation using several image series from different sources shows the robustness of our methods.     

A novel automated magnetic resonance image segmentation approach based on elliptical gamma mixture model for breast lumps detection

This article introduces a novel semisupervised automated segmentation approach for breast magnetic resonance (MR) image on multicore CPU-GPU systems. The basic idea of the proposed method is clustering-based semisupervised classifier devised by elliptical gamma mixture model (EGMM). Parameters of EGMM are identified by the iterative log-expectation maximization (EM) algorithm. The suggested classifier labels the groups of voxels in an input image first and then classifies the image slices using the EGMM. Two different implementations of the proposed algorithm have been developed based on two different types of high-performance computing architectures such as graphics processing units (GPUs) and multicore processors. To realize the real-time segmentation performance of our algorithm with two distinctive architecture, we have tested a set of breast MR images collected from MedPix. Comparison between two architectures in terms of segmentation performance and computational cost is assessed by the analysis of simulation and experimental results.     

红外图像的动态阈值分割

在深入探讨目前图像分割算法的基础上，针对实际红外图像的分割提出了一种新的方法－－动态阈值分割算法。它利用局部空间阈值适度调整全局统计最优阈值，因而其分割阈值是动态的。实验表明该算法能够突出图像中感兴趣的细节，单动态阈值的分割效果相当于常规固定双域值的分割。     

A matrix-free approach for finite-strain hyperelastic problems using geometric multigrid

This work investigates matrix-free algorithms for problems in quasi-static finite-strain hyperelasticity. Iterative solvers with matrix-free operator evaluation have emerged as an attractive alternative to sparse matrices in the fluid dynamics and wave propagation communities because they significantly reduce the memory traffic, the limiting factor in classical finite element solvers. Specifically, we study different matrix-free realizations of the finite element tangent operator and determine whether generalized methods of incorporating complex constitutive behavior might be feasible. In order to improve the convergence behavior of iterative solvers, we also propose a method by which to construct level tangent operators and employ them to define a geometric multigrid preconditioner. The performance of the matrix-free operator and the geometric multigrid preconditioner is compared to the matrix-based implementation with an algebraic multigrid (AMG) preconditioner on a single node for a representative numerical example of a heterogeneous hyperelastic material in two and three dimensions. We find that matrix-free methods for finite-strain solid mechanics are very promising, outperforming linear matrix-based schemes by two to five times, and that it is possible to develop numerically efficient implementations that are independent of the hyperelastic constitutive law.     

A snake‐based approach to automated segmentation of tongue image using polar edge detector

Tongue diagnosis, one of the most important diagnosis methods of Traditional Chinese Medicine, is very competitive as a candidate of remote diagnosis method because of its simplicity and noninvasiveness. Recently, considerable research interests have been given to the development of automated tongue segmentation technologies, which is difficult due to the complexity of pathological tongue, variance of tongue shape, and interference of the lips. In this paper, we propose a novel automated tongue segmentation method via combining polar edge detector and active contour model (ACM) technique. First, a polar edge detector is presented to effectively extract the edge of the tongue body. Then we design an edge filtering scheme to avoid the adverse interference from the nontongue boundary. After edge filtering, a local adaptive edge bi‐thresholding algorithm is introduced to perform the edge binarization. Finally, a heuristic initialization and an ACM are proposed to segment the tongue body from the image. The experimental results demonstrate that the proposed method can segment the tongue body accurately and effectively. A quantitative evaluation on 200 images indicates that the normalized mean distance to the closest point is 0.48%, and the average true positive percent of our method is 97.1%. © 2007 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 16, 103–112, 2006.     

层次式图切分快速分割算法

图切分(Graph Cuts,GC)是近年来兴起的基于图论框架的图像分割方法,该理论的新颖之处在于它的全局最优性和结合多种知识的统一性。但当图像较大时运算非常耗时。该文提出了一种基于GC的层次式图像分割方法。先在低分辨率中用GC以较低的分割代价获取粗尺度的初始分割,再将结果轮廓映射回高分辨率图像中并构造出窄带,进而采用matting思想,在窄带内获取精确分割。实验结果表明,本文方法在确保分割结果准确性的同时,运算速度大幅度提高。     

Efficient image segmentation based on deep learning for mineral image classification

Mineral image segmentation plays a vital role in the realization of machine vision based intelligent ore sorting equipment. However, the existing image segmentation methods still cannot effectively solve the problem of adhesion and overlap between mineral particles, and the segmentation performance of small and irregular particles still needs to be improved. To overcome these bottlenecks, we propose a deep learning based image segmentation method to segment the key areas in mineral images using morphological transformation to process mineral image masks. This investigation explores four aspects of the deep learning-based mineral image segmentation model, including backbone selection, module configuration, loss function construction, and its application in mineral image classification. Specifically, referring to the designs of U-Net, FCN, Seg Net, PSP Net, and DeepLab Net, this experiment uses different backbones as Encoder to building ten mineral image segmentation models with different layers, structures, and sampling methods. Simultaneously, we propose a new loss function suitable for mineral image segmentation and compare CNNs-based segmentation models' training performance under different loss functions. The experiment results show that the proposed mineral image segmentation has excellent segmentation performance, effectively solves adhesion and overlap between adjacent particles without affecting the classification accuracy. By using the Mobile Net as backbone, the PSP Net and DeepLab can achieve a high segmentation performance in mineral image segmentation tasks, and the 15 × 15 is the most suitable size for erosion element structure to process the mask images of the segmentation models.     

