I am developing an Android application using Opencv to detect objects from images.
I used Canny edge detector to detect the edges and extract contours, and it's working good so far.
But I need to understand the difference of usage of Canny and Watershed segmentation algorithm.
What's the difference between those two algorithms in terms of performance and accuracy ? Or it just depends on the application ?
And can Watershed works on a generic way? That means can it detect unknown number objects from an image and detect objects with different colors ?