TY - GEN
T1 - SAR automatic target recognition via non-negative matrix approximations
AU - Riasati, Vahid
AU - Srinivas, Umamahesh
AU - Monga, Vishal
PY - 2012
Y1 - 2012
N2 - The set of orthogonal eigen-vectors built via principal component analysis (PCA), while very effective for com- pression, can often lead to loss of crucial discriminative information in signals. In this work, we build a new basis set using synthetic aperture radar (SAR) target images via non-negative matrix approximations (NNMAs). Owing to the underlying physics, we expect a non-negative basis and an accompanying non-negative coecient set to be a more accurate generative model for SAR proles than the PCA basis which lacks direct physical interpretation. The NNMA basis vectors while not orthogonal capture discriminative local components of SAR target images. We test the merits of the NNMA basis representation for the problem of automatic target recognition using SAR images with a support vector machine (SVM) classier. Experiments on the benchmark MSTAR database reveal the merits of basis selection techniques that can model imaging physics more closely and can capture inter-class variability, in addition to identifying a trade-off between classication performance and availability of training.
AB - The set of orthogonal eigen-vectors built via principal component analysis (PCA), while very effective for com- pression, can often lead to loss of crucial discriminative information in signals. In this work, we build a new basis set using synthetic aperture radar (SAR) target images via non-negative matrix approximations (NNMAs). Owing to the underlying physics, we expect a non-negative basis and an accompanying non-negative coecient set to be a more accurate generative model for SAR proles than the PCA basis which lacks direct physical interpretation. The NNMA basis vectors while not orthogonal capture discriminative local components of SAR target images. We test the merits of the NNMA basis representation for the problem of automatic target recognition using SAR images with a support vector machine (SVM) classier. Experiments on the benchmark MSTAR database reveal the merits of basis selection techniques that can model imaging physics more closely and can capture inter-class variability, in addition to identifying a trade-off between classication performance and availability of training.
UR - http://www.scopus.com/inward/record.url?scp=84862642789&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84862642789&partnerID=8YFLogxK
U2 - 10.1117/12.919348
DO - 10.1117/12.919348
M3 - Conference contribution
AN - SCOPUS:84862642789
SN - 9780819490698
T3 - Proceedings of SPIE - The International Society for Optical Engineering
BT - Automatic Target Recognition XXII
T2 - Automatic Target Recognition XXII
Y2 - 23 April 2012 through 24 April 2012
ER -