Fine-grained Material Classification using Micro-geometry and Reflectance

File Description SizeFormat 
1119.pdfAccepted version7.56 MBUnknownView/Open
Title: Fine-grained Material Classification using Micro-geometry and Reflectance
Authors: Kampouris, C
Zafeiriou, S
Ghosh, A
Malassiotis, S
Item Type: Conference Paper
Abstract: In this paper we focus on an understudied computer vision problem, particularly how the micro-geometry and the reflectance of a surface can be used to infer its material. To this end, we introduce a new, publicly available database for fine-grained material classification, consisting of over 2000 surfaces of fabrics (http://​ibug.​doc.​ic.​ac.​uk/​resources/​fabrics.). The database has been collected using a custom-made portable but cheap and easy to assemble photometric stereo sensor. We use the normal map and the albedo of each surface to recognize its material via the use of handcrafted and learned features and various feature encodings. We also perform garment classification using the same approach. We show that the fusion of normals and albedo information outperforms standard methods which rely only on the use of texture information. Our methodologies, both for data collection, as well as for material classification can be applied easily to many real-word scenarios including design of new robots able to sense materials and industrial inspection.
Issue Date: 16-Sep-2016
Date of Acceptance: 25-Jul-2016
URI: http://hdl.handle.net/10044/1/41053
DOI: https://dx.doi.org/10.1007/978-3-319-46454-1_47
ISSN: 0302-9743
Publisher: Springer
Start Page: 778
End Page: 792
Journal / Book Title: Lecture Notes in Computer Science
Volume: 9909
Copyright Statement: The final publication is available at Springer via https://dx.doi.org/10.1007/978-3-319-46454-1_47
Sponsor/Funder: The Royal Society
Engineering & Physical Science Research Council (EPSRC)
Funder's Grant Number: WM 120040
EP/N006259/1
Conference Name: European Conference on Computer Vision 2016
Keywords: Artificial Intelligence & Image Processing
08 Information And Computing Sciences
Publication Status: Published
Start Date: 2016-10-11
Finish Date: 2016-10-14
Conference Place: Amsterdam, the Netherlands
Appears in Collections:Faculty of Engineering
Computing



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commonsx