首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献,搜索用时 0 毫秒
1.
Naturally deformed ice contains subgrains with characteristic geometries that have recently been identified in etched surfaces using high-resolution light microscopy (LM). The probable slip systems responsible for these subgrain boundary types can be determined using electron backscattered diffraction (EBSD), providing the etch features imaged with reflected LM can be retained during EBSD data acquisition in a scanning electron microscope (SEM). Retention of the etch features requires that the ice surface is stable. Depending on the pressure and temperature, sublimation of ice can occur. The equilibrium temperature for a low pressure SEM operating at 1 × 10(-6) hPa is about -112°C and operating at higher temperatures causes sublimation. Although charging of uncoated ice samples is reduced by sublimation, important information contained in the etch features are removed as the surface sublimes. We developed a method for collecting EBSD data on stable ice surfaces in a low pressure SEM. We found that operating at temperatures of <-112°C reduced sublimation so that the original etch surface features were retained. Charging, which occurred at low pressures (<1.5 × 10(-6) to 2.8 × 10(-5) hPa) was reduced by defocusing the beam. At very low pressures (<1.5 × 10(-6) hPa) the spatial resolution with a defocused beam at 10 kV was about 3 μm in the x-direction at -150°C and 0.5 μm at -120°C, because at higher temperature charging was less and only a small defocus was needed to compensate it. Angular resolution was better than 0.7° after orientation averaging. Excellent agreement was obtained between LM etch features and EBSD mapped microstructures. First results are shown, which indicate subgrain boundary types comprised of basal (tilt and twist) and nonbasal dislocations (tilt boundaries).  相似文献   

2.
In traditional cancer diagnosis, (histo)pathological images of biopsy samples are visually analysed by pathologists. However, this judgment is subjective and leads to variability among pathologists. Digital scanners may enable automated objective assessment, improved quality and reduced throughput time. Nucleus detection is seen as the corner stone for a range of applications in automated assessment of (histo)pathological images. In this paper, we propose an efficient nucleus detector designed with machine learning. We applied colour deconvolution to reconstruct each applied stain. Next, we constructed a large feature set and modified AdaBoost to create two detectors, focused on different characteristics in appearance of nuclei. The proposed modification of AdaBoost enables inclusion of the computational cost of each feature during selection, thus improving the computational efficiency of the resulting detectors. The outputs of the two detectors are merged by a globally optimal active contour algorithm to refine the border of the detected nuclei. With a detection rate of 95% (on average 58 incorrectly found objects per field‐of‐view) based on 51 field‐of‐view images of Her2 immunohistochemistry stained breast tissue and a complete analysis in 1 s per field‐of‐view, our nucleus detector shows good performance and could enable a range of applications in automated assessment of (histo)pathological images.  相似文献   

3.
基于Otsu方法的钢轨图像分割   总被引:1,自引:0,他引:1  
由于钢轨图像灰度分布不均,一般的图像分割法难以将目标从背景中分割出来,故本文提出了目标方差加权的类间方差阈值分割法对钢轨图像进行阈值分割。分析了钢轨图像的特点,总结了加权的目标方差(Otsu)方法及其它全局阈值分割法对钢轨图像分割存在的问题。然后,对Otsu方法进行改进,以目标出现的概率为权重,对类间方差的目标方差加权,使分割阈值靠近单模直方图的左边缘和双模直方图的谷底。最后,计算图像的错误分类误差、钢轨图像的缺陷检测率和误检率来验证算法的有效性。实验结果表明,改进的Otsu方法能有效地分割钢轨图像,错误分类误差接近0。与其它阈值分割法如Otsu法、其它改进的Otsu法、最大熵阈值分割法相比,本文方法对钢轨图像的分割效果更优,缺陷检测率和误检率分别为93%和6.4%,适合机器视觉缺陷检测的实时应用。  相似文献   

