Processing real-world imagery with FACADE-based approaches

Abstract

This paper considers the processing of realworld imagery in the so-called Form-And-Color-And-DEpth (FACADE) framework, which features some superior mechanisms of the human vision system (HVS). FACADE framework was originally proposed by Grossberg et al. as an integrative model of the HVS to illustrate the possible procedures for visual perception of shape (the boundary contour), surface (luminance and color), and binocular depth. As a simplified, reasonable and mathematically full-fledged approach to the HVS, we saw FACADE as a promising infrastructure through which to construct a powerful image processing engine. However, in our attempts to use the approach in its original modality, to deal with real-world imagery, we found it to be inefficient and non-robust.

After re-introducing the model hierarchy and illustrating the involved cell dynamics of the FACADE framework, this paper reveals the crucial issues that lead to the deficiency and accordingly present our substitutive solutions by incorporating the mechanisms of anisotropic spatial- and diffusive orientational-competition to make the HVS-featured model efficient and robust. A computer system based on the improved FACADE engine has been implemented and tested not only with illustrative images to highlight the model characteristics, but also with some real-world imagery in both monocular and binocular situations, thereby demonstrating the ability of the FACADE-based image processing approach featuring the HVS.

Keywords

visual perception / human vision system (HVS) / Form-And-Color-And-DEpth (FACADE) framework / real-world imagery

References

[1] Gabor D. Theory of communication. Journal of the Institution of Electrical Engineers, 1946, 93: 429-459

[2] Jones J P, Palmer L A. An evaluation of the twodimensional Gabor filter model of simple receptive fields in cat striate cortex. Journal of Neurophysiology, 1987, 58(6): 1233-1258

[3] Riesenhuber M, Poggio T. Hierarchical models of object recognition in cortex. Nature Neuroscience, 1999, 2(11): 1019-1025

[4] Serre T, Riesenhuber M. Realistic modelling of simple and complex cell tuning in the HMAX model, and implications for invariant object recognition in cortex. Technical Report CBCLPaper 239/AIMemo 2004-017. Cambridge: Massachusetts Institute of Technology, 2004

[5] Serre T, Kouh M, Cadieu C, Knoblich U, Kreiman G, Poggio T. A theory of object recognition: computations and circuits in the feed-forward path of the ventral stream in primate visual cortex. Technical Report AI Memo 2005-036/CBCL Memo 259. Cambridge: Massachusetts Institute of Technology, 2005

[6] Serre T, Wolf L, Poggio T. Object recognition with features inspired by visual cortex. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2005, 2: 994-1000

[7] Wallis G, Rolls E T. A model of invariant object recognition in the visual system. Progress in Neurobiology, 1997, 51(2): 167-194

[8] Deco G, Rolls E T. A neurodynamical cortical model of visual attention and invariant object recognition. Vision Research, 2004, 44(6): 621-642

[9] Rolls E T, Stringer S M. Invariant visual object recognition: a model, with lighting invariance. Journal of Physiology, 2006, 100(1-3): 43-62

[10] Stringer S M, Perry G, Rolls E T, Proske J H. Learning invariant object recognition in the visual system with continuous transformations. Biological Cybernetics, 2006, 94(2): 128-142

[11] Grossberg S. 3-D vision and figure-ground separation by visual cortex. Perception and Psychophysics, 1994, 55(1): 48-120

[12] Grossberg S. Linking the laminar circuits of visual cortex to visual perception: development, grouping, and attention. Neuroscience and Biobehavioral Reviews, 2001, 25(6): 513-526

[13] Cao Y, Grossberg S. A laminar cortical model of stereopsis and 3D surface perception: closure and da Vinci stereopsis. Spatial Vision, 2005, 18(5): 515-578

[14] Huang T R, Grossberg S. Cortical dynamics of contextually cued attentive visual learning and search: spatial and object evidence accumulation. Psychological Review, 2010, 117(4): 1080-1112

