多尺度无监督彩色图像分割

非采样Contourlet变换是一种新的多尺度多分辨率分析工具.本文提出了一种基于非采样Contourlet变换的彩色图像无监督分割算法.首先利用非采样Contourlet变换的平移不变性在其变换域应用梯度向量法提取图像多尺度边缘|然后在Contourlet变换域的低频子带和高频子带中分别提取局部低频能量纹理特征与高频多尺度Zernike矩纹理特征,并将二种纹理特征融合.最后在边缘图像中映射种子像素点,利用纹理和颜色特征欧氏距离,对彩色图像采用区域生长和区域合并的方法进行分割.实验结果证明:该算法将图像空间域的颜色特征与非采样Contourlet变换域的多尺度边缘和纹理特征恰当结合在一起实现彩色图像无监督自动分割,与传统算法相比有更高的准确性和鲁棒性.     

基于多尺度Radon变换的图像检索

根据Radon变换的统计特性构造了不变量,提出一种新的基于多尺度Radon变换的图像形状检索方法.对检索图像作小波变换,根据小波模极大原理得到边缘图像,对边缘图像构造Radon变换中心矩,在中心矩的基础上根据Radon的统计原理构造出尺度不变矩.由于矩阵的奇异值具有旋转不变性,因此针对不变矩向量矩阵求奇异值,该奇异值特征向量具有平移、尺度和旋转不变性.将该Radon变换的不变量作为形状特征,并进行高斯归一化,按照欧氏距离计算不同图像间的形状相似度.试验结果表明,该方法对高斯噪音具有较强的鲁棒性,与其它方法相比具有较好的检索效果.     

多尺度无监督彩色图像分割

非采样Contourlet变换是一种新的多尺度多分辨率分析工具,本文提出了一种基于非采样Contourlet变换的彩色图像无监督分割算法.首先利用非采样Contourlet变换的平移不变性在其变换域应用梯度向量法提取图像多尺度边缘;然后在Contourlet变换域的低频子带和高频子带中分别提取局部低频能量纹理特征与高频...     

一种新的基于纹理和空间分布特征的图像检索

提出一种新的基于纹理和空间分布特征的图像检索方法.将检索图像分块,采用平移和尺度不变小波对各图像子块进行分解,在改进的快速小波直方图算法基础上提取图像子块的小波直方图,并提取每个图像子块的小波信息熵和三阶中心距作为纹理特征.对小波信息熵和中心矩特征进行高斯归一化,并利用特征向量的欧氏距离计算图像的纹理和空间特征的相似度.基于纹理图像库和自然图像库的检索试验表明,该方法比基于快速小波直方图算法和对数极坐标变换检索算法具有较高的检索准确度.     

基于相位一致性和Hough变换的多源图像配准方法

由于红外图像与可见光图像对比度不同,常用基于梯度幅值的特征匹配方法难以正确配准。在分析红外图像与可见光图像成像机制的基础上,提出了一种结合相位一致性边缘检测与Hough变换的多源图像配准新方法。该算法首先采用高通滤波和平台直方图均衡方法对红外图像进行预处理以提高红外图像的对比度,再利用具有图像对比度不变性的相位一致性边缘检测法提取两幅图像的边缘,结合Hough变换选取图像空间中最长的线作为特征,采用改进相位相关法作为相似性度量,在对数极坐标域下计算出两幅图像的几何变形参数。仿真实验结果表明,该方法能够以较高查准率实现红外与可见光图像自动配准,并具有较强的鲁棒性。     

线状目标实时检测算法的研究

提出了一种基于FPGA和DSP的算法并设计了相应的硬件系统,能对大小为256×256像素、帧频为25帧/s的视频图像进行实时处理。即先对输入图像采用改进的Sobel算子提取边缘,再用改进的Hough变换算法进行直线检测。解决了传统的Sobel算子提取的边缘较粗及Hough变换算法计算量大、难以实时实现的难题。     

Circle detection using scan lines and histograms

Circle detection is significant in image processing and pattern recognition. We present a new algorithm for detecting circles, which is based on the global geometric symmetry of circles. First, the horizontal and vertical midpoint histograms of the edge image are obtained by using scan lines. Then, we apply the peak-finding algorithm to the midpoint histograms to look for the center of the circle. The normalized radius histogram is finally used to verify the existence of the circle and extract its radius. Synthetic images with different levels of pepper noise and real images containing several circles have been taken to test the performance. Experimental results demonstrate that the proposed algorithm has the advantage of computational efficiency as compared with the randomized Hough transform and some other algorithms.     

