broader view was taken later (Jain et al., 1998). A comprehensive survey of flexible extractions
from medical imagery (McInerney and Terzopolous, 1996) reinforces the dominance of snakes
in medical image analysis, to which they are particularly suited given a target of smooth shapes.
(An excellent survey of history and progress of medical image analysis is available (Duncan
and Ayache, 2000).) Few of the textbooks devote much space to shape extraction, and snakes,
especially level set methods, are too recent a development to be included in many textbooks.
One text alone is dedicated to shape analysis (van Otterloo, 1991) and contains many discussions
on symmetry. A visit to Professor Cootes’ website (http://www.isbe.man.ac.uk/∼bim/) reveals a
lengthy report on flexible shape modelling and a lot of support material (including Windows and
Linux code) in active shape modelling. For work on level set methods for image segmentation,
see Cremers et al. (2007).
Adalsteinsson, D. and Sethian, J., A Fast Level Set Method for Propagating Interfaces, J. Com-
putational Physics, 118(2), pp. 269–277, 1995