核最小二乘算法检测红外点目标(英文)

对于背景呈非线性变化的复杂图像,用背景预测的方法对红外点目标进行检测时,传统的线性最小二乘法(Least Squares,LS)的效果比较差.文章使用核方法(Kernel Methods,KMs)推导了最小二乘法的非线性版本:核最小二乘算法(Kernel Least Squares,KLS);进一步推导出了更适合动态系统时序预测的指数加权形式的核最小二乘算法(Kemel Exponential wleighted Least Squares,KEWLS).提出了一种基于核方法的红外点目标检测算法,先用KEWLS非线性回归算法预测红外图像背景,再通过自适应门限检测残差图像中的目标,非线性函数回归和红外序列图像检测实验表明核方法较大地改进了算法的非线性函数估计与红外背景预测能力.     

一种基于DA-GMRF的无监督图像分割方法

提出一种基于间断自适应高斯马尔可夫随机场(DA-GMRF)模型的无监督图像分割方法.针对MRF模型中的过平滑问题,利用边缘信息构造能量函数,定义了一种DA-GMRF模型.利用灰度直方图势函数自动确定分类数及分割阈值,进行多阈值分割,得到DA-GMRF模型中标记场的初始化,用Metroplis采样器算法进行标记场的优化,实现了图像的无监督分割.实验结果表明了该方法的有效性.     

基于序贯蒙特卡罗的多线索目标跟踪算法

颜色直方图对噪声和部分遮挡不敏感,当背景颜色与目标颜色相近时,会影响跟踪效果.本文提出一种有效的基于多线索融合的序贯蒙特卡罗图像序列跟踪方法,采用颜色直方图和边缘直方图与序贯蒙特卡罗算法结合起采进行视频跟踪.颜色直方图和边缘直方图一起构建目标观测似然函数.在序贯蒙特卡罗方法的框架下,采用观测模型函数获取图像序列中目标位置的后验概率分布.实验结果表明,结合图像颜色与边缘特征,在序贯蒙特卡罗的框架下可以取得更为有效和稳健的跟踪效果.     

基于FSVM时域背景预测的红外弱小目标检测

本文提出了一种基于模糊支持向量机(FSVM)时域背景预测的红外弱小目标检测方法.首先针对前几帧图像中对应同一位置像素点的灰度值序列,利用模糊支持向量机进行函数拟合,并据此预测下一帧图像在该位置处像素点的灰度值:然后将原始图像与预测图像相减得到预测残差图像,利用基于二维Tsallis-Havrda-Charvat熵的阈值选取快速算法进行分割,并根据小目标运动的连续性和轨迹的一致性进一步分离噪声和小目标.文中给出了实验结果及分析,并与现有的检测红外小目标的空域和时域背景预测算法进行了比较.结果表明,本文提出的算法具有更高的检测概率,明显优于已有的基于背景预测的红外小目标检测算法.     

基于新核函数的支持向量机在物体分类中的应用

在基于视的物体识别中,将图像的局部信息引入到图像的相似性度量,提出了一种新的图像距离度量,并把它嵌入到支持向量机的核函数中,得到了一种新的核函数--基于局部卡方距离(Chi-square distance)的核函数.物体分类实验结果表明,新算法优于非线性支持向量机,区别张量一阶分解(DTROD),稀疏网络模型(SNW)等方法.     

图像插值的改进自适应核回归方法

针对 steering 自适应核回归的插值算法中图像整体灰度值偏离较大和空洞的现象,本文提出了一种基于改进的自适应核回归函数的图像插值算法.该方法根据图像的自相似性原理,通过把图像邻域中像素间几何距离函数融入 steering 自适应核函数中,实现一种改进的自适应核函数,并采用这种核函数对图像进行回归插值.实验结果表明...     

基于小波域局部统计模型的图像去噪方法

提出了一种基于小波域局部统计模型图像去噪方法.该方法利用图像小波子带的方向性特点以及小波系数尺度内和尺度间的相关性:将小波系数尺度内的相关性建模为一种各向异性马尔可夫随机场(Markov Random Field,MRF)先验概率模型,将小波系数尺度间的相关性建模为局部奇异性的条件概率模型.通过在贝叶斯框架中采用这种先验概率模型和条件概率模型可以得到一种具有自适应性的贝叶斯萎缩函数.利用这种萎缩函数可以实现对小波系数的修正.实验结果表明利用该方法进行图像去噪能够取得良好的效果,同时可以有效地保留图像的细节.     

基于小波域多分辨率MRF的声呐图像目标分割

声呐图像受噪声影响严重,分辨率低,传统算法对其目标分割效果较差,为此,提出了小波域多分辨率MRF模型的声呐图像分割算法。小波域多分辨率分析有利于提取声呐图像弱特征信息;每一分辨率中的观测特征采用高斯混合模型建模,尺度内同标记的观测特征用高斯模型建模,用各向同性的双点多级逻辑(Multi-Level Logistic,MLL)模型建模每一尺度的标记场;最后,用迭代条件模式(Iterated Conditional Mode,ICM)实现多分辨率马尔可夫随机场(Multi-Resolution Markov Random Field,MRA-MRF)中能量函数的最优解,获取标记场,完成声呐图像分割。从视觉效果和定量分析两方面验证。对比实验的结果表明,该文算法能有效地提取声呐图像的弱目标信息,较好地将目标区域和背景区域分割出来,具有较高的分割精度和鲁棒性。     

一种运动小目标的自动识别算法

远距离运动小目标的自动识别在军事上有着非常重要的意义,可以应用于远距离监视如搜索和跟踪系统以及防御武器系统.在复杂背景中对低对比度运动小目标的自动捕获与跟踪是非常困难的.主要是由于低对比度的小目标很容易被系统噪声或复杂的背景所淹没.本文提出一种自动检测小目标的算法,首先在图像序列中检测可能的目标,然后根据时空一致性去除假目标.     

