Abstract
This study researches the coding model adaptive for information processing of the bottom-up attention mechanism. We constructed a coding model satisfying the neurobiological constraints of the primary visual cortex. By quantitatively changing the coding constraints, we carried out experiments on images used in cognitive psychology and natural image sets to compare the effects on the saliency detection performance. The experimental results statistically demonstrated that the encoding of invariant features and representation of overcomplete bases is advantageous to the bottom-up attention mechanism.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Treisman A M, Gelade G. A feature-integration theory of attention. Cogn Psychol, 1980, 12: 97–136
Itti L, Koch C. Computational modeling of visual attention. Nat Rev Neurosci, 2001, 2: 194–203
Itti L, Koch C, Niebur E. A model of saliency-based visual attention for rapid scene analysis. IEEE Trans Patt Anal Mach Intell, 1998, 20: 1254–1259
Gustavo D, Edmund T R. A Neurodynamical cortical model of visual attention and invariant object recognition. Vision Res, 2004, 44: 621–642
Yan J, Zhu M, Liu H, et al. Visual Saliency detection via sparsity pursuit. IEEE Signal Proc Lett, 2010, 17: 739–742
Zhao** L. Theoretical understanding of the early visual processes by data compression and data selection. Network Comp Neural, 2006, 17: 301–334
Maunsell J H R, Treue S. Feature-based attention in visual cortex. Trends Neurosci, 2006, 29: 317–322
Suder K, Worgotter F. The control of low-level information flow in the visual system. Rev Neurosci, 2000, 11: 127–146
Koch C, Ullman S. Shifts in selective visual attention: Towards the underlying neural circuitry. Human Neurobiol, 1985, 4: 219–227
Meur O L, Callet P L, Barba D, et al. A coherent computational approach to model the bottom-up visual attention. IEEE Trans Patt Anal Mach Intell, 2006, 28: 802–817
Hyvarinen A, Hoyer P. A two-layer sparse coding model learns simple and complex cell receptive fields and topography from natural images. Vision Res, 2001, 41: 2413–2423
Wiskott L. How Does Our Visual System Achieve Shift and Size Invariance? Chapter 16 in 23 Problems in Systems Neuroscience. New York: Oxford University Press, 2006
Gao D, Mahadevan V, Vasconcelos N. On the plausibility of the discriminant center-surround hypothesis for visual saliency. J Vision, 2008, 8: 1–18
Grigorescu C, Petkov N, Westenberg M A. Contour detection based on nonclassical receptive field inhibition. IEEE Trans Image Process, 2003, 12: 729–739
Chikkerur S, Serre T, Tan C, et al. What and where: A Bayesian inference theory of attention. Vision Res, 2010, 50: 2233–2247
Chikkerur S, Serre T, Poggio T. Attentive processing improves object recognition. Technical Report. Cambridge, MA: Massachusetts Institute of Technology, 2009
Liu T, Yuan Z, Sun J, et al. Learning to detect a salient object. IEEE Trans Patt Anal Mach Intell, 2011, 33: 353–367
Palmer S E. Modern Theories of Gestalt Perception. Understanding Vision. New York: Blackwell, 1992
Olshausen B A, Field D J. Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature, 1996, 381: 607–609
Hyvarinen A, Hoyer P. Emergence of phase-and shift-invariant features by decomposition of natural images into independent feature subspaces. Neural Comput, 2000, 12: 1705–1720
Wang Z, Huang Y, Luo S, et al. A Biologically Inspired System for Fast Handwritten Digit Recognition. In: Benoit M, Peter S, eds. Proceedings of the 18th IEEE International Conference on Image Processing, Sept. 11–14, Brussels, Belgium, 2011
Elliffe M C M, Rolls E T, Stringer S M. Invariant recognition of feature combinations in the visual system. Biol Cybern, 2002, 86: 59–71
Nothdurft H C, Gallant J L, van Essen D C. Response modulation by texture surround in primate area V1: Correlates of “popout” under anesthesia. Vision Neurosci, 1999, 16: 15–34
Zenger B, Sagi D. Isolating excitatory and inhibitory nonlinear spatial interactions involved in contrast detection. Vision Res, 1996, 36: 2497–2513
Itti L, Koch C. A comparison of feature combination strategies for saliency-based visual attention systems. SPIE Human Vision Electron Imag IV, 1999, 3644: 373–382
McAdams C J, Maunsell J H R. Attention to Both Space and Feature Modulates Neuronal Responses in Macaque Area V4. J Neurophysiol, 2000, 83: 1751–1755
Bolz J, Gilbert C D. Generation of end-inhibition in the visual cortex via interlaminar connections. Nature, 1986, 320: 362–365
Palmer S E. Vision Science-Photons to Phenomenology. Cambridge, MA: MIT Press, 1999
Kapadia M K, Westheimer G, Gilbert C D. Spatial distribution of contextual interactions in primary visual cortex and in visual perception. J Neurophysiol, 2000, 84, 2048–2062
Polat U, Mizobe K, Pettet M W, et al. Collinear stimuli regulate visual responses depending on cell’s contrast threshold. Nature, 1998, 391: 580–584
Bruce N, Tsotsos J. Saliency based on information maximization. Adv Neural Infor Process Syst, 2005, 18: 155–162
Tatler B, Baddele R, Gilchrist, I. Visual correlates of fixation selection: Effects of scale and time. Vision Res, 2005, 14: 643–659
DeAngelis G C, Freeman R D, Ohzawa I. Length and width tuning of neurons in the cat’s primary visual cortex. J Neurophisiol, 1994, 71: 347–374
Sun Y, Fisher R. Object-based visual attention for computer vision. Artif Intell, 2003, 146: 77–123
Geman S, Bienenstock E, Doursat R. Neural networks and the bias/ variance dilemma. Neural comput, 1992, 4: 1–58
Poggio T. The Computational magic of the ventral stream: Towards a theory. Nat Preced, 2011, 10: 19–59
Author information
Authors and Affiliations
Corresponding author
Additional information
This article is published with open access at Springerlink.com
Rights and permissions
This article is published under an open access license. Please check the 'Copyright Information' section either on this page or in the PDF for details of this license and what re-use is permitted. If your intended use exceeds what is permitted by the license or if you are unable to locate the licence and re-use information, please contact the Rights and Permissions team.
About this article
Cite this article
Zou, Q., Wang, Z., Luo, S. et al. A computational coding model for saliency detection in primary visual cortex. Chin. Sci. Bull. 57, 3943–3952 (2012). https://doi.org/10.1007/s11434-012-5402-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11434-012-5402-x