Blind Image Deconvolution Based on Complex Mapping
Fatih Kara, Cabir Vural · 2007
In linear image deconvolution problems, the blur operator is usually assumed to be known, but in practice, this information is mostly unavailable. Therefore, image restoration must be done using only the observed noisy and blurred image. In this work, a two-dimensional version of the constant-modulus algorithm, which is commonly used in communications, is adopted to the problem of image restoration. The problem of degradation in performance as the bit number increases when real-valued mapping is used is eliminated by using complex mapping and a complex-valued adaptive filter.