A recurrent dynamic model for correspondence-based face recognition.

Our aim here is to create a fully neural, functionally competitive, and correspondence-based model for invariant face recognition. By recurrently integrating information about feature similarities, spatial feature relations, and facial structure stored in memory, the system evaluates face identity ("what"-information) and face position ("where"-information) using explicit representations for both. The network consists of three functional layers of processing, (1) an input layer for image representation, (2) a middle layer for recurrent information integration, and (3) a gallery layer for memory storage. Each layer consists of cortical columns as functional building blocks that are modeled in accordance with recent experimental findings. In numerical simulations we apply the system to standard benchmark databases for face recognition. We find that recognition rates of our biologically inspired approach lie in the same range as recognition rates of recent and purely functionally motivated systems.

[1]  Doris Y. Tsao,et al.  A Cortical Region Consisting Entirely of Face-Selective Cells , 2006, Science.

[2]  B. Richmond,et al.  Intrinsic dynamics in neuronal networks. I. Theory. , 2000, Journal of neurophysiology.

[3]  I Biederman,et al.  Neurocomputational bases of object and face recognition. , 1997, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[4]  T. Womelsdorf,et al.  Dynamic shifts of visual receptive fields in cortical area MT by spatial attention , 2006, Nature Neuroscience.

[5]  R. Douglas,et al.  Neuronal circuits of the neocortex. , 2004, Annual review of neuroscience.

[6]  T. Poggio,et al.  Hierarchical models of object recognition in cortex , 1999, Nature Neuroscience.

[7]  Patrick J. Flynn,et al.  Overview of the face recognition grand challenge , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[8]  M. Goldberg,et al.  The time course of perisaccadic receptive field shifts in the lateral intraparietal area of the monkey. , 2003, Journal of neurophysiology.

[9]  Rolf P. Würtz,et al.  Image Representation by Complex Cell Responses , 2004, Neural Computation.

[10]  J. Daugman.  Two-dimensional spectral analysis of cortical receptive field profiles , 1980, Vision Research.

[11]  E. Ross.  The Organization of Will , 1916, American Journal of Sociology.

[12]  Aleix M. Martinez,et al.  The AR face database , 1998 .

[13]  Christoph von der Malsburg,et al.  What Is the Optimal Architecture for Visual Information Routing? , 2007, Neural Computation.

[14]  Vernon B Mountcastle,et al.  Introduction. Computation in cortical columns. , 2003, Cerebral cortex.

[15]  Stefan Wermter,et al.  A self-organizing map of sigma-pi units , 2007, Neurocomputing.

[16]  I. Biederman.  Recognition-by-components: a theory of human image understanding. , 1987, Psychological review.

[17]  I. Gauthier,et al.  Expertise for cars and birds recruits brain areas involved in face recognition , 2000, Nature Neuroscience.

[18]  Frank Rosenblatt,et al.  PRINCIPLES OF NEURODYNAMICS. PERCEPTRONS AND THE THEORY OF BRAIN MECHANISMS , 1963 .

[19]  A. Peters,et al.  Myelinated axons and the pyramidal cell modules in monkey primary visual cortex , 1996, The Journal of comparative neurology.

[20]  Joachim M. Buhmann,et al.  Distortion Invariant Object Recognition in the Dynamic Link Architecture , 1993, IEEE Trans. Computers.

[21]  Bartlett W. Mel.  SEEMORE: Combining Color, Shape, and Texture Histogramming in a Neurally Inspired Approach to Visual Object Recognition , 1997, Neural Computation.

[22]  Harry Wechsler,et al.  The FERET database and evaluation procedure for face-recognition algorithms , 1998, Image Vis. Comput..

[23]  J. Cowan,et al.  A mathematical theory of the functional dynamics of cortical and thalamic nervous tissue , 1973, Kybernetik.

[24]  R Lawson,et al.  The effect of prior experience on recognition thresholds for plane-disoriented pictures of familiar objects , 1999, Memory & cognition.

[25]  Joel Waldfogel,et al.  Introduction , 2010, Inf. Econ. Policy.

[26]  D. V. van Essen,et al.  A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information , 1993, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[27]  Wulfram Gerstner,et al.  Population Dynamics of Spiking Neurons: Fast Transients, Asynchronous States, and Locking , 2000, Neural Computation.

[28]  C. Bundesen,et al.  Visual transformation of size. , 1975, Journal of experimental psychology. Human perception and performance.

