Tolerant rough set on satellite remote sensing data classification
Wen Qi · Computer Engineering and Applications Journal · 2007
In combination of rough set theory and the distribution information of the land cover spectral feature space,a spectral feature neighborhood based tolerant rough set classification method is proposed to handle the uncertainty in the process of satellite remote sensing data classification.Experiment is carried out with Landsat-5 TM image of eastern Beijing.Working mechanism of the method is discussed and classification result is validated and analyzed.Outcome indicates that the proposed method is well interpretable and reliable,and can effectively handle the uncertainty in the process of satellite remote sensing classification.It is a promising tool at classifying areas with complex spectral feature.