Context dependent graph-based method for laser cladding image thresholding

For segmentation method to be useful it must be fast, easy to use, and produce high quality segmentations, but few algorithms can offer this in various conditions and applications. In this paper, we propose a context dependent graph-based method for transition region extraction and thresholding. The graph-based approach is introduced into image thresholding, and context dependent graph is constructed from a given image, which can adaptively extract the pixel context and shape information because of the scalable neighborhood. Then an edge weight function is defined as the measure of possible transition pixels, and a robust fully automatic scheme for the optimal threshold is also presented. The proposed approach is validated both quantitatively and qualitatively. Compared with the traditional state-of-art algorithms on synthetic and real images, as well as laser cladding images, the experimental results suggest that the new proposal is efficient and effective.     

An anisotropic images segmentation and bias correction method

Intensity inhomogeneities cause considerable difficulty in the quantitative analysis of magnetic resonance (MR) images. Thus, bias field correction is a necessary step before quantitative analysis of MR data can be undertaken. This paper presents an anisotropic approach to bias correction and segmentation for images with intensity inhomogeneities and noise. Intensity-based methods are usually applied to estimate the bias field; however, most of them only concern the intensity information. When the images have noise or slender topological objects, these methods cannot obtain accurate results or bias fields. We use structure information to construct an anisotropic Gibbs field and combine the anisotropic Gibbs field with the Bayesian framework to segment images while estimating the bias fields. Our method is able to capture bias of quite general profiles. Moreover, it is robust to noise and slender topological objects. The proposed method has been used for images of various modalities with promising results.     

A robust level set method based on local statistical information for noisy image segmentation

The paper presents an improved local region-based active contour model for image segmentation, which is robust to noise. A data fitting energy functional is defined in terms of curves and the energy terms which are based on the differences between the local average intensity and the global intensity means. Then the energy is incorporated into a level set variational formulation, from which a curve evolution equation is derived for energy minimization. And then the level set function is regularized by Gaussian filter to keep smooth and eliminate the re-initialization. By using the local statistical information, the proposed model can handle with noisy images. The proposed model is first presented as a two-phase level set formulation and then extended to a multi-phase one. Experimental results show desirable performances of the proposed model for both noisy synthetic and real images, especially with high level noise.     

A parametric imaging approach for the segmentation of ultrasound data

When an ultrasonic examination is performed, a segmentation tool would often be very useful, either for the detection of pathologies, the early diagnosis of cancer or the follow-up of the lesions. Such a tool must be both reliable and accurate. However, because of the relatively reduced quality of ultrasound images due to the speckled texture, the segmentation of ultrasound data is a difficult task. We have previously proposed to tackle the problem using a multiresolution Bayesian region-based algorithm. For computation time purposes, a multiresolution version has been implemented. In order to improve the quality of the segmentation, we propose to perform the segmentation not only from the envelope image but to combine more information about the properties of the tissues in the segmentation process. Several acoustical parameters have thus been computed, either directly from the images or from the radio-frequency (RF) signal.

In a previous study, two parametric images were involved in the segmentation process. The parameter represented the integrated backscatter (IBS) and the mean central frequency (MCF), which is a measurement related to the attenuation of ultrasound waves in the media. In this study, parameters representative of the scattering conditions in the tissue are evaluated in the multiparametric segmentation process. They are extracted from the K-distribution (,b) and the Nakagami distribution (m,Ω) and are related to the local density of scatterers (,m), the size of the scatterers (b) and the backscattering properties of the medium (Ω).

The acoustical features are calculated locally on a sliding window. This procedure allows to built parametric mapping representing the particular characteristics of the medium. To test the influence of the acoustical parameters in the segmentation process, a set of numerical phantoms has been computed using the Field software developed by J.A. Jensen. Each phantom consists in two regions with two different acoustical properties: the density of scatterers and the scattering amplitude. From both the simulated RF signals and envelope images, the parameters have been computed; their relevance to represent a particular characteristic of the medium is evaluated. The segmentation has been processed for each phantom. The ability of each parameter to improve the segmentation results is validated. A agar–gel phantom has also been created, in order to test the accuracy of the parameters in conditions closer to the in vivo ultrasound imaging. This phantom contains four inclusions with different concentrations of silica. A B&K ultrasound device provides the RF data. The quantification of the segmentation quality is based on the rate of correctly classified pixels and it has been computed for all the parameters either from the field images or the phantom images. The large improvement in the segmentation results obtained reveals that the multiparametric segmentation scheme proposed in this study can be a reliable tool for the processing of noisy ultrasound data.     

