基于FastICA的高光谱图像目标分割

针对高光谱图像目标识别与分类的应用背景,提出了一种基于快速独立成分分析的高光谱图像目标分割算法.通过引入虚拟维数对图像中的目标端元数量进行估计,利用基于非监督正交子空间投影的异常端元提取算法自动获取目标端元光谱,并将其作为快速独立成分分析的初始混合矩阵.采用最小噪声分量变换对原始数据进行降维,利用快速独立成分分析从降维后的主成分中依次提取出图像中的独立分量.最后,对各独立分量进行恒虚警率检测与形态学滤波,从而得到最终的目标分割结果.对AVIRIS型高光谱图像的实验结果表明,该方法可有效探测出图像中的目标,并可获得较好的分割结果.     

基于FastICA的高光谱图像目标分割

针对高光谱图像目标识别与分类的应用背景,提出了一种基于快速独立成分分析的高光谱图像目标分割算法.通过引入虚拟维数对图像中的目标端元数量进行估计,利用基于非监督正交子空间投影的异常端元提取算法自动获取目标端元光谱,并将其作为快速独立成分分析的初始混合矩阵.采用最小噪声分量变换对原始数据进行降维,利用快速独立成分分析从降维后的主成分中依次提取出图像中的独立分量.最后,对各独立分量进行恒虚警率检测与形态学滤波,从而得到最终的目标分割结果.对AVIRIS型高光谱图像的实验结果表明,该方法可有效探测出图像中的目标,并可获得较好的分割结果.     

基于流形学习和空间信息的改进N-FINDR端元提取算法

光谱端元提取是对高光谱数据进一步分析的重要前提。由于双向反射分布函数(BRDF),像元内的多重散射和亚像元成分的异质性等因素,高光谱图像中的混合像元实际上是非线性光谱混合。传统的端元提取算法是以线性光谱混合模型为基础,因此提取的端元精度不高。在光谱非线性混合的基础上,提出一种将流形学习与空间信息结合的改进N-FINDR端元提取算法。首先通过自适应的局部切空间排列算法寻找嵌入在高维非线性数据空间的本质的低维结构,将原始高光谱数据非线性降维到低维空间。接着利用地物分布具有连续性的特点,通过增大空间同质区域的像元的权重进行空间预处理。最后通过寻找最大单形体体积进行端元提取。提出算法很好的解决了高光谱遥感数据非线性结构,并利用了空间信息,提高了端元提取的精度。模拟数据实验和真实高光谱遥感数据实验结果均表明,采用该算法得到的结果优于顶点成分分析(VCA) 算法、基于测地线距离的最大单形体体积(GSVM)算法和空间预处理的N-FINDR(SPPNFINDR)算法。     

一种改进的快速N-FINDR端元提取算法

为了解决传统N-FINDR算法计算量大,提取结果对噪声和初始端元选取敏感,且容易将异常点作为端元而造成误提取的问题,提出一种改进的快速N-FINDR端元提取算法.该方法通过光谱距离提取并去除高光谱图像中的冗余信息,减少N-FINDR提取端元的搜索范围,平滑噪声影响,并自适应剔除异常点,通过最大化光谱距离选取N-FINDR的初始端元,避免了随机选择的盲目性.采用合成数据和真实高光谱数据进行仿真分析并与现有算法进行对比,结果表明,本文算法能在噪声与奇异点干扰下正确提取端元,其提取效率和鲁棒性均优于现有算法.     

光谱最小信息熵的高光谱影像端元提取算法

端元提取是混合像元分解的关键,研究其算法在高精度的地物识别、丰度反演和定量遥感等方面具有重要意义。通过研究高光谱遥感影像光谱特征,结合信息熵理论,应用高斯分布函数,建立了一种新的高光谱影像端元提取算法,即光谱最小信息熵(spectral minimum shannon entropy,SMSE)算法。将该算法应用于AVRIRS高光谱影像的端元光谱提取,并经过与美国地质勘探局(United States Geological Survey,USGS)波谱库中的数据匹配,得知其提取端元的精度较高。同时,通过与经典的纯净像元指数(pixel purity index,PPI)和连续最大角凸锥(sequential maximum angle convex cone,SMACC)等端元提取算法进行实验比较和结果综合分析,发现光谱最小信息熵算法提取端元光谱效率更高、精度更好。此外,分别利用SMACC和SMSE提取Hyperion高光谱影像端元,得出SMSE的端元提取效果好于SMACC,从而可认为SMSE算法具有一定普适性。     

小波包分解支持下的高光谱混合像元盲分解

提出将小波包辅助下子带分解的独立成分分析用于高光谱混合像元盲分解.利用小波包分解改进独立成分分析技术,并考虑到高光谱数据的特点提出了高光谱混合像元盲分解方法,该方法能克服独立成分分析方法要求端元光谱统计独立带来的问题.利用两组合成数据和三组室内实测数据对本算法进行测试,证明了本算法能较为准确的提取端元光谱波形和端元丰度,其准确度明显优于独立成分分析方法.该方法为高光谱遥感影像的盲分解提供了一条新的途径.     

