O'Sullivan, Andrew and Keyes, Laura and Winstanley, Adam C. (2006) An extended system for labeling graphical documents using statistical language models. In: Graphics Recognition. Ten Years Review and Future Perspectives. Lecture Notes in Computer Science (LNCS) (3926). Springer, pp. 61-75. ISBN 9783540347118

Preview

Download (238kB) | Preview

Abstract

This paper describes a proposed extended system for the recognition and labeling of graphical objects within architectural and engineering documents that integrates Statistical Language Models (SLMs) with shape classifiers. Traditionally used for Natural Language Processing, SLMS have been successful in such fields as Speech Recognition and Information Retrieval. There exist similarities between natural language and technical graphical data that suggest that adapting SLMs for use with graphical data is a worthwhile approach. Statistical Graphical Language Models (SGLMs) are applied to graphical documents based on associations between different classes of shape in a drawing to automate the structuring and labeling of graphical data. The SGLMs are designed to be combined with other classifiers to improve their recognition performance. SGLMs perform best when the graphical domain being examined has an underlying semantic system, that is; graphical objects have not been placed randomly within the data. A system which combines a Shape Classifier with SGLMS is described.

Item Type:	Book Section
Additional Information:	Cite this paper as: O’Sullivan A., Keyes L., Winstanley A. (2006) An Extended System for Labeling Graphical Documents Using Statistical Language Models. In: Liu W., Lladós J. (eds) Graphics Recognition. Ten Years Review and Future Perspectives. GREC 2005. Lecture Notes in Computer Science, vol 3926. Springer, Berlin, Heidelberg
Keywords:	labeling; graphical documents; statistical language models; shape classifiers;
Academic Unit:	Faculty of Science and Engineering > Computer Science
Item ID:	8103
Identification Number:	https://doi.org/10.1007/11767978_6
Depositing User:	Dr. Adam Winstanley
Date Deposited:	30 Mar 2017 14:32
Publisher:	Springer
Refereed:	Yes
URI:	http://link.springer.com
Use Licence:	This item is available under a Creative Commons Attribution Non Commercial Share Alike Licence (CC BY-NC-SA). Details of this licence are available here

Repository Staff Only(login required)

Item control page

Downloads

Origin of downloads