Title :
A simple cleaning procedure for improvement of training site statistics
Author :
Gill, Gennette ; Gill, Gennette
Author_Institution :
Punjab Remote Sensing Centre, India
Abstract :
For improving the effectiveness of supervised training, a cleaning procedure which operates by selectively dropping training site pixels based on the Mahalanobis distance and class probability has been proposed. The method is iterative and takes into account the spectral overlap in all image hands. The procedure results in greater classification accuracy with a narrower confidence interval. The Bhattacharrya distance measure of class separability improved from an average value of 1.9373 to 1.9797 with a maximum change for a class pair from 1.2671 to 1.9052. The overall classification accuracy increased from 94.74±0.64 to 39.63±0.19
Keywords :
geophysical techniques; geophysics computing; image recognition; learning (artificial intelligence); neural nets; remote sensing; Bhattacharrya distance measure; Mahalanobis distance; class probability; class separability; classification accuracy; cleaning procedure; geophysical measurement technique; image classification; image processing; iterative; land surface; neural net; remote sensing; selectively dropping training site pixel; supervised training; training site statistics; Cleaning; Cotton; Data compression; Displays; Dynamic range; Humans; Purification; Remote sensing; Statistics; Training data;
Conference_Titel :
Geoscience and Remote Sensing Symposium, 1993. IGARSS '93. Better Understanding of Earth Environment., International
Conference_Location :
Tokyo
Print_ISBN :
0-7803-1240-6
DOI :
10.1109/IGARSS.1993.322039