基于Hough变换的金刚石颗粒测量方法研究

针对金刚石颗粒图像分析时的颗粒边缘非闭合性问题,本文提出了一种基于Hough变换的金刚石颗粒测量新方法。该方法首先对图像进行形态学去噪、平滑滤波和Canny边缘检测等预处理,得到金刚石颗粒图像的初始边缘曲线,然后采用Hough变换提取边缘曲线的直线特征,并通过极径和极角对多个直线特征进行判断和图形识别,得到确定的金刚石颗粒边缘轮廓,最后对得到的边缘轮廓进行拟合,测量出金刚石颗粒的粒径、椭圆度和圆度等参数大小。该方法在VC+ 环境下,用OpenCV编程技术对其进行了实验验证,结果表明：该方法可以准确快速地测量出金刚石颗粒特征参数,为金刚石颗粒的等级评定提供了技术支持。     

The high precision positioning algorithm of circular landmark center in visual measurement

For vision measurement in the center circle landmark location problem, an improved center of the ellipse based on Zernike moments sub-pixel positioning algorithm was proposed. First, using Sobel operator edge of the image pixel level positioning and then use the constructed Zernike moments to solve the model, combined with Zernike orthogonal polynomials and completeness and plural moment magnitude rotational invariance calculated edge sub-pixel position; followed by analysis of the principle deviation generated by the moments template and ideals model, a correction formula was proposed to compensate and improved edge criterion used to image sub-pixel edge positioning; finally, using the least-squares ellipse fitting algorithm fitting circle center, reverse edge point, filtered residuals larger point, and then precise positioning of the ellipse center. The experimental results show that this method has good stability and high positioning accuracy can be efficiently used in many applications.     

改进的Zernike矩工业CT图像边缘检测

为提高工业计算机断层扫描(CT)图像亚像素边缘检测的精度和速度,研究了一种改进的Zernike矩边缘检测方法。该方法采用Sobel边缘算子快速检测出图像所有可能的边缘,通过Zernike矩算子对所有可能的边缘进行重新检测,最后,检测出图像的亚像素边缘并计算其精确位置。由于采用Sobel算子检测出可能的边缘使后续Zernike矩算子检测范围缩小,从而减小了运算量,提高了运算速度。对实际CT图像进行的实验结果表明:改进的Zernike矩工业CT图像边缘检测精度绝对误差<0.24 pixel,改进算法的运算速度提高了约70%。     

基于Hough变换的高精度机器视觉对准系统的研究

随着集成电路特征尺寸的不断减小,I/O引脚数日益增加。对于高密度封装,尤其是2.5D/3D封装中,电子元件和基底快速而准确的对准十分关键。利用高性能CCD搭建了一套精密的光学视觉对准系统,并采用Hough变换算法对芯片和基底进行对准试验。采集的图像经过去噪预处理后采用形态学边缘检测方法提取对齐标记,并通过Hough变换得到4组平行直线,然后计算基底的位移和旋转角度并完成对准。使用Matlab编程配准,程序运行时间约为4.2 s,旋转参数的误差小于1.2°,x和y轴的平移误差均小于1 pixel。试验结果表明基于Hough变换算法的光学视觉对准系统可以快速而精确地实现芯片和基底对准,满足IC封装需求。     

Geometrically robust image watermarking using scale-invariant feature transform and Zernike moments

In order to resist geometric attacks, a robust image watermarking algorithm is proposed using scaleinvariant feature transform (SIFT) and Zernike moments. As SIFT features are invariant to rotation and scaling, we employ SIFT to extract feature points. Then circular patches are generated using the most robust points. An invariant watermark is generated from each circular patch based on Zernike moments.The watermark is embedded into multiple patches for resisting locally cropping attacks. Experimental results show that the proposed scheme is robust to both geometric attacks and signal processing attacks.     

