A Rotation and Translation Invariant Discrete Saliency Network

Part of Advances in Neural Information Processing Systems 14 (NIPS 2001)

Bibtex Metadata Paper


Lance Williams, John W. Zweck


We describe a neural network which enhances and completes salient closed contours. Our work is different from all previous work in three important ways. First, like the input provided to V1 by LGN, the in- put to our computation is isotropic. That is, the input is composed of spots not edges. Second, our network computes a well deļ¬ned function of the input based on a distribution of closed contours characterized by a random process. Third, even though our computation is implemented in a discrete network, its output is invariant to continuous rotations and translations of the input pattern.