File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/CVPR.2008.4587820
- Scopus: eid_2-s2.0-51949087732
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: A framework for reducing ink-bleed in old documents
Title | A framework for reducing ink-bleed in old documents |
---|---|
Authors | |
Issue Date | 2008 |
Citation | 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2008, article no. 4587820 How to Cite? |
Abstract | We describe a novel application framework to reduce the effects of ink-bleed in old documents. This task is treated as a classification problem where training-data is used to compute per-pixel likelihoods for use in a dual-layer Markov Random Field (MRF) that simultaneously labels image pixels of the front and back of a document as either foreground, background, or ink-bleed, while maintaining the integrity of foreground strokes. Our approach obtains better results than previous work without the need for assumptions about ink-bleed intensities or extensive parameter tuning. Our overall framework is detailed, including front and back image alignment, training-data collection, and the MRF formulation with associated likelihoods and intra- and inter-layer cost computations. ©2008 IEEE. |
Persistent Identifier | http://hdl.handle.net/10722/321352 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Huang, Yi | - |
dc.contributor.author | Brown, Michael S. | - |
dc.contributor.author | Xu, Dong | - |
dc.date.accessioned | 2022-11-03T02:18:20Z | - |
dc.date.available | 2022-11-03T02:18:20Z | - |
dc.date.issued | 2008 | - |
dc.identifier.citation | 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2008, article no. 4587820 | - |
dc.identifier.uri | http://hdl.handle.net/10722/321352 | - |
dc.description.abstract | We describe a novel application framework to reduce the effects of ink-bleed in old documents. This task is treated as a classification problem where training-data is used to compute per-pixel likelihoods for use in a dual-layer Markov Random Field (MRF) that simultaneously labels image pixels of the front and back of a document as either foreground, background, or ink-bleed, while maintaining the integrity of foreground strokes. Our approach obtains better results than previous work without the need for assumptions about ink-bleed intensities or extensive parameter tuning. Our overall framework is detailed, including front and back image alignment, training-data collection, and the MRF formulation with associated likelihoods and intra- and inter-layer cost computations. ©2008 IEEE. | - |
dc.language | eng | - |
dc.relation.ispartof | 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR | - |
dc.title | A framework for reducing ink-bleed in old documents | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/CVPR.2008.4587820 | - |
dc.identifier.scopus | eid_2-s2.0-51949087732 | - |
dc.identifier.spage | article no. 4587820 | - |
dc.identifier.epage | article no. 4587820 | - |