基于机器视觉的工业产品表面缺陷检测算法研究

RESEARCH ON MACHINE VISION BASED INDUSTRIAL PRODUCT SURFACE DEFECT DETECTION ALGORITHM

目前机器视觉在工业产品缺陷检测中的应用越来越广泛,针对目前常用的几种非纹理图像缺陷检测算法进行了研究分析,结合纸杯表面的缺陷特征,针对模板匹配法提出了两种改进的方法,即统计平均差影法,粗放型灰度相关法。最后进行了试验分析比较,检测结果达到了预期效果。

At present machine vision is more and more widely applied to industrial product defect detection.The paper studies and analyzes several frequently used non-texture image defect detection algorithms,combines defect features on the paper cup surface,and,targeting at template matching method,puts forward two improved methods,namely,statistical average shadow difference method and extensive gray scale correlation method.After analysis and comparison with tests,it is proven that the test results have achieved the desired effects.