Patch-based Object Recognition Using Discriminatively Trained Gaussian Mixtures

A. Hegerath, T. Deselaers, H. Ney
2006 Procedings of the British Machine Vision Conference 2006  
We present an approach using Gaussian mixture models for part-based object recognition where spatial relationships of the parts are explicitly modeled and parameters of the generative model are tuned discriminatively. These extensions lead to great improvements of the classification accuracy. Furthermore we evaluate several improvements over our baseline system which incrementally improve the obtained results which compare favorable well to other published results for the three Caltech tasks and the PASCAL evaluation 05 tasks.
doi:10.5244/c.20.54 dblp:conf/bmvc/HegerathDN06 fatcat:dpvurruosfdchh2odroa4ot5f4