Abstract
This paper presents a computational approach in studying vision and models proposed
for two of the early vision mechanisms: one for obtaining the disparity map in stereo vision, and
the other for edges enhancement in contour integration. A computational perspective in modelling
early visual processes is important for understanding the biological mechanisms, as well as for
integrating the known cortical architecture of primary visual area (V1) and the physiological
functions (some already proved in the experiments, some only presumed). Therefore, our approach
is based on the neuro-physiological findings about the functional columns in V1. We also
developed computer applications for implementing and testing the proposed models and the
results of the simulation were consistent with the biological data.
