一种基于视觉熵的图像分割压缩方法

基于视觉熵概念提出了一种静止图像分割压缩方法.通过对人类视觉系统特性的归纳,总结了基于视觉熵的图像分割原理,提出了用于量化图像特征的数学定义和基于视觉嫡的分割算法.实验结果表明,这种基于视觉熵的图像分割压缩算法既提高了压缩比,又能保证压缩后的重建图像整体上具有高的主观视觉感知质量.     

基于HSV色彩空间的图像分割

为了辨识和分析目标,需要将这些有关区域分离出来,在此基础上才有可能对目标进一步处理。本文提出了一种利用HSV色彩空间的图像分割方法,根据HSV色彩空间的颜色和亮度无关,将彩色图像从RGB空间变换到HSV空间,然后经过H分割对绿地植被信息进行提取得到分割结果。实验表明该方法具有很强的鲁棒性。     

浅谈图像分割技术

文章介绍了图像分割技术的概念,分析了图像分割的基本类型,以及当今图像分割的前沿策略,并由此给我们在图像分割技术上的新的启示。     

基于边缘信息和先验形状的水平集图像分割方法及其在病原菌识别中的应用

研究从多目标图像中自动提取单个目标的图像处理方法.从分析曲线的水平集表示入手,首先探讨了水平集动态轮廓分割和配准模型构建的统计思想和变分方法,然后针对多目标粘连图像的特点,提出了含边缘信息和先验形状的水平集图像分割模型,并将其应用于病原菌的识别.由于引入边缘信息改进对分割的约束,加强了目标边缘对分割轮廓的吸引,同时消除了一些由噪声、阴影和杂质造成的影响.实验表明,改进后的先验形状水平集图像分割方法能直接从多目标粘连图像中提取单个目标,进一步完善了依据显微镜图像识别病原菌的图像处理方法.     

基于水平集的钢水图像分割方法

钢水质量和收得率是转炉生产的两项重要生产考核指标.通过红外热成像法检测转炉出钢钢水图像中钢渣占比率,从而有效控制钢水质量和收得率是转炉生产工艺之一.由于转炉出钢钢水红外灰度图像具有背景噪声干扰大、钢渣呈多目标分离标状且边缘非规则等特点,因此如何提高钢水图像分割及钢渣占比检测准确率一直是难点问题.针对该问题,提出了一种基...     

OpenCV技术在数字图像处理中的应用

OpenCV是开发的C源码,基于Intel处理器指令集开发的优化代码,具有统一的结构、功能定义、强大的矩阵计算能力以及方便灵活的接口等特点,实现了实时的图像处理和计算机视觉方面的通用算法.OpenCV包括CV模块、CVAUX模块、CXCORE模块、ML模块和HIGHGUI模块,有间接存取、直接存取和带指针直接存取三种存取方式.     

基于CNN-PDE偏差异质扩散预处理的红外图像分水岭分割

为了抑止采用分水岭方法分割红外图像时的过分割现象,首先利用细胞神经网络高效求解偏微分方程的能力,实现了可调偏差异质扩散滤波器并用其对图像作预处理.为了消除噪声残留,引入了平滑系数与限制强度系数对梯度图作阈值化处理.实际红外图像的分水岭分割结果显示,所提出的预处理方法能够有效抑止过分割现象.     

热轧带钢在线测宽中的图像分割

对带钢质量检测中图像处理和分析的过程进行了论述.结合热轧带钢现场图像,应用最终测量精度准则对图像处理算法进行评价.实验评价结果表明,动态双阈值的图像分割效果最佳,适合应用于带宽实时在线检测.     

一种数码金相显微图像放大倍率的标定方法

本发明涉及数码金相显微图像放大倍率的标定方法,解决现有数码金相显微图像其放大倍率无法精确标定的技术问题。本发明通过采用具有溯源值金相显微标尺、调节金相显微镜的视场光栏、调节数码相机的变焦控制,建立标准物理长度与标定数字图像像素之间的对应关系,制作系统标尺文件;通过标尺文件调入并加载到当前的金相图像操作系统,对数字化后的金相图像进行标定。将标尺文件存放在标尺文件数据库中,对于采用相同状态得到的数码显微图像,可以调用相应状态的标尺文件,直接进行放大倍率标定,因此可以对相同状态的图像进行批处理。图像标定时在原始图像上精确插入标尺,当对图像编辑时,插入的标尺随图像倍率改变而实时改变。该方法有效地提高了金相检测工作效率。     

改进遗传算法在雾天图像清晰化中的应用

将改进遗传算法应用于雾天图像的区域分割,从而使图像清晰化.该方法首先用遗传算法求出近景和远景的分割阈值将图像分割出来,然后通过移动模板对整个图像进行相应的清晰化处理,防止区域边界效应的产生,最后对获取的图像进行信息融合,进一步提高图像质量.通过试验证实了该算法能有效改善雾天图像的退化现象,提高图像的清晰度.     

