Improving Density based Algorithm using Cuckoo Search Algorithm in Segmentation of Medical Images

Medical images have complex geometrical shapes, non-uniform intensity and weak boundaries, therefore one of the main challenges in diagnosing diseases is proper segmentation and feature extraction of medical images. One of the algorithms which is used in segmentation is density based algorithm. One of the main problems in using this algorithm is high time complexity in determining neighborhood radius and number of neighbors which is usually done by the user. One of the main challenges of researchers is to define desirable values of the mentioned parameters. Thus, thus paper tries to use Cuckoo search algorithm to determine optimal values of the mentioned parameters in segmentation based on density algorithm. Results show that Cuckoo search has better performance compared to PSO is segmentation of medical images and determining neighborhood radius and number of neighbors optimally

کلیدواژه ها:

medical images ، segmentation ، Cuckoo search algorithm ، density based algorithm ، particle swarm optimization