Share Email Print
cover

Proceedings Paper • Open Access

Current progress in multiple-image blind demixing algorithms
Author(s): Harold H. Szu

Paper Abstract

Imagery edges occur naturally in human visual systems as a consequence of redundancy reduction towards `sparse and orthogonality feature maps,' which have been recently derived from the maximum entropy information-theoretical first principle of artificial neural networks. After a brief match review of such an Independent Component Analysis or Blind Source Separation of edge maps, we explore the de- mixing condition for more than two imagery objects recognizable by an intelligent pair of cameras with memory in a time-multiplex fashion.

Paper Details

Date Published: 16 June 2000
PDF: 7 pages
Proc. SPIE 3831, Sixth International Conference on Education and Training in Optics and Photonics, (16 June 2000); doi: 10.1117/12.388716
Show Author Affiliations
Harold H. Szu, Office of Naval Research (United States)


Published in SPIE Proceedings Vol. 3831:
Sixth International Conference on Education and Training in Optics and Photonics
Jose Javier Sanchez-Mondragon, Editor(s)

© SPIE. Terms of Use
Back to Top