---

Purdue University
School of Electrical and Computer Engineering
Digital Image Processing Laboratories

Image Restoration

---

Abstract

A common inverse problem in image processing is the estimation of an image given a corrupted version. In this laboratory, an optimal linear filter is designed to perform this task. A nonlinear filter known as a weighted median filter, is also applied.

To run this laboratory, you will need:

• Matlab with both the signal and image processing tool boxes.
• An application for displaying TIFF images.
• An ANSI C compiler such as gcc or MS Visual Studio.

Laboratory Procedure - Instructions for running the laboratory in pdf format.

images.zip - Contains four images used in the lab. img14g.tif is the original, and img14bl.tif, img14gn.tif, and img14sp.tif are three corrupted versions.

C-code - A GitHub repository containing an example ANSI C programs.

Questions or comments should be sent to:

Prof. Charles A. Bouman, School of Electrical and Computer Engineering, Purdue University, West Lafayette IN 47907; (765) 494-0340; bouman@ecn.purdue.edu