%0 Conference Paper %B Proc. SPIE Conference on Document Recognition and Retrieval X %D 2003 %T Content Features for Logical Document Labeling %A Liang,Jian %A David Doermann %X The use of content features extracted from recognized text is valuable in labeling logical elements in documents withoutrigid layout structure, like business letters. This paper discusses a model-based approach to combining content features with other geometrical and presentation features for logical labeling. Models are automatically initialized and adaptively improved using training samples. Satisfactory experimental results are presented. %B Proc. SPIE Conference on Document Recognition and Retrieval X %P 189 - 196 %8 2003/// %G eng