4.
木材表面图像的缺陷分割与类型识别方法   总被引:1,自引:0,他引:1  
为了识别死节、活节、虫眼三种木材表面缺陷,采用Gabor变换和模糊C均值聚类进行缺陷分割;采用数学形态学运算对分割图像进行了后处理;获取了木材缺陷区域的12维频率能量参数和2维几何形状参数;用支持向量机进行木材表面缺陷类型的识别。采用Gabor变换和模糊C均值聚类方法对死节、活节、虫眼三种木材表面缺陷的分割精度都达到94%以上,支持向量机对缺陷类型分类正确率达到93%以上,这说明本文的方法对木材表面缺陷的分割与识别是可行的。  相似文献   

5.
为了克服人工观测法中风浪及主观因素的不利影响,提出了以图像采集和分析为核心的船舶吃水深度检测方法。设计实现了以爬壁机器人为载体携带网络摄像机的水尺图像采集的系统,该系统能在平板电脑的控制下游走于复杂面型的船侧板完成水尺拍摄,且可连续采集涵盖多个波浪周期的高清图像(1600pixel×1200pixel)。基于形态学和神经网络算法对图像中的水尺字符进行预处理和判别,有效提高了“6”、“8”、“9”几个相似字符的区分度。同时基于彩色图像分割算法对图像中的吃水线进行识别,通过对比吃水线在数值化水尺上的相对位置来确定船舶吃水深度,成功消除了波浪浸润所导致的假水线的干扰,从而实现了吃水线位置的自动判定。实验表明,该方法的最终识别精度可达1mm,明显高于人工目测法所能达到的5mm。此外,还特别利用现场测量数据对比证明了综合运用多幅图像数据来降低风浪干扰的必要。

  相似文献   

6.
为了克服人工观测法中风浪及主观因素的不利影响,提出了以图像采集和分析为核心的船舶吃水深度检测方法。设计实现了以爬壁机器人为载体携带网络摄像机的水尺图像采集的系统,该系统能在平板电脑的控制下游走于复杂面型的船侧板完成水尺拍摄,且可连续采集涵盖多个波浪周期的高清图像(1600pixel×1200pixel)。基于形态学和神经网络算法对图像中的水尺字符进行预处理和判别,有效提高了“6”、“8”、“9”几个相似字符的区分度。同时基于彩色图像分割算法对图像中的吃水线进行识别,通过对比吃水线在数值化水尺上的相对位置来确定船舶吃水深度,成功消除了波浪浸润所导致的假水线的干扰,从而实现了吃水线位置的自动判定。实验表明,该方法的最终识别精度可达1mm,明显高于人工目测法所能达到的5mm。此外,还特别利用现场测量数据对比证明了综合运用多幅图像数据来降低风浪干扰的必要。

  相似文献   

7.
研究了温室内灌溉对象的实时采集和识别技术,以及图像处理与分析软件系统的开发.建立了基于图像识别的自动灌溉水车系统,对信号采集、图像处理、数据传输交换等主要问题作了较深入的研究.提出了基于色彩因子的图像分割算法,和传统方法相比,在不影响分割效果的同时大大提高了图像分割处理的实时性和准确性.试验结果表明,该系统运行良好,具有广阔的应用前景.  相似文献   

8.
面向机器视觉检测鉴别的语义分割卷积神经网络(Convolutional Neural Network,CNN)模型能识别、测量被测对象的零部件、尺寸等特征,针对机器视觉检测鉴别增加识别零部件或关键部位的需求,以及进一步迁移学习会损失CNN模型部分权值的问题,提出一种基于标签预留Softmax算法的语义分割迁移学习技术....  相似文献   

9.
用机器视觉检测集成电路芯片的图像分割方法研究   总被引:2,自引:0,他引:2  
在研制检测集成电路芯片的机器视觉系统中,研究运用Mahalanobis距离方法,对摄取的芯片图像进行图象分割。实验结果表明,对处于环境复杂、低对比度、细节多的芯片图象能够产生很好的分割效果。该方法鲁棒性强,能保证分割质量,能显著提高机器视觉的检测精度。亦可用于对其它产品的尺寸及表面质量检验测量。  相似文献   

