Please use this identifier to cite or link to this item: https://doi.org/10.1109/TIP.2010.2048971
Title: User-assisted ink-bleed reduction
Authors: Huang, Y.
Brown, M.S. 
Xu, D.
Keywords: Document imaging processing
Dual-layer markov random field (mrf)
Ink-bleed reduction
Issue Date: 2010
Source: Huang, Y., Brown, M.S., Xu, D. (2010). User-assisted ink-bleed reduction. IEEE Transactions on Image Processing 19 (10) : 2646-2658. ScholarBank@NUS Repository. https://doi.org/10.1109/TIP.2010.2048971
Abstract: This paper presents a novel user-assisted approach to reduce ink-bleed interference found in old manuscripts. The problem is addressed by first having the user provide simple examples of foreground ink, ink-bleed, and the manuscript's background. From this small amount of user-labeled data, likelihoods of each pixel being foreground, ink-bleed, or background are computed and used as the data costs of a dual-layer Markov random field (MRF) that simultaneously labels all pixels in both the front and back sides of the manuscript. This user-assisted approach produces better results than existing algorithms without the need for extensive parameter tuning or prior assumptions about the inkbleed intensity characteristics. Our overall application framework is discussed along with details of the features used in the data costs, a comparison between -nearest neighbor and support vector machine for likelihood estimation, the dual-layer MRF formulation with associated inter- and intra-layer costs, and a comparison of our approach against other ink-bleed reduction algorithms. © 2010 IEEE.
Source Title: IEEE Transactions on Image Processing
URI: http://scholarbank.nus.edu.sg/handle/10635/39694
ISSN: 10577149
DOI: 10.1109/TIP.2010.2048971
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

13
checked on Dec 5, 2017

WEB OF SCIENCETM
Citations

10
checked on Dec 5, 2017

Page view(s)

54
checked on Dec 11, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.