Skip to main content
placeholder image

Salient object detection via weighted low rank matrix recovery

Journal Article


Abstract


  • Image-based salient object detection is a useful and important technique, which can promote the efficiency of several applications such as object detection, image classification/retrieval, object co-segmentation, and content-based image editing. In this letter, we present a novel weighted low-rank matrix recovery (WLRR) model for salient object detection. In order to facilitate efficient salient objects-background separation, a high-level background prior map is estimated by employing the property of the color, location, and boundary connectivity, and then this prior map is ensembled into a weighting matrix which indicates the likelihood that each image region belongs to the background. The final salient object detection task is formulated as the WLRR model with the weighting matrix. Both quantitative and qualitative experimental results on three challenging datasets show competitive results as compared with 24 state-of-the-art methods.

UOW Authors


  •   Tang, Chang (external author)
  •   Wang, Pichao (external author)
  •   Zhang, Changqing (external author)
  •   Li, Wanqing

Publication Date


  • 2017

Citation


  • Tang, C., Wang, P., Zhang, C. & Li, W. (2017). Salient object detection via weighted low rank matrix recovery. IEEE Signal Processing Letters, 24 (4), 490-494.

Scopus Eid


  • 2-s2.0-85017610726

Number Of Pages


  • 4

Start Page


  • 490

End Page


  • 494

Volume


  • 24

Issue


  • 4

Abstract


  • Image-based salient object detection is a useful and important technique, which can promote the efficiency of several applications such as object detection, image classification/retrieval, object co-segmentation, and content-based image editing. In this letter, we present a novel weighted low-rank matrix recovery (WLRR) model for salient object detection. In order to facilitate efficient salient objects-background separation, a high-level background prior map is estimated by employing the property of the color, location, and boundary connectivity, and then this prior map is ensembled into a weighting matrix which indicates the likelihood that each image region belongs to the background. The final salient object detection task is formulated as the WLRR model with the weighting matrix. Both quantitative and qualitative experimental results on three challenging datasets show competitive results as compared with 24 state-of-the-art methods.

UOW Authors


  •   Tang, Chang (external author)
  •   Wang, Pichao (external author)
  •   Zhang, Changqing (external author)
  •   Li, Wanqing

Publication Date


  • 2017

Citation


  • Tang, C., Wang, P., Zhang, C. & Li, W. (2017). Salient object detection via weighted low rank matrix recovery. IEEE Signal Processing Letters, 24 (4), 490-494.

Scopus Eid


  • 2-s2.0-85017610726

Number Of Pages


  • 4

Start Page


  • 490

End Page


  • 494

Volume


  • 24

Issue


  • 4