Adaptive segmentation of magnetic resonance images with intensity inhomogeneity using level set method

It is a big challenge to segment magnetic resonance (MR) images with intensity inhomogeneity. The widely used segmentation algorithms are region based, which mostly rely on the intensity homogeneity, and could bring inaccurate results. In this paper, we propose a novel region-based active contour model in a variational level set formulation. Based on the fact that intensities in a relatively small local region are separable, a local intensity clustering criterion function is defined. Then, the local function is integrated around the neighborhood center to formulate a global intensity criterion function, which defines the energy term to drive the evolution of the active contour locally. Simultaneously, an intensity fitting term that drives the motion of the active contour globally is added to the energy. In order to segment the image fast and accurately, we utilize a coefficient to make the segmentation adaptive. Finally, the energy is incorporated into a level set formulation with a level set regularization term, and the energy minimization is conducted by a level set evolution process. Experiments on synthetic and real MR images show the effectiveness of our method.     

Sharpening enhancement of ultrasound images using contourlet transform

The furry regions of ultrasound images are to be enhanced for good quality visual perception. This paper proposes a contourlet transform (CT) based sharpening technique (ST) for contrast enhancement in ultrasound (US) images. While sharpening, noise emphasize is the drawback of the classical ST methods. The proposed ST is operated on the multiscale, multidirectional CT decomposition of the underlying US image. The new ST not only sharpens the US image but also control the noise effect with tunable parameters. The results are compared with common unsharp masking and recently proposed nonlinear unsharp masking. The parameters like enhancement measure, structural similarity, and blind image quality measure evaluate the improved performances of the proposed technique.     

A nonrigid registration algorithm for longitudinal breast MR images and the analysis of breast tumor response

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) can estimate parameters relating to blood flow and tissue volume fractions and therefore may be used to characterize the response of breast tumors to treatment. To assess treatment response, values of these DCE-MRI parameters are observed at different time points during the course of treatment. We propose a method whereby DCE-MRI data sets obtained in separate imaging sessions can be co-registered to a common image space, thereby retaining spatial information so that serial DCE-MRI parameter maps can be compared on a voxel-by-voxel basis. In performing inter-session breast registration, one must account for patient repositioning and breast deformation, as well as changes in tumor shape and volume relative to other imaging sessions. One challenge is to optimally register the normal tissues while simultaneously preventing tumor distortion. We accomplish this by extending the adaptive bases algorithm through adding a tumor-volume preserving constraint in the cost function. We also propose a novel method to generate the simulated breast magnetic resonance (MR) images, which can be used to evaluate the proposed registration algorithm quantitatively. The proposed nonrigid registration algorithm is applied to both simulated and real longitudinal 3D high resolution MR images and the obtained transformations are then applied to lower resolution physiological parameter maps obtained via DCE-MRI. The registration results demonstrate the proposed algorithm can successfully register breast MR images acquired at different time points and allow for analysis of the registered parameter maps.     

A snake-based method for segmentation of intravascular ultrasound images and its in vivo validation

Image segmentation for detection of vessel walls is necessary for quantitative assessment of vessel diseases by intravascular ultrasound. A new segmentation method based on gradient vector flow (GVF) snake model is proposed in this paper. The main characteristics of the proposed method include two aspects: one is that nonlinear filtering is performed on GVF field to reduce the critical points, change the morphological structure of the parallel curves and extend the capture range; the other is that balloon snake is combined with the model. Thus, the improved GVF and balloon snake can be automatically initialized and overcome the problem caused by local energy minima. Results of 20 in vivo cases validated the accuracy and stability of the segmentation method for intravascular ultrasound images.     

