Assuming I already have a working convolution matrix algorithm in place, I'm looking for practical examples of general matrices that are useful for image processing in particular.
The canonical examples you'll find everywhere are non-gaussian box blur:
1 1 1
1 1 1
1 1 1
Image sharpening:
0 -1 0
-1 5 -1
0 -1 0
Edge detection:
0 1 0
1 -4 1
0 1 0
and emboss:
-2 -1 0
-1 1 1
0 1 2
Are there more I'm missing?
have you ever played with jitter, the image processing framework that's part of max/msp? There are a lot of examples of convolution matrices within the example patches, and it's an extremely flexible algorithm prototying environment.
http://cycling74.com
One thing that comes to mind immediately that's not in your list is feedback, but that's usually more interesting in a video context.