An Approach to Derive Parametric L-System Using Genetic Algorithm

In computer graphics, L-System is widely used to model artificial plants structures and fractals. The Genetic Algorithm (GA) is the most popular form of Evolutionary Algorithms. This paper examines a method for automatic plant modeling which is based on an integration of GA and Parametric L-System using appropriate fitness function. The approach is specifically based on the implementation of two layered GA to derive the rewriting rules of Parametric L-System. The higher level of GA deals with the evolution of symbols and lower level deals with the evolution of numerical parameters. Initial results derived from the approach are very promising, which shows that complicated branching structures can be easily derived by the multilayered architecture of GA.