Two-Stream Network One-Class Classification Model for Defect Inspections

Abstract

Defect inspection is important to ensure consistent quality and efficiency in industrial manufacturing. Recently, machine vision systems integrating artificial intelligence (AI)-based inspection algorithms have exhibited promising performance in various applications, but practically, they often suffer from data imbalance. This paper proposes a defect inspection method using a one-class classification (OCC) model to deal with imbalanced datasets. A two-stream network architecture consisting of global and local feature extractor networks is presented, which can alleviate the representation collapse problem of OCC. By combining an object-oriented invariant feature vector with a training-data-oriented local feature vector, the proposed two-stream network model prevents the decision boundary from collapsing to the training dataset and obtains an appropriate decision boundary. The performance of the proposed model is demonstrated in the practical application of automotive-airbag bracket-welding defect inspection. The effects of the classification layer and two-stream network architecture on the overall inspection accuracy were clarified by using image samples collected in a controlled laboratory environment and from a production site. The results are compared with those of a previous classification model, demonstrating that the proposed model can improve the accuracy, precision, and F1 score by up to 8.19%, 10.74%, and 4.02%, respectively.

GWO-Based Joint Optimization of Millimeter-Wave System and Multilayer Perceptron for Archaeological Application

“…On the contrary, low-THz frequency radar-based techniques [38,39] provide compact systems while offering high lateral resolution within the diffraction limit of half a wavelength (typ. 1.5 mm at 100 GHz) [35,38,39].…”

“…In coiled shards, the pores are aligned linearly (Figure 3a), in contrast to spiral shards (Figure 3b). However, the alignment is unlikely to be visible to the naked eye (Figure 3c,d), but can be identified with non-destructive testing [35]. Due to the size of the pores, alignments of the order of the millimeter, CT-scan [36], or synchrotron [37] were previously used but they are bulky and expansive.…”