Perceptual completion of occluded surfaces
Computer Vision and Image Understanding
Grouping Based on Coupled Diffusion Maps
Shape, Contour and Grouping in Computer Vision
| Hi-index | 0.00 |
In the Kanizsa figure, an illusory central area and its contours are perceived. Replacing the pacman inducers with other shapes can significantly influence this effect. Psychophysical studies indicate that the determination of depth is a task that our visual system constantly conducts. We hypothesized that the illusion is due to the modification of the image according to the higher level depth interpretation. This idea was implemented in a feedback model based on a surface completion scheme. The relative depths, with their signs reflecting the polarity of the image, were determined from junctions by convolution of Gaussian derivative based filters, while a diffusion equation reconstructed the surfaces. The feedback loop was established by converting this depth map to modify the lightness of the image. This model created a central surface and extended the contours from the inducers. Results on a variety of figures were consistent with psychophysical experiments.