Product defect detection based on convolutional autoencoder and one-class classification

Chaabi M.; Hamlich M.; Garouani M.

首页> 外文期刊>IAES International Journal of Artificial Intelligence >Product defect detection based on convolutional autoencoder and one-class classification

【24h】

Product defect detection based on convolutional autoencoder and one-class classification

机译：

获取原文

获取原文并翻译 | 示例

获取外文期刊封面封底 >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

To meet customer expectations and remain competitive, industrials try constantly to improve their quality control systems. There is hence increasing demand for adopting automatic defect detection solutions. However, the biggest issue in addressing such systems is the imbalanced aspect of industrial datasets. Often, defect-free samples far exceed the defected ones, due to continuous improvement approaches adopted by manufacturing companies. In this sense, we propose an automatic defect detection system based on one-class classification (OCC) since it involves only normal samples during training. It consists of three sub-models, first, a convolutional autoencoder serves as latent features extractor, the extracted features vectors are subsequently fed into the dimensionality reduction process by performing principal component analysis (PCA), then the reduced-dimensional data are used to train the one-class classifier support vector data description (SVDD). During the test phase, both normal and defected images are used. The first two stages of the trained model generate a low-dimensional features vector, whereas the SVDD classifies the new input, whether it is defect-free or defected. This approach is evaluated on the carpet images from the industrial inspection dataset MVTec anomaly detection (MVTec AD). During training, only normal images were used. The results showed that the proposed method outperforms the state-of-the-art methods. © 2023, Institute of Advanced Engineering and Science. All rights reserved.

著录项

来源
《IAES International Journal of Artificial Intelligence》 |2023年第2期|912-920|共9页
作者
Chaabi M.; Hamlich M.; Garouani M.;
展开▼
作者单位

Complex Cyber Physical System (CCPS) Laboratory, ENSAM, University of Hassan II;

展开▼
收录信息
原文格式 PDF
正文语种英语
中图分类
关键词
Defect detection; Imbalanced data; MVTec anomaly detection; One-class classification; Support vector data description;

相似文献

外文文献
中文文献
专利

1. Colour-patterned fabric defect detection based on an unsupervised multi-scale U-shaped denoising convolutional autoencoder model [J] . Hongwei Zhang, Shuting Liu, Quanlu TanShuai LuLe YaoZhiqiang Ge Coloration technology . 2022,第5期

机译：Colour-patterned fabric defect detection based on an unsupervised multi-scale U-shaped denoising convolutional autoencoder model
2. Research Reports from Qingdao University of Technology Provide New Insights into Scientific Programming (Casting Defect Detection and Classification of Convolutional Neural Network Based on Recursive Attention Model) [J] . Network Daily News . 2022,第28期

机译：Research Reports from Qingdao University of Technology Provide New Insights into Scientific Programming (Casting Defect Detection and Classification of Convolutional Neural Network Based on Recursive Attention Model)
3. TriMap thermography with convolutional autoencoder for enhanced defect detection of polymer composites [J] . Liu Yi, Zheng Mingkai, Liu KaixinYao YuanSfarra Stefano Journal of Applied Physics . 2022,第14期

机译：TriMap thermography with convolutional autoencoder for enhanced defect detection of polymer composites
4. Display Panel Defect Detection Algorithm Based On Group Convolutions [C] . Wei Fei Ma, Sheng Sen Zhang, Zeng Qiang Zheng International Conference on Display Technology;Society for Information Display . -1

机译：Display Panel Defect Detection Algorithm Based On Group Convolutions
5. Um modelo de projeto de layout para ambientes job shop com alta variedade de peças baseado nos conceitos da produção enxuta A layout design model for job shop environments with high variety of parts based on lean production concepts [O] . Alessandro Lucas da Silva, Antonio Freitas Rentes 2012

机译：Um modelo de projeto de layout para ambientes job shop with based based of products of based on product我们的产品en布局布局设计模型，适用于基于精益生产概念的零件种类繁多的作业车间环境

Product defect detection based on convolutional autoencoder and one-class classification

摘要

著录项

相似文献

相关主题

期刊订阅