The analytically continued Fourier transform of a two-dimensional imag
e vanishes to zero on a two-dimensional surface embedded in a four-dim
ensional space. This surface uniquely characterizes the image and is k
nown as a zero sheet. An algorithm is described that employs the zero-
sheet concept to blindly deconvolve an ensemble of differently blurred
images. To overcome the difficulty of operating within a four-dimensi
onal space, we calculate projections of the zero sheets, known as zero
tracks. The zero tracks of each member of the ensemble are superimpos
ed on a plane. The zero tracks that pertain to the original image are
similar for every blurred and contaminated image. By contrast those as
sociated with the blurring vary widely across the ensemble. A method o
f selecting the appropriate zero tracks in order to reconstruct an est
imate of the original image is presented. Preliminary results for smal
l positive images suggest that this deconvolution technique may be suc
cessful even when the level of contamination is significant.