Recognizing Planar Objects Using Invariant Image Features

Given a familiar object extracted from its surroundings, we
humans have      little difficulty in recognizing it irrespective
of its size, position and   orientation in our field of view.
Changes in lighting and the effects of      perspective also pose
no problems. How do we achieve this, and more            importantly,
how can we get a computer to do this? One very                        promising
approach is to find mathematical functions of an                           object's
image, or of an object's 3D description, that are invariant
to the transformations caused by the object's motion.
This book is devoted to   the theory and practice of such
invariant image features, so-called image   invariants, for
planar objects. It gives a comprehensive summary of            the
field, discussing methods for recognizing both occluded                        and
partially occluded objects, and also contains a definitive
treatmentof moment invariants and a tutorial introduction
to algebraic invariants,   which are fundamental to affine
moment invariants and to many projective      invariants.
A number of novel invariant functions are presented and            the
results of numerous experiments investigating the stability
of new   and old invariants are discussed. The main conclusion
is that moment            invariants are very effective, both for
partially occluded objects and for   recognizing objects in
grey-level images.