COMMON COMPUTATIONAL STRATEGIES IN MACHINE AND BIOLOGICAL VISION

Humans effortlessly perform visual tasks, like face detection and recognition, that have turned out to be extremely difficult for artificial vision systems. Research into the principles underlying biological object recognition therefore is of great potential interest to the machine vision community. Recent experiments — both psychophysical and physiological — have provided evidence that instead of using 3D models as in many “classical” computer vision systems, a biological strategy for object recognition is view-based, in the sense that objects are represented by a set of 2D views. Several models have presented plausible mechanisms explaining how this “snapshot”-based representation can develop and how it can be used to perform object recognition. Extending the view-based paradigm to artificial systems has proved to be an extremely successful approach to developing robust and flexible computer vision systems that are able to perform reliably in real-world situations. Among others, we present applications to object detection, face recognition, and pose estimation and synthesis.

[1]  Tomaso A. Poggio,et al.  Example-Based Learning for View-Based Human Face Detection , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Tomaso A. Poggio,et al.  Just One View: Invariances in Inferotemporal Cell Tuning , 1997, NIPS.

[3]  Tomaso A. Poggio,et al.  Linear Object Classes and Image Synthesis From a Single Example Image , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Tomaso A. Poggio,et al.  Pedestrian detection using wavelet templates , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

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

[6]  Peter Dayan,et al.  Neural Models for Part-Whole Hierarchies , 1996, NIPS.

[7]  Tomaso A. Poggio,et al.  3D Object Recognition: A Model of View-Tuned Neurons , 1996, NIPS.

[8]  Keiji Tanaka,et al.  Optical Imaging of Functional Organization in the Monkey Inferotemporal Cortex , 1996, Science.

[9]  Tomaso Poggio,et al.  Learning to see , 1996 .

[10]  Geoffrey E. Hinton,et al.  The "wake-sleep" algorithm for unsupervised neural networks. , 1995, Science.

[11]  N. Logothetis,et al.  Shape representation in the inferior temporal cortex of monkeys , 1995, Current Biology.

[12]  N. Logothetis,et al.  Psychophysical and physiological evidence for viewer-centered object representations in the primate. , 1995, Cerebral cortex.

[13]  Vladimir Vapnik,et al.  The Nature of Statistical Learning , 1995 .

[14]  Minami Ito,et al.  Size and position invariance of neuronal responses in monkey inferotemporal cortex. , 1995, Journal of neurophysiology.

[15]  Leslie G. Ungerleider,et al.  ‘What’ and ‘where’ in the human brain , 1994, Current Opinion in Neurobiology.

[16]  David Beymer,et al.  Face recognition under varying pose , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Keiji Tanaka,et al.  Neuronal selectivities to complex object features in the ventral visual pathway of the macaque cerebral cortex. , 1994, Journal of neurophysiology.

[18]  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.

[19]  Tomaso Poggio,et al.  Example Based Image Analysis and Synthesis , 1993 .

[20]  David I. Perrett,et al.  Neurophysiology of shape processing , 1993, Image Vis. Comput..

[21]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[22]  M. Young,et al.  Sparse population coding of faces in the inferotemporal cortex. , 1992, Science.

[23]  H H Bülthoff,et al.  Psychophysical support for a two-dimensional view interpolation theory of object recognition. , 1992, Proceedings of the National Academy of Sciences of the United States of America.

[24]  Peter Földiák,et al.  Learning Invariance from Transformation Sequences , 1991, Neural Comput..

[25]  R. Desimone,et al.  Visual properties of neurons in area V4 of the macaque: sensitivity to stimulus form. , 1987, Journal of neurophysiology.