We investigate the relationship between the classification error and the Bhattacharyya distance of two normally distributed classes and propose a new equation that provides an accurate error estimation for the Gaussian ML classifier. With the error estimation equation, it is possible to estimate the classification error within a 1-2% margin.
|Number of pages||5|
|Journal||IEEE Transactions on Geoscience and Remote Sensing|
|Publication status||Published - 2000|
All Science Journal Classification (ASJC) codes
- Electrical and Electronic Engineering
- Earth and Planetary Sciences(all)