小波包分解支持下的高光谱混合像元盲分解

提出将小波包辅助下子带分解的独立成分分析用于高光谱混合像元盲分解.利用小波包分解改进独立成分分析技术,并考虑到高光谱数据的特点提出了高光谱混合像元盲分解方法,该方法能克服独立成分分析方法要求端元光谱统计独立带来的问题.利用两组合成数据和三组室内实测数据对本算法进行测试,证明了本算法能较为准确的提取端元光谱波形和端元丰度...     

基于最大化N维立体光谱角的高光谱端元提取

提出了一种基于最大化N维立体光谱角(Maximum N-dimensional Solid Spectral Angle,MNSSA)的端元提取方法.该方法通过计算N个光谱向量在高维欧几里得空间的光谱夹角,定量衡量该N个光谱向量的独立性.在线性混合模型假设下,端元光谱向量的欧几里得空间夹角大于混合像素构成的夹角.MNSSA法不受待提取端元数目及波段数目的限制,对光谱向量幅值变化不敏感,能够克服阴影及光照因素对端元幅值的影响.使用模拟数据及AVIRIS(Airborne Visible/Infrared Imaging Spectrometer)获取的真实高光谱数据对MNSSA端元提取法及现有基于几何的端元提取法进行了对比评价.仿真结果表明,MNSSA法能够克服阴影影响因子对端元幅值的影响,端元提取准确率优于现有端元提取法,且具有良好的抗噪声性能,能显著降低高光谱数据的重构误差.     

高光谱遥感图像光谱解混的独立成分分析技术

高光谱遥感在对地球陆地、海洋、大气的观测中发挥着重要作用,高光谱遥感图像分析的关键是提取像元光谱内部各物质成分及其含量,即光谱解混。独立成分分析提供了一种先进的技术手段,在很少先验知识的前提下,实现端元(物质成分)光谱及其丰度(含量)的同时提取。但丰度约束破坏了各成分独立的前提条件,导致了独立成分分析的局限性。针对这一问题,提出了丰度约束下总体相关性最小化的解决方案,并指出总体相关性最小化下的理想角度,通过设计角度修正的独立成分分析算法把各成分调整到理想角度上。利用模拟数据与真实数据算法进行检验,结果表明：经过角度修正后,独立成分分析突破了原有的局限性,有助于进一步提高独立成分分析技术在光谱分析中的有效性。     

基于标志点等距映射的高光谱图像端元提取算法

针对Isomap-NFINDR端元提取算法复杂度高、占用内存多、效率低的缺点,提出一种基于标志点选择Isomap的快速端元提取算法。该方法采用最大最小距离法来选取初始的K个聚类中心点,并采用光谱夹角距离SAD代替欧式距离来进行聚类分割;根据图像的空间特性,从去除聚类的边界点后剩余点间隔抽取距离聚类中心距离最小的N个点作为标志点。真实高光谱图像实验结果表明,提出的算法精度接近原始的基于Isomap-NFINDR算法,而效率提高了将近60倍。     

基于Gabor小波变换的ICA火灾图像纹理识别算法

针对火灾图像纹理识别问题,提出了基于Gabor小波变换的ICA火灾图像纹理识别算法,并根据火灾图像纹理识别特点进行了优化。首先用不同尺度和方向的Gabor滤波器对待识别图像滤波,得到其特征图像,然后将特征图像转化成特征向量作为ICA的输入,得到基矢量子空间,再将测试图像经过Gabor滤波器的特征向量投影到ICA子空间中得到系数向量作为目标识别特征,最后用支持向量机进行识别。通过与Gabor滤波器法和ICA方法的对比实验,表明该算法可以在火灾纹理图像的识别率上比传统方法提高5%以上,为火灾图像识别提供了一种新思路。     

An improved fast fractal image compression using spatial texture correlation

This paper utilizes a spatial texture correlation and the intelligent classification algorithm (ICA) search strategy to speed up the encoding process and improve the bit rate for fractal image compression. Texture features is one of the most important properties for the representation of an image. Entropy and maximum entry from co-occurrence matrices are used for representing texture features in an image. For a range block, concerned domain blocks of neighbouring range blocks with similar texture features can be searched. In addition, domain blocks with similar texture features are searched in the ICA search process. Experiments show that in comparison with some typical methods, the proposed algorithm significantly speeds up the encoding process and achieves a higher compression ratio, with a slight diminution in the quality of the reconstructed image; in comparison with a spatial correlation scheme, the proposed scheme spends much less encoding time while the compression ratio and the quality of the reconstructed image are almost the same.     

