Conference Paper

Neural Network Model Completing Occluded Contour.

Conference: The Fifth International Conference on Neural Information Processing, ICONIP'R98, Kitakyushu, Japan, October 21-23, 1998, Proceedings
Source: DBLP
1 Read
  • [Show abstract] [Hide abstract]
    ABSTRACT: Zhou et al. had found through physiological experiments that in early visual system there are cells encoding the side of the object to which local contour-elements belong, and they called this way of representation “border-ownership coding” (Zhou et al., 2000). This study shows that a simple neural network model supposing early visual system can encode border-ownership. We confirmed that the cells in our model exhibited responses similar to the cells coding border-ownership found by Zhou et al. by computer simulation
    Artificial Neural Networks - ICANN 2001, International Conference Vienna, Austria, August 21-25, 2001 Proceedings; 08/2001
  • [Show abstract] [Hide abstract]
    ABSTRACT: When some parts of a pattern are occluded by other objects, the visual system can often estimate the shape of occluded contours from visible parts of the contours. This paper proposes a neural network model capable of such function, which is called amodal completion. The model is a hierarchical multi-layered network that has bottom-up and top-down signal paths. It contains cells of area V1, which respond selectively to edges of a particular orientation, and cells of area V2, which respond selectively to a particular angle of bend. Using the responses of bend-extracting cells, the model predicts the curvature and location of the occluded contours. Missing contours are gradually extrapolated and interpolated from the visible contours. Computer simulation demonstrates that the model performs amodal completion to various stimuli in a similar way as observed by psychological experiments.
    Neural networks: the official journal of the International Neural Network Society 10/2009; 23(4):528-40. DOI:10.1016/j.neunet.2009.10.002 · 2.71 Impact Factor

Similar Publications