Fuzzy-ART背景抑制的单帧红外弱小目标检测

针对现有背景抑制算法未能有效地抑制背景而导致目标检测率低的问题,提出一种基于模糊自适应共振理论(Fuzzy-ART)进行背景抑制、基于行列k均值(k-means)聚类实现阈值分割的单帧红外弱小目标检测算法.首先依据红外成像原理仿真生成红外弱小目标训练样本;然后采用Fuzzy-ART神经网络建立目标模型,并以此分析各像素点的目标模糊隶属度来抑制背景杂波;最后采用基于行列k-means聚类的自适应阈值分割算法来检测真实目标.实验结果表明,该算法能有效地抑制背景杂波和突显目标,并能有效地提高信噪比检测弱小目标.     

联合形态滤波和MRF模型的红外小目标检测

针对复杂背景下红外弱小目标检测难题,提出一种基于自适应形态滤波和Markov随机场(MRF)模型的小目标检测算法。设计基于图像局部熵优化的自适应形态滤波器,采用该滤波器进行背景杂波抑制和目标增强,利用MRF理论描述图像像素间关系,构造新的势函数和能量函数,建立目标检测识别模型,通过模型计算自动识别出红外图像中的小目标。理论分析和实验结果表明,该算法可在复杂背景下自适应地抑制背景杂波,成功检测出红外小目标。     

基于核模糊聚类多模型LS-SVM背景预测的红外小目标检测

针对复杂背景中小目标的提取问题,提出了一种基于核模糊聚类多模型最小二乘支持向量机背景预测的红外小目标检测算法。首先,对训练样本用最近邻聚类法进行划分,获取聚类个数和初始聚类中心,并用核模糊C均值算法(KFCM)对聚类中心进行优化;其次,用LS-SVM计算模糊模型的回归参数,利用回归参数预测图像背景;之后,将原图像和预测图像相减得到残差图像;最后,依据最大类间绝对差选取阈值,从残差图像中分割出小目标。实验结果表明:文中算法相比传统基于模糊C均值(FCM)的小目标检测算法检测性能更优越。     

一种基于邻域滤波的星空图像背景杂波抑制算法

针对空间图像弱小目标检测和质心高精度定位问题,提出一种能最大限度保持目标边缘的背景杂波抑制算法。首先用最小二乘拟合估计背景均值和方差,再通过四邻域滤波区分背景和目标,最后通过阈值分割将目标边缘中过小像素滤除,在保留完整目标边缘的同时最大限度抑制了噪声,由于邻域面积较小且运算量相对较小,该算法具有很好的实时性和工程实用性。     

改进的基于区域的运动目标分割方法

针对视频监控系统，提出了一种改进的基于区域的运动目标分割方法。与传统方法相比，在运动检测阶段，结合时域差分和背景差分进行运动检测。并通过自适应方法进行背景更新；在差分图像二值化时，采用自适应阈值方法来代替传统的手工确定阈值法；对于区域分割，使用基于加权平方欧式距离的均值聚类算法代特传统的均值聚类算法。实验结果表明该改进方法比传统方法具有更好的实时性、鲁棒性和有效性。     

融入类贡献抑制因子的灰度级模糊C均值图像分割

基于灰度级模糊C均值图像分割算法具有分割速度快的优势。由于无损检测图像中背景类和目标类差异较大,该算法不能有效地将目标分割出来,故提出改进的基于灰度级的模糊C均值算法。构建了一种与类大小反向相关的类贡献抑制因子表达式,将之融入目标函数后能够降低较大类对目标函数的贡献,这可避免较小类的聚类中心受较大类的影响而靠近较大类的聚类中心。最小化新的目标函数可得新形式的隶属度和聚类中心表征形式。采用类大小差异较大的无损检测图像进行试验,结果显示本文算法得到的分割图像视觉效果良好,而且指标G_mean也更高,进一步提升了基于灰度级模糊C均值算法适应能力。     

彩色图像分割方法及其在农业中的应用

根据作物生长状态参数检测的特点,采用了一种基于混合颜色空间的模糊C均值聚类分割方法来提取目标以便测量.该方法对传统模糊C均值聚类算法中存在的一些问题进行了改进,首先在HSV空间分析H直方图确定出最佳聚类数,并在Lab空间初始化聚类中心,最终在Lab空间对图像进行分割来得到目标图像.将该方法应用到作物生长状态参数的检测中来提取目标,相比其他方法取得了较好的结果.     

