publication . Other literature type . Conference object . 2019

Probabilistic modelling combined with a CNN for boundary detection of carbon fiber fabrics

Name: Probabilistic Modelling combined with a CNN for boundary detection of carbon fiber fabrics
Keywords: Deep learning, probabilistic modelling, U-Net

Christian Eitzinger; Sebastian Zambal; Christoph Heindl;

Open Access

Published: 21 Aug 2019

Publisher: Zenodo

Summary

Abstract

Abstract: For many industrial machine vision applications it is difficult to acquire good training data to deploy deep learning techniques. In this paper we propose a method based on probabilistic modelling and rendering to generate artificial images of carbon fiber fabrics. We deploy a convolutional neural network (CNN) to learn detection of fabric contours from artificially generated images. Our network largely follows the recently proposed U-Net architecture. We provide results for a set of real images taken under controlled lighting conditions. The method can easily be adapted to similar problems in quality control for composite parts.

doi: 10.5281/zenodo.3373640 , 10.5281/zenodo.3373641 , 10.1109/indin41052.2019.8972094

Subjects

free text keywords: Deep learning, probabilistic modelling, U-Net, Real image, Architecture, Computer vision, Rendering (computer graphics), Deep learning, Convolutional neural network, Artificial intelligence, business.industry, business, Boundary detection, Probabilistic modelling, Carbon fibers, visual_art.visual_art_medium, visual_art, Computer science

Related Organizations