Name
Abstract | ||
|---|---|---|
The Fukunaga-Koontz transform (FKT) has been proposed as a feature selection methodology for nearly 32 years. There are a huge number of citations. We have not seen a direct analysis between FKT, and a well established statistical method: Fisher quadratic discriminant analysis (QDA). In this letter, under certain assumptions, we establish such a connection. We speculate that a link in a more gener... |
Year | DOI | Venue |
|---|---|---|
2004 | 10.1109/LSP.2003.821650 | IEEE Signal Processing Letters |
Keywords | Field | DocType |
Statistical analysis,Covariance matrix,Eigenvalues and eigenfunctions,Target recognition,Linear discriminant analysis,Analysis of variance,Computer vision,Face detection,Statistical distributions,Convolution | Optimal discriminant analysis,Pattern recognition,Feature selection,Kernel Fisher discriminant analysis,Feature extraction,Artificial intelligence,Linear discriminant analysis,Mathematics,Machine learning,Quadratic classifier,Statistical analysis | Journal |
Volume | Issue | ISSN |
11 | 2 | 1070-9908 |
Citations | PageRank | References |
4 | 0.51 | 2 |
Authors | ||
1 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xiaoming Huo | 1 | 157 | 24.83 |