作者: Riccardo Poli
DOI: 10.1007/BFB0032777
关键词: Image texture 、 Scale-space segmentation 、 Genetic algorithm 、 Computer science 、 Pattern recognition 、 Feature detection (computer vision) 、 Genetic programming 、 Feature (computer vision) 、 Image segmentation 、 Segmentation-based object categorization 、 Artificial intelligence
摘要: Genetic Programming is a method of program discovery/optimisation consisting special kind genetic algorithm capable operating on nonlinear chromosomes (parse trees) representing programs and an interpreter which can run the being optimised. In this paper we describe set terminals functions for parse trees handled by programming enable it to develop effective image filters. These filters either be used highly enhance detect features interest or build pixel-classification-based segmentation algorithms. Some experiments with medical images show efficacy approach are reported.