Number of the records: 1
View Dependent Surface Material Recognition
- 1.0510488 - ÚTIA 2020 RIV CH eng C - Conference Paper (international conference)
Mikeš, Stanislav - Haindl, Michal
View Dependent Surface Material Recognition.
Advances in Visual Computing : 14th International Symposium on Visual Computing (ISVC 2019). Cham: Springer, 2019 - (Bebis, G.; Boyle, R.; Parvin, B.; Koracin, D.), s. 156-167, č. článku 12. Lecture Notes in Computer Science, 11844. ISBN 978-3-030-33719-3. ISSN 0302-9743. E-ISSN 1611-3349.
[International Symposium on Visual Computing (ISVC 2019) /14./. Lake Tahoe (US), 07.10.2019-09.10.2019]
R&D Projects: GA ČR(CZ) GA19-12340S
Institutional support: RVO:67985556
Keywords : convolutional neural network * texture recognition * Bidirectional Texture Function recognition
OECD category: Automation and control systems
http://library.utia.cas.cz/separaty/2019/RO/haindl-0510488.pdf
The paper presents a detailed study of surface material recognition dependence on the illumination and viewing conditions which is a hard challenge in a realistic scene interpretation. The results document sharp classification accuracy decrease when using usual texture recognition approach, i.e., small learning set size and the vertical viewing and illumination angle which is a very inadequate representation of the enormous material appearance variability. The visual appearance of materials is considered in the state-of-the-art Bidirectional Texture Function (BTF) representation and measured using the upper-end BTF gonioreflectometer. The materials in this study are sixty-five different wood species. The supervised material recognition uses the shallow convolutional neural network (CNN) for the error analysis of angular dependency. We propose a Gaussian mixture model-based method for robust material segmentation.
Permanent Link: http://hdl.handle.net/11104/0302678
Number of the records: 1