Lung computed axial tomography image segmentation using possibilistic fuzzy C-means approach for computer aided diagnosis system

Soft computing is an associate rising field that plays a crucial half in the area of engineering and science. One of the most significant applications of soft computing is image segmentation. It focuses on an exploiting tolerance of imprecision and uncertainty. Segmentation supported soft computing remains a difficult task within the medical field. Medical images are habitually used in the segmentation process to extract the meaningful portions and to know and clarify the condition of the particular patient. In this article, we implement an efficient possibilistic fuzzy C-means (PFCM) approach to segment the lung portion in the computed tomography (CT) image and the result shows that it improves the segmentation accuracy upto 98.5012% and results are compared with existing segmenting approaches like fuzzy possibilistic C-means method, fuzzy bitplane method and so forth. Also, the PFCM approach increases the diagnostic accuracy of the computer aided diagnosis system using CT images. The radiologist may utilize this computer aided diagnosis system results as a second opinion of their diagnosed results.     

Inhomogeneous surface diffusion for image filtering

Most of the recent work on inhomogeneous diffusion in image filtering focuses on diffusing the isotope curve. We present a less familiar approach to the development of inhomogeneous diffusion algorithms in which the image is regarded as a surface in three-space. The magnitude of the surface normal controls a diffusion that evolves the image surface at a speed proportional to its mean curvature. A discrete algorithm to implement this proposed diffusion is introduced, and we show experimentally that the algorithm develops singularities that reveal, preserve, and enhance the underlying signal. If the input signal is an isolated noisy edge, this leads to complete noise removal and enhancement without affecting the edge locality. © 1997 John Wiley & Sons, Inc. Int J Imaging Syst Technol, 8, 450–456, 1997     

利用变分的平面网格图像自适应分割算法

针对管道弯曲度测量系统中照度不均匀的平面网格图像,提出了一种利用变分的自适应阈值分割方法。综合考虑图像的灰度分布和梯度信息,以图像的边缘点作为插值点,构造一个自适应的阈值曲面。在极小化阈值曲面能量函数时,使用变分方法化简Poisson方程,并利用逐次超松弛迭代法求方程的收敛解,从而产生稳定、光滑的阈值曲面,实现对照度不均匀的平面网格图像进行有效分割。为了验证该方法的有效性,进行了图像分割实验,选择超松弛参数为1.5,变分参数为26。并且与常用的最大类间方差法、迭代法和一维最大熵法进行了比较。实验结果表明,对于照度不均匀的平面网格图像,该分割算法的分割效果明显优于其他三种算法,它能准确地分割出平面网格图案。     

用于彩色图像分割的改进遗传FCM算法

本文提出了一种适用于彩色图像分割的遗传模糊C均值聚类(GAFCM)算法.该算法使用Ohta等人提出的彩色特征集中的第一个分量作为图像像素的一维特征向量,并利用由像素空间到特征空间的映射来改进目标函数,从而大大降低了运算量;使用对特征空间结构没有特殊要求的特征距离代替欧氏距离,从而克服了特征空间结构对聚类结果的影响;使用引入FCM优化的遗传算法来搜索最优解,从而提高了搜索速度.实验表明,该算法不但能很好地分割彩色图像,而且具有运算量小、收敛速度快的优点.     

Method of coordinate transformation for adaptive image segmentation

Translated from Izmeritel'naya Tkhnika, No. 12, pp. 9–10, December, 1990.     

Two-scale image decomposition based image fusion using structure tensor

The PET/SPECT image generates functional information of the human brain. In the field of multimodal medical image fusion, the decomposition scheme of PET/SPECT image in pseudo-color is thought to be negligible. In this article, a two-step model for PET/SPECT image decomposition is proposed to achieve contrast enhancement that inherently captures gradient to distinguish individual edge information from detail information. First, sharp structure is preserved using structure tensor on the intensity component of PET/SPECT image. Second, sharp structure in gray is transformed back into the image in pseudo-color by generalized intensity-hue-saturation, one of the color space methods. The combination of structure tensor and generalized intensity-hue-saturation based fusion technique can preserve not only more intensity information but also functional information content. Finally, we demonstrate the effectiveness of our proposed decomposition method in the context of PET/SPECT image and then make a comparison of fusion result by two-scale image fusion method in terms of the full-reference objective metric structural similarity and no-reference objective metric natural image quality evaluator.     

一种适合于多目标检测的图像分割方法

提出一种适合于多目标检测的8邻域图像分割方法,用以获取目标特征量,准确分割图像。在对二值化图像扫描形成目标块的过程中,标记各个目标像素,记录目标的边界点,得出分割目标的面积、周长、质心坐标。利用这些信息,可以选择跟踪一个或多个目标。仿真结果证明了该方法实用可行。     

Kernel-based spectral color image segmentation

In this work, we propose a new algorithm for spectral color image segmentation based on the use of a kernel matrix. A cost function for spectral kernel clustering is introduced to measure the correlation between clusters. An efficient multiscale method is presented for accelerating spectral color image segmentation. The multiscale strategy uses the lattice geometry of images to construct an image pyramid whose hierarchy provides a framework for rapidly estimating eigenvectors of normalized kernel matrices. To prevent the boundaries from deteriorating, the image size on the top level of the pyramid is generally required to be around 75 x 75, where the eigenvectors of normalized kernel matrices would be approximately solved by the Nystr?m method. Within this hierarchical structure, the coarse solution is increasingly propagated to finer levels and is refined using subspace iteration. In addition, to make full use of the abundant color information contained in spectral color images, we propose using spectrum extension to incorporate the geometric features of spectra into similarity measures. Experimental results have shown that the proposed method can perform significantly well in spectral color image segmentation as well as speed up the approximation of the eigenvectors of normalized kernel matrices.