%0 Journal Article %T ON ACCURACY OF THE LAND COVEK CLASSIFICATION IN CASE OF USING FRACTAL FEATUE
利用分形特征量提高土地覆盖分类图精度的研究 %A 塔西浦拉提·特依拜 %J 遥感学报 %D 1994 %I %X The objective of this study is to evaluate the land cover classificationaccuracy for incorporating the effective spatial information such as texture and fra-ctal features into spectral information. It has been tested using SPOT HRV multi-spectral data.9 cases have been used to evaluate the approach and the classificationaccuracies have been compared.As a result,PCC(Probability of Correct Classifica-tion)is increased from 88.1% to 90.2% by incorporating fractal features. %K Texture feature %K Fractal feature %K Classification accuracy PCC
结构特征量,分形特征量,分类精度,PCC %U http://www.alljournals.cn/get_abstract_url.aspx?pcid=E62459D214FD64A3C8082E4ED1ABABED5711027BBBDDD35B&cid=A41A70F4AB56AB1B&jid=F926358B31AC94511E4382C083F7683C&aid=B8C28340224B7247ADEB628314D95EEF&yid=3EBE383EEA0A6494&iid=0B39A22176CE99FB&journal_id=1007-4619&journal_name=遥感学报&referenced_num=0&reference_num=0