10.
为了解决汽车门锁人工检测劳动强度大、效率和精度低的问题,设计了一套基于机器视觉的汽车门锁自动检测系统,该系统由硬件系统和软件系统组成。针对门锁表面对比度低、装配件多和结构复杂的问题,研究了改进的距离保持水平集图像分割算法和改进的SIFT图像匹配算法,最后将这些算法在计算机中编程实现,完成图像处理软件与系统界面软件设计。测试结果表明,该系统硬件选型合理,软件稳定性好、效率高,提高了汽车门锁检测的效率与精度,具有很高的实际意义和经济价值。同时,该系统也可推广到其他工业装配件的质量检测中。  相似文献   

11.
    
Y. ZOU  B. LEI  F. DONG  G. XU  S. SUN  P. XIA 《Journal of microscopy》2017,266(2):153-165
Partitioning epidermis surface microstructure (ESM) images into skin ridge and skin furrow regions is an important preprocessing step before quantitative analyses on ESM images. Binarization segmentation is a potential technique for partitioning ESM images because of its computational simplicity and ease of implementation. However, even for some state‐of‐the‐art binarization methods, it remains a challenge to automatically segment ESM images, because the grey‐level histograms of ESM images have no obvious external features to guide automatic assessment of appropriate thresholds. Inspired by human visual perceptual functions of structural feature extraction and comparison, we propose a structure similarity‐guided image binarization method. The proposed method seeks for the binary image that best approximates the input ESM image in terms of structural features. The proposed method is validated by comparing it with two recently developed automatic binarization techniques as well as a manual binarization method on 20 synthetic noisy images and 30 ESM images. The experimental results show: (1) the proposed method possesses self‐adaption ability to cope with different images with same grey‐level histogram; (2) compared to two automatic binarization techniques, the proposed method significantly improves average accuracy in segmenting ESM images with an acceptable decrease in computational efficiency; (3) and the proposed method is applicable for segmenting practical EMS images. (Matlab code of the proposed method can be obtained by contacting with the corresponding author.)  相似文献   

12.
灰度直方图和支持向量机在磁环外观检测中的应用   总被引:1,自引:3,他引:1  
本文提出了一套基于灰度直方图和支持向量机的磁环自动分类系统。为了用低维的灰度信息来描述磁环的特征,提出了一套图像处理的算法。将图像从背景分离之后,进行灰度直方图处理来提取灰度特征。接着采用主分量分析法,将灰度统计信息由256维向量降低到20维向量,以这20维向量作为输入,用支持向量机进行分类。最后,经过训练得到最优分类函数,分类正确率达到97.3%。  相似文献   

13.
    
1Introduction Computer aideddiagnosisofmammo grams[12]usestheoutputofthecomputerizeda nalysisofmammogramsasa\"secondopinion\"to assistaradiologistindetectinglesionsandin makingdiagnosisdecisions.Automatedextrac tionofthebreastregionfrommammogramsis animportantpreprocessingstepforthecomput er aideddiagnosis.Byexcludingthebackground region,furthersearchoperationforabnormali tiesarelimitedtothebreastregion.Withoutun dueinfluencefromthebackgroundregion,the reliabilityandefficiencyoffurtheranalysisca…  相似文献   

14.
极片作为锂离子电池的重要组件,在涂覆、辊压等环节中,表面容易产生划痕、露箔等缺陷,这些缺陷会严重影响电池的质量和使用寿命,从而使得电池极片表面缺陷检测和管控工序是锂离子电池生产过程中不可缺少的工艺环节。首先对锂离子电池极片的生产工艺进行介绍,并对生产过程中可能产生极片表面缺陷的原因和缺陷种类进行分析;然后阐述了用机器视觉代替人工对极片进行自动化检测的极片表面缺陷识别方法,主要介绍了传统机器视觉缺陷检测方法的原理以及优缺点,并深入分析了深度学习在极片表面缺陷检测领域中应用的原理和流程,同时对目标检测算法中的单、双阶段算法在锂离子电池极片表面缺陷检测中的应用进行重点分析与比较;最后对基于深度学习的机器视觉检测方法在锂离子电池极片表面缺陷检测中的未来发展方向进行展望,为该领域的研究人员提供更多参考。总的来说,极片表面缺陷检测技术的发展不仅依赖于工业相机等硬件设备的技术突破,更需要软件算法的不断优化和创新,软件和硬件的协同工作才能在保证检测精度的同时,提高检测效率和降低检测成本,进一步推动锂离子电池产业的高质量发展。  相似文献   

