Foundry is an important industry that supplies key products to other important sectors of the society. In order to assure the quality of the final product, the castings are subject to strict safety controls. One of the most important test in these controls is surface quality inspection. In particular, our work focuses on three of the most typical surface defects in iron foundries: inclusions, cold laps and misruns. In order to automatise this process, we introduce the QT Clustering approach to increase the perfomance of a segmentation method. Finally, we categorise resulting areas using machine-learning algorithms.We show that with this addition our segmentation method increases its coverage.
CITATION STYLE
Pastor-López, I., Santos, I., De-La-Peña-Sordo, J., García-Ferreira, I., Zabala, A. G., & Bringas, P. G. (2014). Enhanced image segmentation using quality threshold clustering for surface defect categorisation in high precision automotive castings. In Advances in Intelligent Systems and Computing (Vol. 239, pp. 191–200). Springer Verlag. https://doi.org/10.1007/978-3-319-01854-6_20
Mendeley helps you to discover research relevant for your work.