Automatic Extraction of Line Drawings from Complex Scenes

Line drawings contain most of the shape-related information in complex scenes. From a technical standpoint, however, automatic extraction of line drawings from raw images has proven extremely difficult, primarily because shape contours are influenced by widely dispersed visual fea-tures acting in subtle geometric combinations. To address this problem, we developed a recurrent network architecture inspired by the intercon-nection circuitry of primary visual cortex, which incorporates several representational biases tailored to the task of long-range visual contour integration. A learning scheme was used to train the modifiable parame-ters of the network to capture the statistical regularities of contour shape. We find that when the trained network is applied to complex images, well-organized contours are selectively boosted and texture edges are se-lectively suppressed, leading to a rough line-drawing-like sketch of the scene