Skip Navigation
Lister Hill Center Logo  

Search Tips
About the Lister Hill Center
Innovative Research
Publications and Lectures
Training and Employment
LHNCBC: Document Abstract
Year: 2003Adobe Acrobat Reader
Download Free Adobe Acrobat Reader
LHNCBC-2003-017
Stochastic Language Model for Style-Directed Physical Layout
Kanungo T, Mao S
Analysis of Documents IEEE Transactions on Image Processing. 2003 May;12 (5)5:583-596.
Image segmentation is an important component of any document image analysis system. While many segmentation algorithms exist in the literature, very few i) allow users to specify the physical style, and ii) incorporate user-specified style information into the algorithm's objective function that is to be minimized. We describe a segmentation algorithm that models a document's physical structure as a hierarchical structure where each node describes a region of the document using a stochastic regular grammar. The exact form of the hierarchy and the stochastic language is specified by the user, while the probabilities associated with the transitions are estimated from groundtruth data. We demonstrate the segmentation algorithm on images of bilingual dictionaries.
PDF