Receptive Field Structures for Recognition

Localized operators, like Gabor wavelets and difference-of-gaussian filters, are considered useful tools for image representation. This is due to their ability to form a sparse code that can serve as a basis set for high-fidelity reconstruction of natural images. However, for many visual tasks, the more appropriate criterion of representational efficacy is recognition rather than reconstruction. It is unclear whether simple local features provide the stability necessary to subserve robust recognition of complex objects. In this article, we search the space of two-lobed differential operators for those that constitute a good representational code under recognition and discrimination criteria. We find that a novel operator, which we call the dissociated dipole, displays useful properties in this regard. We describe simple computational experiments to assess the merits of such dipoles relative to the more traditional local operators. The results suggest that nonlocal operators constitute a vocabulary that is stable across a range of image transformations.

[1]  P. Sinha,et al.  Dissociated Dipoles: Image Representation via Non-local Comparisons , 2003 .

[2]  G. Moushegian,et al.  Response characteristics of neurons in the cochlear nuclei to sinusoidal and vowel‐sound stimulation , 1974 .

[3]  Pawan Sinha,et al.  Qualitative Representations for Recognition , 2002, Biologically Motivated Computer Vision.

[4]  Shimon Ullman,et al.  Class-Specific, Top-Down Segmentation , 2002, ECCV.

[5]  F. Attneave.  Some informational aspects of visual perception. , 1954, Psychological review.

[6]  Pietro Perona,et al.  A Bayesian approach to unsupervised one-shot learning of object categories , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[7]  D Regan,et al.  Coincidence detectors: visual processing of a pair of lines and implications for shape discrimination , 2000, Vision Research.

[8]  S. Laughlin.  A Simple Coding Procedure Enhances a Neuron's Information Capacity , 1981, Zeitschrift fur Naturforschung. Section C, Biosciences.

[9]  Terrence J. Sejnowski,et al.  The “independent components” of natural scenes are edge filters , 1997, Vision Research.

[10]  Sameer A. Nene,et al.  Columbia Object Image Library (COIL100) , 1996 .

[11]  Stephen M. Pizer,et al.  Object representation by cores: Identifying and representing primitive spatial regions , 1995, Vision Research.

[12]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[13]  J. Mollon,et al.  Comparison at a Distance , 2003, Perception.

[14]  B Julesz,et al.  Experiments in the visual perception of texture. , 1975, Scientific American.

[15]  Hiroshi Murase,et al.  Real-time 100 object recognition system , 1996, Proceedings of IEEE International Conference on Robotics and Automation.

[16]  Pietro Perona,et al.  Object class recognition by unsupervised scale-invariant learning , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[17]  David J. Field,et al.  Sparse coding with an overcomplete basis set: A strategy employed by V1? , 1997, Vision Research.

[18]  Alex Pentland,et al.  Bayesian face recognition , 2000, Pattern Recognit..

[19]  Shimon Edelman.  Representing 3D objects by sets of activities of receptive fields , 1993 .

[20]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[21]  David J. Field,et al.  What Is the Goal of Sensory Coding? , 1994, Neural Computation.

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

[23]  D Kersten,et al.  Predictability and redundancy of natural images. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[24]  D. Regan,et al.  Opponent model for line interval discrimination: Interval and vernier performance compared , 1987, Vision Research.

[25]  J. Chapin,et al.  Laminar differences in sizes, shapes, and response profiles of cutaneous receptive fields in the rat SI cortex , 2004, Experimental Brain Research.

[26]  Shimon Ullman,et al.  Learning to Segment , 2004, ECCV.

[27]  D. Hubel,et al.  Receptive fields of single neurones in the cat's striate cortex , 1959, The Journal of physiology.

[28]  Pietro Perona,et al.  Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[29]  Norbert Krüger,et al.  Face Recognition by Elastic Bunch Graph Matching , 1997, CAIP.

[30]  Edward H. Adelson,et al.  The Design and Use of Steerable Filters , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[31]  Eero P. Simoncelli,et al.  Natural image statistics and neural representation. , 2001, Annual review of neuroscience.

[32]  Michel Vidal-Naquet,et al.  Visual features of intermediate complexity and their use in classification , 2002, Nature Neuroscience.

[33]  Andy Harter,et al.  Parameterisation of a stochastic model for human face identification , 1994, Proceedings of 1994 IEEE Workshop on Applications of Computer Vision.

[34]  D. M. Green,et al.  Signal detection theory and psychophysics , 1966 .

[35]  David J. Field,et al.  Emergence of simple-cell receptive field properties by learning a sparse code for natural images , 1996, Nature.

[36]  Takeo Kanade,et al.  Probabilistic modeling of local appearance and spatial relationships for object recognition , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[37]  Maximilian Riesenhuber,et al.  Investigating shape representation in area V4 with HMAX: Orientation and Grating selectivities , 2003 .