Bhattacharyya distance feature selection
- 1 January 1996
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2 (10514651) , 195-199 vol.2
- https://doi.org/10.1109/icpr.1996.546751
Abstract
A recursive algorithm called Bhattacharyya distance feature selection for selecting a real-optimum feature under normal multidistribution is presented. The key of this method is to change the problem of minimizing the criterion of the sum of the upper bound of error probability of every two class pairs in subspace to a problem of solving a nonlinear matrix equation in a multiclass problem under an orthonormal coordinate system. The recursive algorithm is considered as finding the optimal solution of a transformation matrix from the nonlinear matrix equation. The theoretical analysis and experimental results show that under normal multidistribution the performance of the proposed algorithm is superior to the performance of any previous one.Keywords
This publication has 5 references indexed in Scilit:
- An optimal orthonormal system for discriminant analysisPattern Recognition, 1985
- An Optimal Set of Discriminant VectorsIEEE Transactions on Computers, 1975
- A class of upper bounds on probability of error for multihypotheses pattern recognition (Corresp.)IEEE Transactions on Information Theory, 1969
- Comments on linear feature extraction [Corresp.]IEEE Transactions on Information Theory, 1969
- On the effectiveness of receptors in recognition systemsIEEE Transactions on Information Theory, 1963