A Biologically Plausible Approach to Cat and Dog Discrimination
Conference paper
First Online:
Abstract
The paper describes a computational model of human expert object recognition in terms of pattern recognition algorithms. In particular, we model the process by which people quickly recognize familiar objects seen from familiar viewpoints at both the instance and category level. We propose a sequence of unsupervised pattern recognition algorithms that is consistent with all known biological data. It combines the standard Gabor-filter model of early vision with a novel cluster-based local linear projection model of expert object recognition in the ventral visual stream. This model is shown to be better than standard algorithms at distinguishing between cats and dogs.
Keywords
Visual Memory Inferior Frontal Gyrus Independent Component Analysis Gabor Filter Familiar Object
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Download
to read the full conference paper text
References
- [1]A. D. Milner and M. A. Goodale, The Visual Brain in Action. Oxford: Oxford University Press, 1995.Google Scholar
- [2]K. Nakamura, R. Kawashima, N. Sata, A. Nakamura, M. Sugiura, T. Kato, K. Hatano, K. Ito, H. Fukuda, T. Schormann, and K. Zilles, “Functional delineation of the human occipito-temporal areas related to face and scene processing: a PET study,” Brain, vol. 123, pp. 1903–1912, 2000.CrossRefGoogle Scholar
- [3]K. M. O’Craven and N. Kanwisher, “Mental Imagery of Faces and Places Activates Corresponding Stimulus-Specific Brain Regions,” Journal of Cognitive Neuroscience, vol. 12, pp. 1013–1023, 2000.CrossRefGoogle Scholar
- [4]I. Gauthier and M. J. Tarr, “Unraveling mechanisms for expert object recognition: Bridging Brain Activity and Behavior,” Journal of Experimental Psychology: Human Perception and Performance, vol. in press, 2002.Google Scholar
- [5]A. Puce, T. Allison, J. C. Gore, and G. McCarthy, “Face-sensitive regions in human extrastriate cortex studied by functional MRI,” Journal of Neurophysiology, vol. 74, pp. 1192–1199, 1995.Google Scholar
- [6]V. P. Clark, K. Keil, J. M. Maisog, S. Courtney, L. G. Ungeleider, and J. V. Haxby, “Functional Magnetic Resonance Imaging of Human Visual Cortex during Face Matching: A Comparison with Positron Emission Tomography,” NeuroImage, vol. 4, pp. 1–15, 1996.CrossRefGoogle Scholar
- [7]N. Kanwisher, M. Chun, J. McDermott, and P. Ledden, “Functional Imaging of Human Visual Recognition,” Cognitive Brain Research, vol. 5, pp. 55–67, 1996.CrossRefGoogle Scholar
- [8]E. Maguire, C. D. Frith, and L. Cipolotti, “Distinct Neural Systems for the Encoding and Recognition of Topography and Faces,” Neurolmage, vol. 13, pp. 743–750, 2001.CrossRefGoogle Scholar
- [9]F. Tong, K. Nakayama, M. Moscovitch, O. Weinrib, and N. Kanwisher, “Response Properties of the Human Fusiform Face Area,” Cognitive Neuropsychology, vol. 17, pp. 257–279, 2000.CrossRefGoogle Scholar
- [10]L. L. Chao, A. Martin, and J. V. Haxby, “Are face-responsive regions selective only for faces?,” NeuroReport, vol. 10, pp. 2945–2950, 1999.CrossRefGoogle Scholar
- [11]A. Ishai, L. G. Ungerleider, A. Martin, J. L. Schouten, and J. V. Haxby, “Distributed representation of objects in the human ventral visual pathway,” Science, vol. 96, pp. 9379–9384, 1999.Google Scholar
- [12]M. J. Tarr and I. Gauthier, “FFA: a flexible fusiform area for subordinate-level visual processing automatized by expertise,” Neuroscience, vol. 3, pp. 764–769, 2000.Google Scholar
- [13]I. Gauthier, M. J. Tarr, J. Moylan, A. W. Anderson, P. Skudlarski, and J. C. Gore, “Does Visual Subordinate-level Categorization Engage the Functionally Defined Fusiform Face Area?,” Cognitive Neuropsychology, vol. 17, pp. 143–163, 2000.CrossRefGoogle Scholar
