Patch-based Object Recognition Using Discriminatively Trained Gaussian Mixtures | Zendy

Andre Hegerath | Zendy; Thomas Deselaers | Zendy; Hermann Ney | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

Patch-based Object Recognition Using Discriminatively Trained Gaussian Mixtures

Author(s) -

Andre Hegerath,

Thomas Deselaers,

Hermann Ney

Publication year - 2006

Publication title -

rwth publications (rwth aachen)

Language(s) - English

Resource type - Conference proceedings

DOI - 10.5244/c.20.54

Subject(s) - pascal (unit) , computer science , artificial intelligence , gaussian , pattern recognition (psychology) , object (grammar) , baseline (sea) , generative grammar , gaussian process , mixture model , generative model , cognitive neuroscience of visual object recognition , machine learning , physics , quantum mechanics , oceanography , programming language , geology

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.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research