复杂背景彩色图像中的文字分割

提出了一种纹理和连通域特征相结合的彩色文字分割方法。基于文字的边缘纹理特征,粗略分割出可能的文字区域。计算各区域内的颜色统计直方图,进行二类颜色聚类。分析文字连通域的几何特征,滤除非文字连通域。计算文字连通域像素点的垂直投影,估计文字的宽度和文字间隔,判断是否为文字排列,对粗分割的文字区域进行校验,确定文字区域的边框。通过自然场景下拍摄的100幅图像的文字分割实验,证明了该文字定位和分割方法的有效性。     

A novel multi-scale segmentation algorithm for high resolution remote sensing images based on wavelet transform and improved JSEG algorithm

Considering the difficulties in image segmentation caused by the complexity of diverse ecological environments and various artificial targets in high resolution remote sensing images, especially in city scene, and in order to overcome the limitations existing in the traditional segmentation algorithm, JSEG (J-Segmentation), for high resolution remote sensing image segmentation and to further improve the segmentation accuracy, WJSEG (Wavelet-JSEG), a novel multi-scale segmentation algorithm based on wavelet transform, is proposed, which is an improved JSEG algorithm. WJSEG is an improved form of JSEG in relation to three aspects, including color quantization, multi-scale segmentation and region merging by introducing the multi-scale analysis tool based on wavelet transform. Experiments have been conducted on high resolution SPOT 5 pan-sharpened multispectral image and IKONOS panchromatic image. These experimental results were compared with those gained by the traditional JSEG algorithm and the famous commercial software named eCognition, which validated the effectiveness and reliability of the proposed WJSEG algorithm.     

基于混合能量模型水平集的合成孔径声纳图像分割方法

本文讨论了合成孔径声纳图像分割问题。首先介绍了Chan-Vese模型水平集方法,针对该模型存在的边界定位和重复初始化等问题,提出了一种改进的水平集方法。该方法的能量模型由区域信息项、边界信息项和距离约束函数构成的内部能量项三部分混合形成,既兼顾了全局优化特性和局部定位精度,又避免了水平集函数重复初始化,提高了运算效率。实验结果表明,该模型对于噪声干扰严重、边缘模糊的合成孔径声纳图像分割效果良好。     

An entropy-based approach to automatic image segmentation of satellite images

An entropy-based image segmentation approach is introduced and applied to color images obtained from Google Earth. Segmentation refers to the process of partitioning a digital image in order to locate different objects and regions of interest. The application to satellite images paves the way to automated monitoring of ecological catastrophes, urban growth, agricultural activity, maritime pollution, climate changing and general surveillance. Regions representing aquatic, rural and urban areas are identified and the accuracy of the proposed segmentation methodology is evaluated. The comparison with gray level images revealed that the color information is fundamental to obtain an accurate segmentation.     

利用对称区域生长算法实现三维ICT图像的快速分割

图像分割作为一种基础的分析手段在工业计算机断层(Industrial Computed Tomography,ICT)检侧中有着广泛的应用.随着CT扫描方式从二维断层扫描向三维立体扫描的发展,对于CT图像的分析也由二维图像处理发展为三维序列图像处理,所以传统的图像分割手段已经不能很好地适应这种需求了.以目前在计算机视觉...     

Classification of visible and infrared hyperspectral images based on image segmentation and edge-preserving filtering

The classification of hyperspectral images with a few labeled samples is a major challenge which is difficult to meet unless some spatial characteristics can be exploited. In this study, we proposed a novel spectral-spatial hyperspectral image classification method that exploited spatial autocorrelation of hyperspectral images. First, image segmentation is performed on the hyperspectral image to assign each pixel to a homogeneous region. Second, the visible and infrared bands of hyperspectral image are partitioned into multiple subsets of adjacent bands, and each subset is merged into one band. Recursive edge-preserving filtering is performed on each merged band which utilizes the spectral information of neighborhood pixels. Third, the resulting spectral and spatial feature band set is classified using the SVM classifier. Finally, bilateral filtering is performed to remove “salt-and-pepper” noise in the classification result. To preserve the spatial structure of hyperspectral image, edge-preserving filtering is applied independently before and after the classification process. Experimental results on different hyperspectral images prove that the proposed spectral-spatial classification approach is robust and offers more classification accuracy than state-of-the-art methods when the number of labeled samples is small.     

