Special Section on Image/Video Quality and System Performance

Multiview saliency detection based on improved multimanifold ranking

[+] Author Affiliations
Yanjiao Shi

Northeast Normal University, School of Computer Science and Information Technology, Key Laboratory of Intelligent Information Processing of Jilin Universities, Changchun 130117, China

Northeast Normal University, School of Mathematics and Statistics, Changchun 130117, China

Yugen Yi

Northeast Normal University, School of Computer Science and Information Technology, Key Laboratory of Intelligent Information Processing of Jilin Universities, Changchun 130117, China

Northeast Normal University, School of Mathematics and Statistics, Changchun 130117, China

Ke Zhang

Northeast Normal University, School of Computer Science and Information Technology, Key Laboratory of Intelligent Information Processing of Jilin Universities, Changchun 130117, China

Jun Kong

Northeast Normal University, School of Computer Science and Information Technology, Key Laboratory of Intelligent Information Processing of Jilin Universities, Changchun 130117, China

Northeast Normal University, School of Mathematics and Statistics, Changchun 130117, China

Ming Zhang

Northeast Normal University, School of Computer Science and Information Technology, Key Laboratory of Intelligent Information Processing of Jilin Universities, Changchun 130117, China

Jianzhong Wang

Northeast Normal University, School of Computer Science and Information Technology, Key Laboratory of Intelligent Information Processing of Jilin Universities, Changchun 130117, China

Northeast Normal University, National Engineering Laboratory for Druggable Gene and Protein Screening, Changchun 130117, China

J. Electron. Imaging. 23(6), 061113 (Sep 19, 2014). doi:10.1117/1.JEI.23.6.061113
History: Received March 21, 2014; Revised August 25, 2014; Accepted September 2, 2014
Text Size: A A A

Abstract.  As an important problem in computer vision, saliency detection is essential for image segmentation, super-resolution, object recognition, and so on. We propose a saliency detection method for images. Instead of using contrast between salient regions and their surrounding areas, both cues from salient and nonsalient regions are considered in our study. Based on these cues, an improved multimanifold ranking algorithm is proposed. In our algorithm, features from multiple views are utilized and the different contributions of these multiview features are taken into account. Moreover, an iterative updating optimization scheme is explored to solve the objective function, during which the feature fusion is performed. After two-stage ranking by the improved multimanifold ranking algorithm, each image patch can be assigned a ranking score, which determines the final saliency. The proposed method is evaluated on four public datasets and is compared with the state-of-the-art methods. Experimental results indicate that the proposed method outperforms existing schemes both in qualitative and quantitative comparisons.

© 2014 SPIE and IS&T

Citation

Yanjiao Shi ; Yugen Yi ; Ke Zhang ; Jun Kong ; Ming Zhang, et al.
"Multiview saliency detection based on improved multimanifold ranking", J. Electron. Imaging. 23(6), 061113 (Sep 19, 2014). ; http://dx.doi.org/10.1117/1.JEI.23.6.061113


Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging & repositioning the boxes below.

Related Book Chapters

Topic Collections

Advertisement
  • Don't have an account?
  • Subscribe to the SPIE Digital Library
  • Create a FREE account to sign up for Digital Library content alerts and gain access to institutional subscriptions remotely.
Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).
Access This Proceeding
Sign in or Create a personal account to Buy this article ($15 for members, $18 for non-members).
Access This Chapter

Access to SPIE eBooks is limited to subscribing institutions and is not available as part of a personal subscription. Print or electronic versions of individual SPIE books may be purchased via SPIE.org.