Iterative Tuning of Simple Cells for Contrast Invariant Edge Enhancement

This work describes a novel model for orientation tuning of simple cells in V1. The model has been inspired by a regular structure of simple cells in the visual primary cortex of mammals. Two new features distinguish the model: the iterative processing of visual inputs; and amplification of tuned responses of spatially close simple cells. Results show that after several iterations the processing converges to a stable solution while making edge enhancement largely contrast independent. The model suppresses weak edges in the vicinity of contrastive luminance changes but enhances isolated low-intensity changes. We demonstrate the capabilities of the model by processing synthetic as well as natural images.