An edge detection technique using genetic algorithm-based optimization

摘要: Abstract In this paper we present a genetic algorithm-based optimization technique for edge detection. The problem of detection is formulated as one choosing minimum cost configuration. configurations are viewed two-dimensional chromosomes with fitness values inversely proportional to their costs. design the crossover and mutation operators in context chromosomal representation described. knowledge-augmented operator which exploits knowledge local structure shown result rapid convergence. incorporation meta-level strategies such elitism strategy, engineered conditioning adaptation rates discussed improve convergence rate. algorithm various combinations tested on synthetic natural images. performance minimization compared both qualitatively quantitatively search-based simulated annealing-based approaches. perform very well terms robustness noise, rate quality final image.