基于隶属度光滑约束的模糊C均值聚类算法

传统的FCM聚类算法未利用图像的空间信息,在分割叠加了噪声的MR图像时分割效果不理想。本文考虑到脑部MR图像真实的灰度值具有分片为常数的特性,按照合理利用图像空间信息的原则,对传统的FCM聚类算法进行了改进,增加了使隶属度趋向于分片光滑的约束项,得到了新的聚类算法。通过对模拟脑部MR图像和临床脑部MR图像的分割实验结果表明,本文提出的新算法比传统的FCM算法等多种图像分割算法有更精确的图像分割能力,并且运算简单、运算速度快、稳健性好。     

一种分割脑部磁共振图像的FCM改进算法

脑部MRI的快速准确分割是脑部疾病临床诊断过程的关键步骤之一。针对FCM算法部分参数设置影响分割结果和鲁棒性差的缺陷,提出一种基于非局部空间信息的快速模糊C均值核聚类改进算法,并应用于脑部MRI分割中。依次通过直方图、K-means算法、核函数、基于积分图的非局部空间信息解决了部分初始参数值难以控制、抗噪性差和运算效率低等问题。实验表明,该算法错分率低至2.0%,运行时间平均减少至13.89 s。     

基于多目标规划的模糊C均值聚类算法

模糊C均值聚类算法(FCM)是一种非常经典的非监督聚类技术,已被广泛地应用到医学图像分割。由于传统的FCM聚类算法在分割图像时仅利用了图像的灰度信息,未利用图像的空间信息,在分割叠加了噪声的磁共振(MR)图像时分割效果不理想。考虑到脑部MR图像真实的灰度值具有分片为常数的特性,按照合理利用图像空间信息的原则,对传统的FCM聚类算法进行了改进,引入多目标规划的概念,提出了一种新的,更加合理的应用图像空间信息的聚类算法。实验结果表明,应用该算法可以有效地分割含有噪声的图像。     

Pavement image segmentation based on fast FCM clustering with spatial information in internet of things

Pavement image segmentation needs to deal with noise spots and has real time requirement. The original FCM method only considers the pixel’s gray value and doesn’t fully utilize the spatial information of the image. A new fast FCM algorithm is proposed, and it has noise immunity. By comparing with other FCM algorithms, it achieves better segmentation results through less iteration times and more rapid runtime. It is an effective and noise-resistant algorithm for pavement image segmentation from video multimedia in IOT (internet of things) platform.

     

An adaptive spatial information-theoretic fuzzy clustering algorithm for image segmentation

This paper presents an adaptive spatial information-theoretic fuzzy clustering algorithm to improve the robustness of the conventional fuzzy c-means (FCM) clustering algorithms for image segmentation. This is achieved through the incorporation of information-theoretic framework into the FCM-type algorithms. By combining these two concepts and modifying the objective function of the FCM algorithm, we are able to solve the problems of sensitivity to noisy data and the lack of spatial information, and improve the image segmentation results. The experimental results have shown that this robust clustering algorithm is useful for MRI brain image segmentation and it yields better segmentation results when compared to the conventional FCM approach.     

Fuzzy c-means clustering with weighted image patch for image segmentation

Fuzzy c-means (FCM) clustering has been widely used in image segmentation. However, in spite of its computational efficiency and wide-spread prevalence, the FCM algorithm does not take the spatial information of pixels into consideration, and hence may result in low robustness to noise and less accurate segmentation. In this paper, we propose the weighted image patch-based FCM (WIPFCM) algorithm for image segmentation. In this algorithm, we use image patches to replace pixels in the fuzzy clustering, and construct a weighting scheme to able the pixels in each image patch to have anisotropic weights. Thus, the proposed algorithm incorporates local spatial information embedded in the image into the segmentation process, and hence improve its robustness to noise. We compared the novel algorithm to several state-of-the-art segmentation approaches in synthetic images and clinical brain MR studies. Our results show that the proposed WIPFCM algorithm can effectively overcome the impact of noise and substantially improve the accuracy of image segmentations.     

基于MICO+FCM的MRI脑组织分割

针对MRI中存在的强度不均匀问题以及颅骨组织对于脑部组织提取所造成的影响,为了解决对特定脑部组织的研究问题,提出一个MICO+FCM脑组织分割算法。算法首先利用基于MICO的能量最小化算法对脑部MRI进行强度不均匀性估计和矫正,并且通过该算法完成对图像的初步分割,然后通过区域生长算法对图像中的颅骨组织进行去除,再利用FCM算法完成脑部组织中脑白质和脑灰的分割提取。通过仿真表明,相对于传统FCM算法及其它图像分割算法,提出的MICO+FCM脑组织分割算法在分割准确率和分割效率上均有所提升。     

