[1]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):143-147.[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(02):143-147.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 023]
点击复制

基于深度自编码器网络的压盖缺陷检测()
分享到：

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

卷:
32
期数:
2022年02期
页码:
143-147
栏目:
应用前沿与综合
出版日期:
2022-02-10

文章信息/Info

Title:
Capping Defect Detection Based on Deep Autoencoder Network
文章编号:
1673-629X(2022)02-0143-05
作者:
张洪波; 隋文涛; 袁摇 林; 李长安; 逯海滨
山东理工大学 机械工程学院,山东 淄博 255000
Author(s):
ZHANG Hong-bo; SUI Wen-tao; YUAN Lin; LI Chang-an; LU Hai-bin
School of Mechanical Engineering,Shandong University of Technology,Zibo 255000,China
关键词:
压盖质量; 缺陷检测; 自编码器; 神经网络; 多层感知器
Keywords:
capping quality; defect detection; autoencoder; neural network; multilayer perceptron
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 02. 023
摘要:
口服液压盖过程,会出现压盖不良等情况,瓶盖可能会出现划痕、刮花、表面卷曲、压盖破损等缺陷,为保证食品药品安全必须在出厂前进行检测。 在基于深度学习的口服液瓶压盖缺陷检测的研 究过程中,使用传统卷积神经网络对口服液压盖缺陷数据集进行训练,需要进行人工标注,效率较低。 为有效解决上述问题,设计出一种无监督学习的深度卷积去噪自编码器网络模型用于口服液瓶压盖质量检测,并使用结构相似性 SSIM 作为损失函数。 针对口服液压盖质量图像进行预处理,建立合格产品图像数据集,然后构建一种以卷积神经网络为基础,结合多层感知器的去噪自编码器网络模型。该模型仅以无缺陷产品图像进行训练并学习无缺陷产品特征,通过将缺陷图像重构为无缺陷图像,再与缺陷图像相减,获得包含缺陷信息的残差图。 实验结果表明:该方法能够很好地识别口服液瓶压盖缺陷,准确率达到 95. 2% ,且具有较好的泛化能力和鲁棒性。
Abstract:
In the process of oral hydraulic cap,there will be problems such as poor capping,and the bottle cap may have defects such asscratches,scratches,surface curling and capping damage. To ensure the safety of food and drugs,it must be tested before leaving thefactory. In the research process of oral liquid bottle capping defect detection based on deep learning,the traditional convolutional neuralnetwork is used to train the oral hydraulic cap defect data set, which requires manual annotation and has low efficiency. In order toeffectively solve the above problems,? an unsupervised learning deep convolution denoising autoencoder network model is designed for thequality detection of oral liquid bottle caps,and the structural similarity SSIM is used as? the loss function. The quality image of the oralhydraulic cover is preprocessed to establish a qualified product image data set,and then a denoising autoencoder network model based ona convolutional neural network combined with a multi - layer perceptron is constructed. The model only uses non - defective productimages for training and learns the features of non-defective products. The defect images are reconstructed into non-defective images andthen subtracted from the defective images to obtain a residual image containing defect information. The experiment shows that theproposed method can well identify the capping defects of oral liquid bottles,with an accuracy rate of 95. 2% ,and has ideal generalizationability and robustness.

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,(02):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,(02):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,(02):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,(02):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,(02):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(02):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(02):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(02):13.[doi:10. 3969 / j. issn. 1673-629X. 2019. 04. 003]
[9]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(02):208.[doi:10. 3969 / j. issn. 1673-629X. 2022. 09. 032]
[10]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.[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(02):194.[doi:10. 3969 / j. issn. 1673-629X. 2022. 12. 029]

更新日期/Last Update: 2022-02-10