A Real Time Computer Vision System based on the Standard Model

Motivation The standard model is a biologically motivated architecture for computer vision whose components are in close agreement with existing physiological evidence. It is ’standard’ because it attempts to consolidate all the widely accepted facts and observations in a single model. The model was compared extensively to other front-end vision algorithms [7, 1, 6, 3] and has been shown to outperform state-of-the-art computer vision systems in object recognition task.

[1]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

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

[3]  Lucas J. van Vliet,et al.  Recursive Gabor filtering , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[4]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[5]  Tomaso Poggio,et al.  A New Biologically Motivated Framework for Robust Object Recognition , 2004 .

[6]  Lior Wolf,et al.  A Unified System For Object Detection, Texture Recognition, and Context Analysis Based on the Standard Model Feature Set , 2005, BMVC.

[7]  Shimon Ullman,et al.  Feature hierarchies for object classification , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[8]  Thomas Serre,et al.  A Theory of Object Recognition: Computations and Circuits in the Feedforward Path of the Ventral Stream in Primate Visual Cortex , 2005 .

[9]  David G. Lowe,et al.  Multiclass Object Recognition with Sparse, Localized Features , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).