Image segmentation by a deformable contour model incorporating region analysis

Deformable contour models are useful tools for image segmentation. However, many fields depend mainly on local edge-based image features to guide the convergence of the contour. This makes the models sensitive to noise and the initial estimate. Our model incorporates region-based image features to improve its convergence and to reduce its dependence on initial estimation. Computational efficiency is achieved by an optimization strategy, modified from the greedy algorithm of Williams and Shah. The model allows a simultaneous optimization of multiple contours, making it useful for a large variety of segmentation problems.     

Development of multicomponent immunoassay and micro-localization analysis by laser-photoacoustic and microscopic image analyzer]

Laser photoacoustic spectroscopy (PAS) has a potential to be developed as a sensitive and solid-phase analytical method and was applied to enzyme immunoassay. The test sample for immunoassay was prepared by adsorbing multi-component immunoglobulins on a nitrocellulose membrane filter. Human lambda- and kappa-chains, which are used as a principal indication of malignant lymphoreticular disease, and immunoglobulin G were used as model proteins, and PAS immunoassay was applied to the individual detection of these three proteins in the urine. Furthermore, in order to develop a sensitive analysis for particular biological components in tissues or cells, laser photoacoustic microscopy (PAM) and video intensified microscopy (VIM) were developed. PAM was shown to be applicable to the detection and quantification of human lambda-chain in a micro-region of the tissue sections of the human fetal spleen and pancreas. VIM was applied to the detection of stimulation-response processes in a cell. By using neutrophils which are stimulated by many substances and produce active oxidants as the results, dynamic changes in the stimulation-response process in a living cell were visualized as fluorescence or chemiluminescence images by the VIM system.     

Comparison of the Bio Image Visage 2000 and the GELLAB-II two-dimensional electrophoresis image analysis systems

To compare the Visage 2000 analysis system (Bio Image, Ann Arbor, MI, USA) with the GELLAB-II analysis system (National Cancer Institute, Frederick, MD, USA), we used each to perform image analysis of the same 29 silver-stained two-dimensional electrophoresis (2DE) gel image files from a study of urinary proteins in metal recovery plant workers who had confirmed body burdens of cadmium. Visage, aided by interactive analysis, detected an average of 890 +/- 177.6 spots per gel, or a total of 25,800 spots, whereas GELLAB-II detected 1971 +/- 198.5 spots per gel, or a total of 57,160 (a 222% increase over the Visage system), without operator intervention. Visage automatically quantified 52.5% (13,556) of the spots; 47.2% (12,173), consisting mostly of larger spots, had to be quantified interactively with an image editor, and 0.3% (71) were not quantified. GELLAB-II automatically quantified all detected spots. After we interactively assigned the maximum allowed number of landmarks (30 for Visage and 52 for GELLAB-II), we found that Visage matched 657 +/- 211.2 spots per gel, and GELLAB-II matched all detected spots and also extrapolated an average of 1269 virtual spots per gel. Plots of densities from the two systems on selected spots showed excellent agreement, and both systems showed high correlation between their measurements of the beta-2-microglobulin spot densities and an independent radioimmunoassay quantification of the original urine samples. By comparing the regression of the densities of all spots with urinary cadmium (UCD) levels, we found that several of the same detected spots from each system were highly correlated. The densities of four acidic proteins with relative molecular weights of approximately 112,000 Da (as quantified by GELLAB-II but not by Visage) were highly correlated with UCD concentrations. These proteins are new candidate biomarkers of cadmium toxicity. We compared the estimated labor costs of using each system to analyse a hypothetical 20-sample (60 gels) 2DE study and found that GELLAB-II was six times less expensive to use than Visage, primarily because of the operator time required to do interactive error correction with the Visage system.     

自适应分数阶微分在图像纹理增强中的应用

针对目前只能通过人为实验指定最佳分数阶微分阶数的现状,为了节省大量人工寻求最佳分数阶微分阶数的时间,研究并提出了可以依据掩模窗口大小、G-L公式、图像梯度特征和人眼视觉特性等理论的能够自动生成分数阶微分阶数的新方法,基于该自适应阶数,设计并实现了对应的算子掩模.采用了信息熵、平均梯度等图像纹理特征评价参数做定量分析和实验验证,结果表明,该方法对任意灰度图像可以得到连续变化的增强效果,接近于最佳分数阶微分增强效果,符合人们的视觉感受,是有效的图像纹理增强方法.     

