Abstract
In this work, we present a biologically inspired model for recognition of occluded patterns. The general architecture of the model is based on the two visual information processing pathways of the human visual system, i.e. the ventral and the dorsal pathways. The proposed hierarchically structured model consists of three parallel processing channels. The main channel learns invariant representations of the input patterns and is responsible for pattern recognition task. But, it is limited to process one pattern at a time. The direct channel represents the biologically based direct connection from the lower to the higher processing level in the human visual cortex. It computes rapid top-down pattern-specific cues to modulate processing in the other two channels. The spatial channel mimics the dorsal pathway of the visual cortex. It generates a combined saliency map of the input patterns and, later, segments the part of the map representing the occluded pattern. This segmentation process is based on our hypothesis that the dorsal pathway, in addition to encoding spatial properties, encodes the shape representations of the patterns as well. The lateral interaction between the main and the spatial channels at appropriate processing levels and top-down, pattern-specific modulation of the these two channels by the direct channel strengthen the locations and features representing the occluded pattern. Consequently, occluded patterns become focus of attention in the ventral channel and also the pattern selected for further processing along this channel for final recognition.
References
Aisa B, Mingus B, O’Reilly R (2008) The emergent neural modeling system. Neural Netw 21(8):1146–1152
Bajcsy R, Solina F, Gupta A (1990) Segmentation versus object representation-are they separable? In: Jain RC, Jain A (eds) Analysis and interpretation of range images. Springer series in perception engineering. Springer, New York, pp. 207–223. http://dx.doi.org/10.1007/978-1-4612-3360-2_4
Bar M (2003) A cortical mechanism for triggering top-down facilitation in visual object recognition. J Cogn Neurosci 15:600–609
Biederman I (1972) Perceiving real-world scenes. Science 177(4043):77–80
Biederman I (1987) Recognition-by-components: a theory of human image understanding. Psychol Rev 94(2):115
Borenstein E, Ullman S (2002) Class-specific, top-down segmentation. In: Heyden A, Sparr G, Nielsen M, Johansen P (eds) Computer vision—ECCV 2002. LNCS, vol. 2351. Springer, Heidelberg, pp 109–122. http://dx.doi.org/10.1007/3-540-47967-8_8
Borenstein E, Ullman S (2008) Combined top-down/bottom-up segmentation. IEEE Trans Pattern Anal Mach Intell 30(12):2109–2125
Du Buf J, Kardan M, Spann M (1990) Texture feature performance for image segmentation. Pattern Recogn 23(3):291–309
Ferrari V, Tuytelaars T, Van Gool L (2004) Simultaneous object recognition and segmentation by image exploration. Computer Vision-ECCV 2004:40–54
Kelly F, Grossberg S (2000) Neural dynamics of 3-D surface perception: figure-ground separation and lightness perception. Atten Percept Psychophys 62(8):1596–1618
Kosslyn SM (1987) Seeing and imagining in the cerebral hemispheres: a computational approach. Psychol Rev 94(2):148
Lehky SR, Sereno AB (2007) Comparison of shape encoding in primate dorsal and ventral visual pathways. J Neurophysiol 97(1):307
Leibe B, Leonardis A, Schiele B (2008) Robust object detection with interleaved categorization and segmentation. Int J Comput Vision 77(1–3):259–289
Marr D (1976) Early processing of visual information. Philos Trans R Soc Lond B Biol Sci 275(942):483–519
McClelland JL (1993) Toward a theory of information processing in graded, random, and interactive networks. In: Meyer DE, Kornblum S (eds) Attention and performance XIV: synergies in experimental psychology, artificial intelligence and cognitive neuroscience. MIT Press, Cambridge, pp 655–688
Montanari U (1971) On the optimal detection of curves in noisy pictures. Commun ACM 14(5):335–345
Mozer MC, Zemel RS, Behrmann M, Williams CKI (1992) Learning to segment images using dynamic feature binding. Neural Comput 4(5):650–665
Needham A (2001) Object recognition and object segregation in 4.5-month-old infants. J Exp Child Psychol 78(1):3–24
Neisser U (1967) Cognitive psychology. Appleton-Century-Crofts, New York
