Friday, November 14, 2008


We often times get engaged in a debate over definitions and the usefulness of certain words. Image Enhancement is one of those terms that gets people riled up.

I was in an e-mail exchange with a reader seeking to wrap his head around the problems of using the term in testimony. He had heard elsewhere that analysts avoid using the term because of the various implications associated with it. Some use the term Clarify instead of Enhance. Let's take a look at the issue.

Alasdair McAndrew, in his book Introduction to Digital Image Processing with Matlab, gives the following definitions:

Image Enhancement: processing an image so that the result is more suitable for a particular application. 

He then lists the following image processing algorithms associated with Image Enhancement:
  • sharpening or deblurring an out of focus image,
  • highlighting edges,
  • improving image contrast or brightening and image, and
  • removing noise.
Image Restoration: an image may be restored by the damage done to it by an known cause, for example:
  • removing the blur caused by linear motion,
  • removal of optical distortions, and
  • removing periodic interference.
My advice to the reader was to tell his story using words he was comfortable using, to not sound contrived or to talk above himself. If he's comfortable using the word enhanced, then so be it ... just so long as he knows the definition and is comfortable explaining it in real world terms. McAndrew, as a PhD and an imaging educator, is quite a good source to draw from. There are others out there, to be sure.

No comments: