Translator Disclaimer
16 June 2000 Current progress in multiple-image blind demixing algorithms
Author Affiliations +
Proceedings Volume 3831, Sixth International Conference on Education and Training in Optics and Photonics; (2000) https://doi.org/10.1117/12.388716
Event: Education and Training in Optics and Photonics (ETOP'99), 1999, Cancun, Mexico
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.
© (2000) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Harold H. Szu "Current progress in multiple-image blind demixing algorithms", Proc. SPIE 3831, Sixth International Conference on Education and Training in Optics and Photonics, (16 June 2000); https://doi.org/10.1117/12.388716
PROCEEDINGS
7 PAGES


SHARE
Advertisement
Advertisement
Back to Top