摘要
针对氢能燃料电池涂布缺陷检测难度大的问题,提出了基于区域生长与BLOB分析的涂布缺陷图像检测方法。首先对图像进行ROI区域提取及高斯滤波处理,然后利用区域生长分割图像,最后利用Blob分析标记连通区域。实验结果表明,文中方法能够有效检测出氢能电池涂布缺陷,准确率达到检测要求。
In view of the difficulty in detecting coating defects in hydrogen fuel cells,an image detection method for coating defects based on region growth and binary large object(BLOB)analysis was proposed.Firstly,the region of interest of the image was extracted and processed by Gaussian filtering.Then,the image was segmented by region growth.Finally,the connected region was marked by BLOB analysis.The experimental results show that the method in this paper can effectively detect the coating defects in hydrogen fuel cells,and the accuracy meets the detection requirements.
作者
王伟
王生怀
钟明
杨帅
陈哲
Wang Wei;Wang Shenghuai;Zhong Ming;Yang Shuai;Chen Zhe(School of Mechanical Engineering,Hubei University of Automotive Technology,Shiyan 442002,China;Wuhan Zoomedu Technology Co.Ltd,Wuhan 430000,China)
出处
《湖北汽车工业学院学报》
2024年第3期51-55,65,共6页
Journal of Hubei University Of Automotive Technology
基金
国家自然科学基金(51675167)
湖北省重点研发计划项目(2021BAA056)
湖北省教育厅科研项目(T2020018,Q20191801)。
