12 April 2016 Spectral saliency via automatic adaptive amplitude spectrum analysis
Author Affiliations +
J. of Electronic Imaging, 25(2), 023020 (2016). doi:10.1117/1.JEI.25.2.023020
Suppressing nonsalient patterns by smoothing the amplitude spectrum at an appropriate scale has been shown to effectively detect the visual saliency in the frequency domain. Different filter scales are required for different types of salient objects. We observe that the optimal scale for smoothing amplitude spectrum shares a specific relation with the size of the salient region. Based on this observation and the bottom-up saliency detection characterized by spectrum scale-space analysis for natural images, we propose to detect visual saliency, especially with salient objects of different sizes and locations via automatic adaptive amplitude spectrum analysis. We not only provide a new criterion for automatic optimal scale selection but also reserve the saliency maps corresponding to different salient objects with meaningful saliency information by adaptive weighted combination. The performance of quantitative and qualitative comparisons is evaluated by three different kinds of metrics on the four most widely used datasets and one up-to-date large-scale dataset. The experimental results validate that our method outperforms the existing state-of-the-art saliency models for predicting human eye fixations in terms of accuracy and robustness.
© 2016 SPIE and IS&T
Xiaodong Wang, Jialun Dai, Yafei Zhu, Haiyong Zheng, Xiaoyan Qiao, "Spectral saliency via automatic adaptive amplitude spectrum analysis," Journal of Electronic Imaging 25(2), 023020 (12 April 2016). https://doi.org/10.1117/1.JEI.25.2.023020

Eye models

Spectrum analysis



Data modeling

Visual process modeling

Fourier transforms

Back to Top