A surface defect detection method for mobile phone chip shielding shell based on LSDANet
刘克平 1刘博浩 1李岩 1宋誉2
扫码查看
点击上方二维码区域，可以放大扫码查看
作者信息
1. 长春工业大学电气与电子工程学院,吉林长春 130012
2. 东莞市三瑞自动化科技有限公司,广东东莞 523000
折叠
摘要
为了解决手机芯片屏蔽壳表面白印缺陷微小、尺度各异等因素影响检测快速性和准确性的问题,本文提出一种基于长短连接通路和双注意力网络(long short link and double attention net-work,LSDANet)的手机芯片屏蔽壳表面缺陷检测方法.首先,通过构建基于编码和解码的语义分割模型和利用长短距离连接通路,提高网络模型对尺度各异缺陷的特征提取能力.其次,分别设计基于通道和空间的注意力机制,增大5-10 pixel尺寸的白印缺陷在空间和通道上的特征权重.最后,融合双注意力机制和长短距离连接通路分割模型,构建LSDANet缺陷检测网络,应用于手机芯片屏蔽壳表面缺陷检测.实验数据表明,LSDANet网络能够达到96.21％的平均像素精度、66.13％的平均交并比和39.03的每秒检测帧数,相比多种语义分割算法均具有更高的检测精度和速度.
Abstract
To address the issues that the detection rapidity and accuracy are disturbed by the tiny defects,different scales and other factors on the surface white print of the mobile phone chip shielding shell,an long short link and double attention network(LSDANet)-based surface defect detection method is de-vised in this paper.First,the feature extraction ability of the network model for defects with different scales is enhanced via constructing an encoding and decoding-based semantic segmentation model and uti-lizing the long short-distance connection path.Second,the feature weights of white print defects with a size of 5 to 10 pixel in space and channel are increased via designing the space-and channel-based atten-tion mechanisms,respectively.Ultimately,a LSDANet defect detection network using the dual attention mechanism and long short-distance connection path segmentation model is proposed for surface defect detection of the mobile phone chip shielding shell.The experimental results demonstrate that the detec-tion performances of the LSDANet-based algorithm in mean pixel accuracy,mean intersection over union and frames per second are 96.21％,66.13％and 39.03,which are superior to the other semantic seg-mentation methods in terms of detection precision and speed.
关键词
深度学习/屏蔽壳/缺陷检测/语义分割
Key words
deep learning/chip shielding shell/defect detection/semantic segmentation
维普
万方数据