Object indexing using an iconic sparse distributed memory

  title={Object indexing using an iconic sparse distributed memory},
  author={R. P. Rao and D. Ballard},
  journal={Proceedings of IEEE International Conference on Computer Vision},
  • R. P. Rao, D. Ballard
  • Published 1995
  • Computer Science
  • Proceedings of IEEE International Conference on Computer Vision
  • A general-purpose object indexing technique is described that combines the virtues of principal component analysis with the favorable matching properties of high-dimensional spaces to achieve high-precision recognition. An object is represented by a set of high-dimensional iconic feature vectors comprised of the responses of derivatives of Gaussian filters at a range of orientations and scales. Since these filters can be shown to form the eigenvectors of arbitrary images containing both natural… CONTINUE READING
    103 Citations
    An Active Vision Architecture Based on Iconic Representations
    • 263
    Retrieving images by similarity of visual appearance
    • S. Ravela, R. Manmatha
    • Mathematics
    • 1997 Proceedings IEEE Workshop on Content-Based Access of Image and Video Libraries
    • 1997
    • 24
    A local color descriptor for efficient scene-object recognition
    • 2
    • PDF
    Image retrieval by appearance
    • 40
    Complex Feature Recognition: A Bayesian Approach for Learning to Recognize Objects
    • 34
    Affine invariant shape representation and recognition using Gaussian kernels and multi-dimensional indexing
    • J. Ben-Arie, Zhiqian Wang, K. Rao
    • Mathematics, Computer Science
    • 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings
    • 1996
    • 11
    Syntactic characterization of appearance and its application to image retrieval
    • 21
    • PDF
    Recognition without Correspondence using Multidimensional Receptive Field Histograms
    • 500
    • PDF


    An Active Vision Architecture Based on Iconic Representations
    • 263
    Eigenfaces for Recognition
    • 14,588
    • PDF
    Active vision
    • 1,011
    View-based and modular eigenspaces for face recognition
    • 2,218
    • PDF
    Seeing Behind Occlusions
    • 12
    A computational model of spatiochromatic image coding in early vision
    • 46
    Model-based recognition in robot vision
    • 657
    • PDF
    Sparse Distributed Memory
    • 955
    The Design and Use of Steerable Filters
    • 3,304
    • PDF