Stochastic language models for style-directed layout analysis of document images

Authors:
T. Kanungo;Song Mao
Affiliations:
IBM Almaden Res. Center, San Jose, CA, USA;-
Venue:
IEEE Transactions on Image Processing
Year:
2003

Citing 0
Cited 3

Active Document Layout Synthesis

ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Model-Guided Segmentation and Layout Labelling of Document Images Using a Hierarchical Conditional Random Field

PReMI '09 Proceedings of the 3rd International Conference on Pattern Recognition and Machine Intelligence
Using grammars for pattern recognition in images: A systematic review

ACM Computing Surveys (CSUR)

Quantified Score

Hi-index	0.01

Visualization

Abstract

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.