PROJECT TITLE :
Unsupervised Hyperspectral Image Band Selection via Column Subset Selection
During this letter, we proposed a completely unique band selection algorithm for hyperspectral pictures (HSIs) based on column subset selection. The main idea of the proposed algorithm comes from the column subset selection downside in numerical linear algebra. It selects a cluster of bands, which maximizes the quantity of the selected subset of columns. Since the high dimensionality decreases the distinction between bands, we use Manhattan distance to obtain a better choice quality. Experimental results on real HSIs show that the proposed algorithm obtains competitively smart results, in terms of classification accuracy, and is robust to noisy bands.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here