Image Information Extraction Model Based onMulti-features of K-nearest Neighbors

DOI

10.2991/icmmct-16.2016.355How to use a DOI?

Keywords

K-nearest neighbor; multi-feature; BRDF modeling; information extraction

Abstract

Bidirectional Reflectance Distribution Function (BRDF) and Bidirectional Texture Function (BTF) are two major methods used to describe the reflectance of light at a surface under different illuminations and different views. However, due to a large number of measurement data, an efficient compression method is needed. Meanwhile, the requirements of real-time rendering should be met. Under this background, this paper mainly does some exploratory research on BRDF modeling methods based on the qualitative measurements of textures. By conducting BRDF modeling on the measurements derives with different acquisition devices, it obtains the illumination properties of textures. Finally, combined with the property information of textures on the surface of object, under a new light source, from a new viewpoint, it renders the relighting effect of the object under a new light source.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Anmin Xu
PY  - 2016/03
DA  - 2016/03
TI  - Image Information Extraction Model Based onMulti-features of K-nearest Neighbors
BT  - Proceedings of the 2016 4th International Conference on Machinery, Materials and Computing Technology
PB  - Atlantis Press
SP  - 1782
EP  - 1786
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmmct-16.2016.355
DO  - 10.2991/icmmct-16.2016.355
ID  - Xu2016/03
ER  -