Medical Image Registration: Theory, Algorithm, and Case Studies in Surgical Simulation, Chest Cancer, and Multiple Sclerosis - Biomedical Image Analysis - page 30

α

α i

U P

U P

β

i

α

i

d i

β

P

U P i

i

d i

P i

U P i

d

SPS image at P

Figure 1.10: (a) For each important point on the surface a signature image is
obtained. This image encodes the angle difference between the normal at the
point in focus and the normal at each other point on the surface. (b) Examples
of signature images taken at different important points locations. Notice how
the image provides features the curvature information. The dark intensity in the
image represents a high curvature seen from the point while the light intensity
represents a low curvature. Also notice how different the image corresponding
to a location is from images of other locations.