Director Field Model of the Primary Visual Cortex for Contour Detection
This work addresses contour detection in computer vision, which is incremental as it builds on existing neural models but introduces a simpler approach.
The authors tackled the problem of detecting long, noisy contours in cluttered visual scenes by modeling the primary visual cortex with a continuous director field and a linear-nonlinear dynamical model, resulting in high-precision, high-recall detection of large objects with substantially fewer degrees of freedom than traditional models.
We aim to build the simplest possible model capable of detecting long, noisy contours in a cluttered visual scene. For this, we model the neural dynamics in the primate primary visual cortex in terms of a continuous director field that describes the average rate and the average orientational preference of active neurons at a particular point in the cortex. We then use a linear-nonlinear dynamical model with long range connectivity patterns to enforce long-range statistical context present in the analyzed images. The resulting model has substantially fewer degrees of freedom than traditional models, and yet it can distinguish large contiguous objects from the background clutter by suppressing the clutter and by filling-in occluded elements of object contours. This results in high-precision, high-recall detection of large objects in cluttered scenes. Parenthetically, our model has a direct correspondence with the Landau - de Gennes theory of nematic liquid crystal in two dimensions.