Complex Cells and Object Recognition


Nearest-neighbor correlation-based similarity computation in the space of outputs of complex-type receptive elds can support robust recognition of 3D objects. Our experiments with four collections of objects resulted in mean recognition rates between 84% and 94%, over a 40 40 range of viewpoints, centered on a stored canonical view and related to it by rotations in depth. This result has interesting implications for the design of a front end to an arti cial object recognition system, and for the understanding of the faculty of object recognition in primate vision



    Upload a copy of this work     Papers currently archived: 78,037

External links

Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

  • Only published works are available at libraries.

Similar books and articles

Computational theories of object recognition.Shimon Edelman - 1997 - Trends in Cognitive Sciences 1 (8):296-304.
Object recognition is not predication.Jean-Louis Dessalles & Laleh Ghadakpour - 2003 - Behavioral and Brain Sciences 26 (3):290-291.
Is visual recognition entirely impenetrable?Azriel Rosenfeld - 1999 - Behavioral and Brain Sciences 22 (3):391-392.
A strange hand: On self-recognition and recognition of another.Jenny Slatman - 2009 - Phenomenology and the Cognitive Sciences 8 (3):321-342.
How do animals solve object-recognition tasks?Dave G. Mumby - 1999 - Behavioral and Brain Sciences 22 (3):461-462.
On mechanical recognition.R. J. Nelson - 1976 - Philosophy of Science 43 (1):24-52.


Added to PP

91 (#141,191)

6 months
1 (#485,976)

Historical graph of downloads
How can I increase my downloads?

Author's Profile

Shimon Edelman
Cornell University

Citations of this work

No citations found.

Add more citations

References found in this work

Add more references