The Vaguelette-Curvelet Decomposition for Image Deblurring
Changhun Cho, Aggelos K. Katsaggelos, Joonki Paik · IEIE Transactions on Smart Processing and Computing · 2013
We present a vaguelette-curvelet decomposition based image deblurring algorithm. We first perform denoising based on the hard-thresholding rule by estimating unknown curvelet coefficients. The proposed algorithm then calculates vaguelette functions by deconvolving the curvelet bases by the point spread function. Vaguelette transform is finally performed to make a clearly restored image. Since the proposed algorithm uses the curvelet transform to sensitively express the edges in all directions, it is possible to restore images with more naturally preserved edges in all directions.