1 March 1991 Neural network for inferring the shape of occluded objects
Author Affiliations +
Two different approaches have been implemented to model the filling-in procedure for inferring the shape of occluded objects: computational and back-propagation network. The two approaches have been found to have functional similarities. The receptive fields of the units have been analyzed and an analogy with the receptive field of neurons in area V2 of visual cortex was suggested.
© (1991) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ljubomir Citkusev, Lucia M. Vaina, "Neural network for inferring the shape of occluded objects", Proc. SPIE 1468, Applications of Artificial Intelligence IX, (1 March 1991); doi: 10.1117/12.45517; https://doi.org/10.1117/12.45517

Back to Top