Saliency Detection Using Sparse and Nonlinear Feature Representation
Joint Authors
Anwar, Shahzad
Zhao, Qingjie
Manzoor, Muhammad Farhan
Ishaq Khan, Saqib
Source
Issue
Vol. 2014, Issue 2014 (31 Dec. 2014), pp.1-16, 16 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2014-05-08
Country of Publication
Egypt
No. of Pages
16
Main Subjects
Medicine
Information Technology and Computer Science
Abstract EN
An important aspect of visual saliency detection is how features that form an input image are represented.
A popular theory supports sparse feature representation, an image being represented with a basis dictionary having sparse weighting coefficient.
Another method uses a nonlinear combination of image features for representation.
In our work, we combine the two methods and propose a scheme that takes advantage of both sparse and nonlinear feature representation.
To this end, we use independent component analysis (ICA) and covariant matrices, respectively.
To compute saliency, we use a biologically plausible center surround difference (CSD) mechanism.
Our sparse features are adaptive in nature; the ICA basis function are learnt at every image representation, rather than being fixed.
We show that Adaptive Sparse Features when used with a CSD mechanism yield better results compared to fixed sparse representations.
We also show that covariant matrices consisting of nonlinear integration of color information alone are sufficient to efficiently estimate saliency from an image.
The proposed dual representation scheme is then evaluated against human eye fixation prediction, response to psychological patterns, and salient object detection on well-known datasets.
We conclude that having two forms of representation compliments one another and results in better saliency detection.
American Psychological Association (APA)
Anwar, Shahzad& Zhao, Qingjie& Manzoor, Muhammad Farhan& Ishaq Khan, Saqib. 2014. Saliency Detection Using Sparse and Nonlinear Feature Representation. The Scientific World Journal،Vol. 2014, no. 2014, pp.1-16.
https://search.emarefa.net/detail/BIM-1048429
Modern Language Association (MLA)
Anwar, Shahzad…[et al.]. Saliency Detection Using Sparse and Nonlinear Feature Representation. The Scientific World Journal No. 2014 (2014), pp.1-16.
https://search.emarefa.net/detail/BIM-1048429
American Medical Association (AMA)
Anwar, Shahzad& Zhao, Qingjie& Manzoor, Muhammad Farhan& Ishaq Khan, Saqib. Saliency Detection Using Sparse and Nonlinear Feature Representation. The Scientific World Journal. 2014. Vol. 2014, no. 2014, pp.1-16.
https://search.emarefa.net/detail/BIM-1048429
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1048429