[15] Serre T, Wolf L, Bileschi S, Riesenhuber M, Poggio T. Robust object recognition with cortex-like mechanisms. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(3): 411-426

[16] Rolls E T, Milward T. A model of invariant object recognition in the visual system: learning rules, activation functions, lateral inhibition, and information-based performance measures. Neural Computation, 2000, 12(11): 2547-2572

[17] Grossberg S. The quantized geometry of visual space: the coherent computation of depth, form, and lightness. The Behavioral and Brain Sciences, 1983, 6: 625-692

[18] Grossberg S. Outline of a theory of brightness, color, and form perception. In: Degreef E, van Buggenhaut J, eds. Trends in Mathematical Psychology. Amsterdam: North-Holland, 1984: 59-85

[19] Cohen M A, Grossberg S. Neural dynamics of brightness perception: features, boundaries, diffusion, and resonance. Perception and Psychophysics, 1984, 36(5): 428-456

[20] Fazl A, Grossberg S, Mingolla E. View-invariant object category learning, recognition, and search: how spatial and object attention are coordinated using surface-based attentional shrouds. Cognitive Psychology, 2009, 58(1): 1-48

[21] Grossberg S, Mcloughlin N. Cortical dynamics of 3-D surface perception: binocular and half-occluded scenic images. Neural Networks, 1997, 10(9): 1583-1605

[22] Grossberg S. Cortical dynamics of three-dimensional figureground perception of two-dimensional pictures. Psychological Review, 1997, 104(3): 618-658

[23] Raizada R, Grossberg S. Towards a theory of the laminar architecture of cerebral cortex: computational clues from the visual system. Cerebral Cortex, 2003, 13(1): 100-113

[24] Grossberg S. How does the cerebral cortex work? Development, learning, attention, and 3D vision by laminar circuits of visual cortex. Behavioral and Cognitive Neuroscience Reviews, 2003, 2(1): 47-76

[25] Grossberg S, Howe P D I. A laminar cortical model of stereopsis and three-dimensional surface perception. Vision Research, 2003, 43(7): 801-829

[26] Grossberg S, Swaminathan G. A laminar cortical model for 3D perception of slanted and curved surfaces and of 2D images: development, attention and bistability. Vision Research, 2004, 44(11): 1147-1187

[27] Grossberg S, Yazdanbakhsh A. Laminar cortical dynamics of 3D surface perception: stratification, transparency, and neon color spreading. Vision Research, 2005, 45(13): 1725-1743

[28] Grossberg S, Yazdanbakhsh A, Cao Y, Swaminathan G. How does binocular rivalry emerge from cortical mechanisms of 3-D vision? Vision Research, 2008, 48(21): 2232-2250

[29] Grossberg S, Kuhlmann L, Mingolla E. A neural model of 3D shape-from-texture: multiple-scale filtering, boundary grouping, and surface filling-in. Vision Research, 2007, 47(5): 634-672

[30] Grossberg S, Mingolla E, Williamson J. Synthetic aperture radar processing by a multiple scale neural system for boundary and surface representation. Neural Networks, 1995, 8(7-8): 1005-1028

[31] Mingolla E, Ross W, Grossberg S. A neural network for enhancing boundaries and surfaces in synthetic aperture radar images. Neural Networks, 1999, 12(3): 499-511

[32] Peng X H, Zhou Z T, Wang Z Z. Acquiring disparity distribution from stereo images with monocular cues based on cell cooperation and competition. Acta Electronica Sinica, 2000, 28(8): 1-4 (in Chinese)

[33] Song B Q, Zhou Z T, Hu D W, Wang Z Z. A new computational model of biological vision for stereopsis. Lecture Notes in Computer Science, 2004, 3174: 525-530

[34] Chen Y. Research on attention in visual neural system. Dissertation for Master’s Degree. Changsha: National University of Defense Technology, 2009 (in Chinese)

RIGHTS & PERMISSIONS

2014 Higher Education Press and Springer-Verlag Berlin Heidelberg