Metaheuristic algorithms are an upper level type of heuristic algorithms.They are known for their efficiency in solving many complex NP problems suchas time table scheduling, traveling salesman, telecommunication, geosciences andmany other scientific, economic and social problems. There are many metaheuristicalgorithms, but the most important one is the Genetic Algorithm (GA).
What makesGA an exceptional algorithm is the ability to adapt to the problem to find the mostsuitable solution that is the global optimal solution. Adaptability of GA is the resultof the population consists of “chromosomes ” which are replaced with a newone using genetics inspired operators of crossover (reproduction ), and mutation. The performance of the algorithm can be enhanced if hybridized with heuristicalgorithms. these heuristics are sometime needed to slow the convergence of GAtoward the local optimal solution that can occur with some problems, and to helpin obtaining the global optimal solution.
GA is known to be very slow comparedto other known optimization algorithms such as Simulated Annealing (SA). Thisspeed will further decrease when GA is hybridized (HyGA). To overcome this issue,it is important to change the structure of the chromosomes and the population. In general, this is done by creating variable length chromosomes . This type ofstructure is called Hybrid Dynamic Genetic Algorithm (HyDyGA).
In this Chapter,GA is covered in detail, this includes hybridization using Hill Climbing algorithm.The improvements to GA are used to solve a very complex NP problem which is theimage segmentation process. Using multicomponent images increases the complexityof the segmentation problem and puts more burden on the Genetic Algorithmperformance.
The efficiency of HyGA and HyDyGA in the segmentation processof multicomponent images is proved using collected field samples and it can reachmore than 97%. In addition, the reliability and the robustness of the new algorithmsare proved using different analysis methods.