复合校正算法在硬币图像校正中的应用

针对移动硬币图像获取过程中产生的图像失真问题,提出了一种可以获得清晰标准图像的复合校正算法。该算法将透视映射校正与椭圆变换理论相结合,对抓拍到的非静止状态下的失真硬币图像进行还原校正,为获得清晰标准的硬币表面花纹图案提供了一种高效的图像形变矫正手段,降低了硬币图像捕捉环节对机械结构精密度的依赖。实验表明,该算法图像校正精度更高,其图像平均灰度值仅为椭圆直接变换法的10%。     

基于几何光学的图像矫正法在圆管PIV实验中的应用研究

粒子图像速度技术被广泛用于流体流动测量,介质折射率差异使光在圆管壁面发生偏折,导致图像失真,直接影响速度测量精度。本文建立了光学折射的物理模型,得到圆形管道中物点和图像点之间的函数关系进而得到矫正后图像的像素坐标,使用双线性插值算法得到像素灰度值重建出矫正后的粒子图像,最后根据多重网格迭代算法计算管内速度场。分别对流体进行管内静态流体与管内层流速度场测量实验,对比了光学矫正箱法、线性矫正以及基于光学模型的畸变矫正方法误差。结果表明,本文提出的基于几何光学的图像矫正方法精度优于光学矫正箱法和线性矫正方法,并通过静态与流动实验充分验证了所建立几何光学模型的准确性和有效性。     

发散扫描模式下OCT图像畸变分析与矫正

针对光学相干断层成像(OCT)系统在发散扫描模式下图像失真的问题,本文研究了图像产生畸变的机理,对图像的畸变量进行了定量分析,提出了一种发散扫描模式OCT图像矫正与重构算法。首先,基于最大类间方差法对原始图像进行了降噪与增强预处理,以减少背景噪声对图像重构的影响。然后,建立OCT原始图像和重构图像的映射关系,从而实现对畸变图像的矫正。利用OCT系统对玻璃样品在发散扫描模式下进行成像,对图像进行矫正后测量样品厚度和宽度并与实际值对比,厚度测量误差为-0.012～0.053 mm,宽度测量误差为-0.107～0.045 mm。以离体猪眼为样品,对比平行扫描模式和发散扫描模式的测量结果,角膜厚度测量误差为-0.022～0.014 mm,虹膜间距测量误差为-0.121～-0.015 mm。实验验证了该算法在抑制OCT图像背景噪声的同时,能够有效矫正图像畸变,对于发散扫描模式OCT图像在医疗诊断和手术导航领域的应用具重要意义。     

基于统计概率模型红眼检测消除算法研究

研究红眼检测和消除问题.针对数字照相机在拍摄过程中容易产生红眼的问题,提出了一种全新的利用不同区域红眼出现概率来进行红眼定位和矫正的算法.首先通过对图像中各像素提取特征并初始筛选红眼像素,确定一些红眼可能出现的区域.在这些区域内在进行融合,再次计算红眼出现的概率,并使用支持向量机进行识别.将识别的置信度与红眼的矫正算法充分融合在一起,最终得到红眼定位和矫正的结果.仿真实验表明了该方法能准确定位图像中的红眼,并能平滑的矫正红眼,获得良好的视觉效果.     

基于机器视觉检测的摄像机快速标定与误差分析

为了提高引线键合机中机器视觉检测子系统中的测量精度和效率,必须对摄像机镜头进行畸变矫正,提出一种基于畸变矫正的摄像机快速标定算法并对该算法的误差进行分析。该算法采用一阶径向畸变模型进行摄像机标定,算法中将复杂的非线性问题转化为线性问题进行参数求解,并且逆向求解了标定块上的空间特征点坐标,进而计算误差。试验验证,标定误差精度为4.26‰,减少了算法的时间复杂度,并且更准确的计算误差,同时本套算法还可用于其它有图像畸变的场合进行误差评定,因此具有较高的实用价值。     

畸变车牌定位与矫正方法研究

算法实现了对畸变车牌的准确定位、矫正并完成分割、识别,结合形态学对HSV模型定位方法进行改进,提升车牌区域粗定位准确性,之后由定位子算法实现对车牌粗定位结果的精确定位。Hough变换获取定位后车牌图像端点信息,以此利用数学方法重构、矫正车牌图像,从而对车牌进行分割与识别。实验证明,本算法对畸变车牌图像矫正效果显著,对提高车牌识别准确率具有重要意义。     

智能空间中基于畸变矫正的改进视觉标定

为了解决智能空间中机器人环境建模时的视觉标定,提出了一种基于几何畸变矫正的改进标定算法.首先对模板图像进行阈值分割和循环腐蚀等预处理;然后利用改进Harris算法进行角点提取;再基于非线性最优和立方卷积插值来矫正畸变图形;最后在此基础上实现摄像机标定.     