[29]  Pietro Perona,et al.  One-shot learning of object categories , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Jennifer A. Mangels,et al.  Predictive Codes for Forthcoming Perception in the Frontal Cortex , 2006, Science.

[31]  David W. Arathorn,et al.  Map-Seeking Circuits in Visual Cognition: A Computational Mechanism for Biological and Machine Vision , 2002 .

[32]  Keiji Tanaka,et al.  Inferotemporal cortex and object vision. , 1996, Annual review of neuroscience.

[33]  Geoffrey E. Hinton.  A Parallel Computation that Assigns Canonical Object-Based Frames of Reference , 1981, IJCAI.

[34]  Azriel Rosenfeld,et al.  Face recognition: A literature survey , 2003, CSUR.

[35]  B. Renault,et al.  ERPs and chronometry of face recognition: following‐up Seeck et al. and George et al. , 1998, Neuroreport.

[36]  Nancy Kanwisher.  Neuroscience. What's in a face? , 2006, Science.

[37]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[38]  Jörg Lücke,et al.  Glial cells for information routing? , 2007, Cognitive Systems Research.

[39]  J. P. Jones,et al.  An evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex. , 1987, Journal of neurophysiology.

[40]  M. Tarr,et al.  FFA: a flexible fusiform area for subordinate-level visual processing automatized by expertise , 2000, Nature Neuroscience.

[41]  Haim Sompolinsky,et al.  Chaotic Balanced State in a Model of Cortical Circuits , 1998, Neural Computation.

[42]  A. Peters,et al.  Neuronal organization in area 17 of cat visual cortex. , 1993, Cerebral cortex.

[43]  Cristina Savin,et al.  Resonance or integration? Self-sustained dynamics and excitability of neural microcircuits. , 2007, Journal of neurophysiology.

[44]  LinLin Shen,et al.  Face authentication test on the BANCA database , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[45]  Jörg Lücke,et al.  Invariant Face Recognitionin a Network of Cortical Columns , 2008, VISAPP.

[46]  E. Callaway,et al.  Excitatory cortical neurons form fine-scale functional networks , 2005, Nature.

[47]  Kevan A. C. Martin,et al.  A Canonical Microcircuit for Neocortex , 1989, Neural Computation.

[48]  E. G. Jones,et al.  A microcolumnar structure of monkey cerebral cortex revealed by immunocytochemical studies of double bouquet cell axons , 1990, Neuroscience.

[49]  Rajesh P. N. Rao,et al.  Bilinear Sparse Coding for Invariant Vision , 2005, Neural Computation.

[50]  G Wallis.  Linear models of simple cells: correspondence to real cell responses and space spanning properties. , 2001, Spatial vision.

[51]  E. G. Jones,et al.  Microcolumns in the cerebral cortex. , 2000, Proceedings of the National Academy of Sciences of the United States of America.

[52]  Laurenz Wiskott,et al.  Face recognition by dynamic link matching , 1996 .

[53]  Thomas Serre,et al.  Robust Object Recognition with Cortex-Like Mechanisms , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[54]  Rolf P W Urtz.  Building Visual Correspondence Maps | from Neuronal Dynamics to a Face Recognition System , 1995 .

[55]  V. Lamme.  Why visual attention and awareness are different , 2003, Trends in Cognitive Sciences.

[56]  D. Kelly,et al.  Minicolumnar organization within somatosensory cortical segregates: II. Emergent functional properties. , 1994, Cerebral cortex.

[57]  D. Buxhoeveden,et al.  The minicolumn hypothesis in neuroscience. , 2002, Brain : a journal of neurology.

[58]  Gustavo Deco,et al.  Reward-biased probabilistic decision-making: Mean-field predictions and spiking simulations , 2006, Neurocomputing.

[59]  Markus Graf,et al.  Coordinate transformations in object recognition. , 2006, Psychological bulletin.

[60]  Heinrich H. Bülthoff,et al.  Proceedings of the First IEEE International Workshop on Biologically Motivated Computer Vision , 2000 .

[61]  J R Duhamel,et al.  The updating of the representation of visual space in parietal cortex by intended eye movements. , 1992, Science.

[62]  R Kree,et al.  Recognition of topological features of graphs and images in neural networks , 1988 .

[63]  P. Jolicoeur.  The time to name disoriented natural objects , 1985, Memory & cognition.

[64]  D. Hubel,et al.  Ferrier lecture - Functional architecture of macaque monkey visual cortex , 1977, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[65]  M. Diamond,et al.  Demonstration of discrete place‐defined columns—segregates—in the cat SI , 1990, The Journal of comparative neurology.

