Dynamic Light Settings as Data Augmentations for Automated Scratch Detection

The manufacture of plastic parts requires a rigorous visual examination of its production to avoid the shipment of some that would be defective to its customers. In an attempt to ease the detection of scratches on plastic parts, the prototype of a computer-assisted visual inspection system was developed. The aim of this paper is to introduce how we explored ways to design a semi-automatic system comprising of a lamp whose orientations and intensities help in revealing irregularities on subjects that would have been missed with a unique light configuration. This process was qualified as “hardware data augmentation”. The pictures collected by our system were then used to train several convolutional neural networks (YOLOv4 algorithm/architecture). Finally, the performances of their models were confronted to evaluate the effects of the different light settings, and deduce which parameters are favourable to capture datasets leading to robust defect detection systems.

@article{Valentin2022,
  title     = {Dynamic Light Settings as Data Augmentations for Automated Scratch Detection},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {13},
  number    = {12},
  year      = {2022},
  publisher = {The Science and Information Organization},
  author    = {GRAVE Valentin and FUKUDA Osamu and YEOH Wen Liang and OKUMURA Hiroshi and YAMAGUCHI Nobuhiko},
  doi       = {10.14569/IJACSA.2022.01312107},
  url       = {https://doi.org/10.14569/IJACSA.2022.01312107}
}