Summary: Voting scheme nonlinearity-based binary composite filter
Farid Ahmed, Mohammad A. Karimt and Fahmida Rahman
Western Michigan University
Department of Electrical and Computer Engineering
Kalamazoo, MI 49008
fDept. of Electrical Engineering and Electro-Optics Program
University of Dayton, Dayton OH 45469.
A voting scheme for the design of composite filter is proposed here. Different types of synthetic discriminant
function (SDF) filters, like minimum average correlation energy (MACE), minimum variance SDF (MVSDF) ,and
optimal tradeoff SDF (OTSDF) have been proposed recently for the distortion-invariant recognition. Discretiza-
tion of these filters is necessary to realize them using the available spatial light modulator (SLM). which limits
the efficiency of the continuous domain filters. In this report, we address this SLM-constraint of the composite
filter design. Our design starts with a binary SLM. in particular, binary modulation capability of the SLM is
incorporated in the composite filter design as a constraint in the form of voting scheme nonlinearity.
Keywords: composite filter , distortion-invariance, discretization , voting scheme.
Composite filter design for distortion invariance is attempted primarily in three different ways. In the synthetic
discriminant function (SDF) filter approach,"2 a number of distorted patterns are trained to design a filter, which
is expected to perform well under all other possible distortions. Minimum variance synthetic discriminant filter