Independent component analysis (ICA) aims at extracting unknown components from multivariate data assuming that the underlying components are mutually independent. This technique has been successfully applied to the recognition and classification of objects. We present a method that combines the benefits of ICA and the ability of the integral imaging technique to obtain 3D information for the recognition of 3D objects with different orientations. Our recognition is also possible when the 3D objects are partially occluded by intermediate objects.
© 2009 Optical Society of America
Original Manuscript: August 28, 2008
Manuscript Accepted: November 11, 2008
Published: January 20, 2009
Cuong Manh Do, Raúl Martínez-Cuenca, and Bahram Javidi, "Three-dimensional object-distortion-tolerant recognition for integral imaging using independent component analysis," J. Opt. Soc. Am. A 26, 245-251 (2009)