Abstract
An adaptive wavelet decomposition algorithm called the Best Wavelet Packet Basis is used to extract the most useful spectral features from the original hyperspectral data for classification applications. Tested on a set of AVIRIS data, the novel feature extraction method is evaluated and compared with some contemporary feature extraction methods.
| Original language | English |
|---|---|
| Pages | 1667-1669 |
| Number of pages | 3 |
| Publication status | Published - 2002 Jan 1 |
| Event | 2002 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2002) - Toronto, Ont., Canada Duration: 2002 Jun 24 → 2002 Jun 28 |
Other
| Other | 2002 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2002) |
|---|---|
| Country/Territory | Canada |
| City | Toronto, Ont. |
| Period | 02-06-24 → 02-06-28 |
All Science Journal Classification (ASJC) codes
- Computer Science Applications
- General Earth and Planetary Sciences