Automatic salient object extraction with contextual cue and its applications to recognition and alpha matting

A method for automatically extracting salient object from a single image is presented in this paper. The proposed method is cast in an energy minimization framework. Unlike that only appearance cues are leveraged in most previous methods, an auto-context cue is used as a complementary data term. Ben...

Full description

Saved in:
Bibliographic Details
Published in:Pattern recognition 2013-11, Vol.46 (11), p.2874-2889
Main Authors: Xue, Jianru, Wang, Le, Zheng, Nanning, Hua, Gang
Format: Article
Language:English
Subjects:
Applied sciences
Convergence
Detection, estimation, filtering, equalization, prediction
Effectiveness
Exact sciences and technology
Graph cut
Information, signal and communications theory
Learning
Object extraction
Object recognition
Optimization
Pattern recognition
Recognition
Salient object
Segmentation
Signal and communications theory
Signal representation. Spectral analysis
Signal, noise
Telecommunications and information theory
Visual attention
Visual context
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A method for automatically extracting salient object from a single image is presented in this paper. The proposed method is cast in an energy minimization framework. Unlike that only appearance cues are leveraged in most previous methods, an auto-context cue is used as a complementary data term. Benefitting from a generic saliency model for bootstrapping, the segmentation of the salient object and the learning of the auto-context model are iteratively performed without any user intervention. Upon convergence, the method outputs not only a clear separation of the salient object, but also an auto-context classifier which can be used to recognize the same type of object in other images. Our experiments on four benchmarks demonstrated the efficacy of the added contextual cue. It is shown that our method compares favorably with the state-of-the-art, some of which even embraced user interactions. Furthermore, we present some initial recognition results from the induced auto-context model and also show that the segmentation produced by our approach could serve as a good initialization for alpha matting. •An image segmentation method extracts the object of interest automatically.•An energy minimization model leverages multiple features.•A novel way fuses saliency cue, appearance cue, and contextual cue.•An iterative algorithm jointly extracts the object, and learns its model.•The learned object model can recognize the same type of object in new images.
ISSN:0031-3203
1873-5142
DOI:10.1016/j.patcog.2013.03.028