Research Repository

Evaluating Deep Convolutional Neural Networks for Material Classification

Kalliatakis, Grigorios and Stamatiadis, Georgios and Ehsan, Shoaib and Leonardis, Ales and Gall, Juergen and Sticlaru, Anca and McDonald-Maier, Klaus D (2017) Evaluating Deep Convolutional Neural Networks for Material Classification. In: International Conference on Computer Vision Theory and Applications, 2017-02-27 - 2017-03-01, Porto, Portugal.

VISAPP_2017_187.pdf - Published Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (408kB) | Preview


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.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Published proceedings: Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Divisions: Faculty of Science and Health > Computer Science and Electronic Engineering, School of
Depositing User: Elements
Date Deposited: 29 Apr 2020 21:19
Last Modified: 29 Apr 2020 21:19

Actions (login required)

View Item View Item