Selective background prior for saliency detection

Wenjing Cai; Luping Wang; Luping Zhang; Zengguo Yang

doi:10.1117/12.2245117

29 August 2016 Selective background prior for saliency detection

Wenjing Cai, Luping Wang, Luping Zhang, Zengguo Yang

Proceedings Volume 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016); 100335W (2016) https://doi.org/10.1117/12.2245117
Event: Eighth International Conference on Digital Image Processing (ICDIP 2016), 2016, Chengu, China

Abstract

There is an emerging interest on using background prior in saliency detection. However, these methods fail to locate the position of background accurately. In this paper, a novel saliency detection approach which chooses more precise background regions is proposed. First, in order to pick out the real background from the boundary of the image, the background probability is measured by boundary ratio. Next, according to the geodesic distance to background regions, the edge saliency map and color saliency map are calculated in the Edge and RGB-LAB-XY feature space, respectively. Furthermore, combining the saliency cues by using an energy function, the final saliency map is generated. The proposed model has the following two advantages: the erroneous background removal guarantees the accuracy of background and the detection of objects located at the boundary of image; the energy minimization enable the detected objects to be more complete and edges of targets to be clearer. Comprehensive experiments on two benchmark datasets demonstrate the superiority of the proposed algorithm over the 5 state-of-the-art methods.

Citation Download Citation

Wenjing Cai, Luping Wang, Luping Zhang, and Zengguo Yang "Selective background prior for saliency detection", Proc. SPIE 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016), 100335W (29 August 2016); https://doi.org/10.1117/12.2245117

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available