A Defect-Inspection System Constructed by Applying Autoencoder with Clustered Latent Vectors and Multi-Thresholding Classification

Cheng-Chang Lien,Yu-De Chiu

doi:10.3390/app12041883

Abstract

Defect inspection is an important issue in the field of industrial automation. In general, defect-inspection methods can be categorized into supervised and unsupervised methods. When supervised learning is applied to defect inspection, the large variation of defect patterns can make the data coverage incomplete for model training, which can introduce the problem of low detection accuracy. Therefore, this paper focuses on the construction of a defect-inspection system with an unsupervised learning model. Furthermore, few studies have focused on the analysis between the reconstruction error on the normal areas and the repair effect on the defective areas for unsupervised defect-inspection systems. Hence, this paper addresses this important issue. There are four main contributions to this paper. First, we compare the effects of SSIM (Structural Similarity Index Measure) and MSE (Mean Square Error) functions on the reconstruction error. Second, various kinds of Autoencoders are constructed by referring to the Inception architecture in GoogleNet and DEC (Deep Embedded Clustering) module. Third, two-stage model training is proposed to train the Autoencoder models. In the first stage, the Autoencoder models are trained to have basic image-reconstruction capabilities for the normal areas. In the second stage, the DEC algorithm is added to the training of the Autoencoder model to further strengthen feature discrimination and then increase the capability to repair defective areas. Fourth, the multi-thresholding image segmentation method is applied to improve the classification accuracy of normal and defect images. In this study, we focus on the defect inspection on the texture patterns. Therefore, we select the nanofiber image database and carpet and grid images in the MVTec database to conduct experiments. The experimental results show that the accuracy of classifying normal and defect patch nanofiber images is about 86% and the classification accuracy can approach 89% and 98% for carpet and grid datasets in the MVTec database, respectively. It is obvious that our proposed defect-inspection and classification system outperforms the methods in MVTec.

Highlights

Defect inspection is an indispensable process in the field of industrial automation
The DEC algorithm is added to the training of the Autoencoder model to further strengthen feature discrimination and increase the capability to repair defective areas
The experimental results show that the accuracy of classifying normal and defect patch nanofiber images is about 86% and the classification accuracy can approach 89% and 98% for carpet and grid datasets in the MVTec database, respectively

Summary

Introduction

Defect inspection is an indispensable process in the field of industrial automation. To identify these defect regions, the defect area, color variation, and texture complexity are important factors that can affect the accuracy of defect inspection. Due to the development of deep-learning technology, many deep-learning models for defect inspection have been proposed, mainly divided into supervised learning and unsupervised learning. Supervised defect-inspection methods can be categorized into bounding-boxbased methods and pixel-based methods. The representative bounding-box-based methods are the YOLO series [1–4]. Research in [5–9] used different versions of YOLO architectures to detect the defect regions and their experiments show that both of the classification and region locating are accurate.

Objectives

Results

Conclusion