Evaluating Deep Convolutional Neural Networks for Material Classification

Grigorios Kalliatakis, Georgios Stamatiadis, Shoaib Ehsan, Ales Leonardis, Juergen Gall, Anca Sticlaru, Klaus D. McDonald-Maier

2017

Abstract

Determining the material category of a surface from an image is a demanding task in perception that is drawing increasing attention. Following the recent remarkable results achieved for image classification and object detection utilising Convolutional Neural Networks (CNNs), we empirically study material classification of everyday objects employing these techniques. More specifically, we conduct a rigorous evaluation of how state-of-the art CNN architectures compare on a common ground over widely used material databases. Experimental results on three challenging material databases show that the best performing CNN architectures can achieve up to 94.99% mean average precision when classifying materials.

Paper Citation

in Harvard Style

Kalliatakis G., Stamatiadis G., Ehsan S., Leonardis A., Gall J., Sticlaru A. and McDonald-Maier K. (2017). Evaluating Deep Convolutional Neural Networks for Material Classification . In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-226-4, pages 346-352. DOI: 10.5220/0006166603460352

in Bibtex Style

@conference{visapp17,
author={Grigorios Kalliatakis and Georgios Stamatiadis and Shoaib Ehsan and Ales Leonardis and Juergen Gall and Anca Sticlaru and Klaus D. McDonald-Maier},
title={Evaluating Deep Convolutional Neural Networks for Material Classification},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017)},
year={2017},
pages={346-352},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006166603460352},
isbn={978-989-758-226-4},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017)
TI - Evaluating Deep Convolutional Neural Networks for Material Classification
SN - 978-989-758-226-4
AU - Kalliatakis G.
AU - Stamatiadis G.
AU - Ehsan S.
AU - Leonardis A.
AU - Gall J.
AU - Sticlaru A.
AU - McDonald-Maier K.
PY - 2017
SP - 346
EP - 352
DO - 10.5220/0006166603460352