The topic of constructing data-dependent dictionaries, referred to as dictionary learning, has received considerable interest in the past decade. In this work, we compare the ability of two dictionary learning algorithms, K-SVD and geometric multi-resolution analysis (GMRA), to perform image reconstruction using a fixed number of coefficients. K-SVD is an algorithm originating from the compressive sensing community and relies on optimization techniques. GMRA is a multi-scale technique that is based on manifold approximation of highdimensional point clouds of data. The empirical results of this work using a synthetic dataset of images of vehicles with diversity in viewpoint and lighting show that the K-SVD algorithm exhibits better generalization reconstruction performance with respect to test images containing lighting diversity that were not present in the construction of the dictionary, while GMRA exhibits superior reconstruction on the training data.

Date Published: 20 April 2015
PDF: 9 pages
Proc. SPIE 9477, Optical Pattern Recognition XXVI, 94770J (20 April 2015); doi: 10.1117/12.2180022

Published in SPIE Proceedings Vol. 9477:
Optical Pattern Recognition XXVI
David Casasent; Mohammad S. Alam, Editor(s)