Complex Handwritten Page Segmentation Using Contextual Models

Authors:
Stephane Nicolas;Thierry Paquet;Laurent Heutte
Affiliations:
Universite de Rouen UFR des Sciences et Techniques, Cedex, France;Universite de Rouen UFR des Sciences et Techniques, Cedex, France;Universite de Rouen UFR des Sciences et Techniques, Cedex, France
Venue:
DIAL '06 Proceedings of the Second International Conference on Document Image Analysis for Libraries
Year:
2006

Citing 0
Cited 4

Automatic scoring of short handwritten essays in reading comprehension tests

Artificial Intelligence
A method for combining complementary techniques for document image segmentation

Pattern Recognition
A method for combining complementary techniques for document image segmentation

Pattern Recognition
Automatic line and word segmentation applied to densely line-skewed historical handwritten document images

Integrated Computer-Aided Engineering

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we address the problem of segmenting complex handritten pages such as novelist drafts or authorial manuscripts. We propose to use stochastic and contextual models in order to cope with local spatial variability, and to take into account some prior knowledge about the global structure of the document image. The models we propose to use are Markov Random Field models. After a formal description of the theoretical framework of Markov Random Fields and the principles of image segmentation using such models, we describe the implementation of our model and the proposed segmentation method. Then we discuss the results obtained with this approach on the drafts of the French novelist Gustave Flaubert, for different segmentation tasks. In conclusion, an extension of this work towards the use of discrimative models is discused.