Feature extraction based on the Bhattacharyya distance for multimodal data

In this paper, we propose a feature extraction method based on the Bhattacharyya distance for multimodal data. First, we estimate the classification error based on the Bhattacharyya distance between two multimodal classes that are approximated by a finite mixture of Gaussian distributions. Then we extract the features that minimize the estimated classification error. In order to find such features, we explore two search methods: sequential search and global search. Experiments show that the proposed feature extraction algorithm shows promising results