基于伪魏格纳分布分解的合成孔径雷达图像目标与阴影分割

在二维魏格纳分布的框架内,针对魏格纳变换的交叉项问题和计算量大的问题,提出了合成孔径雷达图像局部伪魏格纳变换的目标和目标阴影的分割方法.首先,将合成孔径雷达图像进行二维伪魏格纳变换,得到各像素点的二维能量谱图|然后提取各像素点的二维能量谱图对应位置值形成多个不同频段的与原图像同大小的能量谱图|最后,对不同频段的能量谱图采用不同的处理方法后,将各能量谱图相加处理后形成区域标识图像,最终得到原图像的目标和目标阴影分割图像.本文利用该方法对MSTAR切片图像进行了分割试验,并对分割图像与频谱最大值距离或方位分割算法和基于双参量CFAR与隐马尔科夫联合分割算法进行了分割图像对比度对比.实验结果表明,采用本文算法的合成孔径雷达分割图像,对比度明显提高,且保留了目标图像细节.     

高光谱成像技术无损检测赣南脐橙表面农药残留研究

高光谱成像技术具备图像和光谱的双重优势,作为一种快速无损检测分析技术,检测过程无损、无污染和无接触。高光谱成像数据包括样本的图像信息和光谱信息,采集样本高光谱成像数据时,样本的每个像素点都有一条光谱与之对应,样本的每个波长都有一幅灰度图像与之对应。研究采用高光谱成像技术无损检测不同稀释浓度的农药在赣南脐橙样品表面残留随时间变化的关系。用蒸馏水把农药分别配置成1∶20,1∶100和1∶1 000倍的溶液。然后把不同浓度的溶液滴到30个洗净的脐橙表面,将涂有农药的脐橙分别放置0,4和20d,然后采集在900~1 700nm波长范围的高光谱成像原始数据。通过主成分分析获取930,980,1 100,1 210,1 300,1 400,1 620和1 680nm共8个特征波长,基于这些特征波长做第二次主成分分析,应用PC-2图像并经过适当的图像处理方法对不同浓度及放置不同天数的农药残留进行无损检测。采用高光谱成像技术检测三个时间段较高稀释浓度的果面农药残留都比较明显。高光谱成像技术作为一种检测方法,可用于评价各个时间段较高浓度的农药残留。     

Simulating electron momentum spectra of iso-C2H2Cl2： A study of the core electronic structure

Electron momentum spectroscopy(EMS) has been used for the first time to study core electronic structure of isoC2H2Cl2. In the present work, the pronounced difference between ionization energies of two C1 score orbitals(2A1 and 3A1) is seen as a chemical shift of 3 eV, which is due to different chemical environments of the related carbon atoms. Both the calculated spherically averaged core electron momentum distributions(MDs) and three-dimensional electron momentum density maps show that these core molecular orbitals(MOs) 2A1and 3A1 exhibit strong atomic orbital characteristics in real and momentum space. However, the core states 2B2 and 4A1, which are almost degenerate and related to two equivalent atoms, exhibit notable differences between the momentum and position depictions. In contrast to the position space, the momentum density maps of these two core MOs highlight the interference effects which are due to the nuclear positions. The 2B2 orbital of iso-C2H2Cl2 is the antisymmetric counterpart of the 4A1 core orbital in real space. However, it relates to the 4A1 orbital by an exchange of maxima and minima in momentum space. Due to interference effects between electrons scattered from different atomic centers, modulations with a periodicity of 1.12 a.u. can be seen in the computed momentum densities, which tend to decay with increasing electron momenta. Accordingly, the EMS can not only effectively image the electronic structure of compounds by studying valence orbitals, but also provides direct information on the nature of the nuclear geometry by investigating the core states.     

基于岩石重构图像的核磁共振响应模拟

能够反映孔隙介质内部真实复杂结构的CT图像经常被用于模拟研究中并能取得较好的结果. 但是,在很多情况下缺少三维CT图像或者其分辨率受限,此时,更易于获取的二维薄片图像被用于构建三维的孔隙结构图像. 假定孔隙介质各向同性,基于二维图像,使用多点统计方法可以构建岩石的三维孔隙结构. 基于数字图像,采用随机游走方法模拟得到核磁共振响应,然后由模拟得到的回波串反演得到T₂分布. 研究表明,岩石重构图像中的模拟结果与CT图像中的模拟结果有较好的一致性. 基于数字图像的核磁共振响应模拟为分析不同孔隙结构的核磁共振响应提供了便利,同时,模拟结果也为验证孔隙结构的重构效果提供了依据.     

基于多任务卷积神经网络的红外与可见光多分辨率图像融合

红外与可见光图像融合一直是图像领域研究的热点,融合技术能弥补单一传感器的不足,为图像理解与分析提供良好的成像基础。因生产工艺以及成本的限制,红外探测器的分辨率远低于可见光探测器,并在一定程度上因源图像分辨率的差异阻碍了实际应用。针对红外与可见光图像分辨率不一致的问题,提出了用于红外图像超分辨率重建与融合的多任务卷积网络框架,应用于多分辨率图像融合。在网络结构方面,首先设计了双通道网络分别提取红外与可见光特征,使算法不受源图像分辨率的限制;其次提出了特征上采样模块,先用双线性插值方法增加像素个数,再通过多层感知器精细化拟合像素平滑空间与高频空间的映射关系,无需重新训练模型即可实现任意尺度的红外图像上采样;接着将线性注意力引入网络,学习特征空间位置间的非线性关系,抑制无关信息并增强网络对全局信息的表达。在损失函数方面,提出了梯度损失,保留红外与可见光图像中绝对值较大的滤波器响应值,并计算该值与重建的融合图像响应值的Frobenius范数,无需理想的融合图像作为真值监督网络学习就能生成融合图像;此外,在梯度损失、像素损失的共同作用下对多任务模型进行优化,可以同时重建融合图像和高分辨率红外图像...     

