Text versus non-text distinction in online handwritten documents
Emanuel Indermühle, Horst Bunke, Faisal Shafait, Thomas Michael Breuel · 2010
The aim of this paper is to explore how well the task of text vs. non-text distinction can be solved in online handwritten documents us-ing only offline information. Two systems are introduced. The first system generates a document segmentation first. For this purpose, four methods originally developed for machine printed documents are compared: x-y cut, morphological closing, Voronoi segmen-tation, and whitespace analysis. A state-of-the art classifier then distinguishes between text and non-text zones. The second sys-tem follows a bottom-up approach that classifies connected com-ponents. Experiments are performed on a new dataset of online handwritten documents containing different content types in arbi-trary arrangements. The best system assigns 94.3 % of the pixels to the correct class.