结构光测量自动聚焦系统开发和研究

为配合结构光测量系统来进行更深入的处理和测量,在以PC机为控制核心的基础上设计了一种自动聚焦系统,以实现对不同场景图像的亮度自动调节和精确聚焦功能。系统以Sobel-Tenengrad函数为评价函数,通过登山法搜索极值,在10 s内完成精确聚焦。通过该系统在不同场景下对四种灰度评价函数值进行计算,对其单峰性和鲁棒性进行分析和总结,经过实验后发现Sobel-Tenengrad函数、梯度向量平方函数、拉普拉斯函数综合性能良好,而方差函数未能表现出评价函数应具有的性能。     

一种改进的自动聚焦搜索算法及其实现

自动聚焦的过程就是镜头按照自动聚焦搜索算法来回搜索聚焦评价函数求最大值的过程。传统的爬山搜索算法会受到聚焦评价函数局部极值的干扰而不能准确聚焦,并且在大幅离焦状态下近聚焦缓慢。详细介绍了一种改进的自动聚焦搜索算法的原理和实现方法,它能有效地排除这种干扰,减少大幅离焦状态下近聚焦的时间,使系统可靠的聚焦。     

基于图像处理的自动聚焦技术及应用

自动聚焦技术是提高压痕直径测量系统测量精度、智能化和自动化的重要手段.介绍了采用图像处理法实现压痕直径测量系统的自动聚焦技术,核心就是选择一个合适的图像清晰度评价函数.在研究了众多图像清晰度评价函数的基础上,提出了基于向量模型和改进DCT变换的图像清晰度评价函数,实验表明,提出的算法具有良好的单峰性、准确性、稳定性、可靠性和快速性.最后通过基于COM组件技术的Matlab与VB混合编程来保证算法实现和软件设计.     

自动换片细胞显微图像分析仪自动聚焦系统的研究

针对自主研发的可自动换片的显微图像分析仪(Auto-Slide ICM),研制了切实可行的自动聚焦系统。详细描述了细胞图像聚焦评价函数、空场判别函数和支持自动换片的聚焦搜索策略等关键技术。基于此聚焦系统,Auto-Slide ICM可以实现无人干预快速连续扫描20张载玻片,提高了ICM的自动化程度和工作效率。     

基于高清网络摄像机的自动聚焦算法

针对传统的聚焦评价函数运算量大、峰值搜索算法易受干扰且视频质量反复变化的问题,实现一种较传统聚焦评价函数与爬山算法相结合的聚焦算法更好的自动聚焦算法.采用TI公司的TMS320DM368处理器自带的自动聚焦(AF)引擎作为硬件实现的聚焦评价函数;采用的峰值搜索算法将聚焦曲线分为聚焦区和散焦区,在散焦区使用大步长的GM(1,1)模型预测搜索方向,在聚焦区使用小步长的爬山算法搜索峰值.实验结果表明,该算法拥有更好地实时性与准确性,适用于高清网络摄像机的自动聚焦.     

自动聚焦技术在智能视频监控系统中的应用

将自动聚焦技术应用于智能视频监控系统中,采用轮廓波算法构建清晰度评价函数,并利用中心区域最优法选择聚焦区域。将自动聚焦技术应用与智能视频监控系统后可以有效提高系统图像采集质量,提升系统准确性。     

一种摄像头自动聚焦方法及硬件实现

提出了一种基于数字图像处理技术实现自动聚焦的方法,给出了一种改进的灰度差分法作为图像聚焦是否清楚的评价函数。对图像质量进行比较,根据比较结果由单片机驱动镜头到达聚焦点,实现自动聚焦。     

数字图像清晰度评价函数的研究与改进

通过分析常见的图像清晰度评价函数,针对自动对焦系统中图像清晰度评价问题,提出了一种基于聚焦窗口的改进梯度评价函数算法。改进后的算法具有计算量小、实时性好、评价曲线单峰性好、灵敏度高、聚焦检测效率高等特点,可以更好地满足自动对焦系统对图像清晰度评价的要求。     

基于FPGA的步进电机驱动及自动聚焦的实现

基于Xilinx公司的Spartan-IIE系列FPGA XC2S300E-6-PQ208C完成了一种聚焦马达驱动及自动聚焦的完整设计。该设计接收CCD图像传感器套件输出的图像信号,采用一种改进的灰度差分法作为聚焦评价函数,即将一场图像的所有像素的亮度值与周围像素的亮度值差的绝对值的和作为聚焦评价函数,根据相邻同场的聚焦评价函数的比较结果,配合相应的搜索策略来控制步进电机的转动方向,实现图像的自动聚焦。实际实现的聚焦效果优于改进前的聚焦算法。     

