Reconfigurable architecture for mathematical morphology using genetic programming and FPGAs

The task of designing manually morphological operators for a given application is not always a trivial one. Genetic programming is a branch of evolutionary computing and it is consolidating as a promising method for applications of digital image processing. The main objective of genetic programming is to discover how computers can learn to solve problems without being programmed for that. In the literature little has been found about the automatic morphological construction of operators using genetic programming. In this paper, it´s presented an original architecture implemented in a FPGA for classical mathematical morphological (binary and gray level) operations that are generated automatically by a genetic programming approach. The possible applications for the system are: pattern recognition and emulation of simple filters, to name just a few. Practical examples using the developed system are presented.