A model of object recognition

Our model of object recognition [1, 2] puts together many known and accepted ideas about the neurophysiology of the visual cortex, and tries to provide a unified framework for understanding the visual information processing.

Disclaimer of Warranty

The programs provided on this website are provided `as is' without warranty of any kind. We make no warranties, express or implied, that the programs are free of error, or are consistent with any particular standard of merchantability, or that they will meet your requirements for any particular application. They should not be relied upon for solving a problem whose incorrect solution could result in injury to a person or loss of property. If you do use the programs or procedures in such a manner, it is at your own risk. The authors disclaim all liability for direct, incidental or consequential damages resulting from your use of the programs on this website.

New Matlab source code (Summer 2006)

Here is an improved version of the software, which incoporates learned features, biologically plausible operations (normalized dot products and soft-max, replacing Gaussian and max), and more layers (bypass routes and more intermediate layers). Mex-C routine is used to speed up the computation (a full computation of 256x256 image would take about one minute on a regular PC).

Other versions


[1] M. Riesenhuber and T. Poggio. "Hierarchical Models of Object Recognition in Cortex" in Nature Neuroscience: 2, 1019-1025, 1999.

[2] T. Serre, M. Kouh, C. Cadieu, U. Knoblich, G. Kreiman and T. Poggio. "A Theory of Object Recognition: Computations and Circuits in the Feedforward Path of the Ventral Stream in Primate Visual Cortex" in CBCL Paper #259/AI Memo #2005-036, Massachusetts Institute of Technology, Cambridge, MA, 2005.

[3] T. Serre, J. Louie, M. Riesenhuber and T. Poggio. "On the Role of Object-specific Features for Real World Object Recognition in Biological Vision" in Workshop on Biologically Motivated Computer Vision (BMCV), 2002.
Last modified: June, 2006.