Search For:

Displaying 1-3 out of 3 total
FAIR: A Fast Algorithm for Document Image Restoration
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Thibault Lelore,Frederic Bouchara
Issue Date:August 2013
pp. 2039-2048
We present, in this paper, the FAIR algorithm: a fast algorithm for document image restoration. This algorithm has been submitted to different contests where it showed good performance in comparison to the state of the art. In addition, this method is scal...
 
Super-Resolved Binarization of Text Based on the FAIR Algorithm
Found in: Document Analysis and Recognition, International Conference on
By Thibault Lelore,Frédéric Bouchara
Issue Date:September 2011
pp. 839-843
In this paper, we present a novel approach for super-resolved binarization of document images acquired by low quality devices. The algorithm tries to compute the super resolution of the likelihood of text instead of the gray value of pixels. This method is...
 
Document Image Binarisation Using Markov Field Model
Found in: Document Analysis and Recognition, International Conference on
By Thibault Lelore, Frédéric Bouchara
Issue Date:July 2009
pp. 551-555
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 potentia...
 
 1