QQ客服 官方微博 反馈留言

题名	机器视觉尺寸测量精度的关键影响因素研究
作者	来先家
学位类别	硕士
答辩日期	2015
授予单位	中国科学院上海光学精密机械研究所
导师	徐文东
关键词	机器视觉 测量精度 远心度 边缘检测 双远心镜头
其他题名	Study on the key factors of dimension measurement accuracy in machine vision
中文摘要	机器视觉技术在工业测量中具有广泛应用，实现高精度的机器视觉测量对零件的精密加工、制造具有重要意义。目前机器视觉在薄片零件尺寸测量方面具有较高精度，并且不断有研究者提出新的图像检测算法，以求获得更高的测量精度。然而，在对非薄片物体进行测量时则会存在很多影响测量精度的因素，例如，实际检测过程中零件的摆放位置和姿态变化、较厚零件边缘虚化等，所有这些情况都会给测量精度带来直接影响，并且这些因素对测量精度的影响各不相同，很难通过某一个算法完全消除。为提高机器视觉尺寸测量的通用性，改善机器视觉测量精度，本文对影响测量精度的几个关键因素进行了研究，并通过理论分析以及实验验证提出可行的改善测量精度的建议与方法。 本文主要研究内容以及成果如下： （1） 针对机器视觉测量中待测物体偏离焦面导致测量结果出现误差的问题进行了研究。重点讨论了系统中镜头远心度引起的平行性误差对离焦物体测量结果的影响。实验结果表明，在物体偏离最佳成像面而引入的误差中，平行性误差占到90%左右的比重，因此可通过后期对平行性误差进行补偿以较大程度提高系统测量精度。 （2） 采用多种边缘检测算法对待测物体过厚这一情况进行了分析。结果表明在一定范围内，物体纵深方向越厚，边缘检测误差越大。在这一结果的基础上，对算法进行改进，提出一种基于图像灰度曲线的补偿方法，使测量误差由超过20 μm降至10 μm以下。 （3） 对于某些不规则物体在测量过程中姿态发生变动的问题进行简单地讨论，针对一个特定形状的零件进行了分析并提出了几种测量方法，且在理论上分析了其中一种方法的可行性。
英文摘要	Machine vision technology is widely used in industrial measurement. To realize high precision measurement of machine vision is of great significance to precision machining and manufacturing. At present, machine vision can achieve high precision in measuring dimensions of thin sheet parts. And in order to achieve higher precision, researchers constantly put forward new image detection algorithms. However, while measuring the dimension of non-slice objects, many factors will affect the measurement accuracy. Such as, the placement and posture changing of the parts, edge blur of thick parts and so on. Moreover, the influence of these factors on the measurement accuracy varies, measurement errors can hardly be eliminated through a single algorithm. In order to increase the versatility of machine vision measurement and to improve the measurement accuracy, key factors of dimension measurement accuracy in machine vision are studied in this paper. Feasible suggestions and methods are put forward after theoretical analysis and experimental verification. The main study content and fruit is listed as follows. (1) Researches are conducted on the problem that measuring object will cause measurement error in machine vision application when it deviates from the focal plane or has a certain thickness. The influence of parallelism error caused by telecentricity on measurement error of defocused sample is discussed with emphasis. The experiment results show that among all measurement errors caused by sample's deviation from the optimal imaging plane, the proportion of parallelism error accounts for about 90%. Measuring accuracy can be improved greatly by compensating parallelism error. (2) In order to analyze the situation that sample has a large thickness, several edge detection algorithms are used. The experiment results show that within a certain range, the thicker the object is, the larger the edge detection error will be. On the basis of this result, the algorithm is improved, and a compensation method based on image gray - level curve is put forward. As a result, measurement error has decreased from more than 20 μm to less than 10 μm. (3) For some irregular samples, the rotation of sample during the measuring process is simply discussed. A special-shaped parts is analyzed and several methods are put forward. The practicability of one method is analyzed theoretically.
语种	中文
内容类型	学位论文
源URL	[http://ir.siom.ac.cn/handle/181231/16944]
专题	上海光学精密机械研究所_学位论文
推荐引用方式 GB/T 7714	来先家. 机器视觉尺寸测量精度的关键影响因素研究[D]. 中国科学院上海光学精密机械研究所. 2015.

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。