A Model of Contour Integration in Early Visual Cortex. Mundhenk, T. N. & Itti, L. In Lecture Notes in Computer Science, volume 2525, pages 80-89, Nov, 2002.
abstract   bibtex   
We have created an algorithm to integrate contour elements and find the salience value of them. The algorithm consists of basic long-range orientation specific neural connections as well as a group suppression gain control and a fast plasticity term to explain interaction beyond a neurons normal size range. Integration is executed as a series of convolutions on 12 orientation filtered images augmented by the nonlinear fast plasticity and group suppression terms. Testing done on a large number of artificially generated Gabor element contour images shows that the algorithm is effective at finding contour elements within parameters similar to that of human subjects. Testing of real world images yields reasonable results and shows that the algorithm has strong potential for use as an addition to our already existent vision saliency algorithm.
@inproceedings{ Mundhenk_Itti02bmcv,
  author = {T. N. Mundhenk and L. Itti},
  title = {A Model of Contour Integration in Early Visual Cortex},
  abstract = { We have created an algorithm to integrate contour elements
and find the salience value of them. The algorithm consists of basic
long-range orientation specific neural connections as well as a group
suppression gain control and a fast plasticity term to explain
interaction beyond a neurons normal size range. Integration is
executed as a series of convolutions on 12 orientation filtered images
augmented by the nonlinear fast plasticity and group suppression
terms. Testing done on a large number of artificially generated Gabor
element contour images shows that the algorithm is effective at
finding contour elements within parameters similar to that of human
subjects. Testing of real world images yields reasonable results and
shows that the algorithm has strong potential for use as an addition
to our already existent vision saliency algorithm.},
  booktitle = {Lecture Notes in Computer Science},
  volume = {2525},
  year = {2002},
  month = {Nov},
  pages = {80-89},
  type = {mod;bu;cv},
  file = { http://iLab.usc.edu/publications/doc/Mundhenk_Itti02bmcv.pdf },
  review = {full/conf}
}

Downloads: 0