An improvement to the wavelet-modified Optimal Trade-off Maximum Average Correlation Height (OT-MACH) filter with the use of the Rayleigh distribution filter is proposed. The Rayleigh distribution filter is applied to the OT-MACH filter to provide a sharper low frequency cut-off than the Laplacian of Gaussian based wavelet filter that has been previously reported to enhance OT-MACH filter performance. Filters are trained using a 3D CAD model and tested on the corresponding real target object in high clutter environments acquired from a Forward Looking Infra Red (FLIR) sensor. Comparative evaluation of the performance of the original, wavelet and Rayleigh modified OT-MACH filter is reported for the recognition of the target objects present within the thermal infra-red image data set.

Date Published: 23 April 2012
PDF: 7 pages
Proc. SPIE 8398, Optical Pattern Recognition XXIII, 83980D (23 April 2012); doi: 10.1117/12.918756

Published in SPIE Proceedings Vol. 8398:
Optical Pattern Recognition XXIII
David P. Casasent; Tien-Hsin Chao, Editor(s)