低对比度图像高精度轮廓三维重建算法研究

为了解决低对比度成像条件下传统三维轮廓重建算法精度偏低的问题,提出一种基于邻域距离最小化准则、由粗到细的高精度轮廓三维重建算法。首先使用 Canny 算子对目标图像进行边缘检测,再利用目标形状、尺寸等先验信息剔除分割出的虚假目标边缘。随后,计算边缘点法线方向上的梯度加权值作为工件初始化轮廓,根据左右一致性原则筛选出粗匹配点对,在匹配点对邻域附近使用亚像素进行精细搜索,利用邻域距离最小化准则估算出当前最佳亚像素匹配点对,并将其用于激光刻形工件的尺寸测量,总体精度可达 0.1mm。该方法有效降低了轮廓重建算法对边缘定位精度的依赖,同时提高了轮廓重建精度。     

基于图像处理的工件检测

研究了基于图像处理的工件轮廓检测技术的流程及算法,通过图像滤波、图像增强、阈值分割、边缘检测、边缘定位和参数测量及拟合等一系列算法,可以测出被检测工件是否符合要求及其误差范围。     

Integrated phase unwrapping algorithm for the measurement of 3D shapes by Fourier transform profilometry

An integrated and reliable phase unwrapping algorithm is proposed based on residues and blocking-lines detection, closed contour extraction and quality map ordering for the measurement of 3D shapes by Fourier-transform profilometry （FTP）. The proposed algorithm first detects the residues on the wrapped phase image, applies wavelet analysis to generate the blocking- lines that can just connect the residues of opposite polarity, then carries out the morphology operation to extract the closed contour of the shape, and finally uses the modulation intensity information and the Laplacian of Gaussian operation of the wrapped phase image as the quality map. The unwrapping process is completed from a region of high reliability to that of low reliability and the blocking-lines can prevent the phase error propagation effectively. Furthermore, by using the extracted closed contour to exclude the invalid areas from the phase unwrapping process, the algorithm becomes more efficient. The experiment shows the effectiveness of the new algorithm.     

几种经典活动轮廓图像分割模型综述

图像分割是将图像进行特征提取的关键技术。图像分割算法研究成果较多,活动轮廓模型是图像分割获取边缘信息的重要方法。阐述了几种经典的活动轮廓方法,通过大量仿真实验对几种方法进行比较,指出现阶段图像分割遇到的问题并展望其研究趋势。     

GPU实现的椒盐噪声自适应中值滤波算法

提出了一种基于先检测、后滤波的椒盐噪声滤除GPU实现算法。该算法首先依据椒盐噪声的特征,将图像像素分为噪声和信号,然后对噪声像素作标准中值滤波,如果中值为信号,则用中值代替噪声像素灰度值;如果中值为噪声,则取中值邻域,如果中值邻域为信号,则用它代替噪声像素灰度值;否则扩大邻域窗口,重复算法。但随着图像规模的增大,在CPU上执行的时间显著增加。分析并利用图形处理器（GPU）的并行处理特征,并在GPU上实现了本文算法。实验结果表明所提出的算法较经典的自适应中值滤波算法有较好的去噪效果和边缘保护能力,并且随着图像规模的增大,算法执行时间较CPU可以提高最多3个数量级。     

Depth estimation system suitable for hardware design

Depth estimation is an active research area with the developing of stereo vision in recent years. It is one of the key technologies to resolve the large data of stereo vision communication. Now depth estimation still has some problems, such as occlusion, fuzzy edge, real-time processing, etc. Many algorithms have been proposed base on software, however the performance of the computer configurations limits the software processing speed. The other resolution is hardware design and the great developments of the digital signal processor (DSP), and application specific integrated circuit (ASIC) and field programmable gate array (FPGA) provide the opportunity of flexible applications. In this work, by analyzing the procedures of depth estimation, the proper algorithms which can be used in hardware design to execute real-time depth estimation are proposed. The different methods of calibration, matching and post-processing are analyzed based on the hardware design requirements. At last some tests for the algorithm have been analyzed. The results show that the algorithms proposed for hardware design can provide credited depth map for further view synthesis and are suitable for hardware design.     

