基于机器视觉的西林瓶尺寸检测

Vial Size Detection Based on Machine Vision

摘要:

在西林瓶生产过程中，尺寸是一项重要的产品质量判断标准，与传统的西林瓶尺寸人工检测方法相比，基于机器视觉的自动检测具有巨大优越性。为实现西林瓶尺寸的检测，提出了一种基于机器视觉的西林瓶尺寸检测方案，设计了系统的图像采集和背光源照明方案，通过中值滤波对图像进行去噪，利用对图像像素点的运算算法，对图像的灰度进行了校正变换，增强图像的对比度，采用Canny算子成功提取西林瓶边缘，在HALCON平台下实现了西林瓶尺寸测量。设定系统标定方法并选取15个2mL样品西林瓶进行测试，结果表明，该方法对西林瓶尺寸检测快速准确，边缘量化精度达到了亚像素级别，检测精度为0.02mm，满足西林瓶生产的参数测量精度要求，为工业生产产品尺寸的自动检测提供了一种有效的新途径。

Abstract:

Vial size is an important quality criterion in the production process of vial. To achieve vial size detection, a program of vial size detection based on machine vision is presented. The program is based on HALCON platform, using some image processing algorithms to perform edge detection and size measurement. The results show that the detection method is fast and accurate, and the detection accuracy is 0.02mm, edge quantization accuracy can reach to the sub-pixel level, meet the requirements of the vials production accuracy of parameters measurement, provides an effective and automatic way to detect industrial production size.