一种滚球法测橡胶粘度的视觉矫正算法研究

针对橡胶粘度测量精度不高、测试时间长、效率低的问题,对视觉测橡胶粘度的方法进行了研究,提出了一种利用滚球测橡胶粘度的视觉矫正算法。首先对滚球法测橡胶粘度的原理进行了说明,建立了视觉矫正模型,并对矫正算法进行了分析与实现;该算法根据滚球运动不同位置状态进行了分析处理,解决了不同状态下滚球中心位置的确定问题;最后通过粘度测量平台测量橡胶的粘度验证了矫正算法的可行性。实验结果表明:该算法得到的多次实验数据波动较小,满足工业生产的要求;该矫正算法因不存在近似求解,同时模型不受滚球到投影面距离的影响,算法的适用性与测试结果的准确性得到进一步提高。     

用于电容层析成像的一步稳定图像重建算法

本文提出一种基于Landweber迭代的电容层析成像系统一步稳定图像重建算法。该算法通过构建压缩算子可以克服传统Landweber迭代方法存在的半收敛性,得到稳定的重建图像。同时该算法的矩阵算子可以预先计算,然后通过一步矩阵运算实现图像重构。实验结果表明,该算法可保证重建图像的实时性和鲁棒性。     

基于 RANSAC 的视觉里程计优化方法研究

针对图像特征产生误匹配影响基础矩阵计算,导致同步定位与地图构建(SLAM)视觉里程计估计精度差的问题,提出一种基于随机抽样一致(RANSAC)的视觉里程计优化方法。该方法首先通过最小距离阈值法对初始匹配集粗滤除,再采用RANSAC计算图像间相对变换关系,若符合变换关系为内点,内点数最多的迭代结果为正确匹配结果;然后计算图像间单应变换并利用其计算基础矩阵,采用对极几何约束确定内点,得到具有最多内点的基础矩阵;最后采用TUM数据集从特征匹配与基础矩阵计算两方面进行优化算法效果验证。结果表明,该算法可提高运行效率且有效去除误匹配特征点,使匹配正确率提高7.7%,基础矩阵估计算法在提高基础矩阵计算精度的同时,内点率也提高了3%,算法为提高视觉里程计精度估计精度提供了理论基础。     

改进Chebyshev混沌算法的小波变换数字水印技术研究

本文主要利用混沌算法和小波分解实现数字图像的水印处理。首先,利用混沌算法对水印数字图像进行置乱,然后,将置乱后的水印嵌入到小波分解后的宿主图像里面。通过实验证明,该算法对常见的信号攻击和几何剪切攻击均具有较好的鲁棒性。     

Image reconstruction of electrical capacitance tomography based on optimal simulated annealing algorithm using orthogonal test method

Electrical capacitance tomography (ECT) is a visualization measurement method for two-phase flow. Imaging permittivity distributions using electrical capacitance tomography has always been one of the most significant issues studied by scholars, and the algorithm will have a great impact on the accuracy of image reconstruction result. This paper applies simulated annealing (SA) algorithm to image reconstruction in ECT. However, some parameters of SA algorithm need to be optimized in order to obtain better reconstructed images in ECT. The influence of different parameter values in SA algorithm for image reconstruction in ECT is studied, and a set of optimal parameters of the SA algorithm is obtained based on the orthogonal experimental design method in this paper. At the same time, simulation and static experiments are conducted. Reconstructed images by SA algorithm with optimized parameter are compared with the linear back projection (LBP) and Landweber iterative algorithms. The results show that better images can be obtained for typical oil-gas two-phase flow using SA algorithm. The quality and shape fidelity of reconstructed image for the central object are obviously improved.     

