PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Deformation-aware Log-Linear Models
Tobias Gass, Thomas Deselaers and Hermann Ney
In: DAGM 2009, 9-11 Sep 2009, Jena, Germany.


In this paper, we present a novel deformation-aware discriminative model for handwritten digit recognition. Unlike previous approaches our model directly considers image deformations and allows discriminative training of all parameters, including those accounting for non-linear transformations of the image. This is achieved by extending a log-linear framework to incorporate a latent deformation variable. The resulting model has an order of magnitude less parameters than competing approaches to handling image deformations. We tune and evaluate our approach on the USPS task and show its generalization capabilities by applying the tuned model to the MNIST task. We gain interesting insights and achieve highly competitive results on both tasks.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Learning/Statistics & Optimisation
ID Code:5469
Deposited By:Thomas Deselaers
Deposited On:27 September 2009