共查询到16条相似文献,搜索用时 126 毫秒
1.
二维直方图创建的新方法实现图像自动分割 总被引:3,自引:0,他引:3
针对图像的自动分割问题,利用二维熵建立的一般方法和二维熵的性质提出创建二维直方图的两种新方法.第一种方法选择4邻域中心像素灰度值和其余像素的灰度最大值来构造二维直方图,第二种方法选择4邻域中心像素灰度值和其余像素的灰度最小值来构造二维直方图.对典型图像进行对比试验表明,与传统方法相比,采用由4邻域中心像素灰度值和其余像素的灰度最大值构造二维直方图的方法,可以很好地保留目标的细节信息,而采用由4邻域中心像素灰度值和其余像素的灰度最小值构造二维直方图的方法,可以在保留目标轮廓信息的基础上,很好地抑制噪音. 相似文献
2.
《中国计量学院学报》2015,(4)
提出一种改进的图像分割算法SWFFCM(special weight fast fuzzy C-means algorithm),该方法将需要聚类的二维像素点投影到一维灰度直方图空间,利用不同灰度值图像空间像素离散程度的区别,对一维灰度直方图进行线性加权,每一个灰度值变量使用四分位相对离差系数作为其权值.实验表明,算法减少了FCM(fuzzy C-means algorithm)算法的迭代数量,提高了图像聚类分割速度,减少了像素点错分比例,从而提高了图像的分割精度. 相似文献
3.
针对模糊C-均值算法对初始值的依赖,容易陷入局部最优值的缺点,本文提出将量子蚁群算法与FCM聚类算法结合,首先利用量子蚁群算法的全局性和鲁棒性以及快速收敛的优点确定图像的初始聚类中心和聚类个数,再将所得结果作为FCM聚类算法的初始参数,然后用FCM聚类算法对医学图像进行分割。实验结果表明,该方法有效解决了FCM算法对初始参数的依赖,克服了FCM算法及蚁群算法容易陷入局部极值的的缺点,而且在分割速度和精度上得到了较大提高。 相似文献
4.
5.
6.
用于彩色图像分割的改进遗传FCM算法 总被引:4,自引:0,他引:4
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. 相似文献
7.
8.
一种改进的二维最小交叉熵图像分割方法 总被引:2,自引:1,他引:1
针对当前二维最小交又熵阈值法存在计算复杂度高等问题,提出了一种改进的二维最小交叉熵阈值分割方法.首先,依据图像的含噪声类型选择邻域模板并建立相应的二维直方图来提高分割效果;然后,对二维最小交又熵公式进行推导和简化处理,利用定义的数组运算推导出新型递推算法,再确定图像及其邻域图像的实际灰度级别范围,并用这种新算法在所求的灰度级别范围内搜索最佳阈值向量来降低计算复杂度;最后,使用关键阈值一对滤波后的图像进行分割达到最佳的分割效果.仿真实验结果表明,与当前的二维最小交又熵阁值分割法相比,本文提出的方法不仅分割性能及抗噪性能更强,而且分割时间大大减少,小于0.05 s. 相似文献
9.
一种基于FCM的图像分割方法 总被引:1,自引:0,他引:1
提出一种新的图像分割方法 FWFCM(fast walvet fuzzy C-means method),该方法对图像像素点的灰度进行模糊隶属度的分析,将需要聚类的像素空间投影到灰度直方图空间,从而减少了经典FCM算法的迭代计算量,提高了算法的收敛速度;并且利用小波变换的多分辨率的分析,抑制噪声点对图像分割的影响,提高了图像分割的精度. 相似文献
10.
11.
C. Prabu S.V.M.G. Bavithiraja S. Narayanamoorthy 《International journal of imaging systems and technology》2016,26(1):24-28
A process of splitting the image into pixel bands is the image segmentation. As medical imaging contain uncertainties, there are difficulties in classification of images into homogeneous regions. There is a need for segmentation algorithm for removing the noise from the medical image segmentation. The very popular algorithm is Fuzzy C‐Means (FCM) algorithm used for image segmentation. Fuzzy sets, rough sets, and the combination of fuzzy and rough sets play a prominent role in formalizing uncertainty, vagueness, and incompleteness in diagnosis. But it will use intensity values only which will be highly sensitive to noise. In this article, an Intuitionistic FCM (IFCM) algorithm is presented for clustering. Intuitionistic fuzzy (IF) sets are generalized sets and their elements are characterized by a membership value as well as nonmembership value. This IFCM has an uncertainty parameter which is called hesitation degree and a new objective function is integrated in the standard FCM based on IF entropy. The IFCM will provide better performance than FCM for image segmentation. 相似文献
12.