基于改进 K 近邻算法的小型汽车号牌识别系统

为了对现有小型汽车号牌识别系统进行优化,改善车牌字符识别系统性能,借助 OpenCV 图像处理开源库,在车牌图像预处理阶段采用均值滤波方法提高图像质量,采用 Sobel 边缘检测算子对图像边缘进行提取,利用交替的膨胀、腐蚀操作结合车牌长宽比实现车牌轮廓定位,并根据列像素值对车牌字符进行切割,最后采用改进的 K 近邻算法对分割后的单个车牌字符进行识别。实验结果表明,基于改进 K 近邻算法的车牌识别系统处理时间为 2.08s,识别正确率达 91.3%。与传统的 K 近邻算法相比有着更高的识别率,与神经网络法相比,有着更快的识别速度。     

一种融合边缘和区域特征的主动轮廓图像分割

传统的主动轮廓模型只利用图像的边缘或者只利用区域特征实现图像分割。在有些情况下图像分割效果较差．本文给出了一种综合利用图像边缘和区域特征的主动轮廓图像分割方法．实验表明,演变后的曲线与图像的边缘是吻合的,图像分割的结果较好．而对相同的图像应用传统的主动轮廓分割算法得到的图像分割结果则很差．这说明新算法明显提高了传统算法的图像分割性能．     

基于Halcon的光纤端面尺寸检测方法

针对传统光纤端面尺寸检测几何尺寸误差大、效率低的弊端,采用一种基于Halcon的光纤端面尺寸检测方法,利用数字图像处理算法,采用中值滤波的方法对图像进行预处理,消除图像噪声,并对图像进行二值化及形态学处理,选用Canny算子作为边缘检测算子确定像素级边缘,该方法边缘检测性能较好,且具有较强的抗噪声能力|再从选取的边缘中选出类圆度高的部分边缘进行共圆轮廓合并、拟合,通过拟合的椭圆和圆得到光纤半径、不圆度、同心度等几何参数。实验结果表明,纤芯和包层半径可以精确到万分之一,不圆度和同心度可以精确到小数点后8位,测量精度较高且不受操作水平影响。     

基于HLSL的Shadow Map实时阴影实现

为提高三维场景实时阴影渲染性能,通过图形硬件编程方法,采用HLSL实现Shadow Map。实验表明,GPU的渲染速度远远大于CPU,在计算负载由传统的CPU转移到GPU处理之后,算法的运行效率得到明显提升。     

一种新的红外图像人体检测算法

提出一种新的红外图像人体检测算法并实现。首先采用灰关联分析理论从单幅红外图像中获取边缘轮廓清晰的人体候选区域,然后融合边缘方向梯度直方图特征、区域密度特征及人体形状特征来描述人体候选区域,以提高区域特征的描述准确性,最后使用支持向量机分类器对目标进行分类,在不同的红外图像测试集中进行实验,结果表明,所提出的算法识别效果良好,并具有一定的鲁棒性。     

一种基于小波变换的动态轮廓模型

梯度矢量流模型广泛应用于计算机视觉与图像分割,但是受噪声的影响,在处理许多医学图像时不能正确收敛到目标轮廓．本文结合小波变换与梯度矢量流模型提出了一种新的动态轮廓模型．新模型定义小波变换矢量替代梯度矢量,并用多尺度小波变换对图像进行预处理．新模型具有更好的抗噪性,并能够得到连续的边缘点．结果表明新模型提高了动态轮廓模型方法分割复杂图像的能力,是一种有效的医学图像分割方法．     

Automatic segmentation of bladder in CT images

Segmentation of the bladder in computerized tomography （CT） images is an important step in radiation therapy planning of prostate cancer. We present a new segmentation scheme to automatically delineate the bladder contour in CT images with three major steps. First, we use the mean shift algorithm to obtain a clustered image containing the rough contour of the bladder, which is then extracted in the second step by applying a region-growing algorithm with the initial seed point selected from a line-by-line scanning process. The third step is to refine the bladder contour more accurately using the rolling-ball algorithm. These steps are then extended to segment the bladder volume in a slice-by-slice manner. The obtained results were compared to manual segmentation by radiation oncologists. The average values of sensitivity, specificity, positive predictive value, negative predictive value, and Hausdorffdistance are 86.5%, 96.3%, 90.5%, 96.5%, and 2.8 pixels, respectively. The results show that the bladder can be accurately segmented.     

Blocking optimized SIMD tree search on modern processors

Tree search is a widely used fundamental algorithm. Modern processors provide tremendous computing power by integrating multiple cores, each with a vector processing unit. This paper reviews some studies on exploiting single instruction multiple date (SIMD) capacity of processors to improve the performance of tree search, and proposes several improvement methods on reported SIMD tree search algorithms. Based on blocking tree structure, blocking for memory alignment and dynamic blocking prefetch are proposed to optimize the overhead of memory access. Furthermore, as a way of non-linear loop unrolling, the search branch unwinding shows that the number of branches can exceed the data width of SIMD instructions in the SIMD search algorithm. The experiments suggest that blocking optimized SIMD tree search algorithm can achieve 1.6 times response speed faster than the un-optimized algorithm.     

