Feature extraction based on the Bhattacharyya distance

In this paper, we propose a feature extraction method based on the Bhattacharyya distance. Recently, it has been reported that an accurate estimation of classification error is possible using the Bhattacharyya distance. In the proposed method, we try to find feature vectors that minimize the estimated classification error of Gaussian ML classifier. In order to find such feature vectors, we start with arbitrary initial feature vectors and update them using two optimization techniques: sequential search and global search. Since we use the error estimation equation for updating feature vectors, the search time can be reduced significantly. We first apply the algorithm to two class problems and extend it to multiclass problems. Experimental results show that the proposed feature extraction algorithm compares favorably with conventional feature extraction algorithms.