Efficient compression of motion-compensated sub-images with Karhunen-Loeve transform in three-dimensional integral imaging

An approach to highly enhance the compression efficiency of the integral images by applying the Karhunen-Loeve transform (KLT) algorithm to the motion-compensated sub-images is proposed. The sub-images transformed from the elemental images picked-up from the three-dimensional (3D) object might represent the different perspectives of the object. Thus, the similarity among the sub-images gets better than that among the elemental images, so that an improvement of compression efficiency of the sub-images could be obtained. However, motion vectors occurred among the sub-images might result in an additional increase of image data to be compressed. Accordingly, in this paper, motion vectors have been estimated and compensated in all sub-image in advance. Then the KLT algorithm was applied to these motion-compensated sub-images for compression. It is shown from some experimental results that compression efficiency of the proposed method has been improved up to 24.44%, 40.62%, respectively, on the average compared to that of the conventional KLT compression method and that of the JPEG.     

Performance of blind source separation algorithms for fMRI analysis using a group ICA method

Independent component analysis (ICA) is a popular blind source separation technique that has proven to be promising for the analysis of functional magnetic resonance imaging (fMRI) data. A number of ICA approaches have been used for fMRI data analysis, and even more ICA algorithms exist; however, the impact of using different algorithms on the results is largely unexplored. In this paper, we study the performance of four major classes of algorithms for spatial ICA, namely, information maximization, maximization of non-Gaussianity, joint diagonalization of cross-cumulant matrices and second-order correlation-based methods, when they are applied to fMRI data from subjects performing a visuo-motor task. We use a group ICA method to study variability among different ICA algorithms, and we propose several analysis techniques to evaluate their performance. We compare how different ICA algorithms estimate activations in expected neuronal areas. The results demonstrate that the ICA algorithms using higher-order statistical information prove to be quite consistent for fMRI data analysis. Infomax, FastICA and joint approximate diagonalization of eigenmatrices (JADE) all yield reliable results, with each having its strengths in specific areas. Eigenvalue decomposition (EVD), an algorithm using second-order statistics, does not perform reliably for fMRI data. Additionally, for iterative ICA algorithms, it is important to investigate the variability of estimates from different runs. We test the consistency of the iterative algorithms Infomax and FastICA by running the algorithm a number of times with different initializations, and we note that they yield consistent results over these multiple runs. Our results greatly improve our confidence in the consistency of ICA for fMRI data analysis.     

Development of Fluorescence-Linked Immunosorbent Assay for Icariin

We have been looking for a faster and simpler method for traditional Chinese medicine and natural product assay. In this study, we developed a fluorescent immunoassay approach to detect icariin (ICA) using a fluorescently labelled monoclonal antibody. The ICA-specific antibody was purified by the caprylic acid-ammonium sulphate method and then labelled with rhodamine B isothiocyanate (RBITC). Subsequently, an indirect competitive fluorescence-linked immunosorbent assay (icFLISA) was developed to detect ICA using RBITC-labelled anti-ICA MAbs. The RBITC-labelled monoclonal antibody was highly specific for ICA. The fluorescence assay demonstrated an effective ICA measurement range of 1.28 ng/mL to 20 μg/mL (R² = 0.9946) with relative standard deviations below 10% for both intra-assay and inter-assay repeatability and precision. This icFLISA for ICA is simple, rapid, and sensitive, with a 20-fold greater linear range and a 10-fold lower limit of detection than with the previously developed indirect competitive enzyme-linked immunosorbent assay (ELISA). Thus, this study establishes a useful method for detecting ICA, enabling in vivo visualization research. In the future, FLISA can be also used to assay the concentrations of ICA in biological samples, as well as to investigate the pharmacokinetics of ICA in different tissues to explore the targets of ICA in vivo.     

