Connectionists: Free Matlab code for computational models of V1 simple cells and shape-selective V4 neurons with applications to computer vision

[George Azzopardi]

Dear all,

I am pleased to announce that we made publicly available the Matlab code of the following two algorithms:

1. A CORF computational model of a simple cell with application to contour detection 
CORF is a computational model of a simple cell in visual cortex. It is a more realistic model than the Gabor function model as it uses as input the responses of model LGN cells rather than the intensity pixels as they fall on the retina. CORF produces the following two important properties that the Gabor model fails to produce: contrast invariant orientation tuning and cross orientation suppression. Also, the CORF model outperforms the Gabor model in contour detection tasks with high statistical significance. Contour detection is presumably the the primary biological role of simple cells.

Download code:
http://matlabserver.cs.rug.nl/corfweb/web/index.html

Reference:
G. Azzopardi and N. Petkov, "A CORF computational model of a simple cell that relies on LGN input outperforms the Gabor function model", Biological Cybernetics, 106(3), 177-89, 2012.



2. Trainable COSFIRE filters for Keypoint Detection and Pattern Recognition

Download code:
http://matlabserver.cs.rug.nl/cosfireweb/web/index.html

Reference: 
G. Azzopardi and N. Petkov, "Trainable COSFIRE filters for keypoint detection and pattern recognition", IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, DOI: 10.1109/TPAMI.2012.106



Best regards,
George Azzopardi
-------------- next part --------------
An HTML attachment was scrubbed...
URL: https://mailman.srv.cs.cmu.edu/mailman/private/connectionists/attachments/20120914/0dc9d7bd/attachment.html