红外序列图像的支持向量机分割方法

红外序列图像的准确分割是自动目标识别的关键,而当图像背景复杂时,传统的图像分割技术往往难以满足要求,为此,提出了基于支持向量机的红外序列图像分割方法。序列图像中的部分帧被作为训练样本,通过选择适合的模型参数,运用支持向量机方法建立学习机器,将后续图像帧中的目标从复杂的背景中识别出来,从而实现红外图像分割。实际红外序列图像分割表明,基于支持向量机的图像分割方法不需要复杂的预处理和后处理工作,分割效果理想,对于小目标的图像,识别正确率可达 99%。     

A simple segmentation method for DNA microarray spots by kernel density estimation

The DNA microarray analysis is one of the most important areas in biomedical research. For the accurate analysis of microarray data the process of segmentation, classification of pixels as foreground or background, should be done accurately. In this paper we suggest a kernel density estimation approach for the segmentation of the microarray spot. We estimate the density of n pixel intensities for a given target area by the kernel density estimation, and the resulting kernel density estimate gives bimodal density by appropriate choice of the smoothing parameter. We suggest two modes of the kernel density estimate for n pixel intensities as estimates of the foreground (mode with larger value) and the background (mode with smaller value) intensity, respectively. The segmentation method proposed in this paper is easy and simple to use, robust to the shape of spot, and very accurate. This research was supported by Korea Science and Engineering Foundation grant (R14-2003-002-01000-0).     

基于FCM和图割的交互式图像分割方法

为了提高在前景和背景颜色相似情况下图像的分割效果,提出了一种基于模糊C均值聚类(FCM)和图割的交互式图像分割方法。首先,利用分水岭算法对图像进行预处理,将图像分成多个小区域,用区域代替像素点进行分析。然后,采用模糊C均值算法对用户标记的前景区域和背景区域分别进行聚类分析,挖掘用户交互所提供的隐藏信息。用未标记区域的颜色分量到前景区域及背景区域类心的最小距离表示相似能量,用未标记区域与其相邻区域的相关性表示先验能量。最后,利用最大流/最小割算法求能量函数的全局最优解。与其他方法相比,该文方法具有较好的分割性能,能从前景背景相似的图像中较精确地提取感兴趣的物体,且用户操作简单。     

A novel Markov random field model based on region adjacency graph for T1 magnetic resonance imaging brain segmentation

Tissue segmentation in magnetic resonance brain scans is the most critical task in different aspects of brain analysis. Because manual segmentation of brain magnetic resonance imaging (MRI) images is a time‐consuming and labor‐intensive procedure, automatic image segmentation is widely used for this purpose. As Markov Random Field (MRF) model provides a powerful tool for segmentation of images with a high level of artifacts, it has been considered as a superior method. But because of the high computational cost of MRF, it is not appropriate for online processing. This article has proposed a novel method based on a proper combination of MRF model and watershed algorithm in order to alleviate the MRF's drawbacks. Results illustrate that the proposed method has a good ability in MRI image segmentation, and also decreases the computational time effectively, which is a valuable improvement in the online applications. © 2017 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 27, 78–88, 2017     

视频监控中基于在线多核学习的目标再现识别

在非重叠多摄像机或单摄像机视频监控中,识别跟踪目标的再次出现很重要.针对传统支持向量机方法在特征融合方面的缺陷,本文提出了一种新的基于在线多核学习的人体目标再现识别方法.该方法对跟踪目标视频前景图像序列提取具有互补性的视觉单词树直方图和全局颜色直方图二种特征,再采用多核学习方法在线训练人体目标视觉外观,从而得到多核特征融合模型.实验结果表明,该方法能快速训练人体目标外观模型,满足视频监控的实时要求,多核融合模型获得了比单一特征模型和单核支持向量机方法更高的识别性能.     

基于函数变换的水下图像目标分割和特征提取

针对海水信道的特殊性以及成像环境的复杂性,对视觉系统的图像处理和特征提取带来的影响,提出了一种基于模糊变换的图像分割和基于函数变换的特征提取方法,以克服水下不确定因素给目标识别带来的困难,并对其进行了仿真试验.试验结果表明,此方法在对深海烟囱图像的分割和特征提取上能够取得好的效果,可有效地克服水下图像灰度分布不均匀和环境不确定因素的干扰,实现了难于分类判别的深海热液喷口目标的区分.     

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.     

基于最小类内差和最大类间差的图像分割算法研究

针对现有二维Otsu图像分割算法未考虑到目标和背景这二类像素自身的内聚性,提出一种新的自适应二维Otsu算法。该算法通过待分割图像的二维直方图,分别统计类内的绝对差、类间总体离差以反映类内、类间的离散度,从而构造出新阈值判别函数。通过一种改进的遗传算法优化二维阈值判别函数,自动得到较理想的分割阈值。实验结果表明,与其它阈值判别函数相比,通过优化新的阈值判别函数得到的二维阈值,具有了较好的分割效果,能够更好地保留了目标物的轮廓,而且计算量小。     

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.