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：1992
卷号：XXIX Part B3
页码：51-57
出版社：Copernicus Publications
摘要：The fractal-based approaches have been used in a variety of .pplic.tiens. In this paper, Anew method (SAVR) to estimating the fractal dimension (FD) of image data is proposed. AComparative study of the properties of current methods for the FD estimation is carried outand the experiments results show that the SAVR method and the BLANKET method are suitablefor image processing. Furthermore, from the viewpoint of application, we discuss how the FDcan be used as an important measure for image segmentation. Finally, the experiments onfeature extraction and texture segmentation are presented, and some meaningful conclutionsar e obta ined.
