CONFERENCE PROCEEDINGS
Advanced Search
Home > Proceedings > Volume 3831 > Article
Open Access Paper
16 June 2000 Current progress in multiple-image blind demixing algorithms
Harold H. Szu
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.
Citation Download Citation
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
DOWNLOAD PAPER SAVE TO MY LIBRARY
GET CITATION
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Independent component analysis
Sensors
Cameras
Machine learning
Neurons
Image sensors
Fourier transforms
RELATED CONTENT
Subscribe to Digital Library
Receive Erratum Email Alert
Back to Top