[66]  Christof Koch,et al.  Attentional Selection for Object Recognition - A Gentle Way , 2002, Biologically Motivated Computer Vision.

[67]  N. Kanwisher,et al.  The fusiform face area: a cortical region specialized for the perception of faces , 2006, Philosophical Transactions of the Royal Society B: Biological Sciences.

[68]  Bruno A. Olshausen,et al.  Directed visual attention and the dynamic control of information flow , 2005 .

[69]  Denis Fize,et al.  Speed of processing in the human visual system , 1996, Nature.

[70]  A. Yuille,et al.  Opinion TRENDS in Cognitive Sciences Vol.10 No.7 July 2006 Special Issue: Probabilistic models of cognition Vision as Bayesian inference: analysis by synthesis? , 2022 .

[71]  D. Ringach.  Spatial structure and symmetry of simple-cell receptive fields in macaque primary visual cortex. , 2002, Journal of neurophysiology.

[72]  Norbert Krüger,et al.  Face recognition by elastic bunch graph matching , 1997, Proceedings of International Conference on Image Processing.

[73]  R. Desimone,et al.  Neural mechanisms of spatial selective attention in areas V1, V2, and V4 of macaque visual cortex. , 1997, Journal of neurophysiology.

[74]  Christoph von der Malsburg,et al.  A Marker-Based Model for the Ontogenesis of Routing Circuits , 2007, ICANN.

[75]  Christoph von der Malsburg,et al.  Maplets for correspondence-based object recognition , 2004, Neural Networks.

[76]  Hyeonjoon Moon,et al.  The FERET evaluation methodology for face-recognition algorithms , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[77]  Tomaso Poggio,et al.  Fast Readout of Object Identity from Macaque Inferior Temporal Cortex , 2005, Science.

[78]  Jörg Lücke,et al.  Rapid Convergence to Feature Layer Correspondences , 2008, Neural Computation.

[79]  John K. Tsotsos,et al.  Neurobiology of Attention , 2005 .

[80]  Bruno A Olshausen,et al.  Timecourse of neural signatures of object recognition. , 2003, Journal of vision.

[81]  M. Eigen.  Selforganization of matter and the evolution of biological macromolecules , 1971, Naturwissenschaften.

[82]  K. Rockland,et al.  Some thoughts on cortical minicolumns , 2004, Experimental Brain Research.

[83]  Nicolas Pinto,et al.  Why is Real-World Visual Object Recognition Hard? , 2008, PLoS Comput. Biol..

[84]  E. Callaway,et al.  Laminar sources of synaptic input to cortical inhibitory interneurons and pyramidal neurons , 2000, Nature Neuroscience.

[85]  Laurenz Wiskott,et al.  The role of topographical constraints in face recognition , 1999, Pattern Recognition Letters.

[86]  J. Finnigan.  How Nature Works; The science of self-organized criticality , 2001 .

[87]  Y. LeCun,et al.  Learning methods for generic object recognition with invariance to pose and lighting , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[88]  Marc-Oliver Gewaltig,et al.  A model of computation in neocortical architecture , 1999, Neural Networks.

[89]  E. Rolls,et al.  A Neurodynamical cortical model of visual attention and invariant object recognition , 2004, Vision Research.

[90]  Zhi-Hua Zhou,et al.  Recognizing partially occluded, expression variant faces from single training image per person with SOM and soft k-NN ensemble , 2005, IEEE Transactions on Neural Networks.

[91]  Yasuomi D. Sato,et al.  A Visual Object Recognition System Invariant to Scale and Rotation , 2008, ICANN.

[92]  Jörg Lücke,et al.  Rapid Processing and Unsupervised Learning in a Model of the Cortical Macrocolumn , 2004, Neural Computation.

[93]  Keiji Tanaka.  Columns for complex visual object features in the inferotemporal cortex: clustering of cells with similar but slightly different stimulus selectivities. , 2003, Cerebral cortex.

[94]  Nancy Kanwisher,et al.  What's in a Face? , 2006, Science.

[95]  Robert B. Fisher,et al.  Incremental One-Class Learning with Bounded Computational Complexity , 2007, ICANN.

[96]  V. Mountcastle.  The columnar organization of the neocortex. , 1997, Brain : a journal of neurology.

[97]  A. Peters,et al.  The organization of double bouquet cells in monkey striate cortex , 1997, Journal of neurocytology.

[98]  Christoph von der Malsburg,et al.  Attentional Processes in Correspondence-Based Object Recognition , 2008 .