A simple cleaning procedure for improvement of training site statistics
| Autor: | Gurinder Gill, Gurjtt Gill |
|---|---|
| Rok vydání: | 1994 |
| Předmět: |
Mahalanobis distance
Training set Artificial neural network Contextual image classification Pixel Computer science business.industry Multispectral image Geography Planning and Development Image processing Pattern recognition Measure (mathematics) Class (biology) Confidence interval Image (mathematics) Simple (abstract algebra) Statistics Earth and Planetary Sciences (miscellaneous) Artificial intelligence business Data compression Test data |
| Zdroj: | Journal of the Indian Society of Remote Sensing. 22:87-92 |
| ISSN: | 0974-3006 0255-660X |
| Popis: | For improving the effectiveness of supervised training, a simple 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 bands with all the user specified classes. The procedure results in greater classification accuracy with narrower confidence interval. On the test data, Bhattacharrya distance measure of class separability unproved front 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 99.63 ± 0.19. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink