Bottom–up attention: pulsed PCA transform and pulsed cosine transform
- 18 May 2011
- journal article
- research article
- Published by Springer Nature in Cognitive Neurodynamics
- Vol. 5 (4) , 321-332
Abstract
In this paper we propose a computational model of bottom–up visual attention based on a pulsed principal component analysis (PCA) transform, which simply exploits the signs of the PCA coefficients to generate spatial and motional saliency. We further extend the pulsed PCA transform to a pulsed cosine transform that is not only data-independent but also very fast in computation. The proposed model has the following biological plausibilities. First, the PCA projection vectors in the model can be obtained by using the Hebbian rule in neural networks. Second, the outputs of the pulsed PCA transform, which are inherently binary, simulate the neuronal pulses in the human brain. Third, like many Fourier transform-based approaches, our model also accomplishes the cortical center-surround suppression in frequency domain. Experimental results on psychophysical patterns and natural images show that the proposed model is more effective in saliency detection and predict human eye fixations better than the state-of-the-art attention models.Keywords
This publication has 43 references indexed in Scilit:
- Neurofunctional model of large-scale correlates of selective attention governed by stimulus-noveltyCognitive Neurodynamics, 2011
- Visual saliency: a biologically plausible contourlet-like frequency domain approachCognitive Neurodynamics, 2010
- A neural network model of attention-modulated neurodynamicsCognitive Neurodynamics, 2007
- Optimal approximation of uniformly rotated images: relationship between Karhunen-Loeve expansion and discrete cosine transformIEEE Transactions on Image Processing, 1998
- Attention-Based Motion PerceptionScience, 1992
- Conjunction search revisited.Journal of Experimental Psychology: Human Perception and Performance, 1990
- Relations between the statistics of natural images and the response properties of cortical cellsJournal of the Optical Society of America A, 1987
- Simplified neuron model as a principal component analyzerJournal of Mathematical Biology, 1982
- Relation between the Karhunen Loève and cosine transformsIEE Proceedings F Communications, Radar and Signal Processing, 1981
- Comparison of the cosine and Fourier transforms of Markov-1 signalsIEEE Transactions on Acoustics, Speech, and Signal Processing, 1976