期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：2004
卷号：XXXV Part B4
页码：617-622
出版社：Copernicus Publications
摘要：This paper put forward an new solution, which adopted the genetic algorithm to obtain the global optimal solution (approximate) of automated label placement of point feature. In the paper, the basic thought and design framework of using genetic algorithm to solve point feature labelling was firstly introduced, then, some practical technique and new improved method during the experiment procedure of genetic algorithm adopted by the author were presented in detail. Finally, in order to prove the advantage of genetic algorithm, some experiment were conducted which compare the efficiency of genetic algorithm with hill climbing algorithm, simulated annealing, neural network, etc. The result of comparison experiment was given out, which has proved the superiority of genetic algorithm, especially proved the genetic algorithm is a kind of high-efficient, robust, all-purpose algorithm with well- expansibility, and is the most promising solution for automated map labelling