- [14]J. W. Tanaka and T. Curran, “A Neural Basis for Expert Object Recognition,” Psychological Science, vol. 12, pp. 43–47, 2001.CrossRefGoogle Scholar
- [15]T. S. Lee, D. Mumford, R. Romero, and V. A. F. Lamme, “The role of the primary visual cortex in higher level vision,” Vision Research, vol. 38, pp. 2429–2454, 1998.CrossRefGoogle Scholar
- [16]J. V. Haxby, L. G. Ungerleider, V. P. Clark, J. L. Schouten, E. A. Hoffman, and A. Martin, “The Effect of Face Inversion on Activity in Human Neural Systems for Face and Object Recognition,” Neuron, vol. 22, pp. 189–199, 199.Google Scholar
- [17]I. Gauthier, M. J. Tarr, A. W. Anderson, P. Skudlarski, and J. C. Gore, “Behavioral and Neural Changes Following Expertise Training,” presented at Annual Meeting of the Psychonomic Society, Philadelphia, PA, 1997.Google Scholar
- [18]S. M. Kosslyn, Image and Brain: The Resolution of the Imagery Debate. Cambridge, MA: MIT Press, 1994.Google Scholar
- [19]S. M. Kosslyn, “Visual Mental Images and Re-Presentations of the World: A Cognitive Neuroscience Approach,” presented at Visual and Spatial Reasoning in Design, Cambridge, MA, 1999.Google Scholar
- [20]S. M. Kosslyn, A. Pascual-Leone, O. Felician, S. Camposano, J. P. Keenan, W. L. Thompson, G. Ganis, K. E. Sukel, and N. M. Alpert, “The Role of Area 17 in Visual Imagery: Convergent Evidence from PET and rTMS,” Science, vol. 284, pp. 167–170, 1999.CrossRefGoogle Scholar
- [21]N. Petkov and P. Kruizinga, “Computational models of visual neurons specialised in the detection of periodic and aperiodic oriented stimuli: bar and grating cells,” Biological cybernetics, vol. 76, pp. 83–96, 1997.MATHCrossRefGoogle Scholar
- [22]D. A. Pollen, J. P. Gaska, and L. D. Jacobson, “Physiological Constraints on Models of Visual Cortical Function,” in Models of Brain Functions, M. Rodney and J. Cotterill, Eds. New York: Cambridge University Press, 1989, pp. 115–135.Google Scholar
- [23]R. O. Duda and P. E. Hart, Pattern Classification and Scene Analysis. New York: John Wiley and Sons, 1973.MATHGoogle Scholar
- [24]M. Turk and A. Pentland, “Eigenfaces for Recognition,” Journal of Cognitive Neuroscience, vol. 3, pp. 71–86, 1991.CrossRefGoogle Scholar
- [25]A. Hyvärinen and E. Oja, “Independent Component Analysis: Algorithms and Applications,” Neural Networks, vol. 13, pp. 411–430, 2000.CrossRefGoogle Scholar
- [26]B. G. Tabachnick and L. S. Fidell, Using Multivariate Statistics. Boston: Allyn & Bacon, Inc., 2000.Google Scholar
- [27]K. Baek and B. A. Draper, “Factor Analysis for Background Suppression,” presented at International Conference on Pattern Recognition, Quebec City, 2002.Google Scholar
- [28]M. S. Bartlett, Face Image Analysis by Unsupervised Learning: Kluwer Academic, 2001.Google Scholar
- [29]D. D. Lee and H. S. Seung, “Learning the parts of objects by non-negative matrix factorization,” Nature, vol. 401, pp. 788–791, 1999.CrossRefGoogle Scholar
- [30]K. Baek, B. A. Draper, J. R. Beveridge, and K. She, “PCA vs ICA: A comparison on the FERET data set,” presented at Joint Conference on Information Sciences, Durham, N.C., 2002.Google Scholar
- [31]P. Belhumeur, J. Hespanha, and D. Kriegman, “Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection,” IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. 19, pp. 711–720, 1997.CrossRefGoogle Scholar
- [32]B. J. Frey, A. Colmenarez, and T. S. Huang, “Mixtures of Local Linear Subspaces for Face Recognition,” presented at IEEE Conference on Computer Vision and Pattern Recognition, Santa Barbara, CA, 1998.Google Scholar
- [33]N. Kambhatla and T. K. Leen, “Dimension Reduction by Local PCA,” Neural Computation, vol. 9, pp. 1493–1516, 1997.CrossRefGoogle Scholar
Copyright information
© Springer-Verlag Berlin Heidelberg 2002