Specular Free Spectral Imaging Using Orthogonal Subspace Projection

Specularity is an important issue in computer vision. Many algorithms have been proposed to remove highlights for color images. However, to our knowledge, no work has been done so far which specifically handles highlights in spectral imaging. In this paper, we introduce a specular invariant represen...

Full description

Saved in:
Bibliographic Details
Published in18th International Conference on Pattern Recognition (ICPR'06) Vol. 1; pp. 812 - 815
Main Authors Zhouyu Fu, Tan, R.T., Caelli, T.
Format Conference Proceeding
LanguageEnglish
Published IEEE 2006
Subjects
Australia
Color
Computer vision
Geometry
Hyperspectral imaging
Hyperspectral sensors
Image segmentation
Layout
Lighting
Optical reflection
Online AccessGet full text

Cover

More Information
Summary:Specularity is an important issue in computer vision. Many algorithms have been proposed to remove highlights for color images. However, to our knowledge, no work has been done so far which specifically handles highlights in spectral imaging. In this paper, we introduce a specular invariant representation for hyperspectral images based on the dichromatic model and orthogonal subspace projection. It is a simple one step algorithm which only involves pixel-level operations, thus it does not require any segmentation. Nor does it require any pre/postprocessing or explicit spectral normalization. Importantly, unlike the previous methods for color images, it can be theoretically extended to handle highlights caused by multicolored illuminations. Experimental results demonstrate the effectiveness of our algorithm
ISBN:0769525210
9780769525211
ISSN:1051-4651
2831-7475
DOI:10.1109/ICPR.2006.1073