What is the difference between edge and ridge detection?

Question

The title is tells already enough, but citing Wikipedia:

The purpose of ridge detection is usually to capture the major axis of symmetry of an elongated object,[citation needed] whereas the purpose of edge detection is usually to capture the boundary of the object. However, some literature on edge detection erroneously[citation needed] includes the notion of ridges into the concept of edges, which confuses the situation.

But the difference is still not clear to me. Can you help (eventually with some example)?

Possible duplicate of [Implementing ridge detection](http://stackoverflow.com/questions/585160/implementing-ridge-detection) — tfv, May 29 '16 at 07:00
The linked question seeks for an implementation, there is no discussion about the two topics — justHelloWorld, May 29 '16 at 07:19
See [here](http://dsp.stackexchange.com/questions/1714/best-way-of-segmenting-veins-in-leaves) in the answer — Elad Joseph, May 29 '16 at 07:22
I think that now the difference is clear. If you'll post it as an answer, I'll chose it — justHelloWorld, May 29 '16 at 07:27

score 11 · Accepted Answer · edited Apr 13 '17 at 12:47

11

Edges: Borders between areas of high and low gray value.
Ridges: Thin lines darker or brighter than their neighborhood.

Usually, if we do an edge detection on a ridge area we will get a double line, one from each side of the ridge.

This answer is based on this answer, which gives a much more detailed explanation.

edited Apr 13 '17 at 12:47

Community

1
1

answered May 29 '16 at 07:46

Elad Joseph

2,998
26
41

What is the difference between edge and ridge detection?

1 Answers1