Multiscale saliency detection using random walk with restart

Jun Seong Kim, Jae Young Sim, Chang-Su Kim

Research output: Contribution to journalArticlepeer-review

55 Citations (Scopus)


In this paper, we propose a graph-based multiscale saliency-detection algorithm by modeling eye movements as a random walk on a graph. The proposed algorithm first extracts intensity, color, and compactness features from an input image. It then constructs a fully connected graph by employing image blocks as the nodes. It assigns a high edge weight if the two connected nodes have dissimilar intensity and color features and if the ending node is more compact than the starting node. Then, the proposed algorithm computes the stationary distribution of the Markov chain on the graph as the saliency map. However, the performance of the saliency detection depends on the relative block size in an image. To provide a more reliable saliency map, we develop a coarse-to-fine refinement technique for multiscale saliency maps based on the random walk with restart (RWR). Specifically, we use the saliency map at a coarse scale as the restarting distribution of RWR at a fine scale. Experimental results demonstrate that the proposed algorithm detects visual saliency precisely and reliably. Moreover, the proposed algorithm can be efficiently used in the applications of proto-object extraction and image retargeting.

Original languageEnglish
Article number6544572
Pages (from-to)198-210
Number of pages13
JournalIEEE Transactions on Circuits and Systems for Video Technology
Issue number2
Publication statusPublished - 2014 Feb


  • Compactness feature
  • Markov chain
  • hierarchical saliency refinement
  • multiscale saliency detection
  • random walk with restart

ASJC Scopus subject areas

  • Media Technology
  • Electrical and Electronic Engineering


Dive into the research topics of 'Multiscale saliency detection using random walk with restart'. Together they form a unique fingerprint.

Cite this