能量累积与均值漂移聚类结合的红外小目标检测方法

研究红外图像中弱小目标的检测问题,提出了一种基于能量累积与均值漂移聚类的红外小目标检测方法。首先利用滑动窗口处理实现图像序列中目标能量积累,去除图像中的随机噪声,提高信噪比;然后选用不同尺度的核带宽对原始图像进行两次均值漂移聚类滤波,将两次滤波所得的图像灰度进行差分来实现背景抑制,提高目标与背景的对比度;之后根据图像的统计特性确定阈值,用门限分割方法提取目标区域,实现候选目标的准确定位;最后利用序列图像中目标运动的连续性和轨迹的一致性筛选出真正的目标。该算法通过选用不同尺度的核带宽进行聚类来得到目标及背景图像,背景抑制的同时也滤除了噪声。实验结果表明,该方法能快速有效地提取复杂背景条件下的红外小目标。     

能量累积与均值漂移聚类结合的红外小目标检测方法

研究红外图像中弱小目标的检测问题,提出了一种基于能量累积与均值漂移聚类的红外小目标检测方法。首先利用滑动窗口处理实现图像序列中目标能量积累,去除图像中的随机噪声,提高信噪比;然后选用不同尺度的核带宽对原始图像进行两次均值漂移聚类滤波,将两次滤波所得的图像灰度进行差分来实现背景抑制,提高目标与背景的对比度;之后根据图像的统计特性确定阈值,用门限分割方法提取目标区域,实现候选目标的准确定位;最后利用序列图像中目标运动的连续性和轨迹的一致性筛选出真正的目标。该算法通过选用不同尺度的核带宽进行聚类来得到目标及背景图像,背景抑制的同时也滤除了噪声。实验结果表明,该方法能快速有效地提取复杂背景条件下的红外小目标。     

核空间直觉模糊局部C-均值聚类分割算法研究

针对现有直觉模糊C-均值聚类仅适合呈团状数据的不足,采用非线性函数将数据样本从欧式空间映射至再生希尔伯特高维特征空间,得到核空间直觉模糊聚类算法;同时考虑相邻像素的相互影响,将邻域像素融入核空间直觉模糊聚类的最优化目标函数中,经数学推导便得到嵌入像素局部信息的核空间直觉模糊聚类分割算法。图像分割测试结果表明,核直觉模糊C-均值聚类分割法相比现有直觉模糊C-均值聚类分割法能获得更满意的分割效果;同时,嵌入局部信息的核直觉模糊C-均值聚类分割法表现出良好的抗噪鲁棒性。     

Adaptive k-means clustering algorithm for MR breast image segmentation

Image segmentation is vital for meaningful analysis and interpretation of the medical images. The most popular method for clustering is k-means clustering. This article presents a new approach intended to provide more reliable magnetic resonance (MR) breast image segmentation that is based on adaptation to identify target objects through an optimization methodology that maintains the optimum result during iterations. The proposed approach improves and enhances the effectiveness and efficiency of the traditional k-means clustering algorithm. The performance of the presented approach was evaluated using various tests and different MR breast images. The experimental results demonstrate that the overall accuracy provided by the proposed adaptive k-means approach is superior to the standard k-means clustering technique.     

基于免疫网络的k-means文档聚类算法研究

提出了一种把人工免疫网络(aiNet)和k-means算法结合的文档聚类算法.先把文档集预处理成向量集表示,基于向量之间的余弦相似度,用aiNet算法对文档进行聚类,用得到的相似度矩阵初始化k-means的聚类中心,再用k-means算法对文档聚类.实验结果表明,该算法是可行的,并且能改善聚类质量.     

小波神经网络自学习算法用于红外图像分割

在红外动目标序列图像跟踪过程中,由于目标本身的红外特征具有较大的不可预测性,使ATR系统在目标探测阶段产生大量的虚警讯息。因此,必须设法在复杂背景抑制段将虚警探测讯息滤除掉。提出了一种新颖的基于小波神经网络构架的FLIR图像分割技术,旨在将小波变换的时-频局域特性和神经网络的自学习能力相结合,从而使FLIR图像的分割算法具有较强的逼近和容错能力。该算法在FLIR-ATR系统中得到应用,对于FLIR目标图像轮廓的提取和抑制杂散背景方面获得了良好的效果。     

A new integrated on-line fuzzy clustering and segmentation methodology with adaptive PCA approach for process monitoring and fault detection and diagnosis

A new on-line fuzzy clustering-based algorithm is developed using integration of an adaptive principal component analysis approach with a weighted fuzzy C-means (WFCM) methodology for process fault detection and diagnosis (FDD) applications. The proposed algorithm is based on the segmentation of measured multivariate time series process data through a sliding window scheme being realized in a bottom-up cluster merging approach to enable detection of probable changes embedded in their hidden structure. The method recursively maintain updated PCA models and their corresponding fuzzy membership functions based on the most recent arrival of each independent chunk of process data. The extracted chunk features are then retained in the memory to be merged using a new on-line fuzzy C-means methodology before incoming of the following chunks of data. A new formula is then presented for cluster merging improvement by incorporating an on-line weight to address the issue of cluster’s weight updating in the on-line WFCM methodology. The cluster merging mechanism is coordinated by a compatibility criterion, utilizing both similarities of the adapted clusters-based PCA models and their center closeness. The proposed algorithm has been evaluated on an artificial case study and Tennessee Eastman benchmark process plant. The observed performances demonstrate promising capabilities of the proposed algorithm to successfully detect and diagnose the introduced fault scenarios.     

