# TransferD2: Automated Defect Detection Approach in Smart Manufacturing using Transfer Learning Techniques

## TL;DR

This paper introduces TransferD2, a transfer learning-based method for defect detection in smart manufacturing, utilizing data augmentation and pre-trained models to accurately identify unseen defects with limited data.

## Contribution

The paper proposes TransferD2, a novel transfer learning approach that combines data enhancement and multiple pre-trained models for effective defect detection in manufacturing.

## Key findings

- ResNet101V2 achieved 95.72% accuracy on source data.
- Xception achieved 91.00% accuracy on target data.
- Model choice is independent of network depth.

## Abstract

Quality assurance is crucial in the smart manufacturing industry as it identifies the presence of defects in finished products before they are shipped out. Modern machine learning techniques can be leveraged to provide rapid and accurate detection of these imperfections. We, therefore, propose a transfer learning approach, namely TransferD2, to correctly identify defects on a dataset of source objects and extend its application to new unseen target objects. We present a data enhancement technique to generate a large dataset from the small source dataset for building a classifier. We then integrate three different pre-trained models (Xception, ResNet101V2, and InceptionResNetV2) into the classifier network and compare their performance on source and target data. We use the classifier to detect the presence of imperfections on the unseen target data using pseudo-bounding boxes. Our results show that ResNet101V2 performs best on the source data with an accuracy of 95.72%. Xception performs best on the target data with an accuracy of 91.00% and also provides a more accurate prediction of the defects on the target images. Throughout the experiment, the results also indicate that the choice of a pre-trained model is not dependent on the depth of the network. Our proposed approach can be applied in defect detection applications where insufficient data is available for training a model and can be extended to identify imperfections in new unseen data.