Abstract

A novel method of 3D object recognition independent of lighting conditions is presented. The recognition model is based on a vector space representation using an orthonormal basis generated by the Lambertian reflectance functions obtained with distant light sources. Changing the lighting conditions corresponds to multiplying the elementary images by a constant factor and because of that, all possible lighting views will be elements that belong to that vector space. The recognition method proposed is based on the calculation of the angle between the vector associated with a certain illuminated 3D object and that subspace. We define the angle in terms of linear correlations to get shift and illumination-invariant detection.

© 2006 Optical Society of America

Intensity-invariant nonlinear filtering for detection in camouflage

Henri H. Arsenault and Pascuala García-Martínez
Appl. Opt. 44(26) 5483-5490 (2005)

Phase Fourier vector model for scale invariant three-dimensional image detection

José J. Vallés, Pascuala García-Martínez, Javier García, and Carlos Ferreira
Opt. Express 15(12) 7818-7825 (2007)

Spherical nonlinear correlations for global invariant three-dimensional object recognition

José J. Vallés, Pascuala García-Martínez, and Carlos Ferreira
Appl. Opt. 47(4) A43-A51 (2008)

Recognition of unsegmented targets invariant under transformations of intensity

Daniel Lefebvre, Henri H. Arsenault, Pascuala Garcia-Martinez, and Carlos Ferreira
Appl. Opt. 41(29) 6135-6142 (2002)

Detection of three-dimensional objects under arbitrary rotations based on range images

Javier García, Jose J. Valles, and Carlos Ferreira
Opt. Express 11(25) 3352-3358 (2003)