A Network Mechanism for the Determination of Shape-from-Texture
Abstract
We propose a computational model for how the cortex discriminates shape and depth from texture. The model consists of four stages: (1) extraction of local spatial frequency, (2) frequency characterization, (3) detection of texture compression by normalization, and (4) integration of the normalized frequency over space. The model accounts for a number of psychophysical observations including experiments based on novel random textures. These textures are generated from white noise and manipulated in Fourier domain in order to produce specific frequency spectra. Simulations with a range of stimuli, including real images, show qualitative and quantitative agreement with human perception.
Cite
Text
Sakai and Finkel. "A Network Mechanism for the Determination of Shape-from-Texture." Neural Information Processing Systems, 1993.Markdown
[Sakai and Finkel. "A Network Mechanism for the Determination of Shape-from-Texture." Neural Information Processing Systems, 1993.](https://mlanthology.org/neurips/1993/sakai1993neurips-network/)BibTeX
@inproceedings{sakai1993neurips-network,
title = {{A Network Mechanism for the Determination of Shape-from-Texture}},
author = {Sakai, Kô and Finkel, Leif H.},
booktitle = {Neural Information Processing Systems},
year = {1993},
pages = {953-960},
url = {https://mlanthology.org/neurips/1993/sakai1993neurips-network/}
}