Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

15

ICDAR
2009
IEEE

favoriteEmaildiscussreport

197views Document Analysis» more ICDAR 2009»

Document Image Binarisation Using Markov Field Model

13 years 2 months ago

Document Image Binarisation Using Markov Field Model

Download www.cvc.uab.es

This paper presents a new approach for the binarization of seriously degraded manuscript. We introduce a new technique based on a Markov Random Field (MRF) model of the document. Depending on the available information, the model parameters (clique potentials) are learned from training data or computed using heuristics. The observation model is estimated thanks to an expectationmaximization (EM) algorithm which extracts text and paper's features. The performance of the proposition is evaluated on several types of degraded document images where considerable background noise or variation in contrast and illumination exist.

Thibault Lelore, Frédéric Bouchara

Real-time Traffic

Considerable Background Noise | Document Analysis | ICDAR 2009 | Markov Random Field | Model |

claim paper

Related Content

» Overlapped text segmentation using Markov random field and aggregation

» A new stochastic image model based on Markov random fields and its application to texture ...

» Handwritten Word Recognition Using Conditional Random Fields

» MAPMRF approach for binarization of degraded document image

» Markov Random Field Modelling of fMRI Data Using a Mean Field EMalgorithm

» A Markovian Approach for Handwritten Document Segmentation

» Unsupervised Color Image Segmentation Using Compound Markov Random Field Model

» Linear intensitybased image registration by Markov random fields and discrete optimization

» A Revisit of Generative Model for Automatic Image Annotation using Markov Random Fields

Post Info
More Details (n/a)

Added	18 Feb 2011
Updated	18 Feb 2011
Type	Journal
Year	2009
Where	ICDAR
Authors	Thibault Lelore, Frédéric Bouchara

Comments (0)