小波及分形理论在互有位移图像序列重构中的应用

提出一种基于小波及分形理论的插值算法,用于互有位移序列图像的重构,它既考虑了各幅图像的细节特征又考虑了图像的全局特征,使得到的重构图像更接近原图。阐述了超分辨力复原技术的理论基础及复原算法,指出了基于序列图像的高分辨力成像技术的合理性,并利用小波及分形相结合的方法对互有位移的双幅图像进行了重构,实验和仿真的复原图像表明,这种方法是可行和有效的。与传统方法相比,此种方法的PSNR提高了约5dB。     

射线图像增强技术仿真研究

图像增强在生物医学、无损检测、卫星遥感等领域得到广泛应用。对于低对比度射线图像而言,局部图像的反差较小是其特点。针对这一特点,将全局自适应均衡与局部动态增强相结合,通过增强倍数进行局部动态调整以适合各种对比度增强的要求。仿真结果表明,该算法能有效提高低对比度射线图像的整体对比度并同时突出细节。在实际应用中,对于其他成像技术的处理也有很好的参考价值。     

基于振幅调制纯相位滤波器的旋转不变识别优化算法研究

为了提高光学匹配滤波相关识别的综合性能,提出一种基于振幅调制纯相位滤波器的旋转不变识别新算法,该算法使用综合鉴别函数和迭代算法将各个不同旋转角度的训练图像构建成子滤波器,并将它们加权求和得到优化的合成滤波器。这种新的优化算法使得相位匹配更加充分,显著提高多种识别条件下的相关峰值,能够一定程度地降低训练量。计算机仿真实验结果表明此种算法具有良好的旋转不变识别效果。     

Structure determination and structure refinement of Al2CuMg precipitates by quantitative high-resolution electron microscopy

The structure of the S-phase (Al2CuMg) precipitate in an Al matrix has been determined by using a combination of image processing, quantitative image comparison, and automatic refinement of imaging and structural parameters. A method for comparing images with unknown origin relationship while quickly estimating a possible translation of the origin is outlined. The optimization algorithm used in the structure determination utilizes space group symmetry, which is deduced from the crystal-zone axis and reduces the number of free parameters.     

Dense nuclei segmentation based on graph cut and convexity–concavity analysis

With the rapid advancement of 3D confocal imaging technology, more and more 3D cellular images will be available. However, robust and automatic extraction of nuclei shape may be hindered by a highly cluttered environment, as for example, in fly eye tissues. In this paper, we present a novel and efficient nuclei segmentation algorithm based on the combination of graph cut and convex shape assumption. The main characteristic of the algorithm is that it segments nuclei foreground using a graph‐cut algorithm with our proposed new initialization method and splits overlapping or touching cell nuclei by simple convexity and concavity analysis. Experimental results show that the proposed algorithm can segment complicated nuclei clumps effectively in our fluorescent fruit fly eye images. Evaluation on a public hand‐labelled 2D benchmark demonstrates substantial quantitative improvement over other methods. For example, the proposed method achieves a 3.2 Hausdorff distance decrease and a 1.8 decrease in the merged nuclei error per slice.     

基于多幅图像的逆向造型方法初步研究

提出了一种由多幅图像初步恢复三维物体形状的方法。在共线光源（光源位于或接近摄像机的光轴上,并且照射方向平行于光轴）照射下,对置于旋转平台上的物体摄像;综合考虑所摄图像序列中包含的几何轮廓信息与光亮度信息,采用立体相交技术和剥离技术,逐步求精地得到三维物体的八叉树表示。这种初步的造型结果可作为其他更精确方法的基础。     

Reconstruction of images of reflectors using the correlation method at an arbitrary number of reflections of an ultrasonic pulse from the boundary of a test object that consists of regions with different acoustic properties

An algorithm for reconstructing images of reflectors from echo signals that propagate in a test object, which consists of several regions with different acoustic properties, is considered. The ray trajectories are calculated using the method of direct construction of the family of rays that escape from the point where a transmitter is located but not the Fermat variational principle. After the family of rays is constructed, their belonging to a certain acoustic scheme can be analyzed and the approximation of the calculated delays on the spatial mesh of the image reconstruction region (IRR) can be performed. This will allow the reconstruction of both the pulse travel time from the transmitter to any point in the IRR and back to the receiver and the attenuation of the pulse amplitude caused by the divergence, reflection, and refraction effects at the boundaries of the regions that constitute the test object. Numerical and model experiments show the working capacity of the proposed algorithm for reconstructing reflector images.     

Development of a novel coordinate transposing fixture system

A novel quick action flexible fixture for two-dimensional clamping is fitted with sensors for automatically measuring the positions of the clamping surfaces and the vice opening. An algorithm is proposed to determine the location and orientation of the workpiece on the fixture. The NC codes preprogrammed with a given origin and orientation can then be modified with these data to appropriately transposed coordinates, which can then be downloaded to the NC controller for NC machining. With this system, the time and cost of fixturing will be greatly reduced.