Feature based fuzzy inference system for segmentation of low-contrast infrared ship images

Segmentation of infrared ship target is important for sea surveillance system. However, as a result of the deficiencies of infrared images, the segmentation of infrared ship image becomes a challenge. For the purpose of addressing this problem, a feature based infrared ship image segmentation method utilizing the fuzzy inference system is proposed. Firstly, the intensity feature is extracted by applying unimodal threshold, which could preserve the low-contrast pixels in the infrared images. Secondly, the local spatial feature is extracted by employing saliency detection, region growing and morphology processing, which could express the shape of the target. Thirdly, the global spatial feature is extracted by utilizing partial region growing and weighted distance transformation, which could suppress the background. Then these features are fuzzified using accommodative ways and prior knowledge. And in light of the fuzzy rules based upon expert knowledge, these fuzzified features are integrated in fuzzy inference system. Finally, the complete target could be directly segmented from the output of the fuzzy inference system. Experimental results illustrate that the proposed method could effectively extract more intact targets from the low-contrast infrared ship images. Additionally, the proposed method outperforms some existed segmentation methods.     

Iterative infrared ship target segmentation based on multiple features

This paper presents an efficient method for ship target segmentation in infrared (IR) images. It consists of mainly two procedures: iterative image segmentation and ship target selection. First, based on the intensity distribution of an IR image, we design a global background subtraction filter (GBSF) to suppress the background, and an adaptive row mean subtraction filter (ARMSF) to enhance the target. After iteratively applying these two filters, we can obtain a proper threshold for image segmentation. Second, based on the geometric properties of the ship target, we construct four shape features and a selection criterion to identify the real target and remove the non-target regions. Experimental results demonstrate that the proposed method can effectively segment ship targets from different backgrounds in IR images. The advantage of the proposed method over the others in the previous literatures is validated in both visual and quantitative comparisons, especially for IR images with low contrast and uneven intensities.     

基于机器视觉的液晶屏Mura缺陷检测方法

通过分析液晶屏中缺陷检测的必要性和人工检测的不足,研究一种基于机器视觉的液晶屏Mura缺陷在线检测系统。针对液晶屏中的Mura缺陷区域和周围背景对比度低、边缘模糊、形状各异、整体亮度不均等特点,建立模拟人工检测的成像系统。提出单帧图像背景建模和背景差分方法,该方法能有效解决液晶屏的亮度不均问题,同时增强Mura缺陷的特征信息。然后基于最大稳定极值区域(Maximally Stable Extremal Region,MSER),提出Mura缺陷自适应阈值缺陷分割方法,建立一个全自动缺陷在线检测的视觉系统。实验结果表明,所提检测算法能很好地解决液晶屏亮度不均的问题,准确地对Mura缺陷进行分割定位,算法的鲁棒性好。并且该系统人工干预少,效率高,能实现在线自动检测。     

广义模糊熵图像阈值分割参数选取的ADE方法

针对广义模糊熵图像阈值分割参数不能自动选取,提出自适应差分进化（Adaptive Differential Evolution,ADE）的广义模糊熵图像阈值分割方法。利用自适应差分进化算法作为优化工具来选取广义模糊熵阈值分割所需要的最佳参数,引入自适应变异算子和提出交叉概率自适应函数对优化过程进行控制,通过把参数带入广义模糊熵的补函数得到图像的阈值,进而得到图像最优分割。为验证其有效性与可行性,分别同基本图像质量评价准则的模糊熵图像阈值分割算法和粒子群优化广义模糊熵图像阈值分割算法相比较,实验表明,针对不同细节的图片,该算法所得分割结果多数情况下背景信息更少,目标信息更清晰,用时更短,分割更稳定且效果良好。     

基于双模型融合的自适应目标跟踪算法

针对目标跟踪过程中的光照变化、背景混乱和目标形变等问题,提出一种背景抑制的HS直方图和核相关滤波双模型融合的自适应跟踪算法。首先引入非线性核相关滤波跟踪模型;其次提出背景抑制的HS颜色直方图跟踪模型,通过分离亮度分量以减小光照干扰,并采用背景加权突出目标信息;然后提出一种自适应融合策略,根据目标与背景的HS特征相似度来动态调整两个模型融合权重,以降低背景混乱和目标姿态变化的影响;最后针对目标尺度变化问题,采用尺度金字塔估计策略进行解决。实验表明,与现有算法相比,提出的算法能更好降低光照、背景混乱等复杂因素干扰,鲁棒性更强。