A network model of object recognition in human vision (1991) [6 citations — 3 self]
|
Popular Tags
No tags have been applied to this document.
BibTeX | Add To MetaCart
@INPROCEEDINGS{Edelman91anetwork,author = {S. Edelman},
title = {A network model of object recognition in human vision},
booktitle = {Neural networks for perception},
year = {1991},
pages = {25--40},
publisher = {Academic Press}
}
Years of Citing Articles
Abstract:
Unlike basic-level categorization, which is largely viewpoint-invariant, ob-ject recognition at the subordinate levels depends on the observer's point of view in several ways. The first part of this article surveys three viewpoint-dependent aspects of human performance in recognition: canonical views, mental rotation, and limited anisotropic generalization to novel views. The second part offers a detailed but informal computational account of these phenomena, obtained by analyzing the functioning of an implemented net-work model of recognition. The success of the model in replicating central features of huntan performance supports the notion that at least one of the available pathways to recognition in the huntan visual system relies on viewpoint-specific representations.
