Skip to main content
Advertisement
  • Loading metrics

PLoS Computational Biology Issue Image | Vol. 3(9) September 2007

Synthetic "dead-leaves" image

Natural images occupy a small subset of the high-dimensional manifold of possible images, and are therefore characterized by certain statistical properties. The image shown here is a synthetic "dead-leaves" image, which preserves many of the statistical structures common to natural images. Artificial neural networks were trained to recognize surfaces within these images under illumination that vary in space and time, with the result that the trained networks exhibited responses commensurate with human lightness illusions (see Corney and Lotto, e180).

Image Credit: Image by David Corney and R. Beau Lotto (http://www.lottolab.org)

thumbnail
Synthetic "dead-leaves" image

Natural images occupy a small subset of the high-dimensional manifold of possible images, and are therefore characterized by certain statistical properties. The image shown here is a synthetic "dead-leaves" image, which preserves many of the statistical structures common to natural images. Artificial neural networks were trained to recognize surfaces within these images under illumination that vary in space and time, with the result that the trained networks exhibited responses commensurate with human lightness illusions (see Corney and Lotto, e180).

Image Credit: Image by David Corney and R. Beau Lotto (http://www.lottolab.org)

https://doi.org/10.1371/image.pcbi.v03.i09.g001