Abstract
In this paper we present a parallel artificial cortical network inspired by the Human visual system, which enhances the salient contours of an image. The network consists of independent processing elements, which are organized into hypercolumns. They process concurrently the distinct orientations of all the edges of the image. These processing elements are a new set of orientation kernels appropriate for the discrete lattice of the hypercolumns. The Gestalt laws of proximity and continuity that describe the process of saliency extraction in the human brain are encoded by means of weights. These weights interconnect the kernels according to a novel connection pattern based on co-exponentiality. The output of every kernel is modulated by the outputs of its neighboring kernels, according to a new affinity function. This function takes into account the degree of difference between the facilitation of the two lobes of the kernel. Saliency enhancement results as a consequence of the local interactions between the kernels. The network was tested on real and synthetic images and displays promising results for both. Comparisons with other methods with the same scope, demonstrate that the proposed method performs adequately. Furthermore it exhibits O(N) complexity with execution times that have never been reported by any other method so far, even though it is executed on a conventional PC
Similar content being viewed by others
References
Alter TD, Basri R (1998) Extracting salient curves from images: an analysis of the salience network. Int J Comput Vis 27:51–69
Ben-Shahar O, Huggins PS, Izo T, Zucker SW (2003) Cortical connections and early visual function: intra- and inter-columnar processing. J Physiol Paris 97:191–208
Braun J (1999) On the detection of salient contours. Spat Vis 12(2):211–225
Choe Y, Miikkulainen R (2004) Contour integration and segmentation with self-organized lateral connections. Biol Cybern 90:75–88
Field DJ, Hayes A (2004) Contour integration and the lateral connections of V1 neurons. In: The visual neurosciences, vol 2. MIT Press, Cambridge pp 1069–1079
Field DJ, Hayes A, Hess RF (1993) Contour integration by the human visual system: evidence for a local “association field”. Vis Res 33:173–193
Fitzpatrick D (1996) The functional-organization of local circuits in visual-cortex – insights from the study of tree shrew striate cortex. Cereb Cortex 6:329–341
Freeman WT, Adelson EH (1991) The design and use of steerable filters. IEEE Trans Pattern Anal Mach Intell 13:891–906
Geisler WS, Perry JS, Super BJ, Gallogly DP (2001) Edge co-occurrence in natural images predicts contour grouping performance. Vis Res 41:711–724
Gilbert CD, Das A, Ito M, Kapadia M, Westheimer G (1996) Spatial integration and cortical dynamics. Proc Nat Acad Sci USA 93:615–622
Grossberg S (1994) 3-d vision and figure-ground separation by visual cortex. Percep Psychophys 55:48–121
Grossberg S (2004) Visual boundaries and surfaces. In: The visual neurosciences, vol 2. MIT Press, Cambridge pp 1624–1639
Grossberg S, Mingolla E (1985) Neural dynamics of perceptual grouping: textures, boundaries, and emergent segmentations. Percept Psychophys 38:141–171
Grossberg S, Mingolla E, Williamson J (1995) Synthetic aperture radar processing by a multiple scale neural system for boundary and surface representation. Neural Netw 8:1005–1028
Herault L, Horaud R (1993) Figure-ground discrimination: a combinatorial optimisation approach. IEEE Trans Pattern Analy Mach Intell 15:899–914
Hess RF, Hayes A, Field DJ (2003) Contour integration and cortical processing. J Physiol Paris 97:105–119
Hubel DH, Wiesel TN (1965) Receptive fields and functional architecture in nonstriate areas (188 and 19) of the cat. J Neurophysiol 28:229–289
Hubel DH, Wiesel TN (1968) Receptive fields, binocular interaction and functional architecture of monkey striate cortex. J Physiol 195:215–243
Kapadia MK, Ito M, Gilbert CD, Westheimer G (1995) Improvement in visual sensitivity by changes in local context: parallel studies in human observers and in V1 of alert monkeys. Neuron 15:843–856
Kapadia MK, Westheimer G, Gilbert CD (2000) Spatial distribution of contextual interactions in primary visual cortex and in visual perception. F. Neurophysiology 84:2048–2062
