Parametric PSF estimation via sparseness maximization in the wavelet domain

摘要: Image degradation is a frequently encountered problem in different imaging systems, like microscopy, astronomy, digital photography, etc. The usually modeled as convolution with blurring kernel (or Point Spread Function, psf) followed by noise addition. Based on the combined knowledge about image and statistical features of original images, one able to compensate at least partially for using so-called restoration algorithms thus retrieve information hidden observer. One that often this unknown, has be estimated before actual restoration can performed. In work, we assume psf function single parameter, estimate value parameter. As an example such single-parametric psf, have used Gaussian. However, method generic applied account more realistic degradations, optical defocus,