摘要
针对人工检测一次性医用口罩耳绳时的速度慢、精度低、主观性强等问题,提出了一种基于机器视觉和图像金字塔模板匹配相结合的一次性医用口罩耳绳缺陷检测算法。首先,使用“Weickert”模式的各向异性滤波,对红色背光源下捕捉的待检测图片创建金字塔图像;然后,对鼻梁片模板匹配,通过仿射变换找到耳绳固定焊点的相对位置;最后,通过阈值分割,特征提取,计算焊点个数及面积,识别耳绳缺陷。实验结果表明:所提检测方法可以快速准确地判断口罩耳绳的缺陷问题。
Aiming the problems such as slow speed,low precision,and strong subjectivity in manually inspection of disposable medical mask ear band,an inspection algorithm based on machine vision and image pyramids template matching is proposed.Firstly,the anisotropic filtering of the"Weickert"mode is used to create a pyramid image of the picture captured under the red backlight.Then,the nose strip is matched through the template,and the position of the fixed welding spots of the ear band is determined by affine transformation.Finally,ear band defects are identified by threshold segmentation,feature extraction,and calculation of the number and area of welding spots.Experimental results show that the detection method can quickly and accurately determine the defects of mask ear band.
作者
刘飞飞
马礼然
LIU Feifei;MA Liran(College of Electrical Engineering and Automation,Jiangxi University of Science and Technology,Ganzhou 341000,China;College of Mechanical and Electrical Engineering,Jiangxi University of Science and Technology,Ganzhou 341000,China)
出处
《传感器与微系统》
CSCD
北大核心
2022年第1期157-160,共4页
Transducer and Microsystem Technologies
基金
国家自然科学基金资助项目(61364014)。
关键词
医用口罩
图像金字塔
各向异性滤波
仿射变换
medical mask
image pyramids
anisotropic filtering
affine transformation
