Translator Disclaimer
Paper
16 July 2019 Deflectometric data segmentation based on fully convolutional neural networks
Author Affiliations +
Proceedings Volume 11172, Fourteenth International Conference on Quality Control by Artificial Vision; 1117209 (2019) https://doi.org/10.1117/12.2521740
Event: Fourteenth International Conference on Quality Control by Artificial Vision, 2019, Mulhouse, France
Abstract
The purpose of this paper is to explore the use of Fully Convolutional Neural Networks (FCN) to perform a semantic segmentation of deflectometric recordings for quality control of reflective surfaces. The proposed method relies on a U-Net network to identify the location and boundaries of the object, and the possible defective areas present, by performing a pixel-wise classification based on local curvatures and data modulation. Experiments performed on a real industrial problem demonstrate that the combination of geometric and photometric information enables the identification of a wider variety of shape and texture imperfections, with predictions closely correlated with the visual impact of the defects. The research also highlights the relevance of the labeling process and human inspection limits, and suggestions are presented for a near-term industrial utilization.
© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Daniel Maestro-Watson, Julen Balzategui, Luka Eciolaza, and Nestor Arana-Arexolaleiba "Deflectometric data segmentation based on fully convolutional neural networks", Proc. SPIE 11172, Fourteenth International Conference on Quality Control by Artificial Vision, 1117209 (16 July 2019); https://doi.org/10.1117/12.2521740
PROCEEDINGS
8 PAGES


SHARE
Advertisement
Advertisement
RELATED CONTENT


Back to Top