A Model of Saliency-Based Visual Attention for Rapid Scene Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
2006 Special Issue: Modeling attention to salient proto-objects
Neural Networks
Frequency spectrum modification: a new model for visual saliency detection
ISNN'10 Proceedings of the 7th international conference on Advances in Neural Networks - Volume Part II
Hi-index | 0.00 |
In this paper, a new approach for visual attention selection called Amplitude Modulation Fourier Transform is proposed, which is based on two up-to-date works: Spectral Residual model (SR) and Phase Fourier Transform (PFT). We try to explore the nature of AMFT by analyzing its intrinsic mechanism and summarizing its merits and disadvantages. We also propose a new attention selection method called Multi-Channel and Multi-Scale Amplitude Modulation (MCMSAM). For proving the advantage of MCMSAM, we design several simulations to compare our model with Spectral Residual Model, Phase Fourier Transform and traditional Saliency ToolBox.