Spectral salient object detection

Keren Fu, Chen Gong, Irene Y.H. Gu, Jie Yang, Xiangjian He

Research output: Journal PublicationConference articlepeer-review

5 Citations (Scopus)

Abstract

Many existing methods for salient object detection are performed by over-segmenting images into non-overlapping regions, which facilitate local/global color statistics for saliency computation. In this paper, we propose a new approach: spectral salient object detection, which is benefited from selected attributes of normalized cut, enabling better retaining of holistic salient objects as comparing to conventionally employed pre-segmentation techniques. The proposed saliency detection method recursively bi-partitions regions that render the lowest cut cost in each iteration, resulting in binary spanning tree structure. Each segmented region is then evaluated under criterion that fit Gestalt laws and statistical prior. Final result is obtained by integrating multiple intermediate saliency maps. Experimental results on three benchmark datasets demonstrate the effectiveness of the proposed method against 13 state-of-the-art approaches to salient object detection.

Original languageEnglish
Article number6890142
JournalProceedings - IEEE International Conference on Multimedia and Expo
Volume2014-September
Issue numberSeptmber
DOIs
Publication statusPublished - 3 Sept 2014
Externally publishedYes
Event2014 IEEE International Conference on Multimedia and Expo, ICME 2014 - Chengdu, China
Duration: 14 Jul 201418 Jul 2014

Keywords

  • Gestalt laws
  • Normalized cut
  • Partition
  • Pre-segmentation
  • Salient object detection

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Spectral salient object detection'. Together they form a unique fingerprint.

Cite this