Text/non-text classification in online handwritten documents with conditional random fields

Abstract

In this work, we present a new method for discriminating textual from non-textual ink strokes in unconstrained handwritten online documents. A Conditional Random Field is utilized for jointly modeling several sources of information (local, spatial, temporal) that contribute to improve the classification accuracy at the stroke level. Experiments over the publicly available IAM-OnDo database validate the approach with an overall recognition rate of more than 96%, and highlight the contributions of the different sources of contextual information. © 2012 Springer-Verlag.