Why direct LDA is not equivalent to LDA

@article{Gao2006WhyDL,
  title={Why direct LDA is not equivalent to LDA},
  author={Hui Gao and James W. Davis},
  journal={Pattern Recognition},
  year={2006},
  volume={39},
  pages={1002-1006}
}
In this paper, we present counterarguments against the direct LDA algorithm (D-LDA), which was previously claimed to be equivalent to Linear Discriminant Analysis (LDA). We show from Bayesian decision theory that D-LDA is actually a special case of LDA by directly taking the linear space of class means as the LDA solution. The pooled covariance estimate is completely ignored. Furthermore, we demonstrate that D-LDA is not equivalent to traditional subspace-based LDA in dealing with the Small… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.
38 Citations
7 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 38 extracted citations

Similar Papers

Loading similar papers…