Translator Disclaimer
27 October 2013 Saliency detection based on manifold learning
Author Affiliations +
Proceedings Volume 8919, MIPPR 2013: Pattern Recognition and Computer Vision; 891906 (2013)
Event: Eighth International Symposium on Multispectral Image Processing and Pattern Recognition, 2013, Wuhan, China
Visual saliency has recently attracted lots of research interest in the computer vision community. In this paper, we propose a novel computational model for bottom-up saliency detection based on manifold learning. A typical graphbased manifold learning algorithm, namely the diffusion map, is adopted for establishing our saliency model. In the proposed method, firstly, a graph is constructed using low-level image features. Then, the diffusion map algorithm is performed to learn the diffusion distances, which are utilized to derive the saliency measure. Compared to existing saliency models, our method has the advantage of being able to capture the intrinsic nonlinear structures in the original feature space. Moreover, due to the inherent characteristics of the diffusion map algorithm, our method can deal with the multi-scale issue effectively, which is crucial to any saliency model. Experimental results on publicly available data demonstrate that our method outperforms the state-of-the-art saliency models, both qualitatively and quantitatively.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Zhi Yang, DeHua Li, Jie Wang, and Xuan Li "Saliency detection based on manifold learning", Proc. SPIE 8919, MIPPR 2013: Pattern Recognition and Computer Vision, 891906 (27 October 2013);

Back to Top