ICP-AES分析技术的发展及其在冶金分析中的应用

评述了近 2 0年来ICP AES分析技术的发展及其在冶金分析中的应用。内容包括 :ICP AES的发展历程、ICP AES分析方法的特性、ICP AES仪器的发展、在冶金分析中的应用现状、发展趋势。文中引用文献 6 2篇。     

Motion edges and regions guide image segmentation by colour

Image segmentation is an important early stage in visual processing in which the visual system groups together parts of the image that belong together, prior to or in conjunction with object recognition. Two principal processes may be involved in image segmentation: an edge-based process that uses feature contrasts to mark boundaries of coherent regions, and a region-based process that groups similar features over a larger scale. Earlier, we have shown that motion and colour interact strongly in image segmentation by the human visual system. Here we explore the nature of this interaction in terms of edge- and region-based processes. We measure performance on a region-based colour segmentation task in the presence of distinct types of motion information, in the form of edges and regions which in themselves do not reveal the location of the colour target. The results show that both motion edges and regions may guide the integrative process required for this colour segmentation task. Motion edges appear to act by delimiting areas over which to integrate colour information, whereas motion similarities define primitive surfaces within which colour grouping and segmentation processes are deployed.     

基于格结构的三带小波构造及在图像融合中的应用

提出了一种构造具有正交性、对称性、紧支性以及较高消失矩的三带尺度滤波器与小波滤波器的方法.首先,通过设置尺度滤波器消失矩并转移尺度滤波器的对称性性质,有效地减少了构造尺度滤波器过程中未知量的个数以及计算推导过程的复杂度.在此基础上,利用格结构理论,给出了对具有仿酉特性的多相位矩阵的一种分解方法,并利用这种分解求出了冲击响应长度为9、消失矩为3以及响应长度为15、消失矩分别为3和4的小波滤波器.最后,把所求得的小波滤波器应用到多聚焦图像的融合中.实验结果表明,利用具有上述性质的三带小波进行图像融合可以得到比利用二带小波进行融合更好的效果.     

关于生存分析中的统计方法及其应用

设计了4组实验,通过对老鼠注射某种药物,观测老鼠的生存时间,收集科学数据,然后利用对数(log-rank)检验理论,对观测到的数据进行生存分析,最终确定药物的疗效.     

A microscopic theory for antiphase boundary motion and its application to antiphase domain coarsening

A microscopic diffusional theory for the motion of a curved antiphase boundary is presented. The interfacial velocity is found to be linearly proportional to the mean curvature of the boundary, but unlike earlier theories the constant of proportionality does not include the specific surface free energy, yet the diffusional dissipation of free energy is shown to be equal to the reduction in total boundary free energy. The theory is incorporated into a model for antiphase domain coarsening. Experimental measurements of domain coarsening kinetics in Fe-Al alloys were made over a temperature range where the specific surface free energy was varied by more than two orders of magnitude. The results are consistent with the theory; in particular, the domain coarsening kinetics do not have the temperature dependence of the specific surface free energy.     

共沉淀法合成三硅酸镁及其微观分析

由Na₂O·nSiO₂和Mg(NO₃)₂经沉淀法合成了三硅酸镁,用450℃煅烧或酸化方法对合成的样品进行改性.采用XRD、IR、TG/DTA和BET等表征手段,考察了原料加入顺序、酸化和煅烧过程对样品的结晶度和表面织构的影响规律,并对其影响机理进行了探讨.结果表明,不同滴定顺序和不同活化方法制得的样品均为非晶态物质.TG/DTA分析显示不同滴定顺序样品的组成相同.pH对样品的表面织构有明显的影响.BET分析表明,Mg(NO₃)₂滴加入泡花碱溶液合成的样品为微孔材料,以1~3nm和0.7~0.9nm的微孔为主,比表面积达568.93m²·g^-1,水合硅酸镁含量较高.泡花碱滴加入Mg(NO₃)₂合成的样品为大孔材料,比表面积为179.40m²·g^-1,水合硅酸镁含量降低.煅烧和酸处理增加样品的结晶度,减少样品比表面积,并改变样品的孔径分布.煅烧使中孔含量增加,形成中孔材料.酸处理使Mg²⁺被H⁺取代,表面形成硅羟基基团,材料以中孔为主.