基于K-means和图割的脑部MRI分割算法

为了克服原始图割算法在用户选定的像素种子点较少情况下,目标边界容易出现错分这一现象,本文提出了基于K-means和图割(Graph cut,GC)算法相结合的交互式K-均值图割（K-means and graph cut,KMGC）算法,对脑部核磁共振图像（Magnetic resonance image,MRI） 进行交互式操作,该算法通过K-means聚类,对脑部MRI的灰度不均匀性进行了处理,在此基础上,再使用图割算法进一步对脑部MRI进行细化,从而达到有效地分割脑白质和脑 灰质的目的。本文分别在仿真和真实的脑部MRI数据上进行了大量的实验,分别从定量分析和定性分析两个角度对实验结果进行了分析,并与其他分割算法进行了对比,对比实验结果标明,KMGC算法能够有效地对脑部MRI进行分割,并在分割效果上优于其他算法。     

Fuzzy c-means clustering with non local spatial information for noisy image segmentation

As an effective image segmentation method, the standard fuzzy c-means (FCM) clustering algorithm is very sensitive to noise in images. Several modified FCM algorithms, using local spatial information, can overcome this problem to some degree. However, when the noise level in the image is high, these algorithms still cannot obtain satisfactory segmentation performance. In this paper, we introduce a non local spatial constraint term into the objective function of FCM and propose a fuzzy cmeans clustering algorithm with non local spatial information (FCM_NLS). FCM_NLS can deal more effectively with the image noise and preserve geometrical edges in the image. Performance evaluation experiments on synthetic and real images, especially magnetic resonance (MR) images, show that FCM_NLS is more robust than both the standard FCM and the modified FCM algorithms using local spatial information for noisy image segmentation.     

基于小波图像融合算法和改进FCM聚类的MR脑部图像分割算法

针对很多基于模糊C均值(FCM)的图像分割算法存在对噪声敏感和分割轮廓不清晰等问题,提出一种基于小波变换图像融合算法和FCM聚类算法的MR医学图像分割算法。在图像分割系统的第一阶段,利用Haar小波多分辨率特性保持像素间的空间信息;第二阶段,利用小波图像融合算法对得到的多分辨率图像和原始图像进行融合,进而增强被处理图像的清晰度并降低噪声;第三阶段,利用改进型FCM技术对所处理的图像进行分割。在BrainWeb数据集上进行实验,与现有相关算法相比,提出的算法具有较高的分割精度,且对噪声的鲁棒性比较强,处理时间也没有明显增加。     

非局部降噪快速模糊C-均值聚类算法

传统的模糊C-均值聚类算法未利用图像的空间信息,在分割迭加了噪声的MR图像时分割精度较差。采用了既能有效去除噪声又能较好地保持图像边缘特征的非局部降噪方法,结合基于图像灰度直方图聚类分析的快速模糊C-均值聚类算法,得到了一种具有较高分割精度的图像快速分割算法。通过对模拟图像、仿真脑部MR图像和临床脑部MR图像的分割实验,表明提出的新算法比已有的快速模糊C-均值聚类算法有更精确的图像分割能力。     

Fuzzy C-mean based brain MRI segmentation algorithms

Brain image segmentation is one of the most important parts of clinical diagnostic tools. Fuzzy C-mean (FCM) is one of the most popular clustering based segmentation methods. In this paper, a review of the FCM based segmentation algorithms for brain MRI images is presented. The review covers algorithms for FCM based segmentation algorithms, their comparative evaluations based on reported results and the result of experiments for neighborhood based extensions for FCM.     

利用邻域差异性信息的FCM改进算法

为了克服模糊C均值（FCM）无法处理图像噪声的缺点以及常用改进算法分割不足,提出了一种利用邻域差异性信息的FCM改进算法。利用高斯函数来合理刻画邻域间像素的空间位置和灰度差异特性,实现对中心像素隶属度的调整,达到分割噪声图像的目的。实验证明,该算法可以有效地处理高斯和椒盐噪声,在去除噪声的同时较完整地保留了图像的细节,其分割效果优于几种常用FCM改进算法。     

基于分裂式K均值聚类的图像分割方法

模糊C均值聚类(FCM)算法是一种有效的无监督图像分割方法,适用于任意分类数,不需要预知图像特征,但其聚类效果直接受待分类样本噪声和分类初始条件的影响。因此,提出了一种适用于彩色图像分割的分裂式K均值聚类(FKM)算法,该算法首先使用中值滤波对分类样本去噪,然后使用一种分裂聚类法对图像样本进行预分类,得到一组样本集初始划分,最后以这组划分为起点,使用基于概率距离的K均值聚类对图像分割进行迭代优化。实验结果表明,该算法可以避免FCM的误分类,诸如陷于中心死区、中心重叠和局部极小值,而且提高了分割速度。     

