Iterative maximum-likelihood estimators for positively constrained objects

We present a unified approach for constructing iterative restorations of positively constrained objects. Specifically, a set of nonlinear algorithms, one of which is the Richardson-Lucy algorithm, is described for estimating positively constrained objects from data modeled by either Poisson or Gaussian processes. Exponential and monomial functions are used to remap the estimation space and to positively constrain the restorations. This technique also provides a method to accelerate the rate of convergence of known algorithms. Both one- and two-dimensional examples are presented. (C) 1996 Optical Society of America