15.
介绍了机器视觉系统的组成,分析了各种视觉识别技术在农业机械中的应用特点,最后提出其发展趋势和存在的问题。  相似文献   

16.
高光谱图像分类是利用高光谱数据图谱合一且光谱信息丰富的特点,对图像中的每个像素进行分门别类,以达到对地物目标进行高精度分类和自动化识别的目的,是对地观测的重要组成部分。在分析高光谱图像特点的基础上,本文从普通机器学习和深度学习这两方面对高光谱图像像素级分类的研究进展及效果进行总结、评述和比较,通过具体实验的结果对比,直观地展现各种算法的优劣。针对高光谱分类问题,本文从两个方面对今后的研究方向及发展前景进行了分析和展望。一方面,在算法研究上,高光谱图像分类算法可在保证分类精度的前提下降低算法的复杂度,利用多源遥感数据、多特征综合、多尺度复合,提升小样本、少参数分类模型的分类精度,适应智能化、快速化高光谱遥感对地观测的发展要求;另一方面要紧密结合市场应用需求,重视高光谱图像在实际中的应用,研究具有市场竞争力的高效分类算法,提升高光谱图像分类在遥感技术应用领域的竞争力。  相似文献   

17.
针对无人机图像中图像分辨率低、背景杂乱等问题,提出了一种电力线图像自动检测方法。通过使用机器学习方法对无人机采集的图像进行自动识别,可以排除噪声区域图像,准确识别出无人机图像中的电力线部分。通过使用 9 张无人机采集的图像对所提方法进行了验证,结果表明所提出的方法可以有效地进行电力线图像的自动识别。  相似文献   

18.
    
This paper describes an image processing method for discriminating the inter‐ and intragranular delta phase precipitates in Inconel 718 (IN 718). The successive practical operations and the motivations of their choices are presented in detail. The method was applied to IN 718 specimens heat treated with different parameters to produce microstructures containing various amounts of both types of precipitates. They were characterized by electron microscopy in backscattered electron imaging. The main difficulty arose from the fact that the brightness distributions of inter‐ and intragranular precipitates partially overlap. Additional information on their morphology and their spatial distribution had to be exploited in order to differentiate them. The shape and the orientation of the precipitates were evaluated using the structure tensor, an operator that quantifies the directionality of the intensity distribution in an image. The distance between parallel precipitates was also used as an additional property to identify clusters of intragranular precipitates.  相似文献   

19.
眼底图像中的视盘在青光眼筛查和诊断中起着重要作用。因此,从眼底图像中对视盘进行准确、快速地定位与分割具有重要意义。在过去,研究者们已经进行了对视盘的深入研究,但如何提高定位准确率和分割精度仍是视盘分割的一大难题。对此本文提出一种采用深度学习结构U-Net的视网膜视盘自动分割的方法,该方法结合机器学习,通过深度网络提取输入图像的视盘特征,从而得出相应的分割结果图。相对于传统的视盘分割方法,本文的U-Net神经网络能够有效学习有利于分割视盘的特征,从而提高分割的精确度,而且分割耗时更短。  相似文献   

20.
应用机器视觉技术的齿轮测量方法   总被引:1,自引:2,他引:1  
应用IMAQVision工具包在LabVIEW虚拟仪器平台上可以快速、灵活地开发齿轮测量的机器视觉系统。采用阈值分析进行图像分割、用形态学方法改进图像质量是齿轮测量的基础。采用图像分析的方法进行齿轮主要几何参数的测量 ,通过实际测试数据分析 ,讨论了机器视觉技术在齿轮测量中的实用价值和发展前景  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号