The fuzzy c-partition entropy approach for threshold
selection is one of the best image thresholding techniques, but its
complexity increases with the number of thresholds. In this paper,
the selection of thresholds (fuzzy parameters) was seen as an
optimization problem and solved using particle swarm optimization
(PSO) and differential evolution (DE) algorithms. The proposed
fast approaches have been tested on many images. For example, the
processing time of four-level thresholding using both PSO and DE
is reduced to less than O.4s. PSO and DE show equal performance
when the number of thresholds is small. When the number of
thresholds is greater, PSO algorithm performs better than DE in
terms of precision, robustness and execution time.