In this paper, we propose a novel method for extracting the geometric
primitives from geometric data, which is essentially an optimization p
roblem. Specifically, we use tabu search to solve geometric primitive
extraction problem. To the best of our knowledge, it is the first atte
mpt that tabu search is used in computer vision. Our tabu search (TS)
has a number of advantages: (1) TS avoids entrapment in local minima a
nd continues the search to give a near-optimal final solution; (2) TS
is very general and conceptually much simpler than either simulated an
nealing (SA) or genetic algorithm (GA); (3) TS has no special space re
quirement and is very easy to implement (the entire procedure only occ
upies a few lines of code); (4) our TS-based method can successfully e
xtract some geometric primitives which are specially difficult for the
traditional methods such as Hough Transform (HT) and Robust Statistic
s(RS). TS is a flexible framework of a variety of strategies originati
ng from artificial intelligence and is therefore open to further impro
vement. (C) 1997 Published by Elsevier Science B.V.