Document Type
Journal Article
Abstract
This paper proposes a sparse representation of animage using discrete δ - μ functions. A δ - μ function is definedas as the product of a Kronecker delta function and a stepfunction. Based on the sparse representation, we have developeda novel and effective method for reconstructing an image fromlimited-angle projections. The method first estimates the parametersof the sparse representation from the incomplete projectiondata, and then directly calculates the image to be reconstructed.Experiments have shown that the proposed method can effectivelyrecover the missing data and reconstruct images more accuratelythan the total-variation (TV) regularized reconstruction method.
RIS ID
32096
COinS