A Neural Network Model for Extraction of Salient Contours

Qiling Tang, Nong Sang, Tianxu Zhang

Abstract

In this paper, we construct a neural network structure to model the mechanisms of visual perception for salient contour – for some stimulus conditions, the response of a visual central stimulus is suppressed and for other conditions the response is enhanced. The proposed method which distinguishes between contours and texture edges can effectively eliminates surround textures, and at the same time, enables preservation of smooth contour. In particular, while some contours embedded in cluttered background are destructed due to surround disturbance, our approach can restore them better.
BibTeX
@inproceedings{tang2005neural,
  author = {Qiling Tang and Nong Sang and Tianxu Zhang},
  title = {{A Neural Network Model for Extraction of Salient Contours}},
  booktitle = {ISNN},
  year = {2005},
  doi = {10.1007/11427445\_51},
}

Loading related content...

Figure