A Shared Parts Model for Document Image Recognition

We address document image classification by visual ap- pearance. An image is represented by a variable-length list of visually salient features. A hierarchical Bayesian net- work is used to model the joint density of these features. This model promotes generalization from a few samples by sharing component probability distributions among differ- ent categories, and by factoring out a common displace- ment vector shared by all features within an image. The Bayesian network is implemented as a factor graph, and parameter estimation and inference are both done by loopy belief propagation. We explain and illustrate our model on a simple shape classification task. We obtain close to 90% accuracy on classifying journal articles from memos in the UWASH-II dataset, as well as on other classification tasks on a home-grown data set of technical articles.