General Structure of Regularization Procedures in Image Reconstruction

Astronomy and Astrophysics – Astrophysics

Scientific paper

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

62

Scientific paper

Regularization procedures are portrayed as compromises between the conflicting aims of fidelity with the observed image and perfect smoothness. The selection of an estimated image involves the choice of a prescription, indicating the manner of smoothing, and of a smoothing parameter, which defines the degree of smoothing. Prescriptions of the minimum-penalized- distance type are considered and are shown to be equivalent to maximum-penalized-smoothness prescriptions. These include, therefore, constrained least-squares and constrained maximum entropy methods. The formal link with Bayesian statistical analysis is pointed out. Two important methods of choosing the degree of smoothing are described, one based on criteria of consistency with the data and one based on minimizing a risk function. The latter includes minimum mean-squared error criteria. Although the maximum entropy method has some practical advantages, there seems no case for it to hold a special place on philosophical grounds, in the context of image reconstruction.

No associations

LandOfFree

Say what you really think

Search LandOfFree.com for scientists and scientific papers. Rate them and share your experience with other people.

Rating

General Structure of Regularization Procedures in Image Reconstruction does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with General Structure of Regularization Procedures in Image Reconstruction, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and General Structure of Regularization Procedures in Image Reconstruction will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFWR-SCP-O-818399

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.