An effective noise removal technique for recovering the shapes of diamond abrasive grains in SLM images degraded by clustered spike noise

A new noise-removal technique is applied to scanning laser microscopic (SLM) images to remove clustered spike noise in the images and to recover the shapes of diamond abrasive grains degraded by the noise. For achievement of this purpose, noise points in the SLM image are accurately detected by taking advantage of their properties in the space and spatial-frequency regions. The noise points are removed by a method of smoothing that is based on linear interpolation; that is, their pixel values are replaced by the interpolated values of their non-noise neighboring points. Noise-point information in the space region is acquired from image segmentation based on pixel classification, while noise-point information in the frequency region is derived from redundant wavelet decomposition for the SLM image. Fisher's linear discriminant method is used to yield the two noise-point images. The degraded grain shapes in the SLM images at different noise levels are satisfactorily recovered with a single iteration of smoothing without losses in sharp edges although a single smoothing needed four interpolations. Thus, the present noise-removal technique is shown to be effective for recovering the original shapes of the grains in every SLM image.     

Linear-fitting-based similarity coefficient map for tissue dissimilarity analysis in T_2~*-w magnetic resonance imaging

Similarity coefficient mapping(SCM) aims to improve the morphological evaluation of T*2weighted magnetic resonance imaging(T*2-w MRI). However, how to interpret the generated SCM map is still pending. Moreover, is it probable to extract tissue dissimilarity messages based on the theory behind SCM? The primary purpose of this paper is to address these two questions. First, the theory of SCM was interpreted from the perspective of linear fitting. Then, a term was embedded for tissue dissimilarity information. Finally, our method was validated with sixteen human brain image series from multiecho T*2-w MRI. Generated maps were investigated from signal-to-noise ratio(SNR) and perceived visual quality, and then interpreted from intra- and inter-tissue intensity. Experimental results show that both perceptibility of anatomical structures and tissue contrast are improved. More importantly, tissue similarity or dissimilarity can be quantified and cross-validated from pixel intensity analysis. This method benefits image enhancement, tissue classification, malformation detection and morphological evaluation.     

Combined MR-relaxation and MR-cryoporometry in the study of bone microstructure.

MR-Relaxation (MRR) of 1H nuclei and MR-Cryoporometry (MRC) are combined to assess their feasibility and their potential in the study of bone microstructure. In principle, both techniques are able to give information on the structure of the pore space confining the fluids. Cow femur samples were carefully cored and cleaned in order to remove the natural fluids inside. For MRR analysis quasi-continuous distributions of T(1) and T(2) were obtained on samples fully saturated with water. Cyclohexane was used as a saturating fluid for MRC analysis. All T(1) and T(2) quasi-continuous distributions of water confined in bone samples are more than three decades wide, showing sufficient details to differentiate the samples. Pore size distributions obtained by MRC also differentiate the samples showing different characteristics of the pore space structure in the range of the highest sensitivity of the method (typically 3 to 100 nm, mesopore range). In particular, in samples where MRR shows a large fraction of signal with relaxation times below 10(2) ms, MRC indicates a large fraction of pore volume with pore sizes in the mesopore range.     

基于混合光模式阵列的自由空间编码通信

光学涡旋的产生、传输与应用是当前光学领域的研究热点之一.光学涡旋具有轨道角动量,作为一种全新的自由度,丰富了目前光通信的方式.利用面向目标的共轭对称延拓傅里叶计算全息技术,基于空间光调制器,用单束激光直接产生混合光模式阵列进行编码通信.采用由单光涡和复合光涡构成的4种易于识别的模式组成2×2混合光模式阵列,进行灰度图像的编码传输.在接收端提取混合光模式阵列图的信息并进行解码,实现零误码的灰度图像再现.以传输一幅Lena图像为例,使用2×2混合光模式阵列进行编码通信,相对于传统单光涡编码通信,其信息容量可增加4倍.该方法光路简单易行,可扩展性强,进一步拓展使用4×4混合光模式阵列进行编码通信,信息容量提升16倍.提出的混合光模式阵列编码通信方法对于提高信息传输容量具有重要价值.     

红外和彩色可见光图像亮度-对比度传递融合算法

以红外和彩色可见光图像为研究对象,提出了一种基于亮度-对比度传递（LCT）技术的彩色图像融合算法。首先借助灰度融合方法将红外图像与彩色可见光图像亮度分量融合,然后用LCT技术改善灰度融合结果的亮度和对比度,最后利用快速YCBCR变换融合策略在RGB空间内直接生成彩色融合图像。文中利用像素平均融合法和多分辨率融合法作为不同的灰度融合措施以分别满足高实时性和高融合质量的需求。实验结果表明,提出算法的融合结果不仅具有与输入彩色可见光图像相近的自然色彩,而且具备令人满意的亮度和对比度,即使采用运算简单的像素平均法进行灰度融合,同样可以获得良好的融合效果。