Author:
Wang Jun,Wu Zemin,Tian Chang,Hu Lei
Abstract
This paper proposes a bottom-up saliency detection algorithm based on multi-dictionary sparse recovery. Firstly, the SLIC algorithm is used to segment the image into superpixels in multilevel and atoms with a high background possibility are selected from the boundary superpixels to construct the multidictionary. Secondly, sparse recovery of the entire image is achieved using multi-dictionary to get subsaliency maps from the perspective of sparse recovery errors. The final saliency map is generated in a weighted fusion manner. Experimental results on three public datasets demonstrate the effectiveness of our model.
Reference16 articles.
1. Li Y,
Zhou Y,
Xu L, et al. Incremental sparse saliency detection.
IEEE International Conference on Image Processing. IEEE Press,
2009: 3057-3060.
2. Han B.,
Zhu H., and Ding Y.D.,
2011.
Bottom-up Saliency based on weighted sparse coding residual. In Proceeding of ACM International conference on multimedia,
2011: 1117-1120.
3. Li X.,
Lu, Zhang H.,
Ruan X. et al,
2013.
Saliency detection via dense and sparse reconstruction. In IEEE International Conference on Computer Vision.
4. Saliency detection via a unified generative and discriminative model
5. SLIC Superpixels Compared to State-of-the-Art Superpixel Methods