基于全自动控制显微镜的自动聚焦算法研究

图像自动聚焦评价函数的选择是垒自动控制显微镜无源方式自动聚焦系统的关键问露。对几种主要的图像聚焦评价函散(灰度方差算子、灰度梯度算子、能量谱方法等)进行了比较、研究，并在此基础上首次将改进的Laplacian算子作为聚焦评价函数引人自动聚焦之中,同时为了消除噪声的影响，引入了步长和阈值两个参数。实验结果表明，改进的LapIacian算子比其他评价函数更为准确、稳定和可靠，该算法已成功应用于显微镜自动词焦系统中。     

超大视场自适应快速对焦算法

为满足超大视场机器视觉自动对焦系统快速检测的要求,研究了一种基于对焦深度的自适应快速对焦算法。该算法采用粗对焦与精确对焦相结合的二级对焦策略,在不同的检测区域实现自适应选择最佳评价函数,实现自适应快速对焦。实验结果表明该算法在保持调焦精度的前提下,能够在大视场内快速聚焦,最终实现平均对焦时间小于0.5 s,一次性对焦成功率高达95%,满足自动对焦系统对高速、高精度自动对焦的要求。     

Optimal depth estimation by combining focus measures using genetic programming

Three-dimensional (3D) shape reconstruction is a fundamental problem in machine vision applications. Shape From Focus (SFF) is one of the passive optical methods for 3D shape recovery that uses degree of focus as a cue to estimate 3D shape. In this approach, usually a single focus measure operator is applied to measure the focus quality of each pixel in the image sequence. However, the applicability of a single focus measure is limited to estimate accurately the depth map for diverse type of real objects. To address this problem, we develop Optimal Composite Depth (OCD) function through genetic programming (GP) for accurate depth estimation. The OCD function is constructed by optimally combining the primary information extracted using one/or more focus measures. The genetically developed composite function is then used to compute the optimal depth map of objects. The performance of the developed nonlinear function is investigated using both the synthetic and the real world image sequences. Experimental results demonstrate that the proposed estimator is more useful in computing accurate depth maps as compared to the existing SFF methods. Moreover, it is found that the heterogeneous function is more effective than homogeneous function.     

显微视觉系统对柱状微零件自动聚焦技术研究

针对显微视觉中的柱状物体图像的清晰度问题,提出了一种实时检测图像特征并跟踪特征区域进行自动聚焦的方法。该聚焦算法包括聚焦评价函数、聚焦搜索算法和聚焦区域选择。该聚焦搜索算法实现了显微视觉系统下快速准确的聚焦,克服了爬山搜索算法的缺点,有效避免搜索结果陷入局部极大值。显微视觉中对聚焦区域的选择尤为重要,以图像特征区域作为聚焦区域,实时检测该特征区域进行聚焦,实现了在景深小于柱状物体半径的情形下对柱状物体边缘的精确聚焦。粗聚焦后电机位置的标准差为205μm,精聚焦后电机位置的标准差为37μm。实验结果表明,该自动聚焦方法能够满足微装配系统对显微视觉的聚焦需求。     

利用空间信息实现保留上下文体绘制

直接体绘制中,为了去除非感兴趣组织对感兴趣区的遮挡,增强感兴趣区域的显示效果,提出利用空间信息的保留上下文体绘制方法。通过人机交互设定焦点,快速定位感兴趣区;提取光线上每个采样点与焦点的空间位置以及夹角信息;根据这些信息构建高斯衰减函数,作用于当前采样点的不透明度,控制光线合成,以突出显示感兴趣区。对CT头部数据的实验结果表明,该方法可以去除非感兴趣组织对感兴趣组织的遮挡,突出显示感兴趣区,且具有良好的人机交互性。     

基于静态分析的函数调用关系研究

为了帮助研发人员理解复杂系统的架构,通过对源码进行静态分析,在此基础之上,重点对函数调用关系进行研究,并且基于开源编译器ncc实现了函数调用关系的解析.实验结果表明该方法可以有效地获取函数的调用关系且准确地解析钩子函数对应的回调函数.     