Denoising of chaotic signal using independent component analysis and empirical mode decomposition with circulate translating

In this paper, a new method to reduce noises within chaotic signals based on ICA(independent component analysis)and EMD(empirical mode decomposition) is proposed. The basic idea is decomposing chaotic signals and constructing multidimensional input vectors, firstly, on the base of EMD and its translation invariance. Secondly, it makes the independent component analysis on the input vectors, which means that a self adapting denoising is carried out for the intrinsic mode functions(IMFs) of chaotic signals. Finally, all IMFs compose the new denoised chaotic signal. Experiments on the Lorenz chaotic signal composed of different Gaussian noises and the monthly observed chaotic sequence on sunspots were put into practice. The results proved that the method proposed in this paper is effective in denoising of chaotic signals.Moreover, it can correct the center point in the phase space effectively, which makes it approach the real track of the chaotic attractor.     

Integrating Independent Component Analysis with Artificial Neural Network to Analyze Overlapping Fluorescence Spectra of Organic Pollutants

Independent component analysis (ICA) combined with Elman recurrent neural network (ERNN) regression as a hybrid approach named ICA-ERNN was proposed for the simultaneous spectrofluorimetric determination of organic pollutants. Fluorescence spectra of these compounds under study are strongly overlapped, which does not permit direct determination without prior separation by conventional spectrofluorimetry. ICA is a blind source separation (BSS) method aiming at extracting independent source variables and their corresponding concentration profiles from the observed fluorescence spectra of chemical mixtures without using any prior knowledge about the components. The proposed method combining the idea of ICA denoising with ERNN calibration provides the ability for enhancing the extraction of characteristic information and the noise removal as well as the quality of regression. The relative standard errors of prediction (RSEP) obtained for all components using ICA-ERNN, ERNN and partial least squares (PLS) were compared. Experimental results demonstrated that the ICA-ERNN method had better result than ERNN and PLS methods and was successful even when there was severe overlap of fluorescence spectra.     

Validating the performance of one-time decomposition for fMRI analysis using ICA with automatic target generation process

Independent component analysis (ICA) has been proven to be effective for functional magnetic resonance imaging (fMRI) data analysis. However, ICA decomposition requires to optimize the unmixing matrix iteratively whose initial values are generated randomly. Thus the randomness of the initialization leads to different ICA decomposition results. Therefore, just one-time decomposition for fMRI data analysis is not usually reliable. Under this circumstance, several methods about repeated decompositions with ICA (RDICA) were proposed to reveal the stability of ICA decomposition. Although utilizing RDICA has achieved satisfying results in validating the performance of ICA decomposition, RDICA cost much computing time. To mitigate the problem, in this paper, we propose a method, named ATGP-ICA, to do the fMRI data analysis. This method generates fixed initial values with automatic target generation process (ATGP) instead of being produced randomly. We performed experimental tests on both hybrid data and fMRI data to indicate the effectiveness of the new method and made a performance comparison of the traditional one-time decomposition with ICA (ODICA), RDICA and ATGP-ICA. The proposed method demonstrated that it not only could eliminate the randomness of ICA decomposition, but also could save much computing time compared to RDICA. Furthermore, the ROC (Receiver Operating Characteristic) power analysis also denoted the better signal reconstruction performance of ATGP-ICA than that of RDICA.     

基于独立分量分析和粒子群算法的太阳能电池表面缺陷红外热成像检测

根据红外成像特性及太阳能电池电致发光原理,研究一种基于限制式独立分量分析(ICA)模型和粒子群优化(PSO)方法的太阳能电池组件表面缺陷检测方法。利用太阳能电池红外图像的结构特点,首先设计一种ICA滤波器,并使用具有多方向搜索特性的PSO算法来求解ICA的分离矩阵,求解中加入限制式,使图像正常区域经滤波后有一致的反应值并有效凸显缺陷区域。然后使用ICA滤波器对图像进行旋积运算,最后使用阈值分割得到检测结果。实验结果表明,提出的ICA滤波检测方法对太阳能电池组件表面缺陷检测效果显著,检测精度高,能很好地区分背景和缺陷。     

A method for comparing group fMRI data using independent component analysis: application to visual, motor and visuomotor tasks

Independent component analysis (ICA) is an approach for decomposing fMRI data into spatially independent maps and time courses. We have recently proposed a method for ICA of multisubject data; in the current paper, an extension is proposed for allowing ICA group comparisons. This method is applied to data from experiments designed to stimulate visual cortex, motor cortex or both visual and motor cortices. Several intergroup and intragroup metrics are proposed for assessing the utility of the components for comparisons of group ICA data. The proposed method may prove to be useful in answering questions requiring multigroup comparisons when a flexible modeling approach is desired.