Multicontext wavelet-based thresholding segmentation of brain tissues in magnetic resonance images

A novel segmentation method based on wavelet transform is presented for gray matter, white matter and cerebrospinal fluid in thin-sliced single-channel brain magnetic resonance (MR) scans. On the basis of the local image model, multicontext wavelet-based thresholding segmentation (MCWT) is proposed to classify 2D MR data into tissues automatically. In MCWT, the wavelet multiscale transform of local image gray histogram is done, and the gray threshold is gradually revealed from large-scale to small-scale coefficients. Image segmentation is independently performed in each local image to calculate the degree of membership of a pixel to each tissue class. Finally, a strategy is adopted to integrate the intersected outcomes from different local images. The result of the experiment indicates that MCWT outperforms other traditional segmentation methods in classifying brain MR images.     

基于均值漂移的遥感图像海陆边界分割算法

光学遥感图像海陆边界分割是海洋近岸目标检测和识别的重要技术基础。由于光学遥感图像分辨率的提高,海陆边界分割存在背景复杂、干扰多等问题。为解决复杂背景下高清遥感图像海陆边界分割问题,提出了一种新的海陆边界分割算法。该方法包含三个部分:使用均值漂移算法将遥感图像处理成若干同质区域;采用一种新的基于扫描线的方法选择海水区域种子像素点,利用区域增长算法填充海水区域;通过连通区域分析的方法分离陆地部分,得到海陆分割结果。实验证明,该方法能够对于复杂背景下的光学遥感图像实现准确、稳定的海陆分割,算法具有较强的鲁棒性和准确性。     

A fully automatic three-step liver segmentation method on LDA-based probability maps for multiple contrast MR images

Automatic 3D liver segmentation in magnetic resonance (MR) data sets has proven to be a very challenging task in the domain of medical image analysis. There exist numerous approaches for automatic 3D liver segmentation on computer tomography data sets that have influenced the segmentation of MR images. In contrast to previous approaches to liver segmentation in MR data sets, we use all available MR channel information of different weightings and formulate liver tissue and position probabilities in a probabilistic framework. We apply multiclass linear discriminant analysis as a fast and efficient dimensionality reduction technique and generate probability maps then used for segmentation. We develop a fully automatic three-step 3D segmentation approach based upon a modified region growing approach and a further threshold technique. Finally, we incorporate characteristic prior knowledge to improve the segmentation results. This novel 3D segmentation approach is modularized and can be applied for normal and fat accumulated liver tissue properties.     

Study on the methods of image enhancement for liver CT images

Image enhancement methods for liver CT images are studied in this paper. The liver region is first segmented from the whole CT image by simply using the characteristics of the gray distribution of the liver. The segmented liver CT image is processed by direct gray stretching, logarithmic transformation and linear stretching with histogram fitting. In addition, the method of selective histogram equalization is proposed to enhance the segmented liver CT image. It is proven from the experimental results that by this two-step method, the visual effect of the segmented image can be effectively improved and the focus is obviously highlighted.     

A segmentation method for noisy photoelectric image

In order to improve the ability of noisy photoelectric image segmentation and satisfy the requirement of human visual apperception, a noisy photoelectric image segmentation method is proposed in this paper. Firstly, the basic principle of FCM algorithm is analyzed in detail. Secondly, on the basis of PCM algorithm, only such pixels affected by noise lesser that centralized in the diagonal area of two-dimensional histogram is actualized image processing, and the probability of the pixel that lie in such area is obtained. Thirdly, objective function, membership matrix and cluster centers are renovated on the basis of PCM algorithm. Finally, experiment contrast between our method and other methods is executed, the results of experiment indicate that our method has relatively better segmentation quality and faster segmentation speed.     

一种基于光学干涉原理的图像分割方法

 介绍了基于光学干涉原理的图像分割理论算法。在计算机上模拟一个均匀相干光源、一个滤波器和一个接收屏。选择强度 相位的转换曲线，将输入图像的强度信息转化成伪相位信息，并显示在滤波器上。利用光源照明滤波器上的相位图，在接收屏上得到其干涉条纹。再通过选择阈值对干涉图进行分割得到二值图，从而实现输入图像的边缘分割。计算结果表明，该方法得到的图像轮廓，与Sobel 算子效果相当。与实验结果对比分析可得，改善硬件并实现良好的分割效果的关键在于：控制光源的相干长度，或增大液晶的点阵间隔，并利用CCD相机和计算机相连，对干涉图进行二值化。