The Visual Computer

, Volume 32, Issue 5, pp 611–623

A generalized nonlocal mean framework with object-level cues for saliency detection

Original Article

DOI: 10.1007/s00371-015-1077-z

Cite this article as:
Zhong, G., Liu, R., Cao, J. et al. Vis Comput (2016) 32: 611. doi:10.1007/s00371-015-1077-z


Nonlocal mean (NM) is an efficient method for many low-level image processing tasks. However, it is challenging to directly utilize NM for saliency detection. This is because that conventional NM method can only extract the structure of the image itself and is based on regular pixel-level graph. However, saliency detection usually requires human perceptions and more complex connectivity of image elements. In this paper, we propose a novel generalized nonlocal mean (GNM) framework with the object-level cue which fuses the low-level and high-level cues to generate saliency maps. For a given image, we first use uniqueness to describe the low-level cue. Second, we adopt the objectness algorithm to find potential object candidates, then we pool the object measures onto patches to generate two high-level cues. Finally, by fusing these three cues as an object-level cue for GNM, we obtain the saliency map of the image. Extensive experiments show that our GNM saliency detector produces more precise and reliable results compared to state-of-the-art algorithms.


Generalized nonlocal mean  Saliency detection Objectness cue 

Copyright information

© Springer-Verlag Berlin Heidelberg 2015

Authors and Affiliations

  • Guangyu Zhong
    • 1
  • Risheng Liu
    • 2
  • Junjie Cao
    • 1
  • Zhixun Su
    • 1
  1. 1.School of Mathematical SciencesDalian University of TechnologyDalianChina
  2. 2.School of Software TechnologyDalian University of TechnologyDalianChina

Personalised recommendations