
Low-level feature extraction (including edge detection) 145
The reason is the inclusion of the second term in Equation 4.68. In general, the measure of
correlation is not only useful to compute curvature, but this technique has much wider
application in finding points for matching pairs of images.
4.7 Describing image motion
We have looked at the main low-level features that we can extract from a single image. In
the case of motion, we must consider more than one image. If we have two images obtained
at different times, then the simplest way in which we can detect motion is by image
differencing. That is, changes of motion can be located by subtracting ...