Multiclass Object Recognition with Sparse, Localized Features

11 years 1 months ago
Multiclass Object Recognition with Sparse, Localized Features
We apply a biologically inspired model of visual object recognition to the multiclass object categorization problem. Our model modifies that of Serre, Wolf, and Poggio. As in that work, we first apply Gabor filters at all positions and scales; feature complexity and position/scale invariance are then built up by alternating template matching and max pooling operations. We refine the approach in several biologically plausible ways, using simple versions of sparsification and lateral inhibition. We demonstrate the value of retaining some position and scale information above the intermediate feature level. Using feature selection we arrive at a model that performs better with fewer features. Our final model is tested on the Caltech 101 object categories and the UIUC car localization task, in both cases achieving state-of-the-art performance. The results strengthen the case for using this class of model in computer vision.
Jim Mutch, David G. Lowe
Added 12 Oct 2009
Updated 12 Oct 2009
Type Conference
Year 2006
Where CVPR
Authors Jim Mutch, David G. Lowe
Comments (0)