为提高复合材料夹杂缺陷的检测效率,本文提出利用深度学习网络设计一种夹杂缺陷自动检测系统.在图像预处理环节采用两级反锐化掩膜算法突出夹杂缺陷特征,构建复合材料夹杂缺陷图像数据库;采用Mask R-CNN网络模型,经过网络模型训练,得到最优权重参数,最终设计实现缺陷检测软件系统.实验结果表明,Mask R-CNN算法网络准确率达 94.6%,召回率达 92.4%,AP值达 87.3%.该系统应用方便快捷,将有效提高一线人员的缺陷检测效率和检测精度.
In order to improve the detection efficiency of composite inclusion defects,an automatic inclusion defect detection system based on deep learning network is proposed in this paper.In the process of image prepro-cessing,a two-stage unsharping mask algorithm is used to highlight the features of inclusion defects,and a compos-ite image database of inclusion defects is constructed.The Mask R-CNN network model is used,and the optimal weight parameters are obtained through network model training.Finally,the defect detection software system is de-signed and realized.The experimental results show that the network accuracy of Mask R-CNN algorithm is 94.6%,the recall rate is 92.4%,and the AP value is 87.3%.The system is convenient and fast in application,and will ef-fectively improve the efficiency and accuracy of defect detection for front-line personnel.