[1]丁龙飞,曾水玲.基于多重注意力机制的电机磁瓦表面缺陷检测[J].计算机技术与发展,2022,32(12):194-199.[doi:10. 3969 / j. issn. 1673-629X. 2022. 12. 029]
　DING Long-fei,ZENG Shui-ling.Detection of Surface Defects of Motor Magnetic Tiles Based on Multiple Attention Mechanisms[J].,2022,32(12):194-199.[doi:10. 3969 / j. issn. 1673-629X. 2022. 12. 029]
点击复制

基于多重注意力机制的电机磁瓦表面缺陷检测()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
32
期数:
2022年12期
页码:
194-199
栏目:
新型计算应用系统
出版日期:
2022-12-10

文章信息/Info

Title:
Detection of Surface Defects of Motor Magnetic Tiles Based on Multiple Attention Mechanisms
文章编号:
1673-629X(2022)12-0194-06
作者:
丁龙飞; 曾水玲
吉首大学 信息科学与工程学院,湖南 吉首 416000
Author(s):
DING Long-fei; ZENG Shui-ling
School of Information Science and Engineering,Jishou University,Jishou 416000,China
关键词:
电机磁瓦缺陷; 缺陷检测; 残差网络; 注意力机制; 目标检测
Keywords:
motor magnetic tile defect; defect detection; residual network; attention mechanism; target detection
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 12. 029
摘要:
在电机磁瓦生产中可能因生产工艺不可避免产生残次品从而影响电机质量,因此对电机磁瓦质量进行挑选,去除残次品,成为电机磁瓦生产中的必须工序。 为解决传统图像处理检测能力弱、效率低且检测精准度低等问题,在 ResNet-50 的网络结构基础上,提出一种融合多重注意力机制残差网络的电机磁瓦缺陷检测网络模型。 该目标检测网络结合卷积网络和注意力机制( Convolutional Block Attention Module,CBAM) 构建了一种可以和网络进行端到端训练的非降维通道注意力和空间注意力串联模块,以建立特征之间的空间相关性,增强网络性能。 在电机磁瓦数据集上的实验结果表明,改进的目标检测网络在电机磁瓦缺陷图像的全类别平均准确率 mAP 达到 96. 92% ,所提算法的 mAP 值较原始 ResNet-50网络算法提升了 2. 17% 。 验证了所提算法对电机磁瓦缺陷检测任务的有效性。
Abstract:
In the production of motor magnet tiles,defective products may inevitably be produced due to the production process,whichwill affect the quality of the motor. Therefore,selecting the quality of motor magnet tiles and removing defective products has become anecessary process in the production of motor magnet tiles. 　　In order to solve the problems of weak detection ability,low efficiency and lowdetection accuracy of traditional image processing,based on the network structure 　　of ResNet-50,a motor magnetic tile defect detectionnetwork model integrating multiple attention mechanism residual networks is proposed. The target detection network combinesConvolutional Block Attention Module ( CBAM) to construct a non-dimensional reduction channel attention and spatial attention serialmodule 　that can be trained end - to - end with the network to establish spatial correlation between features and enhance networkperformance. Experiments on the motor magnetic tile data set show that the improved target detection network has an average accuracyrate of mAP of 96. 92% for all categories of motor magnetic tile defect images. The mAP value of the proposed algorithm is 2. 17%higher than that of the original ResNet-50 network algorithm,which verifies the effectiveness of the proposed algorithm for the detectiontask of motor magnetic tile defects.

相似文献/References:

[1]张燕 刘春.基于圆心定位的瓶口三圆周快速缺陷检测算法[J].计算机技术与发展,2009,(06):243.
　ZHANG Yan,LIU Chun.A Rapid Defect Detecting Algorithm of Bottle＇s Rim Based on Central Location and Three- Circle Method[J].,2009,(12):243.
[2]舒坚 胡茂林.基于Markov随机场模型的纹理图像的缺陷检测[J].计算机技术与发展,2006,(05):65.
　SHU Jian,HU Mao-lin.Detection of Defect Based on Texture of Markov Random Field Model[J].,2006,(12):65.
[3]邓忠华 刘飞.印刷品缺陷检测的初步方案[J].计算机技术与发展,2006,(10):171.
　DENG Zhong-hua,LIU Fei.Preliminary Scheme for Defect Inspection of Printed Material[J].,2006,(12):171.
[4]李雪晨 汪仁煌 艾星芳.改进的弯曲度算法在阶梯修剪检测中的应用[J].计算机技术与发展,2012,(03):166.
　LI Xue-chen,WANG Ren-huang,AI Xing-fang.Use of Improved Tortuosity Algorithm in Step Form Disfigurement Test[J].,2012,(12):166.
[5]杨杰,卢盛林,赵晓芳.机器视觉在钢化玻璃缺陷检测中的应用研究[J].计算机技术与发展,2013,(03):211.
　YANG Jie,LU Sheng-lin,ZHAO Xiao-fang.Application and Research of Machine Vision in Tempered Glass Defect Inspection[J].,2013,(12):211.
[6]陈星[],徐迎晖[],肖青海[][]. QR码印刷品缺陷检测[J].计算机技术与发展,2015,25(10):191.
　CHEN Xing[],XU Ying-hui[],XIAO Qing-hai[][]. Defect Detection of Printed QR Code Image[J].,2015,25(12):191.
[7]杜晓辉,刘霖,张静,等.火花塞端面缺陷自动检测算法设计[J].计算机技术与发展,2019,29(02):172.[doi:10．3969/j．issn．1673－629X．2019．02．036]
　DU Xiaohui,LIU Lin,ZHANG Jing,et al.Optoelectronic Inspection of Defects for Surface of Spark Plug[J].,2019,29(12):172.[doi:10．3969/j．issn．1673－629X．2019．02．036]
[8]刘钱超,董超群,张垚.基于容器技术的软件测试优化研究[J].计算机技术与发展,2019,29(04):13.[doi:10. 3969 / j. issn. 1673-629X. 2019. 04. 003]
　LIU Qian-chao,DONG Chao-qun,ZHANG Yao.Research on Optimization of Software Testing Based on Container Technology[J].,2019,29(12):13.[doi:10. 3969 / j. issn. 1673-629X. 2019. 04. 003]
[9]张洪波,隋文涛,袁摇 林,等.基于深度自编码器网络的压盖缺陷检测[J].计算机技术与发展,2022,32(02):143.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 023]
　ZHANG Hong-bo,SUI Wen-tao,YUAN Lin,et al.Capping Defect Detection Based on Deep Autoencoder Network[J].,2022,32(12):143.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 023]
[10]徐奎奎,董兆伟,孙立辉,等.基于深度学习的 GH4169 合金组织表面缺陷检测[J].计算机技术与发展,2022,32(09):208.[doi:10. 3969 / j. issn. 1673-629X. 2022. 09. 032]
　XU Kui-kui,DONG Zhao-wei,SUN Li-hui,et al.Surface Defect Detection of GH4169 Alloy Structure Based on Deep Learning[J].,2022,32(12):208.[doi:10. 3969 / j. issn. 1673-629X. 2022. 09. 032]

更新日期/Last Update: 2022-12-10