Current progress in multiple-image blind demixing algorithms
Harold H Szu · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2000
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.