自动对焦显微镜系统设计及仿真

设计了一种基于条纹投影的自动对焦显微镜系统。通过红外光源将光栅掩膜板投射到被测物表面,用于对焦判断。通过白光光源进行系统照明。使用带通滤光片分离出由红外光源投射的光栅像,并由线阵CCD采集,用于离焦量和离焦方向的判断。由白光光源照射得到被测物的像,并由面阵CCD接受用于直接观测。使用Tracepro对设计的系统进行仿真,分析得到适用于线阵CCD采集的光栅图的一维清晰度评价函数,并使用系统对不同被测物进行仿真对焦实验与误差分析。仿真结果表明,本系统可对不同被测物进行自动对焦。     

一种改进的数字图像清晰度评价函数研究

图像自动聚焦时，由于噪声和不同光照条件影响图像质量，实时评价图像清晰度效果较差。本文比较了能量梯度函数、频谱函数、灰度熵函数、灰度变化函数评价图像清晰度的优劣，提出了一种改进的能量梯度闽值方法评价图像清晰度，建立了数学模型，并给出了三种不同物体的数字图像聚焦重复精度的试验结果和分析。试验结果表明：实时评价图像清晰度该方法速度快，计算量小，信噪比高，可靠性好，聚焦重复精度高。     

MSIMCNN: Multi-scale inception module convolutional neural network for multi-focus image fusion

The aim of image fusion is to obtain a clear image by combining useful information coming from multiple images. However, the fused image usually has the problem of artifacts and unclear boundary. To address these problems, a deep convolutional neural network based framework for multi-focus image fusion is proposed in this paper, called multi-scale inception module convolutional neural network (MSIMCNN). MSIMCNN converts the entire image into a binary mask to estimate the focus characteristics, and obtains the clear boundary between focus and defocus. First of all, a pair of focus images and the corresponding feature images detected by the Laplace operator are inputted into the network. The Laplace operator can detect the edge and gradient of focus in the image, which can help us accurately reconstruct the focused area in the focus map and distinguish the focus and defocus boundaries. Then, in the feature extraction stage, different scales of convolution kernels are designed to extract the rich and complementary features at different scales of the source images. At the same time, the inception module is added to increase the width of the network and reduce the parameters, which can extract more focus features required for image reconstruction and reduce the complexity. Finally, the focus map of the source image pair can be obtained in the feature reconstruction stage. In this stage, an efficient method is proposed to make the focus mask, which is used for the calculation of the loss function and the generation of the training set. The experimental results on different data sets confirm the superiority and effectiveness of MSIMCNN compared with other methods.

     

In‐field assessment of display resolution and noise: Performance evaluation of a commercial measurement system

Abstract— Two key metrics of image quality for high‐fidelity displays, including medical displays, are resolution and noise. Until now, these properties have been primarily measured in laboratory settings. For the first time, a system consisting of a CCD camera and analysis software has been made commercially available for measuring the resolution and noise of medical displays in a clinical setting. This study aimed at evaluating this new product in terms of accuracy and precision. In particular, the project involved the measurement of the modulation transfer function (MTF) and the signal‐to‐noise ratio (SNR) of two medical imaging displays, one cathode‐ray tube (CRT) display and one liquid‐crystal display (LCD) using this camera/software system. To assess the system's precision, measurements were made multiple times at the same setting. To check for accuracy, the results were compared with published values of the MTF and noise for the same displays. The performance of the system was also ascertained as a function of the focus setting of the camera. The results indicated that for the LCD, when the camera is focused within ±0.6 mm of the optimum focus setting, the MTF values lie within approximately 14% of the best focus MTF at the Nyquist frequency and 11% of the optimum overall sharpness (∫ MTF² df). Similar results were obtained in the horizontal and vertical directions. For the CRT, this focus produced vertical and horizontal MTF values at the Nyquist frequency within 15.2% and 61.2% of the optimum focus MTF, respectively. The figures in terms of overall sharpness were 3.0% and 0.7%. The results for the noise measurements showed a repeatability of 3% for the LCD and 13% for the CRT and a relative (but not absolute) magnitude of the noise between the two displays reflective of prior measurements. Overall, the measurement system yielded reasonably precise resolution and noise results for both display devices. The accuracy was traceable to published results only for the MTF and for relative level of display noise with differences in the absolute magnitude of noise between current and prior measurements attributed to variations in the non‐standard techniques applied for display noise measurements.     

基于聚类欠采样的集成分类算法

不平衡数据常出现在各应用领域中,传统分类器往往关注于多数类样本而导致样本分类效果不理想。针对此问题,提出一种基于聚类欠采样的集成分类算法(ClusterUndersampling-AdaCost, CU-AdaCost)。该算法通过计算样本间维度加权后的欧氏距离得出各簇的样本中心位置,根据簇心邻域范围选择出信息特征较强的多数类样本,形成新的训练集;并将训练集放在引入代价敏感调整函数的集成算法中,使得模型更加关注于少数类别。通过对6组UCI数据集进行对比实验,结果表明,该算法在欠采样过程中抽取的样本具有较强的代表性,能够有效提高模型对少数类别的分类性能。