Tampere University of Technology

TUTCRIS Research Portal

Probabilistic saliency estimation

Research output: Contribution to journalArticleScientificpeer-review

Details

Original languageEnglish
Pages (from-to)359-372
Number of pages14
JournalPattern Recognition
Volume74
Early online date20 Sep 2017
DOIs
Publication statusPublished - 2018
Publication typeA1 Journal article-refereed

Abstract

In this paper, we model the salient object detection problem under a probabilistic framework encoding the boundary connectivity saliency cue and smoothness constraints into an optimization problem. We show that this problem has a closed form global optimum solution, which estimates the salient object. We further show that along with the probabilistic framework, the proposed method also enjoys a wide range of interpretations, i.e. graph cut, diffusion maps and one-class classification. With an analysis according to these interpretations, we also find that our proposed method provides approximations to the global optimum to another criterion that integrates local/global contrast and large area saliency cues. The proposed unsupervised approach achieves mostly leading performance compared to the state-of-the-art unsupervised algorithms over a large set of salient object detection datasets including around 17k images for several evaluation metrics. Furthermore, the computational complexity of the proposed method is favorable/comparable to many state-of-the-art unsupervised techniques.

Keywords

  • Diffusion maps, One-class classification, Probabilistic model, Saliency, Salient object detection, Spectral graph cut

Publication forum classification

Field of science, Statistics Finland