Abstract: This work evaluates real-time techniques for a novel concept of identifying weeds, location and extraction of outline features. THE proposed techniques are conducted by electro- optical methods and perform with the speed of light. The optical system is compact, easy to align and uses a small number of inexpensive components. Generating the 'right' filter for a pattern recognition problem is presented as an optimization process for which the filter performance is the function to be maximized. The genetic algorithm is introduce as a search procedure that uses a biologically motivated random choice as a tool to guide a highly exploitative search through the filter space for nonlinear correlation. The features of the genetic algorithm are ideal for a highly efficient and fast learning process. Computer simulations demonstrate very efficient pattern recognition and excellent discrimination. !10
展开▼
