Title :
Degraded Document Bleed-Through Removal
Author :
Rowley-Brooke, Roisin ; Kokaram, Anil
Author_Institution :
Dept. of Electron. & Electr. Eng., Trinity Coll., Dublin, Ireland
Abstract :
This paper presents a Bayesian approach for bleed-through reduction in degraded document images based on a simple linear degradation model. A variation of ICM optimisation is used whereby samples are drawn for the bleed-through reduced images, whilst the remaining variables are estimated via the mode of their conditional probabilities. The proposed method is tested on various samples of scanned manuscript images with different degrees of degradation, and the results show some convincing removal of bleed-through.
Keywords :
Bayes methods; document image processing; optimisation; Bayesian approach; ICM optimisation; bleed-through reduced images; conditional probability mode; degradation degrees; degraded document image bleed-through removal; linear degradation model; scanned manuscript images; variable estimation; Bayesian methods; Degradation; Estimation; Hidden Markov models; Image restoration; Interference; Noise; mobile mapping system; stereo camera calibration; wide field of view;
Conference_Titel :
Machine Vision and Image Processing Conference (IMVIP), 2011 Irish
Conference_Location :
Dublin
Print_ISBN :
978-1-4673-0230-2
DOI :
10.1109/IMVIP.2011.21
