Conference paper Open Access
Sebastian Zambal; Christoph Heindl; Christian Eitzinger
<?xml version='1.0' encoding='utf-8'?> <oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd"> <dc:creator>Sebastian Zambal</dc:creator> <dc:creator>Christoph Heindl</dc:creator> <dc:creator>Christian Eitzinger</dc:creator> <dc:date>2019-08-21</dc:date> <dc:description>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.</dc:description> <dc:identifier>https://zenodo.org/record/3373641</dc:identifier> <dc:identifier>10.5281/zenodo.3373641</dc:identifier> <dc:identifier>oai:zenodo.org:3373641</dc:identifier> <dc:relation>info:eu-repo/grantAgreement/EC/H2020/721362/</dc:relation> <dc:relation>doi:10.5281/zenodo.3373640</dc:relation> <dc:rights>info:eu-repo/semantics/openAccess</dc:rights> <dc:subject>Deep learning, probabilistic modelling, U-Net</dc:subject> <dc:title>Probabilistic modelling combined with a CNN for boundary detection of carbon fiber fabrics</dc:title> <dc:type>info:eu-repo/semantics/conferencePaper</dc:type> <dc:type>publication-conferencepaper</dc:type> </oai_dc:dc>
All versions | This version | |
---|---|---|
Views | 51 | 51 |
Downloads | 65 | 65 |
Data volume | 230.6 MB | 230.6 MB |
Unique views | 50 | 50 |
Unique downloads | 58 | 58 |