Next: Feature point extraction
Up: Feature extraction and matching
Previous: Feature extraction and matching
Image regions are typically compared using sum-of-square-differences (SSD) or normalized cross-correlation (NCC). Consider a window in image and a corresponding region in image . The dissimilarity between two image regions based on SSD is given by
where is a weighting function that is defined over W. Typically, or it is a Gaussian.
The similarity measure between two image regions based on NCC is given by
the mean image intensity in the considered region. Note that this last measure is invariant to global intensity and contrast changes over the considered regions.