PROJECT TITLE :

Iterative filtering and smoothing of measurements possessing poisson noise

ABSTRACT:

The minimum-variance filter and smoother are generalized to include Poisson-distributed measurement noise components. It's shown that the resulting filtered and smoothed estimates are unbiased. The use of the filter and smoother among expectation-maximization algorithms are described for joint estimation of the signal and Poisson noise intensity. Conditions for the monotonicity and asymptotic convergence of the Poisson intensity iterates also are established. An Image Restoration example is presented that demonstrates improved estimation performance at low signal-to-noise ratios.