Icqpso-Based Multilevel Thresholding Scheme Applied On Colour Image Segmentation

This study proposes an improved cooperative quantum-behaved particle swarm optimisation (ICQPSO) algorithm to find multiple threshold levels for colour images with multilevel Renyi entropy (MRE). In the proposed method, the context vector of each particle is updated each time dynamically when a cooperation operation is completed with other particles. The improved search ability and optimisation performance of ICQPSO algorithm with MRE (hence called MRE-ICQPSO) extensively investigated with other well known nature-inspired algorithms such as Levi flight-guided firefly, cuckoo search, artificial bee colony, and beta differential evolution. The proposed method is applied to the Berkley segmentation dataset with 300 distinct colour images to show the effective performance of the algorithm in terms of fidelity parameters and computation time.