Abstract
The lure of hierarchies is almost irresistable. They provide elegantly simple representations that organize data for efficient search, or processors for communication. Since many current computer vision systems are focused on recognition, it is perhaps not surprising that they are also organized hierarchically. Although some success in object recognition has been achieved, it is notably within restricted problem domains. Fragility near the domain boundaries remains a problem. An analogy with biological vision systems suggests the limitation lies in the area of perceptual organization, or those processes that abstract image constructs into task-relevant terms. For machine vision applications this organization is subsumed by domain (image) preselection. Using border ownership as an example, we show that in biological vision this task is (necessarily) solved by non-hierarchical processing organizations. If the whole computer vision system is truly to be more than a sum of parts, we need to move from trees to the graph that they are approximating.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Simoncelli E, Olshausen BA (2001) Annu Rev Neurosci 24:1193
Schwartz O, Pillow JW, Rust NC, Simoncelli EP (2006) J Vis 6:484
Lamme VA (2003) Trends Cogn Sci 7(1):12
Itti L, Rees G, Tsotsos J (eds) (2005) Elsevier/Academic Press
Serre T, Wolf L, Bileschi S, Riesenhuber M, Poggio T (2007) IEEE Trans Pattern Anal Mach Intell 29(3):411
Fidler S, Boben M, Leonardis A (2009) In: Object categorization: computer and human vision perspectives. Cambridge University Press, Cambridge. http://vicos.fri.uni-lj.si/data/alesl/chapterLeonardis.pdf
Lecun Y, Bengio Y (1995) In: Arbib MA (ed) The handbook of brain theory and neural networks. MIT Press, Cambridge
Hinton GE, Osindero S, Teh YW (2006) Neural Comput 18:1527
Mori G, Ren X, Efros A, Malik J (2004) In: Proceedings of the 2004 IEEE computer society conference on computer vision and pattern recognition, 2004, CVPR 2004, vol 2, pp II-326–II-333. doi:10.1109/CVPR.2004.1315182
Yao BZ, Yang X, Lin L, Lee MW, Zhu SC (2010) Proc IEEE 98(8):1485
Olshausen BA, Field D (2006) In: van Hemmen J, Sejnowski T (eds) 23 problems in systems neuroscience. Oxford University Press, Oxford. doi:10.1093/acprof:oso/9780195148220.001.0001
Pinto N, Cox DD, DiCarlo JJ (2008) PLoS Comput Biol 4(1):e27. doi:10.1371/journal.pcbi.0040027
Ungerleider LG, Mishkin M (1982) In: Ingle D, Goodale MA, Mansfield R (eds) Analysis of visual behavior. MIT Press, Cambridge
Goodale M, Milner AD (1992) Trends Neurosci 15(1):20
Desimone R, Schein S (1987) J Neurophysiol 57(3):835
Wertheimer M (1923) Psychol Forsch 4:301
Koffka K (1935) Principles of Gestalt psychology. Harcourt, Brace & World, New York
Nakayama K, Shimojo S (1992) Science 257(5075):1357
Felleman D, Essen DV (1991) Cereb Cortex 1:1
Lindberg DC (1996) Theories of vision from Al-kindi to Kepler. University of Chicago Press, Chicago
Selfridge O (1959) In: Laboratory NP (ed) Symposium on the mechanization of thought processes. H. M. Stationary Office, London
Hubel DH, Wiesel TN (1977) Proc R Soc Lond B 198:1
Gross CG (2002) Neuroscientist 8(5):512. doi:10.1177/107385802237175
Fukushima K (1980) Biol Cybern 36:193
Rosenfeld A, Thurston M (1971) IEEE Trans Comput C-20:562
Marr D, Hildreth E (1979) Theory of edge detection. Tech. Rep. MIT AI Memo 518, MIT AI Lab
Koenderink JJ (1984) Biol Cybern 50:363
Witkin AP (1983) In: Proceedings of the 8th international joint conference on artificial intelligence, Karlsruhe, West Germany, pp 1019–1022
Lindeberg T (1994) Scale-space theory in computer vision. Kluwer Academic, Norwell
Caselles V, Morel JM, Sbert C (1998) IEEE Trans Image Process 7(3):376
Zeki S, Shipp S (1988) Nature 335:311
Geman D, Jedynak B (1996) An active testing model for tracking roads in satellite images. Tech. Rep. 2757, INRIA
Amit Y, Geman D (1997) Neural Comput 9(7):1545
Viola P, Jones M (2001) Rapid object detection using a boosted cascade of simple features
Lee H, Grosse R, Ranganath R, Ng AY (2009) In: International conference on machine learning
Ullman S (1994) In: Koch C, Davis J (eds) Large-scale neuronal theories of the brain. MIT Press, Cambridge, pp 257–270
Ullman S, Vidal-Naquet M, Sali E (2002) Nat Neurosci 5:682
Pelillo M, Siddiqi K, Zucker SW (1998) IEEE Trans Pattern Anal Mach Intell 21:1105
Sivic J, Russell BC, Zisserman A, Freeman WT, Efros AA (2008) In: IEEE conference on computer vision and pattern recognition
Tappen MF, Freeman WT (2003) In: International conference on computer vision
Arora S (1998) J ACM 45(5):753. doi:10.1145/290179.290180
Arbeláez P, Maire M, Fowlkes C, Malik J (2011) IEEE Trans Pattern Anal Mach Intell 33(5):898. doi:10.1109/TPAMI.2010.161
Ullman S, Epshtein B (2006) In: Ponce J, Hebert M, Schmid C, Zisserman A (eds) Toward category-level object recognition. Lecture notes in computer science, vol 4170. Springer, Berlin, pp 321–344
Ben-Shahar O, Zucker SW (2003) Neural Comput 16:445
Ben-Shahar O, Huggins P, Izo T, Zucker SW (2003) J Physiol (Paris) 97:191
Ben-Shahar O, Zucker SW (2004) Neural Netw 17:753
Kanizsa G (1979) Organization in vision: essays on Gestalt perception. Praeger, New York
Koffka K (1935) Principles of Gestalt psychology. Harcourt Brace and Co., New York
Zhou H, Friedman H, von der Heydt R (2000) J Neurosci 20:6594
Zucker SW (2012) J Physiol (Paris) 106:297
Dimitrov P, Lawlor M, Zucker SW (2011) In: Third international conference on scale space and variational methods in computer vision, Israel
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag London
About this chapter
Cite this chapter
Zucker, S.W. (2013). The Visual Hierarchy Mirage: Seeing Trees in a Graph. In: Dickinson, S., Pizlo, Z. (eds) Shape Perception in Human and Computer Vision. Advances in Computer Vision and Pattern Recognition. Springer, London. https://doi.org/10.1007/978-1-4471-5195-1_11
Download citation
DOI: https://doi.org/10.1007/978-1-4471-5195-1_11
Publisher Name: Springer, London
Print ISBN: 978-1-4471-5194-4
Online ISBN: 978-1-4471-5195-1
eBook Packages: Computer ScienceComputer Science (R0)