Saliency detection via statistical non-redundancy

Aanchal Jain, Alexander Wong, Paul W. FieguthICIP 2012 · OpenReview

Abstract

A novel algorithm based on statistical non-redundancy is proposed for saliency detection in natural images. By modeling site neighbourhoods as realizations of other site neighbourhoods under a Gaussian process, the saliency of any arbitrary site can be characterized by the statistical non-redundancy of its site neighbourhood with respect to other site neighbourhoods in a given image. Preliminary results using natural images show that the proposed method provides improved precision vs. recall characteristics over previous methods such as spectral residuals and spectral whitening.
BibTeX
@inproceedings{jain2012saliency,
  author = {Aanchal Jain and Alexander Wong and Paul W. Fieguth},
  title = {{Saliency detection via statistical non-redundancy}},
  booktitle = {ICIP},
  year = {2012},
  url = {https://openreview.net/forum?id=StHTyjrLJA},
}

Loading related content...

Figure