A computational coding model for saliency detection in primary visual cortex

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.

[1]  Iain D. Gilchrist,et al.  Visual correlates of fixation selection: effects of scale and time , 2005, Vision Research.

[2]  T. Poggio.  THE COMPUTATIONAL MAGIC OF THE VENTRAL STREAM: TOWARDS A THEORY , 2011 .

[3]  David J. Field,et al.  Emergence of simple-cell receptive field properties by learning a sparse code for natural images , 1996, Nature.

[4]  Robert B. Fisher,et al.  Object-based visual attention for computer vision , 2003, Artif. Intell..

[5]  C. Gilbert,et al.  Spatial distribution of contextual interactions in primary visual cortex and in visual perception. , 2000, Journal of neurophysiology.

[6]  Christof Koch,et al.  A Model of Saliency-Based Visual Attention for Rapid Scene Analysis , 2009 .

[7]  I. Ohzawa,et al.  Length and width tuning of neurons in the cat's primary visual cortex. , 1994, Journal of neurophysiology.

[8]  Nicolai Petkov,et al.  Contour detection based on nonclassical receptive field inhibition , 2003, IEEE Trans. Image Process..

[9]  Nanning Zheng,et al.  Learning to Detect a Salient Object , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Stephen E. Palmer,et al.  Modern Theories of Gestalt Perception , 1990 .

[11]  Aapo Hyvärinen,et al.  A two-layer sparse coding model learns simple and complex cell receptive fields and topography from natural images , 2001, Vision Research.

[12]  K Suder,et al.  The Control of Low-Level Information Flow in the Visual System , 2000, Reviews in the neurosciences.

[13]  John H. R. Maunsell,et al.  Attention to both space and feature modulates neuronal responses in macaque area V4. , 2000, Journal of neurophysiology.

[14]  Li Zhaoping,et al.  Theoretical understanding of the early visual processes by data compression and data selection , 2006, Network.

[15]  Nuno Vasconcelos,et al.  On the plausibility of the discriminant center-surround hypothesis for visual saliency. , 2008, Journal of vision.

[16]  U. Polat,et al.  Collinear stimuli regulate visual responses depending on cell's contrast threshold , 1998, Nature.

[17]  Patrick Le Callet,et al.  A coherent computational approach to model bottom-up visual attention , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Aapo Hyvärinen,et al.  Emergence of Phase- and Shift-Invariant Features by Decomposition of Natural Images into Independent Feature Subspaces , 2000, Neural Computation.

[19]  A. Treisman,et al.  A feature-integration theory of attention , 1980, Cognitive Psychology.

[20]  Edmund T. Rolls,et al.  Invariant recognition of feature combinations in the visual system , 2002, Biological Cybernetics.

[21]  Zhe Wang,et al.  A biologically inspired system for fast handwritten digit recognition , 2011, 2011 18th IEEE International Conference on Image Processing.

[22]  Christof Koch,et al.  Comparison of feature combination strategies for saliency-based visual attention systems , 1999, Electronic Imaging.

[23]  E. Rolls,et al.  A Neurodynamical cortical model of visual attention and invariant object recognition , 2004, Vision Research.

[24]  S Ullman,et al.  Shifts in selective visual attention: towards the underlying neural circuitry. , 1985, Human neurobiology.

[25]  T. Poggio,et al.  What and where: A Bayesian inference theory of attention , 2010, Vision Research.

[26]  C. Gilbert,et al.  Generation of end-inhibition in the visual cortex via interlaminar connections , 1986, Nature.

[27]  C. Koch,et al.  Computational modelling of visual attention , 2001, Nature Reviews Neuroscience.

[28]  Jeroen J. A. van Boxtel,et al.  Retinotopic and non-retinotopic stimulus encoding in binocular rivalry and the involvement of feedback. , 2008, Journal of vision.

[29]  Junchi Yan,et al.  Visual Saliency Detection via Sparsity Pursuit , 2010, IEEE Signal Processing Letters.

[30]  Elie Bienenstock,et al.  Neural Networks and the Bias/Variance Dilemma , 1992, Neural Computation.

[31]  Laurenz Wiskott,et al.  How Does Our Visual System Achieve Shift and Size Invariance , 2004 .

[32]  S. Palmer.  Vision Science : Photons to Phenomenology , 1999 .

[33]  D. Sagi,et al.  Isolating Excitatory and Inhibitory Nonlinear Spatial Interactions Involved in Contrast Detection * * Part of this paper was presented at the 17th ECVP conference, Eindhoven, The Netherlands (September 1994). , 1996, Vision Research.

[34]  Thomas Serre,et al.  Attentive processing improves object recognition , 2009 .

[35]  John K. Tsotsos,et al.  Saliency Based on Information Maximization , 2005, NIPS.

[36]  John H. R. Maunsell,et al.  Feature-based attention in visual cortex , 2006, Trends in Neurosciences.

[37]  D. V. van Essen,et al.  Response modulation by texture surround in primate area V1: Correlates of “popout” under anesthesia , 1999, Visual Neuroscience.