loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Silvan Mertes 1 ; Andreas Margraf 2 ; Christoph Kommer 1 ; Steffen Geinitz 2 and Elisabeth André 1

Affiliations: 1 University of Augsburg, Universitätsstraße 1, 86159 Augsburg, Germany ; 2 Fraunhofer IGCV, Am Technologiezentrum 2, 86159 Augsburg, Germany

Keyword(s): Image-to-Image Translation, Carbon Fiber, Data Augmentation, Computer Vision, Industrial Monitoring.

Abstract: Computer vision systems are popular tools for monitoring tasks in highly specialized production environments. The training and configuration, however, still represents a time-consuming task in process automation. Convolutional neural networks have helped to improve the ability to detect even complex anomalies withouth exactly modeling image filters and segmentation strategies for a wide range of application scenarios. In recent publications, image-to-image translation using generative adversarial networks was introduced as a promising strategy to apply patterns to other domains without prior explicit mapping. We propose a new approach for generating augmented data to enable the training of convolutional neural networks for semantic segmentation with a minimum of real labeled data. We present qualitative results and demonstrate the application of our system on textile images of carbon fibers with structural anomalies. This paper compares the potential of image-to-image translation net works with common data augmentation strategies such as image scaling, rotation or mirroring. We train and test on image data acquired from a high resolution camera within an industrial monitoring use case. The experiments show that our system is comparable to common data augmentation approaches. Our approach extends the toolbox of semantic segmentation since it allows for generating more problem-specific training data from sparse input. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.91.8.23

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Mertes, S.; Margraf, A.; Kommer, C.; Geinitz, S. and André, E. (2020). Data Augmentation for Semantic Segmentation in the Context of Carbon Fiber Defect Detection using Adversarial Learning. In Proceedings of the 1st International Conference on Deep Learning Theory and Applications - DeLTA; ISBN 978-989-758-441-1, SciTePress, pages 59-67. DOI: 10.5220/0009823500590067

@conference{delta20,
author={Silvan Mertes. and Andreas Margraf. and Christoph Kommer. and Steffen Geinitz. and Elisabeth André.},
title={Data Augmentation for Semantic Segmentation in the Context of Carbon Fiber Defect Detection using Adversarial Learning},
booktitle={Proceedings of the 1st International Conference on Deep Learning Theory and Applications - DeLTA},
year={2020},
pages={59-67},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009823500590067},
isbn={978-989-758-441-1},
}

TY - CONF

JO - Proceedings of the 1st International Conference on Deep Learning Theory and Applications - DeLTA
TI - Data Augmentation for Semantic Segmentation in the Context of Carbon Fiber Defect Detection using Adversarial Learning
SN - 978-989-758-441-1
AU - Mertes, S.
AU - Margraf, A.
AU - Kommer, C.
AU - Geinitz, S.
AU - André, E.
PY - 2020
SP - 59
EP - 67
DO - 10.5220/0009823500590067
PB - SciTePress