Abstract
This paper presents a novel method for estimation of the joint probability of multisensory signals by introducing dimension-reduction mapping functions based on the principle of maximum entropy. A maximum mutual information criterion is derived for selecting the desired mapping functions. An algorithm is further presented for linear transformations of Gaussian random vectors. Experimental results are shown to demonstrate the performance of the proposed method.
Original language | English (US) |
---|---|
Pages (from-to) | 1431-1437 |
Number of pages | 7 |
Journal | Pattern Recognition Letters |
Volume | 22 |
Issue number | 13 |
DOIs | |
State | Published - Nov 2001 |
Keywords
- Canonical correlation analysis
- Joint probability
- Maximum mutual information
- Multisensory information fusion
- The maximum entropy principle
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition
- Signal Processing
- Electrical and Electronic Engineering