Saliency Detection using Superpixel Belief Propagation

Soo-Chang Pei, Department of Electrical Engineering, National Taiwan University, Taipei.
Wen-Wen Chang, Graduate Institute of Communication Engineering, National Taiwan University, Taipei
Chih-Tsung Shen, Graduate Institute of Networking and Multimedia, National Taiwan University, Taipei

We propose a method to detect saliency from a single image
using feature extraction and superpixel belief propagation.
We observe that the previous works are hard to deal with
the intrinsic material discontinuity and non-homogeneous
color distribution within an object or a region. Motivated
by this observation, we bring the belief propagation into the
saliency detection. First, we separate the image into middlelevel
superpixels and also extract the low-level feature within
each superpixel. Then, we build up a Markov-Random-Field
(MRF) on the middle-level super-pixels and adopt propagation
technique to optimize the superpixel saliency. Afterward,
we refine this middle-level solution to per-pixel saliency map.
Experimental results demonstrate that our proposed method
is promising as compared to the state-of-the-art methods in
both MSRA-1000 and SED datasets.

[Image Data]

Experimental Results on MSRA-1000 Dataset( Input, Superpixels, PR2014, ICCV2013, Ours)

Experimental Results on SED Dataset( Input, Superpixels, CA, RC, Ours)