Objectness to assist salient object detection. Issue 5 (1st May 2016)

• Record Type: Journal Article
• Authors: Sun, Xiaoliang; Su, Ang; Chen, Shengyi; Yu, Qifeng; Liu, Xiaolin
• Is Part Of: IET image processing. Volume 10:Issue 5(2016)
• Page Start: 391
• Page End: 397
• Publication Date: 2016-05-01
• Subjects: object detection -- Markov processes -- Gaussian processes; salient object detection -- low‐level cues -- full‐connected Gaussian Markov random field -- objectness score -- public benchmark datasets; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2015.0487
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : When dealing with salient object that contains several regions with different appearances, salient object detection can be a difficult task as often only parts of the salient object are highlighted and consistency between the salient regions is poor. This study tackles this problem by introducing objectness to assist the salient object detection. Rather than treating objectness in the same manner as other low‐level cues (e.g. uniqueness, location etc.) for the determination of regional saliency values, the authors emphasise that objectness should also play a significant role in tuning the consistency between salient regions. The authors integrate objectness, uniqueness and centre bias to find potential salient regions and then enforce consistency between these regions using a full‐connected Gaussian Markov random field with the weights determined by the objectness score. Experimental results on public benchmark datasets indicate that the authors' method performs well on many images which cannot be well detected traditionally.