Kovács I, Julesz B (1993) A closed curve is much more than an incomplete one: effect of closure in figure-ground segmentation. Proc Nat Acad Sci 90:7495–7497
Kovács I, Julesz B (1994) Perceptual sensitivity maps within globally defined visual shapes. Nature 370:644–646
Lance W, Karvel T (2000) A comparison of measures for detecting natural shapes in cluttered backgrounds. Int J Comput Vis 34:81–96
Li Z (1998) A neural model of contour integration in the primary visual cortex. Neural Comput 10:903–940
Mahamud S, Williamns LR, Thornber KK, Xu K (2003) Segmentation of multiple salient closed contours from real images. IEEE Trans Pattern Anal Mach Intell 25:433–444
Mundhenk TN, Itti L (2002) A model of contour integration in early visual cortex. In: Proceedings of 2nd international workshop on biologically motivated computer vision, pp 80–89
Mundhenk TN, Itti L (2003) CINNIC, a new computational algorithm for the modeling of early visual contour integration in humans. Neurocomputing 52–54:599–604
Mundhenk TN, Itti L (2005) Computational modelling and exploration of contour integration for visual saliency. Biol Cybern 93:188–212
Newsome WT, Britten KH, Movshon JA (1989) Neuronal correlates of a perceptual decision. Nature 341:52–54
Parent P, Zucker SW (1989) Trace inference, curvature consistency, and curve detection. IEEE Trans Pattern Anal Mach Intell 11:823–839
Perona P (1992) Steerable-scalable kernels for edge detection and junction analysis. In: Proceedings of 2nd European conference computer vision, pp 3–18
Perona P (1995) Deformable kernels for early vision. IEEE Trans Pattern Anal Mach Intell 17:488–499
Pettet MW, McKee SP, Grzywacz NM (1998) Constrains on long-range interactions mediating contour-detection. Vis Res 38:865–879
Polat UK, Mizobe K, Pettet MW, Kasamatsu T, Norcia AM (1998) Collinear stimuli regulate visual responses depending on cell’s contrast threshold. Nature 391:580–584
Rockland KS, Lund JS (1982) Widespread periodic intrinsic connections in the tree shrew visual cortex. Sci 215:532–534
Rockland KS, Lund JS (1983) Intrinsic laminar lattice connections in primate visual cortex. J Comp Neurol 216:303–318
Ross WD, Mingolla E (1998) Recent progress in modeling neural mechanisms of form and color vision. Image Vis Comput 16:447–472
Shashua A, Ullman S (1988) Structural saliency: the detection of globally salient structures using a locally connected network. In: Proceeding of 2nd ICCV, pp 321–327
Sincich LC, Blasdel GG (2001) Oriented axon projections in primary visual cortex of the monkey. J Neurosci 21:4416–4426
Singer W, Gray CM (1995) Visual feature integration and the temporal correlation hypothesis. Annu Rev Neurosci 18:555–586
Soundararajan P, Sarkar S (2003) An in-depth study of graph partitioning measures for perceptual organization. IEEE Trans Pattern Anal Mach Intell 25:642–660
Wang S, Kubota T, Siskind JM, Wang J (2005) Salient closed boundary extraction with ratio contour. IEEE Trans Pattern Anal Mach Intell 27:546–560
Watamaniuk SN, Sekuler R (1992) Temporal and spatial integration in dynamic random-dot stimuli. Vis Res 32:2341–2347
Yen SC, Finkel LH (1997) Salient contour extraction by temporal binding in a cortically-based network. Adv Neural Inf Process Sys 10:915–921
Yen SC, Finkel LH (1998) Extraction of perceptually salient contours by striate cortical networks. Vis Res 38:719–741
Yen SC, Menschik ED, Finkel LH (1998) Cortical synchronization and perceptual salience. In: Computational neuroscience: trends in research, Plenum Press, New York, pp 125–130
Young RA (1987) The Gaussian derivative model for spatial vision: I. retinal mechanisms. Spat Vis 2:273–293
Young RA, Lesperance RM (1993) A physiological model of motion analysis for machine vision. Proc SPIE Int Soc Opt Eng 1913:48–123
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Vonikakis, V., Gasteratos, A. & Andreadis, I. Enhancement of Perceptually Salient Contours using a Parallel Artificial Cortical Network. Biol Cybern 94, 192–214 (2006). https://doi.org/10.1007/s00422-005-0040-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00422-005-0040-x