Fuzzy C means integrated with spatial information and contrast enhancement for segmentation of MR brain images 下载免费PDF全文
R. Meena Prakash R. Shantha Selva Kumari 《International journal of imaging systems and technology》2016,26(2):116-123
This paper proposes a fully automated method for MR brain image segmentation into Gray Matter, White Matter and Cerebro‐spinal Fluid. It is an extension of Fuzzy C Means Clustering Algorithm which overcomes its drawbacks, of sensitivity to noise and inhomogeneity. In the conventional FCM, the membership function is computed based on the Euclidean distance between the pixel and the cluster center. It does not take into consideration the spatial correlation among the neighboring pixels. This means that the membership values of adjacent pixels belonging to the same cluster may not have the same range of membership value due to the contamination of noise and hence misclassified. Hence, in the proposed method, the membership function is convolved with mean filter and thus the local spatial information is incorporated in the clustering process. The method further includes pixel re‐labeling and contrast enhancement using non‐linear mapping to improve the segmentation accuracy. The proposed method is applied to both simulated and real T1‐weighted MR brain images from BrainWeb and IBSR database. Experiments show that there is an increase in segmentation accuracy of around 30% over the conventional methods and 6% over the state of the art methods. 相似文献
13.
针对采集到的人民币号码图像都是彩色图像并携带有噪声这一现象,本文提出基于 HSI空间和改进的 C-means算法的人民币彩色号码图像分割方法。选用 HSI颜色空间作为彩色分割空间,在 HSI空间内,将 HSI的 3-D搜索问题转化为 3个 1-D的搜索问题,求取图像在 3个 1-D方向上的灰度直方图,该方法根据图像当前点 3×3邻域内每个像素灰度值与当前点灰度值差值的大小情况,确定聚类算法中当前点的灰度值 p(m)的值,采用 C-means聚类算法分别确定文字和非文字的聚类中心,利用欧式距离进行人民币号码前景和背景的聚类判断。该方法直接对彩色人民币号码图像进行分割,考虑了当前点与邻域像素点之间的相互关系,具有一定的自适应性。实验结果表明,提出的号码图像分割方法不受图像噪声和局部边缘变化的影响,且变换后数据量减少,易于计算,该方法对字母和数字的分割都有效,鲁棒性较强。 相似文献
14.
15.
基于无序分割投影策略与重力模型的图像加密算法 总被引:2,自引:2,他引:0
目的解决当前图像算法因其像素置乱和扩散操作与明文无关,导致其抗明文攻击能力较弱,且其置乱过程存在周期性,使其安全性不佳等问题。方法提出基于无序分割投影策略与重力模型的图像加密算法。首先对输入明文进行无序分割,获取重叠子块,并构建每个子块的位置坐标计算模型,输出图像子块的位置;根据明文像素量计算Kent映射的初值,通过迭代Kent映射获取随机序列组;定义位置置乱机制,对重叠子块进行混淆;再引入分割投影策略,互换每个置乱子块中的像素位置,再对其重组,输出置乱密文;通过设计像素质量变化函数替换重力模型的固定质量,改进重力模型,对置乱密文完成像素加密。结果实验结果显示与当前图像加密技术相比,文中算法具有更高的安全性,输出密文中的相邻两像素间的关联度最低,具有更强的抗明文攻击与剪切攻击性能。结论所提加密算法能够较好地用于图像信息安全传输,具有较好的应用价值。 相似文献
16.
Tumor detection in T1, T2, FLAIR and MPR brain images using a combination of optimization and fuzzy clustering improved by seed‐based region growing algorithm 下载免费PDF全文
G. Vishnuvarthanan M. Pallikonda Rajasekaran N. Anitha Vishnuvarthanan T. Arun Prasath M. Kannan 《International journal of imaging systems and technology》2017,27(1):33-45
Tumor and Edema region present in Magnetic Resonance (MR) brain image can be segmented using Optimization and Clustering merged with seed‐based region growing algorithm. The proposed algorithm shows effectiveness in tumor detection in T1 ‐ w, T2 – w, Fluid Attenuated Inversion Recovery and Multiplanar Reconstruction type MR brain images. After an initial level segmentation exhibited by Modified Particle Swarm Optimization (MPSO) and Fuzzy C – Means (FCM) algorithm, the seed points are initialized using the region growing algorithm and based on these seed points; tumor detection in MR brain images is done. The parameters taken for comparison with the conventional techniques are Mean Square Error, Peak Signal to Noise Ratio, Jaccard (Tanimoto) index, Dice Overlap indices and Computational Time. These parameters prove the efficacy of the proposed algorithm. Heterogeneous type tumor regions present in the input MR brain images are segmented using the proposed algorithm. Furthermore, the algorithm shows augmentation in the process of brain tumor identification. Availability of gold standard images has led to the comparison of the suggested algorithm with MPSO‐based FCM and conventional Region Growing algorithm. Also, the algorithm recommended through this research is capable of producing Similarity Index value of 0.96, Overlap Fraction value of 0.97 and Extra Fraction value of 0.05, which are far better than the values articulated by MPSO‐based FCM and Region Growing algorithm. The proposed algorithm favors the segmentation of contrast enhanced images. © 2017 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 27, 33–45, 2017 相似文献