Mutual relations among optimum image restoration filters

✍ Scribed by Yukihiko Yamashita; Hidemitsu Ogawa

• Publisher: John Wiley and Sons
• Year: 1993
• Tongue: English
• Weight: 774 KB
• Volume: 24
• Category: Article
• ISSN: 0882-1666
• DOI: 10.1002/scj.4690240608

✦ Synopsis

Abstract

An optimum image restoration filter is an image restoration filter satisfying some optimum criterion, and there are many different optimum restoration filters corresponding to different optimization criterion. Close relationships exist between these various filters, and through understanding these relationships we can, along with gaining a better understanding of the principles behind the filters, approximate or replace one filter by another and reduce the computing complexity required to compute it.

The relationships between these filters have been explored on a one‐by‐one basis in the past, but in this paper a systematic assessment is made of the relationships between nine kinds of optimum restoration filters. In addition, it is confirmed experimentally that the parametric Wiener filter can approximate the averaged projection filter with arbitrary precision.