一种基于DCT域与图像置乱的数字水印算法研究

提出了一种将水印图像进行Arnold置乱后嵌入到经DCT域进行变化的载体图像中的数字水印算法。算法研究结果表明水印具有较好的不可见性及健壮性。同时,文中采用不同图像处理方式对嵌入水印后的图像进行了攻击实验,实验表明该算法对于JPEG压缩具有较好的鲁棒性。     

二维条码技术在服装吊牌中的应用

阐述现阶段品牌服装防伪现状及应用二维条码在服装吊牌上的可行性。针对商标图像以色块图为主、颜色少的特点,在对商标图像进行边缘检测、轮廓跟踪及轮廓特征信息提取的基础上,提出了一种商标图像大比例压缩算法,实现将服装吊牌中商标和服装其他特征信息制成一种带PDF417二维条形码的服装吊牌。通过识读出二维条码中的服装文字信息及商标图案和服装吊牌上信息相对比,实现服装吊牌的防伪。     

A maximum a posteriori super resolution algorithm based on multidimensional Lorentzian distribution

This paper presents a threshold-free maximum a posteriori （MAP） super resolution （SR） algorithm to reconstruct high resolution （HR） images with sharp edges. The joint distribution of directional edge images is modeled as a multidimensional Lorentzian （MDL） function and regarded as a new image prior. This model makes full use of gradient information to restrict the solution space and yields an edge-preserving SR algorithm. The Lorentzian parameters in the cost function are replaced with a tunable variable, and graduated nonconvexity （GNC） optimization is used to guarantee that the proposed multidimensional Lor- entzian SR （MDLSR） algorithm converges to the global minimum. Simulation results show the effectiveness of the MDLSR algorithm as well as its superiority over conventional SR methods.     

基于车辆轮廓对称与车牌定位信息融合的车辆检测方案(英文)

为了有效地定位交通监控图像中的车辆区域,提出了一种基于车辆轮廓对称和车牌定位信息融合的车辆检测方法. 该方法首先检测图像中的车辆轮廓竖直对称轴,然后以车辆轮廓对称轴位置为基准检测车牌水平和竖直对称轴,最后根据车牌横纵对称轴和车辆轮廓图像的水平、竖直投影进行车辆区域定位. 以450 张 15 类车型的图片为测试集进行了基于对称特征融合的车辆区域检测,并与基于车辆边缘、车牌、车辆纹理特征和车辆图像 Gabor 特征的 4 种方法进行了对比,实验结果表明基于车辆轮廓对称与车牌对称特征融合的车辆区域检测方法最优,其检测率和检测时间分别为 90. 7%和 125 ms.     

应用GPU加速结合压缩传感技术解宽角度电磁散射问题

本文基于矩量法（MOM）中阻抗矩阵与入射角度的不相关性,提出将压缩传感（CS）技术引入电磁散射问题的方法,以达到在不降低计算精度的前提下减少计算时间的目的.该方法结合了压缩感知和计算统一设备架构（CUDA）技术,通过利用图形处理器（GPU）的并行计算解决了宽角度的电磁散射问题.数值计算结果表明,该方法与传统计算方法相比,在保持精度的同时,大大降低了计算所需的时间.     

基于Canny和双线性插值的镍片边缘提取算法

手机锂电池保护板在生产过程中需要利用视觉检测镍片角度偏差、折叠等各类缺陷,但由于镍片尺寸小且这些缺陷在灯光下会产生不同程度的反光,导致获得的镍片图像边缘不清晰。为此,本研究提出了一种基于Canny算子和双线性插值的高亮镍片边缘提取算法。首先对原始图像分割出感兴趣区域并进行灰度处理,再利用Canny算子提取其像素级边缘,最后用双线性插值法提取其亚像素级边缘。为验证该算法的有效性,将其与工程中常用的Sobel 边缘提取算法进行实验对比,计算边缘内部包含面积的像素数量、等级及边缘提取的时间,判断两类算法在精度和效率上的优劣。实验结果表明,基于Canny 算子和双线性插值的高亮镍片边缘提取算法能精准提取镍片的亚像素边缘,提取的像素精度达到了0.1 pixel,平均边缘提取时间为0.835 s,比Sobel 节省了20.57%的时间,能够满足工业生产的精度需求与效率要求。