Consistency and convexity in object reconstruction from projections

A projection-space approach for reconstruction from projections is presented. This approach uses the known convex support of the object both as a penalty term in a variational problem defined in projection-space and as a guide to the specification of optimal smoothing coefficients that may vary spatially. Partial consistency of the sinogram is provided by including mass and center-of-mass constraints in the variational formulation. An outline of the general approach and calculations for a specific example are provided. Computer simulations are provided for evaluation of the performance in this special case