This paper shows the performance of four deep learning algorithms on Baynat foam classification (Resnet, Mobilenet, Inception and Xception). One of the key components on headliner manufacturing is the foam. It provides acoustic isolation, lightness and robustness. Together with foam, other components are added such as textile fabrics and fiber components. Depending on the foam cell-size distribution, right amount of glue to be applied is determined correspondingly. This paper introduce AI algorithms on foam classification. The experiments are carried out using a dataset of 3000 images of foam cuts obtained from a single foam block.
CITATION STYLE
Muthuselvam, R. S., Moreno, R., Guemes, M., Del Río Cristobal, M., de Rodrigo Tobías, I., & López, A. J. L. (2023). Deep Learning Based Baynat Foam Classification for Headliners Manufacturing. In Lecture Notes in Networks and Systems (Vol. 531 LNNS, pp. 383–390). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-18050-7_37
Mendeley helps you to discover research relevant for your work.