O’Reilly RC (1996) Biologically plausible error-driven learning using local activation differences: the generalized recirculation algorithm. Neural Comput 8(5):895–938
O’Reilly RC, Munakata Y (2000) Computational explorations in cognitive neuroscience: understanding the mind by simulating the brain. The MIT Press, Cambridge, MA
Palmer S, Rock I (1994) Rethinking perceptual organization: the role of uniform connectedness. Psychon Bull Rev 1(1):29–55
Peterson MA (1994) Object recognition processes can and do operate before figure-ground organization. Curr Dir Psychol Sci 3(4):105–111
Peterson MA, Gibson BS (1991) The initial identification of figure-ground relationships: contributions from shape recognition processes. Bull Psychon Soc 29(3):199–202
Peterson MA, Gibson BS (1993) Shape recognition inputs to figure-ground organization in three-dimensional grounds. Cogn Psychol 25(3):383–429
Peterson MA, Gibson BS (1994a) Must figure-ground organization precede object recognition? An assumption in peril. Psychol Sci 5(5):253
Peterson MA, Gibson BS (1994b) Object recognition contributions to figure-ground organization: operations on outlines and subjective contours. Atten Percept Psychophys 56(5):551–564
Potter MC (1975) Meaning in visual search. Science 187(4180):565–566
Prinzmetal W, Millis-Wright M (1984) Cognitive and linguistic factors affect visual feature integration. Cogn Psychol 16(3):305–340
Rao RP, Ballard DH (1999) Predictive coding in the visual cortex: a functional interpretation of some extra-classical receptive field effects. Nat Neurosci 2:79–87
Rao RP, Ballard DH (2004) Probabilistic models of attention based on iconic representations and predictive coding. In: Itti L (ed) Neurobiology of attention. Elsevier Academic Press, Amsterdam, pp 553–561
Reicher GM (1969) Perceptual recognition as a function of meaningfulness of stimulus material. J Exp Psychol 81(2):275
Rock I, Campbell B (1975) An introduction to perception. Macmillan, New York
Rubin E (1958) Figure and ground. In: Beardslee D, Wertheimer M (eds and trans) Readings in perception. Van Nostrand, Princeton, pp 35–101 (Original work published 1915)
Rumelhart DE (1989) The architecture of mind: a connectionist approach. In: Posner MI (ed) Foundations of cognitive science. MIT Press, Cambridge, pp 133–159. http://dl.acm.org/citation.cfm?id=102953.102957
Saifullah M, Kovordányi R (2011) Emergence of attention focus in a biologically-based bidirectionally-connected hierarchical network. In: Dobnikar A, Lotric U, Ster B (eds) Adaptive and natural computing algorithms. LNCS, vol 6593. Springer, Heidelberg, pp 200–209. http://dx.doi.org/10.1007/978-3-642-20282-7_21
Sereno A, Maunsell J (1987) Shape selectivity in primate lateral intraparietal cortex. J Exp Psychol Hum Percept Perform 12:388–391
Spratling MW (2008) Reconciling predictive coding and biased competition models of cortical function. Front Comput Neurosci 2:4
Thorpe S, Fize D, Marlot C et al (1996) Speed of processing in the human visual system. Nature 381(6582):520–522
Tu Z, Chen X, Yuille AL, Zhu SC (2005) Image parsing: unifying segmentation, detection, and recognition. Int J Comput Vision 63(2):113–140
Ullman S (1989) Aligning pictorial descriptions: an approach to object recognition. Cognition 32(3):193–254
Vecera SP, Farah MJ (1997) Is visual image segmentation a bottom-up or an interactive process? Atten Percept Psychophys 59(8):1280–1296
Vecera SP, O’Reilly RC (1998) Figure-ground organization and object recognition processes: an interactive account. J Exp Psychol Hum Percept Perform 24(2):441
Weeks AR, Hague GE (1997) Color segmentation in the HSI color space using the K-means algorithm. Proc SPIE 3026:143–154
Wertheimer M (1958) Principles of perceptual organization. In: Beardslee D, Wertheimer M (eds and trans) Readings in perception. Van Nostrand, Princeton, pp 115–135 (Original work published in 1923)
Wheeler DD (1970) Processes in word recognition. Cogn Psychol 1(1):59–85
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Saifullah, M., Balkenius, C. & Jönsson, A. A biologically based model for recognition of 2-D occluded patterns. Cogn Process 15, 13–28 (2014). https://doi.org/10.1007/s10339-013-0578-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10339-013-0578-9