基于空间信息的可能性模糊C均值聚类遥感图像分割

可能性模糊C均值(PFCM)聚类算法作为模糊C均值(FCM)聚类算法的一种改进算法,能在一定程度上克服FCM算法对噪声的敏感性;但由于PFCM没有考虑像元间的空间信息,对含有较大噪声的图像分割效果依然不理想。为此,提出一种新的基于空间信息的PFCM算法(SPFCM),克服了PFCM算法对含有较大噪声的图像分割效果不佳的缺点。通过对人工图像和IKONOS遥感图像进行分析,结果表明,SPFCM算法无论是在视觉上还是在分割正确率上都优于传统的FCM算法、PFCM算法及两种加入空间信息的FCM算法;对于含有高斯噪声和盐椒噪声的图像,平均分割正确率高达99.71%,是一种去噪效果较好的图像分割算法。     

融入空间信息的医学图像优质分割

传统的FCM分割算法只考虑到图像的灰度信息,而忽略了灰度的空间信息,对于迭加了噪声的图像,难以得到准确的结果。从马尔可夫随机场（MRF）中得到启示,考虑到图像灰度信息及其空间分布出发,提出了一种新的基于邻域（Neighbor）信息FCM分割算法,即NFCM算法。实验结果表明该算法所得到的目标图像的边界特征保持完好,图像边界细腻、连续且定位性能好。     

An automated hybrid approach using clustering and nature inspired optimization technique for improved tumor and tissue segmentation in magnetic resonance brain images

In the domain of human brain image analysis, identification of tumor region and segmentation of tissue structures tend to be a challenging task. Automated segmentation of Magnetic Resonance (MR) brain images would be of great assistance to radiologist, as they minimize the complication evolved due to human interface and offer quicker segmentation results. Automated algorithms offer minimal time duration and lesser manual intervention to a radiologist during clinical diagnosis. Moreover, larger volumes of patient data could be assessed with the aid of an automated algorithm and one such algorithm is proposed through this research to identify the tumor region bounded between normal tissue regions and edema portions. The proposed algorithm offers a better support to a radiologist in the process of diagnosing the pathologies, since; it utilizes both optimization and clustering techniques. Bacteria Foraging Optimization (BFO) and Modified Fuzzy K − Means algorithm (MFKM) are the optimization and clustering techniques used to render efficient MR brain image analysis. The proposed combinational algorithm is compared with Particle Swarm Optimization based Fuzzy C − Means algorithm (PSO based FCM), Modified Fuzzy K − Means (MFKM) and conventional FCM algorithm. The suggested methodology is evaluated using the comparison parameters such as sensitivity, Specificity, Jaccard Tanimoto Co − efficient Index (TC) and Dice Overlap Index (DOI), computational time and memory requirement. The algorithm proposed through this paper has produced appreciable values of sensitivity and specificity, which are 97.14% and 93.94%, respectively. Finally, it is found that the proposed BFO based MFKM algorithm offers better MR brain image segmentation and provides extensive support to radiologists.     

基于形态学重建改进的FCM算法

传统的FCM(fuzzy c-means)算法可以准确的分割多数无噪声图像,但对噪声图像非常敏感。针对于此类问题,提出了一种基于形态学重建的改进FCM算法。首先利用形态学闭合重建算子对含噪图像进行光滑化。然后利用基于邻域信息的改进FCM算法对合成图像及医学图像进行分割处理,最终得出了更加精确的分割结果。通过与其它两类算法进行数值实验对比,验证了所提出算法的有效性和实用性。     

改进FCM和LFP相结合的白细胞图像分类

研究白细胞图像分类识别中有效的图像分割与特征提取方法,以提高白细胞图像的正确识别率.由于某些白细胞(粒细胞)中颗粒的存在,严重影响细胞核与细胞质区域的正确分割,通过将空间信息与核函数融入模糊C-均值聚类(FCM)算法,提出一种改进的FCM算法.应用该算法对白细胞图像进行分割,并采用数学形态学方法对分割后的图像进行处理,获得了很好的分割效果,解决了粒细胞的质核分割难题.对于细胞的纹理特征提取,通过对局部二值模式(LBP)中阈值参数的模糊化,建立了基于局部模糊模式(LFP)的纹理特征提取算法.运用本文方法进行图像分割和纹理提取,以支持向量机作为分类器,对CellAtlas的100幅白细胞图像进行了分类识别的实验,结果表明白细胞的正确识别率达到93％.     

改进的FCM与局部信息相结合的图像分割

传统的EM算法和FCM算法分割精度低,时间消耗大。为解决以上不足,提出了一种基于EM、FCM和KCN三种算法相结合的全新的图像分割算法。该算法有较好的分割精度。考虑到图像会受到噪声的干扰,在改进算法的基础上又引入图像的局部信息。首先利用图像的局部信息重塑图像的灰度直方图,增强了像素的类间散布性和类内紧凑性,然后让改进的算法在重塑图像上执行。实验结果表明,该算法具有很好的分割效果和较强的抗噪性能。