Title :
A morphological approach for feature space partitioning
Author :
Barata, Teresa ; Pina, Pedro
Author_Institution :
Geo-Syst. Centre, Inst. Superior Tecnico, Lisbon, Portugal
Abstract :
A mathematical morphology-based methodology to construct decision region borders that geometrically model the training sets of points is presented in this letter. It is shown that the incorporation of the geometric features of the training sets leads to higher classification rates. Our approach is illustrated with two features of seven land-cover classes [forest (3), soil (2), vegetation, and water] constructed from remotely sensed images of a region in the center of Portugal.
Keywords :
feature extraction; geophysical signal processing; geophysical techniques; image texture; remote sensing; Portugal; anisotropic distance function; classification rates; decision region borders; directional structuring elements; feature space partitioning; forestry; geometric features; land-cover classes; mathematical morphology-based methodology; remotely sensed images; training sets; vegetation; Costs; Helium; Mathematical model; Satellites; Shape; Soil; Solid modeling; Spatial resolution; Testing; Vegetation mapping; Anisotropic distance function; decision region borders; directional structuring elements; textural units;
Journal_Title :
Geoscience and Remote Sensing Letters, IEEE
DOI :
10.1109/LGRS.2005.861539