空间矩和Zernike矩亚像素边缘算子分析

讨论了空间矩、Zernike矩两个亚像素边缘算子的运行时间和定位精度。分析结果表明,Zernike具有更快的运行速度,当计算3个用于边缘定位的参数时,其运行时间较空间矩算子节约了50%。理论分析了空间矩和Zernike矩算子的关系,并推导出了两个算子边缘距离为l的差值公式。测试结果表明,当两个算子的l都限制在中心像素内时,空间矩算子的边缘厚度多达3个像素,而Zernike矩算子的边缘厚度小于1个像素,可见Zernike矩算子的定位精度为真正的亚像素级。经比较,Zernike矩算子的运行时间和定位精度均好于空间矩算子。     

Performance analysis of quantitative phase retrieval method in Zernike phase contrast X-ray microscopy

Since the invention of Zernike phase contrast method in 1930,it has been widely used in optical microscopy and more recently in X-ray microscopy.Considering the image contrast is a mixture of absorption and phase information,we recently have proposed and demonstrated a method for quantitative phase retrieval in Zernike phase contrast X-ray microscopy.In this contribution,we analyze the performance of this method at different photon energies.Intensity images of PMMA samples are simulated at 2.5 keV and 6.2 keV,respectively,and phase retrieval is performed using the proposed method.The results demonstrate that the proposed phase retrieval method is applicable over a wide energy range.For weakly absorbing features,the optimal photon energy is 2.5 keV,from the point of view of image contrast and accuracy of phase retrieval.On the other hand,in the case of strong absorption objects,a higher photon energy is preferred to reduce the error of phase retrieval.These results can be used as guidelines to perform quantitative phase retrieval in Zernike phase contrast X-ray microscopy with the proposed method.     

基于消失点检测算法的束靶红外图像畸变校正

传统的霍夫变换、Cannylines直线检测算法、霍夫概率变换方法在图像上的直线检测效果不佳,存在检测线段不连续不正确的问题,因而,利用Sobel滤波对红外图像横轴和纵轴两个方向分别进行锐化,通过线段检测(LSD)算法实现线段特征检测,进而经线段聚类拟合获得图像中完整的直线,通过对直线交点计算获得消失点,最后依据透视关系计算得到校正图像。实验结果表明,该方法可以实现对中性束红外图像的自动有效校正。     

基于模糊快速Hough变换的盘孔边界识别方法

为了快速准确地识别出某型航空发动机篦齿盘均压孔的边界,提出一种新的模糊快速Hough变换.利用局部梯度信息将检测圆所需的3D Hough变换转化为一个2D Hough变换检测圆心位置和一个1D Hough变换检测圆的半径.在检测圆心位置时,对2D参量空间进行多分辨率分级,通过迭代计算由粗到精逐步细化参量空间.采用模糊投票的方法来处理边缘像素位置和梯度方向的不确定性.通过实验对比了模糊快速Hough变换与标准Hough变换、随机Hough变换进行盘孔边界识别的效果,结果表明模糊快速Hough变换可以快速准确地识别出盘孔的边界,性能优于另外两种算法.     

A local voting and refinement method for circle detection

Improving the accuracy of circle detection in images is important for feature detection in remote sensing imagery. The standard Hough transform detects circles from the whole image space, which inclines to be disturbed by noise and the imperfection of the edge information. In this paper, a method of voting and determining circles locally is proposed. This method improves the accuracy and stability of circle detection in images with noise, incomplete edge information and complex backgrounds. Synthetic and real satellite images are used to demonstrate the effectivity of circle detection of the proposed method.     

多特征融合的交通标志检测与分类研究

针对国内交通标志的属性特征,提出了一种基于颜色和形状的交通标志分类算法。采用RGB模型分量值互减的方法对自然背景下的交通标志图像进行分割,提取出感兴趣区域,对标志区域进行形态学处理、边缘检测,提取标志外层轮廓。利用Hough变换识别交通标志线性特征。在识别交通标志颜色和几何形状的基础上,利用交通标志的分类知识实现交通标志的快速分类。实验结果表明,该方法容易实现,满足实时性要求,并能达到较好的分类效果。