A Continual Learning Framework for Adaptive Defect Classification and Inspection

TL;DR

This paper presents a continual learning framework for defect classification that efficiently updates models with new defect types, reducing storage and computation, demonstrated through image and 3D point cloud case studies.

Contribution

It introduces a general, efficient framework for adaptive defect classification that dynamically incorporates new defect types with minimal resource overhead.

Findings

Effective detection of new defect types in high-volume data

Reduced storage and computational requirements

Successful application to image and 3D surface defect detection

Abstract

Machine-vision-based defect classification techniques have been widely adopted for automatic quality inspection in manufacturing processes. This article describes a general framework for classifying defects from high volume data batches with efficient inspection of unlabelled samples. The concept is to construct a detector to identify new defect types, send them to the inspection station for labelling, and dynamically update the classifier in an efficient manner that reduces both storage and computational needs imposed by data samples of previously observed batches. Both a simulation study on image classification and a case study on surface defect detection via 3D point clouds are performed to demonstrate the effectiveness of the proposed method.